Image processing apparatus, image processing method, and storage medium

Abstract

The invention provides an image processing apparatus, an image processing method, and a storage medium. The image processing apparatus includes: a scanning unit configured to scan an original image and generate image data; an accepting unit configured to accept a setting of a condition for generating a summary based on the image data; and a transmission unit configured to transmit the generated image data and information indicating the set condition, in which the summary generated based on the transmitted information is published to a channel of a chat service.

Description

Technical Field

[0001] The present disclosure relates to an image processing device, an image processing method, and a storage medium. Background Art

[0002] Japanese Patent Application Laid-Open No. 2021-078084 discusses an image processing device that transmits image data generated by scanning an original image to a chat server that provides a chat service.

[0003] According to Japanese Patent Application Laid-Open No. 2021-078084, scanned data can be uploaded to a chat room of a chat service. However, if the content of the uploaded file cannot be determined from the file name of the uploaded file, the file needs to be opened once to check its content, which may be time-consuming. Summary of the invention

[0004] The present disclosure is intended to enable easy inspection of the contents of a file when the file is uploaded to a chat service.

[0005] According to one aspect of the present disclosure, there is provided an image processing device, comprising: a scanning unit configured to scan an original image and generate image data; an accepting unit configured to accept the setting of a condition for generating a summary based on the image data; and a sending unit configured to send the generated image data and information indicating the set condition, wherein the summary generated based on the sent information is published to a channel of a chat service.

[0006] Further features of the present disclosure will become apparent from the following description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a diagram illustrating an example of a system configuration according to an exemplary embodiment of the present disclosure.

[0008] Figure 2 is a diagram showing an example of a hardware configuration of an image processing apparatus.

[0009] Figure 3 is a diagram showing an example of a hardware configuration of a mobile terminal.

[0010] Figure 4 is a diagram showing an example of a hardware configuration of a message application server.

[0011] Figure 5 is a diagram showing an example of a hardware configuration of a character recognition server.

[0012] Figure 6 is a diagram showing an example of the hardware configuration of a large language model server.

[0013] Figure 7 : is a diagram showing an example of a main screen displayed on the operation unit of the image processing apparatus.

[0014] Figure 8 is a diagram showing an example of a sequence in which an image processing apparatus transmits a file and a thumbnail image generated by scanning to a message application server.

[0015] Fig. 9 is a flowchart illustrating an example of a process in which an image processing apparatus transmits a file and a thumbnail image generated by scanning to a message application server.

[0016] FIG. 10A to FIG. 10D is a diagram showing an example of a screen of the Scan to Chat function according to the first exemplary embodiment.

[0017] Fig.11 is a diagram showing an example of a setting registration screen.

[0018] Fig.12 is a diagram showing an example of a message screen of a message application according to the first exemplary embodiment.

[0019] Fig.13 is a diagram illustrating an example of a sequence in which an image processing apparatus transmits a file generated by scanning and a character string extracted by optical character recognition (OCR) to a message application server.

[0020] Fig.14 : is a flowchart showing an example of a process in which an image processing apparatus transmits a file generated by scanning and a character string extracted by OCR to a message application server.

[0021] FIG. 15A to FIG. 15D is a diagram showing an example of a screen of the Scan to Chat function.

[0022] Fig.16 : is a diagram showing an example of a sequence in which the image processing apparatus transmits a document generated by scanning and a summary of a character string extracted by OCR to a message application server.

[0023] Fig.17 : is a flowchart showing an example of a process in which an image processing apparatus transmits a document generated by scanning and a summary of a character string extracted by OCR to a message application server.

[0024] 18A to 18E is a diagram showing an example of a screen of the Scan to Chat function.

[0025] Fig.19 is a diagram showing an example of a message screen of a message application. DETAILED DESCRIPTION

[0026] Exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings. The configurations described in the following exemplary embodiments are merely examples, and the present disclosure is not limited to the illustrated configurations.

[0027] A first exemplary embodiment of the present disclosure will be described below. Figure 1 1 is a diagram showing an example of a system configuration according to the present exemplary embodiment. The system configuration according to the present exemplary embodiment includes: a mobile terminal 300 as an example of a terminal device, and an image processing device (multi-function peripheral [MFP]) 101 and a message application server 400 that can communicate with the mobile terminal 300 via a network 100. The character recognition server 500 and the large language model server 600 are also connected via the network 100 and can communicate with each other. The message application server 400 receives messages and image data sent from the image processing device 101 and the mobile terminal 300. The message application server 400 is a chat server that manages a chat service for displaying received messages and image data on the mobile terminal 300 and a personal computer (PC) not shown. The character recognition server 500 is a server having a function of extracting characters from image data and converting image data into character data. The large language model server 600 is a server equipped with a language model that uses artificial intelligence to generate natural sentences in response to requests made in natural language. The network 100 according to the present exemplary embodiment may be the Internet or a local area network (LAN). The network 100 may be a wired network or a wireless network. The message application server 400 may directly receive the image data from the image processing apparatus 101. The cloud storage service may receive the image data from the image processing apparatus 101, and the message application server 400 may receive the image data from the cloud storage service.

[0028] Figure 2 2 is a diagram showing an example of a hardware configuration of the image processing apparatus 101. The image processing apparatus 101 includes a central processing unit (CPU) 202, a read-only memory (ROM) 203, a random access memory (RAM) 204, a memory 205, an operation unit interface (I / F) 206, an operation unit 207, a reading unit I / F 208, a reading unit 209, a printing unit I / F 210, a printing unit 211, a wireless communication unit I / F 212, and a wireless communication unit 213. The image processing apparatus 101 also includes a facsimile (FAX) unit I / F 214, a FAX communication unit 215, a communication unit I / F 216, and a communication unit 217.

[0029] The control unit 201 including the CPU 202 controls the operation of the entire image processing apparatus 101. The CPU 202 reads the control program stored in the ROM 203 or the memory 205 into the RAM 204, and performs various types of control such as read control and print control. The ROM 203 stores the control program executable by the CPU 202. The ROM 203 also stores the boot program and font data. The RAM 204 is a main storage memory, and is used as a work area and a temporary storage area for loading various control programs stored in the ROM 203 and the memory 205. The memory 205 stores image data, print data, various programs, and various types of setting information. In the present exemplary embodiment, it is assumed that a flash memory is used as the memory 205. However, an auxiliary storage device such as a solid state drive (SSD) and a hard disk drive (HDD) can be used. An embedded multimedia card (eMMC) can be used.

[0030] The image processing apparatus 101 according to the present exemplary embodiment is constructed so that a single CPU 202 uses a single memory (RAM 204) to perform various processes shown in the flowchart to be described below. However, this is not restrictive. For example, multiple CPUs, RAMs, ROMs, and memories may collaborate to perform the processes shown in the flowchart to be described below. Some processes may be performed using hardware circuits such as an application specific integrated circuit (ASIC) and a field programmable gate array (FPGA).

[0031] An operation unit I / F 206 connects an operation unit 207 including a display unit such as a touch screen and hardware keys with the control unit 201. The operation unit 207 displays information to the user and detects an input of the user.

[0032] The reading unit I / F 208 connects the reading unit 209 (such as a scanner) with the control unit 201. The reading unit 209 reads the document image, and the CPU 202 converts the image into image data such as binary data. The image data generated based on the image read by the reading unit 209 is sent to an external device or printed on a recording sheet. The reading unit 209 includes a conveying unit (such as an automatic document feeder (ADF)) not shown, and can convey a plurality of documents placed on the placing unit, and scan images of the plurality of documents based on a single scan execution instruction given by the user.

[0033] The printing unit I / F 210 connects a printing unit 211 such as a printer with the control unit 201. The CPU 202 transfers image data (print data) stored in the RAM 204 to the printing unit 211 via the printing unit I / F 210. The printing unit 211 prints an image based on the transferred image data on a recording sheet fed from a feed cassette.

[0034] The wireless communication unit I / F 212 is an I / F for controlling the wireless communication unit 213. The wireless communication unit I / F 212 wirelessly connects the control unit 201 with an external wireless device (here, the mobile terminal 300).

[0035] The control device 201 controls a FAX communication unit 215 (such as FAX) to connect to the public switched telephone network 107 by using a FAX unit I / F 214. The FAX unit I / F 214 is an I / F for controlling the FAX communication unit 215, and can connect to the public switched telephone network 107 and control the FAX communication protocol by controlling a FAX communication modem or a network control unit (NCU).

[0036] The communication unit I / F 216 connects the control unit 201 with the network 100. The communication unit I / F 216 sends the image data and various types of information inside the image processing device 101 to the external device on the network 100, and receives the print data and information on the network 100 from the information processing device on the network 100 via the communication unit 217. As a method of sending and receiving via the network 100, sending and receiving based on email or sending files using other protocols (such as file transfer protocol [FTP], server message block [SMB], and network distributed authoring and versioning [WebDAV]) can be performed. Image data and various types of setting data can also be sent and received on the network 100 through access using hypertext transfer protocol (HTTP) communication by the mobile terminal 300, the message application server 400, the character recognition server 500, and the large language model server 600.

[0037] Figure 3 is a diagram showing an example of a hardware configuration of the mobile terminal 300. In the present exemplary embodiment, it is assumed that a device such as a smartphone and a tablet PC is used as the mobile terminal 300. However, any other information processing apparatus capable of Wi-Fi communication may be used.

[0038] The CPU 307 reads a control program stored in the ROM 308 and performs various types of processing for controlling the operation of the mobile terminal 300. The ROM 308 stores the control program. The RAM 309 is used as a temporary storage area such as a main memory and a work area of ​​the CPU 307. The HDD 310 stores various types of data including pictures and electronic documents.

[0039] The operation panel 301 has a touch screen function capable of detecting a user's touch operation, and displays various screens provided by an operating system (OS) and an email sending application. The operation panel 301 is also used to communicate with the message application server 400 to perform information checking. The user can input a desired operation instruction to the mobile terminal 300 by inputting a touch operation to the operation panel 301. The mobile terminal 300 includes hardware keys not shown, and the user can input an operation instruction to the mobile terminal 300 using the hardware keys.

[0040] The camera 304 captures images based on the user's imaging instruction. The pictures captured by the camera 304 are stored in a predetermined area of ​​the HDD 310. Information can be obtained from a Quick Response (QR) code (registered trademark) read by the camera 304 using a program capable of performing QR code (registered trademark) analysis.

[0041] The mobile terminal 300 can communicate with the user through the near field communication (NFC) communication unit 305, The communication unit 306 and the wireless LAN communication unit 311 exchange data with various peripheral devices. The communication unit 306 may support Low energy consumption.

[0042] Figure 4 401. It is a diagram showing an example of the hardware configuration of the message application server 400. The CPU 401 reads the control program stored in the ROM 402 and performs various types of processing for controlling the operation of the message application server 400. The ROM 402 stores the control program. The RAM 403 is used as a temporary storage area such as a main memory and a work area of ​​the CPU 401. The HDD 405 stores various types of data such as messages, image data, and channel information. The message application server 400 can send and receive data with various devices such as the mobile terminal 300, the image processing device 101, the character recognition server 500, and the large language model server 600 via the communication unit 404. The communication unit 404 can use Ethernet (trademark) for wired communication, or can perform wireless communication such as Wi-Fi.

[0043] Figure 55 is a diagram showing an example of the hardware configuration of the character recognition server 500. The CPU 501 reads the control program stored in the ROM 502, controls the operation of the character recognition server 500, and converts the image data into character data in response to a request from the image processing device 101. The ROM 502 stores the control program. The RAM 503 is used as a temporary storage area such as a main memory and a work area of ​​the CPU 501. The HDD 505 stores various types of data such as messages, image data, and channel information. The character recognition server 500 can send and receive data with various devices such as the mobile terminal 300, the image processing device 101, and the message application server 400 via the communication unit 504.

[0044] Figure 6 6 is a diagram showing an example of a hardware configuration of the large language model server 600. The CPU 601 reads a control program stored in the ROM 602, controls the large language model server 600, and processes requests from the image processing apparatus 101, the mobile terminal 300, and the message application server 400. The ROM 602 stores the control program.

[0045] RAM 603 is used as a temporary storage area such as a main memory and a work area of ​​CPU 601. HDD 605 stores schedule information about each user. Large language model server 600 can transmit and receive data with various devices such as image processing apparatus 101, mobile terminal 300 and message application server 400 via communication unit 604.

[0046] Figure 7 7 is a diagram showing an example of a main screen displayed on the operation unit 207 of the image processing device 101. The operation unit 207 includes a touch screen 701 that displays an operation screen and light emitting diodes (LEDs) 710 and 711. The touch screen 701 is an instruction unit, and also serves as an acceptance unit for accepting instructions from a user, and a display unit for displaying a screen. The user directly touches the screen displayed on the touch screen 701 with a finger or an object such as a stylus pen, and gives instructions to execute various functions based on the displayed screen.

[0047] Figure 7 The touch screen 701 shown displays a home screen 708. The home screen 708 is an initial screen for giving instructions to execute various functions of the image processing apparatus 101. The home screen 708 is a screen for selecting a screen display to configure various settings of functions to be executed by the image processing apparatus 101, such as copy, FAX, scan, and media print functions.

[0048] A status check button 705 is an object for displaying a screen (status check screen) for checking the status of the image processing apparatus 101. The status check screen (not shown) can display a transmission history and a job execution history.

[0049] The Scan to Chat button 702 is an object for displaying a setting screen for Scan to Chat processing. If the user selects the Scan to Chat button 702, a Fig. 10A The scan to chat screen 1001 is shown. Figure 8 and Fig. 9 Describes the Scan to Chat process in detail.

[0050] The scan button 703 is an object for displaying a scan selection screen (not shown) by the image processing apparatus 101. The scan selection screen is a screen for selecting a sending function such as electronic mail sending (email), file sending using SMB, FTP or HTTP, and Internet FAX (I-FAX) sending. By touching a display object representing each sending function, a setting screen for the sending function is displayed.

[0051] The address book button 704 is an object for displaying the address book screen of the image processing apparatus 101 when selected by the user. The LED 710 and the LED 711 are used to notify the user of the state of the image processing apparatus 101. The LED 710 lights up during reception of an e-mail or during reception or execution of a print job. In the event of an error in the image processing apparatus 101, the LED 711 lights up. The stop button 706 is an object for canceling various operations. This object is continuously displayed on the operation unit 207. The main button 707 is an object for displaying the main screen 708. This object is continuously displayed on the operation unit 207. The menu button 712 is an object for displaying a screen for configuring environment settings (such as language settings) and various function settings.

[0052] Figure 8 is a diagram showing an example of a sequence in which the image processing apparatus 101 transmits a file and a thumbnail image generated by scanning to the message application server 400 .

[0053] In step S801, the CPU 202 of the image processing device 101 controls the communication unit 217 to request the channel information from the message application server 400 through HTTP communication. Specifically, the CPU 202 sends the token information input to the image processing device 101 and the information indicating the request for the channel information in the workspace indicated by the token information to the message application server 400. The image processing device 101 can accept the input of account information (such as a user identifier (ID) and password of a chat service), obtain the token information corresponding to the account information from the message application server 400, and send the token information. The user ID information (user ID) input to the image processing device 101 is sent to the message application server 400, and the information related to the user ID in the workspace can be identified. If the reading and writing of the user information in the workspace is authorized only to a single user, the password information (password) corresponding to the user ID information input to the image processing device 101 is further sent to the message application server 400 to obtain the authority.

[0054] An example of the command to be sent here is "HTTP GET https: / / message.com / api / conversations.list". The uniform resource locator (URL) "https: / / message.com / Api / conversations.list" included in the command is a URL for accessing the message application server 400. If the token information is sent to the URL, the message application server 400 searches for a channel associated with a workspace and a user corresponding to the token information. The user accesses the workspace via the display on the operation unit 207 of the image processing device 101. Fig.11 The setting registration screen 1101 enters token information.

[0055] As used herein, a workspace refers to an organization, etc., to which multiple users belong in a messaging application, and may be referred to as a team. A channel is synonymous with a chat room in a workspace. As used herein, a chat room is a mechanism for multiple participating users to send and receive messages to each other for conversational interaction. In this exemplary embodiment, a channel will be described as a chat room, but the mechanism for multiple users to send and receive messages for conversational interaction is not limited thereto. Examples may include group chats, rooms, chat rooms, and groups.

[0056] In step S802, the CPU 401 of the message application server 400 checks whether access to the URL is permitted based on the token information and the user ID received from the image processing apparatus 101 via the communication unit 404. If access is permitted, the CPU 401 returns the channel information included in the workspace corresponding to the token information to the image processing apparatus 101. The image processing apparatus 101 displays the received channel information on the operation unit 207.

[0057] In step S803, the CPU 202 waits for a channel finalization operation by the user. In step S804, the user finalizes the channel information.

[0058] In step S805, the CPU 202 of the image processing apparatus 101 accepts a scan execution instruction via the operation unit 207. In addition to selecting a channel to be posted (hereinafter referred to as a posting destination channel), the CPU 202 also accepts scan settings, send settings, and thumbnail settings from the user. This sequence relates to the case where the image is posted through the summary / character extraction / thumbnail setting screen 1030 (see Fig. 10D ) to select "Thumbnail" by clicking the Send Together button 1031 on the left.

[0059] In step S806 , the CPU 202 of the image processing apparatus 101 controls the reading unit 209 to scan the document image based on the scan setting set by the user.

[0060] In step S807, the CPU 202 of the image processing apparatus 101 generates an image file of the scanned image in the format set by the scan setting. The scan setting is specified by the user on the Scan to Chat detailed setting screen not shown. The scan setting can be displayed and set together with the send setting. Fig. 10B On the sending setting screen 1010.

[0061] In step S808 , the CPU 202 of the image processing apparatus 101 generates a thumbnail image based on the scanned data. The thumbnail image is generated in the format and resolution set on the summary / character extraction / thumbnail setting screen 1030 .

[0062] In step S809, the CPU 202 of the image processing device 101 transmits the same token information as in step S801, information about the publishing destination channel selected in step S804, and the image file generated in step S807 to the message application server 400 via the communication unit 217. In step S809, the CPU 202 also transmits the thumbnail image generated in step S808 by HTTP communication. An example of the command transmitted here is "HTTP POST https: / / message.com / api / files.upload". The file format specified by the user on the Scan to Chat transmission setting screen 1010 is used here.

[0063] In step S810, the CPU 401 of the message application server 400 searches for the workspace information registered using the token information received in step S809, and stores the received image file and thumbnail image in association with the channel specified by the channel information. Therefore, when the user starts the message application on the mobile terminal 300 and selects the publishing destination channel, a screen for publishing the image file and thumbnail image sent from the image processing device 101 appears. The sent image file and thumbnail image are stored in a folder corresponding to the channel selected in step S804. The folder is a folder managed on the chat service and is also a folder on the cloud storage service associated with the chat service.

[0064] In step S811, the CPU 401 of the message application server 400 sends a result corresponding to whether the message is successfully published as response information to the image processing apparatus 101 through HTTP communication. If the publication fails, the CPU 202 of the image processing apparatus 101 may display a notification of the failure of publication on the operation unit 207. If the publication succeeds, the CPU 202 of the image processing apparatus 101 may also display a notification of the success of publication on the operation unit 207.

[0065] Fig. 9 2 is a flowchart showing an example of the scan-to-chat process performed by the image processing apparatus 101. The process is performed by the CPU 202 reading a program stored in the ROM 203 into the RAM 204 and executing the program. Fig. 9 Processing of the flowchart in .

[0066] In step S901 , the CPU 202 detects that the Scan to Chat button 702 is selected. In step S902 , the CPU 202 displays the Scan to Chat screen 1001 on the touch screen 701 of the operation unit 207 .

[0067] Now refer to Fig. 10A The screen displayed when the Scan to Chat button 702 is selected is described.

[0068] Fig. 10A An example of a Scan to Chat screen displayed on the operation unit 207 is shown. A Scan to Chat screen 1001 is displayed on the touch screen 701 in response to selection of a Scan to Chat button 702 displayed on the home screen 708 .

[0069] If the reset button 1005 is selected on the Scan to Chat screen 1001, the information being set is cleared. Here, the channel information, user information, and summary / character extraction / thumbnail settings being set are cleared.

[0070] If the monochrome start button 1006 or the color start button 1007 is selected on the scan to chat screen 1001, the scan to send process starts.

[0071] Fig. 10B An example of a transmission setting screen displayed on the operation unit 207 is shown.

[0072] When the send setting button 1002 is selected on the scan to chat screen 1001, the send setting screen 1010 is displayed. The read size, file format, message, and file name can be set on this screen. For example, the user can select a file format from the file format candidates by selecting the file format button 1011. The user can freely input the message and file name using the software keyboard.

[0073] Fig. 10C An example of a channel setting screen displayed on the operation unit 207 is shown.

[0074] When the channel setting button 1003 is selected on the scan to chat screen 1001, the channel setting screen 1020 is displayed. The channel setting screen 1020 displays the channel based on the channel information received by the image processing device 101 from the message application server 400. The publishing destination channel and the mentioned user can be set on this screen. If the channel button 1021 is selected, the selected channel is set as the publishing destination channel. The channel setting screen 1020 can be configured so that more than one channel can be selected. The user button 1022 is displayed based on the user participating in the channel corresponding to the channel button 1021. The mentioned user can be set by selecting the user button 1022.

[0075] If the return button 1023 is selected, the channel selection is stored, and the Scan to Chat screen 1001 is displayed on the operation unit 207 .

[0076] Fig. 10D An example of an outline / character extraction / thumbnail setting screen displayed on the operation unit 207 is shown.

[0077] When the summary / character extraction / thumbnail setting button 1004 is selected on the Scan to Chat screen 1001 , the summary / character extraction / thumbnail setting screen 1030 is displayed.

[0078] If the send together button 1031 is selected, the content to be sent can be selected among the summary, the extracted character string, and the thumbnail. Fig. 10D Display is shown in the case where a thumbnail is sent together with an image file. The summary and the extracted character string will be described in the second exemplary embodiment and the third exemplary embodiment.

[0079] You can select "None" to not send any of these with the image file. You can combine multiple items.

[0080] If the format button 1032 in the thumbnail settings is selected, the format of the thumbnail image can be determined. Fig. 10D In the example of , the Joint Photographic Experts Group (JPEG) format is selected. The format is not limited to JPEG as long as the thumbnail of the format can be previewed on the message application server 400.

[0081] If the resolution button 1033 is selected, it is possible to select at which resolution the thumbnail image is to be generated. Fig. 10D In the example shown, the resolution is 720×480.

[0082] If the page number button 1034 is selected, the page number of the scanned document for which a thumbnail image is to be generated can be selected. Fig. 10D In the example, the settings generate a thumbnail image for the first page.

[0083] Although Fig. 10D The setting items of format, resolution, and page number are shown, but the settings related to the thumbnail image are not limited thereto. For example, an enlarged thumbnail of a portion of a page may be generated instead of the entire page. A plurality of thumbnails may be set according to circumstances. The scan result may be displayed on the operation unit 207 so that the user can select a portion to be cropped. The thumbnail image may be freely set without departing from the gist of the present disclosure.

[0084] Back to Fig. 9 Description of the flowchart.

[0085] In step S903, the CPU 202 detects that the channel setting button 1003 is selected. In step S904, the CPU 202 requests the message application server 400 for channel information through HTTP communication using pre-registered token information and user ID.

[0086] We will now describe Fig.11 The setting registration screen of Fig.11 11 is a diagram showing an example of a setting registration screen. The setting registration screen 1101 is a screen displayed on the operation unit 207 of the image processing apparatus 101. The setting registration screen 1101 can be displayed as a web page on the operation unit of an information processing apparatus such as a PC connected to the image processing apparatus 101 via the network 100. Content registered from the setting registration screen 1101 is stored in the memory 205.

[0087] A connection destination 1102 is a column indicating organizational information about the connection destination. A token information 1103 is a column indicating registered token information. An operation button 1104 is a column of operation buttons. An edit button 1105 and a generate button 1106 are displayed in this item.

[0088] If the edit button 1105 is selected, the character string of the token information and the connection destination information can be input or modified using the keyboard. If the generate button 1106 is selected, the scan to chat button 702 is set to be displayed on the main screen 708.

[0089] If the new registration button 1107 is selected, additional connection destination and token information can be registered by accepting a character string input by the user.

[0090] Back to Fig. 9 Description of the flowchart.

[0091] In step S905, the CPU 202 determines whether channel information is received from the message application server 400 in response to the channel information acquisition request sent in step S904. Specifically, if the status code included in the HTTP communication response indicates an error or the body information of the response includes a parameter indicating that the information is not available, the CPU 202 determines that the channel information is not received. If it is determined that the channel information is received ("Yes" in step S905), the process proceeds to step S906. Otherwise ("No" in step S905), the process proceeds to step S917.

[0092] In step S917, the CPU 202 displays information indicating that the channel information has not been successfully received on the channel setting screen 1020. Here, the channel setting screen 1020 does not display any channel options.

[0093] In step S918, the CPU 202 determines whether the return button 1023 is selected. If it is determined that the return button 1023 is selected (YES in step S918), the process returns to step S902. Otherwise (NO in step S918), the process returns to step S918.

[0094] In step S906 , the CPU 202 displays the channel setting screen 1020 , which displays the channel information received from the message application server 400 , on the touch screen 701 of the operation unit 207 .

[0095] In step S907 , the CPU 202 detects whether the channel and the user are finally determined by operating the channel setting screen 1020 via the touch screen 701 of the operation unit 207 .

[0096] If the channel and the user have been finally determined ("YES" in step S907), the process proceeds to step S908. Otherwise ("NO" in step S907), the process returns to step S907.

[0097] In step S908, the CPU 202 detects that the summary / character extraction / thumbnail setting button 1004 is pressed. In step S909, the CPU 202 displays the summary / character extraction / thumbnail setting screen 1030 on the operation unit 207.

[0098] In step S910, the CPU 202 detects whether the thumbnail setting is finalized by operating the summary / character extraction / thumbnail setting screen 1030 via the touch screen 701 of the operation unit 207. If the thumbnail setting has been finalized ("Yes" in step S910), the process proceeds to step S911. Otherwise ("No" in step S910), the process returns to step S910.

[0099] In step S911, if the monochrome start button 1006 or the color start button 1007 displayed on the operation unit 207 is selected, the CPU 202 reads the document image and generates image data by controlling the reading unit 209 based on the scan setting. The scan setting is specified by the user on the Scan to Chat detailed setting screen not shown.

[0100] In step S912 , the CPU 202 generates an image file by converting the image data generated in step S911 into the file format set using the file format button 1011 on the transmission setting screen 1010 .

[0101] In step S913 , the CPU 202 generates a thumbnail image based on the image data generated in step S911 and the format and resolution set on the summary / character extraction / thumbnail setting screen 1030 .

[0102] In step S914, the CPU 202 generates a posting parameter. The posting parameter includes information about a posting destination channel, a referring user, a file format, a file name, and a message. The file format is a format included in the send setting set using the file format button 1011. The file name is a file name specified by the send setting.

[0103] In step S915, the CPU 202 uses the pre-registered token information to send the image file generated in step S912 and the publishing parameters generated in step S914 to the message application server 400 through the HTTP communication POST method. When these data (conversion file of image data, thumbnail image and publishing parameters) are sent to the message application server 400, the message application server 400 publishes the image file and thumbnail image to the designated channel based on the received parameters. The message application server 400 publishes the image file and adds the information.

[0104] In step S916 , the CPU 202 displays the processing result of the message application server 400 on the touch screen 701 of the operation unit 207 .

[0105] In this way, the user can post the image file and its thumbnail image from the image processing apparatus 101 to a specific channel of the message application server 400 .

[0106] Fig.12 1 is a diagram showing an example of a message screen of a message application. The message application is started on the mobile terminal 300 and the image processing device 101 performs Fig. 9 After a series of processing shown in Fig.12 Here, the mobile terminal 300 is communicating with the message application server 400.

[0107] When the user launches the message application on the mobile terminal 300 and logs in by inputting the user's account ID and password, a user-specific screen is displayed.

[0108] Message 1202 is a chat message displayed when a user whose account is user 1 posts a message to channel 3. The user whose account is user 1 uses the user ID of user 1 and uses image processing device 101 to send the image file generated by scanning and the posting parameters to message application server 400 to display (post) message 1202. Fig.12 In the example of , the publishing parameters specify "channel 3" as the publishing channel, "user 3" as the mentioned user, "material.pdf" as the file name, and "this is the meeting material" as the message.

[0109] By performing the above process, material.pdf and a thumbnail image of material.pdf are published together like message 1202, so that the approximate content of material.pdf can be understood without opening the file.

[0110] A second exemplary embodiment of the present disclosure will be described below. In the first exemplary embodiment, it is described that a thumbnail image is attached to an image file. The second exemplary embodiment relates to an example in which optical character recognition (OCR) processing is performed to extract some sentences and the extracted character strings are sent together with the image file.

[0111] Fig.13 is a diagram showing an example of a sequence in which the image processing apparatus 101 extracts some sentences from an OCR result of a scanned document and transmits the extracted character strings together with the document to the message application server 400 .

[0112] The processing from step S801 to step S807 is the same as Figure 8 The processing in is similar. Therefore, its description will be omitted. Fig.13The example relates to a case where character extraction is selected by the send-together button 1031 on the summary / character extraction / thumbnail setting screen 1030 .

[0113] In step S1301, the CPU 202 of the image processing apparatus 101 transmits the image file generated in step S807 to the character recognition server 500 via the communication unit 217 or the wireless communication unit 213. Here, the CPU 202 may transmit the setting information about character extraction set on the outline / character extraction / thumbnail setting screen 1030 to the character recognition server 500. In this case, the character recognition server 500 performs character recognition based on the received setting information and edits the obtained character information as in step S1304.

[0114] In step S1302, the CPU 501 of the character recognition server 500 performs character recognition processing on the image represented by the image file and obtains character information.

[0115] In step S1303, the image processing apparatus 101 receives the obtained character information from the character recognition server 500. The information received here may be text data or document data in which the obtained character string is arranged based on the layout of the image in the image file.

[0116] In step S1304, the CPU 202 of the image processing apparatus 101 organizes the character information extracted from the data received in step S1303. This processing is performed based on the character extraction setting set on the overview / character extraction / thumbnail setting screen 1030. Examples include processing to crop only the first three lines of the first page, and processing to extract only keywords such as dates, names, and titles. If detailed designation is given at the stage of step S1301 and organization of the character information is not required, step S1304 can be skipped. Character information is generated by organizing the extracted character information.

[0117] In step S1305, the CPU 202 of the image processing apparatus 101 transmits the character information generated in step S1304 together with the image file generated in step S807 to the message application server 400 by HTTP communication via the communication unit 217. Here, channel information on the posting destination channel and the message are also transmitted.

[0118] The processing of step S810 and step S811 is the same as Figure 8 The processing in is similar. Therefore, its description will be omitted.

[0119] Although in Fig.132 , it is described that the character recognition server 500 performs OCR processing, but the CPU 202 of the image processing apparatus 101 may perform OCR processing and transmit character information in step S1305 using the result of the OCR processing.

[0120] Fig.14 2 is a flowchart showing an example of the scan-to-chat process of the image processing apparatus 101. The process is performed by the CPU 202 reading a program stored in the ROM 203 into the RAM 204 and executing the program. Fig.14 Flowchart of the process.

[0121] The processing from step S901 to step S909 is the same as Fig. 9 The processing in is similar. Therefore, the description thereof will be omitted. The present exemplary embodiment relates to an example in which character extraction is selected by the send-together button 1031 on the summary / character extraction / thumbnail setting screen 1030 displayed in step S909.

[0122] Now refer to Fig.15D The summary / character extraction / thumbnail setting screen 1030 is described.

[0123] Fig.15A An example of a Scan to Chat screen displayed on the operation unit 207 according to the second exemplary embodiment is shown. The display content is similar to that of the first exemplary embodiment. Therefore, a description thereof will be omitted.

[0124] Fig. 15B An example of a transmission setting screen displayed on the operation unit 207 according to the second exemplary embodiment is shown. The display content is similar to that of the first exemplary embodiment. Therefore, a description thereof will be omitted.

[0125] Fig. 15C An example of a channel setting screen displayed on the operation unit 207 according to the second exemplary embodiment is shown. The display content is similar to that of the first exemplary embodiment. Therefore, the description thereof will be omitted.

[0126] Fig.15D An example of an outline / character extraction / thumbnail setting screen displayed on the operation unit 207 according to the second exemplary embodiment is shown.

[0127] In the first exemplary embodiment, the description is made that "thumbnail" is selected by the send together button 1031, and the display thumbnail setting is described. In the second exemplary embodiment, character extraction is selected and a setting screen for character extraction is displayed.

[0128] If the character extraction position button 1501 in the character extraction setting is selected, it is possible to select which part of the image represented by the image file to perform OCR for character recognition and extraction from the options provided in advance. Fig.15D In the example, the setting is to extract characters in the first three lines. Other setting options may include extracting characters from the beginning to the tenth line, and extracting only important items such as dates, names, and titles.

[0129] If the maximum number of characters button 1502 is selected, the maximum number of characters can be set. Fig.15D In the example of , the maximum number of characters is set to 300. This setting is a function for preventing chat messages from being too long, and the maximum number of characters does not necessarily need to be limited. If the maximum number of characters button 1502 is selected, the user can freely enter the number of characters.

[0130] Although in Fig.15D , but the settings related to OCR are not limited thereto. For example, the language to be recognized in the OCR process can be set. The scanned image data can be set to be tilt-corrected before the OCR process. The image of the scanned image data can be displayed on the operation unit 207 so that the user can select the area for the OCR process.

[0131] Back to Fig.14 Description of the flowchart.

[0132] In step S1401, the CPU 202 detects whether the character extraction setting is finalized by operating the outline / character extraction / thumbnail setting screen 1030 via the touch screen 701 of the operation unit 207. If the character extraction setting is finalized ("Yes" in step S1401), the process proceeds to step S911. Otherwise ("No" in step S1401), the process returns to step S1401.

[0133] The processing of step S911 and step S912 is similar to that of the first exemplary embodiment, and therefore description thereof will be omitted.

[0134] In step S1402, the CPU 202 of the image processing device 101 sends the image file generated in step S912 to the character recognition server 500 via the communication unit 217 or the wireless communication unit 213, and requests the character recognition server 500 to extract character information from the image file. For example, if the area for OCR processing is set in advance, information about the area can be sent to the character recognition server 500, and the character recognition server 500 can perform OCR processing based on the received information about the area. In other words, OCR processing is performed only on the area indicated by the received area information in the image of the received image file. This can reduce the time of OCR processing.

[0135] In step S1403, the CPU 202 of the image processing apparatus 101 receives character information obtained by OCR processing of the character recognition server 500 via the communication unit 217 or the wireless communication unit 213. The character information received here may be text data or document data based on an image layout of an image file.

[0136] In step S914, CPU 202 generates a publishing parameter. For example, if the character extraction setting is set to the character extraction position "first three lines" and the maximum number of characters "300", the character information about the first three lines and within 300 characters is extracted (recognized) from the character information received in step S1403. If the character information about the first three lines exceeds 300 characters, character information up to 300 characters can be extracted. The character extraction position or the maximum number of characters can be set separately.

[0137] In addition to the aforementioned extracted character information, the publishing parameters also include information on the publishing destination channel, information indicating the mentioned user, and the message.

[0138] In step S915, the CPU 202 uses the pre-registered token information to send the image file generated in step S912 and the publishing parameters generated in step S914 to the message application server 400 through the HTTP communication POST method. When these data (the converted file of the image data and the publishing parameters) are sent to the message application server 400, the message application server 400 publishes the image file and the character string represented by the extracted character information to the designated channel based on the parameters. The publishing of the image file and the addition of the information are performed by the message application server 400. The processing of steps S916 to S918 is the same as that of the message application server 400. Fig. 9 The processing in is similar. Therefore, its description will be omitted.

[0139] In the present exemplary embodiment, the character recognition server 500 is described as being independent of the image processing device 101 and the message application server 400. However, this is not restrictive. For example, the CPU 202 of the image processing device 101 can perform a character recognition process (OCR process). The CPU 401 of the message application server 400 can perform a character recognition process (OCR process). If the CPU 401 of the message application server 400 performs a character recognition process, the image processing device 101 sends information indicating a character extraction setting to the message application server 400.

[0140] Then, the message application server 400 extracts the character information based on the received information indicating the character extraction setting. Then, the message application server 400 publishes the extracted character information and the image file received from the image processing apparatus 101 based on the received publishing parameters.

[0141] In this manner, the user can post the image file and character information obtained by performing a character recognition process on the image of the image file (character information extracted therein) to a specific channel of the message application server 400 .

[0142] The third exemplary embodiment of the present disclosure will be described below. In the first exemplary embodiment, it was described that thumbnail images are attached together. In the second exemplary embodiment, it was described that OCR processing is performed, and it is described that a part of the obtained character information is extracted and sent together with the image file. The third exemplary embodiment relates to an example in which a sentence is summarized using a large language model, and the summary is sent together with the image file.

[0143] Fig.16 is a diagram showing an example of a sequence in which the image processing apparatus 101 transmits a document generated by scanning to the message application server 400 together with a summary generated using a large language model.

[0144] Steps S801 to S807 are similar to those of the first exemplary embodiment, and therefore description thereof will be omitted. Fig.16 The example relates to a case where “summary” is selected by the send-together button 1031 on the summary / character extraction / thumbnail setting screen 1030 .

[0145] In step S1301, the CPU 202 of the image processing apparatus 101 transmits the image file generated in step S807 to the character recognition server 500 via the communication unit 217 or the wireless communication unit 213. Here, the setting information about character extraction set on the outline / character extraction / thumbnail setting screen 1030 may be transmitted to the character recognition server 500. In this case, the character recognition server 500 performs character recognition based on the received setting information and edits the obtained character information as in step S1304.

[0146] In step S1302, the CPU 501 of the character recognition server 500 performs character recognition processing on the image represented by the image file and obtains character information.

[0147] In step S1303, the image processing apparatus 101 receives the obtained character information from the character recognition server 500. The information received here may be text data or document data in which the obtained character string is arranged based on the layout of the image in the image file.

[0148] In step S1601, the CPU 202 of the image processing device 101 sends the data obtained in step S1303 to the large language model server 600 via the communication unit 217 or the wireless communication unit 213, and requests the large language model server 600 to summarize the sentence. The request sent here includes model information and message information. Model information is information indicating which language model to use. Message information includes items called roles (which specify whose message the message is), and items called content (which describe instructions that can be written in natural language). For example, by specifying "user" as a role, "summarize the following sentence in three lines" as content, and inputting sentence data, a three-line summary of the input sentence data in the form of a symbol list can be requested. The request sent here may include the character information (sentence data) obtained in step S1303 and information indicating summary conditions. The information indicating summary conditions may be instructions described in natural language. A request including information indicating summary conditions may be sent by specifying a URL of a network application programming interface (API). The large language model server 600 may have a character recognition function and perform processing similar to that of the character recognition server 500. In this case, the image processing apparatus 101 transmits the image file generated by scanning to the large language model server 600 .

[0149] In step S1602 , the large language model server 600 generates summary data based on the character information (sentence data) and the information indicating the summary condition received in step S1601 .

[0150] In step S1603, the image processing apparatus 101 receives the generated summary data from the large language model server 600. The response from the large language model server 600 includes "assistant" as a role, and embeds the summary result in the context.

[0151] In step S1604, the CPU 202 of the image processing apparatus 101 displays the character string represented by the summary data obtained in step S1603 on the operation unit 207, and asks the user whether the summary result is acceptable. If re-summarization is to be performed, the CPU 202 also accepts instructions on how to summarize.

[0152] If re-summarization is not required, in step S1605, the CPU 202 of the image processing apparatus 101 transmits the image file generated in step S807 and the received summary data to the message application server 400 via the communication unit 217 by HTTP communication. Here, the CPU 202 also transmits a message about the publishing destination channel and information. The processing of steps S810 and S811 is the same as that of steps S811. Figure 8 The processing in is similar. Therefore, its description will be omitted.

[0153] On the other hand, if re-summarization is to be performed as a result of step S1604, in step S1610, the CPU 202 of the image processing device 101 transmits an instruction for re-summarization to the large language model server 600 via the communication unit 217. The character information to be summarized has been transmitted and stored in the large language model server 600 in step S1601, but may be transmitted again in step S1610.

[0154] In step S1611 , the large language model server 600 generates summary data based on the character information and summary conditions received again. In step S1612 , the image processing apparatus 101 receives summary data from the large language model server 600 .

[0155] In step S1613, the CPU 202 of the image processing apparatus 101 displays the character string represented by the summary data obtained in step S1610 again on the operation unit 207, and asks the user whether the summary result is acceptable. The CPU 202 can repeat the re-summarization again by returning to step S1610 to make the summary result closer to the result expected by the user.

[0156] exist Fig.16 In FIG. 1 , it is described that the character recognition server 500 performs the OCR process, and it is described that the large language model server 600 performs the summarization process. However, the image processing apparatus 101 may perform the character recognition process and the summary data generation process.

[0157] Fig.172 is a flowchart showing an example of the scan-to-chat process of the image processing apparatus 101. The process is performed by the CPU 202 reading a program stored in the ROM 203 into the RAM 204 and executing the program. Fig.17 Processing of the flowchart in .

[0158] The processing from step S901 to step S909 is similar to Fig. 9 Therefore, the description thereof will be omitted. The present exemplary embodiment relates to an example in which “Summary” is selected by the send-together button 1031 on the summary / character extraction / thumbnail setting screen 1030 displayed in step S909.

[0159] Now refer to Fig.18D The summary / character extraction / thumbnail setting screen 1030 is described.

[0160] Fig.18A An example of a Scan to Chat screen displayed on the operation unit 207 according to the third exemplary embodiment is shown. The display content is similar to that of the first exemplary embodiment. Therefore, a description thereof will be omitted.

[0161] Fig.18B An example of a transmission setting screen displayed on the operation unit 207 according to the third exemplary embodiment is shown. The display content is similar to that of the first exemplary embodiment. Therefore, the description thereof will be omitted.

[0162] Fig.18C An example of a channel setting screen displayed on the operation unit 207 according to the third exemplary embodiment is shown. The display content is similar to that of the first exemplary embodiment. Therefore, the description thereof will be omitted.

[0163] Fig.18D An example of an outline / character extraction / thumbnail setting screen displayed on the operation unit 207 according to the third exemplary embodiment is shown.

[0164] In the second exemplary embodiment, it is described that character extraction is selected by the send together button 1031, and that character extraction settings are displayed. In the third exemplary embodiment, "Overview" is selected, and an overview setting screen is displayed.

[0165] If the summarization method button 1801 is selected, how to summarize the character data can be selected from the options provided in advance. Fig.18D In the example, a three-line summary is set. In addition to "Three-line summary", "Bullet list" and "Unspecified" can also be set. If "Bullet list" is set, the summary is generated in bullet list form. If "Unspecified" is set, the summary is generated in free form.

[0166] If the maximum number of characters button 1802 is selected, the number of characters of the summary to be generated can be selected. The image processing apparatus 101 can thus accept the condition of the number of characters of the summary. Fig.18D In the example of , the maximum number of characters is set to 300. As with the second exemplary embodiment, this setting is only a function to prevent the chat message from being too long, and the number of characters does not necessarily need to be limited.

[0167] If the summary translation button 1803 is selected, a request to translate the summary into a desired language may be issued. The translation may also assist the chat message recipient in understanding the content. For example, if the summary translation button 1803 is selected, a list of languages ​​such as Japanese, English, and Chinese is displayed. The operation unit 207 may accept the user's selection.

[0168] If the emphasis setting button 1804 is selected, a request is issued to summarize the character data with emphasis on dates and key points. Emphasis settings may include emphasis based on word selection, emphasis using symbols, and using heading-level expressions in a markup output format instead of plain text.

[0169] If the organization understanding button 1805 is selected to set the organization understanding function to ON, it can be set to obtain the organization information stored in the message application server 400, and generate a summary with polite sentences based on the relationship between the other party's position and the sender. The sender here refers to the user corresponding to the user ID sent in step S801. The other party refers to the user designated as the mentioned user. The other party may refer to a user participating in the publishing destination channel. In this case, if the participants of the publishing destination channel include at least one user with a higher position than the sender, a summary using honorifics is automatically generated. In this case, the image processing device 101 obtains the organization information from the message application server 400 and transmits the organization information to the large language model server 600. In order to obtain the organization information, the image processing device 101 communicates with the message application server 400 and obtains the organization information before step S1601, and then issues a summary instruction in step S1601.

[0170] If the wording learning button 1806 is selected to set the wording learning function to ON, the image processing apparatus 101 refers to the publishing destination channel and causes the large language model server 600 to learn the wording before issuing a request to generate a summary. This setting makes the publication of the expression closer to the usual conversation between the sender and the receiver than the setting based on the organization information. Similarly, in the case of wording learning, the image processing apparatus 101 communicates with the message application server 400 and obtains text information about the channel before step S1601, and then issues a summary instruction in step S1601.

[0171] Although an example of automatically adjusting the expression using the organization understanding button 1805 and the wording learning button 1806 has been described, this is not restrictive. For example, settings such as "honorific language" and "disable honorific language" can be accepted from the user on the summary / character extraction / thumbnail setting screen 1030, and a summary instruction can be issued based on the accepted settings.

[0172] If the free description button 1807 is selected, the user can freely input the summarization method using the software keyboard. If the summarization method is set using the free description button 1807, other setting items may be disabled.

[0173] Referenced Fig.18D Setting items such as summarization method, maximum number of characters, summary translation, emphasis setting, organizational understanding, wording learning, and free description are described. However, the settings related to the summary are not limited to this. Various items can be freely set without departing from the main points of the present disclosure.

[0174] Fig.18E An example of a summary result check screen 1800 displayed on the operation unit 207 according to the third exemplary embodiment is shown. After selecting the monochrome start button 1006 or the color start button 1007 to execute scanning and complete the summarization process, the summary result is displayed in the area 1810. The user observes the screen and checks the summary result generated by the large language model server 600.

[0175] The summary result check screen 1800 displays a yes button 1811 and a no button 1812. After re-summarization setting is performed by selecting a re-summarization setting button 1813, the no button 1812 becomes selectable. As in the case of the free description button 1807, if the re-summarization setting button 1813 is selected, a text input can be accepted using a keyboard. This enables the user to freely give instructions to the summarization method.

[0176] Back to Fig.17 In step S1701, the CPU 202 detects whether the summary setting is finalized by operating the summary / character extraction / thumbnail setting screen 1030 via the touch screen 701 of the operation unit 207. If the summary setting is finalized ("Yes" in step S1701), the process proceeds to step S911. Otherwise ("No" in step S1701), the process returns to step S1701.

[0177] The processing of step S911 and step S912 is similar to that of the first exemplary embodiment, and therefore description thereof will be omitted.

[0178] In step S1402, the CPU 202 of the image processing device 101 sends the image file generated in step S912 to the character recognition server 500 via the communication unit 217 or the wireless communication unit 213, and requests the character recognition server 500 to extract character information from the image file. For example, if the area for OCR processing is set in advance, information about the area can be sent to the character recognition server 500, and the character recognition server 500 can perform OCR processing based on the received information about the area. In other words, only the area indicated by the received area information in the image of the received image file is subjected to OCR processing. This can reduce the time of OCR processing.

[0179] In step S1403, the CPU 202 of the image processing apparatus 101 receives character information obtained by OCR processing of the character recognition server 500 via the communication unit 217 or the wireless communication unit 213. The character information received here may be text data or document data based on an image layout of an image file.

[0180] In step S1702, the CPU 202 of the image processing apparatus 101 transmits the character information received in step S1403 to the large language model server 600 via the communication unit 217 or the wireless communication unit 213, and requests the large language model server 600 to generate a summary. Here, the CPU 202 transmits the character information, the summary generation instruction, and the instruction in step S1403 to the large language model server 600. Fig.18D The information of the summary conditions set on the summary / character extraction / thumbnail setting screen 1030 is sent to the large language model server 600.

[0181] In step S1703 , the CPU 202 of the image processing device 101 receives the summary data generated by the large language model server 600 via the communication unit 217 or the wireless communication unit 213 .

[0182] In step S1704, the CPU 202 of the image processing apparatus 101 displays the summary represented by the summary data from the large language model server 600 on the operation unit 207, and inquires the user whether to perform re-summarization.

[0183] In step S1705, the CPU 202 of the image processing apparatus 101 determines whether the user requests re-summarization. If the user presses the No button 1812 to request re-summarization (YES in step S1705), the process proceeds to step S1706. On the other hand, if the user presses the Yes button 1811 (NO in step S1705), the process proceeds to step S914.

[0184] In step S1706, the CPU 202 of the image processing apparatus 101 accepts as an instruction the setting constructed using the re-summarization setting button 1813. The process returns to step S1702, and transmission of a summarization request to the large language model server 600 is restarted.

[0185] In step S914, the CPU 202 generates posting parameters. The posting parameters include the aforementioned summary data, as well as information on the posting destination channel, information indicating the mentioned user, and the message.

[0186] In step S915, the CPU 202 uses the pre-registered token information to send the image file generated in step S912 and the publishing parameters generated in step S914 to the message application server 400 through the HTTP communication POST method. When these data (the converted file of the image data and the publishing parameters) are sent to the message application server 400, the message application server 400 publishes the image file and the character string represented by the summary data to the specified channel based on the received parameters. The message application server 400 publishes the image file and adds the information. The processing of steps S916 to S918 is the same as that of the message application server 400. Fig. 9 The processing in is similar. Therefore, its description will be omitted.

[0187] In this way, the user can publish an image file together with a summary generated using a large language model from the image processing apparatus 101 to a specific channel of the messaging application server 400 .

[0188] In the third exemplary embodiment, it is described that the character recognition server 500 performs character recognition processing on the image data (image file) generated by scanning, and it is described that the large language model server 600 performs summary generation processing. However, this is not restrictive. The message application server 400 or other servers connected to the message application server 400 can perform character recognition processing on the image data generated by scanning. The summary generation processing can also be performed by the message application server 400 or other servers. In this case, the image processing device 101 sends the image data generated by scanning and the publishing parameters (including information indicating the summary conditions, summary instructions and information about the publishing destination information) to the message application server 400. The message application server 400 performs summary generation processing based on the information indicating the summary conditions included in the received publishing parameters. Alternatively, the message application server 400 can entrust the summary generation processing to other servers. In this case, the message application server 400 sends the information indicating the summary conditions to other servers related to the chat service. Note that the server related to the chat service includes multiple servers as follows, and the multiple servers include the message application server 400 and other servers. The message application server 400 publishes the generated summary and the received image data to the publishing destination channel specified by the publishing parameter. Even in the case where the message application server 400 performs character recognition processing and / or summary generation processing, the summary can be checked via the operation unit 207. To this end, the message application server 400 sends the generated summary data to the image processing device 101.

[0189] The generated image data and the publishing parameters including the profile conditions may be sent to other servers related to the chat service instead of the message application server 400, and the other servers may send the image data and the publishing parameters to the message application server 400. The same applies to the sending of the publishing parameters according to the first exemplary embodiment and the second exemplary embodiment. The above-mentioned other servers may be general servers not related to the chat service.

[0190] The message application server 400 publishes the image data and the summary in the same message, so that the image data corresponding to the published summary can be clearly seen. In other words, the received image data and the summary are published in association with each other.

[0191] Fig.19 1 is a diagram showing an example of a message screen of a message application. The message application is started on the mobile terminal 300 and the image processing device 101 performs Fig.17 After a series of processing, the display Fig.19 Message screen 1201.

[0192] When the user starts the message application on the mobile terminal 300 and logs in by inputting the user's account ID and password, a user-specific screen is displayed.

[0193] Message 1901 is a chat message displayed by a user whose account is user 1 posting a message to channel 3. In this exemplary embodiment, message 1901 is displayed (posted) by a user whose account is user 1 operating image processing apparatus 101 using user ID of user 1 and sending an image file generated by scanning and posting parameters to message application server 400.

[0194] exist Fig.19 In the example, the publishing parameters specify "channel 3" as the publishing channel, "user 3" as the mentioning user, and "materials.pdf" as the file name. Fig.17 , so a three-line summary based on "Materials.pdf" is included in the published notes.

[0195] like Fig.19 As shown, when material.pdf and the summary of material.pdf are published together, the contents of the document such as the decision made at the meeting and the date of the next meeting can be seen without opening material.pdf. In addition, past chat messages can be searched by using keywords in the summary results.

[0196] When uploading a file to a chat service, the contents of the file can be easily inspected.

[0197] Other embodiments

[0198] The embodiments of the present invention may also be implemented by reading and executing computer executable instructions (e.g., one or more programs) recorded on a storage medium (which may also be more completely referred to as a "non-transitory computer-readable storage medium") to perform one or more functions in the above-mentioned embodiments, and / or a computer of a system or device including one or more circuits (e.g., an application-specific integrated circuit (ASIC)) for performing one or more functions in the above-mentioned embodiments, and the embodiments of the present invention may be implemented by, for example, reading and executing the computer executable instructions from the storage medium by the computer of the system or device to perform one or more functions in the above-mentioned embodiments, and / or controlling the one or more circuits to perform one or more functions in the above-mentioned embodiments. The computer may include one or more processors (e.g., a central processing unit (CPU), a microprocessing unit (MPU)), and may include a network of separate computers or separate processors to read and execute the computer executable instructions. The computer executable instructions may be provided to the computer, for example, from a network or the storage medium. The storage medium may include, for example, a hard disk, a random access memory (RAM), a read-only memory (ROM), a memory of a distributed computing system, an optical disk (such as a compact disc (CD), a digital versatile disc (DVD), or a Blu-ray disc (BD) TM ), flash memory devices, memory cards, etc.

[0199] While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments.The scope of the following claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.

Claims

1. An image processing device, comprising: A scanning unit, which is used to scan an original image and generate image data; an accepting unit configured to accept setting of a condition for generating a summary based on the image data; as well as a transmitting section for transmitting the generated image data and information indicating the set conditions, The summary generated based on the sent information is published to a channel of the chat service.

2. The image processing device according to claim 1, wherein: The condition is related to the number of characters of the summary.

3. The image processing device according to claim 1, wherein: The conditions are related to the statements in the summary.

4. The image processing device according to claim 3, wherein: The transmission section is configured to transmit information indicating the set condition to a server related to the chat service.

5. The image processing device according to claim 1, further comprising: The receiving unit is configured to receive the summary from a server that has generated the summary based on the information transmitted by the transmitting unit.

6. The image processing device according to claim 5, further comprising: A display unit is used to display the received summary.

7. The image processing device according to claim 1, wherein: The image data and the information are transmitted by the transmitting unit, and the summary and the image data are published to the channel.

8. The image processing device according to claim 7, wherein: The summary and the image data are published to the channel in association with each other. 9 . The image processing apparatus according to claim 1 , further comprising a printing section.

10. An image processing method, comprising: Scanning an original image and generating image data; accepting setting of conditions for generating a summary based on the image data; as well as sending the generated image data and information indicating the set conditions, The summary generated based on the sent information is published to the channel of the chat service.

11. A non-transitory computer-readable storage medium storing a program for causing a computer to perform an image processing method, the image processing method comprising: Scanning an original image and generating image data; accepting setting of conditions for generating a summary based on the image data; as well as sending the generated image data and information indicating the set conditions, The summary generated based on the sent information is published to the channel of the chat service.

12. The storage medium according to claim 11, wherein: The condition is related to the number of characters of the summary.

13. The storage medium according to claim 11, wherein: The conditions are related to the statements in the summary.

14. The storage medium according to claim 13, wherein: Information indicating the set condition is sent to a server associated with the chat service.

15. The storage medium according to claim 11, wherein the image processing method further comprises: The summary is received from a server that has generated the summary based on the transmitted information. 16 . The storage medium of claim 15 , the image processing method further comprising displaying the received summary.

17. The storage medium according to claim 11, wherein: By sending the image data and the information, the summary and the image data are published to the channel.

18. The storage medium according to claim 17, wherein: The summary and the image data are published to the channel in association with each other.

Images