Terminal code-based express delivery method, device, equipment and storage medium

Abstract

The present invention discloses a terminal code-based express delivery method, device, equipment and storage medium. Aiming at the problem that the existing address-based terminal code generation method has low recognition rate and low accuracy, the present invention obtains the express order information, extracts the keyword information including the province, city, district and telephone number, and obtains the information to be queried; the information to be queried is input into the terminal code generator, and after the terminal code generator obtains the query information of the province, city, district and telephone number, it runs the preset association retrieval model to obtain the corresponding terminal code. The terminal code generation method based on the telephone number can greatly improve the accuracy of express delivery. In addition, the present invention also adopts the terminal code generation method based on the address + name, which can improve the target recognition rate.

Description

Technical Field

[0001] The present invention belongs to the technical field of express delivery, and in particular relates to an express delivery method, device, equipment and storage medium based on a terminal code. Background Art

[0002] With the development of economy and e-commerce, the logistics industry has become an indispensable part of life. Due to the rapid development of the logistics industry, logistics transportation has been divided into many nodes, among which the delivery of goods to express cabinets and express stations has become the last node of logistics transportation. Express delivery personnel can deliver the goods according to the terminal code (terminal code).

[0003] The terminal code contains information about cabinets, post stations and other collection points, and is an important information carrier for the express delivery to be accurately delivered to the customer. Even in a community, there are many terminal codes. How to calculate the terminal code in a timely and accurate manner based on the information filled in by the user is a major problem in the industry.

[0004] In the existing technology, the express terminal code is mainly calculated based on the express address keyword and address fence. Among them, the address keyword method is prone to low recognition rate due to incomplete statistics, and the accuracy rate is low due to repeated building or road section names, while the address fence has low accuracy and recognition rate due to factors such as longitude and latitude drift and geographical environment. Summary of the invention

[0005] The purpose of the present invention is to provide an express delivery method, device, equipment and storage medium based on terminal code. The terminal code generation method based on telephone number can greatly improve the accuracy of express delivery. In addition, the terminal code generation method based on address + name can improve the recognition rate.

[0006] To solve the above problems, the technical solution of the present invention is:

[0007] A terminal code-based express delivery method, comprising:

[0008] The server obtains the express order information, extracts the keyword information including province, city, district, and telephone number, and obtains the information to be queried;

[0009] Input the information to be queried into the terminal code generator to obtain the corresponding terminal code; wherein, after obtaining the query information of the province, city, district, and telephone number, the terminal code generator runs a preset associated search model to obtain the corresponding terminal code;

[0010] The terminal code is transmitted to the target query terminal to indicate the delivery cabinet or express station.

[0011] According to an embodiment of the present invention, after the terminal code generator obtains the query information of the province, city, district, and telephone number, it runs a preset associated search model to obtain the corresponding terminal code further comprising:

[0012] Pre-form a mapping path and associated search model for provinces, cities, districts, telephone numbers and corresponding terminal codes;

[0013] Retrieve the province, city, and district keyword data in the terminal code generator, and the associated search model reads the required data from the relevant database according to the mapping path to obtain the first screening result;

[0014] The telephone number value is retrieved based on the first screening result, the required data is read from the relevant database according to the mapping path, and the corresponding terminal code is output.

[0015] According to an embodiment of the present invention, forming a mapping path and an associated retrieval model further includes:

[0016] The coding tag contains keyword field information including province, city, district, telephone number, and terminal code;

[0017] Determine the complete mapping path between the search entry and the information stored in each field;

[0018] Substituting the tag code into the complete mapping path forms the associative retrieval model.

[0019] According to an embodiment of the present invention, reading required data from a related database according to the mapping path further comprises:

[0020] Read a certain mapping path required according to the search keyword;

[0021] Through load balancing, the matching fields are searched in the data cache dictionary service first;

[0022] If there are matching fields, read all relevant information;

[0023] If there is no matching field, unrecognized is returned.

[0024] According to an embodiment of the present invention, the step of inputting the information to be queried into the terminal code generator to obtain the corresponding terminal code further comprises:

[0025] The terminal code generator obtains query information including province, city, district, street address and name, and runs a preset association retrieval model. The association retrieval model reads required data from a related database according to a mapping path based on the query information of province, city and district to obtain a second screening result; based on the second screening result, the corresponding terminal code is output according to the street address and name.

[0026] According to an embodiment of the present invention, the server obtains the express order information, extracts the keyword information including the province, city, district, and telephone number, and before obtaining the information to be queried, further includes:

[0027] Create a terminal code generator and train the terminal code generator.

[0028] According to an embodiment of the present invention, the step of creating an end code generator further comprises:

[0029] Use the word segmentation model to accurately segment the express order information and obtain the province, city, district, street address, name, and telephone number information;

[0030] An associated search model is established in the form of a key-value pair, wherein the key-value pair includes: {province, city, district+address suffix+name: terminal code}, {province, city, district+telephone number: terminal code}.

[0031] The present invention also provides an express delivery device based on a terminal code, comprising:

[0032] The information extraction module is used by the server to obtain the express order information, extract the keyword information including the province, city, district, and telephone number, and obtain the information to be queried;

[0033] The terminal code generation module is used to input the information to be queried into the terminal code generator to obtain the corresponding terminal code; wherein, after the terminal code generator obtains the query information of the province, city, district, and telephone number, it runs a preset association search model to obtain the corresponding terminal code;

[0034] The sending module is used to transmit the terminal code to the target query terminal to indicate the express cabinet or express station for delivery.

[0035] The present invention further provides an express delivery device based on a terminal code, comprising:

[0036] A memory and a processor, wherein instructions are stored in the memory, and the memory and the processor are interconnected via a line;

[0037] The processor calls the instructions in the memory to implement the terminal code-based express delivery method in one embodiment of the present invention.

[0038] In addition, there is a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the terminal code-based express delivery method in one embodiment of the present invention is implemented.

[0039] Due to the adoption of the above technical solution, the present invention has the following advantages and positive effects compared with the prior art:

[0040] The express delivery method based on terminal code in one embodiment of the present invention aims at the problem that the existing terminal code generation method based on address has low recognition rate and low accuracy. By acquiring the express order information, the keyword information including province, city, district, and telephone number is extracted to obtain the information to be queried; the information to be queried is input into the terminal code generator, and after the terminal code generator obtains the query information of province, city, district, and telephone number, it runs the preset association retrieval model to obtain the corresponding terminal code. The use of the terminal code generation method based on telephone number can greatly improve the accuracy of express delivery. In addition, the present invention also adopts the terminal code generation method based on address + name, which can improve the target recognition rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 The flowchart of the express delivery method based on the terminal code in one embodiment of the present invention;

[0042] Figure 2 is a logic flow of an end code generator in an embodiment of the present invention;

[0043] Figure 3 is a block diagram of an express delivery device based on terminal code in one embodiment of the present invention;

[0044] Figure 4 It is a schematic diagram of an express delivery device based on a terminal code in one embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following is a further detailed description of a terminal code-based express delivery method, device, equipment and storage medium proposed by the present invention in conjunction with the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description and claims.

[0046] Embodiment 1

[0047] In view of the low recognition rate and accuracy of the existing terminal code generation method based on the address, this embodiment provides an express delivery method based on the terminal code. The method obtains the express order information, extracts the keyword information including the province, city, district, and telephone number, and obtains the information to be queried; the information to be queried is input into the terminal code generator, and after the terminal code generator obtains the query information of the province, city, district, and telephone number, it runs the preset association retrieval model to obtain the corresponding terminal code. The terminal code generation method based on the telephone number can greatly improve the accuracy of express delivery. In addition, the terminal code generation method based on the address + name is also adopted to improve the target recognition rate.

[0048] For details, please see Figure 1 The terminal code-based express delivery method comprises the following steps:

[0049] S1: The server obtains the express order information, extracts the keyword information including province, city, district, and telephone number, and obtains the information to be queried;

[0050] S2: Input the information to be queried into the terminal code generator to obtain the corresponding terminal code; after the terminal code generator obtains the query information of the province, city, district, and telephone number, it runs a preset association search model to obtain the corresponding terminal code;

[0051] S3: Transmit the terminal code to the target query terminal to indicate the delivery cabinet or express station.

[0052] Before step S1, an end code generator is created in advance and trained.

[0053] The terminal code generator can generate the corresponding code (terminal code) according to the input conditions, according to the preset logic or algorithm. The terminal code can be a string of numbers or a string of characters. The terminal code can be recognized by the courier to obtain the name or address of the express cabinet or express station where the express is to be delivered.

[0054] When creating a terminal code generator, it is necessary to use a word segmentation model to accurately segment the express order information to obtain the province, city, district, street address, name, and telephone number information; and establish an associated retrieval model in the form of key-value pairs.

[0055] Among them, the express order information uses the historical express order information of the recent period (generally 1-3 months). Pre-process the express order information, remove complaints, intercepted items, failed shipments, returned items, changed address items, time-limited test items, inter-city delivery orders, same-city delivery orders and mobile salesperson delivery data, and retain the main information such as province, city, street address, telephone number, name, terminal code, and receipt time. Reprocess the retained main information, delete the rows with empty fields, and ensure that all fields are not empty; sort the data in reverse order according to the receipt time, delete duplicate addresses, and retain the row data of the latest address; splice the province, city, street and name to form new data.

[0056] The above processing of express order information data can be completed by using a word segmentation model. The word segmentation model can be a word segmentation algorithm based on an N-gram speech model, a word segmentation algorithm based on an HMM (Hidden Markov Model), or a word segmentation algorithm based on a CRF (Conditional Random Field). The express order information is cut into word fragments by a word segmentation algorithm, and then the word fragments are spliced ​​into new words by splicing the word fragments back and forth through the bigram (2-gram), so that the province, city, district, street, and name can be spliced ​​into new data.

[0057] After the express order information is processed as above, the province, city, district, street address, name, and telephone number information are obtained. Then, this information needs to be stored in the preset association retrieval model in the form of key-value pairs. The association retrieval model includes two layers. The first layer is used to store the province, city, district information and the corresponding database name; the second layer is used to store the telephone and the corresponding terminal code and / or the street address + name corresponding terminal code. Correspondingly, the key-value pairs are: {province, city, district + address suffix + name: terminal code}, {province, city, district + telephone number: terminal code}. The address suffix here can be a street name, a community name, or a road name.

[0058] In this way, the corresponding database name can be obtained according to the province, city and district information, and then the corresponding terminal code can be obtained by searching the database according to the phone number or street address and name. The data can be stored in computer memory or redis middleware, which can speed up the subsequent search speed. The data in the database can be updated regularly, and the update time can be determined in combination with the operating hours of the express delivery industry. Generally, the data is updated at 3 am when it is relatively idle.

[0059] After the terminal code generator is created, it needs to be trained to achieve the predetermined recognition rate and accuracy requirements.

[0060] The specific training method can adopt the existing retrieval model training method, such as obtaining a sample set to be retrieved and a storage document library, where one sample to be retrieved corresponds to a target terminal code (document). Generate a queue for each sample to be retrieved to obtain a training sample queue corresponding to each sample to be retrieved. Each training sample queue includes a sample to be retrieved and at least one negative sample. Input the training sample queue into the association retrieval model containing initial parameters. Through the association retrieval model, the training sample queue and each stored document in the database are processed by BERT-based embedded vector encoding, and the ANN search algorithm and the KNN algorithm are used to perform vector retrieval on the training sample queue processed by embedded vector encoding from the stored documents processed by embedded vector encoding, obtain the retrieval results, and record the number of training times. Through the loss function, the loss value is calculated based on the training sample queue processed by embedded vector encoding and the retrieval results. When the number of training times is a multiple of the preset number of times and the loss value has not reached the preset convergence condition, the initial parameters of the associated retrieval model are iteratively updated, and the training sample queue is updated according to the retrieval results obtained before the current iterative update, and the step of inputting the training sample queue into the associated retrieval model containing the initial parameters is executed until the loss value reaches the preset convergence condition, and the associated retrieval model after convergence is recorded as the trained associated retrieval model.

[0061] In step S1, the server obtains the express order information, extracts the keyword information including the province, city, district, and telephone number, and obtains the information to be queried.

[0062] The express order information obtained by the server may be keyboard input text or pasted data by users, or information transmitted by e-commerce systems, which usually contain noise, such as character strokes, full-width and half-width punctuation marks, and other characters that affect subsequent word segmentation.

[0063] The server needs to pre-process the express order information and clean and normalize the text of the express order information. Specifically, the following steps are included:

[0064] a. Convert English punctuation marks to Chinese punctuation marks;

[0065] b. Remove duplicate emoji, character paintings and other characters;

[0066] c. Remove two or more consecutive blank characters

[0067] d. Replace the carriage return character with a Chinese semicolon and the space with a comma;

[0068] e. Determine the length of the string. Strings shorter than 2 do not contain order-related information, so they are directly filtered out.

[0069] After the express order information is processed as above, it is necessary to extract information to obtain relevant information such as province, city, district, telephone number, etc. as the information to be queried.

[0070] The purpose of information extraction is to complete the information extraction of each predefined field. Express order information includes fields such as express address (delivery address), name (consignee), and telephone number. The express address is generally a combination of province, city, district (or county), street, community, building number, and house number; the telephone number is usually 11 digits. When extracting information, word segmentation methods can be used, such as word segmentation methods based on N-gram speech models, word segmentation methods based on HMM (hidden Markov model), or word segmentation methods based on CRF (conditional random field).

[0071] In step S2, the information to be queried is input into the terminal code generator to obtain the corresponding terminal code. After the terminal code generator obtains the query information of the province, city, district and telephone number, it runs the preset associated retrieval model to obtain the corresponding terminal code.

[0072] In this embodiment, after the terminal code generator obtains the query information of the province, city, district, and telephone number, it runs a preset associated search model to obtain the corresponding terminal code, including the following steps:

[0073] S201: Preliminarily form a mapping path and an associated search model for the province, city, district, telephone number and corresponding terminal code;

[0074] S202: Searching for province, city, and district keyword data in the terminal code generator, the associated search model reads the required data from the relevant database according to the mapping path, and obtains the first screening result;

[0075] S203: Retrieve the telephone number value based on the first screening result, read the required data from the relevant database according to the mapping path, and output the corresponding terminal code.

[0076] In step S201, forming a mapping path and an associated search model further includes:

[0077] The coding tag contains keyword field information such as province, city, district, telephone number, and terminal code. In actual application, you can define the coding form of your own system, such as 12-digit mixed code, 10-digit pure code or 15-digit pure code.

[0078] Determine the complete mapping path between the search entry and the information stored in each field, and substitute the tag code into the complete mapping path to form an associated search model. The associated search model is the main functional structure of the terminal code generator, which connects the search entry and the database. The search entry here is the input interface of the terminal code generator.

[0079] In step S202, reading required data from the relevant database according to the mapping path further includes:

[0080] Read a certain mapping path required according to the search keyword; search for matching fields in the data cache dictionary service first through load balancing; if there are matching fields, read all relevant information; if there are no matching fields, return unrecognized.

[0081] Please see Figure 2 The terminal code generator receives the information to be queried (province, city, district, telephone number), first searches the province, city and district in the associated search model to determine whether it is found. If not, it returns that it cannot be recognized; if so, it proceeds to the next step of retrieval: searching the telephone number to determine whether it is found. If so, it returns the corresponding terminal code, if not, it returns that it cannot be recognized.

[0082] from Figure 2 It can be seen that the terminal code generator can also obtain query information including province, city, district, street address, and name, run the preset association retrieval model, and obtain the corresponding terminal code.

[0083] The associated search model in the terminal code generator obtains the second screening result based on the query information of the province, city, and district; based on the second screening result, the corresponding terminal code is output according to the street address and name. That is, the terminal code generator receives the information to be queried (province, city, district, street address, name), first searches the province, city, and district in the associated search model, and determines whether it is found. If not, it returns that it cannot be recognized; if so, it performs the next search: searching the street address + name, and determines whether it is found. If so, it returns the corresponding terminal code, and if not, it returns that it cannot be recognized.

[0084] The above two search methods can be processed in parallel or individually. When processed in parallel, if the terminal code can be obtained by searching the phone number, the result can be returned directly without searching the street address + name, or ignoring the search results of the street address + name. Compared with the street address + name, the phone number can better reflect the uniqueness.

[0085] In step S3, the terminal code is transmitted to the target query terminal to indicate the express cabinet or express station for delivery.

[0086] The server transmits the terminal code to the query terminal corresponding to the express order data query. The query terminal is the query terminal corresponding to the courier. After receiving the terminal code, the courier will deliver the courier according to the courier cabinet or courier post pointed to by the terminal code.

[0087] Embodiment 2

[0088] This embodiment provides an express delivery device based on terminal code, which can implement the steps of the express delivery method based on terminal code in the above embodiment 1. Figure 3 The terminal code-based express delivery device comprises:

[0089] Information extraction module 1, used for the server to obtain express order information, extract keyword information including province, city, district, telephone number, and obtain information to be queried;

[0090] The terminal code generation module 2 is used to input the information to be queried into the terminal code generator to obtain the corresponding terminal code; wherein, after the terminal code generator obtains the query information of the province, city, district, and telephone number, it runs a preset association search model to obtain the corresponding terminal code;

[0091] The sending module 3 is used to transmit the terminal code to the target query terminal, indicating the express cabinet or express station for delivery.

[0092] The terminal code generation module 2 is also used to receive query information including province, city, district, street address, and name, and run a preset associated search model to obtain a corresponding terminal code.

[0093] Specifically, the information extraction module 1 includes a data preprocessing unit and a word segmentation unit. The data preprocessing unit is used to obtain the text of the express order information, and clean and normalize the text.

[0094] The specific steps include:

[0095] a. Convert English punctuation marks to Chinese punctuation marks;

[0096] b. Remove duplicate emoji, character paintings and other characters;

[0097] c. Remove two or more consecutive blank characters

[0098] d. Replace the carriage return character with a Chinese semicolon and the space with a comma;

[0099] e. Determine the length of the string. Strings shorter than 2 do not contain order-related information, so they are directly filtered out.

[0100] The word segmentation unit is used to segment the normalized text output by the data preprocessing unit and extract information including province, city, district, telephone number, street address, name, etc. The word segmentation unit samples a preset word segmentation algorithm to segment the express order information text to obtain data such as province, city, district, telephone number, street address, name, etc. The word segmentation algorithm can be a word segmentation algorithm based on an N-gram speech model, a word segmentation algorithm based on an HMM (Hidden Markov Model), or a word segmentation algorithm based on a CRF (Conditional Random Field).

[0101] The terminal code generation module 2 includes a terminal code generator, which is created and trained using the method described in the first embodiment, and will not be described in detail here.

[0102] The terminal code generator receives the information to be queried (province, city, district, telephone number), first searches the province, city and district in the associated retrieval model to determine whether it is found. If not, it returns that it cannot be recognized; if so, it proceeds to the next step of retrieval: searching the telephone number to determine whether it is found. If so, it returns the corresponding terminal code. If not, it returns that it cannot be recognized.

[0103] Or the terminal code generator receives the information to be queried (province, city, district, street address, name), first searches the province, city and district in the associated retrieval model to determine whether it is found, if not, returns unrecognizable; if so, proceeds to the next step of retrieval: searches the street address + name to determine whether it is found, if so, returns the corresponding terminal code, if not, returns unrecognizable.

[0104] The above two terminal code generator search methods can be processed in parallel or individually. When processed in parallel, if the terminal code can be obtained by searching the phone number, the result can be directly returned without searching the street address + name, or ignoring the search results of the street address + name. This is because compared with the street address + name, the phone number can better reflect the uniqueness.

[0105] The express delivery device based on the terminal code obtains the express order information, extracts the keyword information including the province, city, district, telephone number, street address, and name, and obtains the information to be queried; retrieves the associated search model according to the province, city, district, telephone number (or province, city, district, street address, name) in the information to be queried, and obtains the corresponding terminal code. The terminal code generation method based on the telephone number can greatly improve the accuracy of express delivery. The terminal code generation method based on the address + name can improve the target recognition rate.

[0106] Embodiment 3

[0107] This embodiment provides a terminal code based express delivery device. Figure 4 The terminal code-based express delivery device 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 510 (for example, one or more processors) and memory 520, and one or more storage media 530 (for example, one or more mass storage devices) storing application programs 533 or data 532. Among them, the memory 520 and the storage medium 530 can be short-term storage or permanent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the terminal code-based express delivery device 500.

[0108] Furthermore, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the terminal code-based express delivery device 500.

[0109] The terminal code-based express delivery device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input and output interfaces 560, and / or one or more operating systems 531, such as Windows Serve, Vista, etc.

[0110] Those skilled in the art will understand that Figure 4The illustrated structure of the terminal code-based express delivery equipment does not constitute a limitation on the terminal code-based express delivery equipment, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0111] Another embodiment of the present invention further provides a computer-readable storage medium.

[0112] The computer-readable storage medium may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, cause the computer to execute the steps of the express delivery method based on the terminal code in the first embodiment.

[0113] If the express delivery method based on the terminal code is implemented in the form of program instructions and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of software. The computer software is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0114] Those skilled in the art can clearly understand that, for the sake of convenience and brevity in description, the identification content specifically executed by the above-described system and device can refer to the corresponding process in the aforementioned method embodiment.

[0115] The embodiments of the present invention are described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above embodiments. Even if various changes are made to the present invention, if these changes fall within the scope of the claims of the present invention and their equivalents, they still fall within the protection scope of the present invention.

Claims

1. A terminal code-based express delivery method, characterized in that: include: The server obtains the express order information, extracts the keyword information including province, city, district, and telephone number, and obtains the information to be queried; Input the information to be queried into the terminal code generator to obtain the corresponding terminal code; wherein, after obtaining the query information of the province, city, district, and telephone number, the terminal code generator runs a preset associated search model to obtain the corresponding terminal code; The terminal code is transmitted to the target query terminal to indicate the delivery cabinet or delivery station; After the terminal code generator obtains the query information of the province, city, district, and telephone number, it runs a preset associated search model to obtain the corresponding terminal code, further comprising: Pre-form a mapping path and associated search model for provinces, cities, districts, telephone numbers and corresponding terminal codes; Retrieve the province, city, and district keyword data in the terminal code generator, and the associated search model reads the required data from the relevant database according to the mapping path to obtain the first screening result; The telephone number value is retrieved based on the first screening result, the required data is read from the relevant database according to the mapping path, and the corresponding terminal code is output.

2. The express delivery method based on terminal code according to claim 1, characterized in that: The forming of the mapping path and the associated retrieval model further comprises: The coding tag contains keyword field information including province, city, district, telephone number, and terminal code; Determine the complete mapping path between the search entry and the information stored in each field; Substituting the tag code into the complete mapping path forms the associative retrieval model.

3. The express delivery method based on terminal code according to claim 1, characterized in that: The step of reading the required data from the relevant database according to the mapping path further includes: Read a certain mapping path required according to the search keyword; Through load balancing, the matching fields are searched in the data cache dictionary service first; If there are matching fields, read all relevant information; If there is no matching field, unrecognized is returned.

4. The express delivery method based on terminal code according to claim 1, characterized in that: The step of inputting the information to be queried into the terminal code generator to obtain the corresponding terminal code further comprises: The terminal code generator obtains query information including province, city, district, street address and name, and runs a preset association retrieval model. The association retrieval model reads required data from a related database according to a mapping path based on the query information of province, city and district to obtain a second screening result; based on the second screening result, the corresponding terminal code is output according to the street address and name.

5. The express delivery method based on terminal code according to claim 1, characterized in that: The server obtains the express order information, extracts the keyword information including the province, city, district, and telephone number, and before obtaining the information to be queried, further includes: Create a terminal code generator and train the terminal code generator.

6. The express delivery method based on terminal code according to claim 5, characterized in that: The creating terminal code generator further comprises: Use the word segmentation model to accurately segment the express order information and obtain the province, city, district, street address, name, and telephone number information; An associated search model is established in the form of a key-value pair, wherein the key-value pair includes: {province, city, district+address suffix+name: terminal code}, {province, city, district+telephone number: terminal code}.

7. A terminal code-based express delivery device, characterized in that: include: The information extraction module is used by the server to obtain the express order information, extract the keyword information including the province, city, district, and telephone number, and obtain the information to be queried; The terminal code generation module is used to input the information to be queried into the terminal code generator to obtain the corresponding terminal code; wherein, after the terminal code generator obtains the query information of the province, city, district, and telephone number, it runs a preset association search model to obtain the corresponding terminal code; A sending module, used to transmit the terminal code to a target query terminal to indicate a delivery cabinet or delivery station; The terminal code generation module is further used to pre-form a mapping path and an associated retrieval model for the province, city, district, telephone number and the corresponding terminal code; retrieve the province, city and district keyword data in the terminal code generator, and the associated retrieval model reads the required data from the relevant database according to the mapping path to obtain a first screening result; retrieve the telephone number value based on the first screening result, read the required data from the relevant database according to the mapping path, and output the corresponding terminal code.

8. A terminal code-based express delivery device, characterized in that: include: A memory and a processor, wherein instructions are stored in the memory, and the memory and the processor are interconnected via a line; The processor calls the instructions in the memory to implement the terminal code-based express delivery method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the terminal code-based express delivery method as described in any one of claims 1 to 6 is implemented.

Images