WO2022262114A1 - Rpa and ai combined customs declaration information processing method and processing device - Google Patents

Abstract

The present disclosure provides a robotic process automation (RPA) and AI combined customs declaration information processing method and processing device. The method comprises: performing content recognition on a target customs declaration document on the basis of optical character recognition (OCR) to obtain customs declaration data of a plurality of customs declaration items in the target customs declaration document; for a public item in the plurality of customs declaration items, according to a preset first RPA operation process, inputting customs declaration data of the public item into a corresponding first standard item in a customs declaration interface; querying a commodity identifier from the plurality of customs declaration items; and according to the commodity identifier, determining, from the plurality of customs declaration items, a commodity item associated with the commodity identifier, and inputting customs declaration data of the commodity item into a corresponding second standard item in the customs declaration interface. In this way, the method can improve timeliness, save labor costs, reduce the risk of entry errors, and improve efficiency.

Description

Processing method and processing device combining RPA and AI customs declaration information

Cross References to Related Applications

This disclosure is based on a Chinese patent application with application number 202110667458.2 and a filing date of June 16, 2021, and claims the priority of this Chinese patent application. The entire content of this Chinese patent application is hereby incorporated by reference into this disclosure.

technical field

The present disclosure relates to the technical fields of RPA and AI, and in particular to a processing method and processing device combining RPA and AI for customs declaration information.

Background technique

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

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

In related technologies, the customs declaration personnel of Sinotrans need to declare hundreds of thousands of freight manifests every day, and it is required to input the customs declaration forms with different formats from each consignment company into the unified standard customs declaration form, and the business personnel need to spend a lot of money More human and material resources are invested in this work, resulting in poor timeliness, low efficiency, and error-prone.

Contents of the invention

The present disclosure aims to solve one of the technical problems in the related art at least to a certain extent.

Therefore, the first purpose of this disclosure is to propose a processing method combining RPA and AI customs declaration information, which can improve timeliness, save labor costs, reduce the risk of input errors, and improve efficiency.

The second purpose of the present disclosure is to propose a processing device combining RPA and AI customs declaration information.

The third object of the present disclosure is to provide an electronic device.

A fourth object of the present disclosure is to propose a non-transitory computer-readable storage medium.

A fifth object of the present disclosure is to provide a computer program product.

In order to achieve the above-mentioned purpose, the embodiment of the first aspect of the present disclosure proposes a processing method combining RPA and AI customs declaration information, including the following steps: based on optical character recognition OCR (Optical Character Recognition, optical character recognition) to carry out the content of the target customs declaration document Identification, to obtain the customs declaration data of multiple customs declaration items in the target customs declaration document; the public items in the multiple customs declaration items, according to the preset first robot process automation RPA operation process, the customs declaration of the public items Entering the data into the corresponding first standard entry in the customs declaration interface; querying the commodity identification from the multiple customs declaration entries; according to the commodity identification, determining the commodity entry associated with the commodity identification from the multiple customs declaration entries, And enter the customs declaration data of the commodity item into the second standard item corresponding to the customs declaration interface.

According to the processing method combining RPA and AI customs declaration information according to the embodiment of the present disclosure, content recognition is performed on the target customs declaration document based on optical character recognition (OCR), so as to obtain the customs declaration data of multiple customs declaration items in the target customs declaration document; For public entries, according to the pre-set first robotic process automation RPA operation process, the customs declaration data of public entries is entered into the corresponding first standard entry in the customs declaration interface; the commodity identification is queried from multiple customs declaration entries; according to the commodity identification, from multiple Determine the commodity entry associated with the commodity identifier in the first customs declaration entry, and enter the customs declaration data of the commodity entry into the second standard entry corresponding to the customs declaration interface. Therefore, the method can improve timeliness, save labor costs, reduce the risk of input errors, and improve efficiency.

In addition, the processing method combining RPA and AI customs declaration information proposed in the first aspect of the present disclosure may also have the following additional technical features:

According to an embodiment of the present disclosure, according to the commodity identifier, the commodity item associated with the commodity identifier is determined from the plurality of customs declaration entries, and the customs declaration data of the commodity entry is entered into the corresponding customs declaration interface. The second standard entry includes: querying the relationship between the commodity identifier and the commodity entry according to the commodity identifier; if the commodity entry associated with the commodity identifier is found, according to the preset second RPA operation process, Enter the customs declaration data of the commodity entry into the second standard entry corresponding to the customs declaration interface; if no commodity entry associated with the commodity identifier is found, according to the second standard entry in the customs declaration interface, from the Searching for a customs declaration item with similar semantics among the plurality of customs declaration items is used as the commodity item, and entering the customs declaration data of the commodity item into the second standard item corresponding to the customs declaration interface.

According to an embodiment of the present disclosure, according to the second standard item in the customs declaration interface, searching for customs declaration items with similar semantics from the plurality of customs declaration items as the commodity item includes: searching the customs declaration interface In the second standard entry, determine the semantic similarity with each of the customs declaration entries based on natural language processing NLP; according to the customs declaration entry with the highest semantic similarity, determine the semantic similarity with the second standard entry Product entry.

According to an embodiment of the present disclosure, after querying the commodity identifiers from the multiple customs declaration entries, it further includes: inputting the commodity identifiers into the corresponding standard entries in the customs declaration interface, so as to display all items in the customs declaration interface. Describe the second standard item.

According to an embodiment of the present disclosure, before performing content recognition on the target customs declaration document based on optical character recognition (OCR) to obtain the customs declaration data of multiple customs declaration items in the target customs declaration document, it further includes: according to the target customs declaration document The document type identifies each of the said customs declaration items to be identified.

According to an embodiment of the present disclosure, there are multiple target customs declaration documents, including a customs declaration form; the OCR-based optical character recognition is used to perform content recognition on the target customs declaration document, so as to obtain customs declarations of multiple customs declaration items in the target customs declaration document The data includes: performing content identification on the customs declaration form based on OCR, so as to obtain customs declaration data of multiple customs declaration items contained in the customs declaration form.

According to an embodiment of the present disclosure, according to the commodity identifier, the commodity item associated with the commodity identifier is determined from the plurality of customs declaration entries, and the customs declaration data of the commodity entry is entered into the corresponding customs declaration interface. After the second standard item, it also includes: if there is the first standard item and/or the second standard item not entered in the customs declaration interface, based on OCR, the rest of the customs declaration form Target customs declaration documents for content identification.

In order to achieve the above purpose, the embodiment of the second aspect of the present disclosure proposes a processing device combining RPA and AI customs declaration information, including: a first recognition module, used to perform content recognition on the target customs declaration document based on optical character recognition (OCR), to obtain The customs declaration data of multiple customs declaration entries in the target customs declaration document; the first entry module is used to use the public entries in the multiple customs declaration entries according to the preset first robotic process automation RPA operation process, and transfer the public entries The customs declaration data of the entry is entered into the corresponding first standard entry in the customs declaration interface; the query module is used to query the commodity identification from the multiple customs declaration entries; the second input module is used to select from the multiple Determine the commodity entry associated with the commodity identifier in the first customs declaration entry, and enter the customs declaration data of the commodity entry into the second standard entry corresponding to the customs declaration interface.

According to the processing device combining RPA and AI customs declaration information according to an embodiment of the present disclosure, the first recognition module performs content recognition on the target customs declaration document based on optical character recognition (OCR), so as to obtain the customs declaration data of multiple customs declaration items in the target customs declaration document, and through the second An input module inputs the public items among the multiple customs declaration items into the corresponding first standard item in the customs declaration interface according to the pre-set first robotic process automation RPA operation process, and uses the query module to select from multiple items The commodity identification is queried in the customs declaration entry, and the commodity entry associated with the commodity identification is determined from the multiple customs declaration entries through the second input module according to the commodity logo, and the customs declaration data of the commodity entry is entered into the second standard entry corresponding to the customs declaration interface. Therefore, the device can improve timeliness, save labor costs, reduce the risk of input errors, and improve efficiency.

In addition, the processing device combining RPA and AI customs declaration information proposed in the second aspect of the present disclosure may also have the following additional technical features:

According to an embodiment of the present disclosure, the second entry module includes: a query unit, configured to query the relationship between the commodity identifier and the commodity entry according to the commodity identifier; In the case of a commodity item associated with the commodity identifier, according to the preset second RPA operation process, the customs declaration data of the commodity entry is entered into the second standard entry corresponding to the customs declaration interface; the second input unit is used to If no commodity item associated with the commodity identifier is found, according to the second standard entry in the customs declaration interface, query a customs declaration entry with similar semantics from the plurality of customs declaration entries as the commodity entry, and Entering the customs declaration data of the commodity item into the second standard item corresponding to the customs declaration interface.

According to an embodiment of the present disclosure, the second entry unit includes: a first determining subunit, configured to determine, based on natural language processing (NLP), the items related to each of the customs declarations for the second standard item in the customs declaration interface. Semantic similarity between items; a second determining subunit, configured to determine commodity items semantically similar to the second standard item according to the customs declaration item with the highest semantic similarity.

According to an embodiment of the present disclosure, the above-mentioned processing device further includes: a display module, configured to enter the commodity identifier into a corresponding standard item in the customs declaration interface, so as to display the second standard item on the customs declaration interface .

According to an embodiment of the present disclosure, the above processing device further includes: a determining module configured to determine each of the customs declaration items to be identified according to the document type of the target customs declaration document.

According to an embodiment of the present disclosure, there are multiple target customs declaration documents, including a customs declaration form; the first identification module includes: an identification unit, configured to perform content identification on the customs declaration form based on OCR, so as to obtain the The customs declaration data of multiple customs declaration items included in the customs declaration form.

According to an embodiment of the present disclosure, the above-mentioned processing device further includes: a second identification module, configured to have the first standard item and/or the second standard item not entered in the customs declaration interface Next, based on OCR, perform content identification on the rest of the target customs declaration documents except the customs declaration form.

To achieve the above purpose, the embodiment of the third aspect of the present disclosure provides an electronic device, including: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores information that can be used by the Instructions executed by at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can execute the above-mentioned processing method combining RPA and AI customs declaration information.

In order to achieve the above purpose, the embodiment of the fourth aspect of the present disclosure proposes a non-transitory computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned processing of combining RPA and AI customs declaration information is realized method.

To achieve the above purpose, the embodiment of the fifth aspect of the present disclosure proposes a computer program product. When the instructions in the computer program product are executed by the processor, the above-mentioned processing method combining RPA and AI customs declaration information is executed.

Additional aspects and advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.

Description of drawings

The above and/or additional aspects and advantages of the present disclosure will become apparent and understandable from the following description of the embodiments in conjunction with the accompanying drawings, wherein:

FIG. 1 is a schematic flow diagram of a processing method combining RPA and AI customs declaration information provided by an embodiment of the present disclosure;

FIG. 2 is a schematic flow diagram of a processing method combining RPA and AI customs declaration information provided by an embodiment of the present disclosure;

Fig. 3 is a schematic flow diagram of a processing method combining RPA and AI customs declaration information provided by a specific embodiment of the present disclosure;

FIG. 4 is an overall business flow chart of a processing method combining RPA and AI customs declaration information provided by a specific embodiment of the present disclosure;

FIG. 5 is a schematic block diagram of a processing device combining RPA and AI customs declaration information provided by an embodiment of the present disclosure;

FIG. 6 shows a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure.

detailed description

Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the drawings, in which the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present disclosure and should not be construed as limiting the present disclosure.

The following describes the processing method, processing device, electronic equipment, non-transitory computer-readable storage medium and computer program product combining RPA and AI customs declaration information according to the embodiments of the present disclosure with reference to the accompanying drawings.

In related technologies, the customs declaration personnel of Sinotrans need to declare hundreds of thousands of freight manifests every day, requiring the customs declaration data of various shipping companies to be input into a unified standard customs declaration form, and the business personnel need to spend a lot of money Human and material resources are invested in this work, and the specific process is as follows: manually check the customs declaration list data, and reply to the supplier's customs declaration data after the verification is correct; manually log in to the customs declaration system according to the data of the customs declaration documents, and the corresponding fields The data needs to be entered into the customs declaration system one by one; the customs declaration system will perform verification according to the entered data, and complete the submission after the verification is passed.

But there are following disadvantages:

① Poor timeliness: Customs declaration personnel have to urge suppliers to submit customs declaration data to Sinotrans every day, otherwise it will easily affect the timeliness of customs declaration. Once the customs declaration is not passed, it will affect the normal process of goods, greatly reduce the transportation efficiency of goods, and also affect the company's Huge occupation and waste of transportation costs;

②Low efficiency: Customs declaration personnel need to collect customs declaration forms every day, and then input them into the customs declaration system according to the customs declaration forms. On the one hand, there are many styles of customs declaration documents, and the fields of each commodity code are in different positions. It is very troublesome to find, and the font is also small , The commodity code is very long, and 3,000 customs declaration forms need to be entered every day. The work tasks are heavy, and the work efficiency and job satisfaction are not high.

③ Error-prone: The staff has to find the corresponding commodity code in many customs declaration forms, and then search for the corresponding code field record, and then enter it into the customs declaration system. As a result, the efficiency is very poor. In fact, the customs declaration personnel can only enter 100 copies per person per day.

In order to solve the above problems, this disclosure proposes a processing method combining RPA and AI customs declaration information, which can improve timeliness, save labor costs, reduce the risk of input errors, and improve efficiency.

FIG. 1 is a schematic flowchart of a processing method combining RPA and AI customs declaration information provided by an embodiment of the present disclosure.

As shown in Figure 1, the processing method of combining RPA and AI customs declaration information in the embodiment of the present disclosure includes the following steps:

S11, performing content recognition on the target customs declaration document based on optical character recognition (OCR), so as to obtain customs declaration data of multiple customs declaration items in the target customs declaration document.

In this embodiment, there may be multiple target customs declaration documents, such as including at least one of customs declaration form, packing list, waybill, various licenses, export collection verification and write-off form, power of attorney, contract, certificate of origin, etc. . The target customs declaration document needs to be of the same quality as the sample, such as a clear scan.

What OCR can do is to recognize the frame line of the target customs declaration document, extract the content of each cell, and return the position of each item in the cell. Among them, what needs to be done for extraction is to structure the frameless table, such as aligning rows and columns to extract structured information. It should be noted that during the extraction process, if the unit of measurement of an object in the target customs declaration document is different, normalization processing is required, that is, the unit of measurement is unified. Based on the extracted results, it is necessary to ensure that the documents (such as customs declaration, packing list, waybill, export foreign exchange verification and write-off form) are consistent, and the documents (customs declaration, packing list, waybill, export foreign exchange collection verification and write-off form and various license, certificate of origin), and the documents (customs declaration, packing list, waybill, export collection verification and contract).

Multiple customs declaration entries include public entries and commodity entries, where the public entry is a public field extracted through OCR, including at least one of the domestic consignor, overseas consignee, exit customs, export date, declaration date, etc. ; Commodity entries are commodity identifiers and element fields extracted through OCR, wherein the element fields include at least one of brand type, export preference, use, material, brand, specification or model.

S12. Enter the common items among the multiple customs declaration items into the corresponding first standard items in the customs declaration interface according to the preset first robotic process automation RPA operation process.

Among them, the pre-set first robot process automation RPA operation process is the order in which the first robot fills in the customs declaration data of public items, for example, public items such as domestic consignor, overseas consignee, exit customs, export date 1. The customs declaration data of the declaration date is entered into the corresponding first standard entry (public column) in the customs declaration interface. The first standard entry can be shown in Table 1 below.

Table 1

For example, after obtaining the domestic consignor, overseas consignee, exit customs, export date, and declaration date, according to the pre-set first robotic process automation RPA operation process, the domestic consignor and overseas consignee The customs declaration data of , exit customs, export date, and declaration date are entered in the corresponding first standard entry in the customs declaration interface in sequence.

S13. Query commodity identifiers from multiple customs declaration entries.

Commodity identification refers to the collective term of various expressions and instructions used to identify a commodity or its characteristics and performance, for example, it may be a commodity number.

S14. According to the commodity identifier, determine the commodity entry associated with the commodity identifier from the plurality of customs declaration entries, and enter the customs declaration data of the commodity entry into the second standard entry corresponding to the customs declaration interface.

According to the product identification, select the product item associated with the product identification from multiple customs declaration items, such as at least one of brand type, export preference, use, material, brand, specification or model, and submit the specific customs declaration data Enter the second standard entry corresponding to the customs declaration interface, the second standard entry can be shown in Table 2 below.

Table 2

After filling in the first standard entry and the second standard entry, click Generate Table Body Information and fill in the cargo information column, as shown in Table 3 below.

table 3

After completing Form 1, Form 2 and Form 3, the customs declaration form in standard format can be exported.

Therefore, the processing method of customs declaration information combined with RPA and AI in the embodiment of the present disclosure, based on optical character recognition (OCR), performs content recognition on the target customs declaration document to obtain customs declaration data of multiple customs declaration items in the target customs declaration document, and multiple customs declaration items According to the pre-set first robotic process automation RPA operation process, the public entry in the public entry will enter the customs declaration data of the public entry into the corresponding first standard entry in the customs declaration interface, and query the commodity identification from multiple customs declaration entries. According to the commodity identification, A commodity entry associated with the commodity identifier is determined from the multiple customs declaration entries, and the customs declaration data of the commodity entry is entered into a second standard entry corresponding to the customs declaration interface. Therefore, this method can save manual operation steps, save labor costs, greatly improve efficiency, and greatly reduce the work pressure of personnel; because before the need to see with eyes, human errors are prone to occur during the data entry process, and In terms of data review, the system and paper-based document data are often inconsistent, which increases the risk of customs declaration. This disclosure optimizes the process, which reduces the risk to a certain extent and makes the entry error rate controllable.

As an achievable manner, as shown in FIG. 2, the above step S14 may include the following steps:

S21. Query the association relationship between the commodity identifier and the commodity entry according to the commodity identifier.

S22. If the commodity item associated with the commodity identifier is found, according to the preset second RPA operation process, enter the customs declaration data of the commodity item into the second standard entry corresponding to the customs declaration interface.

S23. If the commodity item associated with the commodity identifier is not found, then according to the second standard entry in the customs declaration interface, search for customs declaration entries with similar semantics from multiple customs declaration entries as commodity entries, and enter the customs declaration data of the commodity entries into the corresponding customs declaration interface. in the second standard item.

As an achievable way, according to the second standard entry in the customs declaration interface, search for customs declaration entries with similar semantics as commodity entries from multiple customs declaration entries, including: for the second standard entry in the customs declaration interface, based on natural language processing NLP Determine the semantic similarity with each customs declaration item; determine the commodity item semantically similar to the second standard item according to the customs declaration item with the highest semantic similarity.

It should be noted that in the text classification of natural language processing NLP, the text needs to be segmented first. The original text may consist of hundreds of thousands of Chinese entries, and the latitude is very high. In order to improve the accuracy and efficiency of text classification, the words with little significance for decision-making are generally eliminated first, which is the purpose of feature word extraction.

Specifically, after obtaining the commodity identifier, the relationship between the commodity identifier and the commodity entry is queried from multiple customs declaration entries according to the commodity identifier. Among them, when the commodity entry associated with the commodity identifier can be queried from multiple customs declaration entries, according to the preset second RPA operation process, the specific customs declaration data is entered into the second standard entry corresponding to the interface; When the commodity entry associated with the commodity identifier cannot be found in the customs declaration entry, for the second standard entry in the customs declaration interface, the semantic similarity between the customs declaration entry and each customs declaration entry is determined based on natural language processing NLP, and the customs declaration with the highest semantic similarity is selected entry, as a commodity entry semantically similar to the second standard entry.

In order for the business personnel to clearly understand the second standard item, after querying the commodity identification from the multiple customs declaration items, it also includes: entering the commodity identification into the corresponding standard item in the customs declaration interface, so as to display the second standard item on the customs declaration interface.

In order to quickly identify customs declaration items based on the target customs declaration document and further improve efficiency, content recognition is performed on the target customs declaration document based on optical character recognition (OCR) to obtain the customs declaration data of multiple customs declaration items in the target customs declaration document, including: According to the target The document type of the customs declaration document determines each customs declaration item to be identified.

There are many types of documents that need to be reviewed for customs declaration, such as customs declaration, packing list, waybill, various licenses, export collection verification and write-off form, power of attorney, contract, certificate of origin, etc. Each type of document requires different data to be extracted. Among them, the format of each type of document may be different, and the packaging and unit price of the same product may be different.

For different types of target customs declaration documents, you can first determine the customs declaration items to be identified. For example, when the target customs declaration document is a customs declaration form, determine the customs declaration items to be identified as: domestic consignor, overseas consignee, exit customs Type, export date, declaration date, brand type, export preference, use, material, brand, specification or model; when the target customs declaration document is a contract or invoice, determine the customs declaration items to be identified as: brand, specification or model . In this way, customs declaration items can be identified more quickly based on the target customs declaration documents, further improving efficiency.

Fig. 3 is a schematic flowchart of a processing method combining RPA and AI customs declaration information provided by a specific embodiment of the present disclosure. As shown in Figure 3, when the target customs declaration document includes a customs declaration form, the processing method of combining RPA and AI customs declaration information according to the embodiment of the present disclosure includes the following steps:

S31, performing content recognition on the customs declaration form based on optical character recognition (OCR), so as to obtain customs declaration data of multiple customs declaration items in the target customs declaration document.

S32. Enter the common items among the multiple customs declaration items into the corresponding first standard items in the customs declaration interface according to the preset first robotic process automation RPA operation process.

S33. Query commodity identifiers from multiple customs declaration entries.

S34. According to the commodity identifier, determine the commodity entry associated with the commodity identifier from the plurality of customs declaration entries, and enter the customs declaration data of the commodity entry into the second standard entry corresponding to the customs declaration interface.

It should be noted that, the process of the above-mentioned steps S31-S34 can refer to the above-mentioned steps S11-S14, which will not be detailed here.

S35. If there are unrecorded first standard items and/or second standard items in the customs declaration interface, perform content identification on other target customs declaration documents except the customs declaration form based on OCR.

When the first standard item and/or the second standard item that needs to be entered in the customs declaration interface cannot be found in the customs declaration form, the packing list, waybill, various licenses, and export collection checks other than the customs declaration form can be checked. Content identification of target customs declaration documents such as sales order, power of attorney, contract, certificate of origin, etc., to obtain the first standard item and/or the second standard item that needs to be entered.

In order to make those skilled in the art more clearly understand the processing method of the present disclosure combining RPA and AI customs declaration information, as shown in Figure 4, customers such as customer 1, customer 2, customer 3...etc. send their own company's customs declaration to Sinotrans company. It should be noted that the format of the customs declaration form of each customer may be different, for example, customer 1 uses the customs declaration form 1, customer 2 uses the customs declaration form 2, customer 3 uses the customs declaration form 3, ....

The first robot recognizes the content of the customs declaration form based on optical character recognition (OCR) to extract the public fields and commodity numbers. Among them, the public fields include domestic consignor, overseas consignee, exit customs, export date, declaration date, … The element fields are extracted from the customs declaration form according to the commodity number, where the element fields include brand type, export preference, use, material, .... Then, make a summary and check whether there are customs declaration items that have not been entered into the customs declaration data. If there are still customs declaration items that have not been entered into the customs declaration data, then search for the customs declaration items that have not entered the customs declaration data from the target customs declaration documents other than the customs declaration form. If the customs declaration If the customs declaration data has been entered in the entries, the standard format customs declaration form will be exported.

Therefore, the processing method of customs declaration information combined with RPA and AI in the embodiment of the present disclosure, based on optical character recognition (OCR), performs content recognition on the customs declaration form, so as to obtain the customs declaration data of multiple customs declaration items in the target customs declaration document. According to the pre-set first robotic process automation RPA operation process, the customs declaration data of the public entry is entered into the corresponding first standard entry in the customs declaration interface, and the commodity identification is queried from multiple customs declaration entries. According to the commodity identification, from Determine the commodity entry associated with the commodity identifier among the multiple customs declaration entries, and enter the customs declaration data of the commodity entry into the second standard entry corresponding to the customs declaration interface. If there are unregistered first standard entries and/or second standard entries in the customs declaration interface Items, based on OCR, perform content identification on the rest of the target customs declaration documents except the customs declaration form. Therefore, the method can save manual operation steps and labor costs, greatly improve efficiency, greatly reduce the work pressure of personnel, and control the input error rate.

In order to realize the above embodiments, the present disclosure also proposes a processing device combining RPA and AI customs declaration information.

Fig. 5 is a schematic block diagram of a processing device combining RPA and AI customs declaration information provided by an embodiment of the present disclosure.

As shown in FIG. 5 , the processing device combining RPA and AI customs declaration information in the embodiment of the present disclosure includes: a first identification module 51 , a first entry module 52 , a query module 53 and a second entry module 54 .

Wherein, the first recognition module 51 is configured to perform content recognition on the target customs declaration document based on optical character recognition (OCR), so as to obtain customs declaration data of multiple customs declaration items in the target customs declaration document. The first input module 52 is used to input the public items among the multiple customs declaration items into the corresponding first standard items in the customs declaration interface according to the preset first robotic process automation RPA operation process. The inquiry module 53 is used for inquiring commodity identifiers from multiple customs declaration entries. The second input module 54 is used to determine the commodity item associated with the commodity identifier from multiple customs declaration entries according to the commodity identifier, and enter the customs declaration data of the commodity item into the second standard entry corresponding to the customs declaration interface.

According to an embodiment of the present disclosure, the second input module 54 includes: a query unit, a first input unit and a second input unit. Among them, the query unit is used to query the relationship between the commodity identifier and the commodity entry according to the commodity identifier; the first entry unit is used to query the commodity entry associated with the commodity identifier according to the preset second RPA The operation process is to enter the customs declaration data of the commodity entry into the second standard entry corresponding to the customs declaration interface; the second entry unit is used to, according to the second standard entry in the customs declaration interface, if no commodity entry associated with the commodity identifier is found, Query customs declaration entries with similar semantics from multiple customs declaration entries as commodity entries, and enter the customs declaration data of the commodity entries into the second standard entry corresponding to the customs declaration interface.

According to an embodiment of the present disclosure, the second entry unit includes: a first determination subunit and a second determination subunit. Wherein, the first determining subunit is configured to determine the semantic similarity between the second standard item in the customs declaration interface and each customs declaration item based on natural language processing (NLP). The second determination subunit is configured to determine commodity items semantically similar to the second standard item according to the customs declaration item with the highest semantic similarity.

According to an embodiment of the present disclosure, the above-mentioned processing device combining RPA and AI customs declaration information further includes: a display module, configured to enter the commodity identifier into the corresponding standard item in the customs declaration interface, so as to display the second standard item on the customs declaration interface.

According to an embodiment of the present disclosure, the above-mentioned processing device combining RPA and AI customs declaration information further includes: a determination module configured to determine each customs declaration item to be identified according to the document type of the target customs declaration document.

According to an embodiment of the present disclosure, there are multiple target customs declaration documents, including a customs declaration form; the first identification module 51 includes: an identification unit for performing content identification on the customs declaration form based on OCR, so as to obtain multiple items contained in the customs declaration form; The customs declaration data of the customs declaration item.

According to an embodiment of the present disclosure, the above-mentioned processing device combining RPA and AI customs declaration information further includes: a second identification module, used for unrecorded first standard items and/or second standard items in the customs declaration interface In this case, based on OCR, perform content identification on the rest of the target customs declaration documents except the customs declaration form.

It should be noted that the foregoing explanations of the embodiment of the processing method combining RPA and AI customs declaration information are also applicable to the processing device combining RPA and AI customs declaration information of this embodiment, and details are not repeated here.

According to the processing device combining RPA and AI customs declaration information according to an embodiment of the present disclosure, the first recognition module performs content recognition on the target customs declaration document based on optical character recognition (OCR), so as to obtain the customs declaration data of multiple customs declaration items in the target customs declaration document, and through the second An input module inputs the public items among the multiple customs declaration items into the corresponding first standard item in the customs declaration interface according to the pre-set first robotic process automation RPA operation process, and uses the query module to select from multiple items The commodity identification is queried in the customs declaration entry, and the commodity entry associated with the commodity identification is determined from the multiple customs declaration entries through the second input module according to the commodity logo, and the customs declaration data of the commodity entry is entered into the second standard entry corresponding to the customs declaration interface. Therefore, the device can improve timeliness, save labor costs, reduce the risk of input errors, and improve efficiency.

In order to realize the above-mentioned embodiments, the present disclosure also proposes an electronic device.

An electronic device according to an embodiment of the present disclosure includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to Enabling at least one processor to execute the above-mentioned processing method combining RPA and AI customs declaration information.

In order to realize the above-mentioned embodiments, the present disclosure also proposes a non-transitory computer-readable storage medium.

The non-transitory computer-readable storage medium of the embodiment of the present disclosure stores a computer program thereon, and when the program is executed by a processor, the above-mentioned processing method combining RPA and AI customs declaration information is realized.

In order to realize the above embodiments, the present disclosure also proposes a computer program product.

The computer program product of the embodiment of the present disclosure, when the instructions in the computer program product are executed by the processor, executes the above-mentioned processing method combining RPA and AI customs declaration information.

FIG. 6 shows a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure. The electronic device 12 shown in FIG. 6 is only an example, and should not limit the functions and scope of use of the embodiments of the present disclosure.

As shown in FIG. 6, electronic device 12 takes the form of a general-purpose computing device. Components of electronic device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, bus 18 connecting various system components including system memory 28 and processing unit 16.

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (Industry Standard Architecture; hereinafter referred to as: ISA) bus, Micro Channel Architecture (Micro Channel Architecture; hereinafter referred to as: MAC) bus, enhanced ISA bus, video electronics Standards Association (Video Electronics Standards Association; hereinafter referred to as: VESA) local bus and Peripheral Component Interconnection (hereinafter referred to as: PCI) bus.

Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12 and include both volatile and nonvolatile media, removable and non-removable media.

The memory 28 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (Random Access Memory; hereinafter referred to as: RAM) 30 and/or a cache memory 32 . The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, non-volatile magnetic media (not shown in Figure 7, commonly referred to as "hard drives"). Although not shown in FIG. 7, a disk drive for reading and writing to a removable nonvolatile disk (such as a "floppy disk") may be provided, as well as a disk drive for removable nonvolatile disks (such as a CD-ROM (Compact Disc Read Only Memory; hereinafter referred to as: CD-ROM), Digital Video Disc Read Only Memory (hereinafter referred to as: DVD-ROM) or other optical media). In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present disclosure.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data , each or some combination of these examples may include implementations of network environments. The program modules 42 generally perform the functions and/or methods of the embodiments described in this disclosure.

Electronic device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer system/server 12, and/or Or communicate with any device (eg, network card, modem, etc.) that enables the computer system/server 12 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interface 22 . Moreover, the electronic device 12 can also communicate with one or more networks (such as a local area network (Local Area Network; hereinafter referred to as: LAN), a wide area network (Wide Area Network; hereinafter referred to as: WAN) and/or a public network, such as the Internet, through the network adapter 20. ) communication. As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18 . It should be understood that although not shown, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID (Redundant Arrays of Independent Disks, disk array) systems, tape drives, and data backup storage systems.

The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28 , such as implementing the methods mentioned in the foregoing embodiments.

In the description of this specification, descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific examples", or "some examples" mean that specific features described in connection with the embodiment or example , structure, material or characteristic is included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the described specific features, structures, materials or characteristics may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine different embodiments or examples and features of different embodiments or examples described in this specification without conflicting with each other.

In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

Any process or method descriptions in flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing custom logical functions or steps of a process , and the scope of preferred embodiments of the present disclosure includes additional implementations in which functions may be performed out of the order shown or discussed, including substantially concurrently or in reverse order depending on the functions involved, which shall It is understood by those skilled in the art to which the embodiments of the present disclosure pertain.

The logic and/or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium, For use with instruction execution systems, devices, or devices (such as computer-based systems, systems including processors, or other systems that can fetch instructions from instruction execution systems, devices, or devices and execute instructions), or in conjunction with these instruction execution systems, devices or equipment used. For the purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use in or in conjunction with an instruction execution system, device or device. More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection with one or more wires (electronic device), portable computer disk case (magnetic device), random access memory (RAM), Read Only Memory (ROM), Erasable and Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program can be printed, since the program can be read, for example, by optically scanning the paper or other medium, followed by editing, interpretation or other suitable processing if necessary. The program is processed electronically and stored in computer memory.

It should be understood that various parts of the present disclosure may be implemented in hardware, software, firmware or a combination thereof. In the embodiments described above, various steps or methods may be implemented by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: a discrete Logic circuits, ASICs with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

Those of ordinary skill in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. During execution, one or a combination of the steps of the method embodiments is included.

In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing module, each unit may exist separately physically, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules. If the integrated modules are realized in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, and the like. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations on the present disclosure, and those skilled in the art can understand the above-mentioned embodiments within the scope of the present disclosure. The embodiments are subject to changes, modifications, substitutions and variations.

Claims (17)

A processing method combining RPA and AI customs declaration information, characterized in that it comprises the following steps: performing content recognition on the target customs declaration document based on optical character recognition (OCR), so as to obtain customs declaration data of multiple customs declaration items in the target customs declaration document; Enter the public items in the multiple customs declaration items into the corresponding first standard items in the customs declaration interface according to the preset first robotic process automation RPA operation process; Querying commodity identifiers from the multiple customs declaration entries; According to the commodity identifier, the commodity item associated with the commodity identifier is determined from the plurality of customs declaration entries, and the customs declaration data of the commodity entry is entered into the second standard entry corresponding to the customs declaration interface. The processing method according to claim 1, characterized in that, according to the commodity identifier, the commodity entry associated with the commodity identifier is determined from the multiple customs declaration entries, and the customs declaration data of the commodity entry is Enter the second standard entry corresponding to the customs declaration interface, including: According to the commodity identifier, query the relationship between the commodity identifier and the commodity entry; If the commodity item associated with the commodity identifier is found, according to the preset second RPA operation process, the customs declaration data of the commodity item is entered into the second standard entry corresponding to the customs declaration interface; If the commodity item associated with the commodity identifier is not found, according to the second standard entry in the customs declaration interface, query the customs declaration entry with similar semantics from the multiple customs declaration entries as the commodity entry, and use all The customs declaration data of the commodity item is entered into the second standard item corresponding to the customs declaration interface. The processing method according to claim 2, characterized in that, according to the second standard entry in the customs declaration interface, searching for customs declaration entries with similar semantics from the plurality of customs declaration entries as the commodity entry includes : For the second standard item in the customs declaration interface, determine the semantic similarity with each of the customs declaration items based on natural language processing NLP; According to the customs declaration item with the highest semantic similarity, commodity items semantically similar to the second standard item are determined. The processing method according to claim 2, characterized in that, after querying the commodity identifiers from the multiple customs declaration entries, further comprising: Entering the commodity identifier into the corresponding standard item in the customs declaration interface, so as to display the second standard item in the customs declaration interface. The processing method according to any one of claims 1-4, wherein the OCR-based optical character recognition is used to perform content recognition on the target customs declaration document, so as to obtain the customs declaration data of multiple customs declaration items in the target customs declaration document ,Also includes: According to the document type of the target customs declaration document, each of the customs declaration items to be identified is determined. According to the processing method described in any one of claims 1-4, it is characterized in that there are multiple target customs declaration documents, including a customs declaration form; the content recognition of the target customs declaration document based on optical character recognition OCR is carried out to obtain the Describe the customs declaration data of multiple customs declaration items in the target customs declaration document, including: Content recognition is performed on the customs declaration form based on OCR to obtain customs declaration data of multiple customs declaration items included in the customs declaration form. The processing method according to claim 6, characterized in that, according to the commodity identifier, the commodity entry associated with the commodity identifier is determined from the multiple customs declaration entries, and the customs declaration data of the commodity entry is After entering the second standard entry corresponding to the customs declaration interface, it also includes: If there is the first standard item and/or the second standard item not entered in the customs declaration interface, content identification is performed on other target customs declaration documents except the customs declaration form based on OCR. A processing device combining RPA and AI customs declaration information, characterized in that it includes: The first identification module is used to identify the content of the target customs declaration document based on optical character recognition (OCR), so as to obtain the customs declaration data of multiple customs declaration items in the target customs declaration document; The first input module is used to input the public items among the multiple customs declaration items into the corresponding first standard items in the customs declaration interface according to the preset first robotic process automation RPA operation process. middle; A query module, configured to query commodity identifiers from the multiple customs declaration entries; The second entry module is used to determine the commodity entry associated with the commodity identifier from the plurality of customs declaration entries according to the commodity identifier, and enter the customs declaration data of the commodity entry into the second corresponding to the customs declaration interface. standard entry. The processing device according to claim 8, wherein the second input module comprises: A query unit, configured to query the relationship between the commodity identifier and the commodity entry according to the commodity identifier; The first input unit is configured to input the customs declaration data of the commodity item into the second standard corresponding to the customs declaration interface according to the preset second RPA operation process when the commodity item associated with the commodity identifier is found. entry; The second entry unit is configured to search for customs declaration items with similar semantics from the plurality of customs declaration entries according to the second standard entry in the customs declaration interface if no product item associated with the product identifier is found. as the commodity item, and enter the customs declaration data of the commodity item into the second standard item corresponding to the customs declaration interface. The processing device according to claim 9, wherein the second input unit comprises: The first determining subunit is configured to determine the semantic similarity between the second standard item in the customs declaration interface and each of the customs declaration items based on natural language processing NLP; The second determination subunit is configured to determine commodity items semantically similar to the second standard item according to the customs declaration item with the highest semantic similarity. The processing device according to claim 9, further comprising: A display module, configured to enter the commodity identifier into a corresponding standard item in the customs declaration interface, so as to display the second standard item in the customs declaration interface. The processing device according to any one of claims 8-11, further comprising: The determining module is configured to determine each of the customs declaration items to be identified according to the document type of the target customs declaration document. The processing device according to any one of claims 8-11, wherein the target customs declaration document is multiple, including a customs declaration form; the first identification module includes: The identification unit is configured to perform content identification on the customs declaration form based on OCR, so as to obtain customs declaration data of multiple customs declaration items included in the customs declaration form. The processing device according to claim 13, further comprising: The second identification module is used to declare other targets except the customs declaration form based on OCR when the first standard item and/or the second standard item are not entered in the customs declaration interface. Documents are content-aware. An electronic device, characterized in that it comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform the method described in any one of claims 1-7. Combining RPA and AI customs declaration information processing method. A non-transitory computer-readable storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, it realizes the processing of combining RPA and AI customs declaration information as described in any one of claims 1-7 method. A computer program product, characterized in that when the instructions in the computer program product are executed by a processor, the method for processing customs declaration information combining RPA and AI according to any one of claims 1-7 is executed.

Images