Address data management method and device based on standard address map and multi-strategy matching

Abstract

The invention belongs to the technical field of address data. The invention provides an address data management method and device based on a standard address map and multi-strategy matching. According to the embodiment of the invention, firstly, a national and standardized address hierarchy knowledge graph is constructed based on official data of the State Statistics Office and the like; then, carrying out element identification and analysis on the input original address; and finally, performing error correction, complementation and standardization on the address through a multi-strategy combining lowest-level reverse matching, pinyin fault-tolerant retrieval, address description similarity and an address longest reachable chain. According to the method, the complex problems of hierarchy errors, wrongly written characters, hierarchy missing, hierarchy conflicts and the like in the address data can be effectively solved, and the quality and availability of the address data are remarkably improved.

Description

Technical Field

[0008] ,

[0001] Embodiments of the present disclosure relate to the technical field of address data, and in particular, to an address data governance method and apparatus based on a standard address atlas and multi-strategy matching. Background Art

[0002] Address data is the basic information carrier of social and economic activities and is widely used in key fields such as logistics navigation, public security, and regional economic analysis. High-quality address data is a prerequisite for ensuring the normal operation of these systems and accurate decision-making. However, during the processes of data collection, entry, transfer, and integration, due to reasons such as human errors, system heterogeneity, and inconsistent standards, there are generally serious quality problems in the original address data: 1. Element-level errors: (typos and homophone substitutions): for example, "Xinzhuang" is miswritten as "Xinzhuang"; 2. Structure-level errors (missing and jumping of address levels) such as missing the "district" level and directly jumping from "city" to "road"; 3. Logic-level errors (conflicts in address levels and confusion in subordination relationships): for example, violating the administrative subordination relationship and having impossible logical combinations such as "Chengde City, Sichuan Province, Shaanxi Province".

[0003] Moreover, existing address governance solutions mostly rely on a rule base or a single similarity algorithm, and there are obvious limitations. It is difficult for the rule base to cover all error variants and it is rigid and difficult to maintain; while only using similarity algorithms such as the edit distance, it is impossible to understand the internal hierarchical logic of addresses and the handling ability for cases of hierarchical conflicts and complex omissions is insufficient.

[0004] Existing technical solutions are already inadequate in governing element errors (typos), and are even more stretched when facing structure errors (missing levels) and logic errors (hierarchical conflicts). There is an urgent need for a solution that can deeply understand the internal hierarchical semantics of addresses and comprehensively utilize multiple intelligent strategies for precise and efficient governance.

[0005] Therefore, it is necessary to improve one or more problems existing in the above-mentioned related technical solutions.

[0006] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the embodiments of the present disclosure is to provide an address data governance method based on a standard address atlas and multi-strategy matching, thereby at least overcoming one or more problems caused by the limitations and defects of the related art to a certain extent.

[0008] According to the first aspect of the embodiments of the present disclosure, there is provided an address data governance method based on a standard address atlas and multi-strategy matching, including: Based on address data sources, a standard address knowledge graph is constructed, in which nodes represent standard address elements and directed edges represent the hierarchical relationships between address elements. The input raw address string is processed to identify and extract the address elements at various levels contained therein, forming a set of address elements to be managed; A first correction result set and a second correction result set are obtained by performing multi-strategy matching and correction on the set of address elements to be governed; wherein, the multi-strategy matching and correction strategy includes the finest-grained reverse matching strategy and the pinyin fault-tolerant retrieval strategy; Confidence assessment and path decision are performed on the first and second correction result sets to output the final standard address.

[0009] Furthermore, the attributes of a node must include at least a standard name, a core character, a unique administrative code, and a pinyin code; the edge relationships of a node are hierarchical and exclusive.

[0010] Furthermore, the finest-grained reverse matching strategy includes: From the set of address elements to be governed, identify the elements that can be matched in the standard address hierarchy map and have the finest hierarchy as anchor points; Starting from the node corresponding to the anchor point in the graph, traverse all its parent paths from bottom to top. Match other elements in the address to be rectified with nodes on each parent path, calculate the comprehensive similarity of each path, and output the first rectification result set.

[0011] Furthermore, the pinyin error-tolerant retrieval strategy includes: Convert the elements in the set of address elements to be governed into Pinyin strings; Perform fuzzy matching between the pinyin string and the pinyin codes of nodes in the standard address hierarchy graph; When a match is successful, the corresponding element in the original input is replaced with the element corresponding to the standard node, and the second corrected result set is output.

[0012] Furthermore, the steps of performing confidence assessment and path decision-making on the first and second correction result sets, and outputting the final standard address, include: Calculate the comprehensive similarity for candidate paths in the first and second correction result sets; When multiple candidate paths exist, a decision is made according to the preset multi-path decision rules. The winning address is subjected to an address relationship graph for validity verification and missing structure supplementation to generate a standard address. The multi-path decision rules are based on the order of finest granularity priority and comprehensive similarity priority.

[0013] Furthermore, the calculation process for comprehensive similarity is as follows: For a candidate path P, its comprehensive similarity to the address A to be governed is... for:

[0014] Where Simtext is the average text similarity of matched nodes on the path; Simpinyin is the average pinyin similarity of matched nodes on the path; Lenmatch is the normalized matching path length. As the first weighting coefficient, This is the second weighting coefficient. It is the third weighting coefficient, and .

[0015] According to a second aspect of the present disclosure, an address data governance apparatus based on standard address maps and multi-strategy matching is provided, comprising: The standard address knowledge graph construction and storage module is used to construct and store the standard address knowledge graph based on the address data source. The standard address knowledge graph is represented by nodes and directed edges represent the membership relationships between address elements.

[0016] The address resolution engine is used to process the input raw address string, identify and extract the address elements at all levels contained therein, and form a set of address elements to be managed; A multi-strategy matching engine is used to perform multi-strategy matching and correction strategies on the set of address elements to be governed to obtain a first correction result set and a second correction result set; wherein, the multi-strategy matching and correction strategies include the finest-grained reverse matching strategy and the pinyin error-tolerant retrieval strategy; The decision arbitration and output module is used to perform confidence assessment and path decision on the first and second correction result sets, and output the final standard address.

[0017] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the address data governance method based on standard address maps and multi-policy matching described in any of the above embodiments.

[0018] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: Processor; and Memory for storing the executable instructions of the processor; The processor is configured to execute the steps of the address data governance method based on standard address maps and multi-policy matching described in any of the above embodiments by executing the executable instructions.

[0019] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: In the embodiments of this disclosure, the above-described method and apparatus, on the one hand, firstly, construct a nationwide, standardized address hierarchy knowledge graph based on official data such as that from the National Bureau of Statistics; subsequently, perform element identification and parsing on the input raw addresses; finally, through a combination of multiple strategies—including lowest-level reverse matching, pinyin error-tolerant retrieval, address description similarity, and the longest reachable chain—the addresses are corrected, completed, and standardized. On the other hand, this application can effectively solve complex problems such as hierarchy errors, typos, missing levels, and hierarchy conflicts in address data, significantly improving the quality and usability of address data.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0022] Figure 1 The diagram illustrates the steps of an address data governance method based on standard address maps and multi-policy matching in an exemplary embodiment of this disclosure. Figure 2 A flowchart illustrating the address data governance method based on standard address maps and multi-policy matching in an exemplary embodiment of this disclosure is shown. Figure 3 This diagram illustrates an address data governance apparatus based on standard address maps and multi-policy matching, as shown in an exemplary embodiment of this disclosure. Figure 4 This diagram illustrates a program product according to an exemplary embodiment of the present disclosure; Figure 5 This diagram illustrates an electronic device according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0023] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0024] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0025] This example implementation first provides an address data governance method based on standard address maps and multi-policy matching. This method can be applied to a terminal device, such as a mobile phone, personal digital assistant, laptop, tablet, smartwatch, or other mobile terminal [adjusted flexibly according to specific circumstances, such as a server]. Reference Figure 1 As shown, the method may include the following steps: Step S100: Based on the address data source, construct a standard address knowledge graph in which nodes represent standard address elements and directed edges represent the hierarchical relationships between address elements; Step S200: Process the input raw address string, identify and extract the address elements at all levels contained therein, and form a set of address elements to be managed; Step S300: Perform multi-strategy matching and correction on the set of address elements to be governed to obtain a first correction result set and a second correction result set; wherein, the multi-strategy matching and correction strategy includes the finest-grained reverse matching strategy and the pinyin fault-tolerant retrieval strategy; Step S400: Perform confidence assessment and path decision on the first and second correction result sets, and output the final standard address.

[0026] The above method, on the one hand, firstly constructs a nationwide, standardized address hierarchy knowledge graph based on official data from the National Bureau of Statistics and other sources; then, it identifies and parses the elements of the input raw addresses; finally, it corrects, completes, and standardizes the addresses through a multi-strategy approach combining lowest-level reverse matching, pinyin error-tolerant retrieval, address description similarity, and the longest reachable chain. On the other hand, this application effectively solves complex problems in address data such as hierarchy errors, typos, missing levels, and hierarchy conflicts, significantly improving the quality and usability of address data.

[0027] Below, we will refer to Figures 1 to 2 The steps of the method described above in this example embodiment will be explained in more detail.

[0028] like Figure 2 The diagram shows a flowchart of the address data governance method based on standard address maps and multi-strategy matching.

[0029] In step S100, based on the address data source, a standard address knowledge graph is constructed, in which nodes represent standard address elements and directed edges represent the hierarchical relationships between address elements.

[0030] Specifically, a standard address hierarchy graph is constructed: based on the national official address data source, an address knowledge graph is constructed in which nodes represent standard address elements and directed edges represent the "parent-child" hierarchical relationship; the attributes of the nodes include at least the standard name, core words (standard names with identity words such as province, city, district, neighborhood committee, and community removed), unique administrative code, and pinyin code.

[0031] The standard address hierarchy map has node attributes that include at least a standard name, core words, a unique administrative code, and a pinyin code; its edge relationships have clear hierarchy and exclusivity, and are used to detect and resolve hierarchy conflicts such as "Shaanxi Province, Sichuan Province, Chengde City".

[0032] In step S200, the input original address string is processed to identify and extract the address elements at all levels contained therein, forming a set of address elements to be managed.

[0033] Specifically, address element identification and parsing: Natural Language Processing (NLP) and Named Entity Recognition (NER) are performed on the input raw address string to identify and extract the address elements at various levels contained therein, forming a set of address elements to be processed; and core words are extracted from the elements.

[0034] In step S300, a multi-strategy matching and correction strategy is applied to the set of address elements to be governed to obtain a first correction result set and a second correction result set; wherein, the multi-strategy matching and correction strategy includes the finest-grained reverse matching strategy and the pinyin fault-tolerant retrieval strategy.

[0035] Specifically, multi-strategy matching and correction: the following strategies are executed in parallel or serially: The finest-grained reverse matching strategy is as follows: From the set of address elements to be governed, the finest-grained element that can be matched in the standard address hierarchy map is identified as the anchor point; Starting from the anchor point, all possible parent paths are traversed from bottom to top in the map, and other elements in the address to be governed are matched with the nodes on the path, the comprehensive similarity of the path is calculated, and the first correction result set is output. Pinyin error-tolerant retrieval strategy: Convert the elements in the set of address elements to be governed into pinyin, perform fuzzy matching with the pinyin codes of the nodes in the standard address hierarchy map, identify and correct typos, and output a second correction result set.

[0036] More specifically, step S310: The finest-grained reverse matching strategy involves selecting the lowest-level element from the set of address elements to be governed that has a complete or highly similar match in the standard address map, and using it as the anchor element. Starting from the node of the anchor element in the map, all possible parent paths are traversed upwards. The similarity between other elements in the address to be governed and the nodes on each parent path is calculated, and the path with the highest comprehensive similarity is selected as the basis for completion, thereby reconstructing the complete and correct standard address from the province / city to the anchor element.

[0037] Step S320: The pinyin error-tolerant retrieval strategy converts each element in the set of address elements to be addressed into a pinyin string. The pinyin string is then fuzzily matched with the pinyin codes of all nodes in the standard address map. If the pinyin is completely identical or highly similar, the erroneous element in the original input is replaced with a standard node. This strategy effectively handles address misspellings caused by homophones, near-homophones, and similar-looking characters.

[0038] In step S400, confidence assessment and path decision are performed on the first correction result set and the second correction result set, and the final standard address is output.

[0039] Specifically, for a candidate path P, its comprehensive similarity Simtotal(P,A) with the address A to be governed can be calculated as follows:

[0040] Where Simtext is the average text similarity (Jaro-Winkler distance) of matched nodes on the path; Simpinyin is the average pinyin similarity of matched nodes on the path; Lenmatch is the normalized matching path length (number of matched levels / total number of levels), used to reward more complete paths. α is the first weight coefficient, β is the second weight coefficient, and γ is the third weight coefficient, and α+β+γ=1. According to the test, the optimal weights are (α=0.4, β=0.4, γ=0.2).

[0041] When the text similarity is 1, the pinyin similarity is directly set to 1.

[0042] Multi-path decision-making rules (“winning” rules): When multiple candidate paths are generated, decisions are made in the following priority order: Finest granularity priority: Prioritize the path with the finest anchor point level (i.e., L5 is better than L4, L4 is better than L3, etc.).

[0043] Path length priority: When anchor points are at the same level, the path with the longest effective path (i.e., the path that matches the most address elements) is selected first.

[0044] Overall similarity priority: When both of the above are equal, the path with the highest overall similarity (Simtotal) is selected.

[0045] Based on the above decisions, the winning addresses are subjected to validity checks and missing structural additions to the address relationship diagram, generating standard addresses.

[0046] In a specific embodiment, step S100 (graph construction): The graph contains standard nodes, for example: `(name: Zhejiang Province, code: 33, piny: zhejiang, key: Zhejiang) -> (name: Hangzhou City, code: 3301, piny: hangzhou, key: Hangzhou) -> (name: Xiaoshan District, code: 330109, piny: xiaoshan, key: Xiaoshan) -> ... (name: Shaanxi Province, code: 61, piny: shanxi, key: Shaanxi) -> (name: Xi'an City, code: 6101, piny: xian, key: xian) -> (name: Yanta District, code: 610113, piny: yanta, key: Yanta) ->` Step S200 (Feature Parsing): Input address string, parse out the feature set: [L1: "Zhejiang", L2: "Hangzhou", L3: "Yanta District", L4: "Dayanta Subdistrict", L5: "Dayanta Community"].

[0047] After extracting the core characters, the L3 level element is "Yanta".

[0048] Step S300 (Multi-strategy matching): Step S310 (Finest-grained reverse matching): Finding the anchor point: In the feature set, "Dayan Pagoda Community" (L5) is the lowest level feature. A search in the graph reveals it to be a standard node located on the path "Dayan Pagoda Subdistrict -> Yanta District -> Xi'an City -> Shaanxi Province". Therefore, it is selected as the anchor point.

[0049] Upward traversal and matching: Starting from "Dayan Pagoda Community", traverse upwards. Match "Dayan Pagoda Street", "Yanta District", "Hangzhou", and "Zhejiang" in the address to be governed with the parent nodes on the path respectively.

[0050] Conflicts were found: the parent node "Yanta District" does not match the text of the input element "Yanta District," but "Xi'an City" and "Hangzhou City" do not match at all, and "Shaanxi Province" and "Zhejiang Province" do not match at all. This path can only partially match (L4,L5), and the overall similarity is low.

[0051] Step S320 (Pinyin Fault Tolerance Retrieval): Perform Pinyin conversion on the input element "Yanta District" to obtain "yantaqu".

[0052] Perform Pinyin fuzzy matching within the entire graph spectrum and find that the Pinyin "yantaqu" of the standard node "Yanta District" is exactly the same as it.

[0053] Therefore, correct "Yanta District" to "Yanta District". After correction, this element is associated under "Xi'an City".

[0054] Step S400 (Result Fusion and Arbitration): Generate candidate paths: Path 1 (generated by step S310): Hangzhou City, Zhejiang Province

?Unknown District?

[0055] Path 2 (trigger a new search by step S320): Use the corrected "Yanta District" as a new anchor point and perform reverse matching. The complete path can be obtained: Yanta District, Xi'an City, Shaanxi Province, Big Wild Goose Pagoda Street, Big Wild Goose Pagoda Community (Anchor: L3 -> Find L4, L5 through association, Path Length: 5).

[0056] Decision arbitration: Apply the "Multi - path Decision Rule": Fine - grained first: The anchor point of Path 1 is L5, and the anchor point of Path 2 is L3. Path 1 wins.

[0057] (However) Path - length first: The effective matching length of Path 1 is 3 (province, city, street, community), but there are hierarchical missing parts (district level missing) and conflicts (district name mismatch). The effective matching length of Path 2 is 5 (province, city, district, street, community), which is complete and conflict - free. Path 2 far exceeds Path 1 in terms of integrity.

[0058] In the decision logic of this application, the integrity and logical correctness of the path have a higher priority than the absolute granularity of the anchor point. Therefore, it is finally determined that Path 2 is the correct path.

[0059] Final output: Standard address "Yanta District, Xi'an City, Shaanxi Province, Big Wild Goose Pagoda Street, Big Wild Goose Pagoda Community".

[0060] The key point of this application is to abandon the traditional method of treating addresses as an unordered set of words or a static processing method that only relies on suffix labels, but to understand addresses as a dynamic graph network with strict hierarchical logical relationships. Its core is a governance paradigm of "from point to surface, multiple strategies collaborating".

[0061] A hierarchical relationship model based on standard address graphs: official standard addresses are constructed into a knowledge graph with parent-child hierarchical relationships, providing a unique factual standard for address governance.

[0062] The finest-grained reverse matching strategy uses the finest-grained elements that can be identified in the input address as "anchor points" to perform path search and reconstruction from bottom to top, fundamentally solving the problems of missing levels and conflicts.

[0063] A multi-strategy (text, pinyin, path) integrated decision arbitration mechanism: comprehensively utilizes the structural features of text, pinyin, and path to conduct confidence assessment and selection, ensuring the optimality of the result.

[0064] Existing models are flat and sequentially dependent, unable to handle hierarchical jumps and conflicts. The model in this application is three-dimensional and relationally dependent, capable of naturally discovering and completing paths through graph traversal, significantly improving the ability to manage complex errors.

[0065] Innovation in strategy logic. Existing technologies rely on a "top-down, step-by-step verification" approach, where errors in earlier stages can lead to errors in all subsequent stages. This application employs a multi-path weighted approach, which effectively handles missing or incorrect levels.

[0066] From "Local Optimality" to "Global Optimality": Existing technologies often fall into the trap of focusing on local textual similarities while neglecting overall logic (e.g., "Beijing Haidian District" and "Hainan Haidian District" have similar texts but flawed logic). This application, through path decision rules, prioritizes the standard address with the most complete structure and the most logical coherence, significantly improving the accuracy and reliability of the results.

[0067] Jaro distance is an algorithm used to measure the similarity between two strings. It determines similarity by calculating matching characters and transposition characters between the two strings. The smaller the Jaro distance, the more similar the two strings are.

[0068] The Jaro–Winkler distance is an algorithm for measuring string similarity. It introduces a prefix factor to assign higher similarity weights to strings with the same prefix. It is suitable for word matching scenarios, and its effect is particularly significant when prefixes are similar.

[0069] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps. Furthermore, it is readily understood that these steps may be executed synchronously or asynchronously, for example, in multiple modules / processes / threads.

[0070] Furthermore, this example embodiment also provides an address data governance device based on standard address maps and multi-strategy matching. (See reference...) Figure 2 As shown, the device 100 may include a standard map construction and storage module 110, an address resolution engine 120, a multi-strategy matching engine 140, and a decision arbitration and output module. Wherein: The standard address knowledge graph construction and storage module 110 is used to construct a standard address knowledge graph based on the address data source, with nodes representing standard address elements and directed edges representing the membership relationships between address elements, and to store the standard address knowledge graph.

[0071] The address resolution engine 120 is used to process the input raw address string, identify and extract the address elements at all levels contained therein, and form a set of address elements to be managed. The multi-strategy matching engine 130 is used to perform multi-strategy matching and correction strategies on the set of address elements to be governed to obtain a first correction result set and a second correction result set; wherein, the multi-strategy matching and correction strategies include the finest-grained reverse matching strategy and the pinyin fault-tolerant retrieval strategy. The decision arbitration and output module 140 is used to perform confidence assessment and path decision on the first correction result set and the second correction result set, and output the final standard address.

[0072] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0073] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units. Components shown as modules or units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0074] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a computer program is stored. When executed by a processor, the program can implement the steps of the address data governance method based on standard address maps and multi-policy matching described in any of the above embodiments. In some possible implementations, various aspects of this application can also be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this application described in the section on the address data governance method based on standard address maps and multi-policy matching described above.

[0075] refer to Figure 4 As shown, a program product 300 for implementing the above-described method according to an embodiment of this application is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the program product of this application is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0076] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0077] The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0078] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0079] In exemplary embodiments of this disclosure, an electronic device is also provided, which may include a processor and a memory for storing executable instructions of the processor. The processor is configured to perform the steps of the address data governance method based on standard address maps and multi-policy matching described in any of the above embodiments by executing the executable instructions.

[0080] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0081] The following reference Figure 5 To describe an electronic device 600 according to this embodiment of the present application. Figure 5 The electronic device 600 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0082] like Figure 5 As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including storage unit 620 and processing unit 610), a display unit 640, etc.

[0083] The storage unit stores program code that can be executed by the processing unit 610, causing the processing unit 610 to perform the steps described in the above section of this specification regarding the address data governance method based on standard address maps and multi-policy matching, according to various exemplary embodiments of this application. For example, the processing unit 610 can perform actions such as... Figure 1 The steps are shown in the figure.

[0084] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only memory unit (ROM) 6203.

[0085] The storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0086] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0087] Electronic device 600 can also communicate with one or more external devices 700 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0088] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, or network device, etc.) to execute the above-described address data governance method based on standard address maps and multi-policy matching according to the embodiments of this disclosure.

[0089] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. An address data governance method based on standard address maps and multi-strategy matching, characterized in that, include: Based on address data sources, a standard address knowledge graph is constructed, in which nodes represent standard address elements and directed edges represent the hierarchical relationships between address elements. The input raw address string is processed to identify and extract the address elements at various levels contained therein, forming a set of address elements to be managed; A first correction result set and a second correction result set are obtained by performing multi-strategy matching and correction on the set of address elements to be governed; wherein, the multi-strategy matching and correction strategy includes the finest-grained reverse matching strategy and the pinyin fault-tolerant retrieval strategy; Confidence assessment and path decision are performed on the first and second correction result sets to output the final standard address.

2. The address data governance method based on standard address maps and multi-strategy matching according to claim 1, characterized in that, The attributes of a node include at least a standard name, a core character, a unique administrative code, and a pinyin code; the edge relationships of a node are hierarchical and exclusive.

3. The address data governance method based on standard address maps and multi-strategy matching according to claim 1, characterized in that, The finest-grained reverse matching strategies include: From the set of address elements to be governed, identify the elements that can be matched in the standard address hierarchy map and have the finest hierarchy as anchor points; Starting from the node corresponding to the anchor point in the graph, traverse all its parent paths from bottom to top. Match other elements in the address to be rectified with nodes on each parent path, calculate the comprehensive similarity of each path, and output the first rectification result set.

4. The address data governance method based on standard address maps and multi-strategy matching according to claim 2, characterized in that, Pinyin error-tolerant retrieval strategies include: Convert the elements in the set of address elements to be governed into Pinyin strings; Perform fuzzy matching between the pinyin string and the pinyin codes of nodes in the standard address hierarchy graph; When a match is successful, the corresponding element in the original input is replaced with the element corresponding to the standard node, and the second corrected result set is output.

5. The address data governance method based on standard address maps and multi-strategy matching according to claim 4, characterized in that, The steps of performing confidence assessment and path decision-making on the first and second correction result sets, and outputting the final standard address, include: Calculate the comprehensive similarity for candidate paths in the first and second correction result sets; When multiple candidate paths exist, a decision is made according to the preset multi-path decision rules. The winning address is subjected to an address relationship graph for validity verification and missing structure supplementation to generate a standard address. The multi-path decision rules are based on the order of finest granularity priority and comprehensive similarity priority.

6. The address data governance method based on standard address maps and multi-strategy matching according to claim 5, characterized in that, The calculation process for overall similarity is as follows: For a candidate path P, its comprehensive similarity to the address A to be governed is... for: Where Simtext is the average text similarity of matched nodes on the path; Simpinyin is the average pinyin similarity of matched nodes on the path; Lenmatch is the normalized matching path length. As the first weighting coefficient, This is the second weighting coefficient. It is the third weighting coefficient, and .

7. An address data governance device based on standard address maps and multi-strategy matching, characterized in that, include: The standard address knowledge graph construction and storage module is used to construct and store the standard address knowledge graph based on the address data source. The standard address knowledge graph is represented by nodes and directed edges represent the membership relationships between address elements. The address resolution engine is used to process the input raw address string, identify and extract the address elements at all levels contained therein, and form a set of address elements to be managed; A multi-strategy matching engine is used to perform multi-strategy matching and correction strategies on the set of address elements to be governed to obtain a first correction result set and a second correction result set; wherein, the multi-strategy matching and correction strategies include the finest-grained reverse matching strategy and the pinyin error-tolerant retrieval strategy; The decision arbitration and output module is used to perform confidence assessment and path decision on the first and second correction result sets, and output the final standard address.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the address data governance method based on standard address maps and multi-policy matching as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the steps of the address data governance method based on standard address maps and multi-policy matching as described in any one of claims 1 to 6 by executing the executable instructions.

Images