Address information detection method and its device, equipment, medium and product

Through the editing distance algorithm and sliding window word segmentation technology, the logistics identification problem caused by address information errors in the e-commerce field is solved, the address detection accuracy and transaction efficiency are improved, and more accurate logistics cost calculation is achieved.

CN114528364BActive Publication Date: 2024-12-06GUANGZHOU HUADUO NETWORK TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210150428.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-02-18
Publication Date
2024-12-06
Estimated Expiration
2042-02-18

AI Technical Summary

Technical Problem

In the e-commerce field, there are errors or omissions in the address information submitted by users, which leads to the logistics system being unable to correctly identify it, affecting the punctuality and efficiency of product delivery.

Method used

Using an address information detection method, by obtaining the address information submitted by the client, generating the initial address text, using the edit distance algorithm to match the address characteristics in the preset enumeration address library, and determining the enumeration address with the smallest edit distance as Recommend address text and push it to the client device, supplemented by sliding window word segmentation and similarity calculation to improve detection accuracy.

Benefits of technology

It improves the accuracy of address information detection, reduces the inaccuracy of logistics costs, and improves the interactive efficiency and user experience of the e-commerce transaction process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114528364B_ABST
    Figure CN114528364B_ABST
Patent Text Reader

Abstract

The present application discloses an address information detection method and its device, equipment, medium, and product, the method comprising: obtaining address information submitted by a client device, generating an initial address text according to the address information, wherein the address information includes multiple place names corresponding to multiple administrative levels of a target area; extracting the initial address text by sliding a fixed window according to a preset step length to obtain multiple word segments to form the address features of the initial address text; calculating the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, and determining the enumerated address with the smallest edit distance as the recommended address text; and pushing a notification message containing the recommended address text to the client device. The technical solution of the present application can improve the accuracy of address information recognition in e-commerce orders, guide users to correct erroneous address information, and improve the efficiency of e-commerce order execution.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of e-commerce information processing technology, and in particular to an address information detection method and its corresponding device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] Logistics services are particularly important in the e-commerce sector. Logistics services encompass all the activities from receiving a customer order to delivering the goods to the customer, adding value to the products or services being traded. Their essence is to better meet customer needs, ensuring that the goods they need are delivered on time and within their desired timeframe, and that the service they receive meets their expectations.

[0003] In the logistics service platform in the e-commerce field, the logistics service identifies and extracts the address text provided by the user, and regularly outputs the place names corresponding to each administrative level to assist in the logistics delivery of goods.

[0004] In reality, due to user habits and the lack of address verification mechanisms for some non-platform orders, there are various small errors in the addresses left by users. When merchants use the logistics system to ship goods independently, they find that the system cannot correctly identify the address, resulting in failure to ship normally.

[0005] There are many technical solutions for identifying address information in the existing technology. Most of these solutions use neural network models trained with big data. When used in scenarios where address information is missing, the address information detected and recognized is multiple and the accuracy is limited. Therefore, this application attempts to explore solutions that are closer to actual needs to improve the accuracy of address information detection in the e-commerce field. Summary of the Invention

[0006] The primary purpose of the present application is to solve at least one of the above problems and to provide an address information detection method and its corresponding device, computer equipment, computer-readable storage medium, and computer program product.

[0007] In order to meet the various objectives of this application, this application adopts the following technical solutions:

[0008] An address information detection method provided to meet one of the purposes of this application includes the following steps:

[0009] Obtaining address information submitted by a client device, and generating an initial address text based on the address information, wherein the address information includes a plurality of place names corresponding to a plurality of administrative levels of a target region, the place names including abbreviations of standard place names preset in an administrative place name database of the target region, and the initial address text includes a separator for separating place names of adjacent administrative levels;

[0010] Extracting the initial address text using a fixed window sliding method according to a preset step size to obtain a plurality of segmented words to form address features of the initial address text;

[0011] calculating an edit distance between address features of the initial address text and address features of enumerated addresses in an enumerated address library preset for a target region, and determining an enumerated address with the smallest edit distance as a recommended address text, wherein the enumerated address is composed of standard place names in the administrative place name library according to the administrative hierarchy of the target region;

[0012] Push a notification message containing the recommended address text to the client device.

[0013] In a further embodiment, before calculating the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, the following steps are included:

[0014] Obtain a preset administrative place name database, which contains the abbreviations of all possible standard place names at each administrative level of the target area;

[0015] According to the affiliation of the administrative levels, the abbreviations of the standard place names of each administrative level in the administrative place name database are sequentially spliced ​​to obtain a full enumeration address consisting of an exhaustive combination of all administrative levels;

[0016] For each of the enumerated addresses, extract the enumerated address by sliding a fixed window according to a preset step size to obtain a plurality of segmented words, forming an address feature corresponding to the enumerated address, and constructing mapping relationship data with the enumerated address;

[0017] The mapping relationship data consisting of the full enumeration address and its address characteristics is stored in the enumeration address library.

[0018] In a further embodiment, calculating the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, and determining the enumerated address with the smallest edit distance as the recommended address text includes the following steps:

[0019] Calculate the number of word segments of the address features of the initial address text;

[0020] Calculate the number of word segments of the address feature of any target enumeration address in the enumeration address library;

[0021] Calculate the difference between the sum of the number of segmented words in the initial address text and the target enumeration address and twice the number of identical segmented words between the two as the edit distance between the two;

[0022] All enumerated addresses in the enumerated address library are sorted from small to large according to the edit distance.

[0023] In a preferred embodiment, after sorting all the enumerated addresses in the enumerated address library from small to large according to the edit distance, the following steps are included:

[0024] Determine whether there are multiple enumeration addresses with the same edit distance as candidate enumeration addresses. If so, based on the character length of the address information, for each candidate enumeration address, intercept a partial text with the same character length from the forward and reverse directions respectively;

[0025] Calculating the similarity between the two partial texts and the address information respectively, and obtaining the average similarity between the two;

[0026] The candidate enumerated address with the highest average similarity value is determined as the recommended address text.

[0027] In an extended embodiment, after the step of pushing the notification message containing the recommended address text to the client device, the following steps are included:

[0028] In response to an address correction instruction submitted based on the notification message, the address information in the e-commerce order is corrected using the recommended address text as the delivery address.

[0029] In a specific embodiment, the address information in the e-commerce order is corrected using the recommended address text as the delivery address, including the following steps:

[0030] Replacing the place names of the corresponding administrative levels in the address information of the e-commerce order with the place names set for the recommended address text corresponding to the administrative levels;

[0031] Invoke a preset logistics billing service to calculate the logistics cost of the e-commerce order based on the rates corresponding to the place names of each administrative level in the address information of the e-commerce order;

[0032] The logistics cost is pushed to the client device as an associated item of the e-commerce order for display.

[0033] An address information detection device provided to meet one of the purposes of the present application includes: an initial address acquisition module, a word segmentation feature extraction module, an edit distance optimization module, and a recommended address push module, wherein the initial address acquisition module is used to obtain the address information submitted by the client device and generate an initial address text according to the address information, wherein the address information includes multiple place names corresponding to multiple administrative levels of the target area, the place names include the abbreviations of standard place names preset in the administrative place name library of the target area, and the initial address text includes a separator for separating place names of adjacent administrative levels; word segmentation feature extraction module A module is used to extract the initial address text by sliding a fixed window according to a preset step size to obtain multiple segmentations to constitute the address features of the initial address text; an edit distance optimization module is used to calculate the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, and determine the enumerated address with the smallest edit distance as the recommended address text, wherein the enumerated address is composed of standard place names in the administrative place name library according to the administrative hierarchy affiliation of the target area; a recommended address push module is used to push a notification message containing the recommended address text to the client device.

[0034] In a further embodiment, the edit distance optimization module includes: a place name library calling module for obtaining a preset administrative place name library, which contains the abbreviations of all possible standard place names under each administrative level of the target area; an address enumeration module for orderly splicing the abbreviations of the standard place names of each administrative level in the administrative place name library according to the affiliation of the administrative levels, and obtaining a full enumeration address composed of an exhaustive combination of all administrative levels; an enumeration address extraction module for extracting the enumeration address with a fixed window sliding according to a preset step size for each enumeration address to obtain multiple word segments, constitute the address features corresponding to the enumeration address, and construct mapping relationship data with the enumeration address; an address library construction module for storing the mapping relationship data composed of the full enumeration address and its address features in the enumeration address library.

[0035] In a further embodiment, the edit distance optimization module includes: a first calculation submodule, which is used to calculate the number of word segments of the address feature of the initial address text; a second calculation submodule, which is used to calculate the number of word segments of the address feature of any target enumeration address in the enumeration address library; a distance calculation submodule, which is used to calculate the difference between the sum of the number of word segments of the initial address text and the number of word segments of the target enumeration address and twice the number of the same word segments between the two as the edit distance between the two; an address sorting submodule, which is used to sort all enumeration addresses in the enumeration address library from small to large according to the edit distance.

[0036] In a preferred embodiment, the address sorting submodule includes: an enumeration address determination submodule, which is used to determine whether there are multiple enumeration addresses with the same edit distance as candidate enumeration addresses. If so, based on the character length of the address information, for each candidate enumeration address, local texts with the same character length are intercepted from the forward and reverse directions respectively; a similarity calculation submodule, which is used to calculate the similarity between two local texts and the address information respectively, and calculate the average similarity between the two; an address recommendation submodule, which is used to determine the candidate enumeration address with the highest average similarity as the recommended address text.

[0037] In an extended embodiment, the address information detection device of the present application also includes the following module that is called and run after the recommended address push module: an e-commerce order correction module, which is used to respond to the address correction instruction submitted based on the notification message, and use the recommended address text as the delivery address to correct the address information in the e-commerce order.

[0038] In a specific embodiment, the e-commerce order correction module includes: a place name replacement sub-module, which is used to replace the place names of each corresponding administrative level in the address information of the e-commerce order according to the place names set for each administrative level in the recommended address text; a logistics billing sub-module, which is used to call the preset logistics billing service and calculate the logistics cost of the e-commerce order according to the rates corresponding to the place names of each administrative level in the address information of the e-commerce order; and an order completion sub-module, which is used to push the logistics cost as an associated item of the e-commerce order to the client device for display.

[0039] A computer device provided to meet one of the purposes of the present application includes a central processing unit and a memory, wherein the central processing unit is used to call and run a computer program stored in the memory to execute the steps of the address information detection method described in the present application.

[0040] A computer-readable storage medium is provided to meet another purpose of the present application, which stores a computer program implemented according to the address information detection method in the form of computer-readable instructions. When the computer program is called and executed by a computer, the steps included in the method are executed.

[0041] A computer program product provided to meet another purpose of the present application includes a computer program / instruction, which, when executed by a processor, implements the steps of the method described in any embodiment of the present application.

[0042] According to the typical embodiments and alternative embodiments of the present application, it can be seen that the technical solution of the present application has many advantages, including but not limited to the following aspects:

[0043] First, based on statistical principles, this application uses the enumerated addresses in the enumerated address library constructed according to the standard place names corresponding to the administrative level of the target area as a reference, calculates the edit distance between the initial address text submitted by the client device and each enumerated address, and determines the enumerated address with the smallest edit distance as the recommended address text corresponding to the initial address text. The processed initial address text may include Vietnamese addresses, Thai addresses, English addresses, etc. Since the place names therein include the abbreviations of standard place names preset in the administrative place name library of the target area, the sliding window in the technical solution of this application is used to adjust the window size and / or window movement step as needed to perform more fine-grained word segmentation on the initial address text to form corresponding address features, which can more accurately calculate the edit distance between address features, and quickly determine the enumerated address text that is most similar to the initial address text as the recommended address text, thereby helping to improve detection efficiency.

[0044] Secondly, the technical solution of this application is an algorithm based on statistical implementation when calculating the edit distance between two address texts. It does not need to rely on big data for high-cost training, has higher execution efficiency, and has lower implementation costs. It is suitable for deployment on background servers to respond to massive concurrent demands, thereby obtaining economies of scale.

[0045] In addition, the technical solution of this application is applicable to correcting the address information of e-commerce orders in e-commerce platforms, making the address information of e-commerce orders and the logistics costs calculated based on it more accurate, thereby improving the interaction efficiency during e-commerce transactions and enabling consumer users and merchant users to improve the operational efficiency based on e-commerce orders. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0047] Figure 1 A flowchart of a typical embodiment of the address information detection method of the present application;

[0048] Figure 2 A flowchart of the process of constructing an enumeration address library in an embodiment of the present application is shown;

[0049] Figure 3 Schematic diagram of the process of calculating the edit distance in an embodiment of the present application;

[0050] 4(a) and (b) are respectively principle block diagrams of exemplary applications of the address information detection method of the present application;

[0051] Figure 5 This is a flow chart of the preferred recommended address in the embodiment of the present application;

[0052] Figure 6 This is a flow chart of an extended embodiment of the address information detection method of the present application;

[0053] Figure 7 This is a flowchart of a process for calculating logistics costs based on corrected address information in an extended embodiment of the present application;

[0054] Figure 8 This is a principle block diagram of the address information detection device of this application;

[0055] Figure 9 This is a schematic diagram of the structure of a computer device used in this application. DETAILED DESCRIPTION

[0056] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limiting the present application.

[0057] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any units and all combinations of one or more associated listed items.

[0058] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0059] It will be understood by those skilled in the art that the terms "client," "terminal," and "terminal device" as used herein include both devices that are wireless signal receivers, i.e., devices that only have wireless signal receivers without transmission capabilities, and devices that have receiving and transmitting hardware capable of two-way communication over a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers and tablet computers, which have single-line displays, multi-line displays, or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service), which may combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, Internet / Intranet access, a web browser, a notepad, a calendar, and / or a GPS (Global Positioning System) receiver; and conventional laptop and / or palmtop computers or other devices, which have and / or include a radio frequency receiver. As used herein, the terms "client," "terminal," or "terminal device" may be portable, transportable, or installed in a vehicle (air, sea, and / or land), or may be adapted and / or configured to operate locally and / or in a distributed manner at any other location on Earth and / or in space. As used herein, the terms "client," "terminal," or "terminal device" may also refer to a communication terminal, an Internet terminal, or a music / video playback terminal, such as a PDA, an MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or may include a smart TV, a set-top box, or other device.

[0060] The hardware referred to by names such as "server", "client", and "service node" in this application is essentially an electronic device with capabilities equivalent to those of a personal computer. It is a hardware device that has the necessary components revealed by the von Neumann principle, such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. Computer programs are stored in its memory, and the central processing unit loads the program stored in the external memory into the internal memory for execution, executes the instructions in the program, and interacts with the input and output devices to complete specific functions.

[0061] It should be noted that the concept of "server" referred to in this application can also be extended to server clusters. Based on the network deployment principles understood by those skilled in the art, the servers described should be logically divided. In physical space, these servers can be independent of each other but callable through interfaces, or integrated into a single physical computer or a computer cluster. Those skilled in the art should understand this flexibility and should not use it to constrain the implementation of the network deployment method of this application.

[0062] Unless expressly specified, one or more technical features of the present application can be deployed on a server for implementation and accessed by a client through a remote call to obtain an online service interface provided by the server, or can be directly deployed and run on a client for implementation.

[0063] Unless expressly specified otherwise, the neural network models referenced or may be referenced in this application may be deployed on a remote server and remotely called on the client, or may be deployed and directly called on a client with sufficient device capabilities. In some embodiments, when it runs on the client, its corresponding intelligence may be obtained through transfer learning to reduce the requirements for the client's hardware operating resources and avoid excessive occupation of the client's hardware operating resources.

[0064] Unless explicitly specified, the various data involved in this application can be stored remotely on a server or on a local terminal device, as long as they are suitable for being called by the technical solution of this application.

[0065] Those skilled in the art should be aware that although the various methods of this application are described based on the same concept and thus exhibit commonality, unless otherwise specified, these methods can be independently executed. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept. Therefore, concepts with the same expression, as well as concepts that are appropriately transformed for convenience despite different expression, should be understood as equivalent.

[0066] Unless expressly stated to be mutually exclusive, the various embodiments disclosed in this application may be cross-combined with the relevant technical features of the various embodiments to flexibly construct new embodiments, as long as such combination does not deviate from the creative spirit of this application and can meet the needs of the prior art or resolve certain deficiencies in the prior art. Those skilled in the art should be aware of such flexibility.

[0067] An address information detection method of the present application can be programmed as a computer program product and deployed in a client or server for execution. For example, in the e-commerce platform application scenario of the present application, it is generally deployed in a server for implementation. The method can be executed by accessing the interface opened after the computer program product is run and conducting human-computer interaction with the process of the computer program product through a graphical user interface.

[0068] See also Figure 1 In a typical embodiment, the address information detection method of the present application includes the following steps:

[0069] Step S1100: Acquire address information submitted by a client device, and generate an initial address text based on the address information, wherein the address information includes multiple place names corresponding to multiple administrative levels of a target region, the place names include abbreviations of standard place names preset in an administrative place name database of the target region, and the initial address text includes a separator for separating place names of adjacent administrative levels;

[0070] For e-commerce platforms, the need to detect addresses may occur in various specific business scenarios. For example, when a merchant user needs to send a delivery address to the logistics service interface based on a consumer user's order, or vice versa, when the logistics service interface receives the delivery address; or when a consumer user enters their address information on the order page or the delivery address editing page and submits it to the server, etc., all of these can trigger the detection of the delivery address. The addresses detected in this application include but are not limited to Vietnamese and English.

[0071] In various alternative embodiments, the address information of the present application can be submitted by a consumer user accessing a corresponding page of the e-commerce platform on a client device, such as an address editing page or an order editing page; or by a merchant user accessing certain specialized pages on a client device and submitting the address information corresponding to one or more designated target addresses for detection. It is understood that the source of the address information will vary depending on the specific business scenario, and those skilled in the art should be aware of this.

[0072] The address information is usually managed in units of target areas, such as Vietnam, Thailand, the United States, the United Kingdom, etc. Generally speaking, each target area contains multiple administrative levels, and each administrative level contains multiple place names. The place names include the abbreviations of standard place names preset in the administrative place name database of the target area. For example, the standard place name "SócSo'n" (Shuoshan) corresponds to the abbreviation "Sóc" (Shuo), the latter of which may be omitted by the user for the sake of convenience when entering the address information. The address information submitted by the client device is structurally a text composed of the place names corresponding to these administrative levels arranged in order. For example, "Ha i Sóc ng ” (Chinese translation: Hanoi Shuo Hongji), this address information is the corresponding address in Vietnam, which contains the place names corresponding to administrative levels such as city, county, and street, namely “Ha i City", "Sóc So'n County", " ng Street". According to this example, the address information to be detected submitted by the client device is finally presented in a format that is arranged in a positive and orderly manner according to the customary usage of address information in each region. Furthermore, the names of adjacent administrative levels are separated by English commas as separators, which constitute the initial address text to be detected, such as "Ha i, Sóc, ng ", the separator setting here can be flexibly set by those skilled in the art as needed, so it can also be other alternative characters that serve as a distinction. It can be understood that the administrative place name database can be preset accordingly according to the division of each administrative region announced in the legal form, and the administrative place name database can store place names in units of regions. For example, the database can be built separately according to the Vietnam region, Thailand region, the United States region, and the United Kingdom region. For specific implementation, please refer to other embodiments to be disclosed later in this application, which will not be discussed here for the time being.

[0073] Step S1200: extracting the initial address text by sliding a fixed window according to a preset step size to obtain a plurality of segmented words to form address features of the initial address text;

[0074] In one embodiment, a sliding window with a specific fixed window length is used to perform sliding segmentation on the initial address text. The window length of the sliding window is set to four characters, which include spaces and separators. The preset sliding step of the sliding window can be one character. Thus, the sliding window is slid starting from the first character of the initial address text to obtain a segmentation each time, and then advance one character to continue to obtain the next segmentation, and so on, until the last segmentation is obtained and the sliding segmentation is ended. The number of characters in the last segmentation can be greater than zero and less than or equal to four. It can be understood that, based on this, N-M+1 segmentations are obtained, where N is the total number of characters in the initial address text and M is the window length of the sliding window. The window length setting and the corresponding sliding step setting of the sliding window can be flexibly set by those skilled in the art according to the language characteristics corresponding to the initial address text. The setting can be theoretical or empirical.

[0075] In another embodiment, the N-Gram model based on the statistical language model algorithm can be directly used to implement the process described in the previous embodiment and achieve the same result, thereby avoiding the need to develop related codes by oneself and improving development efficiency.

[0076] It's easy to see that for various languages ​​corresponding to the target region, relatively accurate word segmentation can be achieved by flexibly setting the window length and moving step of the sliding window. For example, for Chinese, considering that single words can express meaning, the moving step can be set to 1 and the window length to 2 Chinese characters. For Vietnamese or Latin languages, the moving step can be set to 1 and the window length to 3 or 4 characters. This shows that this step provides a certain degree of flexibility, facilitating the extraction of address features matching different languages.

[0077] Step S1300: Calculate the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, and determine the enumerated address with the smallest edit distance as the recommended address text, wherein the enumerated address is composed of standard place names in the administrative place name library based on the administrative hierarchy of the target area;

[0078] In order to facilitate the matching of a better recommended address text according to the address features of the initial address text and adapt to any of the target areas, an enumeration address library is pre-constructed, and the enumeration address library stores all possible valid addresses within the target area, that is, enumeration addresses. Of course, the enumeration address is also expressed in the corresponding language. The enumeration address can be pre-collected and prepared by those skilled in the art. Similarly, it is composed of the orderly arrangement of place names corresponding to the various administrative levels of the target area. In addition, the address features corresponding to each enumeration address are also stored in the enumeration address library. The address features can similarly be constructed by performing word segmentation extraction on the enumeration address according to the various embodiments disclosed in the previous step S1200. A subsequent embodiment of this application will further disclose the preparation process of the enumeration address library, which will not be discussed here for the time being.

[0079] From this, it can be seen that the enumerated address library contains all valid addresses within the target area. Since it has been standardized during the preparation stage, in theory, if there are individual typos or missing words (including abbreviations), redundant words, etc. in the initial address text, the enumerated address that is most similar to the initial address text can be used to correct the initial address text.

[0080] In this embodiment, it is recommended to use an edit distance algorithm to calculate the edit distance between the address features of the initial address text and the address features of the enumerated address, thereby obtaining the edit distance corresponding to each enumerated address, wherein the one with the smallest edit distance is the one that is most similar to the initial address text, that is, the closest, meaning that the enumerated address has the fewest typos, missing words, redundant words, etc. relative to the initial address text. Thus, the enumerated address with the smallest edit distance can be determined as the recommended address text for recommendation to the client device. For example, the edit distance calculation formula in the edit distance algorithm is:

[0081] |G N (s)|+|G N (t)|-2×|G N (s)∩G N (t)|

[0082] Among them: G N (s), G N (t) are the total number of segmented words corresponding to the address features of the initial address and the total number of segmented words corresponding to the address features of the enumerated address, respectively. G N (s)∩G N (t) is the total number of word segments corresponding to the similarity between the initial address and the enumerated address.

[0083] Step S1400: Push a notification message containing the recommended address text to the client device.

[0084] After the server determines the recommended address text corresponding to the initial address text, it can encapsulate the recommended address text in a notification message and push it to the client device, and display and use the recommended address text according to the business logic corresponding to the specific business scenario currently being executed. For example, when in a business scenario where a consumer user edits address information, the recommended address text can be displayed on their client device to remind the user whether to replace the currently entered address information. For another example, when in a business scenario where the delivery address of an e-commerce order is corrected in the background, the recommended address text can replace the original delivery address in the e-commerce order and output a corresponding notification message to the client device where the operating user is located as a reminder, and the recommended address text is included in the notification message. In this way, those skilled in the art can flexibly utilize the recommended address text according to different specific business scenarios, and ultimately display it on the client device to be perceived by the user.

[0085] According to the typical embodiments and alternative embodiments of the present application, it can be seen that the technical solution of the present application has many advantages, including but not limited to the following aspects:

[0086] First, based on statistical principles, this application uses the enumerated addresses in the enumerated address library constructed according to the standard place names corresponding to the administrative level of the target area as a reference, calculates the edit distance between the initial address text submitted by the client device and each enumerated address, and determines the enumerated address with the smallest edit distance as the recommended address text corresponding to the initial address text. The processed initial address text may include Vietnamese addresses, Thai addresses, English addresses, etc. Since the place names therein include the abbreviations of standard place names preset in the administrative place name library of the target area, the sliding window in the technical solution of this application is used to adjust the window size and / or window movement step as needed to perform more fine-grained word segmentation on the initial address text to form corresponding address features, which can more accurately calculate the edit distance between address features, and quickly determine the enumerated address text that is most similar to the initial address text as the recommended address text, thereby helping to improve detection efficiency.

[0087] Secondly, the technical solution of this application is an algorithm based on statistical implementation when calculating the edit distance between two address texts. It does not need to rely on big data for high-cost training, has higher execution efficiency, and has lower implementation costs. It is suitable for deployment on background servers to respond to massive concurrent demands, thereby obtaining economies of scale.

[0088] In addition, the technical solution of this application is applicable to correcting the address information of e-commerce orders in e-commerce platforms, making the address information of e-commerce orders and the logistics costs calculated based on it more accurate, thereby improving the interaction efficiency during e-commerce transactions and enabling consumer users and merchant users to improve the operational efficiency based on e-commerce orders.

[0089] See also Figure 2 In a further embodiment, before step S1300, calculating the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, the following steps are included:

[0090] Step S1201: Obtain a preset administrative place name database, which contains the abbreviations of all possible standard place names at each administrative level of the target area;

[0091] The administrative divisions of each region are publicly released in a legal form. Therefore, the administrative place name database corresponding to each region can be collected. The administrative place name database can store place names in units of regions, for example, separately building databases according to Vietnam and Thailand. In each administrative place name database, all possible place names under each administrative level of its corresponding target region can be stored, and the affiliation between each administrative level is established based on the jurisdictional relationship between the place names, thereby completing the construction of the administrative place name database. Since the place names of the upper administrative level and the place names of the administrative level below it are generally a one-to-many relationship, in a more specific embodiment, it is recommended to use a tree storage structure or a directed graph structure to store the place names of each administrative lower level, so that the ordered splicing result between the place names of each node passed by the path formed between the root node and the end node in the tree storage structure or directed graph structure constitutes a valid address of the target region.

[0092] Step S1202: sequentially concatenate the abbreviations of the standard place names of each administrative level in the administrative place name database according to the affiliation of the administrative levels, and obtain a full enumeration address consisting of an exhaustive combination of all administrative levels;

[0093] On the basis of the aforementioned administrative place name database, it is very convenient to obtain the full range of valid addresses of the target area. Specifically, according to the jurisdictional relationship between the superior place names and the subordinate place names in the administrative place name database, the place names at each level can be sequentially spliced ​​together to complete the enumeration of the valid addresses of the target area, that is, to obtain the full range of enumeration addresses of the target area. Combined with the example of the tree storage structure or directed graph structure described above, according to the path of the purple qi root node to each of its terminal nodes in this structure, the string formed by splicing the place names is an enumeration address, and there are multiple enumeration addresses corresponding to multiple terminal nodes.

[0094] Step S1203: for each of the enumerated addresses, extract the enumerated address by sliding a fixed window according to a preset step size to obtain a plurality of segmented words, constitute an address feature corresponding to the enumerated address, and construct mapping relationship data with the enumerated address;

[0095] To facilitate the subsequent calculation of the edit distance between each enumerated address and the initial address text, this embodiment also adopts the same method as the initial address text to obtain address features. A sliding window with a fixed length of 4 characters and a preset sliding step size of 1 character is used to slide the sliding window for each enumerated address to perform word segmentation. The word segmentation set corresponding to each enumerated address is obtained to form the corresponding address feature, and each enumerated address and its address feature are constructed as mapping relationship data. Those skilled in the art will understand that the fixed length of the sliding window and the preset sliding step size can be flexibly set to accommodate the language characteristics corresponding to different languages. For example, for Vietnamese, a fixed length of 4 characters can be set, with a preset sliding step size of 1 character; for Thai, a fixed length of 5 characters can be set, with a preset sliding step size of 1 character. Thus, each enumerated address has a corresponding address feature. Similarly, the N-Gram model can also be used to calculate the address features of enumerated addresses.

[0096] Step S1204: storing the mapping relationship data formed by the full enumeration address and its address characteristics in the enumeration address library.

[0097] In order to facilitate the calculation of the comparative edit distance when detecting the validity of the initial address text in this application, the mapping relationship data between the enumerated address and the address feature obtained in the previous step can be stored in a database to constitute the enumerated address library described in this application for call.

[0098] This embodiment performs full enumeration based on the administrative place name database to generate an enumeration address database. The enumeration address database stores a full set of valid enumeration address of the corresponding target area. The enumeration address database provides a pre-segmented address feature for each enumeration address, which can be used for calculating the edit distance during initial address text detection. Since the enumeration address database is constructed based on the administrative place name database composed of collected legal place names, the validity and accuracy of the enumeration addresses in the enumeration address database are authoritatively guaranteed, and the validity of the initial address text can be detected based on this, which is more accurate and reliable.

[0099] See also Figure 3 In a further embodiment, step S1300, calculating the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, and determining the enumerated address with the smallest edit distance as the recommended address text, includes the following steps:

[0100] Step S1310: Calculate the number of segmented words of the address feature of the initial address text;

[0101] As shown in FIG4 (a), in this embodiment, the sliding window method as described above or the N-Bram model can be used to first calculate the number of word segments of the initial address text. In one embodiment, the initial address text address is “Ha i, Sóc, ng ” contains 15 participles, so the number of its participles is 15 as shown in 100 in Figure 4(a).

[0102] Step S1320: Calculate the number of segmented words of the address feature of any target enumerated address in the enumerated address library;

[0103] Similarly, the address features of any target enumerated address in the enumerated address library are calculated in exactly the same way as in the previous step. In one embodiment, the enumerated address library is a Vietnamese address library, and commas are added between the character strings corresponding to the place names at each level in the valid enumerated address to obtain "Hà i, Sóc So'n, ng ” (Chinese translation: Hanoi, Shuoshan, Hongji), “Hà i, Sóc So'n, Nam So'n" (Chinese translation: Hanoi, Shuoshan, Nanshan) contains 19 participles respectively, so the number of participles is 19 as shown in 101 and 102 in Figure 4(a). Of course, in other embodiments, the number of participles of each enumeration address can also be calculated in advance and associated with the corresponding enumeration address and stored in the enumeration address library. In this case, there is no need to calculate it separately in the step and it can be directly called.

[0104] Step S1330: Calculate the difference between the sum of the number of segmented words in the initial address text and the number of segmented words in the target enumerated address and twice the number of identical segmented words between the two as the edit distance between the two.

[0105] Continuing with the example of the enumerated address in the previous step, after determining the number of segmented words contained in the address features of the initial address text and the enumerated address, it can be used to determine the number of segmented words between the initial address text and the enumerated address to calculate the edit distance between them. Specifically, first calculate the sum of the number of segmented words corresponding to the initial address text and the enumerated address, which is 15+19=34, and then subtract twice the total number of segmented words shared by the two, that is, there are 5 segmented words that are the same between the two, so the total number of segmented words that are the same is 10. Therefore, 34-10=24, which is the sum of the number of segmented words in the aforementioned enumerated address "Hà i, SócSo'n, ng ”, “Hà i, Sóc So'n, Nam So'n" with the initial address text "Ha i, Sóc, ng The edit distance between them is 24.

[0106] Step S1340: sort all the enumerated addresses in the enumerated address library from smallest to largest according to the edit distance.

[0107] It's easy to understand that, following the previous steps, the edit distance between each enumerated address in the enumerated address library and the initial address text can be calculated. This yields an edit distance sequence for each enumerated address in the enumerated address library. This edit distance sequence is sorted from smallest to largest edit distance. The enumerated address with the highest edit distance is the target enumerated address with the smallest difference from the initial address text.

[0108] This embodiment provides a method for determining the edit distance between the initial address text and the enumerated address based on the number of word segments of both, and then determining the recommended enumerated address based on the minimum value of the edit distance. It can be seen that this method is simple and fast to calculate, has low occupation of computer operating resources, and can obtain calculation results relatively quickly, making the address detection process both accurate and efficient.

[0109] See also Figure 5 In a preferred embodiment, after step S1340, sorting all the enumerated addresses in the enumerated address library from small to large according to the edit distance, the following steps are included:

[0110] Step S1341: Determine whether there are multiple enumeration addresses with the same edit distance as candidate enumeration addresses. If so, based on the character length of the address information, for each candidate enumeration address, intercept a partial text with the same character length from the forward and reverse directions respectively;

[0111] Further, according to the judgment that there are multiple enumerated addresses with the same edit distance in the edit distance sequence, these enumerated addresses are used as the candidate addresses. If the candidate addresses exist, the character segmentation of these candidate addresses and the address information is performed accordingly, and the uppercase characters therein are converted into lowercase characters to obtain the corresponding character strings as shown in 200 and 204 in Figure 4(b) and 202 in Figure 4(b). Accordingly, if the character length of the former character string is greater than the character length of the latter character string, the character string corresponding to the candidate address is forwardly intercepted with the character length of the character string corresponding to the address information as shown in 201 and 205 in Figure 4(b), and the forward intercepted character string with the same character length as the address information is obtained as a character string composed of the remaining characters. Furthermore, if the character length of the character string composed of the remaining characters is less than the character length of the character string corresponding to the address information, the character string corresponding to the candidate address is reversely intercepted with the character length of the character string corresponding to the address information as shown in 203 and 206 in Figure 4(b), and the reverse intercepted character string with the same character length as the address information is obtained as another partial text.

[0112] Step S1342: Calculate the similarity between the two partial texts and the address information respectively, and obtain the average similarity between the two;

[0113] Referring to FIG4(b), first, determine the common similar characters in the character strings corresponding to the two partial texts and the address information, for example, the character string "hà" corresponding to the partial text 201 in the above example FIG4(b) isócso' n" and the character string corresponding to the address information " isó ", the common similar characters are " There are nine "isócnh" in total; the string corresponding to the 203 local texts in Figure 4(b) is " isócso' " and the string corresponding to the address information" isó ", the common similar characters are " There are nine "isócnhng" in total. Secondly, the number of characters with similar characters is divided by the length of the character string of the corresponding local text to calculate the similarity between the two local texts. Accordingly, the degree of the character string corresponding to the 201 local text in Figure 4(b) is 9 / 14=0.6429, and the degree of the character string corresponding to the 203 local text in Figure 4(b) is 9 / 14=0.6429. The average of the similarities between the two is further calculated, and the similarity between the candidate address and the address information is obtained.

[0114] Step S1343: Determine the candidate enumerated address with the highest average similarity value as the recommended address text.

[0115] The candidate enumerated addresses are sorted in descending order of the average similarity. The candidate enumerated address ranked first and having the highest average similarity is selected as the recommended address text. For example, in the Vietnamese text example shown in FIG4(b), the similarities of the candidate enumerated addresses calculated through the above steps are 0.6429 and 0.6072, respectively. After sorting them accordingly, the candidate enumerated address with the highest similarity of 0.6429 is selected as the recommended address text.

[0116] In this embodiment, the enumerated addresses in the enumerated address library constructed according to the place names corresponding to the administrative level of the target area are used as a reference. After calculating the edit distance between the initial address text submitted by the client device and each enumerated address, the multiple enumerated addresses with the smallest parallel edit distance are further subjected to character segmentation, and the similarity is calculated with the initial address text that has undergone the same character segmentation. The enumerated address with the highest similarity is determined as the recommended address text corresponding to the initial address text. Accordingly, after the edit distance calculation and the subsequent further fine-grained similarity calculation, the accuracy of the recommended address text in the detection and recognition results is greatly improved.

[0117] Secondly, the technical solution of the present application calculates the edit distance between the initial address text and the enumerated addresses in the enumerated address library, and then performs a subsequent similarity calculation with a finer granularity on the enumerated addresses with the smallest parallel edit distance. Compared with directly performing character segmentation on the initial address text and the enumerated addresses in the enumerated address library at the beginning and then calculating the similarity, the technical solution of the present application undoubtedly greatly reduces the amount of calculation while ensuring the same results, and has higher execution efficiency. It is suitable for deployment on background servers to respond to massive concurrent demands, thereby obtaining economies of scale.

[0118] See also Figure 6 In an extended embodiment, after step S1400, the step of pushing a notification message including the recommended address text to the client device, the following steps are included:

[0119] Step S1500: In response to the address correction instruction submitted based on the notification message, the address information in the e-commerce order is corrected using the recommended address text as the delivery address.

[0120] For the scenario where consumer users place an order, when they obtain the notification message pushed by the aforementioned embodiments of this embodiment based on the address information in their e-commerce order, and obtain the recommended address text in the notification message, the user can determine whether to replace the address information they have selected or entered in advance with the recommended address text. When they decide to make the correction, an address correction instruction is triggered and sent to the server. The server can then modify the data corresponding to the e-commerce order in the background, and replace the address information in the delivery address with the corresponding content in the recommended address text, thereby realizing intelligent error correction of the address information entered by the user based on the detection results, and improving the address detection and error correction accuracy of e-commerce orders.

[0121] See also Figure 7 In a specific embodiment, step S1500, using the recommended address text as the delivery address to correct the address information in the e-commerce order, includes the following steps:

[0122] Step S1510: Replace the place names of the corresponding administrative levels in the address information of the e-commerce order with the place names corresponding to the administrative levels in the recommended address text;

[0123] More specifically, after a consumer user submits the address correction instruction, the server corrects the corresponding address information in the consumer user's e-commerce order based on the corresponding recommended address text. As previously mentioned, since the recommended address text is composed of place names corresponding to each administrative level, the corresponding place names for each administrative level can be determined by referring to the administrative place name database. Based on this, the place names for each corresponding administrative level in the original address information of the e-commerce order can be directly replaced.

[0124] Step S1520: Invoke a preset logistics billing service to calculate the logistics cost of the e-commerce order based on the rates corresponding to the place names at each administrative level in the address information of the e-commerce order;

[0125] More specifically, after a consumer user submits the address correction instruction, the server corrects the corresponding address information in the consumer user's e-commerce order based on the corresponding recommended address text. As previously mentioned, since the recommended address text is composed of place names corresponding to each administrative level, the corresponding place names for each administrative level can be determined by referring to the administrative place name database. Based on this, the place names for each corresponding administrative level in the original address information of the e-commerce order can be directly replaced.

[0126] Step S1530: Push the logistics cost as an associated item of the e-commerce order to the client device for display.

[0127] To facilitate confirmation by consumer users, the logistics cost can be further used as an associated item of the e-commerce order and pushed to the client device where the consumer user is located for display. After the consumer user knows the corresponding delivery address, logistics cost, product price and other information of the e-commerce order, he can confirm and submit the e-commerce order, enter the payment stage, and finally complete the order.

[0128] This embodiment further performs logistics cost billing based on the corrected address information, making the calculation of freight more accurate, ensuring the accuracy of e-commerce transaction information, and facilitating the steady development of the e-commerce platform.

[0129] See also Figure 8 , an address information detection device provided to meet one of the purposes of the present application is a functional embodiment of the address information detection method of the present application, the device includes: an initial address acquisition module 1100, a word segmentation feature extraction module 1200, an edit distance optimization module 1300, and a recommended address push module 1400, wherein the initial address acquisition module 1100 is used to obtain the address information submitted by the client device and generate an initial address text according to the address information, wherein the address information includes multiple place names corresponding to multiple administrative levels of the target area, the place names include the abbreviations of standard place names preset in the administrative place name library of the target area, and the initial address text includes a prefix for separating adjacent lines. a separator for administrative-level place names; a word segmentation feature extraction module 1200, used to extract the initial address text by sliding a fixed window according to a preset step size to obtain multiple word segments to constitute the address features of the initial address text; an edit distance optimization module 1300, used to calculate the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, and determine the enumerated address with the smallest edit distance as the recommended address text, wherein the enumerated address is composed of standard place names in the administrative place name library according to the administrative-level affiliation of the target area; a recommended address push module 1400, used to push a notification message containing the recommended address text to the client device.

[0130] In a further embodiment, the edit distance optimization module 1300 includes: a place name library calling module for obtaining a preset administrative place name library, which contains the abbreviations of all possible standard place names under each administrative level of the target area; an address enumeration module for orderly splicing the abbreviations of the standard place names of each administrative level in the administrative place name library according to the affiliation of the administrative levels, and obtaining a full enumeration address composed of an exhaustive combination of all administrative levels; an enumeration address extraction module for extracting the enumeration address with a fixed window sliding according to a preset step size for each enumeration address to obtain multiple word segments, constitute the address features corresponding to the enumeration address, and construct mapping relationship data with the enumeration address; an address library construction module for storing the mapping relationship data composed of the full enumeration address and its address features in the enumeration address library.

[0131] In a further embodiment, the edit distance optimization module 1300 includes: a first calculation submodule, used to calculate the number of word segments of the address feature of the initial address text; a second calculation submodule, used to calculate the number of word segments of the address feature of any target enumeration address in the enumeration address library; a distance calculation submodule, used to calculate the difference between the sum of the number of word segments of the initial address text and the number of word segments of the target enumeration address and twice the number of the same word segments between the two as the edit distance between the two; an address sorting submodule, used to sort all enumeration addresses in the enumeration address library from small to large according to the edit distance.

[0132] In a preferred embodiment, the address sorting submodule includes: an enumeration address determination submodule, which is used to determine whether there are multiple enumeration addresses with the same edit distance as candidate enumeration addresses. If so, based on the character length of the address information, for each candidate enumeration address, local texts with the same character length are intercepted from the forward and reverse directions respectively; a similarity calculation submodule, which is used to calculate the similarity between two local texts and the address information respectively, and calculate the average similarity between the two; an address recommendation submodule, which is used to determine the candidate enumeration address with the highest average similarity as the recommended address text.

[0133] In an extended embodiment, the address information detection device of the present application also includes the following module that is called and run after the recommended address push module 1400: an e-commerce order correction module, which is used to respond to the address correction instruction submitted based on the notification message, and use the recommended address text as the delivery address to correct the address information in the e-commerce order.

[0134] In a specific embodiment, the e-commerce order correction module includes: a place name replacement sub-module, which is used to replace the place names of each corresponding administrative level in the address information of the e-commerce order according to the place names set for each administrative level in the recommended address text; a logistics billing sub-module, which is used to call the preset logistics billing service and calculate the logistics cost of the e-commerce order according to the rates corresponding to the place names of each administrative level in the address information of the e-commerce order; and an order completion sub-module, which is used to push the logistics cost as an associated item of the e-commerce order to the client device for display.

[0135] In order to solve the above technical problems, the embodiment of the present application also provides a computer device. Figure 9 As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. Among them, the computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor may implement an address information detection method. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may execute the address information detection method of the present application. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0136] In this embodiment, the processor is used to execute Figure 8 The memory stores the program code and various data required to execute the specific functions of each module and its submodule in the address information detection device of the present application. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program code and data required to execute all modules / submodules in the address information detection device of the present application, and the server can call the server's program code and data to execute the functions of all submodules.

[0137] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the address information detection method of any embodiment of the present application.

[0138] The present application also provides a computer program product, comprising a computer program / instruction, which implements the steps of the method described in any embodiment of the present application when executed by one or more processors.

[0139] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments of the present application can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of the method. The aforementioned storage medium can be a computer-readable storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0140] To summarize, the enumerated addresses in the enumerated address library constructed based on the place names corresponding to the administrative level of the target area are used as a reference. After calculating the edit distance between the initial address text submitted by the client device and each enumerated address, the multiple enumerated addresses with the smallest parallel edit distance are further segmented by characters, and the similarities are calculated with the initial address texts that have undergone the same character segmentation. The enumerated address with the highest similarity is determined as the recommended address text corresponding to the initial address text. Based on this, after the edit distance calculation and subsequent further fine-grained similarity calculation, the accuracy of the recommended address text in the detection and recognition results is greatly improved.

[0141] Those skilled in the art will appreciate that the steps, measures, and schemes in the various operations, methods, and processes discussed in this application may be interchanged, modified, combined, or deleted. Furthermore, other steps, measures, and schemes in the various operations, methods, and processes discussed in this application may also be interchanged, modified, rearranged, decomposed, combined, or deleted. Furthermore, steps, measures, and schemes in the prior art that are similar to those disclosed in this application may also be interchanged, modified, rearranged, decomposed, combined, or deleted.

[0142] The above description is only part of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for detecting address information, It is characterized in that The steps include: Acquire address information submitted by the client device, and generate an initial address text according to the address information, wherein the address information includes a plurality of place names corresponding to a plurality of administrative levels of a target region, the place names include abbreviations of standard place names preset in an administrative place name library of the target region, and the initial address text includes a separator for separating place names of adjacent administrative levels; Extracting the initial address text by sliding a fixed window according to a preset step length to obtain a plurality of segmented words, so as to form address features of the initial address text; Calculating the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, and determining the enumerated address with the smallest edit distance as the recommended address text, including: calculating the number of segmented words of the address features of the initial address text; calculating the number of segmented words of the address features of any target enumerated address in the enumerated address library; calculating the difference between the sum of the number of segmented words of the initial address text and the number of segmented words of the target enumerated address and twice the number of the same segmented words between the two as the edit distance between the two; sorting all the enumerated addresses in the enumerated address library from small to large according to the edit distance; the enumerated address is composed of standard place names in the administrative place name library according to the administrative hierarchy affiliation of the target area; Pushing a notification message including the recommended address text to the client device; In response to the address correction instruction submitted based on the notification message, the address information in the e-commerce order is corrected using the recommended address text as the delivery address, including: replacing the place names of the corresponding administrative levels in the address information of the e-commerce order according to the place names set for each administrative level according to the recommended address text; calling the preset logistics billing service to calculate the logistics cost of the e-commerce order according to the rates corresponding to the place names of each administrative level in the address information of the e-commerce order; and pushing the logistics cost as an associated item of the e-commerce order to the client device for display.

2. The address information detection method according to claim 1, It is characterized in that Before calculating the edit distance between the address feature of the initial address text and the address feature of the enumerated address in the enumerated address library preset for the target area, the following steps are included: Obtain a preset administrative place name database, which contains the abbreviations of all possible standard place names at each administrative level of the target area; According to the subordinate relationship of the administrative levels, the abbreviations of the standard place names of each administrative level in the administrative place name database are sequentially spliced ​​to obtain a full enumeration address consisting of an exhaustive combination of all administrative levels; For each of the enumerated addresses, extract the enumerated address by sliding with a fixed window according to a preset step length to obtain a plurality of segmented words, constitute an address feature corresponding to the enumerated address, and construct a mapping relationship data with the enumerated address; The mapping relationship data consisting of the full enumeration address and its address characteristics is stored in the enumeration address library.

3. The address information detection method according to claim 1, It is characterized in that After all the enumeration addresses in the enumeration address library are sorted from small to large according to the edit distance, the following steps are included: Determine whether there are multiple enumeration addresses with the same edit distance as candidate enumeration addresses. If so, based on the character length of the address information, for each candidate enumeration address, intercept a partial text with the same character length from the forward direction and the reverse direction respectively; Calculate the similarity between the two local texts and the address information respectively, and obtain the average similarity between the two; The candidate enumerated address with the highest average similarity is determined as the recommended address text.

4. An address information detection device, It is characterized in that include: An initial address acquisition module, used to acquire address information submitted by a client device, and generate an initial address text according to the address information, wherein the address information includes a plurality of place names corresponding to a plurality of administrative levels of a target region, the place names include abbreviations of standard place names preset in an administrative place name library of the target region, and the initial address text includes a separator for separating place names of adjacent administrative levels; A word segmentation feature extraction module, used to extract the initial address text by sliding a fixed window according to a preset step length to obtain a plurality of word segments to form address features of the initial address text; The edit distance optimization module is used to calculate the edit distance between the address features of the initial address text and the address features of the enumerated addresses in the enumerated address library preset for the target area, and determine the enumerated address with the smallest edit distance as the recommended address text, including: calculating the number of segmented words of the address features of the initial address text; calculating the number of segmented words of the address features of any target enumerated address in the enumerated address library; calculating the difference between the sum of the number of segmented words of the initial address text and the number of segmented words of the target enumerated address and twice the number of the same segmented words between the two as the edit distance between the two; sorting all the enumerated addresses in the enumerated address library from small to large according to the edit distance; the enumerated address is composed of standard place names in the administrative place name library according to the administrative hierarchy affiliation of the target area; A recommended address push module is used to push a notification message containing the recommended address text to the client device, and respond to an address correction instruction submitted based on the notification message, to correct the address information in the e-commerce order using the recommended address text as the delivery address, including: replacing the place names of the corresponding administrative levels in the address information of the e-commerce order according to the place names set for each administrative level according to the recommended address text; calling a preset logistics billing service to calculate the logistics cost of the e-commerce order according to the rates corresponding to the place names of each administrative level in the address information of the e-commerce order; and pushing the logistics cost as a related item of the e-commerce order to the client device for display.

5. A computer device comprising a central processing unit and a memory, It is characterized in that The central processing unit is used to call and run the computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, It is characterized in that It stores a computer program implemented according to the method described in any one of claims 1 to 3 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

7. A computer program product comprising a computer program / instructions, It is characterized in that When the computer program / instructions are executed by a processor, the steps of the method described in any one of claims 1 to 3 are implemented.