Address data processing methods, apparatus, electronic devices and storage media

Abstract

This application provides an address data processing method, apparatus, electronic device, and storage medium, relating to the field of data processing technology, and aiming to convert address data into more accurate and complete high-value data. The method includes: acquiring source address data, and performing word segmentation processing on the source address data based on a preset noise word library, a preset administrative division word library, a preset location word library, and a pre-trained semantic model to obtain word segmentation results; determining target points of interest from a first geographic information database based on the source address data and the word segmentation results, and obtaining the standard administrative division words corresponding to the target points of interest; determining the similarity between the standard administrative division words and the administrative planning words in the word segmentation results; and, if the similarity is greater than or equal to a preset threshold, obtaining target address data based on the standard administrative division words, noise words, location words, and address-oriented words in the word segmentation results.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to an address data processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the development of navigation technology and search engines, a large amount of address data has been generated on the internet. This address data is complex and varies in expression, posing significant challenges to address data management and application. Therefore, address data cleaning is of great practical importance.

[0003] Current technologies for cleaning address data involve processes such as keyword searching and synonym replacement. However, the cleaned data obtained in this way is not ideal. For example, the cleaned address data may still have incomplete information and low accuracy, thus limiting its usability. Summary of the Invention

[0004] This application provides an address data processing method, apparatus, electronic device, and storage medium, aiming to convert address data into more accurate and complete high-value data.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, an address data processing method is provided, comprising: acquiring source address data, and performing word segmentation processing on the source address data based on a preset noise word library, a preset administrative division word library, a preset location word library, and a pre-trained semantic model to obtain word segmentation results; the semantic model is used to identify address-oriented words; when noise words, administrative division words, location words, and address-oriented words exist in the word segmentation results, a target point of interest is determined from a first geographic information database based on the source address data and the word segmentation results, and the standard administrative division word corresponding to the target point of interest is obtained; the similarity between the standard administrative division word and the administrative planning word in the word segmentation results is determined, and when the similarity is greater than or equal to a preset threshold, the target address data is obtained based on the standard administrative division word, the noise words, location words, and address-oriented words in the word segmentation results.

[0007] Optionally, the preset administrative division terminology includes multiple preset administrative division terms; the word segmentation result includes a first sub-result, which is obtained by segmenting the source address data based on the preset administrative division terminology; the first sub-result is obtained by segmenting the source address data based on the preset administrative division terminology, including: dividing each preset administrative division term to obtain a first administrative division sub-term and a second administrative division sub-term for each preset administrative division term; the administrative division level of the first administrative division sub-term is greater than or equal to the preset level, and the administrative division level of the second administrative division sub-term is less than the preset level; a prefix search tree is constructed with the first administrative division sub-term as the head node and the second administrative division sub-term as the child node; based on the prefix search tree, identification is performed in the source address data to obtain the first sub-result.

[0008] Optionally, if the word segmentation results contain noisy words, administrative division words, directional words, and address-oriented words, the target point of interest is determined from the first geographic information database based on the source address data and the word segmentation results. This includes: if the word segmentation results contain noisy words, administrative division words, directional words, and address-oriented words, a first search is performed in the first geographic information database based on the source address data to obtain a first search result; a second search is performed in the first geographic information database based on the word segmentation results to obtain a second search result; if the first search result includes at least one first point of interest and the matching degree corresponding to each first point of interest, and / or the second search result includes at least one second point of interest and the matching degree corresponding to each second point of interest, multiple points of interest are obtained based on the first search result and the second search result, and the point of interest with the highest matching degree is selected as the target point of interest from the multiple points of interest.

[0009] Optionally, the standard administrative division terms corresponding to the target point of interest can be obtained, including: obtaining the location information of the target point of interest and retrieving the standard administrative division terms corresponding to the target point of interest based on reverse geospatial services.

[0010] Optionally, the method further includes: when both the first and second search results are empty, performing index matching based on the source address data in the second geographic information database to obtain matching results; the data volume of the second geographic information database is greater than that of the first geographic information database; the matching results include administrative division terms, directional terms, and address guidance terms corresponding to the source address data.

[0011] Optionally, the method further includes: if no noise words, administrative division words, directional words, and address-oriented words are present in the word segmentation results, index matching is performed based on the source address data in the second geographic information database to obtain the matching results; the second geographic information database has a larger data volume than the first geographic information database; the matching results include administrative division words, directional words, and address-oriented words corresponding to the source address data.

[0012] Secondly, an address data processing device is provided, comprising an acquisition unit, a processing unit, and a determination unit. The acquisition unit is used to acquire source address data. The processing unit is used to perform word segmentation processing on the source address data based on a preset noise word library, a preset administrative division word library, a preset location word library, and a pre-trained semantic model to obtain word segmentation results. The semantic model is used to identify address-oriented words. The determination unit is used to determine target points of interest from a first geographic information database based on the source address data and the word segmentation results when noise words, administrative division words, location words, and address-oriented words exist in the word segmentation results, and to acquire the standard administrative division words corresponding to the target points of interest. The determination unit is also used to determine the similarity between the standard administrative division words and the administrative planning words in the word segmentation results, and if the similarity is greater than or equal to a preset threshold, to obtain target address data based on the standard administrative division words, noise words, location words, and address-oriented words in the word segmentation results.

[0013] Optionally, the preset administrative division terminology includes multiple preset administrative division terms; the word segmentation result includes a first sub-result, which is obtained by segmenting the source address data based on the preset administrative division terminology; the processing unit is specifically used for: dividing each preset administrative division term to obtain the highest administrative division sub-term and non-highest administrative division sub-terms of each preset administrative division term; constructing a prefix search tree with the highest administrative division sub-term as the head node and the non-highest administrative division sub-terms as child nodes; and indexing the source address data based on the prefix search tree to obtain the first sub-result.

[0014] Optionally, the determining unit is specifically used for: when the word segmentation results contain noise words, administrative division words, directional words, and address-oriented words, performing a first search based on the source address data in the first geographic information database to obtain a first search result; and performing a second search based on the word segmentation results in the first geographic information database to obtain a second search result; when the first search result includes at least one first point of interest and the matching degree corresponding to each first point of interest, and / or the second search result includes at least one second point of interest and the matching degree corresponding to each second point of interest, obtaining the first search result and the second search result to obtain multiple points of interest, and selecting the point of interest with the highest matching degree from the multiple points of interest as the target point of interest.

[0015] Optionally, the unit is defined, specifically for: obtaining the location information of the target point of interest, and retrieving the standard administrative division terms corresponding to the target point of interest based on the reverse geospatial service.

[0016] Optionally, the determining unit is further configured to: when both the first and second search results are null, perform index matching based on the source address data in the second geographic information database to obtain matching results; the data volume of the second geographic information database is greater than that of the first geographic information database; the matching results include administrative division terms, directional terms, and address guidance terms corresponding to the source address data.

[0017] Optionally, the determining unit is also used to: if there are no noise words, administrative division words, directional words and address-oriented words in the word segmentation results, perform index matching based on the source address data in the second geographic information database to obtain the matching results; the data volume of the second geographic information database is larger than that of the first geographic information database; the matching results include administrative division words, directional words and address-oriented words corresponding to the source address data.

[0018] Thirdly, an electronic device is provided, comprising: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the address data processing method of the first aspect described above.

[0019] Fourthly, a computer-readable storage medium is provided, on which instructions are stored, such that when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to perform the address data processing method of the first aspect described above.

[0020] The technical solution provided in this application brings at least the following beneficial effects: The address processing device acquires source address data and performs word segmentation processing on the source address data based on a preset noise lexicon, a preset administrative division lexicon, a preset location lexicon, and a pre-trained semantic model to obtain the word segmentation results; the semantic model is used to identify address-oriented words. Since this application references the noise lexicon, administrative division lexicon, location lexicon, and semantic model during word segmentation processing, it is more purposeful in segmenting the source address data, aiming to obtain noise words, administrative divisions, location lexicons, and address-oriented words corresponding to the source address data. When noise words, administrative division words, location words, and address-oriented words exist in the word segmentation results, the address processing device determines the target point of interest from the first geographic information database based on the source address data and the word segmentation results, and obtains the standard administrative division words corresponding to the target point of interest, laying the groundwork for address data standardization. Furthermore, the address processing device determines the similarity between the standard administrative division term and the administrative division term in the word segmentation result. If the similarity is greater than or equal to a preset threshold, the address processing device obtains the target address data based on the standard administrative division term, noise words, directional words, and address-oriented words in the word segmentation result. In this way, the target address data obtained through the above data processing process covers the standard administrative division term, noise words, directional words, and address-oriented words, resulting in a high degree of information completeness. It is more standardized than the source address data, and in subsequent use, noise words in the target address data can be clearly identified, helping to eliminate interference from noise words and improve the accuracy of the target address data. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the structure of a data processing system provided in an embodiment of this application;

[0023] Figure 2 A flowchart illustrating an address data processing method provided in this application embodiment. Figure 1 ;

[0024] Figure 3 This application provides a schematic diagram of the structure of a prefix search tree according to an embodiment of the present application.

[0025] Figure 4 A flowchart illustrating an address data processing method provided in this application embodiment. Figure 2 ;

[0026] Figure 5 This is a schematic diagram of the structure of an address data processing device provided in an embodiment of this application;

[0027] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0028] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0030] It should also be noted that in the embodiments of this application, "of", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be pointed out that when their differences are not emphasized, their meanings are consistent.

[0031] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0032] Before providing a detailed explanation of the embodiments of this application, some related technologies involved in the embodiments of this application will be introduced first.

[0033] With the development of navigation technology and search engines, a large amount of address data has been generated on the internet. This address data is complex and varies in expression, posing significant challenges to address data management and application. Therefore, address data cleaning is of great practical importance.

[0034] Data cleaning refers to the final step in identifying and correcting identifiable errors in data files, including checking data consistency and handling invalid and missing values. Unlike questionnaire review, post-entry data cleaning is generally done by computers rather than manually.

[0035] In practical applications, data cleaning can transform complex and inconsistent address data into data that meets data quality requirements.

[0036] When cleaning address data, related technologies generally only perform keyword queries and synonym substitutions to obtain cleaned address data. However, they are not very effective at identifying noise or interference words. The cleaned address data may still have incomplete information and low accuracy, so its utilization value is not high.

[0037] In view of this, embodiments of this application provide an address data processing method, which aims to transform address data that may contain a large number of errors, name confusion, and incomplete information into more accurate and complete high-value data through data processing means.

[0038] The method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0039] Figure 1 An exemplary application scenario diagram provided by an embodiment of this application is shown. For example... Figure 1 As shown, the address data processing method provided in this application embodiment can be applied to a data processing system 10. The data processing system 10 includes an address data processing device (hereinafter referred to as the data processing device) 11 and an electronic device 12. The data processing device 11 is connected to the electronic device 12. The data processing device 11 and the electronic device 12 can be connected by a wired connection or a wireless connection, and this disclosure embodiment does not limit the connection.

[0040] Electronic device 12 is used to store source address data. For example, electronic device 12 has a database deployed in it, and electronic device 12 stores source address data in the database.

[0041] The data processing device 11 is used to acquire source address data and perform word segmentation processing on the source address data based on a preset noise word library, a preset administrative division word library, a preset location word library, and a pre-trained semantic model to obtain word segmentation results. The data processing device 11 is also used to determine target points of interest from a first geographic information database based on the source address data and the word segmentation results when noise words, administrative division words, location words, and address-oriented words exist in the word segmentation results, and to obtain the standard administrative division words corresponding to the target points of interest. The data processing device 11 is also used to determine the similarity between the standard administrative division words and the administrative division words in the word segmentation results. If the similarity is greater than or equal to a preset threshold, target address data is obtained based on the standard administrative division words, noise words, location words, and address-oriented words in the word segmentation results.

[0042] Electronic device 12 is also used to store target address data in a database.

[0043] In different application scenarios, the data processing device 11 and the electronic device 12 can be independent devices or integrated into the same device. This disclosure does not specifically limit this.

[0044] When the data processing device 11 and the electronic device 12 are integrated into the same device, the data transmission method between the data processing device 11 and the electronic device 12 is the data transmission between modules within the device. In this case, the data transmission process between the two is the same as the data transmission process between the data processing device 11 and the electronic device 12 when they are independent of each other.

[0045] In the following embodiments provided in this disclosure, the data processing device 11 and the electronic device 12 are described as being configured independently of each other.

[0046] Figure 2 This is a flowchart illustrating an address data processing method according to some exemplary embodiments. In some embodiments, the above-described address data processing method can be applied to, for example... Figure 1 The data processing device and electronic equipment shown can also be applied to other similar devices.

[0047] like Figure 2 As shown, the address data processing method provided in this embodiment includes the following steps S201-S203.

[0048] S201. The data processing device acquires source address data and performs word segmentation processing on the source address data based on a preset noise lexicon, a preset administrative division lexicon, a preset location lexicon, and a pre-trained semantic model to obtain the word segmentation results.

[0049] The semantic model is used to identify address-directing words.

[0050] As one possible implementation, the data processing device obtains source address data from the electronic device, and performs word segmentation processing on the source address data based on a preset noise lexicon, a preset administrative division lexicon, a preset location lexicon, and a pre-trained semantic model to obtain the word segmentation result.

[0051] It should be noted that source address data is unprocessed or uncleaned data. While it contains address information, this information may be inaccurate or non-standard. For example, it may contain typos.

[0052] In some embodiments, when performing word segmentation on source address data, the data processing device can refer to noise words in a preset noise word library to determine whether there are identical or similar noise words in the source address data.

[0053] It should be noted that noise words, also known as interfering data, refer to words in source address data that are unrelated to address information. For example, in the source address data "I want to go to Park A", the phrase "I want to go" is unrelated to the specific address and can be considered a noise word.

[0054] In some embodiments, to obtain a noise word library, the data processing device can also acquire search address data in the network through point tracking analysis and manually label the search address data to identify noise words. Further, the data processing device uses the labeled data as samples and, with reference to a large amount of noise-free data in a standard electronic map, trains a conditional random field (CRF) model to obtain a noise word extraction model. Further, the data processing device uses the noise word extraction model to extract noise words from a large amount of unlabeled search address data to obtain a noise word library.

[0055] Similarly, the data processing device can refer to the locative words in the preset locative word library to determine whether there are the same or similar locative words in the source address data.

[0056] The directional term library can be pre-built by maintenance personnel or extracted by data processing devices through model training. This application embodiment does not limit this.

[0057] In some embodiments, when performing word segmentation on source address data, the data processing device can input the source address data into a pre-trained semantic model to extract address-oriented words from the source address data.

[0058] For example, in the source address data "walk 100 meters north to park A", "north" is a directional word, and "walk 100 meters" is an address-directing word.

[0059] In some embodiments, the preset administrative division lexicon includes multiple preset administrative division terms; the word segmentation result includes a first sub-result, which is obtained by segmenting the source address data based on the preset administrative division lexicon.

[0060] In some embodiments, the source address data is segmented based on a preset administrative division terminology to obtain a first sub-result. This includes: the data processing device dividing each preset administrative division term into first and second administrative division sub-terms for each preset administrative division term. The data processing device constructs a prefix search tree using the first administrative division sub-term as the head node and the second administrative division sub-term as the child node. Further, the data processing device indexes the source address data based on the prefix search tree to obtain the first sub-result.

[0061] It should be noted that administrative divisions are regions tiered by relevant departments for ease of administration. For example, an administrative division can have five levels (provincial + municipal + county + township + community). The first administrative division term must be at least as high as the preset level, while the second administrative division term must be at a lower level. The preset levels can be set by the maintenance personnel. In practical applications, the first administrative division term can be the highest-level administrative division term, while the second administrative division term can be any other term that is not the highest-level.

[0062] For example, for administrative division term 1 "Province A, City B, County C, Township D" and administrative division term 2 "Province A, City E, Community F", when constructing the prefix search tree, the data processing device will treat "Province A" as the highest administrative division term and "City B", "County C", "Township D", "City E", and "Community F" as non-highest administrative division terms.

[0063] In other embodiments, the data processing device can also perform word segmentation on the address data based on keywords to obtain a first sub-result. Each keyword corresponds to a different level, and the data processing device can use the level of the keyword matched by the preset administrative division term as the level of the preset administrative division term.

[0064] For example, keywords include province, city, and district, corresponding to levels 1, 2, and 3 respectively. For the source address data "**Province**City**District", the keyword "province" is present in "**province", thus it can be considered an administrative division term, and its level is 1; the keyword "city" is present in "**city", thus it can be considered an administrative division term, and its level is 2; the keyword "district" is present in "**district", thus it can be considered an administrative division term, and its level is 3. For example... Figure 3As shown, an exemplary structure of a prefix search tree is illustrated. "Province A" serves as the head node, with "City B", "County C", "Township D", "City E", and "Community F" connected below the head node as child nodes.

[0065] In practical applications, data processing devices can index the source address data based on the prefix search tree to search for possible administrative division terms in the source address data.

[0066] S202. In the case that there are noisy words, administrative division words, directional words and address-oriented words in the word segmentation results, the data processing device determines the target point of interest from the first geographic information database based on the source address data and word segmentation results, and obtains the standard administrative division words corresponding to the target point of interest.

[0067] As one possible implementation, after the source address data is segmented, if the segmentation results contain noisy words, administrative division words, directional words, and address-oriented words, the data processing device will search the first geographic information database based on the source address data and the segmentation results. If the corresponding point of interest (POI) is found, the data processing device will determine the target point of interest from the search results and obtain the standard administrative division words corresponding to the target point of interest.

[0068] As another possible implementation, if the word segmentation results contain noise words, administrative division words, directional words, and address-oriented words, the data processing device retrieves information from the first geographic information database based on the source address data and the word segmentation results. If a corresponding Point of Interest (POI) is found, multiple POIs are obtained. Further, the data processing device calculates the similarity between each POI and the source address data, and identifies the POI with the highest similarity as the target point of interest. It should be noted that the first geographic information database stores geographic information. For example, the first geographic information database can be a Geographic Information System (GIS or GEO) database.

[0069] In some embodiments, in order to obtain a target point of interest, the data processing device may perform a first search in a first geographic information database based on source address data to obtain a first search result. Further, the data processing device may perform a second search in the first geographic information database based on word segmentation results to obtain a second search result.

[0070] In practical applications, data processing devices can call GEO services to retrieve points of interest.

[0071] For example, when the data processing device calls the GEO service for retrieval, the input content is source address data. If a point of interest corresponding to the input content exists in the first geographic information database, the GEO service outputs the retrieved first point of interest and the matching degree corresponding to each first point of interest. Similarly, when the data processing device calls the GEO service for retrieval, the input content is word segmentation results. If a point of interest corresponding to the input content exists in the first geographic information database, the GEO service outputs the retrieved second point of interest and the matching degree corresponding to each second point of interest. Further, the data processing device obtains the first retrieval result and the second retrieval result, obtains multiple points of interest, and selects the point of interest with the highest matching degree from the multiple points of interest as the target point of interest.

[0072] In some embodiments, the data processing device may employ reverse geospatial reconstruction technology to obtain the standard administrative division terms corresponding to the target point of interest.

[0073] For example, the data processing device acquires the location information (such as latitude and longitude) of the target point of interest. Further, the data processing device uses reverse geospatial services to retrieve the corresponding standard administrative division terms based on the latitude and longitude.

[0074] Understandably, standard administrative division terms are retrieved based on specific location information after that information has been determined. Compared to administrative division terms obtained through word segmentation, standard administrative division terms are more accurate and have a unique correspondence with location information.

[0075] S203. The data processing device determines the similarity between the standard administrative division term and the administrative planning term in the word segmentation result. If the similarity is greater than or equal to a preset threshold, the data processing device obtains the target address data based on the standard administrative division term, noise words, directional words and address guidance words in the word segmentation result.

[0076] As one possible implementation, the data processing device calculates the similarity between the standard administrative division term and the administrative planning term in the word segmentation results using a similarity formula. Further, the data processing device compares the calculated similarity with a preset threshold. If the similarity is greater than or equal to the preset threshold, the data processing device obtains the target address data based on the standard administrative division term, noise words, directional words, and address-oriented words in the word segmentation results.

[0077] For example, the target address data format can be standard administrative division term + location term + address guidance term + noise term.

[0078] In some embodiments, when the similarity is less than a preset threshold, the data processing device obtains the target address data based on administrative division words, noise words, directional words, and address-oriented words in the word segmentation results.

[0079] The technical solution provided in this application provides at least the following beneficial effects: The address processing device acquires source address data and performs word segmentation processing on the source address data based on a preset noise lexicon, a preset administrative division lexicon, a preset location lexicon, and a pre-trained semantic model to obtain the word segmentation results; the semantic model is used to identify address-oriented words. Since this application references the noise lexicon, administrative division lexicon, location lexicon, and semantic model during word segmentation processing, it is more purposeful in segmenting the source address data, aiming to obtain noise words, administrative divisions, location lexicons, and address-oriented words corresponding to the source address data. When noise words, administrative division words, location words, and address-oriented words exist in the word segmentation results, the address processing device determines the target point of interest from the first geographic information database based on the source address data and the word segmentation results, and obtains the standard administrative division words corresponding to the target point of interest, laying the groundwork for address data standardization. Furthermore, the address processing device determines the similarity between the standard administrative division term and the administrative division term in the word segmentation result. If the similarity is greater than or equal to a preset threshold, the address processing device obtains the target address data based on the standard administrative division term, noise words, directional words, and address-oriented words in the word segmentation result. In this way, the target address data obtained through the above data processing process covers the standard administrative division term, noise words, directional words, and address-oriented words, resulting in a high degree of information completeness. It is more standardized than the source address data, and in subsequent use, noise words in the target address data can be clearly identified, helping to eliminate interference from noise words and improve the accuracy of the target address data.

[0080] In some embodiments, in order to ensure that the source address data can be cleaned, if there are no noise words, administrative division words, directional words and address-oriented words in the word segmentation results, the address processing device performs index matching based on the source address data in the second geographic information database to obtain the matching results; wherein, the data volume of the second geographic information database is larger than that of the first geographic information database; the matching results include administrative division words, directional words and address-oriented words corresponding to the source address data.

[0081] Similarly, if both the first and second search results are empty, the address processing device performs index matching in the second geographic information database based on the source address data to obtain the matching result.

[0082] In some embodiments, such as Figure 4As shown, the address processing device performs word segmentation on the source address data to obtain segmentation results. If the segmentation results contain noise words, administrative division words, directional words, and address-oriented words, the address processing device uses the segmentation results to call the GEO service in the first geographic information database to obtain the first search result, and uses the source address data to call the GEO service to obtain the second search result. Conversely, the address processing device uses the source address data to call the GEO service in the second geographic information database to obtain the third search result. If the first and / or second search results contain points of interest, the address processing device selects the point of interest with the highest matching degree as the target point of interest and performs subsequent processing (refer to S202-S203). If the first and second search results do not contain points of interest, the address processing device uses the source address data to call the full-text search service in the second geographic information database to obtain matching results. Similarly, if the third search result does not contain points of interest, the address processing device uses the source address data to call the full-text search service in the second geographic information database to obtain matching results.

[0083] The above embodiments mainly describe the solutions provided by the embodiments of this application from the perspective of an apparatus (device). It is understood that, in order to implement the above methods, the apparatus or device includes hardware structures and / or software modules corresponding to the execution of each method flow. These hardware structures and / or software modules corresponding to the execution of each method flow can constitute a material information determination apparatus. Those skilled in the art should readily recognize that, in conjunction with the algorithm steps of the various examples described in the embodiments of the invention herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0084] This application embodiment can divide the device or equipment into functional modules according to the above method examples. For example, the device or equipment can be divided into functional modules corresponding to each function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0085] Figure 5 This is a schematic diagram illustrating the structure of an address data processing apparatus according to an exemplary embodiment. (Refer to...) Figure 5As shown, the address data processing device 30 provided in this application embodiment includes an acquisition unit 301, a processing unit 302, and a determination unit 303.

[0086] The acquisition unit 301 is used to acquire source address data; the processing unit 302 is used to perform word segmentation processing on the source address data based on a preset noise word library, a preset administrative division word library, a preset location word library, and a pre-trained semantic model to obtain word segmentation results; the semantic model is used to identify address-oriented words; the determination unit 303 is used to determine the target point of interest from the first geographic information database based on the source address data and the word segmentation results when noise words, administrative division words, location words, and address-oriented words exist in the word segmentation results, and to acquire the standard administrative division words corresponding to the target point of interest; the determination unit 303 is also used to determine the similarity between the standard administrative division words and the administrative planning words in the word segmentation results, and if the similarity is greater than or equal to a preset threshold, to obtain the target address data based on the standard administrative division words, noise words, location words, and address-oriented words in the word segmentation results.

[0087] Optionally, the preset administrative division terminology includes multiple preset administrative division terms; the word segmentation result includes a first sub-result, which is obtained by segmenting the source address data based on the preset administrative division terminology; the processing unit 302 is specifically used to: divide each preset administrative division term to obtain the highest administrative division sub-term and non-highest administrative division sub-term of each preset administrative division term; construct a prefix search tree with the highest administrative division sub-term as the head node and the non-highest administrative division sub-term as the child node; and index the source address data based on the prefix search tree to obtain the first sub-result.

[0088] Optionally, the determining unit 303 is specifically used for: when the word segmentation results contain noise words, administrative division words, directional words, and address-oriented words, performing a first search based on the source address data in the first geographic information database to obtain a first search result; and performing a second search based on the word segmentation results in the first geographic information database to obtain a second search result; when the first search result includes at least one first point of interest and the matching degree corresponding to each first point of interest, and / or the second search result includes at least one second point of interest and the matching degree corresponding to each second point of interest, obtaining the first search result and the second search result to obtain multiple points of interest, and selecting the point of interest with the highest matching degree from the multiple points of interest as the target point of interest.

[0089] Optionally, the determination unit 303 is specifically used to: obtain the location information of the target point of interest, and retrieve the standard administrative division term corresponding to the target point of interest based on the reverse geospatial service.

[0090] Optionally, the determining unit 303 is further configured to: when both the first search result and the second search result are empty, perform index matching based on the source address data in the second geographic information database to obtain matching results; the data volume of the second geographic information database is greater than the data volume of the first geographic information database; the matching results include administrative division terms, directional terms and address guidance terms corresponding to the source address data.

[0091] Optionally, the determining unit 303 is further configured to: when there are no noise words, administrative division words, directional words and address-oriented words in the word segmentation results, perform index matching based on the source address data in the second geographic information database to obtain matching results; the data volume of the second geographic information database is greater than that of the first geographic information database; the matching results include administrative division words, directional words and address-oriented words corresponding to the source address data.

[0092] Figure 6 This is a schematic diagram of the structure of an electronic device provided in this application. For example... Figure 6 The electronic device 40 may include at least one processor 401 and a memory 402 for storing processor-executable instructions, wherein the processor 401 is configured to execute the instructions in the memory 402 to implement the address data processing method in the above embodiments.

[0093] In addition, the electronic device 40 may also include a communication bus 403 and at least one communication interface 404.

[0094] Processor 401 may be a processor (central processing unit, CPU), microprocessor unit, ASIC, or one or more integrated circuits for controlling the execution of programs according to the present application.

[0095] The communication bus 403 may include a path for transmitting information between the aforementioned components.

[0096] Communication interface 404 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0097] The memory 402 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may exist independently and be connected to the processor 401 via a bus. The memory may also be integrated with the processor 401.

[0098] The memory 402 stores instructions for executing the scheme of this application, and the processor 401 controls the execution. The processor 401 executes the instructions stored in the memory 402 to realize the functions of the method of this application.

[0099] As an example, combined Figure 5 The functions implemented by the acquisition unit 301, processing unit 302, and determination unit 303 in the address data processing device 30 are the same as those implemented by the acquisition unit 301, processing unit 302, and determination unit 303. Figure 6 The processor 401 in it has the same function.

[0100] In a specific implementation, as one example, processor 401 may include one or more CPUs, for example... Figure 6 CPU0 and CPU1 in the CPU.

[0101] In a specific implementation, as one example, the electronic device 40 may include multiple processors, such as... Figure 6 Processors 401 and 407 are described herein. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor here may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0102] In a specific implementation, as one embodiment, the electronic device 40 may further include an output device 405 and an input device 406. The output device 405 communicates with the processor 401 and can display information in various ways. For example, the output device 405 may be a liquid crystal display (LCD), a light-emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 406 communicates with the processor 401 and can accept input from user objects in various ways. For example, the input device 406 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0103] Those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the electronic device 40, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0104] In addition, this application also provides a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by the processor of an electronic device, enables the electronic device to perform the address data processing method provided in the above embodiments.

[0105] In addition, this application also provides a computer program product, including computer instructions, which, when executed on an electronic device, cause the electronic device to perform the address data processing method provided in the above embodiments.

[0106] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention described herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not invented herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the claims.

Claims

1. An address data processing method, characterized by, The method comprises: obtaining source address data, and performing word segmentation processing on the source address data based on a preset noise word library, a preset administrative division word library, a preset direction word library, and a pre-trained semantic model to obtain a word segmentation result; the semantic model is used to identify address-oriented words; in a case where noise words, administrative division words, direction words, and address-oriented words exist in the word segmentation result, determining a target interest point from a first geographic information database based on the source address data and the word segmentation result, and obtaining a standard administrative division word corresponding to the target interest point; determining a similarity between the standard administrative division word and the administrative planning word in the word segmentation result, and in a case where the similarity is greater than or equal to a preset threshold, obtaining target address data based on the standard administrative division word, the noise word, the direction word, and the address-oriented word in the word segmentation result; in a case where noise words, administrative division words, direction words, and address-oriented words exist in the word segmentation result, the method further comprises: in a case where noise words, administrative division words, direction words, and address-oriented words exist in the word segmentation result, performing first retrieval in the first geographic information database based on the source address data to obtain a first retrieval result; performing second retrieval in the first geographic information database based on the word segmentation result to obtain a second retrieval result; in a case where the first retrieval result includes at least one first interest point and a matching degree corresponding to each first interest point, and / or the second retrieval result includes at least one second interest point and a matching degree corresponding to each second interest point, obtaining a plurality of interest points according to the first retrieval result and the second retrieval result, and selecting an interest point with the highest matching degree from the plurality of interest points as the target interest point.

2. The address data processing method according to claim 1, characterized by, The preset administrative division word library comprises a plurality of preset administrative division words; the word segmentation result comprises a first sub-result obtained by performing word segmentation processing on the source address data based on the preset administrative division word library; the method further comprises: dividing each preset administrative division word to obtain a first administrative division sub-word and a second administrative division sub-word of each preset administrative division word; the division level of the first administrative division sub-word is greater than or equal to a preset level, and the division level of the second administrative division sub-word is less than the preset level; constructing a prefix search tree with the first administrative division sub-word as a head node and the second administrative division sub-word as a sub-node; performing identification in the source address data based on the prefix search tree to obtain the first sub-result.

3. The address data processing method according to claim 2, characterized by, The method further comprises: obtaining position information of the target interest point, and obtaining the standard administrative division word corresponding to the target interest point according to reverse geocoding service retrieval.

4. The address data processing method according to claim 2, characterized by, The method further comprises: In a case where the first search result and the second search result are both null values, index matching is performed in a second geographic information database based on the source address data to obtain a matching result; a data amount of the second geographic information database is greater than a data amount of the first geographic information database; and the matching result includes an administrative division word, a direction word and an address guide word corresponding to the source address data.

5. The address data processing method of claim 1, wherein, The method further includes: In a case where the segmentation result does not include a noise word, an administrative division word, a direction word and an address guide word, index matching is performed in a second geographic information database based on the source address data to obtain a matching result; a data amount of the second geographic information database is greater than a data amount of the first geographic information database; and the matching result includes an administrative division word, a direction word and an address guide word corresponding to the source address data.

6. An address data processing apparatus, characterized by comprising: The apparatus includes an obtaining unit, a processing unit and a determining unit. The obtaining unit is configured to obtain source address data. The processing unit is configured to perform segmentation processing on the source address data based on a preset noise word library, a preset administrative division word library, a preset direction word library and a pre-trained semantic model to obtain a segmentation result. The semantic model is configured to identify an address guide word. The determining unit is configured to, in a case where the segmentation result includes a noise word, an administrative division word, a direction word and an address guide word, determine a target point of interest from a first geographic information database based on the source address data and the segmentation result, and obtain a standard administrative division word corresponding to the target point of interest. The determining unit is further configured to determine a similarity between the standard administrative division word and an administrative planning word in the segmentation result, and in a case where the similarity is greater than or equal to a preset threshold, obtain target address data based on the standard administrative division word, a noise word, a direction word and an address guide word in the segmentation result. The determining unit is specifically configured to: In a case where the segmentation result includes a noise word, an administrative division word, a direction word and an address guide word, perform first search in the first geographic information database based on the source address data to obtain a first search result. Perform second search in the first geographic information database based on the segmentation result to obtain a second search result. In a case where the first search result includes at least one first point of interest and a matching degree corresponding to each first point of interest, and / or the second search result includes at least one second point of interest and a matching degree corresponding to each second point of interest, obtain a plurality of points of interest according to the first search result and the second search result, and select a point of interest with a highest matching degree from the plurality of points of interest as the target point of interest.

7. The address data processing apparatus according to claim 6, wherein The preset administrative division word library includes a plurality of preset administrative division words; the segmentation result includes a first sub-result obtained by performing segmentation processing on the source address data based on the preset administrative division word library; and the processing unit is specifically configured to: The preset administrative division words are divided to obtain first administrative division sub-words and second administrative division sub-words of each of the preset administrative division words; the division level of the first administrative division sub-words is greater than or equal to a preset level, and the division level of the second administrative division sub-words is less than the preset level; A prefix search tree is constructed with the first administrative division sub-words as head nodes and the second administrative division sub-words as sub-nodes; Based on the prefix search tree, the source address data is indexed to obtain the first sub-result.

8. An apparatus, comprising: Comprise: A processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute instructions to implement the address data processing method of any one of claims 1-5.

9. A computer-readable storage medium having stored thereon instructions or a computer program; and / or a computer program, characterized in that, When the computer program or instructions in the computer readable storage medium are executed by the processor of the electronic device, the electronic device can execute the address data processing method as claimed in any one of claims 1-5.

Images