Logistics export order processing method, device and electronic equipment combining RPA and AI

Abstract

The present application proposes a logistics export order processing method combining RPA and AI, which is applied to the robotic process automation RPA system, including: regularly reading the content information of the operation table, wherein the operation table contains the identification of the packing list of each of the multiple logistics export orders and the first node status information, the second node status information and the third node status information of each packing list; each time the content information of the operation table is read, based on the first node status information and the second node status information in the operation table, the content information of the first packing list and the invoice file of the second packing list are downloaded in sequence; according to the second node status information and the third node status information in the operation table, it is determined whether to verify the invoice file, and according to the verification result, it is determined whether to ship the logistics export order corresponding to the invoice file. This solution processes the logistics export order by the RPA system, which can not only reduce labor costs, but also improve the efficiency and timeliness of order processing.

Description

Technical Field

[0001] The present application relates to the technical fields of Robotic Process Automation (RPA) and Artificial Intelligence (AI), and in particular to a logistics export order processing method, device and electronic equipment combining RPA and AI. Background Art

[0002] Robotic Process Automation (RPA), referred to as Robotic Process Automation, 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] In related businesses, logistics export orders are mainly processed manually. Since the export process is cumbersome and the operation process is repeated, it consumes a lot of labor costs. In addition, due to the time difference with foreign countries, when encountering a large number of orders, it is often not processed in time. Summary of the invention

[0005] The embodiment of the present application provides a logistics export order processing method, device and electronic device combining RPA and AI to solve the above problems. The technical solution is as follows:

[0006] In a first aspect, an embodiment of the present application provides a logistics export order processing method combining RPA and AI, which is applied to a robotic process automation (RPA) system. The method includes:

[0007] Periodically read the content information of the operation table, wherein the operation table contains the packing list identifiers of the respective multiple logistics export orders and the first node status information, the second node status information and the third node status information of each packing list; the first node status information is used to indicate whether the content information of the packing list has been downloaded; the second node status information is used to indicate whether the invoice file of the packing list has been downloaded; the third node status information is used to indicate whether the invoice file of the packing list has been verified;

[0008] Each time the content information of the operation table is read, based on the first node status information and the second node status information in the operation table, the content information of the first packing list and the invoice file of the second packing list are downloaded in sequence;

[0009] According to the second node status information and the third node status information in the operation table, determine whether to verify the invoice document, and obtain the verification result when verifying the invoice document. According to the verification result, determine whether to ship the logistics export order corresponding to the invoice document.

[0010] In some embodiments of the present application, sequentially downloading the content information of the first packing list and the invoice file of the second packing list based on the first node status information and the second node status information in the operation table includes:

[0011] Based on the first node status information in the operation table, determining the first packing list from the operation table, downloading the content information of the first packing list, and updating the first node status information of the first packing list; wherein the first packing list is a packing list without downloading the packing list content information;

[0012] Based on the first node status information and the second node status information in the operation table, determine the second packing list from the operation table, download the invoice file of the second packing list, and update the second node status information of the second packing list; wherein the second packing list is a packing list for which the packing list content information has been downloaded but the invoice file has not been downloaded.

[0013] As an implementation manner, based on the first node status information and the second node status information in the operation table, determining the second packing list from the operation table, downloading the invoice file of the second packing list, and updating the second node status information of the second packing list includes:

[0014] Based on the first node status information and the second node status information in the operation table, determine a third packing list from the operation table, and obtain an invoice identifier of the third packing list; wherein the third packing list is a packing list for which the packing list content information has been downloaded and for which an invoice document has not been generated;

[0015] Performing image recognition on the invoice management system based on artificial intelligence (AI) technology, simulating manual operation to log into the invoice management system to produce an invoice file corresponding to the invoice identifier of the third packing list, and updating the second node status information of the third packing list;

[0016] Based on the second node status information in the operation table, determine the fourth packing list from the operation table, and obtain the invoice identifier of the fourth packing list; wherein the fourth packing list is a packing list for which an invoice document has been prepared but the invoice document has not been reviewed;

[0017] Simulate manual operation to log in to the invoice management system to query the review status of the invoice corresponding to the invoice identifier of the fourth packing list, and update the second node status information of the fourth packing list;

[0018] Based on the second node status information in the operation table, determine the fifth packing list from the operation table, and obtain the invoice identifier of the fifth packing list; wherein the fifth packing list is a packing list for which the invoice file has been reviewed and the invoice file has not been downloaded, and a second packing list for which the invoice file does not need to be reviewed and the invoice file has not been downloaded;

[0019] The invoice management system is logged in to simulate manual operation to download the invoice file corresponding to the invoice identifier of the fifth packing list, and the second node status information of the fifth packing list is updated.

[0020] As an implementation manner, determining the third packing list from the operation table based on the first node status information and the second node status information in the operation table, and obtaining the invoice identifier of the third packing list includes:

[0021] Based on the first node status information and the second node status information in the operation table, determining a sixth packing list from the operation table; wherein the sixth packing list is a packing list for which the packing list content information has been downloaded and the invoice mark has not been generated;

[0022] Simulate manual operation to log into the invoice management system to query whether the sixth packing list has generated an invoice identifier;

[0023] If the sixth packing list has generated an invoice identifier, obtain the invoice identifier of the sixth packing list, write the invoice identifier of the sixth packing list into the operation table, and update the second node status information of the sixth packing list;

[0024] Based on the second node status information in the operation table, a third packing list for which an invoice identifier has been generated but an invoice document has not been prepared is determined from the operation table, and the invoice identifier of the third packing list is obtained.

[0025] In some embodiments of the present application, updating the second node status information of the third packing list includes:

[0026] If the first invoice file after being produced needs to be reviewed, the second node status information of the third packing list corresponding to the first invoice file is updated to the invoice file having been produced and the invoice file has not been reviewed, and the first invoice file is submitted to the invoice management system for review;

[0027] If the prepared second invoice document does not need to be reviewed, the second node status information of the third packing list corresponding to the second invoice document is updated to indicate that the invoice document has been prepared and does not need to be reviewed.

[0028] As an implementation manner, determining whether to verify the invoice document according to the second node status information and the third node status information in the operation table, obtaining a verification result when verifying the invoice document, and determining whether to ship the logistics export order corresponding to the invoice document according to the verification result includes:

[0029] Based on the second node status information and the third node status information in the operation table, determine the seventh packing list from the operation table, and obtain the third invoice file of the seventh packing list and the packing list content information corresponding to the third invoice file; wherein the seventh packing list is a packing list for which the invoice file has been downloaded but the invoice file has not been uploaded;

[0030] Performing image recognition on the file management system based on artificial intelligence (AI) technology, simulating manual operation to log into the file management system, packaging the third invoice file and the packing list content information corresponding to the third invoice file and uploading them to the file management system, and updating the third node status information of the seventh packing list;

[0031] Based on the third node status information in the operation table, determine the eighth packing list from the operation table, and obtain the invoice identifier of the eighth packing list; wherein the eighth packing list is a packing list for which the invoice file has been uploaded and has no feedback status;

[0032] Simulate manual operation to log into the file management system to query the feedback status of the fourth invoice file corresponding to the invoice identifier of the eighth packing list;

[0033] If the fourth invoice file has been fed back, the third node status information of the eighth packing list is updated;

[0034] Based on the third node status information in the operation table, determine the ninth packing list from the operation table, obtain the invoice ID of the ninth packing list, and simulate manual login to the file management system to download the feedback file corresponding to the invoice ID; wherein the ninth packing list is a packing list that has been fed back and the invoice file has not been verified;

[0035] Obtaining the fifth invoice document corresponding to the invoice identifier of the ninth packing list, and obtaining the actual amount and the feedback amount of the fifth invoice document according to the fifth invoice document and the feedback document, and comparing the actual amount with the feedback amount to verify whether the two are consistent, obtaining a verification result, and updating the third status information of the ninth packing list;

[0036] If the verification result is that the actual amount is consistent with the feedback amount, the logistics export order corresponding to the fifth invoice document is shipped.

[0037] In some embodiments of the present application, the method further includes:

[0038] Based on the natural language processing (NLP) technology in artificial intelligence (AI) technology, the text information in the feedback file is processed to obtain the logistics information of the logistics export order corresponding to the fifth invoice file;

[0039] Generate ledger information based on the verification result and the logistics information.

[0040] In some embodiments of the present application, the obtaining the actual amount and the feedback amount of the fifth invoice file according to the fifth invoice file and the feedback file includes:

[0041] Obtaining the actual amount of the fifth invoice document;

[0042] Based on the natural language processing (NLP) technology in artificial intelligence (AI) technology, the text information in the feedback file is processed to obtain the feedback amount of the fifth invoice file.

[0043] In one embodiment, before the periodic reading of the operation table, the method further includes:

[0044] Check whether the target email exists in the mailbox;

[0045] In response to the target mail being in the mailbox, a packing list identifier of the logistics export order in the target mail is obtained, and the packing list identifier is written into the operation table.

[0046] In a second aspect, an embodiment of the present application provides a logistics export order processing device combining RPA and AI, which is applied to a robotic process automation (RPA) system. The device includes:

[0047] A reading module is used to periodically read the content information of the operation table, wherein the operation table contains the identifiers of the packing lists of the respective multiple logistics export orders and the first node status information, the second node status information and the third node status information of each of the packing lists; the first node status information is used to indicate whether the content information of the packing list has been downloaded; the second node status information is used to indicate whether the invoice file of the packing list has been downloaded; the third node status information is used to indicate whether the invoice file of the packing list has been verified;

[0048] A download module, configured to download the content information of the first packing list and the invoice file of the second packing list in sequence based on the first node status information and the second node status information in the operation table each time the content information of the operation table is read;

[0049] A determination module is used to determine whether to verify the invoice document according to the second node status information and the third node status information in the operation table, and obtain the verification result when verifying the invoice document, and determine whether to ship the logistics export order corresponding to the invoice document according to the verification result.

[0050] In some embodiments of the present application, the download module includes:

[0051] A first downloading unit is used to determine the first packing list from the operation table based on the first node status information in the operation table, download the content information of the first packing list, and update the first node status information of the first packing list; wherein the first packing list is a packing list for which the packing list content information is not downloaded;

[0052] The second downloading unit is used to determine the second packing list from the operation table based on the first node status information and the second node status information in the operation table, download the invoice file of the second packing list, and update the second node status information of the second packing list; wherein the second packing list is a packing list for which the packing list content information has been downloaded but the invoice file has not been downloaded.

[0053] As an implementation manner, the second downloading unit is specifically used for:

[0054] Based on the first node status information and the second node status information in the operation table, determine a third packing list from the operation table, and obtain an invoice identifier of the third packing list; wherein the third packing list is a packing list for which the packing list content information has been downloaded and for which no invoice has been generated;

[0055] Performing image recognition on the invoice management system based on artificial intelligence (AI) technology, simulating manual operation to log into the invoice management system to produce an invoice file corresponding to the invoice identifier of the third packing list, and updating the second node status information of the third packing list;

[0056] Based on the second node status information in the operation table, determine the fourth packing list from the operation table, and obtain the invoice identifier of the fourth packing list; wherein the fourth packing list is a packing list for which an invoice document has been prepared but the invoice document has not been reviewed;

[0057] Simulate manual operation to log in to the invoice management system to query the review status of the invoice corresponding to the invoice identifier of the fourth packing list, and update the second node status information of the fourth packing list;

[0058] Based on the second node status information in the operation table, determine the fifth packing list from the operation table, and obtain the invoice identifier of the fifth packing list; wherein the fifth packing list is a packing list for which the invoice file has been reviewed and the invoice file has not been downloaded, and a packing list for which the invoice file does not need to be reviewed and the invoice file has not been downloaded;

[0059] The invoice management system is logged in to simulate manual operation to download the invoice file corresponding to the invoice identifier of the fifth packing list, and the second node status information of the fifth packing list is updated.

[0060] As an implementation manner, the second downloading unit is further used for:

[0061] Based on the first node status information and the second node status information in the operation table, determining a sixth packing list from the operation table; wherein the sixth packing list is a packing list for which the packing list content information has been downloaded and the invoice mark has not been generated;

[0062] Simulate manual operation to log into the invoice management system to query whether the sixth packing list has generated an invoice identifier;

[0063] If the sixth packing list has generated an invoice identifier, obtain the invoice identifier of the sixth packing list, write the invoice identifier of the sixth packing list into the operation table, and update the second node status information of the sixth packing list;

[0064] Based on the second node status information in the operation table, a third packing list for which an invoice identifier has been generated but an invoice document has not been prepared is determined from the operation table, and the invoice identifier of the third packing list is obtained.

[0065] In some embodiments of the present application, the second downloading unit is further used for:

[0066] If the first invoice file needs to be reviewed after being produced, the second node status information of the third packing list corresponding to the first invoice file is updated to the state that the invoice file has been produced but the invoice file has not been reviewed, and the first invoice file is submitted to the invoice management system for review;

[0067] If the prepared second invoice document does not need to be reviewed, the second node status information of the third packing list corresponding to the second invoice document is updated to indicate that the invoice document has been prepared and does not need to be reviewed.

[0068] As an implementation manner, the determining module is specifically used for:

[0069] Based on the second node status information and the third node status information in the operation table, determine the seventh packing list from the operation table, and obtain the third invoice file of the seventh packing list and the packing list content information corresponding to the third invoice file; wherein the seventh packing list is a packing list for which the invoice file has been downloaded but the invoice file has not been uploaded;

[0070] Performing image recognition on the file management system based on artificial intelligence (AI) technology, simulating manual operation to log into the file management system, packaging the third invoice file and the packing list information content corresponding to the third invoice file and uploading them to the file management system, and updating the third node status information of the seventh packing list;

[0071] Based on the third node status information in the operation table, determine the eighth packing list from the operation table, and obtain the invoice identifier of the eighth packing list; wherein the eighth packing list is a packing list for which the invoice file has been uploaded and has no feedback status;

[0072] Simulate manual operation to log into the file management system to query the feedback status of the fourth invoice file corresponding to the invoice identifier of the eighth packing list;

[0073] If the fourth invoice file has been fed back, the third node status information of the eighth packing list is updated;

[0074] Based on the third node status information in the operation table, determine the ninth packing list from the operation table, obtain the invoice ID of the ninth packing list, and simulate manual login to the file management system to download the feedback file corresponding to the invoice ID; wherein the ninth packing list is a packing list that has been fed back and the invoice file has not been verified;

[0075] Obtaining the fifth invoice document corresponding to the invoice identifier of the ninth packing list, and obtaining the actual amount and the feedback amount of the fifth invoice document according to the fifth invoice document and the feedback document, and comparing the actual amount with the feedback amount to verify whether the two are consistent, obtaining a verification result, and updating the third status information of the ninth packing list;

[0076] If the verification result is that the actual amount is consistent with the feedback amount, the logistics export order corresponding to the fifth invoice document is shipped.

[0077] In some embodiments of the present application, the determining module is further used to:

[0078] Obtaining the actual amount of the fifth invoice document;

[0079] The natural language processing (NLP) technology in artificial intelligence (AI) technology is used to process the text information in the feedback file to obtain the feedback amount of the fifth invoice file.

[0080] In some embodiments of the present application, the device further includes a generating module, and the generating module is used to:

[0081] Based on the natural language processing (NLP) technology in artificial intelligence (AI) technology, the text information in the feedback file is processed to obtain the logistics information of the logistics export order corresponding to the fifth invoice file;

[0082] Generate ledger information based on the verification result and the logistics information.

[0083] As an implementation manner, the device further includes a writing module, and the writing module is used to:

[0084] Before the content information of the periodic reading operation table is read, query whether there is a target email in the mailbox;

[0085] In response to the existence of the target mail in the mailbox, an identifier of a packing list of the logistics export order in the target mail is obtained, and the packing list identifier is written into the operation table.

[0086] In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the method described in the first aspect above.

[0087] 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 is executed by a processor, it implements the method described in the first aspect above.

[0088] According to the technical solution of the present application, the operation table that records the packing list identification and node status information of each of the multiple logistics export orders is read regularly by the robot process automation RPA system, and each time it is read, based on the first node status information and the second node status information in the operation table, the content information of the first packing list and the invoice file of the second packing list are downloaded in sequence, and according to the second node status information and the third node status information, it is determined whether to verify the invoice file, and based on the verification result, it is determined whether to ship the logistics export order corresponding to the invoice file. This solution uses the robot process automation RPA system to execute the entire order processing process, which can avoid manual repetitive operations, thereby greatly reducing labor costs. In addition, since the RPA system can execute order processing regularly throughout the day, it can avoid the problem of untimely order processing due to time differences and working hours, and can also improve the efficiency of order processing.

[0089] 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

[0090] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments according to the present application and should not be regarded as limiting the scope of the present application.

[0091] Figure 1 A flowchart of a logistics export order processing method combining RPA and AI provided in an embodiment of the present application;

[0092] Figure 2 A flowchart of another method for processing logistics export orders combining RPA and AI provided in an embodiment of the present application;

[0093] Figure 3 A flowchart of an invoice downloading process in an embodiment of the present application;

[0094] Figure 4 A flowchart of another invoice downloading process in an embodiment of the present application;

[0095] Figure 5 A flowchart of an invoice file verification process in an embodiment of the present application;

[0096] Figure 6 A structural block diagram of a logistics export order processing device combining RPA and AI provided in an embodiment of the present application;

[0097] Figure 7 A structural block diagram of an electronic device provided in an embodiment of the present application; DETAILED DESCRIPTION

[0098] 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 only used to explain the present application, and cannot be understood as limiting the present application.

[0099] In the description of this application, the term "RPA system" refers to a Robotic Process Automation (RPA) system, which uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules.

[0100] In the description of this application, the term "AI" refers to Artificial Intelligence (AI), which is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0101] In the description of this application, the term "NLP" refers to Natural Language Processing, which is a branch of artificial intelligence technology. It refers to the technology that enables computers to understand, process and generate language like humans.

[0102] In the description of this application, the term "packing list" is a list used to describe the packaging details of the goods. The main function of the packing list is to supplement the content of the invoice, recording in detail the packing method, packaging materials, number of packages, goods rules, quantity, weight, etc., to facilitate the approval of the goods by customs and other relevant departments.

[0103] In the description of this application, the term "content information of the packing list" refers to the content information recorded in the packing list, which is just a distinction here.

[0104] In the description of this application, the term "operation table" refers to a form used to record the identification and corresponding status information of the packing list of the logistics export order to indicate the processing progress of the logistics export order.

[0105] In the description of this application, the term "logistics export order" refers to an order for a sales agreement with a foreign customer.

[0106] In the description of this application, the term "verification result" refers to the result obtained when verifying the invoice document, which is used to indicate whether the logistics export order corresponding to the invoice document can be shipped.

[0107] In the description of this application, the term "invoice identification" refers to an identification used to represent a unique invoice, such as an invoice number.

[0108] In the description of this application, the term "ledger information" refers to detailed information used to record the amount of a logistics export order, invoice identification, packing list identification, verification results, physical information, etc.

[0109] In the description of the present application, the term "plurality" refers to two or more.

[0110] These and other aspects of the embodiments of the present application will be apparent with reference to the following description and accompanying drawings. In these descriptions and accompanying drawings, some specific implementations in the embodiments of the present application are specifically disclosed to represent 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 thereto. On the contrary, the embodiments of the present application include all changes, modifications and equivalents that fall within the spirit and connotation of the appended claims.

[0111] It should be noted that with the development of domestic manufacturing in recent years, more and more Chinese manufacturing industries have exported their products to all parts of the world, and the number of such businesses has been growing in recent years. In related businesses, logistics export orders are mainly processed manually. Since the export process is cumbersome and the operation process is repeated, a lot of labor costs are consumed. In addition, due to the time difference with foreign countries, when encountering a large number of orders, they are often not processed in time.

[0112] In order to solve the above problems, the following describes a logistics export order processing method, device and electronic device combining RPA and AI according to an embodiment of the present application in conjunction with the accompanying drawings.

[0113] Figure 1 It is a flowchart of a method for processing logistics export orders combining RPA and AI provided in an embodiment of the present application. In some embodiments of the present application, the process of logistics export order processing includes a packing list content information download node, an invoice file download node, and an invoice file verification node. It should be noted that the method for processing logistics export orders combining RPA and AI in an embodiment of the present application can be applied to the logistics export order processing device combining RPA and AI in an embodiment of the present application, and the device can be configured in an electronic device. Figure 1 As shown, the method may include the following steps:

[0114] Step 101, periodically read the content information of the operation table, wherein the operation table contains the identification of the packing lists of multiple logistics export orders and the first node status information, the second node status information and the third node status information of each packing list; the first node status information is used to indicate whether the content information of the packing list has been downloaded; the second node status information is used to indicate whether the invoice file of the packing list has been downloaded; the third node status information is used to indicate whether the invoice file of the packing list has been verified.

[0115] In some embodiments of the present application, an operation sheet refers to a form used to record the identification and corresponding status of the packing list of a logistics export order to indicate the processing progress of the logistics export order. The operation sheet can be stored in a specified path of an electronic device, and the electronic device is configured with an RPA system, so the RPA system can read the operation sheet regularly according to the specified path at a preset time. Among them, the identification of the packing list refers to an identification that can represent a unique packing list, such as a packing list number. The information content of the packing list refers to the detailed information of the content contained in the packing list, which can refer to the detailed list corresponding to the packing list, or other forms of files containing detailed information in the packing list. The first node status information of the packing list is used to indicate the progress status of the content information download node of the packing list in the logistics export order processing flow, to indicate whether the content information of the packing list has been downloaded. The second node status information of the packing list is used to indicate the progress status of the invoice file download node in the logistics export order processing flow, to indicate whether the invoice file of the packing list has been downloaded. The third node status information of the packing list is used to indicate the progress status of the invoice document verification node in the logistics export order processing flow, to indicate whether the invoice document of the packing list has been verified.

[0116] In some embodiments of the present application, the content information of the operation table can be read regularly according to a preset schedule. Since the RPA system needs to download the content information of the corresponding packing list, download the invoice file, and verify the invoice file according to the status information of each packing list each time it reads the content information of the operation table, the RPA system also needs time to perform related processing after reading the operation table each time. Therefore, it can be that after each RPA system is executed, the time for the next reading is determined based on the schedule. It should be noted that the time for the RPA system to read the operation table each time can be determined according to the actual application scenario, and this application does not limit this.

[0117] As an implementation method, a schedule for the RPA system to regularly read the operation table can be preset. For example, the RPA system reads the operation table every five minutes. The time for the RPA system to read the operation table every day can be set to 00:05, 00:10, 00:15, 00:20, 00:25, and so on. If the RPA system starts reading the operation table at 00:05 and completes the logistics export order processing after this reading at 00:08, the RPA system needs to wait until 00:10 to start the next round of reading. If the RPA system starts reading the operation table at 00:05 and completes the logistics export order processing after this reading at 00:21, the RPA system needs to wait until 00:25 to start the next round of reading.

[0118] As another implementation method, the time interval may be calculated each time a program is executed in the RPA system. For example, the next reading of the operation table may be started five minutes after each program is executed.

[0119] It should be noted that in the logistics export order business scenario, each time a new logistics export order appears, the system will automatically send an email to the relevant departments in accordance with the preset email format to inform the relevant departments to process the new logistics export order. The email usually includes the logistics export order identification.

[0120] In order to ensure the timely processing of new logistics export orders, it is necessary to write the packing list identification and status information of the new logistics export order into the operation table. Therefore, before the RPA system reads the operation table regularly, the method may also include: querying whether there is a target email in the mailbox; in response to the existence of the target email in the mailbox, obtaining the packing list identification of the logistics export order in the target email, and writing the packing list identification into the operation table. Among them, the target email refers to the instruction email as a new logistics export order. Since the format of the email is fixed, the RPA system can obtain the target email in the preset email format and the receipt time after the last round of mailbox query according to the preset email format. In addition, if the identification of the packing list of the logistics export order exists in the target email, it can be directly determined in the target email. If the identification of the packing list of the logistics export order is not recorded in the target email, the identification of the packing list of the logistics export order can be queried in the logistics management system using the logistics export order identification.

[0121] It should be noted that the process of the RPA system querying the mailbox and writing the identifier of the packing list into the operation table and the process of reading the operation table can be executed in parallel or in series. If it is executed in parallel, the time interval for querying the mailbox can be preset for the RPA system to regularly write the identifier of the packing list of the new logistics export order into the operation table. If it is executed in series, the RPA system can query the mailbox before reading the operation table each time to write the identifier of the packing list of the new logistics export order.

[0122] Step 102, each time the content information of the operation table is read, based on the first node status information and the second node status information in the operation table, the content information of the first packing list and the invoice file of the second packing list are downloaded in sequence.

[0123] That is to say, each time the RPA system reads the content information of the operation table, it downloads the content information of the packing list, downloads the invoice file, and verifies the invoice file in sequence.

[0124] It can be understood that the process of logistics export order processing includes the packing list content information download node, the invoice file download node and the invoice file verification node, and they are executed in this order. Therefore, each time the RPA system reads the content information of the operation table, it can first obtain the first packing list whose content information has not been downloaded based on the first node status information and the second node status information, download the content information of the first packing list, and then obtain the second packing list whose invoice file has not been downloaded to download the invoice file of the second packing list.

[0125] Among them, the download of the content information of the packing list and the download of the invoice file of the packing list can be executed by the RPA system opening the web page under the corresponding operation business scenario in the electronic device, and the downloaded content information of the packing list and the invoice file are stored in the electronic device according to the preset path. For easy distinction, the content information of each packing list can be named according to the identifier of the packing list, and the invoice file can also be named according to the identifier of the corresponding packing list.

[0126] It should be noted that each time the operation table is read, there may be multiple first packing list content information that needs to be downloaded, and there may also be multiple second packing list invoice files that need to be downloaded, so when the RPA system executes the download, it can perform batch downloads to improve processing efficiency.

[0127] Step 103, based on the second node status information and the third node status information in the operation table, determine whether to verify the invoice document, and obtain the verification result when verifying the invoice document, and determine whether to ship the logistics export order corresponding to the invoice document based on the verification result.

[0128] It can be understood that if the content information of the packing list and the invoice file have been downloaded, the invoice file can be checked to determine whether there are any problems. If there are no problems with the invoice file, the logistics export order corresponding to the invoice file can be shipped. If there are problems with the invoice file, it can be submitted to manual review again.

[0129] That is, if the second node status of a packing list in the operation table is that the invoice has been downloaded and the third node status is that the invoice has not been verified, the invoice file of the packing list can be verified. If the invoice files of all packing lists that meet the above conditions in the operation table have been verified, the RPA system ends this round of processing.

[0130] According to the logistics export order processing method combining RPA and AI in the embodiment of the present application, the operation table recording the packing list identification and node status information of the packing list of each of the multiple logistics export orders is read regularly by the robot process automation RPA system, and each time it is read, based on the first node status information and the second node status information in the operation table, the content information of the first packing list and the invoice file of the second packing list are downloaded in sequence, and according to the second node status information and the third node status information, it is determined whether to verify the invoice file, and based on the verification result, it is determined whether to ship the logistics export order corresponding to the invoice file. This solution uses the robot process automation RPA system to execute the entire order processing process, which can avoid manual repetitive operations, thereby greatly reducing labor costs. In addition, since the RPA system can execute order processing regularly throughout the day, it can avoid the problem of untimely order processing due to time differences and working hours, and can also improve the efficiency of order processing.

[0131] Next, based on the above embodiments, the logistics export order processing method combining RPA and AI of this application will be introduced in detail.

[0132] Figure 2 This is a flow chart of another method for processing logistics export orders combining RPA and AI proposed in an embodiment of the present application. Figure 2 As shown, each time the RPA system is triggered, the method includes the following steps:

[0133] Step 201, read the content information of the operation table, wherein the operation table contains the identification of the packing lists of multiple logistics export orders and the first node status information, the second node status information and the third node status information of each packing list; the first node status information is used to indicate whether the content information of the packing list has been downloaded; the second node status information is used to indicate whether the invoice file of the packing list has been downloaded; the third node status information is used to indicate whether the invoice file of the packing list has been verified.

[0134] Step 202, based on the first node status information in the operation table, determine the first packing list from the operation table, download the content information of the first packing list, and update the first node status information of the first packing list; wherein the first packing list is a packing list without downloading the packing list content information.

[0135] That is, after downloading the content information of the first packing list, it is necessary to simultaneously update the first node status information of the first packing list in the operation table, so as to facilitate the subsequent downloading of the invoice file of the packing list according to the first node status information and the second node status information. For example, the first stage status information of the first packing list is updated from the state in which the content information of the packing list has not been downloaded to the state in which the content information of the packing list has been downloaded.

[0136] As an example, the logistics management system can be subjected to image recognition based on artificial intelligence (AI) technology, and manual operation can be simulated to log into the logistics management system, so as to batch download the content information of the first packing list based on the identification of the first packing list.

[0137] Step 203, based on the first node status information and the second node status information in the operation table, determine the second packing list from the operation table, download the invoice file of the second packing list, and update the second node status information of the second packing list; wherein the second packing list is a packing list for which the packing list content information has been downloaded but the invoice file has not been downloaded.

[0138] In some embodiments of the present application, based on the first node status information and the second node status information in the operation table, the second packing list is determined from the operation table, that is, the second packing list is determined from the operation table after the first node status information of the first packing list is updated, rather than determining the second packing list in the operation table before the update, so as to download as many invoice documents as possible in this round of processing, thereby improving the timeliness of logistics export order processing as a whole.

[0139] As an example, based on the first node status information and the second node status information in the operation table, it can be determined from the operation table that the first node status information is the second packing list in the state of downloaded packing list content information, and the second node status information is the second packing list in the state of not downloading the invoice file; simulate manual operation to log in to the invoice management system, and download the invoice file of the second packing list according to the identification of the second packing list.

[0140] Step 204, based on the second node status information and the third node status information in the operation table, determine whether to verify the invoice document, and obtain the verification result when verifying the invoice document, and determine whether to ship the logistics export order corresponding to the invoice document based on the verification result.

[0141] It can be understood that this step can also be carried out in the operation table after the second node status of the second packing list is updated, according to the operation table, to determine the packing list whose second node status information is the downloaded invoice file status and the third node status information is the unverified invoice file status, and according to the identification of the packing list, obtain the corresponding invoice file under the corresponding invoice file storage path, and verify these invoice files, and obtain the verification results when verifying the invoice files, and determine whether to ship the logistics export order corresponding to the invoice file according to the verification results.

[0142] According to the logistics export order processing method combining RPA and AI in the embodiment of the present application, based on the first node status information, the first packing list whose content information of the packing list has not been downloaded is determined from the operation table, and after the content information of the first packing list is downloaded, the first node status information of the first packing list is updated, and in the updated operation table, based on the first node status information and the second node status information, the second packing list is determined to download the corresponding invoice file, and the second node status information of the second packing list is updated. In this way, each time the RPA system is triggered, as many logistics export orders as possible can be processed in batches, thereby not only improving the timeliness of logistics export order processing, but also further improving processing efficiency.

[0143] In some embodiments of the present application, the invoice download node in the processing flow of the logistics export order includes an invoice file production subnode, an invoice file review subnode, and an invoice file download subnode. Among them, the invoice file production subnode refers to the process of filling in and producing invoice information, the invoice file review subnode refers to the review process of invoice files that meet the preset conditions and need to be reviewed after the invoice is produced, and the invoice file download subnode refers to the process of downloading invoice files that have been reviewed or do not need to be reviewed. Next, we will combine each subnode to Figure 2 Step 202 in FIG. 1 is described in detail.

[0144] Figure 3 FIG. 1 is a flowchart of a process of downloading invoices in an embodiment of the present application. Figure 3 As shown, Figure 2 In step 202, in the operation table, determining that the first node status is the first packing list whose information content of the packing list has not been downloaded, downloading the information content of the first packing list, and updating the first node status of the first packing list to the information content of the packing list has been downloaded may include:

[0145] Step 301, based on the first node status information and the second node status information in the operation table, determine the third packing list from the operation table, and obtain the invoice identifier of the third packing list; wherein the third packing list is a packing list for which the packing list content information has been downloaded and the invoice has not been generated.

[0146] In some embodiments of the present application, since the invoice file download node includes an invoice file production sub-node, an invoice file review sub-node, and an invoice file download sub-node, the status of each sub-node is reflected in the second node status information. As an example, if the invoice document of a packing list has not been prepared, the second node status information of the packing list is that the invoice document has not been prepared; if the invoice document of a packing list has been prepared and the invoice document does not need to be reviewed, the second node status information of the packing list is that the invoice document has been prepared and the invoice document does not need to be reviewed; if the invoice document of a packing list has been prepared and the invoice document needs to be reviewed but has not been reviewed, the second node status information of the packing list is that the invoice document has been prepared and the invoice document has not been reviewed; if the invoice document of a packing list has been reviewed but the invoice document has not been downloaded, the second node status information of the packing list is that the invoice document has been reviewed and the invoice document has not been downloaded; if the invoice document of a packing list does not need to be reviewed but the invoice document has not been downloaded, the second node status information of the packing list is that the invoice document does not need to be reviewed and the invoice document has not been downloaded; if the invoice document of a packing list has been downloaded, the second node status information of the packing list is that the invoice document has been downloaded.

[0147] That is to say, based on the first node status information and the second node status information, it is possible to determine from the operation table the third packing list in which the first node status information is the state in which the packing list content information has been downloaded and the second node status information is the state in which the invoice document has not been produced, and obtain the invoice identification of the third packing list.

[0148] The invoice identifier of the third packing list refers to an identifier used to uniquely indicate the invoice of the third packing list, such as the invoice number of the third packing list. The invoice identifier of the third packing list can be obtained through a related invoice management system. For example, the RPA system can obtain the identifier of the third packing list in the operation sheet, and then simulate manual operation to open a browser and enter the preset invoice management system URL to enter the invoice management system, and use the identifier of the third packing list to search and obtain the invoice identifier of the third packing list.

[0149] Step 302, based on artificial intelligence AI technology, image recognition is performed on the invoice management system, and manual operation is simulated to log in to the invoice management system to produce an invoice file corresponding to the invoice identifier of the third packing list, and the second node status information of the third packing list is updated.

[0150] In the business scenario of logistics export order processing, the system will generate an invoice ID for the new packing list. It is possible that the packing list and the invoice ID are in a one-to-one relationship, or there may be multiple packing lists corresponding to one invoice ID. This is related to the requirements of the business scenario and this application does not limit this.

[0151] In some embodiments of the present application, the RPA system can simulate manual operation to log in to the invoice management system, and edit the invoice file corresponding to the invoice identifier of the third packing list to fill in the necessary information, and the edited content can be preset in the RPA system. It can be understood that if the amount corresponding to the invoice file is large, or when a specific product is involved in the invoice file, or when the invoice file meets other preset conditions, the invoice file needs to be reviewed by other relevant personnel. Therefore, after the RPA system has completed the production of the invoice file, it is necessary to determine whether the produced invoice file needs to be reviewed. If the first invoice file after production needs to be reviewed, the second node status information of the third packing list corresponding to the first invoice file is updated to the state that the invoice file has been produced and the invoice file has not been reviewed, and the first invoice file is submitted to the invoice management system for review; if the second invoice file after production does not need to be reviewed, the second node status information of the third packing list corresponding to the second invoice file is updated to the state that the invoice file has been produced and the invoice file does not need to be reviewed.

[0152] As an implementation method, based on actual business needs, the requirements for invoice documents that need to be reviewed, as well as the correspondence between invoice document features and reviewers can be preset in the RPA system. In this way, the RPA system can compare the produced invoice documents with the preset condition information to determine which invoice documents need to be reviewed and the corresponding reviewers.

[0153] Step 303, based on the second node status information in the operation table, determine the fourth packing list from the operation table, and obtain the invoice identifier of the fourth packing list; wherein the fourth packing list is a packing list for which an invoice document has been prepared but the invoice document has not been reviewed.

[0154] As an example, the packing lists whose second node status is that the invoice documents have been prepared but the invoice documents have not been reviewed can be determined from the operation table updated in step 302, and these packing lists can be determined as the fourth packing lists; the RPA system simulates manual operation to log in to the invoice management system, and queries the invoice identification of the fourth packing list according to the identification of the fourth packing list.

[0155] Step 304, simulating manual operation to log into the invoice management system to query the review status of the invoice corresponding to the invoice identifier of the fourth packing list, and update the second node status information of the fourth packing list.

[0156] That is to say, after the reviewer reviews the invoice file to be reviewed, the review status of the corresponding invoice file in the invoice management system will be updated, so the second node status information of the fourth packing list can be updated by querying the review status of the invoice file corresponding to the invoice identifier of the fourth packing list. In this way, there is no need to frequently query the review status of the invoice, and only the second node status information of the fourth packing list of the invoice file that has been reviewed and approved in this round of query can be updated.

[0157] For example, if after query, the invoice file review status corresponding to the invoice identifier of a fourth packing list is updated to reviewed, then the second node status information of the fourth packing list is updated to the invoice file has been reviewed and the invoice file has not been downloaded; if the invoice file review status corresponding to the invoice identifier of a fourth packing list is still not reviewed, there is no need to update the second node status information of the fourth packing list.

[0158] Step 305, based on the second node status information in the operation table, determine the fifth packing list from the operation table, and obtain the invoice identifier of the fifth packing list; wherein the fifth packing list is a packing list whose invoice file has been reviewed and the invoice file has not been downloaded, and a packing list whose invoice file does not need to be reviewed and the invoice file has not been downloaded.

[0159] As an example, you can obtain the packing list whose second node status information is that the invoice file has been reviewed and the invoice file has not been downloaded, and the packing list whose second node status information is that the invoice file does not need to be reviewed and the invoice file has not been downloaded from the operation table updated after step 304, and use these packing lists as the fifth packing list; manually simulate the operation to log in to the invoice management system, and obtain the invoice identification of the fifth packing list through the identification of the fifth packing list.

[0160] Step 306, simulating manual operation to log into the invoice management system to download the invoice file corresponding to the invoice identifier of the fifth packing list, and updating the second node status information of the fifth packing list.

[0161] Usually, when downloading invoice files, the system can support the simultaneous downloading of corresponding certificates of origin and other related documents. This can be determined based on the needs of the actual business scenario.

[0162] According to the logistics export order processing method combining RPA and AI in the embodiment of the present application, in the process of downloading the invoice file, based on the invoice file production sub-node, the invoice file review sub-node and the invoice file download sub-node, the RPA system updates the second node status after executing each sub-node, and executes the next node based on the updated operation table. That is to say, after each round is triggered, the RPA system can process the invoices corresponding to all packing lists that meet the conditions in this round, thereby further improving the processing efficiency and timeliness of logistics export orders.

[0163] Since there may be a delay in the automatic generation of invoices by the system, in order to further improve the efficiency of the execution of the invoice download node, the invoice file download node may also include an invoice generation sub-node.

[0164] Figure 4 FIG. 1 is a flowchart of another invoice downloading process in an embodiment of the present application. Figure 4 As shown, based on the above embodiments, Figure 2 Step 202 may include the following steps:

[0165] Step 401, based on the first node status information and the second node status information in the operation table, determine the sixth packing list from the operation table; wherein the sixth packing list is a packing list for which the content information of the packing list has been downloaded and the invoice mark has not been generated.

[0166] It can be understood that the invoice file download node also includes an invoice identifier generation subnode, and the execution status of the subnode is also reflected in the second node status information. For example, if the invoice identifier of a packing list has not been generated, then its second node status information is the invoice identifier not generated state; if the invoice identifier of a packing list has been generated and the invoice file has not been produced, then its second node status information is the invoice identifier generated and the invoice file has not been produced state. Therefore, the sixth packing list with the second node status information of the invoice identifier not generated state can be obtained from the operation table.

[0167] Step 402, simulating manual operation to log into the invoice management system to query whether the sixth packing list has generated an invoice ID.

[0168] Step 403: If the invoice identifier of the sixth packing list has been generated, the invoice identifier of the sixth packing list is obtained, the invoice identifier of the sixth packing list is written into the operation table, and the second node status information of the sixth packing list is updated.

[0169] It can be understood that since the subsequent steps all require the invoice identification of the packing list, the invoice identification of the sixth packing list is obtained in batches in the invoice management system through the identification of the sixth packing list, and the respective invoice identifications are written into the operation table. In the subsequent steps 404, 406, and 408, the invoice identification of the corresponding packing list can be directly obtained in the operation table to avoid repeated queries of the invoice identification, thereby improving the efficiency of the RPA system processing process.

[0170] Step 404: Based on the second node status information in the operation table, determine from the operation table the third packing list for which an invoice identifier has been generated but an invoice document has not been prepared, and obtain the invoice identifier of the third packing list.

[0171] Step 405, performing image recognition on the invoice management system based on artificial intelligence AI technology, simulating manual operation to log into the invoice management system to produce an invoice file corresponding to the invoice identifier of the third packing list, and updating the second node status information of the third packing list.

[0172] Step 406, based on the second node status information in the operation table, determine the fourth packing list from the operation table, and obtain the invoice identifier of the fourth packing list; wherein the fourth packing list is a packing list for which an invoice document has been prepared but the invoice document has not been reviewed.

[0173] Step 407, simulating manual operation to log into the invoice management system to query the review status of the invoice corresponding to the invoice identifier of the fourth packing list, and update the second node status information of the fourth packing list.

[0174] Step 408, based on the second node status information in the operation table, determine the fifth packing list from the operation table, and obtain the invoice identifier of the fifth packing list; wherein the fifth packing list is a packing list for which the invoice file has been reviewed and the invoice file has not been downloaded, and a packing list for which the invoice file does not need to be reviewed and the invoice file has not been downloaded.

[0175] Step 409, simulating manual operation to log into the invoice management system to download the invoice file corresponding to the invoice identifier of the fifth packing list, and updating the second node status information of the fifth packing list.

[0176] According to the logistics export order processing method combining RPA and AI in the embodiment of the present application, the invoice generation status is queried for the packing list for which the invoice identification has not been generated, and the invoice identification corresponding to the packing list for which the invoice identification has been generated is written into the operation table. In this way, the corresponding invoice identification can be directly obtained in the operation table in subsequent steps, thereby avoiding repeated queries on the invoice identification, thereby further improving the processing efficiency of the logistics export order.

[0177] Next, the implementation process of the invoice file verification node will be introduced in detail. In the embodiment of the present application, based on the processing flow of the logistics export order, the invoice file verification node may include an invoice file upload subnode, an invoice file feedback subnode and an invoice file verification subnode. Among them, the invoice file upload subnode refers to the process of uploading the invoice file or the package file containing the invoice file, the invoice file feedback subnode refers to the feedback stage of the recipient of the invoice file, and the invoice file verification subnode refers to the process of verifying the invoice file based on the invoice file and the feedback file of the recipient.

[0178] Figure 5 FIG. 1 is a flow chart of an invoice file verification process in an embodiment of the present application. Figure 5 As shown, for the above embodiment Figure 2 The implementation of step 204 may include the following steps:

[0179] Step 501, based on the second node status information and the third node status information in the operation table, determine the seventh packing list from the operation table, obtain the third invoice file of the seventh packing list and the packing list content information corresponding to the third invoice file; wherein the seventh packing list is a packing list for which the invoice file has been downloaded but the invoice file has not been uploaded.

[0180] In some embodiments of the present application, the invoice file verification node may include an invoice file upload subnode, an invoice file feedback subnode, and an invoice file verification subnode, and the status of each subnode is reflected in the third node status information. As an example, if the invoice file of a packing list is not uploaded, the third node status information of the packing list is the invoice file not uploaded state; if the invoice file of a packing list has been uploaded, and the recipient has not yet provided feedback on the invoice file, the third node status information of the packing list is the invoice file uploaded and no feedback state; if the invoice file recipient of a packing list has provided feedback on the invoice file, but has not yet verified the invoice file, the third node status information of the packing list is the feedback and invoice file unverified state; if the invoice file of a packing list has been verified, the third node status of the packing list is the invoice file verified state. In this way, the seventh packing list whose second node status information is the invoice file downloaded state and the third node status information is the invoice file not uploaded state can be obtained from the operation table updated in step 203.

[0181] In some embodiments of the present application, the third invoice file of the seventh packing list refers to the invoice file of the seventh packing list, and the invoice file can be obtained from the downloaded invoice file according to the preset storage path. Since each invoice file can correspond to one packing list or multiple packing lists, the corresponding relationship between the third invoice file and the packing list can be obtained based on the operation table to determine the identifier of the packing list corresponding to each third invoice file, and then the content information of the packing list corresponding to the third invoice file can be obtained from the content information of the downloaded packing list according to the preset storage path.

[0182] Step 502: Perform image recognition on the file management system based on artificial intelligence (AI) technology, simulate manual operation to log into the file management system, package the third invoice file and the packing list content information corresponding to the third invoice file and upload them to the file management system, and update the third node status information of the seventh packing list.

[0183] In an embodiment of the present application, the file management system can be a system for transferring files between the receiver and the sender of a logistics export order. It should be noted that if other related files are downloaded together with the invoice file, the third invoice file, the content information of the packing list corresponding to the third invoice file, and other related files corresponding to the third invoice file can also be packaged and uploaded to the file management system. Among them, updating the third node status information of the seventh packing list can be to update the third node status information of the seventh packing list to the state that the invoice file has been uploaded and there is no feedback.

[0184] Step 503, based on the third node status information in the operation table, determine the eighth packing list from the operation table, and obtain the invoice identifier of the eighth packing list; wherein the eighth packing list is a packing list for which the invoice file has been uploaded and has no feedback status.

[0185] That is, from the operation table updated in step 502, it is determined that the third node status information is the eighth packing list for which the invoice file has been uploaded and there is no feedback status.

[0186] Step 504, simulating manual operation to log into the file management system to query the feedback status of the fourth invoice file corresponding to the invoice identifier of the eighth packing list.

[0187] In actual business scenarios, after receiving the invoice file and other related documents, the recipient of the invoice file can review these documents and upload the feedback file to the file management system to inform the sender of the invoice file. Therefore, during this round of processing, the RPA system can query the feedback status of the fourth invoice file corresponding to the invoice ID of the eighth packing list in the file management system, and promptly process the logistics export order corresponding to the fourth invoice file that has been fed back.

[0188] Step 505: If the fourth invoice file has been fed back, the third node status information of the eighth packing list is updated.

[0189] As an example, if the fourth invoice file has been fed back, the third node status information of the eighth packing list may be updated to a state where the invoice file has been fed back but has not been verified.

[0190] Step 506, based on the third node status information in the operation table, determine the ninth packing list from the operation table, obtain the invoice ID of the ninth packing list, and simulate manual login to the file management system to download the feedback file corresponding to the invoice ID; wherein the ninth packing list is a packing list that has been fed back and the invoice file has not been verified.

[0191] That is to say, from the operation table updated in step 505, determine that the ninth packing list has the third node status information of feedback and the invoice file has not been verified, read the invoice ID of the ninth packing list in the operation table, or simulate manual login to the invoice management system to query the invoice ID of the ninth packing list, and simulate manual login to the file management system to download the feedback file corresponding to the invoice ID of the ninth packing list.

[0192] Step 507, obtain the fifth invoice file corresponding to the invoice identifier of the ninth packing list, and obtain the actual amount and the feedback amount of the fifth invoice file based on the fifth invoice file and the feedback file, and compare the actual amount with the feedback amount to verify whether the two are consistent, obtain the verification result, and update the third node status information of the ninth packing list.

[0193] In an embodiment of the present application, the actual amount of the fifth invoice file can be obtained in the file management system, and then based on the natural language processing (NLP) technology in the artificial intelligence (AI) technology, the text information in the feedback file is processed to obtain the feedback amount of the fifth invoice file, and then the feedback amount is compared with the actual amount to obtain the corresponding verification result.

[0194] Step 508: If the verification result shows that the actual amount is consistent with the feedback amount, the logistics export order corresponding to the fifth invoice document is shipped.

[0195] In some embodiments of the present application, the correspondence between the invoice document and the logistics export order can be determined by querying the correspondence between the logistics export order and the packing list in the logistics management system, and then determining the correspondence between the packing list and the invoice document according to the invoice management system. In addition, the correspondence between the invoice document and the logistics export order can also be determined directly in the file management system.

[0196] In some embodiments of the present application, after the verification is completed, the ledger information can also be generated in the following ways: based on the natural language processing (NLP) technology in the artificial intelligence (AI) technology, the text information in the feedback file is processed to obtain the logistics information of the logistics export order corresponding to the fifth invoice file; wherein the logistics information of the logistics export order can be the carrier airline of the logistics export order, etc.; according to the verification results and logistics information, the ledger information is generated. The ledger information may include the logistics export order identification, invoice identification, amount, packing list identification, verification results, logistics information, etc. corresponding to the fifth invoice file. The RPA system can store the generated ledger information in a preset storage location, and can also send the generated ledger information to relevant business personnel in the form of email.

[0197] According to the logistics export order processing method combining RPA and AI in the embodiment of the present application, the RPA system obtains the invoice files of the packing list of the corresponding status step by step based on the second node status information and the third node status information in the operation table, based on the invoice file upload sub-node, invoice file feedback sub-node and invoice file verification sub-node in the invoice file verification node, and performs invoice file upload, invoice file feedback status query and invoice file verification in sequence. This allows the RPA system to process all invoice files that meet the conditions in this round after each round is triggered, thereby further improving the processing efficiency and timeliness of logistics export orders.

[0198] It should be noted that each time the RPA system is triggered to execute the above-mentioned logistics export order processing method, execution abnormalities may occur due to network abnormalities, electronic equipment service abnormalities, etc. In some embodiments of the present application, a retry mechanism can be set for the RPA system. For example, a three-time retry mechanism is preset. When an error occurs when the RPA system processes the logistics export order, the corresponding processing steps can be re-executed. If no error is reported within three times, the subsequent process will continue to be executed. Otherwise, the corresponding error interface can be screenshotted and sent to the relevant staff by email.

[0199] To facilitate the understanding of the above embodiment, the following will introduce the processing process of a logistics export order by a certain round of RPA system by way of example, as follows:

[0200] (1) The RPA system queries whether the target email exists in the mailbox. If the target email exists, the RPA system obtains the packing list number of the logistics export order in the target email and writes the packing list number into the operation table. The operation table records multiple packing list numbers and the node status corresponding to each packing list number. The node status is represented by different status fields, as shown in Table 1 below. The field PLFile is empty, indicating that the content information of the packing list has not been downloaded. The field PLFile = Y, indicating that the content information of the packing list has been downloaded. The field InvoiceNo. is empty, indicating that the invoice number of the packing list has not been generated. The field InvoiceNo. = Invoice Number, indicating that the invoice number of the packing list has been generated. The field Invoice is empty, indicating that the invoice file of the packing list has not been prepared. The field Invoice is Y, indicating that the invoice file of the packing list has been prepared. The item has been produced; the field WaitCheck is N, indicating that the invoice file of the packing list does not need to be reviewed; WaitCheck is W, indicating that the invoice file of the packing list has not been reviewed; WaitCheck is Y, indicating that the invoice file of the packing list has been reviewed; the field InvoiceDown is empty, indicating that the invoice file of the packing list has not been downloaded; the field InvoiceDown is Y, indicating that the invoice file of the packing list has been downloaded; the field InvoiceUp is empty, the invoice file has not been uploaded, the field InvoiceUp is Y, and the invoice file has been uploaded; the field WaitConfirm is empty, indicating that no feedback has been given; the field WaitConfirm is Y, indicating that feedback has been given; Down is empty, indicating that the invoice file has not been verified; Down is Y, indicating that the invoice file has been verified.

[0201] Table 1 Description of the node status field corresponding to each packing list in the operation table

[0202]

[0203] (2) The RPA system reads the content information in the operation table, obtains the packing list number whose field PLFile is empty, and downloads the content information of the corresponding packing list in batches in the logistics management system, and sets the field PLFile corresponding to these packing list numbers to Y;

[0204] (3) The RPA system determines the packing slip numbers whose field PLFile=Y and InvoiceNo. is empty in the operation table, and queries the invoice management system to see whether the invoice numbers for these packing slip numbers have been generated. If the invoice numbers have been generated, the generated invoice numbers are written into the corresponding field InvoiceNo.;

[0205] (3) The RPA system identifies the packing slips whose InvoiceNo. field is not empty and whose Invoice field is empty in the operation table, obtains the corresponding invoice number, creates an invoice file in the invoice management system, and sets the Invoice status field of these packing slips to Y;

[0206] (4) The RPA system determines whether the invoice document produced in step (3) needs to be reviewed. If it needs to be reviewed, the status field WaitCheck of the corresponding packing list is set to W, and the invoice management system is submitted for review. If it does not need to be reviewed, the status field WaitCheck of the corresponding packing list is set to N.

[0207] (5) The RPA system determines the packing list with the fields Invoice = Y and WaitCheck = W in the operation table, obtains the corresponding invoice number in the field InvoiceNo., and queries the review status of these invoice numbers in the invoice management system. If they have been reviewed, the corresponding status field WaitCheck is set to Y;

[0208] (6) The RPA system identifies the packing lists in the operation table where the field InvoiceDown is empty and WaitCheck = N and the field InvoiceDown is empty and WaitCheck = Y, obtains the corresponding invoice number in the field InvoiceNo., downloads the invoice files corresponding to these invoice numbers in the invoice management system, downloads the corresponding documents such as the certificate of origin, and sets the corresponding status field InvoiceDown to Y;

[0209] (7) The RPA system identifies the packing lists whose fields InvoiceDown = Y and InvoiceUp are empty in the operation table, uploads the invoice files, content information files of the packing lists, and other related files to the file management system, and sets the status field InvoiceUp to Y;

[0210] (8) The RPA system identifies the packing lists in the operation table where the field InvoiceUp = Y and the WaitConfirm is empty, obtains the corresponding invoice number in the field InvoiceNo., and queries the feedback status of these invoices in the file management system. If feedback has been received, the status field WaitConfirm is set to Y;

[0211] (9) The RPA system identifies the packing lists in the operation table where the field WaitConfirm = Y and the Done field is empty, obtains the corresponding invoice number in the InvoiceNo. field, queries the file management system for the corresponding feedback files of these invoice files, compares the amount in the invoice file with the amount in the feedback file to determine whether the two are consistent, and generates a ledger based on the comparison result, setting the status field Done of the corresponding packing list to Y.

[0212] In order to implement the above embodiments, the present application provides a logistics export order processing device that combines RPA and AI.

[0213] Figure 6 This is a structural block diagram of a logistics export order processing device that combines RPA and AI provided in an embodiment of the present application. The device is applied to a robotic process automation (RPA) system, and the logistics export order processing process includes a packing list information content download node, an invoice file download node, and an invoice file verification node. Figure 6 As shown, the device comprises:

[0214] The reading module 610 is used to periodically read the content information of the operation table, wherein the operation table contains the identifiers of the packing lists of the respective logistics export orders and the first node status information, the second node status information and the third node status information of each packing list; the first node status information is used to indicate whether the content information of the packing list has been downloaded; the second node status information is used to indicate whether the invoice file of the packing list has been downloaded; and the third node status information is used to indicate whether the invoice file of the packing list has been verified;

[0215] A download module 620 is used to download the content information of the first packing list and the invoice file of the second packing list in sequence based on the first node status information and the second node status information in the operation table each time the content information of the operation table is read;

[0216] The determination module 630 is used to determine whether to verify the invoice document according to the second node status information and the third node status information in the operation table, and obtain the verification result when verifying the invoice document, and determine whether to ship the logistics export order corresponding to the invoice document according to the verification result.

[0217] In some embodiments of the present application, the download module 620 includes:

[0218] The first downloading unit 621 is used to determine the first packing list from the operation table based on the first node status information in the operation table, download the content information of the first packing list, and update the first node status information of the first packing list; wherein the first packing list is a packing list for which the content information of the packing list has not been downloaded;

[0219] The second downloading unit 622 is used to determine the second packing list from the operation table based on the first node status information and the second node status information in the operation table, download the invoice file of the second packing list, and update the second node status information of the second packing list; wherein the second packing list is a packing list for which the packing list content information has been downloaded but the invoice file has not been downloaded.

[0220] As an implementation manner, the second downloading unit 622 is specifically used for:

[0221] Based on the first node status information and the second node status information in the operation table, determine the third packing list from the operation table, and obtain the invoice identifier of the third packing list; wherein the third packing list is a packing list for which the packing list content information has been downloaded and the invoice has not been generated;

[0222] Perform image recognition on the invoice management system based on artificial intelligence (AI) technology, simulate manual operation to log into the invoice management system to create an invoice file corresponding to the invoice identifier of the third packing list, and update the second node status information of the third packing list;

[0223] Based on the second node status information in the operation table, determine the fourth packing list from the operation table, and obtain the invoice identifier of the fourth packing list; wherein the fourth packing list is a packing list for which an invoice document has been prepared but the invoice document has not been reviewed;

[0224] Simulate manual operation to log in to the invoice management system to query the review status of the invoice corresponding to the invoice identifier of the fourth packing list, and update the second node status information of the fourth packing list;

[0225] Based on the second node status information in the operation table, determine the fifth packing list from the operation table, and obtain the invoice identifier of the fifth packing list; wherein the fifth packing list is a packing list for which the invoice file has been reviewed and the invoice file has not been downloaded, and a packing list for which the invoice file does not need to be reviewed and the invoice file has not been downloaded;

[0226] The invoice management system is logged in to simulate manual operation to download the invoice file corresponding to the invoice identifier of the fifth packing list, and the second node status information of the fifth packing list is updated.

[0227] As an implementation manner, the second downloading unit 622 is further configured to:

[0228] Based on the first node status information and the second node status information in the operation table, determining a sixth packing list from the operation table; wherein the sixth packing list is a packing list for which the packing list content information has been downloaded and the invoice mark has not been generated;

[0229] Simulate manual operation to log in to the invoice management system to check whether the invoice ID has been generated for the sixth packing list;

[0230] If the invoice ID of the sixth packing list has been generated, the invoice ID of the sixth packing list is obtained, the invoice ID of the sixth packing list is written into the operation table, and the second node status information of the sixth packing list is updated;

[0231] Based on the second node status information in the operation table, a third packing list for which an invoice identifier has been generated but an invoice document has not been prepared is determined from the operation table, and the invoice identifier of the third packing list is obtained.

[0232] In some embodiments of the present application, the second downloading unit 622 is further used to:

[0233] If the first invoice file needs to be reviewed after it is produced, the second node status information of the third packing list corresponding to the first invoice file is updated to the state that the invoice file has been produced but the invoice file has not been reviewed, and the first invoice file is submitted to the invoice management system for review;

[0234] If the prepared second invoice document does not need to be reviewed, the second node status information of the third packing list corresponding to the second invoice document is updated to indicate that the invoice document has been prepared and does not need to be reviewed.

[0235] As an implementation manner, the determination module 630 is specifically configured to:

[0236] Based on the second node status information and the third node status information in the operation table, determine the seventh packing list from the operation table, and obtain the third invoice file of the seventh packing list and the content information of the packing list corresponding to the third invoice file; wherein the seventh packing list is a packing list for which the invoice file has been downloaded but the invoice file has not been uploaded;

[0237] Perform image recognition on the file management system based on artificial intelligence (AI) technology, simulate manual operation to log into the file management system, package the information content of the third invoice file and the packing list corresponding to the third invoice file and upload them to the file management system, and update the third node status information of the seventh packing list;

[0238] Based on the third node status information in the operation table, determine the eighth packing list from the operation table, and obtain the invoice identifier of the eighth packing list; wherein the eighth packing list is a packing list for which the invoice file has been uploaded and has no feedback status;

[0239] Simulate manual operation to log in to the file management system to query the feedback status of the fourth invoice file corresponding to the invoice ID of the eighth packing list;

[0240] If the fourth invoice file has been fed back, the third node status information of the eighth packing list is updated;

[0241] Based on the third node status information in the operation table, determine the ninth packing list from the operation table, obtain the invoice ID of the ninth packing list, and simulate manual login to the file management system to download the feedback file corresponding to the invoice ID; wherein the ninth packing list is a packing list that has been fed back and the invoice file has not been verified;

[0242] Obtain the fifth invoice file corresponding to the invoice identifier of the ninth packing list, and obtain the actual amount and the feedback amount of the fifth invoice file according to the fifth invoice file and the feedback file, and compare the actual amount with the feedback amount to verify whether the two are consistent, obtain a verification result, and update the third status information of the ninth packing list;

[0243] If the verification result shows that the actual amount is consistent with the feedback amount, the logistics export order corresponding to the fifth invoice document will be shipped.

[0244] In some embodiments of the present application, the determination module 630 is further configured to:

[0245] Get the actual amount of the fifth invoice document;

[0246] The natural language processing (NLP) technology in artificial intelligence (AI) technology is used to process the text information in the feedback file to obtain the feedback amount of the fifth invoice file.

[0247] In some embodiments of the present application, the apparatus further includes a generating module 640, and the generating module 640 is used to:

[0248] Based on the natural language processing (NLP) technology in artificial intelligence (AI) technology, the text information in the feedback file is processed to obtain the logistics information of the logistics export order corresponding to the fifth invoice file;

[0249] Generate ledger information based on verification results and logistics information.

[0250] As an implementation manner, the device further includes a writing module 650, and the writing module 650 is used to:

[0251] Before regularly reading the content information of the operation table, query whether the target email exists in the mailbox;

[0252] In response to the existence of the target mail in the mailbox, an identifier of the packing list of the logistics export order in the target mail is obtained, and the packing list identifier is written into the operation table.

[0253] According to the logistics export order processing device combined with RPA and AI of the present application, the operation table recording the packing list identification and node status of each of the multiple logistics export orders is read regularly by the robot process automation RPA system, and each time it is read, based on the first node status information and the second node status information in the operation table, the content information of the first packing list and the invoice file of the second packing list are downloaded in sequence, and according to the second node status information and the third node status information, it is determined whether to verify the invoice file, and based on the verification result, it is determined whether to ship the logistics export order corresponding to the invoice file. This solution uses the robot process automation RPA system to execute the entire order processing process, which can avoid manual repetitive operations, thereby greatly reducing labor costs. In addition, since the RPA system can execute order processing regularly throughout the day, it can avoid the problem of untimely order processing due to time differences and working hours, and can also improve the efficiency of order processing.

[0254] The functions of each module in the device of the embodiment of the present application can be found in the corresponding description in the above method, and will not be repeated here.

[0255] Figure 7 The structure block diagram of an electronic device for implementing a logistics export order processing method combining RPA and AI according to an embodiment of the present application is shown. Figure 7 As shown, the device includes: a memory 710 and a processor 720, wherein the memory 710 stores a computer program that can be run on the processor 720. When the processor 720 executes the computer program, the logistics export order processing method combining RPA and AI in the above embodiment is implemented. The number of the memory 710 and the processor 720 can be one or more.

[0256] The electronic device also includes:

[0257] The communication interface 730 is used to communicate with external devices and perform data exchange transmission.

[0258] If the memory 710, the processor 720 and the communication interface 730 are implemented independently, the memory 710, the processor 720 and the communication interface 730 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0259] Optionally, in a specific implementation, if the memory 710, the processor 720 and the communication interface 730 are integrated on a chip, the memory 710, the processor 720 and the communication interface 730 can communicate with each other through an internal interface.

[0260] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present application when the program is executed by a processor.

[0261] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.

[0262] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).

[0263] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0264] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0265] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0266] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0267] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0268] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0269] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0270] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A logistics export order processing method combining RPA and AI, characterized in that: Applied to a robotic process automation (RPA) system, the method includes: Periodically read the content information of the operation table, wherein the operation table contains the identification of the packing lists of the respective logistics export orders and the first node status information, the second node status information and the third node status information of each of the packing lists; the first node status information is used to indicate whether the content information of the packing list has been downloaded; the second node status information is used to indicate whether the invoice file of the packing list has been downloaded; the third node status information is used to indicate whether the invoice file of the packing list has been verified; the operation table is a form used to indicate the processing progress of the logistics export order; Each time the content information of the operation table is read, based on the first node status information and the second node status information in the operation table, the content information of the first packing list and the invoice file of the second packing list are downloaded in sequence; Determine whether to verify the invoice document according to the second node status information and the third node status information in the operation table, obtain the verification result when verifying the invoice document, and determine whether to ship the logistics export order corresponding to the invoice document according to the verification result; Before the periodic reading of the content information of the operation table, the method further includes: Check whether the target email exists in the mailbox; In response to the existence of the target mail in the mailbox, an identifier of a packing list of the logistics export order in the target mail is obtained, and the packing list identifier is written into the operation table.

2. The method according to claim 1, characterized in that: The downloading of the content information of the first packing list and the invoice file of the second packing list in sequence based on the first node status information, the second node status information and the process in the operation table includes: Based on the first node status information in the operation table, determining the first packing list from the operation table, downloading the content information of the first packing list, and updating the first node status information of the first packing list; wherein the first packing list is a packing list without downloading the packing list content information; Based on the first node status information and the second node status information in the operation table, the second packing list is determined from the operation table, the invoice file of the second packing list is downloaded, and the second node status information of the second packing list is updated; wherein the second packing list is a packing list for which the packing list content information has been downloaded but the invoice file has not been downloaded.

3. The method according to claim 2, characterized in that The determining the second packing list from the operation table based on the first node status information and the second node status information in the operation table, downloading the invoice file of the second packing list, and updating the second node status information of the second packing list includes: Based on the first node status information and the second node status information in the operation table, determine a third packing list from the operation table, and obtain an invoice identifier of the third packing list; wherein the third packing list is a packing list for which the packing list content information has been downloaded and for which an invoice document has not been generated; Performing image recognition on the invoice management system based on artificial intelligence (AI) technology, simulating manual operation to log into the invoice management system to produce an invoice file corresponding to the invoice identifier of the third packing list, and updating the second node status information of the third packing list; Based on the second node status information in the operation table, determine the fourth packing list from the operation table, and obtain the invoice identifier of the fourth packing list; wherein the fourth packing list is a packing list for which an invoice document has been prepared but the invoice document has not been reviewed; Simulate manual operation to log in to the invoice management system to query the review status of the invoice corresponding to the invoice identifier of the fourth packing list, and update the second node status information of the fourth packing list; Based on the second node status information in the operation table, determine the fifth packing list from the operation table, and obtain the invoice identifier of the fifth packing list; wherein the fifth packing list is a packing list for which the invoice file has been reviewed and the invoice file has not been downloaded, and a packing list for which the invoice file does not need to be reviewed and the invoice file has not been downloaded; The invoice management system is logged in to simulate manual operation to download the invoice file corresponding to the invoice identifier of the fifth packing list, and the second node status information of the fifth packing list is updated.

4. The method according to claim 3, characterized in that The determining the third packing list from the operation table based on the first node status information and the second node status information in the operation table, and obtaining the invoice identifier of the third packing list includes: Based on the first node status information and the second node status information in the operation table, determining a sixth packing list from the operation table; wherein the sixth packing list is a packing list for which the packing list content information has been downloaded and the invoice mark has not been generated; Simulate manual operation to log into the invoice management system to query whether the sixth packing list has generated an invoice identifier; If the sixth packing list has generated an invoice identifier, obtain the invoice identifier of the sixth packing list, write the invoice identifier of the sixth packing list into the operation table, and update the second node status information of the sixth packing list; Based on the second node status information in the operation table, a third packing list for which an invoice identifier has been generated but an invoice document has not been prepared is determined from the operation table, and the invoice identifier of the third packing list is obtained.

5. The method according to claim 3, characterized in that: The updating of the second node status information of the third packing list includes: If the first invoice file needs to be reviewed after being produced, the second node status information of the third packing list corresponding to the first invoice file is updated to the state that the invoice file has been produced but the invoice file has not been reviewed, and the first invoice file is submitted to the invoice management system for review; If the prepared second invoice document does not need to be reviewed, the second node status information of the third packing list corresponding to the second invoice document is updated to indicate that the invoice document has been prepared and does not need to be reviewed.

6. The method according to claim 2, characterized in that The determining whether to verify the invoice file according to the second node status information and the third node status information in the operation table, obtaining a verification result when verifying the invoice file, and determining whether to ship the logistics export order corresponding to the invoice file according to the verification result includes: Based on the second node status information and the third node status information in the operation table, determine the seventh packing list from the operation table, and obtain the third invoice file of the seventh packing list and the packing list content information corresponding to the third invoice file; wherein the seventh packing list is a packing list for which the invoice file has been downloaded but the invoice file has not been uploaded; Performing image recognition on the file management system based on artificial intelligence (AI) technology, simulating manual operation to log into the file management system, packaging the third invoice file and the packing list content information corresponding to the third invoice file and uploading them to the file management system, and updating the third node status information of the seventh packing list; Based on the third node status information in the operation table, determine the eighth packing list from the operation table, and obtain the invoice identifier of the eighth packing list; wherein the eighth packing list is a packing list for which the invoice file has been uploaded and has no feedback status; Simulate manual operation to log into the file management system to query the feedback status of the fourth invoice file corresponding to the invoice identifier of the eighth packing list; If the fourth invoice file has been fed back, the third node status information of the eighth packing list is updated; Based on the third node status information in the operation table, determine the ninth packing list from the operation table, obtain the invoice ID of the ninth packing list, and simulate manual login to the file management system to download the feedback file corresponding to the invoice ID; wherein the ninth packing list is a packing list that has been fed back and the invoice file has not been verified; Obtaining the fifth invoice document corresponding to the invoice identifier of the ninth packing list, and obtaining the actual amount and the feedback amount of the fifth invoice document according to the fifth invoice document and the feedback document, and comparing the actual amount with the feedback amount to verify whether the two are consistent, obtaining a verification result, and updating the third node status information of the ninth packing list; If the verification result is that the actual amount is consistent with the feedback amount, the logistics export order corresponding to the fifth invoice document is shipped.

7. The method according to claim 6, characterized in that Also includes: Based on the natural language processing (NLP) technology in artificial intelligence (AI) technology, the text information in the feedback file is processed to obtain the logistics information of the logistics export order corresponding to the fifth invoice file; Generate ledger information based on the verification result and the logistics information.

8. The method according to claim 6, characterized in that The obtaining the actual amount and the feedback amount of the fifth invoice file according to the fifth invoice file and the feedback file includes: Obtaining the actual amount of the fifth invoice document; Based on the natural language processing (NLP) technology in artificial intelligence (AI) technology, the text information in the feedback file is processed to obtain the feedback amount of the fifth invoice file.

9. A logistics export order processing device combining RPA and AI, characterized in that: Applied to a robotic process automation (RPA) system, the device comprises: A reading module is used to periodically read the content information of the operation table, wherein the operation table contains the identification of the packing lists of the respective logistics export orders and the first node status information, the second node status information and the third node status information of each of the packing lists; the first node status information is used to indicate whether the content information of the packing list has been downloaded; the second node status information is used to indicate whether the invoice file of the packing list has been downloaded; the third node status information is used to indicate whether the invoice file of the packing list has been verified; the operation table is a form used to indicate the processing progress of the logistics export order; A download module, configured to download the content information of the first packing list and the invoice file of the second packing list in sequence based on the first node status information and the second node status information in the operation table each time the content information of the operation table is read; a determination module, configured to determine whether to verify the invoice document according to the second node status information and the third node status information in the operation table, and obtain a verification result when verifying the invoice document, and determine whether to ship the logistics export order corresponding to the invoice document according to the verification result; Wherein, the device further comprises: The writing module is used to query whether the target email exists in the mailbox before regularly reading the content information of the operation table; In response to the existence of the target mail in the mailbox, an identifier of a packing list of the logistics export order in the target mail is obtained, and the packing list identifier is written into the operation table.

10. The device according to claim 9, characterized in that The download module includes: A first downloading unit is used to determine the first packing list from the operation table based on the first node status information in the operation table, download the content information of the first packing list, and update the first node status information of the first packing list; wherein the first packing list is a packing list for which the packing list content information is not downloaded; The second downloading unit is used to determine the second packing list from the operation table based on the first node status information and the second node status information in the operation table, download the invoice file of the second packing list, and update the second node status information of the second packing list; wherein the second packing list is a packing list for which the packing list content information has been downloaded but the invoice file has not been downloaded.

11. The device according to claim 10, characterized in that The second downloading unit is specifically used for: Based on the first node status information and the second node status information in the operation table, determine a third packing list from the operation table, and obtain an invoice identifier of the third packing list; wherein the third packing list is a packing list for which the packing list content information has been downloaded and for which an invoice document has not been generated; Performing image recognition on the invoice management system based on artificial intelligence (AI) technology, simulating manual operation to log into the invoice management system to produce an invoice file corresponding to the invoice identifier of the third packing list, and updating the second node status information of the third packing list; Based on the second node status information in the operation table, determine the fourth packing list from the operation table, and obtain the invoice identifier of the fourth packing list; wherein the fourth packing list is a packing list for which an invoice document has been prepared but the invoice document has not been reviewed; Simulate manual operation to log in to the invoice management system to query the review status of the invoice corresponding to the invoice identifier of the fourth packing list, and update the second node status information of the fourth packing list; Based on the second node status information in the operation table, determine the fifth packing list from the operation table, and obtain the invoice identifier of the fifth packing list; wherein the fifth packing list is a packing list for which the invoice file has been reviewed and the invoice file has not been downloaded, and a packing list for which the invoice file does not need to be reviewed and the invoice file has not been downloaded; The invoice management system is logged in to simulate manual operation to download the invoice file corresponding to the invoice identifier of the fifth packing list, and the second node status information of the fifth packing list is updated.

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 8.

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 8 is implemented.

Images