Address information verification method, device, equipment, medium and product

Abstract

The application provides an address information verification method, device, equipment, medium and product, which can be used in the field of financial technology. The method comprises the following steps: obtaining target address information to be verified and determining an address attribute label of the target address information; determining a target map search engine matched with the target address information according to the address attribute label and an engine attribute label of each map search engine; searching the target address information by using the target map search engine and obtaining search result address information; determining an address matching degree between the search result address information and the target address information, and determining a verification result of the target address information according to the address matching degree. Before the search result address information is obtained, the target map search engine matched with the target address information is determined according to the address attribute label and the engine attribute label, so that the matching degree between the obtained search result address information and the target address information is improved, and the accuracy of verifying the address information is improved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and in particular to an address information verification method, apparatus, device, medium and product. Background Technology

[0002] When banks and financial institutions provide services to users, their staff need to verify the user's basic information. Among the user's basic information, one of the most important is the user's address.

[0003] Currently, business personnel typically search for user-provided address information in map search engines and determine its authenticity based on the search results. This process is inefficient. Furthermore, different map search engines yield varying results, and because business personnel often use different search engines, discrepancies in search results can lead to lower accuracy in address verification. Summary of the Invention

[0004] This application provides an address information verification method, apparatus, device, medium, and product to solve the problem that the efficiency and accuracy of address information verification are low because business personnel search for user-provided address information in map search engines and judge whether the user-provided address information is real based on the search results.

[0005] Firstly, this application provides an address information verification method, including:

[0006] Obtain the target address information to be verified and determine the address attribute labels of the target address information;

[0007] The target map search engine that matches the target address information is determined based on the address attribute tags and the engine attribute tags of each map search engine.

[0008] Use a target map search engine to search for target address information and obtain the address information of the search results;

[0009] Determine the address matching degree between the search result address information and the target address information, and determine the verification result of the target address information based on the address matching degree.

[0010] Optionally, obtaining the target address information to be verified includes: obtaining an image containing the target address information; and extracting the target address information from the image using optical character recognition (OCR) technology.

[0011] Optionally, the address attribute label includes: a region category label and a type category label; the process of determining the address attribute label of the target address information includes: obtaining the attribute information of the user corresponding to the target address information; determining the type category label in the address attribute label of the target address information based on the attribute information of the corresponding user; and determining the region category label in the address attribute label of the target address information based on the target address information.

[0012] Optionally, the engine attribute tags include: region category tags and type category tags; before determining the target map search engine to be used based on the address attribute tags and the engine attribute tags of each map search engine, the method further includes: obtaining user group attribute information and user share in each region for each map search engine; determining the type category tags in the engine attribute tags of each map search engine based on the user group attribute information; and determining the region category tags in the engine attribute tags of each map search engine based on the user share in each region.

[0013] Optionally, determining the target map search engine based on the address attribute tags and the engine attribute tags of each map search engine includes: determining the tag matching degree between the address attribute tags and the engine attribute tags of each map search engine; and determining the map search engine corresponding to the maximum tag matching degree as the target map search engine.

[0014] Optionally, determining the tag matching degree between the address attribute tag and the engine attribute tag of each map search engine includes: calculating the tag Jaccard distance between the address attribute tag and the engine attribute tag of each map search engine; determining the tag matching degree according to the tag Jaccard distance corresponding to each map search engine; the tag Jaccard distance is negatively correlated with the tag matching degree.

[0015] Optionally, calculating the address matching degree between the search result address information and the target address information includes: performing word segmentation and standardization operations on the target address information to obtain a target address standard field set; performing word segmentation on the search result address information to obtain a result address field set; calculating the address Jaccard distance between the target address standard field set and the result address field set; determining the address matching degree based on the address Jaccard distance; the address Jaccard distance is negatively correlated with the address matching degree.

[0016] Optionally, the search result address information may be multiple, and determining the verification result of the target address information based on the address matching degree includes: sorting the address Jaccard distances of the multiple target address standard field sets and the result address field sets in descending order; if the Jaccard distance of the last address is determined to be less than or equal to a first preset expected threshold, then the verification result of the target address information is determined to be passed; if the Jaccard distance of the last address is determined to be greater than the first preset expected threshold and less than or equal to a second preset expected threshold, then the target address information is sent to the review terminal so that the reviewer can verify the target address information; if the Jaccard distance of the last address is determined to be greater than the second preset expected threshold, then the verification result of the target address information is determined to be failed.

[0017] Secondly, this application provides an address information verification device, comprising:

[0018] The acquisition module is used to obtain the target address information to be verified;

[0019] The tag determination module is used to determine the address attribute tags of the target address information.

[0020] The engine determination module is used to determine the target map search engine that matches the target address information based on the address attribute tags and the engine attribute tags of each map search engine.

[0021] The acquisition module is also used to search for target address information using a target map search engine and obtain the address information of the search results;

[0022] The matching module is used to determine the address matching degree between the search result address information and the target address information, and to determine the verification result of the target address information based on the address matching degree.

[0023] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0024] The processor and the memory are connected in a communication manner;

[0025] The memory stores computer-executed instructions;

[0026] The processor executes computer execution instructions stored in the memory to implement the address information verification method described in the first aspect above.

[0027] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the address information verification method described in the first aspect.

[0028] Fifthly, this application provides a computer program product, including computer execution instructions, which, when executed by a processor, implement the address information verification method described in the first aspect above.

[0029] The address information verification method, apparatus, device, medium, and product provided in this application acquire target address information to be verified and determine the address attribute tags of the target address information; determine a target map search engine that matches the target address information based on the address attribute tags and the engine attribute tags of various map search engines; search for the target address information using the target map search engine and obtain the search result address information; determine the address matching degree between the search result address information and the target address information, and determine the verification result of the target address information based on the address matching degree. Before obtaining the search result address information, a target map search engine that matches the target address information is pre-determined based on the address attribute tags and the engine attribute tags of various map search engines. Therefore, the matching degree between the obtained search result address information and the target address information is improved, thereby improving the accuracy of verifying the address information. Attached Figure Description

[0030] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0031] Figure 1 A flowchart of the address information verification method provided in Embodiment 1 of this application;

[0032] Figure 2 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0033] Figure 3 This is a schematic diagram of the address information verification device provided in Embodiment 5 of this application;

[0034] Figure 4 This is a schematic diagram of the structure of the electronic device provided in Embodiment Six of this application.

[0035] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0036] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data shall comply with relevant laws, regulations and standards.

[0037] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0038] The terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. In the following descriptions of embodiments, "a plurality of" means two or more, unless otherwise explicitly defined.

[0039] The prior art involved in this invention will be described in detail and analyzed below.

[0040] Currently, business personnel typically search for user-provided address information in map search engines and determine its authenticity based on the search results. This process is inefficient. Furthermore, different map search engines yield varying results, and because business personnel often use different search engines, discrepancies in search results can lead to lower accuracy in address verification.

[0041] The inventors discovered in their research that by pre-determining a target map search engine that matches the target address information, and then using that target map search engine to search for the target address information and obtain the search result address information, the matching degree between the obtained search result address information and the target address information can be improved, thereby increasing the accuracy of verifying the address information. Therefore, this application provides an address information verification method that involves: obtaining the target address information to be verified and determining the address attribute tags of the target address information; determining a target map search engine that matches the target address information based on the address attribute tags and the engine attribute tags of each map search engine; using the target map search engine to search for the target address information and obtaining the search result address information; determining the address matching degree between the search result address information and the target address information; and determining the verification result of the target address information based on the address matching degree.

[0042] It should be noted that the address information verification method, apparatus, device, storage medium, and program product of this application can be used in the fintech field. They can also be used in any field other than fintech. The application areas of the address information verification method, apparatus, device, storage medium, and program product of this application are not limited.

[0043] The collection, storage, use, processing, transmission, provision, and disclosure of financial data or user data involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0044] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0045] Example 1

[0046] Figure 1 This is a flowchart of an address information verification method provided in Embodiment 1 of this application. This embodiment addresses the problem that verifying address information is inefficient and inaccurate because business personnel search for user-provided address information in a map search engine and then determine whether the address information is genuine based on the search results. The method in this embodiment is applied to an address information verification device, which can be located in an electronic device. This electronic device can be a digital computer of various forms, such as a laptop computer, desktop computer, workbench, personal digital assistant, server, blade server, mainframe computer, and other suitable computers.

[0047] like Figure 2 As shown, the specific steps of this method are as follows:

[0048] Step S101: Obtain the target address information to be verified and determine the address attribute label of the target address information.

[0049] The target address information is the address information to be verified provided by the user.

[0050] This application does not limit the method of obtaining the target address information to be verified. For example, if the target address information has already been entered into the system, the target address information to be verified can be obtained through system integration or web crawling technology; if the target address information is handwritten in the registration form, an image of the completed registration form can be obtained, and the target address information to be verified can be identified from the image.

[0051] In this embodiment, there can be multiple address attribute tags, and the address attribute tag items and the tag determination strategy corresponding to each tag item can be preset. Specifically, after obtaining the target address information to be verified, the address attribute tags of the target address information can be determined according to the tag determination strategy corresponding to each tag item.

[0052] Step S102: Determine the target map search engine that matches the target address information based on the address attribute tags and the engine attribute tags of each map search engine.

[0053] The embodiments of this application do not limit the method of determining the target map search engine that matches the target address information.

[0054] For example, if the address attribute tags and the engine attribute tags correspond one-to-one, then the map search engine with the highest similarity can be determined as the target map search engine based on the similarity between the address attribute tags of the target address information and the attribute tags of each engine.

[0055] If the address attribute tags and engine attribute tags cannot be matched one-to-one, the target map search engine can be determined based on the correspondence between the address attribute tags and engine attribute tags.

[0056] Step S103: Use the target map search engine to search for target address information and obtain the search result address information.

[0057] Step S104: Determine the address matching degree between the search result address information and the target address information, and determine the verification result of the target address information based on the address matching degree.

[0058] Specifically, after determining the target map search engine, the target address information can be input into the target map search engine to search for the target address information, and the target map search engine outputs the search result address information. After obtaining the search result address information, the address matching degree between the search result address information and the target address information can be determined. The address matching degree can be compared with a preset expected threshold to determine the verification result of the target address information.

[0059] This application does not limit the method of determining the address matching degree between the search result address information and the target address information. For example, a string similarity comparison algorithm can be used to determine the address matching degree between the search result address information and the target address information, such as edit distance, Word2vec distance, etc.

[0060] The address information verification method provided in this application involves: acquiring target address information to be verified and determining the address attribute tags of the target address information; determining a target map search engine that matches the target address information based on the address attribute tags and the engine attribute tags of each map search engine; searching the target address information using the target map search engine and obtaining the search result address information; determining the address matching degree between the search result address information and the target address information; and determining the verification result of the target address information based on the address matching degree. Before obtaining the search result address information, a target map search engine that matches the target address information is pre-determined based on the address attribute tags and the engine attribute tags of each map search engine. The method then uses the target map search engine to search the target address information and obtain the search result address information, thus improving the matching degree between the obtained search result address information and the target address information, thereby improving the accuracy of the verified address information.

[0061] Optionally, one way to obtain the target address information to be verified is to: obtain an image containing the target address information; and use optical character recognition (OCR) technology to extract the target address information from the image.

[0062] Figure 2 The figure illustrates an application scenario provided by an embodiment of this application, including a mobile terminal 1 and an electronic device 2. When a user provides basic information, the user's basic information can be handwritten in a registration form. Business personnel can use the mobile terminal 1 to collect an image containing target address information and send the image containing target address information to the electronic device 2. After receiving the image containing target address information, the electronic device 2 can use optical character recognition (OCR) technology to extract the target address information in the image and execute the address information verification method provided in this application to verify the target address information.

[0063] The address information verification method provided in this application acquires an image containing target address information and extracts the target address information from the image using Optical Character Recognition (OCR) technology. This eliminates the need for manual input of target address information by business personnel, thus improving the efficiency of target address information verification.

[0064] Example 2

[0065] Based on Embodiment 1 above, this embodiment involves the specific process of pre-setting the engine attribute tags of each map search engine and determining the address attribute tags of the target address information. The specific steps for pre-setting the engine attribute tags of each map search engine are as follows:

[0066] Step S201: Obtain user group attribute information and user share in each region for each map search engine.

[0067] Step S202: Determine the type category tag in the engine attribute tags of each map search engine based on the user group attribute information.

[0068] Step S203: Determine the regional category tag in the engine attribute tags of each map search engine based on the user share in each region.

[0069] In this embodiment of the application, the type category label can be determined based on the user group attribute information of each map search engine that can be obtained.

[0070] For example, if the obtained user group attribute information determines whether the user group is mostly individual users, then the type tag can include commercial tags and residential tags. For instance, if the obtained user group attribute information determines that the map search engine's user group is mostly individual users, then the residential tag can be set to 1 and the commercial tag to 0; if the obtained user group attribute information determines that the map search engine's user group is mostly non-individual users, then the residential tag can be set to 0 and the commercial tag to 1.

[0071] For example, if the obtained user group attribute information determines whether the non-individual users in the user group are mostly institutional users or not, then the type tag can also include an institutional tag and an organizational tag. For instance, if the obtained user group attribute information determines that the non-individual user group of the map search engine is mostly institutional users, then the institutional tag can be set to 1 and the organizational tag to 0; if the obtained user group attribute information determines that the non-individual user group of the map search engine is mostly institutional users, then the institutional tag can be set to 0 and the organizational tag to 1.

[0072] Optionally, the type label may also include an organization type label, such as a catering category or a hotel category. This application embodiment does not limit this.

[0073] In this embodiment of the application, the regional category label can be determined based on the user share of each map search engine in each region.

[0074] For example, if the user share of each map search engine in each city can be determined, then regional tags can include provincial tags, regional tags, and city tags. Specifically, if it is determined that the user share of a certain map search engine in Changsha is greater than a preset share threshold, then the provincial tag can be set as province, the regional tag as Central China, and the city tag as Changsha.

[0075] The address information verification method provided in this application obtains user group attribute information and user share in various regions for each map search engine; determines the type category tag in the engine attribute tags of each map search engine based on the user group attribute information; and determines the region category tag in the engine attribute tags of each map search engine based on the user share in various regions. By using user group attribute information and user share in various regions, the attribute tags of the map search engine can be determined from multiple perspectives, resulting in more comprehensive attribute tags and thus improving the accuracy of determining the target map search engine based on attribute tags.

[0076] Optionally, the address attribute label may include: a region category label and a type category label. The specific steps for determining the address attribute label of the target address information are as follows:

[0077] Step S301: Obtain the attribute information of the user corresponding to the target address information.

[0078] Step S302: Determine the type class label in the address attribute label of the target address information based on the attribute information of the corresponding user.

[0079] Step S303: Determine the region category label in the address attribute label of the target address information based on the target address information.

[0080] In this embodiment of the application, the method of determining the type class tag in the address attribute tag of the target address information based on the attribute information of the corresponding user is similar to the method of determining the type class tag in the engine attribute tag of each map search engine, and will not be described in detail here.

[0081] In this embodiment, the regional label in the address attribute tag of the target address information can be determined based on the target address information. For example, if the regional label includes a provincial label, a regional label, and a city label, the provincial address can be determined as a province, autonomous region, or municipality based on the target address information to determine the corresponding provincial label, and the city name can be extracted to determine the corresponding city label. The regional label of the target address information can then be determined based on the city name. For instance, if the target address information includes Beijing, the provincial label can be determined to be a municipality.

[0082] Optionally, the address attribute tags of the determined target address information include: provincial tag, regional tag, city tag,

[0083] The address information verification method provided in this application embodiment obtains the attribute information of the user corresponding to the target address information; determines the type class label in the address attribute label of the target address information based on the attribute information of the corresponding user; and determines the region class label in the address attribute label of the target address information based on the target address information.

[0084] The address information verification method provided in this application obtains the attribute information of the user corresponding to the target address information; determines the type category tag in the address attribute tags of the target address information based on the corresponding user's attribute information; and determines the region category tag in the address attribute tags of the target address information based on the target address information. By combining the corresponding user's attribute information and the target address information, the address attribute tags of the target address information can be determined from multiple perspectives, resulting in more comprehensive attribute tags and thus improving the accuracy of determining the target map search engine based on the attribute tags.

[0085] Example 3

[0086] Based on the above embodiments, this embodiment involves a refinement of an implementation method for step S102, which determines the target map search engine matching the target address information based on the address attribute tags and the engine attribute tags of each map search engine. Specifically, it includes:

[0087] Step S401: Determine the tag matching degree between the address attribute tags and the engine attribute tags of each map search engine.

[0088] Step S402: Determine the map search engine corresponding to the maximum tag matching degree as the target map search engine.

[0089] This application does not limit the method of determining the tag matching degree. After determining the tag matching degree between the address attribute tag and the engine attribute tag of each map search engine, the largest tag matching degree can be determined, and the map search engine corresponding to the largest tag matching degree can be determined as the target map search engine.

[0090] Optionally, if there are two maximum tag matching scores, the map search engines corresponding to these two maximum tag matching scores can be determined as the target map search engine.

[0091] The address information verification method provided in this application determines the tag matching degree between address attribute tags and engine attribute tags of each map search engine; the map search engine corresponding to the highest tag matching degree is determined as the target map search engine. This method enables the determination of the target map search engine, and determining the target map search engine based on tag matching degree can improve the accuracy of the determined target map search engine.

[0092] Alternatively, one way to determine tag matching degree is:

[0093] Step S4011: Calculate the Jaccard distance between the address attribute label and the engine attribute label of each map search engine.

[0094] Step S4012: Determine the tag matching degree according to the Jaccard distance of the tags corresponding to each map search engine.

[0095] It should be understood that the label Jaccard distance is negatively correlated with the label matching degree. The Jaccard distance is defined as follows:

[0096]

[0097] The larger the Jaccard distance, the lower the sample similarity. The symmetric difference is: .

[0098] in, The Jaccard similarity coefficient is used to compare the similarity and differences between finite sample sets. A higher Jaccard coefficient indicates higher sample similarity. The proportion of elements in the intersection of two sets A and B that are also elements in the union of A and B is called the Jaccard coefficient, denoted by the symbol [symbol missing]. This indicates that when sets A and B are empty, Defined as 1, it is an indicator used to measure the similarity between two samples.

[0099] Specifically, address attribute tags and engine attribute tags from various map search engines can be used to generate address attribute tag sets and engine attribute tag sets, respectively. The Jaccard distance algorithm is then used to calculate the tag Jaccard distance between the address attribute tag sets and the engine attribute tag sets.

[0100] For example, address attribute tags and engine attribute tags can include: provincial tag, regional tag, city tag, urban area tag, suburban tag, institution tag, commercial tag, and residential tag; if the target address information has the provincial tag as "province", the regional tag as "South China", the city tag as "f1", the urban area tag as "1", the suburban tag as "0", the institution tag as "1", the commercial tag as "1", and the residential tag as "0", then the determined set of address attribute tags is: If a map search engine has the following engine attribute tag set: province, region tag: South China, city tag: f1, urban area tag: 1, suburb tag: 0, institution tag: 1, institution tag: 0, commercial tag: 1, residential tag: 0, then the determined engine attribute tag set is: The distance between the address attribute label of the target address information and the Jaccard distance of the engine attribute label of the map search engine is:

[0101]

[0102] For example, if another engine's attribute tag set is The Jaccard distance between the address attribute tags of the target address information and the engine attribute tags of the map search engine corresponding to this set of engine attribute tags is:

[0103]

[0104] A Jaccard distance of 0 indicates that the map search engine and the target address information are a perfect match, with a tag matching degree of 100%.

[0105] In this embodiment of the application, after determining the Jaccard distance, the tag matching degree can be determined based on the Jaccard distance. The lower the Jaccard distance, the higher the tag matching degree, and the better the corresponding map search engine matches the target address information.

[0106] The address information verification method provided in this application calculates the Jaccard distance between address attribute tags and engine attribute tags of various map search engines; determines the tag matching degree based on the tag Jaccard distance corresponding to each map search engine; the tag Jaccard distance is negatively correlated with the tag matching degree. Using the tag Jaccard distance between address attribute tags and engine attribute tags can improve the accuracy of the determined matching degree.

[0107] Example 4

[0108] Based on the above embodiments, this embodiment involves a refinement of an implementation method for step S104, which determines the address matching degree between the search result address information and the target address information, and determines the verification result of the target address information based on the address matching degree. Specifically, it includes:

[0109] Step S501: Perform word segmentation and standardization operations on the target address information to obtain a set of standard fields for the target address.

[0110] Step S502: Perform word segmentation on the search result address information to obtain the result address field set.

[0111] Step S503: Calculate the Jaccard distance between the target address standard field set and the result address field set.

[0112] Step S504: Determine the address matching degree based on the Jaccard distance.

[0113] Among them, the Jaccard distance between addresses is negatively correlated with the address matching degree.

[0114] Specifically, after performing word segmentation and standardization operations on the target address information, a set of standard fields for the target address can be obtained. After performing word segmentation on the address information of the search results returned by the map search engine, the set of address fields in the results can be obtained. If you want to retrieve the URL information of multiple search results, you can obtain multiple sets of result URL fields. ... .

[0115] It should be understood that word segmentation, also known as lexicalization, refers to the process of converting a raw character stream into individual words. Lexicalization is a preprocessing step in natural language processing and is the foundation for semantic analysis.

[0116] In this embodiment, the method of calculating the address Jaccard distance between the target address standard field set and the result address field set, and determining the address matching degree based on the address Jaccard distance, is similar to the method of determining the label Jaccard distance and label matching degree in Embodiment 3.

[0117] For example, if the target address standard field set With the set of result address fields If the number of unions is n and the number of intersections is n, then the Jaccard distance is:

[0118]

[0119] If the target address standard field set With the set of result address fields If the number of unions is n and the number of intersections is n / 2, then the Jaccard distance is:

[0120]

[0121] The address information verification method provided in this application performs word segmentation and standardization operations on the target address information to obtain a set of standard fields for the target address; performs word segmentation on the search result address information to obtain a set of result address fields; calculates the address Jaccard distance between the target address's standard field set and the result address's field set; and determines the address matching degree based on the address Jaccard distance. The address Jaccard distance is negatively correlated with the address matching degree. Word segmentation of the target address information and the search result address information allows for the acquisition of field sets, thereby determining the address Jaccard distance between the target address information and the search result address information. Standardization of the target address information avoids a decrease in matching degree due to non-standardization of the target address information, improving the accuracy of the determined address matching degree and further enhancing the accuracy of the verification results.

[0122] In this embodiment, after determining the tag matching degree, if only one search result address is obtained, then the determined tag matching degree is one, and the tag matching degree can be directly compared with a preset expected threshold to determine the verification result of the target address information. If multiple search result address information is obtained, then multiple tag matching degrees are determined. The tag matching degree with the highest matching degree can be determined from the multiple tag matching degrees, and the tag matching degree with the highest matching degree can be compared with a preset expected threshold to determine the verification result of the target address information.

[0123] Optionally, when there are multiple search result address information, steps S505 to S506 can be executed to determine the verification result of the target address information based on the address matching degree.

[0124] Step S505: Sort the Jaccard distances between the multiple target address standard field sets and the result address field sets in descending order.

[0125] Step S506: If the distance to the last address Jaccard is determined to be less than or equal to the first preset expected threshold, then the verification result of the target address information is determined to be passed.

[0126] Step S507: If it is determined that the distance of the last address Jaccard is greater than the first preset expected threshold and less than or equal to the second preset expected threshold, then the target address information is sent to the audit terminal so that the auditor can verify the target address information.

[0127] Step S508: If the distance to the last address Jaccard is determined to be greater than the second preset expected threshold, then the verification result of the target address information is determined to be unsuccessful.

[0128] In this embodiment, the preset expected threshold can be preset according to actual conditions.

[0129] Specifically, the calculated Jaccard distances can be sorted in descending order, and the minimum value can be taken. The Jaccard distance of the last address determines the verification result. If the Jaccard distance of the last address is 0, it means that the search result address information and the target address information match exactly. If the Jaccard distance of the last address is 1, it means that the search result address information and the target address information do not match at all.

[0130] For example, the first preset expected threshold can be 0.05, and the second preset expected threshold can be 0.2; if the Jaccard distance of the last address is less than or equal to the expected value of 0.05, that is... This indicates that the address matching rate is above 95%, thus the verification result for the target address information is considered successful. If... If the similarity is 80%–95%, the target address information needs to be sent to the verification terminal for manual judgment to determine the verification result. If the similarity is less than 80%, then the verification result for the target address information is determined to be unsuccessful.

[0131] Currently, when multiple matching results appear, further manual screening and confirmation are still required. The address information verification method provided in this application embodiment can determine the verification result of the target address information when there are multiple search result address information, which can improve the verification efficiency of multiple search result address information. Furthermore, when it is determined that the Jaccard distance of the last address is greater than the first preset expected threshold and less than or equal to the second preset expected threshold, the target address information is sent to the review terminal so that the reviewer can verify the target address information, which can improve the accuracy of the verification result.

[0132] Example 5

[0133] Figure 3 This is a schematic diagram of the address information verification device provided in Embodiment 5 of this application. The address information verification device provided in this embodiment can execute the processing flow provided in the address information verification method embodiment. Figure 3 As shown, the address information verification device 60 includes: an acquisition module 601, a tag determination module 602, an engine determination module 603, and a matching module 604.

[0134] Specifically, module 601 is used to obtain the target address information to be verified;

[0135] The tag determination module 602 is used to determine the address attribute tag of the target address information;

[0136] Engine determination module 603 is used to determine the target map search engine that matches the target address information based on the address attribute tags and the engine attribute tags of each map search engine;

[0137] The acquisition module 601 is also used to search for target address information using the target map search engine and obtain the search result address information;

[0138] The matching module 604 is used to determine the address matching degree between the search result address information and the target address information, and to determine the verification result of the target address information based on the address matching degree. Optionally, the acquisition module 601 is specifically used to: acquire an image containing the target address information; and extract the target address information from the image using optical character recognition (OCR) technology.

[0139] Optionally, the address attribute labels include: a region category label and a type category label; the label determination module 602 is specifically used to: obtain the attribute information of the user corresponding to the target address information; determine the type category label in the address attribute labels of the target address information based on the attribute information of the corresponding user; and determine the region category label in the address attribute labels of the target address information based on the target address information.

[0140] Optionally, the engine attribute tags include: region-type tags and type-type tags; the tag determination module 602 is also used to: obtain user group attribute information and user share in each region for each map search engine; determine the type-type tags in the engine attribute tags of each map search engine based on the user group attribute information; and determine the region-type tags in the engine attribute tags of each map search engine based on the user share in each region.

[0141] Optionally, the engine determination module 603 includes a calculation unit and a determination unit; the matching degree determination unit is used to: determine the tag matching degree between the address attribute tags and the engine attribute tags of each map search engine; the engine determination unit is used to: determine the map search engine corresponding to the maximum tag matching degree as the target map search engine.

[0142] Optionally, the matching degree determination unit is specifically used to: calculate the Jaccard distance between the address attribute tags and the engine attribute tags of each map search engine; determine the tag matching degree according to the tag Jaccard distance corresponding to each map search engine; the tag Jaccard distance is negatively correlated with the tag matching degree.

[0143] Optionally, the matching module 604 is specifically used for: performing word segmentation and standardization operations on the target address information to obtain a set of standard fields for the target address; performing word segmentation operations on the search result address information to obtain a set of result address fields; calculating the address Jaccard distance between the set of standard fields for the target address and the set of result address fields; determining the address matching degree based on the address Jaccard distance; and the address Jaccard distance is negatively correlated with the address matching degree.

[0144] Optionally, the search result address information includes multiple addresses, and the matching module 604 is further configured to: sort the Jaccard distances of the multiple target address standard field sets and the result address field sets in descending order; if the Jaccard distance of the last address is determined to be less than or equal to a first preset expected threshold, then the verification result of the target address information is determined to be passed; if the Jaccard distance of the last address is determined to be greater than the first preset expected threshold and less than or equal to a second preset expected threshold, then the target address information is sent to the review terminal so that the reviewer can verify the target address information; if the Jaccard distance of the last address is determined to be greater than the second preset expected threshold, then the verification result of the target address information is determined to be failed.

[0145] The apparatus provided in this application embodiment can be specifically used to execute the above method embodiments, and its specific functions will not be described in detail here.

[0146] Example 6

[0147] Figure 4 This is a schematic diagram of the structure of the electronic device provided in Embodiment Six of this application, as shown below. Figure 4 As shown, this application also provides an electronic device 70, including: a memory 701 and a processor 702.

[0148] The processor 702 and the memory 701 are communicatively connected; the memory 701 stores instructions to be executed by the computer. Specifically, the program may include program code, which includes instructions to be executed by the computer. The memory 701 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device.

[0149] Processor 702 is used to execute computer execution instructions stored in memory 701.

[0150] The computer execution instructions are stored in memory 701 and configured to be executed by processor 702 to implement the method provided in any embodiment of this application. Related descriptions can be understood by referring to the relevant descriptions and effects corresponding to the steps in the accompanying drawings, and will not be elaborated upon here.

[0151] In this embodiment, the memory 701 and the processor 702 are connected via a bus. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0152] This application also provides a computer-readable storage medium storing computer-executable instructions thereon, which are executed by a processor to implement the method provided in any embodiment of this application.

[0153] This application also provides a computer program product, including computer execution instructions, which, when executed by a processor, implement the method provided in any embodiment of this application.

[0154] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0155] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0156] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or in a combination of hardware and software functional modules.

[0157] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to the processor or controller of a general-purpose computer, special-purpose computer, or other programmable full-path fusion device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0158] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer 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 of the foregoing.

[0159] Furthermore, although the operations are described in a specific order, this should be understood as requiring that such operations be performed in the specific order shown or in sequential order, or requiring that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this application. Certain features described in the context of individual embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented individually or in any suitable sub-combination in multiple implementations.

[0160] Other embodiments of this application 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 application that follow the general principles of this application 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 application are indicated by the following claims.

[0161] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for verifying address information, characterized in that, include: Obtain the target address information to be verified; Obtain the attribute information of the user corresponding to the target address information, determine the type class label in the address attribute label of the target address information based on the attribute information of the corresponding user, and determine the region class label in the address attribute label based on the target address information, so as to obtain an address attribute label containing region class label and type class label; Before using a map search engine, obtain the user group attribute information and user share in each region of each map search engine. Based on the user group attribute information, determine the type category tag in the engine attribute tag of each map search engine, and based on the user share in each region, determine the region category tag in the engine attribute tag, so as to obtain an engine attribute tag containing region category tag and type category tag. Calculate the Jaccard distance between the address attribute tags and the engine attribute tags of each map search engine, and determine the tag matching degree based on the Jaccard distance; the Jaccard distance is negatively correlated with the tag matching degree. The map search engine corresponding to the highest tag matching degree is determined as the target map search engine; The target address information is searched using the target map search engine to obtain multiple search result address information; The target address information is segmented and standardized to obtain a set of standard fields for the target address; each search result address is segmented to obtain a set of corresponding result address fields. Calculate the Jaccard distance between the target address standard field set and each of the result address field sets, and determine the address matching degree based on the address Jaccard distance; the address Jaccard distance is negatively correlated with the address matching degree. The calculated Jaccard distances of multiple addresses are sorted in descending order, and the Jaccard distance of the last address is taken. If the Jaccard distance of the last address is less than or equal to a first preset expected threshold, the verification result of the target address information is determined to be passed. If the Jaccard distance of the last address is greater than the first preset expected threshold and less than or equal to a second preset expected threshold, the target address information is sent to the review terminal so that the reviewer can verify the target address information. If the Jaccard distance of the last address is greater than the second preset expected threshold, the verification result of the target address information is determined to be failed.

2. The method according to claim 1, characterized in that, The process of obtaining the target address information to be verified includes: Retrieve an image containing the target address information; The target address information in the image is extracted using optical character recognition (OCR) technology.

3. An address information verification device, characterized in that, include: The acquisition module is used to obtain the target address information to be verified; The tag determination module is used to obtain the attribute information of the user corresponding to the target address information, determine the type class tag in the address attribute tag of the target address information according to the attribute information of the corresponding user, and determine the region class tag in the address attribute tag according to the target address information, so as to obtain an address attribute tag containing the region class tag and the type class tag; The engine determination module is used to obtain user group attribute information and user share in each region of each map search engine before using the map search engine to search. Based on the user group attribute information, it determines the type class tag in the engine attribute tag of each map search engine, and determines the region class tag in the engine attribute tag based on the user share in each region, so as to obtain engine attribute tags containing region class tags and type class tags. It is also used to calculate the Jaccard distance between the address attribute tags and the engine attribute tags of each map search engine, and to determine the tag matching degree according to the Jaccard distance; the Jaccard distance is negatively correlated with the tag matching degree; and to determine the map search engine corresponding to the maximum tag matching degree as the target map search engine. The acquisition module is also used to search for the target address information using the target map search engine and obtain multiple search result address information; The matching module is used to perform word segmentation and standardization operations on the target address information to obtain a set of standard fields for the target address; and to perform word segmentation operations on each of the search result address information to obtain a set of corresponding result address fields. Calculate the Jaccard distance between the target address standard field set and each of the result address field sets, and determine the address matching degree based on the Jaccard distance; the Jaccard distance is negatively correlated with the address matching degree; sort the calculated Jaccard distances in descending order and take the last Jaccard distance; if the last Jaccard distance is less than or equal to a first preset expected threshold, the verification result of the target address information is determined to be passed; if the last Jaccard distance is greater than the first preset expected threshold and less than or equal to a second preset expected threshold, the target address information is sent to the review terminal so that the reviewer can verify the target address information; if the last Jaccard distance is greater than the second preset expected threshold, the verification result of the target address information is determined to be failed.

4. The apparatus according to claim 3, characterized in that, The acquisition module is specifically used to: acquire an image containing target address information; and extract the target address information from the image using optical character recognition (OCR) technology.

5. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The processor and the memory are connected in a communication manner; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in claim 1 or 2.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in claim 1 or 2.

7. A computer program product comprising computer-executable instructions, characterized in that, When the computer execution instructions are executed by the processor, they implement the method as described in claim 1 or 2.

Images