Electronic document processing methods, equipment, and storage media combining RPA and AI

Abstract

This application provides an electronic document processing method, device, and storage medium that combine RPA and AI. In some embodiments of this application, the electronic document to be delivered is automatically obtained from the electronic delivery system; text extraction is performed on the target electronic document in the electronic document to be delivered to obtain reference mailing information; the target mailing information is extracted from the mailing page in the electronic delivery system based on artificial intelligence (AI) technology; the target mailing information is compared with the reference mailing information to generate a target comparison result; and when the target comparison result is a passing result, the sending operation of the electronic document to be delivered is automatically executed based on artificial intelligence (AI) technology and RPA robots, thereby reducing labor costs and improving file transmission efficiency.

Description

Technical Field

[0001] The present application relates to the field of robotic process automation and artificial intelligence technology, and in particular to an electronic document processing method, device, and storage medium that combine 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] Currently, when courts mail various legal documents, they must manually log into the electronic delivery system and verify all pending electronic documents for the target case within a centrally printed list. For example, they must verify the completeness of all pending electronic documents for the target case and verify the mailing information is correct. Faced with a large number of cases, this requires manual processing of repetitive and tedious tasks, consuming significant labor costs and impacting document delivery efficiency. Summary of the Invention

[0005] This application embodiment provides an electronic document processing method, device, and storage medium that combine RPA and AI to address the low document delivery efficiency and high labor costs of related technologies. The technical solution is as follows:

[0006] In a first aspect, embodiments of the present application provide an electronic document processing method that combines RPA and AI, including:

[0007] Obtain electronic documents to be served from the electronic service system;

[0008] Extracting text from the target electronic file in the electronic files to be delivered to obtain reference mailing information;

[0009] extracting target mailing information from a mailing page in the electronic delivery system;

[0010] Comparing the target mailing information with the reference mailing information to generate a target comparison result;

[0011] If the target comparison result is a passing result, a sending operation is performed on the electronic file to be delivered.

[0012] In a second aspect, embodiments of the present application further provide an electronic document processing device that combines RPA and AI, the device comprising:

[0013] The file acquisition module is used to obtain the electronic files to be delivered from the electronic delivery system;

[0014] A text extraction module, configured to extract text from a target electronic file in the electronic files to be delivered to obtain reference mailing information;

[0015] An information extraction module, configured to extract target mailing information from a mailing page in the electronic delivery system;

[0016] A result generating module, configured to compare the target mailing information with the reference mailing information to generate a target comparison result;

[0017] The file sending module is used to execute a sending operation on the electronic file to be delivered if the target comparison result is a passing comparison result.

[0018] In a third aspect, embodiments of the present application provide an electronic device comprising: a memory and a processor. The memory and the processor communicate with each other via an internal connection path, the memory is configured to store instructions, and the processor is configured to execute the instructions stored in the memory. When the processor executes the instructions stored in the memory, the processor executes the method according to any one of the aforementioned embodiments.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a computer, the method in any one of the above-mentioned embodiments is executed.

[0020] The advantages or beneficial effects of the above technical solution include at least:

[0021] In some embodiments of the present application, the electronic file to be delivered is automatically obtained from the electronic delivery system; text extraction is performed on the target electronic file in the electronic file to be delivered to obtain benchmark mailing information; the target mailing information is extracted from the mailing page in the electronic delivery system based on artificial intelligence (AI) technology; the target mailing information is compared with the benchmark mailing information to generate a target comparison result; when the target comparison result is a passed comparison result, the sending operation is automatically performed on the electronic file to be delivered based on artificial intelligence (AI) technology and the RPA robot, thereby reducing labor costs and improving file transmission efficiency.

[0022] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present application will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0024] Figure 1 A schematic diagram of the structure of an electronic document processing system provided by an exemplary embodiment of the present application;

[0025] Figure 2 A schematic diagram of a process for delivering electronic documents provided in an exemplary embodiment of the present application;

[0026] Figure 3 A schematic diagram of a login page provided for an exemplary embodiment of the present application;

[0027] Figure 4a A schematic diagram of a copy of a complaint provided for an exemplary embodiment of the present application;

[0028] Figure 4b A schematic diagram of structured information of a complaint provided for an exemplary embodiment of the present application;

[0029] Figure 5 A schematic diagram of a mailing page provided for an exemplary embodiment of the present application;

[0030] Figure 6 A schematic diagram of a file operation record table provided for an exemplary embodiment of the present application;

[0031] Figure 7 A flowchart of an electronic document processing method combining RPA and AI provided in an exemplary embodiment of the present application;

[0032] Figure 8a A schematic structural diagram of an electronic document processing device 80 provided in an exemplary embodiment of the present application;

[0033] Figure 8b A schematic structural diagram of another electronic document processing device 80 provided in an exemplary embodiment of the present application;

[0034] Figure 8c A schematic structural diagram of another electronic document processing device 80 provided in an exemplary embodiment of the present application;

[0035] Figure 9 A schematic structural diagram of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0036] The following describes in detail embodiments of the present application. 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 only used to explain the present application and are not to be construed as limiting the present application.

[0037] In the description of the present application, the term "plurality" refers to two or more.

[0038] In the description of this application, the term "OCR" refers to Optical Character Recognition, which specifically refers to the process in which an electronic device examines characters printed on paper, determines their shapes by detecting dark and light patterns, and then translates the shapes into computer text using character recognition methods; that is, for printed characters, an optical method is used to convert the text in a paper document into a black and white dot matrix image file, and recognition software is used to convert the text in the image into text format for further editing and processing by word processing software.

[0039] These and other aspects of the embodiments of the present application will become apparent with reference to the following description and accompanying drawings. In these descriptions and accompanying drawings, some specific implementations of the embodiments of the present application are disclosed to illustrate some ways of implementing the principles of the embodiments of the present application, but it should be understood that the scope of the embodiments of the present application is not limited thereby. On the contrary, the embodiments of the present application include all changes, modifications and equivalents that fall within the spirit and scope of the appended claims.

[0040] The development requirements of the Five-Year Development Plan for the Informatization of the People's Courts state that in the new era, the informatization of the People's Courts must carefully analyze and accurately grasp the characteristics and patterns of the international and domestic situations, and with the courage to forge ahead wherever there are obstacles and build bridges across rivers, comprehensively deepen and implement national strategic deployments. As the national judicial organ, the People's Courts shoulder the task of safeguarding the last line of defense for fairness and justice in the strategy of comprehensively governing the country according to law. This responsibility is heavy and the mission is lofty. The People's Courts must seize opportunities and vigorously implement informatization construction, integrating advanced information technology into all aspects of the People's Courts' operations, processes, and processes, breaking through the bottlenecks of traditional methods, focusing on promoting the comprehensive rule of law and fully safeguarding long-term national stability. It is imperative to further advance the overall design of information systems and enhance the service capabilities of service platforms.

[0041] When the court mails various legal documents, it is necessary to manually log in to the electronic delivery system and manually check all the electronic documents to be delivered for the target case in the centralized printed page list. For example, it is necessary to check whether the types of electronic documents to be delivered for the target case are complete, and manually check whether the contact numbers and mailing addresses of the parties are correct. If the contact numbers and mailing addresses are incorrect, they need to be manually modified.

[0042] At present, when faced with a large number of cases, a large amount of repetitive and tedious tasks need to be handled manually, which consumes a lot of manpower costs and affects the efficiency of document delivery.

[0043] The following describes the technical solutions provided according to various embodiments of the present application in conjunction with the accompanying drawings.

[0044] Figure 1 FIG. 1 is a structural diagram of an electronic document processing system 10 provided by an exemplary embodiment of the present application. Figure 1 As shown, the electronic document processing system 10 includes a terminal device 10a and a server 10b, wherein a communication connection is established between the terminal device 10a and the server 10b. Figure 1 The terminal device 10a and server 10b presented are only exemplary and do not limit their implementation forms.

[0045] In this embodiment, the terminal device 10a and the server 10b can be connected via a wired or wireless connection. The terminal device 10a can establish a communication connection with the server 10b using a communication method such as WIFI, Bluetooth, infrared, or the like. Alternatively, the terminal device 10a can establish a communication connection with the server 10b via a mobile network. The mobile network can be any of 2G (GSM), 2.5G (GPRS), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G+ (LTE+), 5G, 5G-Advanced, WiMax, and the like.

[0046] In this embodiment, the type of the terminal device 10a is not limited, and the terminal device 10a includes but is not limited to any one of the following: a mobile phone, a personal desktop computer, a laptop computer, a tablet computer, a smart TV, and a smart speaker.

[0047] In this embodiment, the type of server 10b is not limited. For example, server 10b may be a conventional server, a cloud server, a cloud host, a virtual center, or other server device. Server 10b primarily comprises a processor, a hard drive, memory, a system bus, and other components, and utilizes a common computer architecture.

[0048] It's important to note that RPA (Robotic Process Automation) is an application that mimics the manual operations of end users on their computers, providing an alternative way to automate manual processes. RPA provides a comprehensive and professional process automation solution for businesses and individuals. Through a user interface, RPA robots intelligently understand existing enterprise applications and automate routine, rule-based operations, such as repetitively reading emails, accessing Office components, operating databases, web pages, and client software. They also collect data, perform complex calculations, generate large volumes of documents and reports, and complete tedious document checks. This can significantly reduce labor costs, effectively improve existing office efficiency, and complete tasks accurately, stably, and quickly.

[0049] NLP (Natural Language Processing) is a discipline that studies language issues in human-computer interaction. Based on the technical difficulty of implementation, these systems can be categorized into three types: simple matching, fuzzy matching, and paragraph comprehension.

[0050] The electronic service system is an application system used by judges to manage cases.

[0051] The electronic documents to be served include four types of electronic documents, including summons, copy of the complaint, litigation notice and notice of litigation rights and obligations; among them, the litigation notice includes notice of evidence and notice of response; the litigation rights and obligations notice includes litigation instructions and notice of evidence.

[0052] The base mailing information is the mailing information extracted from the target electronic file, including but not limited to: name, contact number and address.

[0053] The target mailing information is the mailing information corresponding to the base mailing information, and can be adjusted based on the base mailing information, including but not limited to: name, contact number and address.

[0054] In this embodiment, the RPA robot is integrated into the terminal device 10a.

[0055] In this embodiment, the RPA robot obtains the electronic file to be delivered from the electronic delivery system; the RPA robot extracts the text of the target electronic file in the electronic file to be delivered to obtain the reference mailing information; the RPA robot extracts the target mailing information from the mailing page in the electronic delivery system based on artificial intelligence (AI) technology; the RPA robot compares the target mailing information with the reference mailing information to generate a target comparison result; when the target comparison result is a passed comparison result, the artificial intelligence (AI) technology and the RPA robot automatically execute the sending operation on the electronic file to be delivered, thereby reducing labor costs and improving file transmission efficiency.

[0056] For example, Figure 2 A schematic diagram of a process for delivering an electronic file provided as an exemplary embodiment of the present application. Figure 3 A schematic diagram of a login page provided for an exemplary embodiment of this application. The RPA robot accesses the centralized delivery platform of the electronic delivery system, enters the case list, and downloads the electronic file to be delivered from the case list. The robot then sends a copy of the indictment and an image of the mailing page in the electronic file to be delivered to server 10b. Server 10b uses artificial intelligence (AI) technology to identify and extract information from the copy of the indictment and the mailing page image, obtaining reference mailing information and target mailing information, respectively. The RPA robot compares the target mailing information with the reference mailing information. If the target comparison result is a passing result, the robot sends the electronic file to be delivered. If the target comparison result is a failing result, the robot deletes the sending record.

[0057] Generally speaking, the electronic document to be served is a legal document associated with a case. The mailing information in the legal document is correct mailing information. However, the mailing information manually entered in the electronic delivery system may contain errors. Therefore, this application performs text extraction on the copy of the complaint in the electronic document to be served to obtain the correct reference mailing information. In this embodiment, terminal device 10a transmits an image of the copy of the complaint to server 10b. Server 10b performs text extraction on the copy of the complaint in the electronic document to be served to obtain the reference mailing information. Server 10b then transmits the reference mailing information to terminal device 10a.

[0058] For example, terminal device 10a sends the image of the copy of the indictment to server 10b. Server 10b performs optical character recognition (OCR) on the image of the copy of the indictment based on artificial intelligence (AI) technology to obtain the text information of the indictment; calls the natural language processing (NLP) service and extracts the benchmark mailing information from the text information of the indictment according to the preset first information extraction rule.

[0059] It should be noted that Figure 4a A schematic diagram of a copy of an indictment provided as an exemplary embodiment of the present application. Figure 4aAs shown, server 10b performs optical character recognition (OCR) processing on the copy image of the indictment based on artificial intelligence (AI) technology to obtain text information of the indictment. Figure 4b A schematic diagram of the structured information of a complaint provided by an exemplary embodiment of this application. Figure 4b As shown, server 10b calls the natural language processing (NLP) service and extracts structured information from the text information of the complaint according to preset file extraction rules; the structured information includes the document type, plaintiff, legal representative, address, contact number and defendant, etc.; and then extracts the benchmark mailing information from the structured information.

[0060] In the above embodiment, the RPA robot extracts the target mailing information from the mailing page in the electronic delivery system. One possible implementation involves issuing a page acquisition operation to obtain an image of the mailing page; performing optical character recognition (OCR) on the mailing page image using artificial intelligence (AI) technology to obtain the mailing information text; and then invoking a natural language processing (NLP) service to recognize the mailing information text to obtain the target mailing information.

[0061] In some embodiments of the present application, the RPA robot issues a page acquisition operation to obtain a mailing page image; the terminal device 10a sends the mailing page image to the server 10b, and the server 10b performs optical character recognition (OCR) processing on the mailing page image based on artificial intelligence (AI) technology to obtain the mailing information text; the server 10b calls a preset second information extraction rule to extract the target mailing information from the mailing information text; the server 10b returns the target mailing information to the terminal device 10a.

[0062] It should be noted that the embodiment of the present application does not limit the first information extraction rule and the second information extraction rule, and the first information extraction rule and the second information extraction rule can be adjusted according to actual conditions.

[0063] For example, Figure 5 A schematic diagram of a mailing page provided as an exemplary embodiment of the present application. Figure 5 As shown, the email page includes the party's name, ID number, party type, and address. Server 10b performs optical character recognition (OCR) on the mailing page image using artificial intelligence (AI) technology to obtain the mailing information text. Server 10b then invokes a preset second information extraction rule to extract the target mailing information from the mailing information text: the mailing address and contact number.

[0064] In this embodiment, after obtaining the target mailing information and the reference mailing information, the terminal device 10a compares the target mailing information with the reference mailing information to generate a comparison result. One implementation method is to call a natural language processing (NLP) service to compare each item of mailing information in the target mailing information with each item of mailing information in the reference mailing information, obtaining a comparison result for each item of mailing information in the target mailing information and each item of mailing information in the corresponding reference mailing information; and then generating a target comparison result based on the comparison result for each item of mailing information in the target mailing information and each item of mailing information in the corresponding reference mailing information. If the comparison results for each item of mailing information in the target mailing information and each item of mailing information in the corresponding reference mailing information are consistent, a comparison pass result is generated; if the comparison results for any item of mailing information in the target mailing information and each item of mailing information in the corresponding reference mailing information are inconsistent, a comparison fail result is generated.

[0065] In the above embodiment of the present application, the target mailing information includes a first document type, a first mailing address, and a first contact number, and correspondingly, the reference mailing information includes a second document type, a second mailing address, and a second contact number. Invoking a natural language processing (NLP) service to compare multiple pieces of mailing information in the target mailing information with multiple pieces of mailing information in the reference mailing information one by one, and obtaining a comparison result between each piece of mailing information in the target mailing information and each piece of mailing information in its corresponding reference mailing information, includes at least one of the following comparison operations:

[0066] Operation method 1: Call the natural language processing (NLP) service to determine whether the first mailing address and the second mailing address are consistent, and obtain a comparison result of whether the first mailing address and the second mailing address are consistent;

[0067] Operation method 2: Perform optical character recognition (OCR) on the electronic document to be served based on artificial intelligence (AI) technology to obtain the type of the electronic document to be served; determine whether the type of the electronic document to be served is complete, and obtain a comparison result to confirm whether the type of the electronic document to be served is complete;

[0068] Operation method three: calling the natural language processing (NLP) service to determine whether the first contact number and the second contact number are consistent, and obtaining a comparison result of whether the first contact number and the second contact number are consistent.

[0069] In the above embodiment, if the first mailing address and the second mailing address are consistent, the type of the electronic file to be delivered is complete, and the first contact number and the second contact number are consistent, a comparison pass result is generated; if at least one of the following conditions is met: the first mailing address and the second mailing address are inconsistent, the type of the electronic file to be delivered is incomplete, and the first contact number and the second contact number are inconsistent, a comparison fail result is generated.

[0070] It should be noted that, in the case that the mailing address and / or contact number in the target mailing information are inconsistent, you can try to correct the target mailing information, and after the correction is consistent with the benchmark mailing information, send the electronic file to be delivered. One feasible way is that if the target comparison result is a failed comparison result, the target mailing information is corrected to obtain a correction result; if the correction result is a successful correction, the sending operation is performed on the electronic file to be delivered; if the correction result is a failed correction, the historical audit log of the electronic file to be delivered is deleted. Among them, if the correction result is a successful correction, after the sending operation is performed on the electronic file to be delivered, the processing status of the case corresponding to the electronic file to be delivered is generated as a "successful processing" status; if the correction result is a failed correction, the processing status of the case corresponding to the electronic file to be delivered is generated as a "failed processing" status.

[0071] In other embodiments of the present application, if the target comparison result is a failed comparison result, it means that at least one of the first document type, the first contact number, and the first mailing address has failed the comparison. Accordingly, when the target comparison result is a failed comparison result, at least one of the following operations may be performed, but is not limited to:

[0072] If the target comparison result is a comparison failure result, and the mailing information that failed the comparison in the target mailing information is the first file type, a first file type correction failure result is generated;

[0073] If the target comparison result is a failed comparison result, and the mailing information in the target mailing information that failed the comparison is the first contact number, the first contact number is replaced with the second contact number in the reference mailing information, and a replacement result of the first contact number is generated;

[0074] If the target comparison result is a failed comparison result, and the mailing information that failed the comparison in the target mailing information is the first mailing address, then the correction type of the first mailing address is determined. If the correction type is an information missing type, then a formal completion operation is performed on the first mailing address. If the correction type is an information error type, then a modification operation is performed on the first mailing address based on the second mailing address in the benchmark mailing information.

[0075] In the above embodiment, if at least one operation results in a failed correction, a target correction result of "failed correction" is generated; if all operations result in successful correction, a target correction result of "successful correction" is generated. If the target correction result is successful correction, the send operation is performed on the electronic file to be delivered; if the target correction result is a failed correction, the historical audit log of the electronic file to be delivered is deleted.

[0076] In the above embodiment, if the target comparison result is a failed comparison result, and the mailing information that failed the comparison in the target mailing information is the first mailing address, the RPA robot determines the correction type of the first mailing address. If the correction type is an information missing type, the RPA robot performs a formal completion operation on the first mailing address. If the correction type is an information error type, the first mailing address is modified based on the second mailing address in the benchmark mailing information.

[0077] In some embodiments of the present application, a formal completion operation is performed on the first mailing address. For example, if the mailing address in the target mailing information lacks a province, the province is automatically completed after the province is identified based on the mailing address. If the target mailing information cannot be corrected, the historical audit log is deleted.

[0078] In some embodiments of the present application, the first mailing address is modified based on the second mailing address in the reference mailing information. For example, if the city name in the mailing address in the target mailing information is incorrect, the correct city name is extracted from the second mailing address and the incorrect city name is modified to the correct one. For example, if the address is located at ** Building, ** Street, Haidian District, Beijing, "Haidian" is modified to "Haidian".

[0079] In other embodiments of the present application, if the target mailing information cannot be modified, the historical audit log of the electronic file to be delivered is deleted. For example, if the mailing address in the target mailing information is "** Village", and there is too little mailing address information to complete or modify the mailing address, then the mailing address cannot be modified, and the historical audit log of the electronic file to be delivered is deleted.

[0080] In some embodiments of the present application, the number of corrections to each item of mailing information in the target mailing information is counted; if the number of corrections exceeds a set number, a target correction result indicating that the correction failed is generated. The embodiments of the present application do not limit the set number and can be adjusted based on actual conditions.

[0081] In this embodiment, a file operation record table is generated for the RPA robot based on the operation record of the RPA robot on the electronic files to be delivered of the case. Figure 6 This is a schematic diagram of a file operation record table provided by an exemplary embodiment of the present application. Figure 6 As shown, the case numbered 1234 has a successful status, while the case numbered 5678 has a failed status.

[0082] This embodiment combines RPA and AI technologies in a repair and forwarding mailing scenario. It automatically identifies party information in civil complaints, automatically matches and verifies the information in the electronic delivery system based on the case number, and batch-checks mailing information within a limited working time. It also generates and stores a file operation log. Compared to manual methods, this improves work efficiency and reduces labor costs.

[0083] In addition, every step of the automated processing is traceable, which allows system errors to be accurately discovered and easier to resolve once a problem occurs.

[0084] In the above-mentioned system embodiment of the present application, the electronic file to be delivered is automatically obtained from the electronic delivery system; text extraction is performed on the target electronic file in the electronic file to be delivered to obtain the reference mailing information; the target mailing information is extracted from the mailing page in the electronic delivery system based on artificial intelligence (AI) technology; the target mailing information is compared with the reference mailing information to generate a target comparison result; when the target comparison result is a passed comparison result, the sending operation is automatically performed on the electronic file to be delivered based on artificial intelligence (AI) technology and the RPA robot, thereby reducing labor costs and improving file transmission efficiency.

[0085] In addition to the electronic document processing system 10 provided above, some embodiments of the present application also provide an electronic document processing method combining RPA and AI. The electronic document processing method combining RPA and AI provided in this application can be applied to the electronic document processing system 10 described above, but is not limited to the electronic document processing system 10 provided in the above embodiments. Figure 7 The following is a flowchart of an electronic document processing method combining RPA and AI provided by an exemplary embodiment of the present application. Figure 7 As shown, the method includes:

[0086] S701: Obtain the electronic document to be delivered from the electronic delivery system;

[0087] S702: extracting text from the target electronic file in the electronic file to be delivered to obtain reference mailing information;

[0088] S703: extracting target mailing information from the mailing page in the electronic delivery system;

[0089] S704: Compare the target mailing information with the reference mailing information to generate a target comparison result; if the target comparison result is a passing result, execute step S705; if the target comparison result is a failing result, execute step S706;

[0090] S705: Execute the sending operation for the electronic file to be delivered;

[0091] S706: Modify the target mailing information.

[0092] In this embodiment, the execution subject of the above method is a terminal device, which includes but is not limited to any one of the following: a mobile phone, a personal desktop computer, a laptop computer, a tablet computer, a smart TV and a smart speaker.

[0093] Generally speaking, the electronic document to be served is a legal document associated with a case. The mailing information in the legal document is correct mailing information. However, the mailing information manually entered in the electronic service system may contain errors. Therefore, this application performs text extraction on the copy of the complaint in the electronic document to be served to obtain the correct reference mailing information. In this embodiment, the terminal device sends an image of the copy of the complaint to the server. The server performs text extraction on the copy of the complaint in the electronic document to be served to obtain the reference mailing information, and the server sends the reference mailing information to the terminal device.

[0094] For example, the terminal device sends the image of the copy of the indictment to the server. The server performs optical character recognition (OCR) on the image of the copy of the indictment based on artificial intelligence (AI) technology to obtain the text information of the indictment; the natural language processing (NLP) service is called to extract the benchmark mailing information from the text information of the indictment according to the preset first information extraction rules.

[0095] It should be noted that Figure 4a A schematic diagram of a copy of an indictment provided as an exemplary embodiment of the present application. Figure 4a As shown, server 10b performs optical character recognition (OCR) processing on the copy image of the indictment based on artificial intelligence (AI) technology to obtain text information of the indictment. Figure 4b A schematic diagram of the structured information of a complaint provided by an exemplary embodiment of this application. Figure 4b As shown, the server calls the natural language processing (NLP) service and extracts structured information from the text information of the complaint according to the preset file extraction rules; the structured information includes the document type, plaintiff, legal representative, address, contact number and defendant, etc.; and then extracts the baseline mailing information from the structured information.

[0096] In the above embodiment, the RPA robot extracts the target mailing information from the mailing page in the electronic delivery system. One possible implementation involves issuing a page acquisition operation to obtain an image of the mailing page; performing optical character recognition (OCR) on the mailing page image using artificial intelligence (AI) technology to obtain the mailing information text; and then invoking a natural language processing (NLP) service to recognize the mailing information text to obtain the target mailing information.

[0097] In some embodiments of the present application, the RPA robot issues a page acquisition operation to obtain a mailing page image; the RPA robot sends the mailing page image to the server, and the server performs optical character recognition (OCR) processing on the mailing page image based on artificial intelligence (AI) technology to obtain the mailing information text; the server calls a preset second information extraction rule to extract the target mailing information from the mailing information text; the server returns the target mailing information to the terminal device.

[0098] It should be noted that the embodiment of the present application does not limit the first information extraction rule and the second information extraction rule, and the first information extraction rule and the second information extraction rule can be adjusted according to actual conditions.

[0099] For example, Figure 5 A schematic diagram of a mailing page provided as an exemplary embodiment of the present application. Figure 5 As shown, the email page includes the party's name, ID number, party type, and address. The server uses artificial intelligence (AI) technology to perform optical character recognition (OCR) on the mailing page image to obtain the mailing information text. The server then uses a pre-set second information extraction rule to extract the target mailing information from the mailing information text: the mailing address and contact number.

[0100] In this embodiment, after obtaining the target mailing information and the reference mailing information, the RPA robot compares the target mailing information with the reference mailing information to generate a comparison result. One possible implementation method is to call a natural language processing (NLP) service to compare each item of mailing information in the target mailing information with each item of mailing information in the reference mailing information, obtaining a comparison result for each item of mailing information in the target mailing information and each item of mailing information in its corresponding reference mailing information; and generating a target comparison result based on the comparison result for each item of mailing information in the target mailing information and each item of mailing information in its corresponding reference mailing information. If the comparison results for each item of mailing information in the target mailing information and each item of mailing information in its corresponding reference mailing information are consistent, a comparison pass result is generated; if the comparison results for any item of mailing information in the target mailing information and its corresponding reference mailing information are inconsistent, a comparison fail result is generated.

[0101] In the above embodiment of the present application, the target mailing information includes a first document type, a first mailing address, and a first contact number, and correspondingly, the reference mailing information includes a second document type, a second mailing address, and a second contact number. Invoking a natural language processing (NLP) service to compare multiple pieces of mailing information in the target mailing information with multiple pieces of mailing information in the reference mailing information one by one, and obtaining a comparison result between each piece of mailing information in the target mailing information and each piece of mailing information in its corresponding reference mailing information, includes at least one of the following comparison operations:

[0102] Operation method 1: Call the natural language processing (NLP) service to determine whether the first mailing address and the second mailing address are consistent, and obtain a comparison result of whether the first mailing address and the second mailing address are consistent;

[0103] Operation method 2: Perform optical character recognition (OCR) on the electronic document to be served based on artificial intelligence (AI) technology to obtain the type of the electronic document to be served; determine whether the type of the electronic document to be served is complete, and obtain a comparison result to confirm whether the type of the electronic document to be served is complete;

[0104] Operation method three: calling the natural language processing (NLP) service to determine whether the first contact number and the second contact number are consistent, and obtaining a comparison result of whether the first contact number and the second contact number are consistent.

[0105] In the above embodiment, if the first mailing address and the second mailing address are consistent, the type of the electronic file to be delivered is complete, and the first contact number and the second contact number are consistent, a comparison pass result is generated; if at least one of the following conditions is met: the first mailing address and the second mailing address are inconsistent, the type of the electronic file to be delivered is incomplete, and the first contact number and the second contact number are inconsistent, a comparison fail result is generated.

[0106] It should be noted that if the mailing address and / or contact number in the target mailing information are inconsistent, you can attempt to correct the target mailing information. After the correction is consistent with the reference mailing information, the electronic file to be delivered can be sent. One possible implementation method is to correct the target mailing information if the target comparison result is a failed result, obtain a correction result, and then send the electronic file to be delivered if the correction result is successful. If the correction result is a failed correction, the historical audit log of the electronic file to be delivered is deleted.

[0107] In other embodiments of the present application, if the target comparison result is a failed comparison result, it means that at least one of the first document type, the first contact number, and the first mailing address has failed the comparison. Accordingly, when the target comparison result is a failed comparison result, at least one of the following operations may be performed, but is not limited to:

[0108] If the target comparison result is a comparison failure result, and the mailing information that failed the comparison in the target mailing information is the first file type, a first file type correction failure result is generated;

[0109] If the target comparison result is a failed comparison result, and the mailing information in the target mailing information that failed the comparison is the first contact number, the first contact number is replaced with the second contact number in the reference mailing information, and a replacement result of the first contact number is generated;

[0110] If the target comparison result is a failed comparison result, and the mailing information that failed the comparison in the target mailing information is the first mailing address, then the correction type of the first mailing address is determined. If the correction type is an information missing type, then a formal completion operation is performed on the first mailing address. If the correction type is an information error type, then a modification operation is performed on the first mailing address based on the second mailing address in the benchmark mailing information.

[0111] In some embodiments of the present application, a formal completion operation is performed on the first mailing address. For example, if the mailing address in the target mailing information lacks a province, the province is automatically completed after the province is identified based on the mailing address. If the target mailing information cannot be corrected, the historical audit log is deleted.

[0112] In some embodiments of the present application, the first mailing address is modified based on the second mailing address in the reference mailing information. For example, if the city name in the mailing address in the target mailing information is incorrect, the correct city name is extracted from the second mailing address and the incorrect city name is modified to the correct one. For example, if the address is located at ** Building, ** Street, Haidian District, Beijing, "Haidian" is modified to "Haidian".

[0113] In the above embodiment, if at least one operation results in a failed correction, a target correction result of "failed correction" is generated; if all operations result in successful correction, a target correction result of "successful correction" is generated. If the target correction result is successful correction, the send operation is performed on the electronic file to be delivered; if the target correction result is a failed correction, the historical audit log of the electronic file to be delivered is deleted.

[0114] In other embodiments of the present application, if the target mailing information cannot be modified, the historical audit log of the electronic file to be delivered is deleted. For example, if the mailing address in the target mailing information is "** Village", and there is too little mailing address information to complete or modify the mailing address, then the mailing address cannot be modified, and the historical audit log of the electronic file to be delivered is deleted.

[0115] In this embodiment, the RPA robot generates a file operation record table based on the operation record of the electronic file to be delivered in the case. Figure 6 This is a schematic diagram of a file operation record table provided by an exemplary embodiment of the present application. Figure 6 As shown, the case numbered 1234 has a successful status, while the case numbered 5678 has a failed status.

[0116] This embodiment combines RPA and AI technologies in a repair and forwarding mailing scenario. It automatically identifies party information in civil complaints, automatically matches and verifies the information in the electronic delivery system based on the case number, and batch-checks mailing information within a limited working time. It also generates and stores a file operation log. Compared to manual methods, this improves work efficiency and reduces labor costs.

[0117] In addition, every step of the automated processing is traceable, which allows system errors to be accurately discovered and easier to resolve once a problem occurs.

[0118] In the above method embodiment of the present application, the electronic file to be delivered is automatically obtained from the electronic delivery system; text extraction is performed on the target electronic file in the electronic file to be delivered to obtain the reference mailing information; the target mailing information is extracted from the mailing page in the electronic delivery system based on artificial intelligence (AI) technology; the target mailing information is compared with the reference mailing information to generate a target comparison result; when the target comparison result is a passed comparison result, the sending operation is automatically performed on the electronic file to be delivered based on artificial intelligence (AI) technology and the RPA robot, thereby reducing labor costs and improving file transmission efficiency.

[0119] Figure 8a This is a schematic diagram of the structure of an electronic document processing device 80 provided by an exemplary embodiment of the present application. Figure 8a As shown, the electronic document processing device 80 includes a file acquisition module 801 , a file extraction module 802 , an information extraction module 803 , a result generation module 804 and a file sending micromodule 805 .

[0120] The file acquisition module 801 is used to acquire the electronic file to be delivered from the electronic delivery system;

[0121] A text extraction module 802 is used to extract text from a target electronic file in the electronic files to be delivered to obtain reference mailing information;

[0122] An information extraction module 803 is used to extract target mailing information from the mailing page in the electronic delivery system;

[0123] A result generating module 804 is used to compare the target mailing information with the reference mailing information to generate a target comparison result;

[0124] The file sending module 805 is used to execute a sending operation on the electronic file to be delivered if the target comparison result is a passing result.

[0125] Optionally, Figure 8b This is a schematic diagram of the structure of another electronic document processing device 80 provided in an exemplary embodiment of the present application. The information extraction module 803 includes: a second acquisition submodule 8031, a processing submodule 8032 and a calling submodule 8033;

[0126] The second acquisition submodule 8031 ​​issues a page acquisition operation to acquire the mailing page image;

[0127] The processing submodule 8032 performs optical character recognition (OCR) on the mailing page image based on artificial intelligence (AI) technology to obtain the mailing information text;

[0128] The submodule 8033 is called to call the natural language processing (NLP) service to identify the mailing information text and obtain the target mailing information.

[0129] Optionally, Figure 8c This is a schematic diagram of the structure of another electronic document processing device 80 provided by an exemplary embodiment of the present application. Figure 8c As shown, the result generation module 804 includes a comparison submodule 8041 and a generation submodule 8042 .

[0130] The comparison submodule 8041 is configured to call a natural language processing (NLP) service to compare the multiple pieces of mailing information in the target mailing information with the multiple pieces of mailing information in the reference mailing information one by one, thereby obtaining a comparison result between the multiple pieces of mailing information in the target mailing information and the multiple pieces of mailing information in the corresponding reference mailing information.

[0131] The generating submodule 8042 is configured to generate a target comparison result based on the comparison results of the multiple pieces of mailing information in the target mailing information and the multiple pieces of mailing information in the corresponding reference mailing information.

[0132] Optionally, the target mailing information includes a first document type, a first mailing address, and a first contact number, and correspondingly, the reference mailing information includes a second document type, a second mailing address, and a second contact number; when the comparison submodule 8041 calls the natural language processing (NLP) service to compare the multiple pieces of mailing information in the target mailing information with the multiple pieces of mailing information in the reference mailing information one by one, and obtains a comparison result between the multiple pieces of mailing information in the target mailing information and the corresponding multiple pieces of mailing information in the reference mailing information, the comparison operation includes at least one of the following:

[0133] Invoke a natural language processing (NLP) service to determine whether the first mailing address and the second mailing address are consistent, and obtain a comparison result of whether the first mailing address and the second mailing address are consistent;

[0134] Perform optical character recognition (OCR) processing on the electronic document to be served based on artificial intelligence (AI) technology to obtain the type of the electronic document to be served; determine whether the type of the electronic document to be served is complete, and obtain a comparison result on whether the type of the electronic document to be served is complete;

[0135] A natural language processing (NLP) service is called to determine whether the first contact number and the second contact number are consistent, and a comparison result of whether the first contact number and the second contact number are consistent is obtained.

[0136] Optionally, when the result generation module 804 generates a target comparison result based on the comparison result of each target mailing information and its corresponding benchmark mailing information, it is used to generate a comparison pass result if the first mailing address and the second mailing address are consistent, the type of the electronic file to be delivered is complete, and the first contact number and the second contact number are consistent; if at least one of the following conditions is met: the first mailing address and the second mailing address are inconsistent, the type of the electronic file to be delivered is incomplete, and the first contact number and the second contact number are inconsistent, a comparison fail result is generated.

[0137] Optionally, the result generation module 804 may also be used to: if the target comparison result is a failed comparison result, and the mailing information in the target mailing information that failed the comparison is a first file type, generate a result of a failed correction of the first file type; if the target comparison result is a failed comparison result, and the mailing information in the target mailing information that failed the comparison is a first contact number, replace the first contact number with the second contact number in the reference mailing information, and generate a replacement result of the first contact number; if the target comparison result is a failed comparison result, and the mailing information in the target mailing information that failed the comparison is a first mailing address, determine a correction type of the first mailing address, and if the correction type is an information missing type, perform a formal completion operation on the first mailing address; if the correction type is an information error type, perform a modification operation on the first mailing address based on the second mailing address in the reference mailing information;

[0138] It can also be used to: generate a target correction result based on the result of at least one of the above operations; if the target correction result is a successful correction, perform a sending operation on the electronic file to be delivered; if the target correction result is a failed correction, delete the historical audit log of the electronic file to be delivered.

[0139] Optionally, the result generation module 804 may also be used to: count the number of corrections to each item of mailing information in the target mailing information; if the number of corrections is greater than a set number, generate a target correction result indicating that the correction failed.

[0140] Optionally, the result generation module 804 can also be used to: obtain the case number of the electronic file to be delivered and the processing status of the electronic file to be delivered; generate a file operation record table based on the case number and processing status of the electronic file to be delivered, wherein the processing status includes successful processing and failed processing.

[0141] The functions of each module in each device in the embodiments of the present application can be found in the corresponding description in the above method and will not be repeated here.

[0142] Figure 9 This is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application. Figure 9 As shown, the electronic device includes: a memory 901 and a processor 902. In addition, the electronic device also includes necessary components such as a power supply component 903, a communication component 904 and a display screen 905.

[0143] The memory 901 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method used to operate on the electronic device.

[0144] Memory 901 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0145] The communication component 904 is used for data transmission with other devices.

[0146] Processor 902 can execute computer instructions stored in memory 901 to perform Figure 7 Each step in the method embodiment.

[0147] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer-readable storage medium stores the computer program and the computer program is executed by one or more processors, the one or more processors execute Figure 7 Each step in the method embodiment.

[0148] Accordingly, the embodiment of the present application further provides a computer program product, the computer program product including a computer program / instruction, the computer program / instruction being executed by a processor Figure 7 Each step in the method embodiment.

[0149] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0150] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0151] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0153] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0154] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0155] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0156] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0157] The above are merely specific embodiments of the present application, intended to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to these embodiments herein, but is intended to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. An electronic document processing method combining RPA and AI, characterized in that: Applied to an RPA robot, the method includes: Obtain electronic documents to be served from the electronic service system; Extracting text from the target electronic file in the electronic files to be delivered to obtain reference mailing information; Extracting target mailing information from a mailing page in the electronic delivery system, including: obtaining a mailing page image; performing optical character recognition (OCR) processing on the mailing page image based on artificial intelligence (AI) technology to obtain mailing information text; and calling a natural language processing (NLP) service to recognize the mailing information text to obtain target mailing information; Comparing the target mailing information with the reference mailing information to generate a target comparison result; If the target comparison result is a passing result, performing a sending operation on the electronic file to be delivered; The method further includes at least one of the following operations: If the target comparison result is a comparison failure result, and the mailing information that failed the comparison in the target mailing information is a first file type, a first file type correction failure result is generated; If the target comparison result is a failed comparison result, and the mailing information in the target mailing information that failed the comparison is the first contact number, the first contact number is replaced based on the second contact number in the reference mailing information, and a replacement result of the first contact number is generated; If the target comparison result is a failed comparison result, and the mailing information in the target mailing information that failed the comparison is the first mailing address, determining a correction type for the first mailing address; if the correction type is an information missing type, performing a form completion operation on the first mailing address; if the correction type is an information error type, performing a modification operation on the first mailing address based on the second mailing address in the reference mailing information; The method further comprises: According to the result of at least one of the above operations, a target correction result is generated; if the target correction result is a successful correction, a sending operation is performed on the electronic file to be delivered; if the target correction result is a failed correction, the historical audit log of the electronic file to be delivered is deleted.

2. The method according to claim 1, characterized in that The target mailing information includes multiple pieces of mailing information, the reference mailing information includes multiple pieces of mailing information, and the comparing the target mailing information with the reference mailing information to generate a comparison result includes: Invoking a natural language processing (NLP) service to compare the multiple pieces of mailing information in the target mailing information with the multiple pieces of mailing information in the reference mailing information one by one, and obtaining a comparison result between each piece of mailing information in the target mailing information and each piece of mailing information in the corresponding reference mailing information; The target comparison result is generated according to the comparison result of each item of mailing information in the target mailing information and each item of mailing information in its corresponding reference mailing information.

3. The method according to claim 2, characterized in that The target mailing information includes a first document type, a first mailing address, and a first contact number, and correspondingly, the reference mailing information includes a second document type, a second mailing address, and a second contact number; calling a natural language processing (NLP) service to compare the multiple pieces of mailing information in the target mailing information with the multiple pieces of mailing information in the reference mailing information one by one, to obtain a comparison result of each piece of mailing information in the target mailing information with each piece of mailing information in its corresponding reference mailing information, includes at least one of the following comparison operations: Invoking a natural language processing (NLP) service to determine whether the first mailing address and the second mailing address are consistent, and obtaining a comparison result of whether the first mailing address and the second mailing address are consistent; Performing optical character recognition (OCR) processing on the electronic file to be delivered based on artificial intelligence (AI) technology to obtain the type of the electronic file to be delivered; determining whether the type of the electronic file to be delivered is complete, and obtaining a comparison result of whether the type of the electronic file to be delivered is complete; A natural language processing (NLP) service is called to determine whether the first contact number and the second contact number are consistent, and a comparison result of whether the first contact number and the second contact number are consistent is obtained.

4. The method according to claim 3, characterized in that The generating the target comparison result according to the comparison result of each item of mailing information in the target mailing information and each item of mailing information in the corresponding reference mailing information includes: If the first mailing address and the second mailing address are consistent, the type of the electronic document to be delivered is complete, and the first contact number and the second contact number are consistent, a comparison pass result is generated; If at least one of the following conditions holds true: the first mailing address and the second mailing address are inconsistent, the type of the electronic file to be delivered is incomplete, and the first contact number and the second contact number are inconsistent, a comparison failure result is generated.

5. The method according to claim 1, characterized in that The method further comprises: Count the number of revisions to each item of mailing information in the target mailing information; If the number of corrections is greater than the set number, a target correction result indicating that the correction failed is generated.

6. The method according to claim 1, characterized in that The method further comprises: Obtain the case number of the electronic document to be served and the processing status of the electronic document to be served; A file operation record table is generated according to the case number and the processing status of the electronic file to be delivered, wherein the processing status includes successful processing and failed processing.

7. An electronic document processing device combining RPA and AI, characterized in that: include: The file acquisition module is used to obtain the electronic files to be delivered from the electronic delivery system; A text extraction module, configured to extract text from a target electronic file in the electronic files to be delivered to obtain reference mailing information; An information extraction module is configured to extract target mailing information from a mailing page in the electronic delivery system, including: obtaining a mailing page image; performing optical character recognition (OCR) processing on the mailing page image based on artificial intelligence (AI) technology to obtain mailing information text; and calling a natural language processing (NLP) service to recognize the mailing information text to obtain target mailing information; A result generating module, configured to compare the target mailing information with the reference mailing information to generate a target comparison result; A file sending module, configured to send the electronic file to be delivered if the target comparison result is a passing comparison result; The file sending module is further configured to: if the target comparison result is a comparison failure result, and the mailing information that fails the comparison in the target mailing information is a first file type, generate a first file type correction failure result; If the target comparison result is a failed comparison result, and the mailing information in the target mailing information that failed the comparison is the first contact number, the first contact number is replaced based on the second contact number in the reference mailing information, and a replacement result of the first contact number is generated; If the target comparison result is a failed comparison result, and the mailing information in the target mailing information that failed the comparison is the first mailing address, determining a correction type for the first mailing address; if the correction type is an information missing type, performing a form completion operation on the first mailing address; if the correction type is an information error type, performing a modification operation on the first mailing address based on the second mailing address in the reference mailing information; Also used for: According to the result of at least one of the above operations, a target correction result is generated; if the target correction result is a successful correction, a sending operation is performed on the electronic file to be delivered; if the target correction result is a failed correction, the historical audit log of the electronic file to be delivered is deleted.

8. The device according to claim 7, characterized in that The target mailing information includes multiple pieces of mailing information, the reference mailing information includes multiple pieces of mailing information, and the result generation module includes a comparison submodule and a generation submodule; The comparison submodule is configured to call a natural language processing (NLP) service to compare the multiple pieces of mailing information in the target mailing information with the multiple pieces of mailing information in the reference mailing information one by one, thereby obtaining a comparison result between each piece of mailing information in the target mailing information and each piece of mailing information in the corresponding reference mailing information; The generating submodule is configured to generate the target comparison result based on the comparison result of each item of mailing information in the target mailing information and each item of mailing information in its corresponding reference mailing information.

9. The device according to claim 7, characterized in that The target mailing information includes a first document type, a first mailing address, and a first contact number, and correspondingly, the reference mailing information includes a second document type, a second mailing address, and a second contact number; The comparison submodule calls the natural language processing (NLP) service to compare the multiple pieces of mailing information in the target mailing information with the multiple pieces of mailing information in the reference mailing information one by one, and obtains a comparison result between each piece of mailing information in the target mailing information and each piece of mailing information in its corresponding reference mailing information, including at least one of the following comparison operations: Invoking a natural language processing (NLP) service to determine whether the first mailing address and the second mailing address are consistent, and obtaining a comparison result of whether the first mailing address and the second mailing address are consistent; Performing optical character recognition (OCR) processing on the electronic file to be delivered based on artificial intelligence (AI) technology to obtain the type of the electronic file to be delivered; determining whether the type of the electronic file to be delivered is complete, and obtaining a comparison result of whether the type of the electronic file to be delivered is complete; A natural language processing (NLP) service is called to determine whether the first contact number and the second contact number are consistent, and a comparison result of whether the first contact number and the second contact number are consistent is obtained.

10. The device according to claim 8, characterized in that When generating the target comparison result based on the comparison result of each item of mailing information in the target mailing information and each item of mailing information in the corresponding reference mailing information, the generating submodule is configured to: If the first mailing address and the second mailing address are consistent, the type of the electronic document to be delivered is complete, and the first contact number and the second contact number are consistent, a comparison pass result is generated; If at least one of the following conditions holds true: the first mailing address and the second mailing address are inconsistent, the type of the electronic file to be delivered is incomplete, and the first contact number and the second contact number are inconsistent, a comparison failure result is generated.

11. The device according to claim 7, characterized in that The file sending module is also used to: Count the number of revisions to each item of mailing information in the target mailing information; If the number of corrections is greater than the set number, a target correction result indicating that the correction failed is generated.

12. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the method according to any one of claims 1 to 6.

13. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images