Method, device and electronic device for automatically identifying and completing address information

By performing structured splitting of addresses and matching of hierarchical categories, the problem of high error rate of address information completion in the existing technology is solved, and a more accurate address completion effect is achieved.

CN118626687BActive Publication Date: 2024-11-19ZHEJIANG ZHENSHU TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411103109.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-11-19
Estimated Expiration
2044-08-13

AI Technical Summary

Technical Problem

The existing technology has a high error rate when renamed in address information completion, and the effect is not ideal, and it cannot effectively solve the problems of delivery delays and items loss caused by incomplete address information.

Method used

By obtaining the standard addresses for structured splitting, a standard subaddress table of different levels is constructed, and string matching is performed based on the order of hierarchical categories, weights are allocated according to the degree of matching, and finally the completed address is determined through weighting calculation.

Benefits of technology

It improves the accuracy and effectiveness of address completion, reduces the error rate, and ensures the accuracy and reliability of address information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118626687B_ABST
    Figure CN118626687B_ABST
Patent Text Reader

Abstract

The embodiments of this specification disclose a method, device and electronic device for automatic identification and completion of address information. The method includes structurally splitting a standard address to obtain standard sub-addresses of different levels, dividing each level into different level categories, and then constructing a standard address table; structurally splitting the address to be identified to obtain each sub-address to be identified, and filling it into a preset address identification table; performing string matching of each level category on the standard address table and the address identification table, and after each match, assigning a weight to each matching result; calculating the weighted value corresponding to each first standard address, and completing the address to be identified based on the second standard address with the largest weighted value. The embodiments of this specification can more accurately complete the address by determining the weights according to the level category, and then calculating the weighted value of each first standard address that can be matched according to the weight, so as to achieve a better completion effect.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] One or more embodiments of the present specification relate to information processing technology, and more particularly, to a method, device and electronic device for automatically identifying and completing address information. Background Art

[0002] In today's increasingly digital environment, many business scenarios require filling in addresses, and incomplete address information is a common problem in daily life. Incomplete address filling may lead to delivery delays, lost or undelivered items. For example, when opening a bank account, applying for a credit card or loan, you need to provide a residential address as part of your identity verification. If banks and financial institutions are unable to send important documents due to incorrect addresses, customers may miss important financial operations such as bill payments and investment operations. Therefore, automatic recognition and completion of address information is particularly important. At present, the existing technology generally completes missing address information through knowledge graph matching. This method has a high completion error rate when duplicate names occur, and the completion effect is not ideal. Summary of the invention

[0003] In order to solve the above problems, one or more embodiments of this specification describe a method, device and electronic device for automatically identifying and completing address information.

[0004] According to a first aspect, a method for automatically identifying and completing address information is provided, the method comprising:

[0005] Obtain a standard address, perform structural decomposition on the standard address to obtain standard sub-addresses of different levels, and divide each level into different level categories based on a preset division rule, and then construct a standard address table based on each of the standard sub-addresses, wherein each level category corresponds to at least two adjacent levels;

[0006] When an address to be identified is detected, the address to be identified is structurally split to obtain sub-addresses to be identified, and each sub-address to be identified is filled into a preset address identification table according to the hierarchy;

[0007] Based on the priority order of the hierarchical categories, the string matching of each hierarchical category is performed on the standard address table and the address identification table in turn, and after each matching is completed, a weight is assigned to each matching result based on the matching degree, and the hierarchical category corresponding to the hierarchical category with a higher average level has a higher hierarchical category priority;

[0008] The weighted value corresponding to each first standard address having a matching result is calculated, and the address to be identified is completed based on the second standard address with the largest weighted value.

[0009] Preferably, the constructing a standard address table based on each of the standard sub-addresses includes:

[0010] A unique code is set for each of the standard sub-addresses respectively, and a standard address table is constructed based on each of the standard sub-addresses and the unique code. The encoding rules for the unique codes corresponding to the standard sub-addresses of different hierarchical categories are different.

[0011] Preferably, the hierarchy categories include administrative area address hierarchy, detailed address hierarchy and precise address hierarchy.

[0012] Preferably, the step of sequentially matching the character strings of the standard address table and the address identification table according to the hierarchy category priority order includes:

[0013] Determine the target hierarchical category to be matched based on the hierarchical category priority order, perform matching calculation on the first character string of the target hierarchical category in the standard address table and the second character string of the target hierarchical category in the address identification table, and obtain each matching result;

[0014] The step of determining the target hierarchical category to be matched based on the hierarchical category priority order is repeated until the character strings of all hierarchical categories have completed the matching calculation.

[0015] Preferably, after each matching is completed, a weight is assigned to each matching result based on the matching degree, including:

[0016] After each matching is completed, the matching degree corresponding to each matching result is determined, the matching results with matching degrees lower than a preset matching degree are deleted, and weights are assigned to the remaining matching results based on the matching degrees.

[0017] Preferably, the step of calculating the weighted value corresponding to each first standard address having a matching result includes:

[0018] For each first standard address with a matching result, the weight corresponding to each of the hierarchical categories in the first standard address is determined, and based on the weight, a weighted calculation is performed on the preset weights corresponding to each of the hierarchical categories to obtain a weighted value of the first standard address.

[0019] Preferably, the method further comprises:

[0020] Every time a preset time period passes, the standard address table is updated based on the standard addresses newly acquired within the preset time period.

[0021] According to a second aspect, a device for automatically identifying and completing address information is provided, the device comprising:

[0022] An acquisition module, used to acquire a standard address, perform structural decomposition on the standard address to obtain standard sub-addresses of different levels, and after dividing each level into different level categories based on a preset division rule, construct a standard address table based on each of the standard sub-addresses, wherein each level category corresponds to at least two adjacent levels;

[0023] A filling module is used for, when an address to be identified is detected, structurally splitting the address to be identified to obtain sub-addresses to be identified, and filling each sub-address to be identified into a preset address identification table according to the hierarchy;

[0024] A matching module, used for matching the character strings of the hierarchical categories of the standard address table and the address identification table in sequence based on the hierarchical category priority order, and after each matching, assigning a weight to each matching result based on the matching degree, wherein the hierarchical category with a higher average level has a higher hierarchical category priority;

[0025] The calculation module is used to calculate the weighted value corresponding to each first standard address with a matching result, and complete the address to be identified based on the second standard address with the largest weighted value.

[0026] According to a third aspect, there is provided an electronic device, comprising a processor and a memory;

[0027] The processor is connected to the memory;

[0028] The memory is used to store executable program code;

[0029] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0030] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a processor, cause the computer or the processor to execute the method provided in the first aspect or any possible implementation of the first aspect.

[0031] The method and device provided in the embodiments of this specification can structurally split the address, and then match only the string corresponding to a certain level category according to the level category priority order of the sub-addresses of different levels corresponding to the level category, and assign weights to each matching result of each match according to the matching degree, and finally perform weighted calculation on the first standard address with a matching result, and use the second standard address with the largest weighted value as the completed address. By determining the weights according to the level category, and then calculating the weighted value of each first standard address that can be matched according to the weights, the address can be completed more accurately, and the completion effect is better. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 It is a flowchart of a method for automatically identifying and completing address information in one embodiment of this specification.

[0034] Figure 2 It is a structural diagram of an address information automatic identification and completion device in one embodiment of the present specification.

[0035] Figure 3 It is a structural diagram of an electronic device in one embodiment of this specification. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0037] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application, and different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, although the embodiment may not be clearly recorded in the following text.

[0038] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present application. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described in some examples may be combined in other examples.

[0039] See also Figure 1 , Figure 1 : is a flowchart of a method for automatically identifying and completing address information provided in an embodiment of the present application. In an embodiment of the present application, the method includes:

[0040] S101, obtaining a standard address, performing structural decomposition on the standard address to obtain standard sub-addresses of different levels, and dividing each level into different level categories based on a preset division rule, and then constructing a standard address table based on each standard sub-address.

[0041] Each of the hierarchical categories is divided into at least two adjacent hierarchical levels.

[0042] The execution entity of this application can be a cloud server.

[0043] In the embodiments of the present specification, the cloud server will first obtain the standard address from various public databases according to the pre-set address acquisition path. The standard address is an address without omissions. After obtaining the standard address, the cloud server will perform a structured splitting of the standard address to split each standard address into standard sub-addresses of different levels. The larger the area covered by the sub-address, the higher the corresponding level. Then, the cloud server will divide each level according to the preset division rules to divide multiple adjacent levels into the same level category, so as to facilitate the subsequent simultaneous processing of sub-addresses of multiple levels in the same level category. After completing the splitting of the standard sub-addresses and the division of the level categories, a standard address table will be constructed based on these standard sub-addresses, and the standard address table will be used as a standard reference table for field matching queries and other operations. Among them, the preset division rule can be set according to the actual situation. Assuming that there are 12 levels in total after the standard address is divided, the preset division rule can be to use a continuous fixed number of levels as a level category. Assuming that the fixed number is three, that is, levels 1-3, levels 4-6, levels 7-9, and levels 10-12 are each a level category. The preset division rule can also be to directly set different numbers of levels for different level categories, for example, levels 1-3, levels 4-8, and levels 9-12 are each a level category, and other implementable methods can also be used.

[0044] As an example, after structural decomposition, the composite address structure of a standard address can be decomposed into hierarchical levels to represent the standard sub-addresses of provinces, cities, counties (cities, districts), streets (townships), communities (administrative villages), streets and lanes, communities, buildings, door addresses, building addresses, units, floors, and households. Provinces have the largest coverage, so their corresponding level is the highest level, and households have the lowest level.

[0045] Structural splitting of addresses is a well-known technology in the art. As an example, the specific process of structural splitting of addresses can be: 1. Data cleaning, which specifically involves removing irrelevant characters (such as brackets and quotation marks), standardizing abbreviations (for example, St. -> Street, Ave. -> Avenue), and converting uppercase and lowercase to maintain consistency. 2. Word segmentation and segmentation, using natural language processing (NLP) technology to identify and segment different parts of the address, such as street name, house number, city, state / province, zip code, etc., and identify specific keywords, such as "Suite", "Apt", "Building", etc., for further segmentation. 3. Regular expression matching, using regular expressions to identify and extract address elements of specific patterns, such as numbers, letter combinations, etc. 4. Database query, comparing with known address databases to verify the validity and accuracy of the address and fill in missing information. 5. Machine learning model training, building a training set based on training data, so as to train sequence labeling models (such as BiLSTM-CRF) in deep learning. 6. Output structured data, automatically parse and classify the various parts of the address through the trained model, and output a structured data object containing the various components of the address.

[0046] In one possible implementation, the level categories include administrative area address level, detailed address level and precise address level.

[0047] In the embodiments of this specification, the hierarchical categories can be divided into three categories, namely, the administrative region address hierarchy, the detailed address hierarchy and the precise address hierarchy. Taking the above example, it is assumed that the hierarchical levels into which the composite address structure is split are used to represent provinces, cities, counties (cities, districts), streets (townships), communities (administrative villages), streets and lanes, communities, buildings, door addresses, building addresses, units, floors, and households. Under one of the preset division rules, the hierarchical levels corresponding to provinces, cities, counties (cities, districts), streets (townships), and communities (administrative villages) will be divided into administrative region address hierarchical levels, the hierarchical levels corresponding to streets and lanes, communities, and buildings will be divided into detailed address hierarchical levels, and the hierarchical levels corresponding to door addresses, building addresses, units, floors, and households will be divided into precise address hierarchical levels.

[0048] In one possible implementation, the constructing a standard address table based on each of the standard sub-addresses includes:

[0049] A unique code is set for each of the standard sub-addresses respectively, and a standard address table is constructed based on each of the standard sub-addresses and the unique code. The encoding rules for the unique codes corresponding to the standard sub-addresses of different hierarchical categories are different.

[0050] In the embodiments of this specification, for each standard sub-address of different levels, the cloud server will also encode these standard sub-addresses respectively, and set a unique code for each standard sub-address. When constructing the standard address table, in addition to the standard sub-address, the table will also store the corresponding unique code for each standard sub-address mapping. In this way, in the subsequent matching query process, each sub-address can be represented in the form of a unique code to ensure that all addresses are presented in a consistent manner, so that matching calculations can be better performed. In addition, different levels of standard sub-addresses can use different coding rules to better distinguish between codes of different levels. As an example, still taking the above example, the administrative area address level can adopt a 15-bit coding rule, the detailed address level can adopt a 5-bit coding rule, and the precise address level can adopt a 6-bit coding rule.

[0051] S102: When an address to be identified is detected, the address to be identified is structurally split to obtain sub-addresses to be identified, and each sub-address to be identified is filled into a preset address identification table according to the hierarchy.

[0052] In the embodiment of the present specification, after the standard address table is constructed, if the cloud server detects that there is an address to be identified that needs to be completed, the cloud server will first perform a structural split on the address to be identified to obtain each sub-address to be identified. Since the address to be identified is incomplete, it cannot be guaranteed that there are sub-addresses to be identified at each level after structural splitting. The cloud server is pre-set with an address identification table, which can contain the original address information and the split address information elements of each level, and each element corresponds to a blank space that can be filled in, so that the cloud server can match keywords for each sub-address to be identified by regular expression, and fill each sub-address to be identified into the blank space of the corresponding level in the address identification table. As an example, assuming that the address to be identified is Cuiyuan New Village, No. 11 Cuibai Road, Xihu District, Hangzhou City, after structural splitting, it will be split into Hangzhou City, Xihu District, No. 11 Cuibai Road, Cuiyuan New Village and other sub-addresses to be identified, and each sub-address to be identified will be filled into the blank space of the corresponding level in the address identification table according to the level identified by the deep learning model during the splitting process.

[0053] S103, performing character string matching of each hierarchical category on the standard address table and the address recognition table in sequence based on the hierarchical category priority order, and after each matching is completed, assigning a weight to each matching result based on the matching degree.

[0054] Among them, the hierarchical category with a higher average level has a higher priority corresponding to the hierarchical category.

[0055] In the embodiments of this specification, different hierarchical categories will be set with different hierarchical category priorities, and will be sorted in order from high to low priority. The higher the average hierarchical category, the higher its corresponding priority. Taking the above example as an example, assuming that the hierarchical categories include three categories: administrative area address level, detailed address level and precise address level, the order of sorting by priority is administrative area address level, detailed address level, precise address level, and the administrative area address level has the highest priority. Then, the cloud server will match the standard address table and the address identification table in turn according to the hierarchical category priority order. Each matching process will only perform string matching on the sub-addresses of each level corresponding to the hierarchical category that is currently ranked at the front in the hierarchical category priority order, so as to achieve the overall splitting of the address, and match the sub-addresses of different ranges respectively according to the process from large range to small range, and obtain the matching results of the sub-address strings of different hierarchical categories respectively. The matching result is used to characterize the matching degree between the sub-address to be identified belonging to the hierarchical category in the address identification table and the standard sub-address part of a standard address in the standard address table in the hierarchical category. The matching result can be represented by the standard sub-address part and the matching degree. The matching degree can be calculated by the longest common subsequence, cosine similarity, exact matching, fuzzy matching algorithm, etc. The higher the matching degree corresponding to a matching result, the higher the matching degree between the standard sub-address corresponding to the matching result and the sub-address to be identified. Finally, after the cloud server completes the matching of each hierarchical category, it will assign weights to each matching result according to the matching degree for subsequent weighted calculation. The higher the matching degree, the greater the weight assigned to the matching result, that is, the greater the weight assigned to the corresponding standard sub-address part. Since the parts of each hierarchical category are matched and calculated separately, the weight is also assigned separately to the part corresponding to each hierarchical category, rather than the weight assigned to a standard address as a whole.

[0056] It should be noted that since a hierarchical category includes multiple levels, the matching process should be performed based on the standard address as a unit, rather than on a single standard sub-address. That is to say, for each standard address in the standard address table, assuming that there are standard sub-address A, standard sub-address B, and standard sub-address C under this hierarchical category, standard sub-address A, standard sub-address B, and standard sub-address C will be treated as a whole, and the whole will be regarded as the standard sub-address part of the standard address and matched with the sub-address part to be identified in the hierarchical category in the address identification table, rather than performing matching calculations with standard sub-address A, standard sub-address B, and standard sub-address C separately. Only in this way can the matching result obtained reflect the matching degree between the address to be identified and each standard address under this hierarchical category.

[0057] In one possible implementation, the step of sequentially matching the strings of the hierarchical categories of the standard address table and the address identification table based on the hierarchical category priority order includes:

[0058] Determine the target hierarchical category to be matched based on the hierarchical category priority order, perform matching calculation on the first character string of the target hierarchical category in the standard address table and the second character string of the target hierarchical category in the address identification table, and obtain each matching result;

[0059] The step of determining the target hierarchical category to be matched based on the hierarchical category priority order is repeated until the character strings of all hierarchical categories have completed the matching calculation.

[0060] In the embodiment of the present specification, the cloud server will first determine the target hierarchical category that needs to be matched according to the hierarchical category priority order, and perform matching calculations on the first character string corresponding to the standard sub-address belonging to the target hierarchical category and the second character string corresponding to the sub-address to be identified in the standard address table and the address identification table to obtain the matching results corresponding to each standard sub-address. Then, the cloud server will repeat the above process, determine the next target hierarchical category to be matched in the hierarchical category priority order, and perform matching calculations again until the character strings of all hierarchical categories have completed the matching calculations.

[0061] In one possible implementation, after each matching is completed, assigning a weight to each matching result based on the matching degree includes:

[0062] After each matching is completed, the matching degree corresponding to each matching result is determined, the matching results with matching degrees lower than a preset matching degree are deleted, and weights are assigned to the remaining matching results based on the matching degrees.

[0063] In the embodiment of this specification, for the standard address table, most of the standard addresses are not similar to the address to be identified, resulting in a very low matching degree in the corresponding matching results. For the subsequent weighted calculation, these matching results are meaningless. In order to avoid a large number of meaningless matching results being cumulatively allocated a large proportion of weights, the cloud server will first delete the matching results that are lower than the preset matching degree after the matching is completed, and then allocate weights according to the matching degree in the remaining matching results.

[0064] S104: Calculate the weighted value corresponding to each first standard address having a matching result, and complete the address to be identified based on the second standard address with the largest weighted value.

[0065] In the embodiment of the present specification, for a certain standard address, if there is a matching result corresponding to it, it means that the standard sub-address part corresponding to at least one hierarchical category of the standard address has a high degree of matching with the corresponding sub-address to be identified of the address to be identified. The cloud server will use this standard address as the first standard address and calculate the weighted values ​​of all first standard addresses respectively. Finally, the second standard address with the largest weighted value is considered to be the address that best matches the address to be identified as a whole, and the cloud server completes the address to be identified based on the second standard address. Among them, assuming that there are three types of hierarchical categories, and a certain standard address has only one hierarchical category with a matching result and is assigned a weight, then in the weighted calculation, the weights of the corresponding parts of the remaining two hierarchical categories will be regarded as 0. Among them, the specific calculation process of the weighted value can be that each hierarchical category part is corresponding to an initial weight value, and each initial weight value is weighted according to each weight to obtain a weighted value. It can also be the weighted value obtained by directly adding the weights corresponding to each hierarchical category together and then calculating it with a fixed weight value, or other implementable methods.

[0066] In one possible implementation, calculating the weighted value corresponding to each first standard address for which a matching result exists includes:

[0067] For each first standard address with a matching result, the weight corresponding to each of the hierarchical categories in the first standard address is determined, and based on the weight, a weighted calculation is performed on the preset weights corresponding to each of the hierarchical categories to obtain a weighted value of the first standard address.

[0068] In the embodiments of this specification, each hierarchical category is set with a preset weight, and the preset weights corresponding to each hierarchical category may be different according to different actual needs. For example, the preset weight of the hierarchical category corresponding to a large area may be smaller than the preset weight of the hierarchical category corresponding to a small area. After determining the weight corresponding to each hierarchical category, the preset weight is calculated by weighting the preset weights through each weight to obtain the weighted value of the first standard address.

[0069] In one embodiment, the method further comprises:

[0070] Every time a preset time period passes, the standard address table is updated based on the standard addresses newly acquired within the preset time period.

[0071] In the embodiments of this specification, the location corresponding to the standard address may change due to construction, demolition, etc. Therefore, in order to ensure the accuracy of the standard address table, every preset period of time, the cloud server needs to obtain the new standard addresses that appear during this period from public channels and update the standard address table based on these standard addresses.

[0072] The following will be combined with the attached Figure 2 , the address information automatic identification and completion device provided in the embodiment of the present application is introduced in detail. It should be noted that the attached Figure 2 The address information automatic recognition and completion device shown is used to execute this application Figure 1 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 The embodiment shown.

[0073] See also Figure 2 , Figure 2 Schematic diagram of the structure of an automatic address information identification and completion device provided in an embodiment of the present application. Figure 2 As shown, the device comprises:

[0074] The acquisition module 201 is used to acquire a standard address, perform structural decomposition on the standard address to obtain standard sub-addresses of different levels, and divide each level into different level categories based on a preset division rule, and then construct a standard address table based on each standard sub-address, wherein each level category is divided into at least two adjacent levels;

[0075] The filling module 202 is used for, when an address to be identified is detected, structurally splitting the address to be identified to obtain sub-addresses to be identified, and filling each sub-address to be identified into a preset address identification table according to the hierarchy;

[0076] The matching module 203 is used to match the character strings of the hierarchical categories of the standard address table and the address identification table in sequence based on the hierarchical category priority order, and after each matching, assign a weight to each matching result based on the matching degree, and the hierarchical category with a higher average level has a higher hierarchical category priority;

[0077] The calculation module 204 is used to calculate the weighted value corresponding to each first standard address with a matching result, and complete the address to be identified based on the second standard address with the largest weighted value.

[0078] In one possible implementation, the acquisition module 201 is specifically used for:

[0079] A unique code is set for each of the standard sub-addresses respectively, and a standard address table is constructed based on each of the standard sub-addresses and the unique code. The encoding rules for the unique codes corresponding to the standard sub-addresses of different hierarchical categories are different.

[0080] In one possible implementation, the level categories include administrative area address level, detailed address level and precise address level.

[0081] In one possible implementation, the matching module 203 is specifically used for:

[0082] Determine the target hierarchical category to be matched based on the hierarchical category priority order, perform matching calculation on the first character string of the target hierarchical category in the standard address table and the second character string of the target hierarchical category in the address identification table, and obtain each matching result;

[0083] The step of determining the target hierarchical category to be matched based on the hierarchical category priority order is repeated until the character strings of all hierarchical categories have completed the matching calculation.

[0084] In one possible implementation, the matching module 203 is further configured to:

[0085] After each matching is completed, the matching degree corresponding to each matching result is determined, the matching results with matching degrees lower than a preset matching degree are deleted, and weights are assigned to the remaining matching results based on the matching degrees.

[0086] In one possible implementation, the calculation module 204 is specifically configured to:

[0087] For each first standard address with a matching result, the weight corresponding to each of the hierarchical categories in the first standard address is determined, and based on the weight, a weighted calculation is performed on the preset weights corresponding to each of the hierarchical categories to obtain a weighted value of the first standard address.

[0088] In one embodiment, the device further comprises:

[0089] The updating module is used to update the standard address table based on the standard addresses newly acquired within the preset time period every time a preset time period passes.

[0090] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0091] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0092] See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3 As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0093] The communication bus 302 is used to realize the connection and communication between these components.

[0094] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0095] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0096] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts of the entire electronic device 300, and executes various functions and processes data of the electronic device 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics central processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0097] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0098] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the address information automatic recognition and completion application stored in the memory 305, and specifically perform the following operations:

[0099] Obtain a standard address, perform structural decomposition on the standard address to obtain standard sub-addresses of different levels, and divide each level into different level categories based on a preset division rule, and then construct a standard address table based on each of the standard sub-addresses, wherein each level category corresponds to at least two adjacent levels;

[0100] When an address to be identified is detected, the address to be identified is structurally split to obtain sub-addresses to be identified, and each sub-address to be identified is filled into a preset address identification table according to the hierarchy;

[0101] Based on the priority order of the hierarchical categories, the string matching of each hierarchical category is performed on the standard address table and the address identification table in turn, and after each matching is completed, a weight is assigned to each matching result based on the matching degree, and the hierarchical category corresponding to the hierarchical category with a higher average level has a higher hierarchical category priority;

[0102] The weighted value corresponding to each first standard address having a matching result is calculated, and the address to be identified is completed based on the second standard address with the largest weighted value.

[0103] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0104] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0105] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0109] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0110] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0111] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for automatically identifying and completing address information, characterized in that: The method comprises: Obtain a standard address, perform structural decomposition on the standard address to obtain standard sub-addresses of different levels, and divide each level into different level categories based on a preset division rule, and then construct a standard address table based on each of the standard sub-addresses, wherein each level category corresponds to at least two adjacent levels; When an address to be identified is detected, the address to be identified is structurally split to obtain sub-addresses to be identified, and each sub-address to be identified is filled into a preset address identification table according to the hierarchy; Based on the priority order of the hierarchical categories, the string matching of each hierarchical category is performed on the standard address table and the address identification table in turn, and after each matching is completed, a weight is assigned to each matching result based on the matching degree, and the hierarchical category corresponding to the hierarchical category with a higher average level has a higher hierarchical category priority; Calculate the weighted value corresponding to each first standard address with a matching result, and complete the address to be identified based on the second standard address with the largest weighted value; The step of sequentially matching the character strings of the standard address table and the address identification table according to the hierarchy category priority order includes: Determine the target hierarchical category to be matched based on the hierarchical category priority order, perform matching calculation on the first character string of the target hierarchical category in the standard address table and the second character string of the target hierarchical category in the address identification table, and obtain each matching result; Repeat the step of determining the target hierarchical category to be matched based on the hierarchical category priority order until the character strings of all hierarchical categories have completed the matching calculation; After each matching is completed, a weight is assigned to each matching result based on the matching degree, including: After each matching is completed, the matching degree corresponding to each matching result is determined, the matching results with matching degrees lower than a preset matching degree are deleted, and weights are assigned to the remaining matching results based on the matching degrees.

2. The method according to claim 1, characterized in that The step of constructing a standard address table based on each of the standard sub-addresses includes: A unique code is set for each of the standard sub-addresses respectively, and a standard address table is constructed based on each of the standard sub-addresses and the unique code. The encoding rules for the unique codes corresponding to the standard sub-addresses of different hierarchical categories are different.

3. The method according to claim 1, characterized in that The level categories include administrative area address level, detailed address level and precise address level.

4. The method according to claim 1, characterized in that: The calculating of the weighted value corresponding to each first standard address having a matching result includes: For each first standard address with a matching result, the weight corresponding to each of the hierarchical categories in the first standard address is determined, and based on the weight, a weighted calculation is performed on the preset weights corresponding to each of the hierarchical categories to obtain a weighted value of the first standard address.

5. The method according to claim 1, characterized in that The method further comprises: Every time a preset time period passes, the standard address table is updated based on the standard addresses newly acquired within the preset time period.

6. A device for automatically identifying and completing address information, characterized in that: The device comprises: An acquisition module, used to acquire a standard address, perform structural decomposition on the standard address to obtain standard sub-addresses of different levels, and after dividing each level into different level categories based on a preset division rule, construct a standard address table based on each of the standard sub-addresses, wherein each level category corresponds to at least two adjacent levels; A filling module is used for, when an address to be identified is detected, structurally splitting the address to be identified to obtain sub-addresses to be identified, and filling each sub-address to be identified into a preset address identification table according to the hierarchy; A matching module, used for matching the character strings of the hierarchical categories of the standard address table and the address identification table in sequence based on the hierarchical category priority order, and after each matching, assigning a weight to each matching result based on the matching degree, wherein the hierarchical category with a higher average level has a higher hierarchical category priority; A calculation module, used to calculate a weighted value corresponding to each first standard address having a matching result, and to complete the address to be identified based on the second standard address with the largest weighted value; The matching module is specifically used for: Determine the target hierarchical category to be matched based on the hierarchical category priority order, perform matching calculation on the first character string of the target hierarchical category in the standard address table and the second character string of the target hierarchical category in the address identification table, and obtain each matching result; Repeat the step of determining the target hierarchical category to be matched based on the hierarchical category priority order until the character strings of all hierarchical categories have completed the matching calculation; The matching module is also specifically used for: After each matching is completed, the matching degree corresponding to each matching result is determined, the matching results with matching degrees lower than a preset matching degree are deleted, and weights are assigned to the remaining matching results based on the matching degrees.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium has instructions stored therein, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 5.