Courier collection and delivery standard identification method and apparatus, device, and storage medium

Abstract

Disclosed in the present invention are a courier collection and delivery standard identification method and apparatus, a device, and a storage medium. The method comprises: obtaining a consignment name to be queried; performing feature extraction on the consignment name to be queried, to obtain an embedding vector of the consignment name to be queried, and querying, from a preset consignment delivery library on the basis of the embedding vector and the consignment name to be queried, a target consignment name and a customs code corresponding to the target consignment name; and querying policy files in a preset policy database by means of the customs code to obtain a target policy file, and processing the target policy file to obtain a collection and delivery standard for a consignment represented by the consignment name to be queried. By means of the method, a related courier policy can be queried by means of a courier consignment name, and international courier collection and delivery standards can be quickly obtained.

Description

Method, device, equipment and storage medium for identifying express delivery and collection standards Technical Field

[0001] The present invention relates to the field of natural language processing technology, and in particular to a method, device, equipment and storage medium for identifying express delivery and collection standards. Background Art

[0002] With the acceleration of globalization, more and more express delivery companies are beginning to expand their business overseas. However, in the international market, they face the challenge of navigating the varying and fluctuating standards for express delivery and collection in different countries and regions. Entry regulations and customs inspection procedures vary across countries and regions. For example, in the United States, FDA forms must be filled out for items such as food and health supplements. In Australia, all incoming packages must pass Australian customs review, while in Europe, regulations such as the EU CE certification must be followed. Failure by express delivery companies to accurately grasp these standards can lead to delivery failures and additional costs such as return shipping fees.

[0003] At present, in order to maintain and update these standards, express delivery companies need to establish a team specifically responsible for collecting, organizing, interpreting and updating the latest express delivery policies in countries and regions around the world. However, relying on manpower to maintain and update the standards can easily lead to low efficiency in identifying express delivery standards.

[0004] Summary of the Invention

[0005] In order to solve the above technical problems, the embodiments of the present invention provide a method and system for identifying express delivery and collection standards, which can use the name of the express consignment to query express-related policies and quickly obtain international express delivery and collection standards.

[0006] A first aspect of an embodiment of the present invention provides a method for identifying express delivery and collection standards, the method comprising:

[0007] Get the name of the consignment to be queried;

[0008] Performing feature extraction on the name of the consignment to be queried to obtain an embedding vector for the name of the consignment to be queried; performing a query from a preset consignment delivery database based on the embedding vector and the name of the consignment to be queried to obtain a target consignment name and a customs code corresponding to the target consignment name;

[0009] The customs code is used to query policy documents in a preset policy database to obtain a target policy document, and the target policy document is sorted to obtain the acceptance and delivery standards of the consignment represented by the name of the consignment to be queried.

[0010] In a possible implementation of the first aspect, querying a preset consignment delivery database based on the embedded vector to obtain the target consignment name and the customs code corresponding to the target consignment name includes:

[0011] Based on the embedded vector and the name of the consignment to be queried, a query is performed from the preset consignment delivery database to obtain the initial target consignment information, wherein the initial target consignment information includes the initial target consignment name and the customs code corresponding to the initial target consignment name;

[0012] It is determined whether the initial target consignment name is consistent with the attributes of the consignment to be queried. If they are consistent, the initial target consignment name is determined to be the target consignment name, and the customs code corresponding to the initial target consignment name is determined to be the customs code corresponding to the target consignment name.

[0013] In a possible implementation of the first aspect, a query is performed from a preset consignment delivery database based on the embedded vector and the name of the consignment to be queried to obtain initial target consignment information, including:

[0014] Calculating the degree of overlap between the name of the consignment to be queried and the names of each consignment in the preset consignment delivery database, and obtaining multiple overlap values;

[0015] Determine the name of the consignment corresponding to the overlap value reaching the preset value as the first target consignment name;

[0016] Determine whether the name of the first target consignment is consistent with the name of the consignment to be queried. If they are equal, determine that the information corresponding to the first target consignment name is the initial target consignment information; if they are not equal, calculate the similarity between the embedding vector of the consignment name to be queried and the embedding vectors of each consignment name in the preset consignment delivery library, obtain multiple similarity values, and determine that the consignment information corresponding to the similarity value greater than the preset similarity value is the initial target consignment information.

[0017] In a possible implementation of the first aspect, before obtaining the name of the consigned item to be queried, the method further includes:

[0018] Build a customs code interpretation database based on import and export tariff policy texts. The customs code interpretation database includes customs codes and their definitions;

[0019] Obtain the name and customs code of the historical consignment, and query the customs code interpretation database based on the customs code of the historical consignment to obtain the customs code interpretation corresponding to the customs code of the historical consignment;

[0020] Determine whether the name of the historical consignment is consistent with the customs code interpretation corresponding to the customs code of the historical consignment. If they are consistent, extract the name of the historical consignment from the customs code interpretation;

[0021] A preset consignment delivery library is constructed based on the historical consignment names.

[0022] In a possible implementation of the first aspect, constructing a preset consignment delivery library based on historical consignment names includes:

[0023] Determine the embedding vectors for the historical consignment names;

[0024] A preset consignment delivery library is constructed based on the historical consignment names, historical consignment customs codes and historical consignment names' embedding vectors.

[0025] In a possible implementation of the first aspect, before obtaining the name of the consigned item to be queried, the method further includes:

[0026] Extracting an embedding vector of a product name or description from a policy or regulation document, and using the embedding vector of the product name or description to query a preset consignment delivery database to obtain information on multiple consignments to be determined;

[0027] The attributes of each consignment to be judged are judged against the product name and product description. If they are the same attributes, the information of the policy and regulatory documents corresponding to the consignment to be judged and the product name is stored in the preset policy database. If they are not the same attributes, the consignment to be judged is deleted.

[0028] A second aspect of an embodiment of the present invention provides a device for identifying express delivery and collection standards, the system comprising:

[0029] The acquisition module is used to obtain the name of the consignment to be queried;

[0030] The first query module is used to extract features of the name of the consignment to be queried, obtain an embedding vector of the name of the consignment to be queried, and query the preset consignment delivery database based on the embedding vector and the name of the consignment to be queried to obtain the target consignment name and the customs code corresponding to the target consignment name;

[0031] The second query module is used to use the customs code to query the policy documents in the preset policy database to obtain the target policy documents, and to sort the target policy documents to obtain the collection and delivery standards of the consignment represented by the name of the consignment to be queried.

[0032] In a possible implementation of the second aspect, the first query module includes an extraction unit and a judgment unit.

[0033] The extraction unit is configured to query a preset consignment delivery database based on the embedded vector and the name of the consignment to be queried, and obtain initial target consignment information, wherein the initial target consignment information includes the name of the initial target consignment and the customs code corresponding to the name of the initial target consignment;

[0034] The judgment unit is used to judge whether the initial target consignment name is consistent with the attributes of the consignment to be queried. If they are consistent, the initial target consignment name is determined to be the target consignment name, and the customs code corresponding to the initial target consignment name is the customs code corresponding to the target consignment name.

[0035] A third aspect of an embodiment of the present invention provides a computer device, including:

[0036] memory for storing computer programs;

[0037] The processor is used to implement the express delivery collection and delivery standard identification method as described in the first aspect when executing the computer program.

[0038] A fourth aspect of an embodiment of the present invention provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the express delivery and collection standard identification method of the first aspect are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] FIG1 is a flow chart showing an embodiment of a method for identifying express delivery and collection standards provided by the present invention;

[0040] FIG2 is a schematic diagram of a flow chart of an express delivery acceptance standard identification method according to an embodiment of the present invention;

[0041] FIG3 is a schematic diagram of the system structure of another embodiment of the express delivery and collection standard identification method provided by the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0043] Please refer to FIG1 , which is a flow chart of an embodiment of a method for identifying express delivery and collection standards according to an embodiment of the present invention, including steps S101 to S103. The specific steps are as follows:

[0044] S101. Obtain the name of the consignment to be queried.

[0045] It is worth noting that the name of the consignment to be queried is the name of the consignment that the user needs to query.

[0046] In this embodiment, in this step, the user needs to input the name of the consignment to be queried. The user enters the name of the consignment to be queried through the query interface, and the backend receives the name of the consignment to be queried input by the user.

[0047] S102: Extract features of the name of the consignment to be queried to obtain an embedding vector of the name of the consignment to be queried; query the preset consignment delivery database based on the embedding vector and the name of the consignment to be queried to obtain the target consignment name and the customs code corresponding to the target consignment name.

[0048] In this embodiment, this step requires a query for the name of the consignment to be queried. Large-scale language modeling technology is used to extract the consignment name's embedding. Based on Chinese character matching and semantic matching of the embedding, similar consignment names are queried from the Consignment Delivery Library Query Interface (HS-INST-API). Once similar consignment names are found, large-scale language modeling technology is used to determine whether the attributes of the similar consignment name are consistent with the input consignment name. If so, the customs code corresponding to the similar consignment name is determined to be the customs code corresponding to the consignment to be queried.

[0049] It's worth noting that Large-Scale Language Modeling (LLM) is a model based on machine learning and natural language processing. Embedding refers to an embedding vector, a multidimensional real-valued vector that maps high-dimensional data into a low-dimensional space.

[0050] S103. Querying policy documents in a preset policy database using the customs code to obtain a target policy document, and sorting the target policy document to obtain the acceptance and delivery standards for the consignment represented by the name of the consignment to be queried.

[0051] In this embodiment, this step requires both query and summary operations. As shown in Figure 2, after obtaining the customs codes of similar consignments, the customs codes of the similar consignments are determined to be the customs codes of the consignments to be queried. This customs code is then used to query the corresponding policy document from the preset policy data. Finally, large-scale language model technology is used to summarize and output the policies, thereby obtaining the acceptance and delivery standards for the consignments to be queried.

[0052] In implementing this embodiment, by obtaining the name of the consignment to be queried, feature extraction is performed on the name of the consignment to be queried, and an embedding vector of the name of the consignment to be queried is obtained. According to the embedding vector and the name of the consignment to be queried, a query is performed from the preset consignment delivery library to obtain the target consignment name and the customs code corresponding to the target consignment name. The customs code is used to query the policy document in the preset policy database to obtain the target policy document. The target policy document is sorted out to obtain the collection and delivery standards of the consignment represented by the name of the consignment to be queried. This method realizes the use of the express consignment name to query express-related policies, and can quickly obtain international express collection and delivery standards.

[0053] In some embodiments, the method includes: querying a preset consignment delivery library based on the embedded vector and the name of the consignment to be queried to obtain initial target consignment information, wherein the initial target consignment information includes the initial target consignment name and the customs code corresponding to the initial target consignment name; judging whether the initial target consignment name is consistent with the attributes of the consignment to be queried, and if so, determining that the initial target consignment name is the target consignment name, and the customs code corresponding to the initial target consignment name is the customs code corresponding to the target consignment name.

[0054] In this embodiment, the consignment name and embedding vector are used to search for similar consignment names in the consignment delivery database. The data fields in the consignment delivery database include <consignment name, hscode, embedding>. The database index field has two fields: the consignment name and the embedding, i.e., the embedding vector. The consignment name is used for character matching, and the embedding is used for vector matching.

[0055] After obtaining similar consignment names, it is determined whether the attributes of each similar consignment name are consistent with the name of the consignment to be queried. If they are consistent, the customs code corresponding to the similar consignment name is determined to be the customs code of the consignment to be queried.

[0056] In some embodiments, the method includes: calculating the degree of overlap between the name of the consignment to be queried and the names of each consignment in the preset consignment delivery library to obtain multiple overlap values; determining that the consignment name corresponding to the overlap value reaching the preset value is the first target consignment name; judging whether the first target consignment name is consistent with the name of the consignment to be queried, and if they are equal, determining that the information corresponding to the first target consignment name is the initial target consignment information; if they are not equal, calculating the similarity between the embedding vector of the consignment name to be queried and the embedding vector of each consignment name in the preset consignment delivery library to obtain multiple similarity values, and determining that the consignment information corresponding to the similarity value greater than the preset similarity value is the initial target consignment information.

[0057] In this embodiment, Chinese character matching and embedding semantic matching are used to query the consignment delivery database query interface, i.e., HS-INST-API, for similar consignment names. The specific process is as follows:

[0058] First, character matching is used. Character matching refers to the number of matching characters. The user enters the name of the consignment to be searched. The system then compares the name with the names in the consignment delivery database, calculates the degree of overlap between the two, and determines which pair has the highest overlap. For example, if consignment name A is "milk" and a similar consignment name B is "milk powder," the overlap between A and B is 1 / 2, meaning that for every two characters in A, one is found in B. To ensure accuracy, the character matching threshold is set to 100%. This means that only when all characters in A are found in B is B considered to meet the requirements.

[0059] However, when using character matching, a one-to-many match may occur. This means that multiple similar consignment names may be found for a given consignment name. For example, if consignment name A is "milk," and the search results are "milk powder" and "milk," the system needs to determine whether consignment name A and a similar consignment name B are completely identical. If "milk" appears in B, then "milk" takes precedence. If the search results include "milk powder" and "cow's milk," but "milk" does not appear in B, embedding is required for further analysis.

[0060] When making embedding judgments, we first use large-scale language model technology to extract the embedding-A of the consignment to be queried. Then, we traverse the consignment delivery library and compare the cosine similarity with each embedding to obtain the consignment name with the highest similarity. For example, if the similarity threshold is set to 0.9, the consignment name with a similarity greater than 0.9 is selected as the target consignment name to be queried.

[0061] In some embodiments, the method includes: before obtaining the name of the consignment to be queried, the method also includes: constructing a customs code interpretation database based on the import and export tariff policy text, the customs code interpretation database including the customs code and the interpretation of the customs code; obtaining the name and customs code of the historical consignment, and querying the customs code interpretation from the customs code interpretation database based on the customs code of the historical consignment to obtain the customs code interpretation corresponding to the customs code of the historical consignment; judging whether the name of the historical consignment is consistent with the customs code interpretation corresponding to the customs code of the historical consignment, and if consistent, extracting the name of the historical consignment from the customs code interpretation; and constructing a preset consignment delivery library based on the name of the historical consignment.

[0062] In this embodiment, it should be noted that the preset consignment item delivery library refers to a database including information such as customs codes and consignment item names, and also refers to the consignment item delivery library mentioned above. The import and export tariff policy text refers to policy documents on import and export related information, including but not limited to laws, regulations, work reports, and plans, etc.

[0063] The preset consignment item delivery library is constructed by using information such as policy and regulation documents and customs codes. The specific construction method is as follows: Obtain relevant national policy documents, and use the relevant national policy documents to construct an interpretation library of customs codes, with fields including <hscode, hscode interpretation>, and construct a query interface for the customs code interpretation library, that is, HS-LIB-API. Obtain the historical consignment items and their customs codes of the express delivery enterprise, use the query interface of the customs code interpretation library to query the corresponding interpretation of the customs code, and use large language model technology to judge whether the consignment item name is consistent with its corresponding customs code interpretation. If they are consistent, use large language model technology to extract the embedding vector of the consignment item name, construct a consignment item delivery library based on customs codes <consignment item name, hscode, embedding>, and construct a query interface for the consignment item delivery library, that is, HS-INST-API. It should be noted that hscode refers to the customs code, and embedding refers to the embedding vector.

[0064] In some embodiments, it includes: determining the embedding vector of the historical consignment item name; constructing the preset consignment item delivery library based on the historical consignment item name, historical consignment item customs code, and the embedding vector of the historical consignment item name.

[0065] In this embodiment, construct a consignment item delivery library based on customs codes according to the historical consignment item name, historical consignment item customs code, and the embedding vector of the historical consignment item name. The data in the consignment item delivery library includes <consignment item name, hscode, embedding>, and construct a query interface for the consignment item delivery library, that is, HS-INST-API.

[0066] In some embodiments, it includes: extracting the embedding vector of the goods name or goods description from the policy and regulation documents, using the embedding vector of the goods name or goods description to query multiple consignment items to be judged information from the preset consignment item delivery library; making an attribute judgment on each consignment item to be judged information and the goods name and goods description. If they are of the same attribute, store the information of the consignment item to be judged information and the policy and regulation document corresponding to the goods name into the preset policy database. If they are not of the same attribute, delete the consignment item to be judged information.

[0067] In this embodiment, policy and regulatory documents are obtained and key information, such as country, product, and import / export requirements, is extracted. Large-scale language modeling technology is then used to extract the embeddings of product names or descriptions from the policy and regulatory documents. Similar consignment names are then queried from the consignment delivery database query interface using Chinese-based character matching and semantic matching of the embeddings. A determination is then made as to whether the multiple similar consignment names found are items with the same attributes as the "product name / description." Since there may be a one-to-many relationship between product descriptions and consignment names, similar consignment names with different attributes are sequentially determined and eliminated, resulting in similar consignment names with the same attributes. For example, "equine animals and related products" and "donkey meat" share the same attribute, while "equine animals and related products" and "horse jacket" have different attributes. Similar consignment names, along with their corresponding customs codes, customs code interpretations, and policy information, are stored in the policy database. The data in the policy database includes <customs code, code description, product name, product description, document title, document content, document link, document release time>, and a policy database query interface, namely POLICY-LIB-API, is constructed.

[0068] It should be noted that the policy database can be updated according to domestic and foreign legal and policy documents to ensure the timeliness of the preset policy database.

[0069] This method uses large-scale language model technology to connect consignments, policies and regulations, and customs codes, extracts and analyzes consignments, obtains effective policy documents, effectively solves the pain point of difficult standard collection in international express business, and improves the efficiency and accuracy of standard collection in international express business.

[0070] In some embodiments, as shown in FIG3 , a block diagram of an express delivery standard identification device 300 provided in an embodiment of the present application is shown, including: an acquisition module 301 , a first query module 302 , and a second query module 303 , wherein:

[0071] The acquisition module 301 is used to obtain the name of the consignment to be queried;

[0072] The first query module 302 is configured to extract features of the name of the consignment to be queried, obtain an embedding vector of the name of the consignment to be queried, and query a preset consignment delivery database based on the embedding vector and the name of the consignment to be queried to obtain the target consignment name and the customs code corresponding to the target consignment name;

[0073] The second query module 303 is used to query policy documents in a preset policy database using the customs code to obtain a target policy document, and to sort the target policy document to obtain the acceptance and delivery standards of the consignment represented by the name of the consignment to be queried.

[0074] In some embodiments, the first query module 302 includes an extraction unit and a judgment unit.

[0075] The extraction unit is configured to query a preset consignment delivery database based on the embedded vector and the name of the consignment to be queried, and obtain initial target consignment information, wherein the initial target consignment information includes the name of the initial target consignment and the customs code corresponding to the name of the initial target consignment;

[0076] The judgment unit is used to judge whether the initial target consignment name is consistent with the attributes of the consignment to be queried. If they are consistent, the initial target consignment name is determined to be the target consignment name, and the customs code corresponding to the initial target consignment name is determined to be the customs code corresponding to the target consignment name. In some embodiments, based on the embedding vector and the name of the consignment to be queried, a query is performed from a preset consignment delivery database to obtain the initial target consignment information, including:

[0077] Calculating the degree of overlap between the name of the consignment to be queried and the names of each consignment in the preset consignment delivery database, and obtaining multiple overlap values;

[0078] Determine the name of the consignment corresponding to the overlap value reaching the preset value as the first target consignment name;

[0079] Determine whether the name of the first target consignment is consistent with the name of the consignment to be queried. If they are equal, determine that the information corresponding to the first target consignment name is the initial target consignment information; if they are not equal, calculate the similarity between the embedding vector of the consignment name to be queried and the embedding vectors of each consignment name in the preset consignment delivery library, obtain multiple similarity values, and determine that the consignment information corresponding to the similarity value greater than the preset similarity value is the initial target consignment information.

[0080] In some embodiments, before obtaining the name of the consignment to be queried, the method further includes:

[0081] Build a customs code interpretation database based on import and export tariff policy texts. The customs code interpretation database includes customs codes and their definitions;

[0082] Obtain the name and customs code of the historical consignment, and query the customs code interpretation database based on the customs code of the historical consignment to obtain the customs code interpretation corresponding to the customs code of the historical consignment;

[0083] Determine whether the name of the historical consignment is consistent with the customs code interpretation corresponding to the customs code of the historical consignment. If they are consistent, extract the name of the historical consignment from the customs code interpretation;

[0084] A preset consignment delivery library is constructed based on the historical consignment names.

[0085] In some embodiments, a preset consignment delivery library is constructed based on the historical consignment names, including:

[0086] Determine the embedding vectors for the historical consignment names;

[0087] A preset consignment delivery library is constructed based on the historical consignment names, historical consignment customs codes and historical consignment names' embedding vectors.

[0088] In some embodiments, before obtaining the name of the consignment to be queried, the method further includes:

[0089] Extracting an embedding vector of a product name or description from a policy or regulation document, and using the embedding vector of the product name or description to query a preset consignment delivery database to obtain information on multiple consignments to be determined;

[0090] The attributes of each consignment to be judged are judged against the product name and product description. If they are the same attributes, the information of the policy and regulatory documents corresponding to the consignment to be judged and the product name is stored in the preset policy database. If they are not the same attributes, the consignment to be judged is deleted.

[0091] In one embodiment of the present application, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program, and the processor implements the above steps when executing the computer program. The implementation principle and technical effects of the computer device provided in this embodiment are similar to those of the above method embodiment and are not further described here.

[0092] In one embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and the above steps are implemented when the computer program is executed by a processor; the computer-readable storage medium provided in this embodiment has an implementation principle and technical effects similar to those of the above method embodiment, and will not be repeated here.

[0093] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0094] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for identifying express delivery collection and delivery standards, characterized in that: include: Get the name of the consignment to be queried; Perform feature extraction on the name of the consignment to be queried to obtain an embedding vector of the name of the consignment to be queried, and perform a query from a preset consignment delivery library according to the embedding vector and the name of the consignment to be queried to obtain a target consignment name and a customs code corresponding to the target consignment name; The customs code is used to query policy documents in a preset policy database to obtain a target policy document, and the target policy document is sorted to obtain the collection and delivery standards of the consignment represented by the name of the consignment to be queried.

2. The express delivery collection and delivery standard identification method according to claim 1, characterized in that: The querying from the preset consignment delivery database according to the embedded vector to obtain the target consignment name and the customs code corresponding to the target consignment name includes: According to the embedding vector and the name of the consignment to be queried, query from a preset consignment delivery database to obtain initial target consignment information, wherein the initial target consignment information includes the name of the initial target consignment and the customs code corresponding to the name of the initial target consignment; It is determined whether the initial target consignment name is consistent with the attributes of the consignment to be queried. If they are consistent, it is determined that the initial target consignment name is the target consignment name, and the customs code corresponding to the initial target consignment name is the customs code corresponding to the target consignment name.

3. The express delivery collection and delivery standard identification method according to claim 2, characterized in that: The querying from a preset consignment delivery library according to the embedded vector and the name of the consignment to be queried to obtain initial target consignment information includes: Calculating the degree of overlap between the name of the consigned object to be queried and the names of each consigned object in the preset consigned object delivery library to obtain a plurality of coincidence values; Determine the name of the consignment corresponding to the overlap value reaching the preset value as the first target consignment name; Determine whether the name of the first target consignment is consistent with the name of the consignment to be queried. If they are equal, determine that the information corresponding to the first target consignment name is the initial target consignment information; if they are not equal, calculate the similarity between the embedding vector of the consignment name to be queried and the embedding vectors of each consignment name in the preset consignment delivery library to obtain multiple similarity values, and determine that the consignment information corresponding to the similarity value greater than the preset similarity value is the initial target consignment information.

4. The express delivery collection and delivery standard identification method according to claim 1, characterized in that: Before obtaining the name of the consigned object to be queried, the method further includes: A customs code interpretation database is constructed based on the import and export tariff policy text. The customs code interpretation database includes customs Definition of codes and customs codes; Obtain the name and customs code of the historical consignment, and query the customs code interpretation from the customs code interpretation database according to the customs code of the historical consignment to obtain the customs code interpretation corresponding to the customs code of the historical consignment; Determine whether the name of the historical consignment is consistent with the customs code interpretation corresponding to the customs code of the historical consignment; if they are consistent, extract the name of the historical consignment from the customs code interpretation; A preset consignment delivery library is constructed based on the historical consignment names.

5. The express delivery collection and delivery standard identification method according to claim 4, characterized in that: The preset consignment delivery library constructed according to the historical consignment names includes: Determining an embedding vector for the name of the historical consignment; A preset consignment delivery library is constructed based on the historical consignment name, the historical consignment customs code and the embedded vector of the historical consignment name.

6. The express delivery collection and delivery standard identification method according to claim 1, characterized in that: Before obtaining the name of the consigned item to be queried, the method further includes: Extracting an embedded vector of a commodity name or a commodity description from a policy and regulation document, and using the embedded vector of the commodity name or the commodity description to query the preset consignment delivery library to obtain a plurality of consignment information to be determined; The attributes of each of the consignment information to be judged, the product name and the product description are judged. If they are the same attributes, the information of the policy and regulatory documents corresponding to the consignment information to be judged and the product name are stored in the preset policy database. If they are not the same attributes, the consignment information to be judged is deleted.

7. A device for identifying express delivery standards, characterized in that: include: The acquisition module is used to obtain the name of the consignment to be queried; The first query module is used to extract features of the name of the consignment to be queried, obtain an embedding vector of the name of the consignment to be queried, and query from a preset consignment delivery library according to the embedding vector and the name of the consignment to be queried to obtain a target consignment name and a customs code corresponding to the target consignment name; The second query module is used to use the customs code to query the policy document in the preset policy database to obtain the target policy document, and to sort the target policy document to obtain the collection and delivery standards of the consignment represented by the name of the consignment to be queried.

8. The express delivery collection and delivery standard identification device according to claim 7, characterized in that: The first query module includes an extraction unit and a judgment unit. The extraction unit is used to query from a preset consignment delivery library according to the embedding vector and the name of the consignment to be queried, and obtain the initial target consignment information, wherein the initial target consignment information includes the initial target The customs code corresponding to the name of the consignment and the name of the initial target consignment; The judgment unit is used to judge whether the initial target consignment name is consistent with the attribute of the consignment to be queried. If they are consistent, the initial target consignment name is determined to be the target consignment name, and the customs code corresponding to the initial target consignment name is the customs code corresponding to the target consignment name.

9. A computer device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the express delivery collection and delivery standard identification method as described in any one of claims 1 to 6 when executing the computer program.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the express delivery collection and delivery standard identification method as described in any one of claims 1 to 6.

Images