Data recognition method, device, electronic device and storage medium combining RPA and AI

Abstract

This application proposes a data recognition method, device, electronic device and storage medium combining RPA and AI, wherein the data recognition method includes: controlling the RPA robot to obtain the file to be recognized from the target folder; controlling the RPA robot to call the file recognition platform to recognize the file to be recognized to generate a recognition result; controlling the RPA robot to write the recognition result to the target file; controlling the RPA robot to provide the target file to the user. In this way, the automatic recognition of the file to be recognized can be realized, thereby saving labor costs and improving the accuracy and efficiency of data recognition.

Description

Technical Field

[0001] The present application relates to the field of RPA and AI technology, and to a data recognition method, device, electronic device and storage medium combining RPA and AI. Background Art

[0002] Robotic Process Automation (RPA) uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules.

[0003] Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0004] At present, in some enterprises, relevant business personnel need to organize operational information data at the beginning of each month, wherein the operational information data can all come from PDF (Portable Document Format) and pictures.

[0005] In the related technology, the collation (processing) of the operating information data can be done by manually identifying the operating information data with the naked eye and then copying them one by one into Excel. In order to speed up the copying speed, business personnel can go online to find free OCR (Optical Character Recognition) to recognize the operating information data through text recognition. However, this recognition requires business personnel to manually capture each page of the PDF image and recognize the text of each image separately. After the text is recognized, it is copied to a local Excel file, and the recognition results are manually reviewed. For the recognition errors, manual corrections are made. Summary of the invention

[0006] The present application aims to solve one of the technical problems in the above-mentioned technology at least to some extent.

[0007] To this end, the first purpose of this application is to propose a data recognition method that combines RPA and AI, which can realize automatic recognition of files to be identified, thereby saving labor costs and improving the accuracy and efficiency of data recognition.

[0008] The second objective of this application is to propose a data recognition device that combines RPA and AI.

[0009] The third objective of the present application is to provide an electronic device.

[0010] A fourth objective of the present application is to provide a computer-readable storage medium.

[0011] A fifth object of the present application is to provide a computer program product.

[0012] To achieve the above-mentioned objectives, the first aspect embodiment of the present application proposes a data recognition method combining RPA and AI, including: controlling the RPA robot to obtain the file to be recognized from the target folder; controlling the RPA robot to call the file recognition platform to recognize the file to be recognized to generate a recognition result; controlling the RPA robot to write the recognition result into the target file; and controlling the RPA robot to provide the target file to the user.

[0013] According to the data recognition method combining RPA and AI in the embodiment of the present application, the RPA robot is first controlled to obtain the file to be recognized from the target folder, and the RPA robot is controlled to call the file recognition platform to recognize the file to be recognized to generate a recognition result, and then the RPA robot is controlled to write the recognition result into the target file, and the RPA robot is controlled to provide the target file to the user. In this way, the automatic recognition of the file to be recognized can be realized, thereby saving labor costs and improving the accuracy and efficiency of data recognition.

[0014] In addition, the data recognition method combining RPA and AI proposed in the above embodiment of the present application may also have the following additional technical features:

[0015] In one embodiment of the present application, before controlling the RPA robot to obtain the file to be identified from the target folder, it includes: controlling the RPA robot to obtain the email title of the unread email through the OA email platform; if the email title meets the identification conditions, controlling the RPA robot to obtain the attachment in the unread email; controlling the RPA robot to use the attachment as the file to be identified, and placing the file to be identified in the target folder.

[0016] In one embodiment of the present application, the file recognition platform recognizes the file to be recognized through the following steps to generate the recognition result: if the file type of the file to be recognized is not the target type, the file type of the file to be recognized is converted to generate a target file to be recognized of the target type, wherein the target type is a picture type; the target file to be recognized is recognized to obtain text information and / or structural information in the target file to be recognized; and the recognition result is generated based on the text information and / or the structural information.

[0017] In one embodiment of the present application, controlling the RPA robot to write the recognition result into the target file includes: controlling the RPA robot to obtain the file name of the file to be recognized; controlling the RPA robot to use the file name as the file name of the target file; controlling the RPA robot to write the text information and / or the structural information into the target file.

[0018] In one embodiment of the present application, controlling the RPA robot to provide the target file to the user includes: controlling the RPA robot to send the target file to the user through the OA mail platform, or sending the target file to the user's communication client.

[0019] In one embodiment of the present application, the file recognition platform is a Mage platform, the Mage platform includes optical character recognition (OCR), and the target file includes one of an Excel file, a Word file, and a TXT file.

[0020] To achieve the above-mentioned objectives, the second aspect embodiment of the present application proposes a data recognition device combining RPA and AI, including: a first acquisition module, used to control the RPA robot to obtain the file to be recognized from the target folder; an identification module, used to control the RPA robot to call the file recognition platform to identify the file to be recognized to generate an identification result; a writing module, used to control the RPA robot to write the recognition result into the target file; and a providing module, used to control the RPA robot to provide the target file to the user.

[0021] The data recognition device combining RPA and AI in the embodiment of the present application first controls the RPA robot to obtain the file to be recognized from the target folder through the first acquisition module, then controls the RPA robot to call the file recognition platform to recognize the file to be recognized through the recognition module to generate the recognition result, and controls the RPA robot to write the recognition result to the target file through the writing module, and finally controls the RPA robot to provide the target file to the user through the providing module. In this way, the automatic recognition of the file to be recognized can be realized, thereby saving labor costs and improving the accuracy and efficiency of data recognition.

[0022] In addition, the data recognition device combining RPA and AI proposed in the above embodiment of the present application may also have the following additional technical features:

[0023] In one embodiment of the present application, the data recognition device combining RPA and AI also includes: a second acquisition module, used to control the RPA robot to obtain the email title of the unread email through the OA email platform; a third acquisition module, used to control the RPA robot to obtain the attachment in the unread email if the email title meets the recognition condition; a placement module, used to control the RPA robot to use the attachment as the file to be identified, and place the file to be identified in the target folder.

[0024] In one embodiment of the present application, the recognition module is specifically used to: if the file type of the file to be recognized is not the target type, perform file type conversion on the file to be recognized to generate a target file to be recognized of the target type, wherein the target type is a picture type; recognize the target file to be recognized to obtain text information and / or structural information in the target file to be recognized; and generate the recognition result based on the text information and / or the structural information.

[0025] In one embodiment of the present application, the writing module is specifically used to: control the RPA robot to obtain the file name of the file to be identified; control the RPA robot to use the file name as the file name of the target file; control the RPA robot to write the text information and / or the structural information into the target file.

[0026] In one embodiment of the present application, the providing module is specifically used to: control the RPA robot to send the target file to the user through the OA mail platform, or send the target file to the user's communication client.

[0027] In one embodiment of the present application, the file recognition platform is a Mage platform, the Mage platform includes optical character recognition (OCR), and the target file includes one of an Excel file, a Word file, and a TXT file.

[0028] To achieve the above-mentioned objectives, the third aspect embodiment of the present application proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the data recognition method combining RPA and AI as described in the first aspect embodiment of the present application.

[0029] The electronic device of the embodiment of the present application controls the RPA robot to obtain the file to be identified from the target folder through the processor executing the instructions stored in the memory; controls the RPA robot to call the file recognition platform to identify the file to be identified to generate the recognition result; controls the RPA robot to write the recognition result to the target file; controls the RPA robot to provide the target file to the user. In this way, the automatic recognition of the file to be identified can be realized, thereby saving labor costs and improving the accuracy and efficiency of data recognition.

[0030] To achieve the above-mentioned objectives, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the data recognition method combining RPA and AI as described in the first aspect embodiment of the present application.

[0031] The computer-readable storage medium of the embodiment of the present application, by storing a computer program and being executed by a processor, controls the RPA robot to obtain the file to be identified from the target folder, controls the RPA robot to call the file identification platform to identify the file to be identified to generate an identification result, controls the RPA robot to write the identification result to the target file, and then controls the RPA robot to provide the target file to the user. In this way, the automatic identification of the file to be identified can be achieved, thereby saving labor costs and improving the accuracy and efficiency of data identification.

[0032] To achieve the above-mentioned objectives, the fifth aspect embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the data recognition method combining RPA and AI as described in the first aspect embodiment of the present application.

[0033] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0035] Figure 1 This is a flowchart of a data recognition method combining RPA and AI according to an embodiment of the present application;

[0036] Figure 2 This is a flowchart of a data recognition method combining RPA and AI according to an embodiment of the present application;

[0037] Figure 3 This is a flowchart of a data recognition method combining RPA and AI according to an embodiment of the present application;

[0038] Figure 4 This is a flowchart of a data recognition method combining RPA and AI according to an embodiment of the present application;

[0039] Figure 5 This is a specific example flow chart of controlling an RPA robot to perform data recognition according to an embodiment of the present application;

[0040] Figure 6 A specific example flow chart according to an embodiment of the present application;

[0041] Figure 7 The present invention is a block diagram of a data recognition device combining RPA and AI according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0043] The following describes the data recognition method, device, electronic device and storage medium combining RPA and AI in an embodiment of the present application with reference to the accompanying drawings.

[0044] The data recognition method combining RPA and AI provided in the embodiment of the present application can be executed by an electronic device, which may be a PC (Personal Computer), a tablet computer, a PDA or a mobile phone, etc., without any limitation here.

[0045] In the embodiment of the present application, a processing component, a storage component and a drive component may be provided in the electronic device. Optionally, the drive component and the processing component may be integrated, the storage component may store an operating system, an application program or other program modules, and the processing component implements the data recognition method combining RPA and AI provided in the embodiment of the present application by executing the application program stored in the storage component.

[0046] Figure 1 The figure is a flowchart of a data recognition method combining RPA and AI according to an embodiment of the present application.

[0047] The data recognition method combining RPA and AI in the embodiment of the present application can also be executed by the data recognition device combining RPA and AI provided in the embodiment of the present application. The device can be configured in an electronic device to control the RPA robot to obtain the file to be recognized from the target folder, and control the RPA robot to call the file recognition platform to recognize the file to be recognized to generate a recognition result, and control the RPA robot to write the recognition result to the target file, and then control the RPA robot to provide the target file to the user, so as to realize the automatic recognition of the file to be recognized, thereby saving labor costs and improving the accuracy and efficiency of data recognition.

[0048] As a possible scenario, the data recognition method combining RPA and AI in an embodiment of the present application can also be executed on the server side. The server can be a cloud server, and the data recognition method combining RPA and AI can be executed in the cloud.

[0049] like Figure 1 As shown, the data recognition method combining RPA and AI may include:

[0050] S101, controlling the RPA robot to obtain the file to be identified from the target folder.

[0051] It should be noted that the file to be identified described in this embodiment may be an operation information data file, and the type of the operation information data file may include a PDF file type and a picture file type.

[0052] In an embodiment of the present application, before the electronic device controls the RPA machine to perform data recognition, the relevant staff (business personnel) may pre-establish the above-mentioned target folder in the storage space of the electronic device according to relevant needs. Among them, the target folder may contain files to be recognized (e.g., operating information data files) in advance, for example, by relevant staff or by the RPA robot, without any limitation here. It should be noted that the target folder described in this embodiment may be a folder known to the above-mentioned RPA robot.

[0053] Specifically, after starting the RPA robot, the electronic device can control the RPA robot to obtain the file to be identified from the above-mentioned target folder.

[0054] S102, control the RPA robot to call the file recognition platform to recognize the file to be recognized to generate a recognition result. The file recognition platform may be a Mage platform, and the Mage platform may include optical character recognition OCR (Optical Character Recognition). It should be noted that the optical character recognition OCR described in this embodiment can support the recognition of general tables.

[0055] Specifically, after obtaining the above-mentioned file to be recognized, the electronic device can control the RPA robot to call the Mage platform to recognize the file to be recognized through the optical character recognition OCR in the Mage platform, and generate a corresponding recognition result.

[0056] It should be noted that the Mage platform described in this embodiment can be installed in an electronic device or on a server that can communicate with the electronic device, and the server can be a cloud server. The RPA robot can call the Mage platform through the relevant API (Application Programming Interface) to use the optical character recognition OCR in the Mage platform to recognize the file to be recognized and generate corresponding recognition results.

[0057] In addition, the recognition result described in this embodiment may be data in JSON (JavaScript Object Notation) format.

[0058] S103, controlling the RPA robot to write the recognition result into the target file.

[0059] The target file may include one of an Excel file, a Word file and a TXT file.

[0060] In the embodiment of the present application, relevant personnel can create a target file in the file format of Excel file, Word file or TXT file according to actual needs, and can put the target file into a specified folder (for example, a result folder). It should be noted that the specified folder described in this embodiment can be a folder known by the above-mentioned RPA robot.

[0061] As a possible scenario, after controlling the RPA robot to generate the above recognition result, the electronic device may control the RPA robot to generate the above target file according to a preset file generation algorithm, wherein the preset file generation algorithm may be calibrated according to actual conditions.

[0062] In an embodiment of the present application, the RPA robot can be controlled to write the recognition result into the target file according to a preset writing strategy, wherein the preset writing strategy can be calibrated according to actual conditions.

[0063] Specifically, after controlling the RPA robot to generate the above-mentioned recognition result, the electronic device may first generate the above-mentioned target file according to a preset file generation algorithm, and then write the recognition result into the target file according to a preset writing strategy.

[0064] S104, controlling the RPA robot to provide the target file to the user.

[0065] Specifically, after writing the recognition result into the target file, the electronic device can control the RPA robot to send the target file to the user in a set manner. For example, the target file can be sent to the user by email, or directly to the user's communication client.

[0066] In the embodiment of the present application, the RPA robot is first controlled to obtain the file to be identified from the target folder, and the RPA robot is controlled to call the file identification platform to identify the file to be identified to generate an identification result, and then the RPA robot is controlled to write the identification result into the target file, and finally the RPA robot is controlled to provide the target file to the user. In this way, the automatic identification of the file to be identified can be realized, thereby saving labor costs and improving the accuracy and efficiency of data identification.

[0067] In order to clarify the above embodiment, in one embodiment of the present application, Figure 2 As shown in the figure, before controlling the RPA robot to obtain the file to be identified from the target folder, the following steps may be included:

[0068] S201, controlling the RPA robot to obtain the email titles of unread emails through the OA email platform.

[0069] In an embodiment of the present application, the RPA robot can be set to start at a scheduled time (for example, 8 a.m. every day). After startup, the electronic device can control the RPA robot to obtain the email titles of unread emails through the OA (Office Automation) email platform at preset time intervals (for example, one hour).

[0070] Specifically, after the RPA robot is started, the electronic device can control the RPA robot to start (call) the OA email platform, enter the account number and password to log in to the OA email platform, and then obtain the email titles of unread emails on the OA email platform.

[0071] It should be noted that the account and password described in this embodiment may be pre-stored in the RPA robot by relevant personnel so that they can be retrieved and used when needed.

[0072] S202: If the email title meets the identification condition, the RPA robot is controlled to obtain the attachments in the unread email.

[0073] In an embodiment of the present application, after controlling the RPA robot to obtain the above-mentioned email title, it can be determined whether the email title contains keywords (for example, OCR recognition file, file to be recognized, please perform file recognition or RPA_operation data, etc.) to determine whether the email corresponding to the email title is an email for optical character recognition OCR recognition request. If so, the email title meets the recognition conditions, and the electronic device can control the RPA robot to download the attachment in the email corresponding to the email title (that is, the above-mentioned unread email). It should be noted that the keywords described in this embodiment can be keywords known by the above-mentioned RPA robot, and can be calibrated according to actual conditions and needs, without any limitation here.

[0074] S203, controlling the RPA robot to treat the attachment as a file to be identified, and putting the file to be identified into a target folder.

[0075] Specifically, after controlling the RPA robot to obtain the above-mentioned email title, the electronic device can determine whether the email title meets the identification conditions through the judgment method in the above-mentioned embodiment. If so, the RPA robot can be controlled to download the attachment in the above-mentioned unread email, and the RPA robot can be controlled to treat the attachment as a file to be identified, and place the file to be identified in the target folder.

[0076] As a possible scenario, the above-mentioned attachment may be a compressed file (for example, a compressed package). After controlling the RPA robot to download the attachment, the electronic device may call a related decompression tool to decompress the attachment, and use the decompressed file as the file to be identified, and place the file to be identified in the target folder.

[0077] It should be noted that the decompression tool described in this embodiment can be pre-installed in the electronic device by relevant staff so that it can be retrieved and used when needed.

[0078] In this way, the files to be identified can be automatically acquired, the efficiency of acquiring the files to be identified can be improved, and the files to be identified can be stored locally without uploading them to the network, thereby ensuring data security.

[0079] In one embodiment of the present application, Figure 3 As shown, the file recognition platform can recognize the file to be recognized through the following steps to generate a recognition result:

[0080] S301: If the file type of the file to be identified is not a target type, convert the file type of the file to be identified to generate a target file to be identified of a target type, wherein the target type is a picture type.

[0081] In an embodiment of the present application, after the electronic device controls the RPA robot to call the file recognition platform, the file recognition platform can first determine whether the file type of the file to be recognized is a picture type. If not, the file type of the file to be recognized can be converted into a picture type through a file format conversion tool to generate a target file to be recognized for subsequent recognition.

[0082] It should be noted that the file format conversion tool described in this embodiment may be a plug-in pre-installed by relevant personnel in the above-mentioned file recognition platform so that it can be called up and used when needed, wherein the file format conversion tool may be a screenshot tool.

[0083] Specifically, when it is determined that the file type of the file to be identified is a non-image type, the file identification platform may call a file format conversion tool to convert the file type of the file to be identified into an image type to generate a target file to be identified.

[0084] For example, assuming that the file type of the file to be identified is a PDF file type, the file identification platform calls the file format conversion tool to screenshot the content of the PDF file according to the number of pages to generate multiple pictures corresponding to the number of pages of the PDF file, that is, to generate the target file to be identified.

[0085] S302: Identify the target file to be identified to obtain text information and / or structure information in the target file to be identified.

[0086] It should be noted that the structural information described in this embodiment may be table structural information, wherein the table structural information includes rows and columns.

[0087] S303: Generate a recognition result according to the text information and / or structure information.

[0088] Specifically, after generating the target file to be recognized, the file recognition platform can call its own optical character recognition (OCR) to recognize the target file to be recognized, obtain text information in the target recognition file, and then generate corresponding recognition results based on the text information.

[0089] As a possible situation, the file recognition platform calls its own optical character recognition (OCR) to recognize the target file to be recognized, obtains the structural information in the target recognition file, and then generates a corresponding recognition result according to the structural information.

[0090] As another possible situation, the file recognition platform may call its own optical character recognition (OCR) to recognize the target file to be recognized, and obtain the text information and structure information in the target recognition file, and then generate a corresponding recognition result based on the text information and structure information.

[0091] It should be noted that when the above-mentioned target file to be recognized contains only text information, the recognition result only contains text information; when the above-mentioned target file to be recognized contains only structural information, the recognition result only contains structural information; when the above-mentioned target file to be recognized contains text information and structural information, the recognition result contains text information and structural information.

[0092] In this way, non-target files to be identified can be converted into images for identification, thereby standardizing the data identification process and improving data identification efficiency.

[0093] In one embodiment of the present application, Figure 4 As shown, controlling the RPA robot to write the recognition results to the target file may include:

[0094] S401, controlling the RPA robot to obtain the file name of the file to be identified.

[0095] S402, controlling the RPA robot to use the file name as the file name of the target file.

[0096] S403, controlling the RPA robot to write text information and / or structure information into a target file.

[0097] Specifically, after the electronic device controls the RPA robot to call the file recognition platform to obtain the above recognition result, it can first control the RPA robot to obtain the file name of the file to be recognized, and name the target file with the file name, and write the text information and / or structure information into the target file according to the above preset writing strategy. In this way, the automatic naming of the target file and the automatic writing of the recognition result can be realized, thereby improving the efficiency of data sorting and optimizing the data sorting effect.

[0098] In one implementation of the present application, controlling the RPA robot to provide the target file to the user may include: controlling the RPA robot to send the target file to the user through the OA mail platform, or sending the target file to the user's communication client.

[0099] Specifically, after writing the recognition result into the above-mentioned target file, the electronic device can control the RPA robot to call the file compression tool to compress and package the target file, generate a compressed package of the target file, and then control the RPA robot to enter the user's email address on the OA email platform, and add the above-mentioned compressed package to the attachment and send it to the user via email.

[0100] It should be noted that the email address described in this embodiment may be the sender address of the email corresponding to the downloaded attachment. The RPA robot obtains the sender address while downloading the attachment and stores it in the RPA robot for easy retrieval and use when needed.

[0101] As a possible scenario, the electronic device can also control the RPA robot to log in to the communication client, for example, xx letter, and search for the user account. After finding the user account, the compressed package of the above target file is provided to the user through the communication client.

[0102] It should be noted that the user account described in this embodiment may be pre-stored in the RPA robot by relevant personnel so that it can be called up and used when needed.

[0103] In this way, the target file can be automatically sent to the user, which improves efficiency and user experience.

[0104] In the embodiment of the present application, during the whole process of the electronic device controlling the RPA robot to identify the file to be identified, the electronic device can monitor in real time through the relevant API whether the RPA robot has any abnormality. If so, the RPA robot can be controlled to initialize and the initialized RPA robot can be controlled to restart the identification of the file to be identified; if not, it means that the identification process of the file to be identified is normal, and a normal identification result can be obtained, and the RPA robot is controlled to continue working. In this way, it can avoid the situation where the identification work stops when the RPA robot has an abnormality, so that the file to be identified can be identified uninterruptedly, thereby improving the identification efficiency.

[0105] In order to make those skilled in the art understand this application more clearly, Figure 5 A specific example flow chart of controlling an RPA robot to perform data recognition according to the present application. Figure 5 As shown, controlling the RPA robot to perform data recognition may include the following steps:

[0106] S501, open the OA email platform.

[0107] S502, enter account password.

[0108] S503, log in.

[0109] S504, determine whether the login is successful. If yes, execute step S505; if not, execute step S501.

[0110] S505, entering unread emails, and determining whether the title of the unread emails meets the identification condition.

[0111] S506, downloading the attachments of the unread emails whose titles meet the identification condition.

[0112] S507, decompression.

[0113] S508, determine whether the file type is a picture type. If yes, execute step S510; if no, execute step S509.

[0114] S509, converting to picture type.

[0115] S510, identifying and generating a recognition result.

[0116] S511, write the target file.

[0117] S512, compress the target file.

[0118] S513, sending the compressed package to the user.

[0119] S514, determine whether an abnormality occurs. If yes, restart; if no, end.

[0120] Further, please refer to Figure 6 The specific example diagrams of this application are as follows: Figure 6 As shown, for the recognition of operational data, the process before automation is that the business personnel first checks the operational data file, uploads it to the cloud, recognizes it through cloud OCR, and then the business personnel move the recognition results, and finally review and modify the recognition results; the process after automation is that the business personnel first send the operational data file to the automated robot (RPA robot) through OA email, and then the automated robot downloads the attachment, calls OCR for recognition through the local Mage platform, and then writes the recognition results into the target file, and returns the target file through email or other means, and finally the business personnel review and modify it.

[0121] The data recognition method combining RPA and AI in the embodiment of the present application can be applied to data information recognition scenarios, such as the recognition of operational data information. Users can control the RPA robot through electronic devices such as PCs, tablets, PDAs or mobile phones to automatically acquire and recognize operational information data based on the data recognition method combining RPA and AI, and send the recognition results to the user.

[0122] Figure 7 The present invention is a block diagram of a data recognition device combining RPA and AI according to an embodiment of the present application.

[0123] The data recognition device combining RPA and AI in the embodiment of the present application can be configured in an electronic device to implement the data recognition method combining RPA and AI in the embodiment of the present application, and can also be executed by the data recognition device combining RPA and AI provided in the embodiment of the present application. The device can be configured in an electronic device to control the RPA robot to obtain the file to be recognized from the target folder, and control the RPA robot to call the file recognition platform to recognize the file to be recognized to generate a recognition result, and control the RPA robot to write the recognition result into the target file, and then control the RPA robot to provide the target file to the user, so as to realize the automatic recognition of the file to be recognized, thereby saving labor costs and improving the accuracy and efficiency of data recognition.

[0124] like Figure 7 As shown, the data recognition device 700 combining RPA and AI according to an embodiment of the present application may include: a first acquisition module 710, an identification module 720, a writing module 730 and a providing module 740.

[0125] Among them, the first acquisition module 710 is used to control the RPA robot to obtain the file to be identified from the target folder.

[0126] The recognition module 720 is used to control the RPA robot to call the file recognition platform to recognize the file to be recognized, so as to generate a recognition result.

[0127] The writing module 730 is used to control the RPA robot to write the recognition result into the target file.

[0128] The providing module 740 is used to control the RPA robot to provide the target file to the user.

[0129] In one embodiment of the present application, Figure 7 As shown, the data recognition device 700 combining RPA and AI according to an embodiment of the present application may also include: a second acquisition module 750 , a third acquisition module 760 and an insertion module 770 .

[0130] Among them, the second acquisition module 750 is used to control the RPA robot to obtain the email titles of unread emails through the OA email platform.

[0131] The third acquisition module 760 is used to control the RPA robot to obtain the attachments in the unread email if the email title meets the identification condition.

[0132] The insertion module 770 is used to control the RPA robot to treat the attachment as a file to be identified and put the file to be identified into a target folder.

[0133] In one embodiment of the present application, the recognition module 720 is specifically used to: if the file type of the file to be recognized is not the target type, convert the file type of the file to be recognized to generate a target file to be recognized of the target type, wherein the target type is a picture type; recognize the target file to be recognized to obtain text information and / or structural information in the target file to be recognized; and generate a recognition result based on the text information and / or structural information.

[0134] In one embodiment of the present application, the writing module 730 is specifically used to: control the RPA robot to obtain the file name of the file to be identified; control the RPA robot to use the file name as the file name of the target file; control the RPA robot to write text information and / or structural information into the target file.

[0135] In one embodiment of the present application, a module 740 is provided, which is specifically used to: control the RPA robot to send the target file to the user through the OA mail platform, or send the target file to the user's communication client.

[0136] In one embodiment of the present application, the file recognition platform is a Mage platform, the Mage platform includes optical character recognition OCR, and the target file includes one of an Excel file, a Word file, and a TXT file.

[0137] It should be noted that for details not disclosed in the data recognition device combining RPA and AI in the embodiment of the present application, please refer to the details disclosed in the data recognition method combining RPA and AI in the above embodiment of the present invention, which will not be repeated here.

[0138] In summary, the data recognition device combining RPA and AI in the embodiment of the present application first controls the RPA robot to obtain the file to be recognized from the target folder through the first acquisition module, and then controls the RPA robot to call the file recognition platform to recognize the file to be recognized through the recognition module to generate a recognition result, and controls the RPA robot to write the recognition result to the target file through the writing module, and finally controls the RPA robot to provide the target file to the user through the providing module. In this way, the automatic recognition of the file to be recognized can be realized, thereby saving labor costs and improving the accuracy and efficiency of data recognition.

[0139] In order to implement the above embodiments, the present application also proposes an electronic device, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above data recognition method combining RPA and AI.

[0140] The electronic device of the embodiment of the present application controls the RPA robot to obtain the file to be identified from the target folder through the processor executing the instructions stored in the memory; controls the RPA robot to call the file recognition platform to identify the file to be identified to generate the recognition result; controls the RPA robot to write the recognition result to the target file; and controls the RPA robot to provide the target file to the user. In this way, the automatic recognition of the file to be identified can be realized, thereby saving labor costs and improving the accuracy and efficiency of data recognition.

[0141] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above data recognition method combining RPA and AI.

[0142] The computer-readable storage medium of the embodiment of the present application, by storing a computer program and being executed by a processor, controls the RPA robot to obtain the file to be identified from the target folder; controls the RPA robot to call the file recognition platform to identify the file to be identified to generate a recognition result; controls the RPA robot to write the recognition result to the target file; and controls the RPA robot to provide the target file to the user. In this way, the automatic identification of the file to be identified can be realized, thereby saving labor costs and improving the accuracy and efficiency of data identification.

[0143] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the above data recognition method combining RPA and AI when executed by a processor.

[0144] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the above-mentioned processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0145] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0146] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0147] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the above-mentioned methods of various embodiments of the present application.

[0148] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0149] The above is a detailed introduction to a data recognition method, device and electronic device combining RPA and AI disclosed in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A data recognition method combining RPA and AI, characterized in that: During the whole process of controlling the RPA robot to identify the file to be identified, whether the RPA robot is abnormal is monitored in real time. If so, the RPA robot is controlled to be initialized, and the initialized RPA robot is controlled to re-identify the file to be identified. If not, the RPA robot is controlled to continue working. The data identification method includes: Control the RPA robot to start at a scheduled time, and after starting, control the RPA robot to obtain the email titles of unread emails through the OA email platform at preset time intervals; If the email title meets the identification condition, control the RPA robot to obtain the attachment in the unread email; Control the RPA robot to take the attachment as a file to be identified, and put the file to be identified into a target folder; Control the RPA robot to obtain the file to be identified from the target folder; Control the RPA robot to call the Mage platform to identify the file to be identified, so as to generate an identification result, wherein the Mage platform includes optical character recognition (OCR), and the optical character recognition (OCR) supports the identification of general forms; Controlling the RPA robot to write the recognition result into a target file; Control the RPA robot to send the target file to the user through the OA mail platform, or send the compressed package of the target file to the user's communication client.

2. The method according to claim 1, characterized in that: The Mage platform identifies the file to be identified through the following steps to generate the identification result: If the file type of the to-be-recognized file is not the target type, performing file type conversion on the to-be-recognized file to generate a target to-be-recognized file of the target type, wherein the target type is a picture type; Identify the target file to be identified to obtain text information and / or structure information in the target file to be identified; The recognition result is generated according to the text information and / or the structural information.

3. The method according to claim 2, characterized in that The controlling the RPA robot to write the recognition result into a target file includes: Control the RPA robot to obtain the file name of the file to be identified; Control the RPA robot to use the file name as the file name of the target file; Control the RPA robot to write the text information and / or the structure information into the target file.

4. The method according to any one of claims 1 to 3, characterized in that in, The target file includes one of an Excel file, a Word file and a TXT file.

5. A data recognition device combining RPA and AI, characterized in that: During the whole process of controlling the RPA robot to identify the file to be identified, the RPA robot is monitored in real time to see if an abnormality occurs. If so, the RPA robot is controlled to be initialized, and the initialized RPA robot is controlled to re-identify the file to be identified. If not, the RPA robot is controlled to continue working. The data identification device includes: The second acquisition module is used to control the RPA robot to obtain the email titles of unread emails through the OA email platform; A third acquisition module is used to control the RPA robot to obtain the attachment in the unread email if the email title meets the identification condition; An insert module, used to control the RPA robot to take the attachment as the file to be identified, and put the file to be identified into the target folder; A first acquisition module is used to control the RPA robot to acquire the file to be identified from the target folder; A recognition module, used to control the RPA robot to call the Mage platform to recognize the file to be recognized, so as to generate a recognition result, wherein the Mage platform includes optical character recognition (OCR), and the optical character recognition (OCR) supports recognition of general forms; A writing module, used to control the RPA robot to write the recognition result into a target file; A module is provided for controlling the RPA robot to send the target file to the user through the OA mail platform, or to send the compressed package of the target file to the user's communication client.

6. The device according to claim 5, characterized in that The identification module is specifically used for: If the file type of the to-be-recognized file is not the target type, performing file type conversion on the to-be-recognized file to generate a target to-be-recognized file of the target type, wherein the target type is a picture type; Identify the target file to be identified to obtain text information and / or structure information in the target file to be identified; The recognition result is generated according to the text information and / or the structural information.

7. The device according to claim 6, characterized in that The writing module is specifically used for: Control the RPA robot to obtain the file name of the file to be identified; Control the RPA robot to use the file name as the file name of the target file; Control the RPA robot to write the text information and / or the structure information into the target file.

8. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the data recognition method combining RPA and AI as described in any one of claims 1-4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the data recognition method combining RPA and AI as described in any one of claims 1 to 4 is implemented.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the data recognition method combining RPA and AI according to any one of claims 1 to 4.

Images