Address coding association method, business data analysis method and corresponding device

Abstract

One or more embodiments of the present specification disclose an address coding association method, a business data analysis method and a corresponding device, the method comprising: by determining the address text information, searching from a preset address library to determine the address code and longitude and latitude corresponding to the address space described by the address text information, and then judging whether there is an information plane code matching the longitude and latitude in the preset information plane code library, each information plane code uniquely marks an information plane in the address space, and if it exists, the information plane code is used as the address unique code of the information plane and associated with the address text information. The address text information located on the same information plane is normalized to achieve address standardization. When there is a relevant statistical demand for the business data related to these normalized address text information, statistical analysis can be directly performed based on the address unique code to improve business processing efficiency.

Description

Technical Field

[0001] This document relates to the field of computer technology, and in particular to an address coding association method, a business data analysis method and corresponding devices. Background Art

[0002] In the real world, an address area can cover multiple different address points. Each address point or address area has address text information that describes its own geographic space. For example, "Chenguang Community" is the address text information of an address area. The Chenguang Community covers multiple communities and even multiple buildings. If each building is taken as an address point, then each address point corresponds to its own address text information, such as: "Chenguang Building 1", "Chenguang Building 2", "Chenguang Building 3" and "Shenghua Building A", "Shenghua Building B".

[0003] It can be seen that each address area or address point has its own address text information, and because the address text information cannot reflect the association between the address spaces, it is impossible to use the address text information to perform statistical analysis on the addresses (address points or address areas) located in the same address area. Summary of the invention

[0004] The purpose of one or more embodiments of the present specification is to provide an address coding association method, a business data analysis method and corresponding devices, so as to associate different address text information representing the same address area through a unique address code, so as to distinguish the same address area from different address areas, and facilitate statistical analysis of business data in business scenarios using address text information.

[0005] To solve the above technical problems, one or more embodiments of this specification are implemented as follows:

[0006] In a first aspect, an address coding association method is proposed, comprising:

[0007] Determine the address text information;

[0008] Searching for an address in a preset address library to determine the address code and longitude and latitude corresponding to the address space described by the address text information;

[0009] Based on the longitude and latitude, determining whether there is an information plane code matching the longitude and latitude in a preset information plane code library, wherein each information plane code uniquely marks an information plane in the address space;

[0010] If it exists, the matching information plane code is used as the unique address code of the information plane and associated with the address text information.

[0011] Secondly, a business data analysis method is proposed, including:

[0012] Determine a business data set to be analyzed, wherein the business data set includes a plurality of target business data carrying address text information, and the address text information carried by each target business data is associated with an address unique code through the method described in the first aspect;

[0013] According to preset business requirements, statistical analysis is performed on the business data in the business data set based on the unique address code associated with the address text information.

[0014] In a third aspect, an address code association device is proposed, comprising:

[0015] A first determination module determines address text information;

[0016] A second determination module searches for an address in a preset address library to determine an address code and longitude and latitude corresponding to the address space described by the address text information;

[0017] A judgment module, based on the longitude and latitude, judges whether there is an information plane code matching the longitude and latitude in a preset information plane code library, wherein each information plane code uniquely marks an information plane in the address space;

[0018] The association module associates the matched information surface code with the address text information as the unique address code of the information surface when the judgment module judges that there is an information surface code matching the longitude and latitude in the preset information surface code library.

[0019] In a fourth aspect, a business data analysis device is proposed, comprising:

[0020] A determination module determines a business data set to be analyzed, wherein the business data set includes a plurality of target business data carrying address text information, and the address text information carried by each target business data is associated with an address unique code through the method described in the first aspect;

[0021] The analysis module performs statistical analysis on the business data in the business data set based on the unique address code associated with the address text information according to preset business requirements.

[0022] In a fifth aspect, an electronic device is provided, comprising:

[0023] Processor; and

[0024] A memory arranged to store computer executable instructions, which, when executed, cause the processor to execute: the address coding association method described in the first aspect, and / or the business data analysis method described in the second aspect.

[0025] In the sixth aspect, a computer-readable storage medium is proposed, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes: the address coding association method described in the first aspect, and / or the business data analysis method described in the second aspect.

[0026] It can be seen from the technical solutions provided by one or more embodiments of the present specification that, through the input address text information, the address code and longitude and latitude corresponding to the address space expressed by the address text information are searched from the preset address library, and then it is determined whether there is an information surface code matching the longitude and latitude in the preset information surface code library. Each information surface code uniquely marks an information surface in the address space. If it exists, the information surface code is used as the address unique code of the information surface and associated with the address text information. In this way, the address text information located on the same information surface is normalized through the information surface code, and an association relationship is established for these address spaces located on the same information surface but expressed using different address text information, thereby achieving address standardization. When there is a relevant statistical demand for the business data related to these normalized address text information, statistical analysis can be directly performed based on the address unique code to improve business processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the description of one or more embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0028] Figure 1 This is one of the step diagrams of an address coding association method provided in an embodiment of this specification.

[0029] Figure 2 It is a schematic diagram of image blocks of different land types obtained by image segmentation.

[0030] Figure 3 It is a schematic diagram of multiple information surfaces obtained by performing image mining provided in an embodiment of this specification.

[0031] Figure 4 This is the second step diagram of an address coding association method provided in an embodiment of this specification.

[0032] Figure 5 It is a schematic diagram of the steps of a business data analysis method provided in an embodiment of this specification.

[0033] Figure 6It is a structural diagram of an address coding association device provided by an embodiment of this specification.

[0034] Figure 7 It is a structural diagram of a business data analysis device provided by an embodiment of this specification.

[0035] Figure 8 This is one of the structural schematic diagrams of an electronic device provided by an embodiment of this specification.

[0036] Fig. 9 This is the second structural diagram of an electronic device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the one or more embodiments described are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0038] Address Purification is a high-performance and high-accuracy standard address algorithm service based on a massive address corpus and powerful natural language processing (NLP) algorithm. In many business scenarios, addresses are filled in by users, and there are inevitably omissions and errors in the addresses. The address standardization service interface can be used to complete and correct the original address text information; it can also provide services such as address data cleaning for enterprises, government agencies and developers, so that address data can better support the business.

[0039] At present, with the prevalence of big data, various application scenarios such as Internet finance, e-commerce, logistics, insurance, tourism, leasing, O2O, etc. may involve address data. For example, the delivery address in the e-commerce order, the visiting address involved in the travel itinerary, the household registration address involved in the insurance order, etc., these addresses can be represented by the address text information corresponding to the actual geographic space.

[0040] In the real world, an address space may be expressed by a variety of different address text information. For example, the address text information corresponding to the address space where University A is located is "University A"; Building B is a teaching building for industry, academia and research in University A, and its corresponding address text information is "Building B"; Hotel C is an internal reception hotel located in University A, and its corresponding address text information is "Hotel C". On the map, these three address spaces overlap. When these three address text information are used to perform related businesses, such as online shopping, different address text information will be displayed in the order data. For various current business scenarios, statistical analysis of business data to improve business efficiency is a necessary technical means. For example, analyzing and counting the distribution address, counting the orders in the same address range together for distribution, and analyzing and counting the order addresses to predict the sales of goods in different address ranges or regions. However, based on the above examples, it can be determined that the existing address text information does not reflect whether the address spaces are associated. Therefore, it is impossible to use address text information to perform statistical analysis on addresses (address points or address areas) located in the same address area.

[0041] In order to solve the above technical problems, the embodiment of this specification proposes an address coding association scheme. The main idea is: through the input address text information, the address code and longitude and latitude corresponding to the address space expressed by the address text information are searched from the preset address library, and then it is determined whether there is an information surface code matching the longitude and latitude in the preset information surface code library. Each information surface code uniquely marks an information surface in the address space. If it exists, the information surface code is used as the address unique code of the information surface and associated with the address text information. In this way, the address text information located on the same information surface is normalized through the information surface code, and an association relationship is established for these address spaces located on the same information surface but expressed using different address text information. When there is a relevant statistical demand for the business data related to these normalized address text information, statistical analysis can be directly performed based on the address unique code, for example, calling business data with the same address unique code, and for example, classifying business data with different address unique codes.

[0042] The following is a brief explanation of the relevant terms that may be involved in the embodiments of this specification.

[0043] Address code is a unique identifier assigned to a specific geographic element or geographic location. In this specification, the address unique code is defined as a mark to determine the same address space. If the address spaces with inconsistent address text descriptions have the same address unique code, then these address spaces represent the same location.

[0044] Multimodality means that each source or form of information can be called a modality, and the address code association scheme in this specification can determine the unique address code through multimodality.

[0045] Streaming processing, that is, the input is a single address text information instead of multiple address text information. It is suitable for scenarios with large data volumes or scenarios where new addresses are added every day, and the processing speed is relatively fast.

[0046] Address normalization is to classify addresses of the same location into the same cluster even though the address text descriptions in a given set of addresses may be different.

[0047] Point of Interest (POI), each POI contains at least four basic information: name, address, category, and coordinates, corresponding to a point on the map, which can be a house, a shop, a community gate or a bus stop, etc.

[0048] Area of ​​Interest (AOI), also known as interest surface, refers to the regional geographical entity building complex in the map data, corresponding to a surface on the map, such as a community, school, shopping mall, office building, industrial park, hospital, scenic spot or stadium.

[0049] In the real world, an address point can correspond to an address code; an address area can correspond to an address code, but at the same time, multiple address points located in the address area can also correspond to their own address codes respectively.

[0050] Embodiment 1

[0051] Reference Figure 1 As shown, it is a schematic diagram of the steps of an address coding association method provided in an embodiment of this specification. It should be understood that the executor of the method can be a hardware device with certain computing and processing capabilities (for example, a smart phone, a personal computer, a wearable device, a tablet computer, etc.) or a software device (for example, a client or a combination of software modules integrated in the aforementioned types of hardware devices), specifically, it can be various types of servers related to address standardization services, for example, a cloud server.

[0052] The address code association method may include the following steps:

[0053] Step 102: Determine address text information.

[0054] In the embodiment of the present specification, the address text information may be text content used to describe and represent the address space, for example, "Building 1, XX Community".

[0055] The address text information generally comes from the user's input on the terminal, and can be collected or sorted from the World Wide Web through legal data collection methods, such as crawling relevant address text information through a web crawler. The address text information can appear alone or be carried in various types of business data. If it appears alone, the address text information can be directly obtained. If it appears alone, the address text information can be extracted from the business data.

[0056] In another achievable manner, the execution subject of the address coding association method may only collect address text information related to specific service data in the local area network to obtain address text information in the local area service environment.

[0057] Therefore, in the embodiment of the present specification, before executing step 102, target service data carrying address text information may be obtained, and the address text information may be extracted from the target service data.

[0058] It should be understood that this specification does not limit the method for determining the address text information. Generally, a single entry or multiple entries can be selected according to the needs of the business scenario. When the address text information involves business scenarios with a large amount of data such as e-commerce and logistics, streaming processing can be preferably used, that is, the input is a single address text information, and the processing speed is relatively fast.

[0059] Step 104: perform an address search from a preset address library to determine the address code and longitude and latitude corresponding to the address space expressed by the address text information.

[0060] The preset address library may be pre-generated, may be generated by default in accordance with the existing address library generation method, or may exist in accordance with the existing library structure. The preset address library may be obtained based on satellite map data mapping, and the preset address library contains the point of interest (POI) information of each address space covered by the satellite map, and each POI information contains at least four basic data: name, address, category, latitude and longitude coordinates, etc.

[0061] Optionally, in step 104, when performing an address search from a preset address library and determining the address code and longitude and latitude corresponding to the address space expressed by the address text information, at least one candidate address can be searched from the preset address library based on the address keyword carried by the address text information; the at least one candidate address is sorted by a preset address sorting model, and the candidate address with the best sorting result is selected as the address space matching the address text information, and the address code and longitude and latitude are obtained based on the information point information of the address space matching the address text information. The preset address sorting model can be an existing address sorting model, such as an LR algorithm, a FTRL algorithm, an FM algorithm, etc.

[0062] Step 106: Based on the longitude and latitude, determine whether there is an information plane code matching the longitude and latitude in a preset information plane code library, wherein each information plane code uniquely marks an information plane in the address space.

[0063] In the embodiments of this specification, the preset information plane coding library can be determined in the following manner:

[0064] The first step is to determine image information to be processed, wherein the image information at least includes image data collected based on the address space.

[0065] The image information to be processed may be image data collected by a satellite system, such as a satellite map; or image data collected by other surveying and mapping collection systems, such as an electronic image. It should be understood that the image information at least includes the address space expressed by the address text information determined in step 102. In other words, if the address text information determined in step 102 is "Hangzhou University", then the image information at least includes the address space corresponding to Hangzhou University, for example, the image information may be an electronic map of Hangzhou. Preferably, when information collection allows, the image information may be a national map or a world map.

[0066] The second step is to perform image segmentation and mining on the image corresponding to the image information to obtain multiple information planes.

[0067] In specific implementation, a preset image segmentation algorithm may be used to segment the image corresponding to the image information into different image blocks, and mark the plot type of each image block; based on the segmentation results and the marking results, multiple information surfaces are mined from the image. Among them, the preset image segmentation algorithm may include a threshold segmentation algorithm, a region segmentation algorithm, an edge segmentation algorithm, a histogram segmentation algorithm, and the like. Plot types can be divided into: grasslands, roads, buildings, cultivated land, structures, woodlands, bare land, artificial excavation land, and water areas according to different land use types. When specifically marking, the identifier assigned to each type of plot can be used to mark. The identifier can be a different color or a different grayscale, or it can be represented by different numbers, symbols, or serial numbers to facilitate the distinction of plot types in the address space. When multiple information surfaces are mined from the image based on the segmentation results and the marking results, the image blocks with the same and adjacent plot types can be merged to mine the appropriate information surface. Among them, Figure 2 As shown, image blocks of different land types are obtained by image segmentation. Figure 3 , which is a schematic diagram of multiple information surfaces obtained by image mining.

[0068] The third step is to assign a code to each information surface obtained by mining, and determine the information surface code of each information surface based on the assigned code to establish an information surface code library.

[0069] In specific implementation, the information surfaces obtained by mining may be sorted according to the blocks, and a sequence code may be assigned to each information surface; and an information surface code may be determined for each information surface based on the assigned sequence code.

[0070] Further, when determining the information plane code for each information plane based on the assigned sequence code, the sequence code assigned to each information plane can be determined as the information plane code of the information plane; or, the sequence code assigned to each information plane is combined with the regional mark of the information plane at different regional levels to determine the information plane code of the information plane. For example, "1-N" sequence codes are directly assigned to multiple information planes in row and column order: the first information plane in the first row is assigned an information plane code of "1", the second information plane in the first row is assigned an information plane code of "2"... the last information plane in the last row is assigned an information plane code of "N". For another example, a regional mark is added on the basis of the sequence code. Assuming that in Hangzhou-Gongshu District, the Hangzhou regional mark is defined as H (city-level mark capital letter), and the Gongshu District regional mark is defined as h (district-level mark lowercase letter): the first information plane in the first row is assigned an information plane code of "Hh-1" the second information plane in the first row is assigned an information plane code of "Hh-2"... the last information plane in the last row is assigned an information plane code of "HhN".

[0071] In fact, when assigning codes to information planes, it is also possible not to assign them in order, but in order to facilitate traversal during query, it is preferred to assign them in order. The order code can be a number arranged in ascending or descending order, or a number arranged in ascending or descending order of letters, and the embodiments of this specification are not limited to this.

[0072] Each information surface in the preset information surface coding library may include AOI information, and what is established in the preset information surface coding library may be a correspondence between the AOI information and the corresponding information surface coding.

[0073] When step 106 queries whether there is an information surface code matching the longitude and latitude from the preset information surface code library based on the determined longitude and latitude, it is possible to first query whether there is corresponding AOI information for the longitude and latitude in the preset information surface code library, and then use the information surface code corresponding to the AOI information as the query result.

[0074] Step 108: If it exists, the matching information plane code is used as the unique address code of the information plane and associated with the address text information.

[0075] If there is an information surface code matching the longitude and latitude in the preset information surface code library, the found information surface code is used as the address unique code of the information surface and is associated with the address text information in step 102. For example, the address text information is marked with the address unique code in the POI information of the address library, or the address unique code is added to the business data related to the address text information for marking.

[0076] Reference Figure 4 As shown, if there is no information plane code matching the latitude and longitude in the preset information plane code library, the solution will execute:

[0077] Step 110: Use the address code as the unique address code of the address space corresponding to the address text information.

[0078] The reason why step 110 occurs is that although the range of image information based on which the preset information surface coding library is generated can be large enough to cover more address space as comprehensively as possible to ensure the comprehensiveness and integrity of the map data. However, when performing image segmentation to mine AOI, Figure 3 As shown, not all address spaces can be mined into an AOI. Therefore, some address space points, such as relatively isolated bus stops, shops and other address space points, are very likely not in the preset information surface coding library. Since these address space points are relatively isolated, there is generally no situation where multiple address text information is used to express them. Therefore, for such situations, if there is no information surface coding matching the longitude and latitude in the preset information surface coding library, then the address coding determined in step 104 can be directly used as the address unique coding of the address space corresponding to the address text information. This means that the address unique coding is marked in the business data related to the address text information or the address text information is marked with the address unique coding in the POI information of the address library.

[0079] Therefore, the address text information located on the same information plane is normalized through information plane coding, and an association relationship is established for these address spaces located on the same information plane but expressed using different address text information; and the address space points that do not have multiple ways of expressing address text information use their own address coding as the unique address coding. When there is a relevant statistical demand for the business data related to these normalized address text information, statistical analysis can be performed directly based on the unique address coding.

[0080] In fact, refer to Figure 4As shown in the flowchart, the address code association scheme actually determines the unique address code through a multimodal method (address code and information plane code), and establishes an association with the address text information to achieve normalization of the address text information. It mainly associates the address text information with the information plane code. When there is no matching information plane code in the preset information plane code library, the address code will be selected as the unique address code for association.

[0081] Embodiment 2

[0082] Reference Figure 5 As shown, it is a schematic diagram of the steps of a business data analysis method provided in an embodiment of this specification. It should be understood that the executor of the method can be a hardware device with certain computing and processing capabilities (for example, a smart phone, a personal computer, a wearable device, a tablet computer, etc.) or a software device (for example, a client or a combination of software modules integrated in the aforementioned types of hardware devices), specifically, it can be various types of servers related to address standardization services, for example, a cloud server.

[0083] The business data analysis method may include the following steps:

[0084] Step 502: Determine a business data set to be analyzed, wherein the business data set includes a plurality of target business data carrying address text information, and the address text information carried by each target business data is associated with an address unique code through the method of steps 102 to 110.

[0085] In this step, the business data set involved may be a business data set involved in various business scenarios listed in Example 1. The address text information carried by each target business data in the business data set may be specifically associated with an address unique code by referring to any of the association methods mentioned in Example 1. Whether the information surface code is used as the address unique code association, or the address code of the address text information is used as the address unique code association. The specific association method and the technical effect achieved may refer to the relevant description in Example 1, which will not be repeated here.

[0086] Step 504: According to preset business requirements, statistical analysis is performed on the business data in the business data set based on the unique address code associated with the address text information.

[0087] Based on the unique address code associated with the address text information, different levels of regional tags and / or sequential codes are called to perform statistical analysis on the business data in the business data set. For example, when the business field covered by the business data set is logistics, the unique address code associated with the address text information can be used to count the orders in the same address range for distribution based on the distribution needs, thereby improving the distribution efficiency. For another example, when the business field covered by the business data set is e-commerce, the unique address code associated with the address text information can be used to analyze and count the order addresses based on the sales needs, and predict the sales volume of goods in different address ranges or regions.

[0088] In fact, all address-related business data can be statistically analyzed using the above solution to improve business processing efficiency and cope with the ever-increasing business needs.

[0089] Embodiment 3

[0090] Reference Figure 6 As shown, the address code association device provided in the embodiment of this specification may include:

[0091] A first determination module 602 determines address text information;

[0092] The second determination module 604 performs an address search from a preset address library to determine the address code and longitude and latitude corresponding to the address space expressed by the address text information;

[0093] A determination module 606 determines, based on the longitude and latitude, whether there is an information plane code matching the longitude and latitude in a preset information plane code library, wherein each information plane code uniquely marks an information plane in the address space;

[0094] The association module 608, when the judgment module determines that there is an information surface code matching the longitude and latitude in the preset information surface code library, associates the matching information surface code as the unique address code of the information surface with the address text information.

[0095] Optionally, as an embodiment, the preset information plane coding library may be determined by the coding library generation module in the following manner:

[0096] Determine image information to be processed, wherein the image information at least includes image data collected based on the address space; perform image segmentation and mining on the image corresponding to the image information to obtain multiple information planes; assign a code to each information plane obtained by mining, and determine the information plane code of each information plane based on the assigned code to establish an information plane code library.

[0097] In a specific implementation of the embodiment of this specification, when the coding library generation module performs image segmentation and mining on the image corresponding to the image information to obtain multiple information planes, it is specifically used to:

[0098] A preset image segmentation algorithm is used to segment the image corresponding to the image information into different image blocks, and the land type of each image block is marked; based on the segmentation result and the marking result, multiple information surfaces are mined from the image.

[0099] In another specific implementation of the embodiment of the present specification, the coding library generation module assigns a code to each information plane obtained by mining, and when determining the information plane code of each information plane based on the assigned code, it is specifically used to:

[0100] According to the order of the plots of the information surfaces obtained by mining, a sequence code is assigned to each information surface; and an information surface code is determined for each information surface based on the assigned sequence code.

[0101] In another specific implementation of the embodiment of the present specification, when the code library generation module determines the information plane code for each information plane based on the assigned sequence code, it is specifically used to:

[0102] The sequential code assigned to each information plane is determined as the information plane code of the information plane; or, the sequential code assigned to each information plane is combined with the regional mark of the information plane at different regional levels to be determined as the information plane code of the information plane.

[0103] In another specific implementation of the embodiment of this specification, the device also includes: an acquisition module, which is used to acquire target business data carrying address text information before determining the address text information; and extract the address text information from the target business data.

[0104] In another specific implementation of the embodiment of this specification, if there is no information plane code matching the longitude and latitude in the preset information plane code library, the association module 608 is further used to use the address code as the unique address code of the address space corresponding to the address text information.

[0105] In another specific implementation of the embodiment of the present specification, when the second determination module 604 searches for an address in a preset address library to determine the address code and longitude and latitude corresponding to the address space expressed by the address text information, it is specifically used to:

[0106] Based on the address keywords carried in the address text information, at least one candidate address is searched from a preset address library; the at least one candidate address is sorted by a preset address sorting model, and the candidate address with the best sorting result is selected as the address space matching the address text information, and the address code and longitude and latitude are obtained from the information point information of the address space matching the address text information.

[0107] It should be understood that the above-mentioned device 600 may also execute Figure 1 and Figure 4 The method and the corresponding device are implemented in Figure 1 and Figure 4 The functions of the illustrated embodiments will not be described in detail in the embodiments of this specification.

[0108] Embodiment 4

[0109] Reference Figure 7 As shown, a business data analysis device provided in an embodiment of this specification is provided, and the device 700 may include:

[0110] Determining module 702, determining a business data set to be analyzed, wherein the business data set includes a plurality of target business data carrying address text information, and the address text information carried by each target business data is associated with an address unique code through the method described in steps 102 to 110;

[0111] The analysis module 704 performs statistical analysis on the business data in the business data set based on the unique address code associated with the address text information according to preset business requirements.

[0112] Optionally, when the analysis module 704 performs statistical analysis on the business data in the business data set based on the address unique code associated with the address text information, it can call different levels of geographical tags and / or sequential codes based on the address unique code associated with the address text information to perform statistical analysis on the business data in the business data set.

[0113] It should be understood that the above-mentioned device 700 can also execute Figure 1 and Figure 4 , Figure 5 The method and the corresponding device are implemented in Figure 1 and Figure 4 , Figure 5 The functions of the illustrated embodiments will not be described in detail in the embodiments of this specification.

[0114] Embodiment 5

[0115] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of this specification. Figure 8At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0116] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0117] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0118] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an address code association device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0119] Determine the address text information; perform an address search from a preset address library to determine the address code and longitude and latitude corresponding to the address space described by the address text information; based on the longitude and latitude, determine whether there is an information plane code matching the longitude and latitude in a preset information plane code library, wherein each information plane code uniquely marks an information plane in the address space; if so, associate the matching information plane code with the address text information as the unique address code of the information plane.

[0120] The above is as in this manual Figure 1 and Figure 4The method performed by the device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in one or more embodiments of this specification can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in one or more embodiments of this specification can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0121] The electronic device may also perform Figure 1 and Figure 4 The method and the corresponding device are implemented in Figure 1 and Figure 4 The functions of the illustrated embodiments will not be described in detail in the embodiments of this specification.

[0122] Fig. 9 This is a schematic diagram of the structure of an electronic device according to an embodiment of this specification. Fig. 9 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0123] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0124] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0125] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a business data analysis device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0126] Determine a business data set to be analyzed, wherein the business data set includes multiple target business data carrying address text information, and the address text information carried by each target business data is associated with an address unique code through the method described in Example 1; according to preset business requirements, perform statistical analysis on the business data in the business data set based on the address unique code associated with the address text information.

[0127] The above is as in this manual Figure 1 and Figure 4 , Figure 5The method performed by the device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in one or more embodiments of this specification can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in one or more embodiments of this specification can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0128] The electronic device may also perform Figure 1 and Figure 4 , Figure 5 The method and the corresponding device are implemented in Figure 1 and Figure 4 , Figure 5 The functions of the illustrated embodiments will not be described in detail in the embodiments of this specification.

[0129] Of course, in addition to software implementation, the electronic device of the embodiments of this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0130] The embodiment of the present specification also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by a portable electronic device including a plurality of application programs, enable the portable electronic device to execute Figure 1 and Figure 4 , Figure 5 The method of the embodiment shown is specifically used to perform the following method:

[0131] Determine the address text information; perform an address search from a preset address library to determine the address code and longitude and latitude corresponding to the address space described by the address text information; based on the longitude and latitude, determine whether there is an information plane code matching the longitude and latitude in a preset information plane code library, wherein each information plane code uniquely marks an information plane in the address space; if so, associate the matching information plane code with the address text information as the unique address code of the information plane.

[0132] or;

[0133] Determine a business data set to be analyzed, wherein the business data set includes multiple target business data carrying address text information, and the address text information carried by each target business data is associated with an address unique code through the method described in Example 1; according to preset business requirements, perform statistical analysis on the business data in the business data set based on the address unique code associated with the address text information.

[0134] In short, the above description is only a preferred embodiment of this specification and is not intended to limit the protection scope of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included in the protection scope of this specification.

[0135] The systems, devices, modules or units described in one or more of the above embodiments may be implemented by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0136] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0137] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0138] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0139] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An address coding association method, comprising: Determine the address text information; Searching for an address in a preset address library to determine the address code and longitude and latitude corresponding to the address space described by the address text information; Based on the longitude and latitude, determining whether there is an information plane code matching the longitude and latitude in a preset information plane code library, wherein each information plane code uniquely marks an information plane in the address space, and the preset information plane code library is established based on multiple information planes and the information plane code of each information plane; If it exists, the matching information plane code is used as the unique address code of the information plane and associated with the address text information.

2. The address coding association method according to claim 1, wherein the preset information plane coding library is determined by: Determine the image information to be processed, wherein: The image information at least includes image data collected based on the address space; Performing image segmentation and mining on the image corresponding to the image information to obtain multiple information planes; A code is assigned to each information surface obtained by mining, and the information surface code of each information surface is determined based on the assigned code to establish an information surface code library.

3. The address code association method according to claim 2, wherein the image corresponding to the image information is segmented and mined to obtain a plurality of information planes, including: Using a preset image segmentation algorithm, the image corresponding to the image information is segmented into different image blocks, and the land type of each image block is marked; Based on the segmentation results and the labeling results, multiple information surfaces are mined from the image.

4. The address code association method according to claim 2 or 3, assigning a code to each information plane obtained by mining, and determining the information plane code of each information plane based on the assigned code, comprising: According to the order of the plots of the information surfaces obtained by mining, a sequential code is assigned to each information surface; An information plane code is determined for each information plane based on the assigned sequence code.

5. The address code association method according to claim 4, determining the information plane code for each information plane based on the assigned sequence code, comprising: Determining the sequence code assigned to each information plane as the information plane code of the information plane; or, The sequential code assigned to each information plane is combined with the regional mark of the information plane at different regional levels to determine the information plane code of the information plane.

6. The address coding association method according to any one of claims 1 to 3, before determining the address text information, the method further comprises: Obtain target business data carrying address text information; The address text information is extracted from the target service data.

7. The address coding association method according to any one of claims 1 to 3, wherein if there is no information surface code matching the longitude and latitude in the preset information surface code library, the address code is used as the unique address code of the address space corresponding to the address text information.

8. The address code association method according to any one of claims 1 to 3, performing an address search from a preset address library to determine the address code and longitude and latitude corresponding to the address space expressed by the address text information, comprising: Based on the address keyword carried in the address text information, searching for at least one candidate address from a preset address library; The at least one candidate address is sorted by a preset address sorting model, and the candidate address with the best sorting result is selected as the address space matching the address text information, and the address code and longitude and latitude are obtained based on the information point information of the address space matching the address text information.

9. A business data analysis method, comprising: Determine a business data set to be analyzed, wherein the business data set includes a plurality of target business data carrying address text information, and the address text information carried by each target business data is associated with an address unique code through the method described in any one of claims 1 to 8; According to preset business requirements, statistical analysis is performed on the business data in the business data set based on the unique address code associated with the address text information.

10. The business data analysis method according to claim 9, performing statistical analysis on the business data in the business data set based on the unique address code associated with the address text information, comprising: Based on the unique address code associated with the address text information, different levels of regional marks and / or sequential codes are called to perform statistical analysis on the business data in the business data set.

11. An address code association device, comprising: A first determination module determines address text information; A second determination module searches for an address in a preset address library to determine an address code and longitude and latitude corresponding to the address space described by the address text information; A judgment module, based on the longitude and latitude, judges whether there is an information plane code matching the longitude and latitude in a preset information plane code library, wherein each information plane code uniquely marks an information plane in the address space; the preset information plane code library is established based on multiple information planes and the information plane code of each information plane; The association module associates the matched information surface code with the address text information as the unique address code of the information surface when the judgment module judges that there is an information surface code matching the longitude and latitude in the preset information surface code library.

12. A business data analysis device, comprising: A determination module determines a business data set to be analyzed, wherein the business data set includes a plurality of target business data carrying address text information, and the address text information carried by each target business data is associated with an address unique code through the method described in any one of claims 1 to 8; The analysis module performs statistical analysis on the business data in the business data set based on the unique address code associated with the address text information according to preset business requirements.

13. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which, when executed, cause the processor to execute the address coding association method described in any one of claims 1-8, and / or the business data analysis method described in any one of claims 9 and 10.

14. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device comprising multiple application programs, enables the electronic device to execute the address coding association method described in any one of claims 1-8, and / or the business data analysis method described in any one of claims 9 and 10.

Images