Address search method, device, equipment and computer-readable storage medium

Abstract

The present invention discloses an address search method, apparatus, device, and computer-readable storage medium. The address search method comprises: parsing the administrative level 4 text and detailed address information of the address to be searched, and performing named entity recognition on the administrative level 4 text and the detailed address information to obtain named entity information; recalling a number of intermediate addresses based on the administrative level 4 text, the detailed address information, and the named entity information; and calculating the text similarity between each intermediate address and the address to be searched based on the text length of the named entity information in each intermediate address, thereby determining the final address. The address search method disclosed in the present invention can improve the accuracy of address searches.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an address search method, device, equipment and computer-readable storage medium. Background Art

[0002] Address search is widely used in map navigation and logistics fields. In the map navigation field, when a navigation request is input into the navigation system in the form of address text, the navigation system can usually extract the address name based on the received navigation request and use the extracted address name to determine multiple target addresses for the user to choose from. Unlike the map navigation field where multiple target addresses are determined for the user to choose from, in the logistics field, it is usually necessary to determine a corresponding target address based on the requested address text, so the accuracy of the target address is extremely important. The traditional method of obtaining the target address through fuzzy search makes it difficult to search for a target address with high accuracy. Summary of the Invention

[0003] The present invention provides an address search method, device, equipment and computer-readable storage medium, which are used to solve the technical problem in the prior art that it is difficult to search for a target address with high accuracy.

[0004] In order to solve the above technical problems, in a first aspect, the present invention provides an address search method, which includes:

[0005] Parsing the administrative level 4 text and detailed address information of the address to be searched, and performing named entity recognition on the administrative level 4 text and the detailed address information to obtain named entity information;

[0006] Recalling a number of intermediate addresses based on the administrative level 4 text, the detailed address information, and the named entity information;

[0007] According to the text length of the named entity information in each intermediate address, the text similarity between each intermediate address and the address to be searched is calculated respectively to determine the final address.

[0008] Optionally, calculating the text similarity between each intermediate address and the address to be searched based on the text length of the named entity information in each intermediate address to determine the final address includes:

[0009] For each intermediate address, the text similarity between the current intermediate address and the address to be searched is calculated based on a refined sorting algorithm formula including the text length of the named entity information in the current intermediate address, the initial text similarity between the current intermediate address and the address to be searched, and the text length of the current intermediate address after removing the administrative level 3 text;

[0010] The intermediate address with the highest text similarity is taken as the final address.

[0011] Optionally, the refined sorting algorithm formula is:

[0012] Where F is the text similarity between the current intermediate address and the address to be searched, s is the initial text similarity, c i is the text length of the i-th entity in the named entity information in the current intermediate address, o is the text length of the current intermediate address after removing the administrative level 3 text, w i is the weight of the i-th entity in the named entity information in the current intermediate address.

[0013] Optionally, based on the administrative level 4 text, the detailed address information, and the named entity information, a number of intermediate addresses are recalled, including:

[0014] Determine the address search scope according to the administrative level 4 text;

[0015] Searching for a plurality of initial addresses having the highest similarity to the detailed address information within the address search range;

[0016] A weighted score is given to each initial address according to the named entity information, and several initial addresses with the highest recall scores are used as intermediate addresses.

[0017] Optionally, determining the address search scope according to the administrative level 4 text includes:

[0018] Determine the address search source according to the second-level administrative text in the four-level administrative text;

[0019] The address search source is used as the address search range.

[0020] Optionally, after determining the address search range according to the fourth-level administrative text, the method further includes:

[0021] According to the third level administrative text in the four level administrative text, the address search range is narrowed.

[0022] Optionally, named entity recognition is performed on the administrative level 4 text and the detailed address information to obtain named entity information, including:

[0023] Performing named entity recognition on the fourth-level administrative text to obtain the fourth-level administrative text as the first entity;

[0024] Performing named entity recognition on the detailed address information according to a preset entity type to obtain a plurality of second entities;

[0025] The first entity and the second entity are used as named entity information.

[0026] In a second aspect, the present invention provides an address search device, comprising an entity information acquisition module, a first address acquisition module, and a second address acquisition module;

[0027] The entity information acquisition module is used to parse the administrative level 4 text and detailed address information of the address to be searched, and perform named entity recognition on the administrative level 4 text and the detailed address information to obtain named entity information;

[0028] The first address acquisition module is configured to recall a plurality of intermediate addresses based on the administrative level 4 text, the detailed address information, and the named entity information;

[0029] The second address acquisition module is used to calculate the text similarity between each intermediate address and the address to be searched according to the text length of the named entity information in each intermediate address, and determine the final address.

[0030] In a third aspect, the present invention provides an address search device, comprising a memory and a processor, wherein:

[0031] The memory is used to store computer programs;

[0032] The processor is used to read the program in the memory and execute the steps of the address search method provided in the first aspect above.

[0033] In a fourth aspect, the present invention provides a computer-readable storage medium having a readable computer program stored thereon, which, when executed by a processor, implements the steps of the address search method provided in the first aspect above.

[0034] Compared with the prior art, the address search method, device, equipment, and computer-readable storage medium provided by the present invention have the following beneficial effects:

[0035] The invention can meet the demand of searching for a target address with higher accuracy and improve the accuracy of address search; by parsing the administrative level 4 text and detailed address information of the address to be searched, and performing named entity recognition on the administrative level 4 text and the detailed address information, named entity information is obtained; the accuracy and efficiency of named entity recognition of the address to be searched can be improved to improve the accuracy and efficiency of subsequent address search; according to the administrative level 4 text, the detailed address information and the named entity information, several intermediate addresses are recalled; the administrative level 4 text and the named entity information are involved in the recall to improve the accuracy of the recalled intermediate addresses; according to the text length of the named entity information in each intermediate address, the text similarity between each intermediate address and the address to be searched is calculated respectively to determine the final address; by involving the text length of the named entity information in the intermediate address in the calculation of text similarity, the accuracy of the text similarity calculation is improved, and the accuracy of address search is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only part of the embodiments of the present invention, rather than all the embodiments. For ordinary technicians in this field, without paying any creative work, other drawings obtained based on these drawings are all within the scope of protection of this application.

[0037] Figure 1 This is a flow chart of an address search method provided by an embodiment of the present invention;

[0038] Figure 2 This is a schematic structural diagram of an address search device provided by an embodiment of the present invention;

[0039] Figure 3 This is a schematic structural diagram of an address search device provided by an embodiment of the present invention;

[0040] Figure 4 It is a schematic diagram of the structure of a computer-readable storage medium provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0042] In order to make the description of the present disclosure more detailed and complete, the following is an illustrative description of the implementation methods and specific examples of the present invention; however, this is not the only form of implementing or using the specific embodiments of the present invention. The implementation methods cover the features of multiple specific embodiments and the method steps and their sequence for constructing and operating these specific embodiments. However, other specific embodiments can also be used to achieve the same or equal functions and step sequences. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0043] It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present invention described herein can be practiced in an order other than that illustrated or described herein.

[0044] In the description of the embodiments of the present application, "multiple" refers to two or more than two, and other quantifiers should be understood similarly. The preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention. In addition, the embodiments of the present application and the features in the embodiments may be combined with each other if there is no conflict.

[0045] Example 1

[0046] like Figure 1 FIG. 1 is a flowchart of an address search method provided by an embodiment of the present invention, wherein the address search method includes the following steps:

[0047] Step S101, parsing the administrative level 4 text and detailed address information of the address to be searched, and performing named entity recognition on the administrative level 4 text and the detailed address information to obtain named entity information;

[0048] The embodiment of the present invention does not limit the specific implementation of the above-mentioned address resolution logic to be searched, and any implementation that can resolve the fourth-level administrative text and detailed address information can be applied to the embodiment of the present invention.

[0049] The address to be searched can be a user-requested address. The AC automaton can be used to parse the administrative level 4 text and detailed address information of the address to be searched. Furthermore, the administrative code can be parsed. The AC automaton is a multi-modal matching algorithm. The administrative level 4 text includes administrative divisions that comply with national standards, and the administrative code can be an administrative division code.

[0050] As an optional implementation, named entity recognition is performed on the administrative level 4 text and the detailed address information to obtain named entity information, including:

[0051] Performing named entity recognition on the fourth-level administrative text to obtain the fourth-level administrative text as the first entity;

[0052] Performing named entity recognition on the detailed address information according to a preset entity type to obtain a plurality of second entities;

[0053] The first entity and the second entity are used as named entity information.

[0054] It should be noted that the named entity information may include a first entity and a second entity, wherein the first entity may be a fourth-level administrative text, ie, a town or a street, and the second entity is the content in the detailed address information.

[0055] Among them, the training data formed by the fourth-level administrative text and detailed address information can be used to train the named entity recognition model formed by ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately)-small combined with CRF (Conditional Random Field) to obtain a trained named entity recognition model, and the trained named entity recognition model is used to perform named entity recognition on the fourth-level administrative text and the detailed address information to obtain named entity information.

[0056] When the named entity recognition model is trained using the training data, the administrative level 4 text and the detailed address information may be annotated at the word level using BIEOS tags.

[0057] It should be noted that ELECTRA-small combined with CRF has better feature extraction performance and higher named entity recognition accuracy, and it takes less time to annotate a single administrative level 4 text and detailed address information.

[0058] In some embodiments, the address to be searched is Unit 3, Building A, Meili Times Garden, at the intersection of Xixiang Avenue and Xinhu Road, Hakka Village, Bao'an District, Shenzhen City, Guangdong Province, and Bao'an Tianhong Shopping Center. The administrative level 4 text and detailed address information of the address to be searched are parsed, and the administrative level 4 obtained by parsing is: "province":"Guangdong Province", "city":"Shenzhen City", "area":"Bao'an District", "town":null. The corresponding administrative level 4 text is "Bao'an District, Shenzhen City, Guangdong Province". The detailed address information after removing the administrative level 4 is Unit 3, Building A, Meili Times Garden, at the intersection of Xixiang Avenue and Xinhu Road, Hakka Village, Bao'an Tianhong Shopping Center. Named entity recognition is performed on the administrative level 4 text and the detailed address information, and the named entity information obtained is "village":"Hakka Village". , "village_group":"Group 3","road":"Xixiang Avenue","0":"and","road":"Xinhu Road","0":"Intersection","poi":"Charming Times Garden","house_no":"Building A","cell_no":"Unit 3","sub_poi":"Baoan Tianhong Shopping Center"; where village represents a community or village, village_group represents a group or team, dev_zone represents a park, road represents a road, road_no represents a road number, poi represents a point of interest, sub_poi represents a sub-point of interest, house_no represents a building number, cell_no represents a unit number, and 0 represents an invalid entity, which can be filtered out.

[0059] Step S102, recalling a number of intermediate addresses based on the administrative level 4 text, the detailed address information, and the named entity information;

[0060] In some embodiments, Elacstic Search is used to recall several intermediate addresses. The algorithm for determining the intermediate addresses in Elacstic Search may be the BM25 algorithm, which has no semantic concept and calculates all text information. When there is a long period of invalid information in the address, it is easy to recall the wrong address. The invalid information may be text that is unrelated to the address, such as mobile phone numbers, names, and sending instructions. In order to avoid Elacstic Search recalling incorrect addresses, administrative level 4 text and named entity information may be included in the recall of Elacstic Search to improve the accuracy of recalling intermediate addresses.

[0061] As an optional implementation, based on the administrative level 4 text, the detailed address information, and the named entity information, several intermediate addresses are recalled, including:

[0062] Determine the address search scope according to the administrative level 4 text;

[0063] Searching for a plurality of initial addresses having the highest similarity to the detailed address information within the address search range;

[0064] A weighted score is given to each initial address according to the named entity information, and several initial addresses with the highest recall scores are used as intermediate addresses.

[0065] In some embodiments, the address search range can be determined based on the administrative level 4 text. For example, the address to be searched is Factory 2, Yulongchang Industrial Park, Pinghushan Xiake Park, Longgang District, Shenzhen City, Guangdong Province, and the administrative level 4 text is Longgang District, Shenzhen City, Guangdong Province. The address search range can be determined by the administrative level 4 text "Longgang District, Shenzhen City, Guangdong Province".

[0066] As an optional implementation, determining the address search range based on the administrative level 4 text includes:

[0067] Determine the address search source according to the second-level administrative text in the four-level administrative text;

[0068] The address search source is used as the address search range.

[0069] In some embodiments, the address search source is determined based on the second-level administrative text in the four-level administrative text. For example, the corresponding data source or address database, ie, the address search source, is determined through the second-level administrative text "Shenzhen City".

[0070] The embodiment of the present invention uses the address search source as the address search range, which can reduce the address search range and improve the efficiency of the address search.

[0071] As an optional implementation manner, after determining the address search range according to the fourth-level administrative text, the method further includes:

[0072] According to the third level administrative text in the four level administrative text, the address search range is narrowed.

[0073] In some embodiments, after determining the address search range based on the fourth-level administrative text, that is, determining the address search source based on the second-level administrative text in the fourth-level administrative text, and using the address search source as the address search range, it is easy to cause the address search to cross regions. Therefore, narrowing the address search range based on the third-level administrative text in the fourth-level administrative text can further improve the efficiency of the address search.

[0074] Each initial address can be weighted and scored according to the named entity information.

[0075] Specifically, if the initial address includes the fourth-level administrative text, that is, the town, the corresponding weight score of the entity is 1; if the initial address includes the fourth-level administrative text and the village, the corresponding weight score of the entity is 1; if the initial address includes the road and the road number, the corresponding weight score of the entity is 1; if the initial address includes the point of interest, the corresponding weight score of the entity is 0.7.

[0076] Within the address search range, multiple initial addresses with the highest similarity to the detailed address information are searched, each initial address is weighted and scored, all initial addresses are arranged from large to small according to the score, and the initial addresses with the highest scores are recalled as intermediate addresses.

[0077] Step S103 : calculating the text similarity between each intermediate address and the address to be searched based on the text length of the named entity information in each intermediate address, and determining the final address.

[0078] After recalling several intermediate addresses based on the administrative level 4 text, the detailed address information and the named entity information, it is necessary to calculate the text similarity between each intermediate address and the address to be searched based on the text length of the named entity information in each intermediate address, so as to determine the address most similar to the address to be searched and return it as the final address, thereby further improving the accuracy of the address search.

[0079] As an optional implementation, the text similarity between each intermediate address and the address to be searched is calculated based on the text length of the named entity information in each intermediate address to determine the final address, including:

[0080] For each intermediate address, the text similarity between the current intermediate address and the address to be searched is calculated based on a refined sorting algorithm formula including the text length of the named entity information in the current intermediate address, the initial text similarity between the current intermediate address and the address to be searched, and the text length of the current intermediate address after removing the administrative level 3 text;

[0081] The intermediate address with the highest text similarity is taken as the final address.

[0082] In some embodiments, a refined sorting algorithm formula including the text length of the named entity information in the current intermediate address, the initial text similarity between the current intermediate address and the address to be searched, and the text length of the current intermediate address after removing the administrative third-level text can be used to score several intermediate addresses separately to obtain a score corresponding to each intermediate address, and then obtain the address that is most similar to the text of the address to be searched from several intermediate addresses.

[0083] As an optional implementation, the refined sorting algorithm formula is:

[0084] Where F is the text similarity between the current intermediate address and the address to be searched, s is the initial text similarity, c i is the text length of the i-th entity in the named entity information in the current intermediate address, o is the text length of the current intermediate address after removing the administrative level 3 text, w i is the weight of the i-th entity in the named entity information in the current intermediate address.

[0085] In some embodiments, the initial text similarity s between the current intermediate address and the address to be searched can be calculated using a cosine similarity algorithm, a TF-IDF algorithm, or a BM25 algorithm.

[0086] The i-th entity can be an entity included in both the address to be searched and the intermediate address. For example, the address to be searched is Bama Tea Industry, a ground floor shop in Fangda Science Park, No. 266, Tianshan Avenue, Changjiang Street, Yuhua District, Shijiazhuang City, Hebei Province. The entities corresponding to the address to be searched include Tianshan Avenue, No. 266, Fangda Science Park, and Bama Tea Industry, a ground floor shop. An intermediate address is Fangda Science Park, No. 266, Tianshan Avenue, Yuhua District, Shijiazhuang City, Hebei Province. The entities corresponding to the intermediate address include Tianshan Avenue, No. 266, and Fangda Science Park. The entities included in both the address to be searched and the intermediate address include Tianshan Avenue, No. 266, and Fangda Science Park.

[0087] In a specific embodiment, if the address to be searched is Bama Tea, a ground floor shop in Fangda Science Park, No. 266, Tianshan Avenue, Changjiang Street, Yuhua District, Shijiazhuang City, Hebei Province, the entities corresponding to the address to be searched include Tianshan Avenue, No. 266, Fangda Science Park, and Bama Tea, a ground floor shop. The corresponding intermediate address is Fangda Science Park, No. 266, Tianshan Avenue, Yuhua District, Shijiazhuang City, Hebei Province. The named entity information corresponding to the intermediate address is Fangda Science Park, No. 266, Tianshan Avenue. The administrative level 4 text corresponding to the intermediate address is Yuhua District, Shijiazhuang City, Hebei Province. The text of the intermediate address after removing the administrative level 3 text includes Fangda Science Park, No. 266, Tianshan Avenue. The text length of the corresponding intermediate address after removing the administrative level 3 text is 13. The entities corresponding to the intermediate address include Tianshan Avenue, No. 266, and Fangda Science Park.

[0088] The above entities and corresponding weights may be specifically set according to specific implementation conditions, and are not limited in this embodiment of the present invention.

[0089] In some embodiments, a road and a road number may be considered as an entity, for example, No. 266 Tianshan Street may be considered as an entity; a town and a village may be considered as an entity.

[0090] If the i-th entity includes roads and road numbers, the corresponding weight can be 3; if the i-th entity only includes roads, the corresponding weight can be 0.5; if the i-th entity includes towns and villages, the corresponding weight can be 1.5; if the i-th entity only includes towns, the corresponding weight can be 1; if the i-th entity only includes villages, the corresponding weight can be 1.5; if the point of interest included in the i-th entity is the first point of interest corresponding to the intermediate address, the corresponding weight can be 1.5; if the point of interest included in the i-th entity is not the first point of interest corresponding to the intermediate address, the corresponding weight can be 0.5; if the i-th entity only includes parks, the corresponding weight can be 1.

[0091] If the i-th entity only includes the road number, the corresponding weight may be -0.6; if the i-th entity only includes the building number, the corresponding weight may be -0.6; if the i-th entity only includes the unit number, the corresponding weight may be -0.6.

[0092] The initial text similarity s between the intermediate address and the address to be searched can be calculated to be 0.803*100, i.e. 80.3. The first entity of the named entity information in the intermediate address is No. 266 Tianshan Street, its text length is 8, and its weight is 3; the second entity is Fangda Science Park, its text length is 5, and its weight is 1. Substitute the above values ​​into the refined sorting algorithm formula , then the text similarity between the intermediate address and the address to be searched is F=[80.3*(8 / 13)*3]+[80.3*(5 / 13))]+80.3≈259.430769.

[0093] An embodiment of the present invention provides an address search method, which parses the administrative level 4 text and detailed address information of the address to be searched, and performs named entity recognition on the administrative level 4 text and the detailed address information to obtain named entity information; the accuracy and efficiency of named entity recognition of the address to be searched can be improved to improve the accuracy and efficiency of subsequent address searches; a number of intermediate addresses are recalled based on the administrative level 4 text, the detailed address information and the named entity information; the administrative level 4 text and the named entity information are involved in the recall to improve the accuracy of the recalled intermediate addresses; the text similarity between each intermediate address and the address to be searched is calculated based on the text length of the named entity information in each intermediate address to determine the final address; by involving the text length of the named entity information in the intermediate address in the calculation of text similarity, the accuracy of the text similarity calculation is improved, and the accuracy of the address search is further improved.

[0094] Example 2

[0095] Based on the above-mentioned address search method, an embodiment of the present invention provides an address search device, whose structural diagram is as follows: Figure 2 As shown, the address search device 20 includes an entity information acquisition module 21, a first address acquisition module 22 and a second address acquisition module 23;

[0096] The entity information acquisition module 21 is used to parse the administrative level 4 text and detailed address information of the address to be searched, and perform named entity recognition on the administrative level 4 text and the detailed address information to obtain named entity information;

[0097] The first address acquisition module 22 is configured to recall a plurality of intermediate addresses based on the administrative level 4 text, the detailed address information, and the named entity information;

[0098] The second address acquisition module 23 is configured to calculate the text similarity between each intermediate address and the address to be searched according to the text length of the named entity information in each intermediate address, and determine the final address.

[0099] For other details about how the modules in the address search device implement the above technical solution, please refer to the description of the address search method provided in the above invention embodiment, which will not be repeated here.

[0100] Example 3

[0101] Based on the above-mentioned address search method, the embodiment of the present invention further provides an address search device, the structural diagram of which is shown in FIG. Figure 3 As shown, the address search device 30 includes a processor 31 and a memory 32 coupled to the processor 31. The memory 32 stores a computer program, which, when executed by the processor 31, enables the processor 31 to perform the steps of the address search method in the above embodiment.

[0102] For other details about how the processor 31 in the address search device implements the above technical solution, please refer to the description of the address search method provided in the above invention embodiment, which will not be repeated here.

[0103] Among them, the processor 31 can also be called a CPU (Central Processing Unit), and the processor 31 may be an integrated circuit chip with signal processing capabilities; the processor 31 can also be a general-purpose processor, DSP (Digital Signal Process), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, among which the general-purpose processor can be a microprocessor or the processor 31 can also be any conventional processor, etc.

[0104] Example 4

[0105] The embodiment of the present invention further provides a computer-readable storage medium, the structure of which is shown in FIG. Figure 4 As shown, the storage medium 40 stores a readable computer program 41; wherein, the computer program 41 can be stored in the above-mentioned storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in various embodiments of the present invention. The aforementioned storage medium includes: a USB flash drive, a mobile hard drive, a magnetic disk or optical disk, ROM (Read-Only Memory), RAM (Random Access Memory), and other media that can store program code, or terminal devices such as computers, servers, mobile phones, and tablets.

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

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

[0108] In addition, the functional modules in the various embodiments of the present application may be integrated into a single processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may be stored in a computer-readable storage medium.

[0109] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0110] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a server, or a data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, a computer, a server, or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium can be a magnetic medium, (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state drive (SSD)).

[0111] The above is a detailed introduction to the technical solution provided by the present application. Specific examples are used in the present application to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0112] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0113] The present application is described with reference to the flowcharts and / or block diagrams of the methods, apparatuses and computer program products according to the present application. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0114] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0116] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. An address search method, characterized in that: include: Parsing the administrative level 4 text and detailed address information of the address to be searched, and performing named entity recognition on the administrative level 4 text and the detailed address information to obtain named entity information; Recalling a number of intermediate addresses based on the administrative level 4 text, the detailed address information, and the named entity information; For each intermediate address, the text similarity between the current intermediate address and the address to be searched is calculated based on the text length of the named entity information in the current intermediate address, the initial text similarity between the current intermediate address and the address to be searched, and the text length of the current intermediate address after removing the administrative level 3 text. The text similarity between the current intermediate address and the address to be searched is calculated based on the refined sorting algorithm formula: Where F is the text similarity between the current intermediate address and the address to be searched, s is the initial text similarity, c i is the text length of the i-th entity in the named entity information in the current intermediate address, o is the text length of the current intermediate address after removing the administrative level 3 text, w i is the weight of the i-th entity in the named entity information in the current intermediate address; The intermediate address with the highest text similarity is taken as the final address.

2. The address search method according to claim 1, wherein: According to the administrative level 4 text, the detailed address information, and the named entity information, several intermediate addresses are retrieved, including: Determine the address search scope according to the administrative level 4 text; Searching for a plurality of initial addresses having the highest similarity to the detailed address information within the address search range; A weighted score is given to each initial address according to the named entity information, and several initial addresses with the highest recall scores are used as intermediate addresses.

3. The address search method according to claim 2, wherein: The address search scope is determined based on the administrative level 4 text, including: Determine the address search source according to the second-level administrative text in the four-level administrative text; The address search source is used as the address search range.

4. The address search method according to claim 2, wherein: After determining the address search scope according to the administrative level 4 text, the following is also included: According to the third level administrative text in the four level administrative text, the address search range is narrowed.

5. The address search method according to claim 1, wherein: Perform named entity recognition on the administrative level 4 text and the detailed address information to obtain named entity information, including: Performing named entity recognition on the fourth-level administrative text to obtain the fourth-level administrative text as the first entity; Performing named entity recognition on the detailed address information according to a preset entity type to obtain a plurality of second entities; The first entity and the second entity are used as named entity information.

6. An address search device, characterized in that: It includes an entity information acquisition module, a first address acquisition module and a second address acquisition module; The entity information acquisition module is used to parse the administrative level 4 text and detailed address information of the address to be searched, and perform named entity recognition on the administrative level 4 text and the detailed address information to obtain named entity information; The first address acquisition module is configured to recall a plurality of intermediate addresses based on the administrative level 4 text, the detailed address information, and the named entity information; The second address acquisition module is used to calculate the text similarity between the current intermediate address and the address to be searched for each intermediate address based on a refined sorting algorithm formula including the text length of the named entity information in the current intermediate address, the initial text similarity between the current intermediate address and the address to be searched, and the text length of the current intermediate address after removing the administrative level 3 text. The refined sorting algorithm formula is: Where F is the text similarity between the current intermediate address and the address to be searched, s is the initial text similarity, c i is the text length of the i-th entity in the named entity information in the current intermediate address, o is the text length of the current intermediate address after removing the administrative level 3 text, w i is the weight of the i-th entity in the named entity information in the current intermediate address; the intermediate address with the highest text similarity is taken as the final address.

7. An address search device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store computer programs; The processor is configured to read the computer program in the memory and execute the steps of any one of the address search methods according to claims 1 to 5.

8. A computer-readable storage medium, characterized in that A readable computer program is stored thereon, and when the program is executed by a processor, the steps of any address search method according to claims 1 to 5 are implemented.

Images