Address text processing method and apparatus

Abstract

The application discloses an address text processing method and device, and relates to the technical field of artificial intelligence. A specific implementation manner of the method comprises the following steps: performing word segmentation on a plurality of address texts matched to coordinate points in advance to obtain address components in the address texts; a mapping relationship between any address component and at least one coordinate point matched to the address component by at least one address text to which the address component belongs is established, and a spatial distribution feature of the address component is determined according to at least one coordinate point in the mapping relationship; and a target coordinate point corresponding to a to-be-processed address text is determined according to spatial distribution features of address components in the to-be-processed address text. The implementation manner can improve address coding accuracy and efficiency by extracting spatial distribution features of address components in address texts.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method and apparatus for processing address text. Background Technology

[0002] In current geocoding processes for address text, machine learning models or rule-based matching are generally used to calculate the geographic entities that match the address text. The coordinates of these pre-determined geographic entities are then used as the encoding result. In this process, the data features used are mainly the statistical features of the address text itself and word vector features; however, there is room for improvement in both accuracy and efficiency. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide an address text processing method and apparatus that can improve the accuracy and efficiency of address encoding by extracting the spatial distribution features of address components in address text.

[0004] To achieve the above objectives, according to one aspect of the present invention, an address text processing method is provided.

[0005] The address text processing method of this invention includes: segmenting multiple address texts that have been pre-matched with coordinate points to obtain address components in the address texts; establishing a mapping relationship between any address component and the coordinate points of at least one address text to which the address component belongs; determining the spatial distribution characteristics of the address component based on at least one coordinate point in the mapping relationship; and determining the target coordinate points corresponding to the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed.

[0006] Optionally, the spatial distribution feature includes: a spatial distribution center point; and the step of determining the spatial distribution feature of the address component based on at least one coordinate point in the mapping relationship includes: determining the center point indicated by each coordinate point in the mapping relationship as the spatial distribution center point of the corresponding address component.

[0007] Optionally, the spatial distribution feature further includes: spatial distribution area; and the step of determining the spatial distribution feature of the address component based on at least one coordinate point in the mapping relationship includes: determining a two-dimensional graphic containing a preset shape of the coordinate point based on the coordinate point in the mapping relationship; wherein the boundary of the two-dimensional graphic passes through part or all of the coordinate point; and determining the area of ​​the two-dimensional graphic as the spatial distribution area of ​​the corresponding address component.

[0008] Optionally, determining the target coordinate point corresponding to the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed includes: determining the comprehensive feature vector of the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed; and inputting the comprehensive feature vector of the address text to be processed into a pre-trained address matching model to obtain the target coordinate point.

[0009] Optionally, determining the comprehensive feature vector of the address text to be processed based on the spatial distribution features of each address component in the address text to be processed includes: obtaining the word embedding vector of the address text to be processed and the position embedding vector representing the location of each address component in the address text to be processed; determining the spatial distribution feature vector of the address text to be processed using the spatial distribution features of each address component in the address text to be processed; and concatenating the word embedding vector, the position embedding vector, and the spatial distribution feature vector into the comprehensive feature vector of the address text to be processed.

[0010] Optionally, determining the target coordinate point corresponding to the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed includes: determining the geographical area covered by any address component in the address text to be processed based on the spatial distribution center point and spatial distribution area of ​​the address component; determining the intersection of the geographical areas covered by each address component in the address text to be processed as the target geographical area of ​​the address text to be processed; matching the address text to be processed with geographical entities in the target geographical area, and determining the coordinate point corresponding to the successfully matched geographical entity as the target coordinate point.

[0011] Optionally, the spatial distribution features further include at least one of the following: the number of coordinate points, the coordinates of at least one cluster center formed by clustering the coordinate points, and the number of cluster categories formed by clustering the coordinate points.

[0012] To achieve the above objectives, according to another aspect of the present invention, an address text processing apparatus is provided.

[0013] The address text processing device of this invention may include: a word segmentation unit, a mapping unit, and a calculation unit.

[0014] The word segmentation unit is used to segment multiple address texts that have been pre-matched with coordinate points to obtain address components in the address texts; the mapping unit is used to establish a mapping relationship between any address component and the coordinate points that match at least one address text to which the address component belongs, and to determine the spatial distribution characteristics of the address component based on at least one coordinate point in the mapping relationship; the calculation unit is used to determine the target coordinate points corresponding to the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed.

[0015] Optionally, the spatial distribution feature includes: a spatial distribution center point; and the mapping unit can be further used to: determine the center point indicated by each coordinate point in the mapping relationship as the spatial distribution center point of the corresponding address component.

[0016] Optionally, the spatial distribution feature further includes: spatial distribution area; and the mapping unit can be further used to: determine a two-dimensional graphic containing a preset shape of a coordinate point according to the coordinate point in the mapping relationship; wherein the boundary of the two-dimensional graphic passes through part or all of the coordinate point; and determine the area of ​​the two-dimensional graphic as the spatial distribution area of ​​the corresponding address component.

[0017] Optionally, the computing unit may be further used to: determine the comprehensive feature vector of the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed; input the comprehensive feature vector of the address text to be processed into a pre-trained address matching model to obtain the target coordinate point.

[0018] Optionally, the computing unit may be further configured to: obtain the word embedding vector of the address text to be processed and the position embedding vector representing the location of each address component in the address text to be processed; determine the spatial distribution feature vector of the address text to be processed using the spatial distribution features of each address component in the address text to be processed; and concatenate the word embedding vector, the position embedding vector and the spatial distribution feature vector into a comprehensive feature vector of the address text to be processed.

[0019] Optionally, the calculation unit may be further configured to: determine the geographical area covered by any address component in the address text to be processed based on the spatial distribution center point and spatial distribution area of ​​any address component; determine the intersection of the geographical areas covered by each address component in the address text to be processed as the target geographical area of ​​the address text to be processed; match the address text to be processed with geographical entities in the target geographical area, and determine the coordinate points corresponding to the successfully matched geographical entities as the target coordinate points.

[0020] Optionally, the spatial distribution features further include at least one of the following: the number of coordinate points, the coordinates of at least one cluster center formed by clustering the coordinate points, and the number of cluster categories formed by clustering the coordinate points.

[0021] To achieve the above objectives, according to another aspect of the present invention, an electronic device is provided.

[0022] An electronic device according to the present invention includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the address text processing method provided by the present invention.

[0023] To achieve the above objectives, according to another aspect of the present invention, a computer-readable storage medium is provided.

[0024] The present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the address text processing method provided by the present invention.

[0025] To achieve the above objectives, according to another aspect of the present invention, a computer program product is provided.

[0026] One computer program product of the present invention includes a computer program that, when executed by a processor, implements the address text processing method provided by the present invention.

[0027] According to the technical solution of the present invention, the embodiments described above have the following advantages or beneficial effects: Multiple address texts with matched coordinate points are pre-segmented to obtain address components. Then, a mapping relationship is established between any address component and the coordinate points of at least one matching address text. Based on at least one coordinate point in the mapping relationship, the spatial distribution characteristics of the address component are determined. These spatial distribution characteristics characterize the distribution center, distribution area, number of coordinate points, and other distribution patterns and features of the corresponding address component in real geographic space. When performing geocoding on the address text to be processed, the corresponding target coordinate points can be calculated using artificial intelligence models or rule matching based on the spatial distribution characteristics of its address components. Because the spatial distribution characteristics of each address component are added during the calculation process, the artificial intelligence model can understand the spatial distribution characteristics of each address component and the weight differences in recall and ranking, or a more precise filtering range (i.e., target geographic area) can be pre-defined during rule matching, thereby improving the accuracy and efficiency of geocoding.

[0028] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0029] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a schematic diagram of the main steps of the address text processing method in an embodiment of the present invention; Figure 2This is a schematic diagram illustrating the specific execution steps of the address text processing method in this embodiment of the invention; Figure 3 This is a schematic diagram of the components of the address text processing device in an embodiment of the present invention; Figure 4 This is an exemplary system architecture diagram that can be applied thereto according to embodiments of the present invention; Figure 5 This is a schematic diagram of the electronic device structure used to implement the address text processing method in the embodiments of the present invention. Detailed Implementation

[0030] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0031] It should be noted that, unless otherwise specified, the embodiments of the present invention and the technical features thereof can be combined with each other.

[0032] Figure 1 This is a schematic diagram of the main steps of the address text processing method in an embodiment of the present invention.

[0033] like Figure 1 As shown, the address text processing method of this invention can be executed by a server, and the specific execution steps are as follows: Step S101: Segment the multiple address texts that have been pre-matched with coordinate points to obtain address components in the address texts. In this step, the server performs word segmentation on the address texts with pre-obtained corresponding coordinate points to obtain at least one address component in the address texts. The address component mentioned above refers to the word segmentation result of the address text.

[0034] Step S102: Establish a mapping relationship between any address component and the coordinate points that match at least one address text to which the address component belongs. Determine the spatial distribution characteristics of the address component based on at least one coordinate point in the mapping relationship. In this step, the server aggregates at the address component level to obtain the coordinate points corresponding to the same address component in each address text, thereby obtaining the spatial distribution characteristics of the address component. The spatial distribution characteristics are used to represent the distribution characteristics of the address component in real geographic space, such as concentration, dispersion, coverage area, and number of coordinate points (the above concentration, dispersion, coverage area, and number of coordinate points are only examples and do not constitute any limitations). Adding spatial distribution characteristics to the address component enables the address component to have characteristics based on real geographic space, thereby improving the accuracy of subsequent calculations.

[0035] Step S103: Determine the target coordinate point corresponding to the address text to be processed according to the spatial distribution characteristics of each address component in the address text to be processed. After obtaining the spatial distribution characteristics of each address component, the address matching calculation can be performed on the address text to be processed by using the spatial distribution characteristics, so as to obtain the target coordinate point corresponding to the address text to be processed.

[0036] Since the spatial distribution characteristics of each address component are added in the calculation process, it enables the artificial intelligence model to understand the spatial distribution characteristics of each address component and the weight differences in recall ranking, or to predefine a more accurate screening range during rule matching, thereby improving the accuracy and efficiency of geocoding.

[0037] Figure 2 It is a schematic diagram of the specific execution steps of the address text processing method in the embodiment of the present invention. See Figure 2 .

[0038] Step S201: The server performs word segmentation on multiple address texts with pre-matched coordinate points to obtain the address components in the address texts. In this step, the server performs word segmentation on multiple address texts with pre-matched coordinate points, so as to obtain the address components in the address texts. Among them, the above address texts can be matched with coordinate points in the historical period through the following method: First, the server analyzes the address texts and matches them with the geographical entities stored in the database. After that, the server determines the coordinate points corresponding to the successfully matched geographical entities as the coordinate points matched by the address texts. For example, the address text "No. 1 Square, Jinghai Road 11, Yizhuang Development Zone, Daxing District, Beijing" can be segmented to obtain the following address components: Beijing City, Daxing District, Yizhuang, Development Zone, Jinghai Road 11, and No. 1 Square.

[0039] Step S202: The server obtains the mapping relationship between each address component and the coordinate point. After separately obtaining the address components in the address text and the coordinate points matched by the address text, the mapping relationship between each address component and the coordinate point can be obtained.

[0040] Step S203: The server aggregates the coordinate points according to the address components. In this step, the server performs aggregation in the dimension of the address components based on the above mapping relationship, so as to obtain the coordinate points corresponding to each address component.

[0041] Step S204: The server determines the spatial distribution characteristics of the address components. In this step, the server uses the coordinates corresponding to any address component to calculate the spatial distribution characteristics of that address component. For example, the spatial distribution characteristics may include at least one of the following dimensions: spatial distribution center point, spatial distribution area, number of coordinate points, coordinates of at least one cluster center formed by clustering the coordinate points, and the number of cluster categories formed by clustering the coordinate points (clustering can use known algorithms such as DBSCAN). These dimensions can characterize the distribution characteristics of the address components in real geographic space. For example, the spatial distribution center point can characterize the center point of the address component, the spatial distribution area can characterize the coverage range of the address component, the number of coordinate points can characterize the number of mapped coordinates of the address component, and the cluster center coordinates and the number of cluster categories can characterize the cluster distribution characteristics of the coordinate points corresponding to the address component. By adding spatial distribution characteristics to the address components, different address components in the address text can have computational weights related to real geographic space, thereby forming a class attention mechanism for different address components in subsequent model calculation or rule matching stages, thus improving the accuracy of address matching. For example, based on the above calculations of spatial distribution characteristics, the address component "Palace Museum" can be characterized by concentrated distribution in spatial distribution characteristics, and can have a higher weight in address matching to facilitate location; while the address component "retail store" can be characterized by dispersed distribution in spatial distribution characteristics, and has a lower weight in address matching.

[0042] In this embodiment of the invention, the server can determine the center point indicated by each coordinate point in the above mapping relationship as the spatial distribution center point of the corresponding address component. For example, the server determines the average longitude of each coordinate point as the longitude of the spatial distribution center point and the average latitude of each coordinate point as the latitude of the spatial distribution center point.

[0043] In one embodiment, the server can calculate the spatial distribution area by the following steps: First, the server determines a two-dimensional graphic containing a preset shape based on the coordinate point in the mapping relationship, wherein the boundary of the two-dimensional graphic passes through part or all of the coordinate point; then, the server determines the area of ​​the two-dimensional graphic as the spatial distribution area of ​​the corresponding address component.

[0044] Step S205: The server receives the address text to be processed. Step S206: The server segments the address text to be processed to obtain address components. In these two steps, the server receives and begins processing the address text to be processed.

[0045] Step S207: The server obtains the spatial distribution characteristics of each address component in the address text to be processed. In this step, the server calculates based on the spatial distribution characteristics of the address components obtained in step S204. There are two calculation methods: one is shown in steps S208 and S209, and the other is shown in steps S210 and S211.

[0046] Step S208: The server constructs a comprehensive feature vector of the address text to be processed based on spatial distribution features. As a preferred embodiment, the server can first obtain the word embedding vector and the position embedding vector representing the location of each address component in the address text. Then, it uses the spatial distribution features of each address component in the address text to determine the spatial distribution feature vector of the address text. For example, the server can arrange the spatial distribution features of each address component in at least one dimension into a spatial distribution feature vector according to a preset order. Alternatively, it can first calculate the spatial distribution feature value of the same address component based on its spatial distribution features in each dimension, and then arrange the spatial distribution feature values ​​of each address component into a spatial distribution feature vector. Finally, the server can concatenate the word embedding vector, the position embedding vector, and the spatial distribution feature vector into a comprehensive feature vector of the address text to be processed.

[0047] Step S209: The server inputs the comprehensive feature vector into the address matching model to obtain the target coordinates. In this step, the server inputs the comprehensive feature vector of the address text to be processed into the pre-trained address matching model to obtain the target coordinates.

[0048] Step S210: The server calculates the target geographic region of the address text to be processed based on spatial distribution characteristics. Preferably, in this step, the server first determines the geographic region covered by any address component in the address text based on its spatial distribution center point and spatial distribution area. Then, the server determines the intersection of the geographic regions covered by each address component in the address text as the target geographic region of the address text to be processed.

[0049] Step S211: The server performs geographic entity matching in the target geographic area to obtain the target coordinate point. In this step, the server matches the address text to be processed with geographic entities in the target geographic area, and determines the coordinate point corresponding to the successfully matched geographic entity as the target coordinate point corresponding to the address text to be processed.

[0050] In the technical solution of this invention embodiment, multiple address texts that have matched coordinate points are pre-segmented to obtain address components in the address texts. Then, a mapping relationship is established between any address component and the coordinate points of at least one matching address text to which that address component belongs. Based on at least one coordinate point in the mapping relationship, the spatial distribution characteristics of the address component are determined. These spatial distribution characteristics can characterize the distribution center, distribution area, number of coordinate points, and other distribution patterns and characteristics of the corresponding address component in real geographic space. When performing geocoding on the address text to be processed, the corresponding target coordinate points can be calculated using an artificial intelligence model or rule matching based on the spatial distribution characteristics of its address components. Because the spatial distribution characteristics of each address component are added during the calculation process, the artificial intelligence model can understand the spatial distribution characteristics of each address component and the weight differences in recall and ranking, or a more precise filtering range can be pre-defined during rule matching, thereby improving the accuracy and efficiency of geocoding.

[0051] It should be noted that the technical solutions of this invention, including the collection, updating, analysis, processing, use, transmission, and storage of user personal information, all comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0052] For the foregoing method embodiments, they are described as a series of actions for ease of description. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, and some steps may actually be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential for implementing the present invention.

[0053] To facilitate better implementation of the above-described solutions of the embodiments of the present invention, related apparatus for implementing the above-described solutions is also provided below.

[0054] Please see Figure 3 As shown, the address text processing device 300 provided in this embodiment of the invention may include: a word segmentation unit 301, a mapping unit 302, and a calculation unit 303.

[0055] The word segmentation unit 301 is used to segment multiple address texts that have been pre-matched with coordinate points to obtain address components in the address texts; the mapping unit 302 is used to establish a mapping relationship between any address component and the coordinate points that match at least one address text to which the address component belongs, and to determine the spatial distribution characteristics of the address component based on at least one coordinate point in the mapping relationship; the calculation unit 303 is used to determine the target coordinate points corresponding to the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed.

[0056] In this embodiment of the invention, the spatial distribution feature includes: a spatial distribution center point; and the mapping unit 302 can be further used to: determine the center point indicated by each coordinate point in the mapping relationship as the spatial distribution center point of the corresponding address component.

[0057] Preferably, the spatial distribution feature further includes: spatial distribution area; and the mapping unit 302 can be further used to: determine a two-dimensional graphic containing a preset shape of a coordinate point according to the coordinate point in the mapping relationship; wherein the boundary of the two-dimensional graphic passes through part or all of the coordinate point; and determine the area of ​​the two-dimensional graphic as the spatial distribution area of ​​the corresponding address component.

[0058] As a preferred embodiment, the computing unit 303 can be further used to: determine the comprehensive feature vector of the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed; input the comprehensive feature vector of the address text to be processed into a pre-trained address matching model to obtain the target coordinate point.

[0059] In one embodiment, the calculation unit 303 may be further configured to: obtain the word embedding vector of the address text to be processed and the position embedding vector representing the location of each address component in the address text to be processed; determine the spatial distribution feature vector of the address text to be processed using the spatial distribution features of each address component in the address text to be processed; and concatenate the word embedding vector, the position embedding vector and the spatial distribution feature vector into a comprehensive feature vector of the address text to be processed.

[0060] Preferably, the calculation unit 303 can be further used to: determine the geographical area covered by any address component in the address text to be processed based on the spatial distribution center point and spatial distribution area of ​​any address component; determine the intersection of the geographical areas covered by each address component in the address text to be processed as the target geographical area of ​​the address text to be processed; match the address text to be processed with the geographical entities in the target geographical area, and determine the coordinate points corresponding to the successfully matched geographical entities as the target coordinate points.

[0061] Furthermore, in this embodiment of the invention, the spatial distribution features further include at least one of the following: the number of coordinate points, the coordinates of at least one cluster center formed by clustering the coordinate points, and the number of cluster categories formed by clustering the coordinate points.

[0062] According to the technical solution of this invention, multiple address texts that have been matched with coordinate points are pre-segmented to obtain address components in the address texts. Then, a mapping relationship is established between any address component and the coordinate points of at least one matching address text to which that address component belongs. Based on at least one coordinate point in the mapping relationship, the spatial distribution characteristics of the address component are determined. These spatial distribution characteristics can characterize the distribution center, distribution area, number of coordinate points, and other distribution patterns and characteristics of the corresponding address component in real geographic space. When performing geocoding on the address text to be processed, the corresponding target coordinate points can be calculated using an artificial intelligence model or rule matching based on the spatial distribution characteristics of its address components. Because the spatial distribution characteristics of each address component are added during the calculation process, the artificial intelligence model can understand the spatial distribution characteristics of each address component and the weight differences in recall and ranking, or a more precise filtering range can be pre-defined during rule matching, thereby improving the accuracy and efficiency of geocoding.

[0063] Figure 4 An exemplary system architecture 400 is shown that can be applied to the address text processing method or address text processing apparatus of the present invention.

[0064] like Figure 4 As shown, system architecture 400 may include terminal devices 401, 402, and 403, network 404, and server 405 (this architecture is merely an example; the components included in a specific architecture may be adjusted according to the specific application). Network 404 serves as the medium for providing a communication link between terminal devices 401, 402, and 403 and server 405. Network 404 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0065] Users can use terminal devices 401, 402, and 403 to interact with server 405 via network 404 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 401, 402, and 403, such as geocoding applications (for example only).

[0066] Terminal devices 401, 402, and 403 can be various electronic devices with displays that support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0067] Server 405 can be a server that provides various services, such as a backend server that supports geocoding applications operated by users using terminal devices 401, 402, and 403 (for example only). The backend server can process received geocoding requests and other data, and feed back the processing results (such as target coordinates - for example only) to terminal devices 401, 402, and 403.

[0068] It should be noted that the address text processing method provided in this embodiment of the invention is generally executed by server 405, and correspondingly, the address text processing device is generally located in server 405.

[0069] It should be understood that Figure 4 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0070] The present invention also provides an electronic device. The electronic device according to an embodiment of the present invention includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the address text processing method provided by the present invention.

[0071] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing an electronic device according to embodiments of the present invention. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0072] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the computer system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0073] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0074] In particular, according to the embodiments disclosed in this invention, the processes described in the above main step diagrams can be implemented as computer software programs. For example, embodiments of this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the main step diagrams. In the above embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit 501, it performs the functions defined in the system of this invention.

[0075] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0076] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0077] The units described in the embodiments of the present invention can be implemented in software or hardware. The described units can also be located in a processor; for example, a processor can be described as including: a word segmentation unit, a mapping unit, and a computing unit. The names of these units do not necessarily limit the unit itself; for example, a word segmentation unit can also be described as "a unit that provides address components to the mapping unit."

[0078] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, and when the device executes the one or more programs, the steps performed by the device include: segmenting multiple address texts pre-matched with coordinate points to obtain address components in the address texts; establishing a mapping relationship between any address component and the coordinate points matching at least one address text to which the address component belongs; determining the spatial distribution characteristics of the address component based on at least one coordinate point in the mapping relationship; and determining the target coordinate points corresponding to the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed.

[0079] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the address text processing method provided by the present invention.

[0080] In the technical solution of this invention embodiment, multiple address texts that have matched coordinate points are pre-segmented to obtain address components in the address texts. Then, a mapping relationship is established between any address component and the coordinate points of at least one matching address text to which that address component belongs. Based on at least one coordinate point in the mapping relationship, the spatial distribution characteristics of the address component are determined. These spatial distribution characteristics can characterize the distribution center, distribution area, number of coordinate points, and other distribution patterns and characteristics of the corresponding address component in real geographic space. When performing geocoding on the address text to be processed, the corresponding target coordinate points can be calculated using an artificial intelligence model or rule matching based on the spatial distribution characteristics of its address components. Because the spatial distribution characteristics of each address component are added during the calculation process, the artificial intelligence model can understand the spatial distribution characteristics of each address component and the weight differences in recall and ranking, or a more precise filtering range can be pre-defined during rule matching, thereby improving the accuracy and efficiency of geocoding.

[0081] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for processing address text, characterized in that, include: Multiple address texts with pre-matched coordinate points are segmented to obtain the address components in the address texts; Establish a mapping relationship between any address component and the coordinate points that match at least one address text to which the address component belongs, and determine the spatial distribution characteristics of the address component based on at least one coordinate point in the mapping relationship; Based on the spatial distribution characteristics of each address component in the address text to be processed, the target coordinate point corresponding to the address text to be processed is determined.

2. The method according to claim 1, characterized in that, The spatial distribution features include: a spatial distribution center point; and determining the spatial distribution features of the address component based on at least one coordinate point in the mapping relationship includes: The center point indicated by each coordinate point in the mapping relationship is determined as the spatial distribution center point of the corresponding address component.

3. The method according to claim 2, characterized in that, The spatial distribution feature further includes: spatial distribution area; and the step of determining the spatial distribution feature of the address component based on at least one coordinate point in the mapping relationship includes: A two-dimensional graphic containing a preset shape is determined based on the coordinate points in the mapping relationship; wherein the boundary of the two-dimensional graphic passes through part or all of the coordinate points. The area of ​​the two-dimensional graphic is determined as the spatial distribution area of ​​the corresponding address components.

4. The method according to claim 1, characterized in that, The step of determining the target coordinate point corresponding to the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed includes: The comprehensive feature vector of the address text to be processed is determined based on the spatial distribution characteristics of each address component in the address text to be processed; The comprehensive feature vector of the address text to be processed is input into a pre-trained address matching model to obtain the target coordinate point.

5. The method according to claim 4, characterized in that, The step of determining the comprehensive feature vector of the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed includes: Obtain the word embedding vector of the address text to be processed, and the position embedding vector representing the location of each address component in the address text to be processed; The spatial distribution feature vector of the address text to be processed is determined by utilizing the spatial distribution features of each address component in the address text to be processed. The word embedding vector, the position embedding vector, and the spatial distribution feature vector are concatenated to form the comprehensive feature vector of the address text to be processed.

6. The method according to claim 3, characterized in that, The step of determining the target coordinate point corresponding to the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed includes: Based on the spatial distribution center point and spatial distribution area of ​​any address component in the address text to be processed, determine the geographical area covered by that address component; The intersection of the geographical regions covered by each address component in the address text to be processed is determined as the target geographical region of the address text to be processed. The address text to be processed is matched with the geographic entities in the target geographic region, and the coordinate points corresponding to the successfully matched geographic entities are determined as the target coordinate points.

7. The method according to claim 2, 3 or 6, characterized in that, The spatial distribution features further include at least one of the following: the number of coordinate points, the coordinates of at least one cluster center formed by clustering the coordinate points, and the number of cluster categories formed by clustering the coordinate points.

8. An address text processing device, characterized in that, include: The word segmentation unit is used to segment multiple address texts that have been pre-matched with coordinate points to obtain the address components in the address texts. A mapping unit is used to establish a mapping relationship between any address component and the coordinate points that match at least one address text to which the address component belongs, and to determine the spatial distribution characteristics of the address component based on at least one coordinate point in the mapping relationship. The calculation unit is used to determine the target coordinate point corresponding to the address text to be processed based on the spatial distribution characteristics of each address component in the address text to be processed.

9. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images