Geographic data management method, device, equipment, storage medium and program product

Abstract

The present invention provides a geographic data management method, apparatus, device, storage medium, and program product, relating to the field of artificial intelligence technology. The geographic data management method includes: obtaining geographic data for different business scenarios; performing at least one of the following management operations on the geographic data: obtaining a time update period for the geographic data and updating the geographic data version according to the time update period; obtaining update information for the geographic data and determining transformation information for the geographic data based on the update information; and classifying the geographic data to obtain the business scenarios corresponding to the geographic data. This management approach can improve geographic data management efficiency and geographic data matching accuracy.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a geographic data management method, apparatus, device, storage medium and program product. Background Art

[0002] Geographic data governance includes a series of data processing processes, including geographic data collection, geographic data version updates, and geographic data scene matching. These processing processes involve multiple business subsystems, and each business subsystem maintains its own set of indicators to reflect its own data governance results. For example, multiple business subsystems include a spatiotemporal dimension processing subsystem for static mapping of data, a version management subsystem for version management of data, and a scene matching subsystem for scene matching of data. However, the spatiotemporal dimension processing subsystem is unable to dynamically perceive data change rules, the version management subsystem is unable to fully reconstruct data version updates, resulting in data waste, and the scene matching subsystem has a low data-scene matching degree.

[0003] In summary, existing data governance methods have the problems of low geographic data governance efficiency and low geographic data matching accuracy. Summary of the Invention

[0004] The present invention provides a geographic data management method, apparatus, device, storage medium and program product to solve the problems of low geographic data management efficiency and low geographic data matching accuracy in existing data management methods.

[0005] In order to solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a geographic data management method, comprising:

[0007] Obtain geographic data for different business scenarios;

[0008] Perform at least one of the following management on the geographic data:

[0009] Obtaining a time update period for the geographic data, and performing a version update on the geographic data according to the time update period;

[0010] Acquiring update information of the geographic data, and determining transformation information of the geographic data according to the update information;

[0011] The geographic data is classified to obtain business scenarios corresponding to the geographic data.

[0012] Optionally, obtaining a time update period of the geographic data includes:

[0013] Using a long short-term memory model (LSTM) and a gating mechanism, the time update information of the data is obtained according to the historical update time of the geographic data;

[0014] The time update period is obtained according to the time update information using a timing encoder.

[0015] Optionally, obtaining update information of the geographic data includes:

[0016] Obtaining the region code corresponding to the geographic data;

[0017] Constructing a geocoding knowledge graph based on the region code, wherein the geocoding knowledge graph includes multi-level administrative region codes corresponding to the geographic data;

[0018] Get the geographic data to be matched;

[0019] Utilize the geocoding knowledge graph and the geographic data to be matched to obtain update information of the geographic data.

[0020] Optionally, the geocoding knowledge graph includes parent-child relationship indication information, where the parent-child relationship indication information is used to indicate a hierarchical relationship between two adjacent administrative district codes;

[0021] According to the region code, a geocoding knowledge graph is constructed, including:

[0022] Splitting the region code into multiple levels of administrative region codes;

[0023] Use similarity algorithm to obtain the similarity value between any two levels of administrative area codes;

[0024] The two-level administrative region codes whose similarity values ​​are greater than a preset threshold are added to the parent-child relationship indication information to obtain the geographic coding knowledge graph.

[0025] Optionally, using the geocoding knowledge graph and the geographic data to be matched, obtaining updated information of the geographic data includes:

[0026] Splitting the region code corresponding to the geographic data to be matched into multiple levels of administrative region codes to be matched;

[0027] Obtaining updated information of the geographic data according to the administrative region code to be matched at each level and the geographic coding knowledge graph;

[0028] The update information of the geographic data includes one of the following instructions:

[0029] New administrative regions are added to the geographic data;

[0030] Incorporating administrative regions into the geographic data;

[0031] Administrative regions are deleted from the geographic data.

[0032] Optionally, classifying the geographic data to obtain a business scenario corresponding to the geographic data includes:

[0033] Acquire a space-time code corresponding to the geographic data, wherein the space-time code is used to indicate address information corresponding to the geographic data;

[0034] Inputting the spatiotemporal code into a scene similarity model to obtain address information corresponding to the business scene output by the similarity model; wherein the scene similarity model is used to indicate the correspondence between the spatiotemporal code and the address information corresponding to the business scene;

[0035] Determine the business scenario according to the address information corresponding to the business scenario.

[0036] Optionally, the method further includes:

[0037] Obtain training space-time coding and training address information corresponding to the business scenario;

[0038] Based on the bidirectional encoder representation method BERT model, the training spatiotemporal coding and the training address information are trained to obtain the scene similarity model.

[0039] In a second aspect, an embodiment of the present invention further provides a geographic data management device, comprising:

[0040] The first acquisition module is used to obtain geographic data in different business scenarios;

[0041] The first processing module is configured to perform at least one of the following management operations on the geographic data:

[0042] Obtaining a time update period for the geographic data, and performing a version update on the geographic data according to the time update period;

[0043] Acquiring update information of the geographic data, and determining transformation information of the geographic data according to the update information;

[0044] The geographic data is classified to obtain business scenarios corresponding to the geographic data.

[0045] In a third aspect, an embodiment of the present invention further provides a geographic data management device, comprising: a processor, a memory, and a program stored on the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the geographic data management method as described in any one of the first aspects are implemented.

[0046] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium having a program stored thereon, and when the program is executed by a processor, the steps in the geographic data management method as described in any one of the first aspects are implemented.

[0047] In a fifth aspect, an embodiment of the present invention further provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps in the geographic data management method as described in any one of the first aspects.

[0048] The beneficial effects of the present invention are:

[0049] The geographic data management method provided by the present invention acquires geographic data for different business scenarios and performs at least one of the following management operations on the geographic data: acquiring the time update cycle of the geographic data and performing version updates on the geographic data according to the time update cycle; acquiring update information for the geographic data and determining transformation information for the geographic data based on the update information; and classifying the geographic data to obtain the business scenarios corresponding to the geographic data. Specifically, the geographic data management method provided by the present invention fully updates data versions based on the time update cycle, dynamically detects geographic data change rules based on the update information, and classifies the geographic data to match geographic data with business scenarios. This management approach can improve geographic data management efficiency and geographic data matching accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart showing a geographic data management method provided by an embodiment of the present invention;

[0051] Figure 2 A schematic diagram of an index architecture provided by an embodiment of the present invention is shown;

[0052] Figure 3 A schematic diagram showing the structure of a geographic data management device provided by an embodiment of the present invention;

[0053] Figure 4 A schematic diagram showing the structure of a geographic data management device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the technical problems, technical solutions and advantages to be solved by the present application clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the present application. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. In addition, for clarity and brevity, the description of known functions and structures has been omitted.

[0055] It should be understood that references throughout this specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present application. Therefore, the appearances of "in one embodiment" or "in an embodiment" throughout this specification do not necessarily refer to the same embodiment. Furthermore, these particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0056] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0057] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0058] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.

[0059] In order to solve the problems of low geographic data management efficiency and low geographic data matching accuracy in existing data management methods, embodiments of the present invention provide a geographic data management method, apparatus, device, storage medium and program product.

[0060] like Figure 1 As shown, an embodiment of the present invention provides a geographic data management method, including:

[0061] Step 101: Obtain geographic data for different business scenarios.

[0062] The business scenarios include business scenarios for different industries, including government affairs, finance, logistics, etc.

[0063] Step 102: Perform at least one of the following management on the geographic data:

[0064] (1) obtaining a time update period for the geographic data, and performing a version update on the geographic data according to the time update period;

[0065] (2) obtaining update information of the geographic data, and determining transformation information of the geographic data according to the update information;

[0066] (3) Classifying the geographic data to obtain business scenarios corresponding to the geographic data.

[0067] That is, the geographic data is managed according to at least one of the above-mentioned management methods (1), (2), and (3).

[0068] In the management method (1), a time update period of the geographic data is obtained, and the geographic data is updated according to the time update period. The time update period may be fixed or variable. In the management method (1), the data version is fully updated according to the time update period.

[0069] In management mode (2), update information of geographic data is obtained, and the change rules of geographic data are dynamically perceived based on the update information, that is, the change information of geographic data is determined, wherein the change information of geographic data is used to indicate the update status of geographic data.

[0070] In management method (3), by classifying geographic data, the business scenarios corresponding to the geographic data are obtained, thereby achieving matching between geographic data and business scenarios.

[0071] Through the above management method, the governance efficiency of geographic data and the matching accuracy of geographic data can be improved.

[0072] In an optional embodiment, obtaining the time update period of the geographic data includes:

[0073] Using a Long Short-Term Memory (LSTM) model and a gating mechanism, the time update information of the data is obtained according to the historical update time of the geographic data;

[0074] The time update period is obtained according to the time update information using a timing encoder.

[0075] Specifically, in this optional embodiment, a time dimension encoder is designed. This encoder uses an LSTM model to capture the historical update time of geographic data and obtains data update time information. This data update time information is used to indicate how the geographic data has been updated historically. Furthermore, a time series encoder is designed to output the time update period of the time dimension based on the update time information.

[0076] Specifically, in an embodiment of the present invention, an improved Transformer-LSTM hybrid architecture is used to obtain the time update cycle. Its core advantage is that the LSTM model is good at capturing short-term dependencies and periodic patterns, and the Transformer models long-distance dependencies through the self-attention mechanism.

[0077] The LSTM model uses a three-layer, 256-hidden unit bidirectional LSTM network as input, using standard historical update time series data (i.e., historical update times of geographic data, such as the version number and effective date of the medical insurance catalog). This model uses a gating mechanism to capture periodic patterns. For example, by training on the national medical insurance catalog update data from 2018 to 2023, the model can identify major adjustments every two years.

[0078] A two-layer Transformer encoder is superimposed after the output of the LSTM model to learn the long-distance dependencies in the time series (i.e., learn the time update information) and output the time dimension feature vector (i.e., the time update period).

[0079] In an optional embodiment, obtaining update information of the geographic data includes:

[0080] Obtain the region code corresponding to the geographic data. This process is the process of standardizing geographic data. The unified coding format is a 12-digit standard administrative division code (such as 330621007233), and supplements historical change records (such as the code of a county changed from 330621 to 330603 in 2020);

[0081] Constructing a geocoding knowledge graph based on the region code, wherein the geocoding knowledge graph includes multi-level administrative region codes corresponding to the geographic data;

[0082] The geographic coding knowledge graph establishes difference rules to capture the coding rules of different regions. For example, the area code of Taoyuan Village, Lanting Street, Keqiao District, Shaoxing City, Zhejiang Province is 330621007233, while the area code of Xiaoge Village, Longgong Town, Xixiu District, Anshun City, Guizhou Province is 520402103.

[0083] Specifically, the geocoding knowledge graph constructs a geocoding knowledge graph, where the nodes are the three-level administrative division codes of province / city / district (e.g., 330621 represents Keqiao District, Shaoxing City, Zhejiang Province), and the edge weights are calculated using Jaccard similarity to calculate geocoding differences;

[0084] The geocoding knowledge graph includes multi-level administrative region codes corresponding to the geographic data. For example, it includes three-level administrative region codes, that is, the geocoding knowledge graph includes three-level nodes:

[0085] Provincial nodes (e.g. Zhejiang Province: 330000);

[0086] City-level nodes (e.g. Shaoxing: 330600);

[0087] District-level nodes (such as Keqiao District: 330621).

[0088] Obtain geographic data to be matched. Specifically, obtain geographic data through the National Geographic Information Public Service Platform (the latest administrative division data in 2023), or obtain geographic data through local government bulletins (such as announcements on the abolition of counties and the establishment of districts), or obtain geographic data by regularly (for example, monthly) crawling the government official website's administrative division change announcements. This geographic data is the geographic data to be matched.

[0089] Among them, the geographic data to be matched is also the administrative code pair to be matched (such as "330621007233" and "520402103"). The administrative division change rules are learned through the graph convolutional network (GCN) to output the spatial dimension feature vector.

[0090] Utilize the geocoding knowledge graph and the geographic data to be matched to obtain update information of the geographic data.

[0091] The update information of the geographic data may be used to indicate whether at least one of the following has occurred in the geographic data: a new administrative district has been added, an administrative district has been deleted, or an administrative district has been merged.

[0092] Furthermore, the geocoding knowledge graph includes parent-child relationship indication information, which is used to indicate the hierarchical relationship between two adjacent administrative district codes; the parent-child relationship indication information can also be called a parent-child relationship edge (such as 330600→330621), with a weight of 1 (fixed hierarchical relationship);

[0093] According to the region code, a geocoding knowledge graph is constructed, including:

[0094] Splitting the region code into multiple levels of administrative region codes, illustratively, dividing the region code into three levels of nodes (i.e., three levels of administrative region codes);

[0095] The similarity value between any two administrative region codes is obtained using a similarity algorithm. For example, the similarity algorithm is the Jaccard similarity calculation method, that is, the change relationship in the geocoding knowledge graph (such as 330621→330603) is changed, and the weight (i.e., the similarity value) is calculated using the Jaccard similarity method.

[0096] The two-level administrative region codes whose similarity values ​​are greater than a preset threshold are added to the parent-child relationship indication information to obtain the geographic coding knowledge graph.

[0097] Furthermore, using the geocoding knowledge graph and the geographic data to be matched, obtaining updated information of the geographic data includes:

[0098] Splitting the region code corresponding to the geographic data to be matched into multiple levels of administrative region codes to be matched;

[0099] Obtaining updated information of the geographic data according to the administrative region code to be matched at each level and the geographic coding knowledge graph;

[0100] The update information of the geographic data includes one of the following instructions:

[0101] Adding a new administrative region to the geographic data, such as establishing a new development zone (330621007);

[0102] Merge administrative regions in the geographic data, such as township merger (330621007233→330621008);

[0103] Administrative regions are deleted from the geographic data, such as deleting old codes after towns are merged.

[0104] Furthermore, the effective time can be added when obtaining the newly added or merged administrative areas (for example, the effective time of 330621 is [2010-01-01, 2020-12-31]).

[0105] In an optional embodiment, classifying the geographic data to obtain a business scenario corresponding to the geographic data includes:

[0106] Acquire a space-time code corresponding to the geographic data, wherein the space-time code is used to indicate address information corresponding to the geographic data;

[0107] Inputting the spatiotemporal code into a scene similarity model to obtain address information corresponding to the business scene output by the similarity model; wherein the scene similarity model is used to indicate the correspondence between the spatiotemporal code and the address information corresponding to the business scene;

[0108] Determine the business scenario according to the address information corresponding to the business scenario.

[0109] For example, the address information corresponding to the geographic data indicated by the space-time code is e-commerce address information, the address information corresponding to the business scenario output by the scene similarity model is household registration address information, and the determined business scenario is a public scenario; for another example, the address information corresponding to the geographic data indicated by the space-time code is registration address information, the address information corresponding to the business scenario output by the scene similarity model is operating address information, and the determined business scenario is an enterprise application scenario; for another example, the address information corresponding to the geographic data indicated by the space-time code is medical insurance participation address information, the address information corresponding to the business scenario output by the scene similarity model is out-of-town medical treatment address information, and the determined business scenario is a medical scenario.

[0110] The scene similarity model may be a scene similarity matrix to achieve cross-scene standard difference discrimination.

[0111] Specifically, the method further includes:

[0112] Obtain training space-time coding and training address information corresponding to the business scenario;

[0113] It should be noted that the training space-time coding and the above space-time coding have basically the same meaning, but the specific parameter values ​​are different. The training address information and the address information corresponding to the above business scenarios have basically the same meaning, but the specific parameter values ​​are different.

[0114] Based on a bidirectional encoder representation method (Bidirectional Encoder Representations from Transformers, BERT) model, the training spatiotemporal coding and the training address information are trained to obtain the scene similarity model.

[0115] Specifically, the BERT model is used to classify scenarios, with different scenarios matching different spatiotemporal codes. For example, the standard differences between e-commerce addresses and household registration addresses in different scenarios. Specific methods include:

[0116] Construct a scenario feature comparison dataset, which includes a large number of sample pairs, such as e-commerce address vs. household registration address, company registration address vs. operating address, etc.

[0117] Based on the BERT-base model, add a contrast loss function:

[0118]

[0119] in, Represents the characteristics of the same scenario (i.e., spatiotemporal coding and training address information under the same business scenario), represents heterogeneous scenario features (i.e., spatiotemporal coding and training address information under different business scenarios), τ = 0.1, represents the temperature parameter.

[0120] The above loss function is used for training, and the scene similarity matrix is ​​finally output to achieve cross-scene standard difference discrimination.

[0121] In summary, the geographic data management method provided by the embodiment of the present invention constructs a three-dimensional spatiotemporal index of standard elements, and the index includes a time axis, a space axis, and a scene axis; a spatiotemporal joint attention module is designed based on the improved spatiotemporal model to automatically identify differences in spatiotemporal rules. Among them, the time axis is associated with the national standard effective period, the geographic coding is based on the grid data of the National Geographic Information Public Service Platform, and the scene labels are automatically annotated by the business scenario classifier, such as logistics distribution scenarios, medical reimbursement scenarios in different places, etc. Specifically, the time dimension encoder uses a Transformer encoder to capture the periodic laws of standard updates; the spatial dimension encoder integrates a rule difference learning network for geographic coding; the scene comparison classification unit classifies scenes through BERT fine-tuning to distinguish standard differences in similar scenes.

[0122] The following combination Figure 2 The index architecture of the geographic data management method provided by the embodiment of the present invention is specifically described. The geographic data passes through the spatiotemporal parsing engine to obtain a spatiotemporal index. Based on the spatiotemporal index, the geographic data is managed in the time dimension, space dimension and scene dimension. The timestamp is determined in the time dimension (the timestamp is), and the geographic data is updated according to the time update cycle. In the spatial dimension, the update information of the geographic coding of the geographic data is obtained, and the transformation information of the geographic data is determined based on the update information. In the scene dimension, the scene label corresponding to the business data is determined (that is, the geographic data is classified), standard elements are obtained, and a unified standard library is established.

[0123] The geographic data management method provided by the embodiment of the present invention can be applied to government affairs scenarios, such as inter-regional medical insurance reimbursement:

[0124] The spatiotemporal index identifies the validity of the insured location and drug coding in the time dimension;

[0125] Dynamically map the medical insurance catalog based on the time dimension label. The specific steps are as follows:

[0126] 1. Extract the insurance location code (such as "330621") and drug code (such as "Z0001").

[0127] 2. The time encoder queries the version library of the medical insurance catalog to identify the validity of the drug code on the reimbursement date (e.g., 2023-08-15).

[0128] 3. The spatial encoder calls the geocoding knowledge graph to determine whether there is an administrative division adjustment between the insurance area and the medical treatment area (such as the abolition of counties and the establishment of districts in 2020).

[0129] 4. The scenario classifier identifies the scenario as "out-of-town outpatient care" and matches the corresponding cross-provincial reimbursement rules.

[0130] Output standardized reimbursement catalog mapping results.

[0131] The geographic data management method provided by the embodiment of the present invention can also be applied to government affairs scenarios and financial scenarios, such as corporate credit assessment:

[0132] Spatial coding solves the problem of address standardization;

[0133] The timeline captures the change of registered place and corrects the credit errors caused by migration;

[0134] The scene label comparison distinguishes the registered address and the operating address.

[0135] The geographic data management method provided by the embodiment of the present invention can reduce the data governance cost of the government platform in the field of government affairs, and can improve the accuracy of the delivery address of express companies and save logistics costs in the field of logistics. In terms of speeding up services, it can shorten the processing time of medical insurance reimbursement materials in other places and improve the standardization coverage of rural logistics.

[0136] like Figure 3 As shown, an embodiment of the present invention further provides a geographic data management device, comprising:

[0137] The first acquisition module 301 is used to acquire geographic data in different business scenarios;

[0138] The first processing module 302 is configured to perform at least one of the following management operations on the geographic data:

[0139] Obtaining a time update period for the geographic data, and performing a version update on the geographic data according to the time update period;

[0140] Acquiring update information of the geographic data, and determining transformation information of the geographic data according to the update information;

[0141] The geographic data is classified to obtain business scenarios corresponding to the geographic data.

[0142] Optionally, the first processing module 302 includes:

[0143] A first processing unit is configured to obtain time update information of the data according to the historical update time of the geographic data by using a long short-term memory model (LSTM) and a gating mechanism;

[0144] The second processing unit is configured to obtain the time update period according to the time update information by using a timing encoder.

[0145] Optionally, the first processing module 302 includes:

[0146] A first acquiring unit, configured to acquire a region code corresponding to the geographic data;

[0147] A third processing unit is configured to construct a geocoding knowledge graph based on the region code, wherein the geocoding knowledge graph includes multi-level administrative region codes corresponding to the geographic data;

[0148] A second acquisition unit is used to acquire geographic data to be matched;

[0149] The fourth processing unit is used to obtain update information of the geographic data by using the geocoding knowledge graph and the geographic data to be matched.

[0150] Optionally, the geocoding knowledge graph includes parent-child relationship indication information, where the parent-child relationship indication information is used to indicate a hierarchical relationship between two adjacent administrative district codes;

[0151] The third processing unit is specifically configured to:

[0152] Splitting the region code into multiple levels of administrative region codes;

[0153] Use similarity algorithm to obtain the similarity value between any two levels of administrative area codes;

[0154] The two-level administrative region codes whose similarity values ​​are greater than a preset threshold are added to the parent-child relationship indication information to obtain the geographic coding knowledge graph.

[0155] Optionally, the fourth processing unit is specifically configured to:

[0156] Splitting the region code corresponding to the geographic data to be matched into multiple levels of administrative region codes to be matched;

[0157] Obtaining updated information of the geographic data according to the administrative region code to be matched at each level and the geographic coding knowledge graph;

[0158] The update information of the geographic data includes one of the following instructions:

[0159] New administrative regions are added to the geographic data;

[0160] Incorporating administrative regions into the geographic data;

[0161] Administrative regions are deleted from the geographic data.

[0162] Optionally, the first processing module 302 includes:

[0163] a third acquiring unit, configured to acquire a spatiotemporal code corresponding to the geographic data, wherein the spatiotemporal code is used to indicate address information corresponding to the geographic data;

[0164] a fifth processing unit, configured to input the spatiotemporal code into a scene similarity model to obtain address information corresponding to the business scene output by the similarity model; wherein the scene similarity model is used to indicate a correspondence between the spatiotemporal code and the address information corresponding to the business scene;

[0165] The sixth processing unit is configured to determine the business scenario according to the address information corresponding to the business scenario.

[0166] Optionally, the first processing module 302 further includes:

[0167] A fourth acquisition unit is used to acquire training address information corresponding to the training spatiotemporal code and the service scenario;

[0168] The seventh processing unit is used to train the training spatiotemporal coding and the training address information based on the bidirectional encoder representation method BERT model to obtain the scene similarity model.

[0169] It should be noted that the geographic data management device provided in the embodiment of the present invention is a device capable of executing the above-mentioned geographic data management method. All embodiments of the above-mentioned geographic data management method are applicable to the device and can achieve the same or similar technical effects.

[0170] like Figure 4 As shown, an embodiment of the present invention further provides a geographic data management device, including: a processor 401; and a memory 403 connected to the processor 401 via a bus interface 402, wherein the memory 403 is used to store programs and data used by the processor 401 when performing operations, and the processor 401 calls and executes the programs and data stored in the memory 403.

[0171] The transceiver 404 is connected to the bus interface 402 and is configured to receive and send data under the control of the processor 401. Specifically, the processor 401 is configured to read the program in the memory 403 and to execute the following process:

[0172] Obtain geographic data for different business scenarios;

[0173] Perform at least one of the following management on the geographic data:

[0174] Obtaining a time update period for the geographic data, and performing a version update on the geographic data according to the time update period;

[0175] Acquiring update information of the geographic data, and determining transformation information of the geographic data according to the update information;

[0176] The geographic data is classified to obtain business scenarios corresponding to the geographic data.

[0177] Optionally, the processor 401 is configured to:

[0178] Using a long short-term memory model (LSTM) and a gating mechanism, the time update information of the data is obtained according to the historical update time of the geographic data;

[0179] The time update period is obtained according to the time update information using a timing encoder.

[0180] Optionally, the processor 401 is configured to:

[0181] Obtaining the region code corresponding to the geographic data;

[0182] Constructing a geocoding knowledge graph based on the region code, wherein the geocoding knowledge graph includes multi-level administrative region codes corresponding to the geographic data;

[0183] Get the geographic data to be matched;

[0184] Utilize the geocoding knowledge graph and the geographic data to be matched to obtain update information of the geographic data.

[0185] Optionally, the geocoding knowledge graph includes parent-child relationship indication information, where the parent-child relationship indication information is used to indicate a hierarchical relationship between two adjacent administrative district codes;

[0186] The processor 401 is specifically configured to:

[0187] Splitting the region code into multiple levels of administrative region codes;

[0188] Use similarity algorithm to obtain the similarity value between any two levels of administrative area codes;

[0189] The two-level administrative region codes whose similarity values ​​are greater than a preset threshold are added to the parent-child relationship indication information to obtain the geographic coding knowledge graph.

[0190] Optionally, the processor 401 is specifically configured to:

[0191] Splitting the region code corresponding to the geographic data to be matched into multiple levels of administrative region codes to be matched;

[0192] Obtaining updated information of the geographic data according to the administrative region code to be matched at each level and the geographic coding knowledge graph;

[0193] The update information of the geographic data includes one of the following instructions:

[0194] New administrative regions are added to the geographic data;

[0195] Incorporating administrative regions into the geographic data;

[0196] Administrative regions are deleted from the geographic data.

[0197] Optionally, the processor 401 is configured to:

[0198] Acquire a space-time code corresponding to the geographic data, wherein the space-time code is used to indicate address information corresponding to the geographic data;

[0199] Inputting the spatiotemporal code into a scene similarity model to obtain address information corresponding to the business scene output by the similarity model; wherein the scene similarity model is used to indicate the correspondence between the spatiotemporal code and the address information corresponding to the business scene;

[0200] Determine the business scenario according to the address information corresponding to the business scenario.

[0201] Optionally, the processor 401 is further configured to:

[0202] Obtain training space-time coding and training address information corresponding to the business scenario;

[0203] Based on the bidirectional encoder representation method BERT model, the training spatiotemporal coding and the training address information are trained to obtain the scene similarity model.

[0204] Among them, Figure 4 In the embodiment, the bus architecture can include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 401 and memory represented by memory 403. The bus architecture can also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are all well known in the art and therefore will not be described further herein. The bus interface provides a user interface 405. The transceiver 404 can be multiple components, that is, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium. The processor 401 is responsible for managing the bus architecture and general processing, and the memory 403 can store data used by the processor 401 when performing operations.

[0205] In addition, a specific embodiment of the present invention further provides a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps in any one of the geographic data management methods described above.

[0206] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection of some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0207] In addition, the functional units in various embodiments of the present invention may be integrated into a single processing unit, each unit may be physically included separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional units.

[0208] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to perform some steps of the resource selection method described in various embodiments of the present invention, or to perform some steps of the information sending method described in various embodiments of the present invention. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, an optical disk, and other media that can store program code.

[0209] A specific embodiment of the present invention further provides a computer program product, including computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiment shown can achieve the same technical effect, and to avoid repetition, they will not be described here.

[0210] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary personnel in this technical field, several improvements and modifications can be made without departing from the principles described in the present invention. These improvements and modifications are also within the scope of protection of the present invention.

Claims

1. A geographic data management method, characterized in that: include: Obtain geographic data for different business scenarios; Perform at least one of the following management on the geographic data: Obtaining a time update period for the geographic data, and performing a version update on the geographic data according to the time update period; Acquiring update information of the geographic data, and determining transformation information of the geographic data according to the update information; Classifying the geographic data to obtain business scenarios corresponding to the geographic data; Wherein, obtaining the time update period of the geographic data includes: Using a long short-term memory model (LSTM) and a gating mechanism, the time update information of the data is obtained according to the historical update time of the geographic data; Using a timing encoder, obtaining the time update period according to the time update information; Wherein, obtaining the updated information of the geographic data includes: Obtaining the region code corresponding to the geographic data; Constructing a geocoding knowledge graph based on the region code, wherein the geocoding knowledge graph includes multi-level administrative region codes corresponding to the geographic data; Get the geographic data to be matched; Using the geocoding knowledge graph and the geographic data to be matched, obtaining updated information of the geographic data; The geographic data is classified to obtain the business scenarios corresponding to the geographic data, including: Acquire a space-time code corresponding to the geographic data, wherein the space-time code is used to indicate address information corresponding to the geographic data; Inputting the spatiotemporal code into a scene similarity model to obtain address information corresponding to the business scene output by the similarity model; wherein the scene similarity model is used to indicate the correspondence between the spatiotemporal code and the address information corresponding to the business scene; Determine the business scenario according to the address information corresponding to the business scenario.

2. The method according to claim 1, characterized in that The geocoding knowledge graph includes parent-child relationship indication information, and the parent-child relationship indication information is used to indicate the hierarchical relationship between two adjacent administrative district codes; According to the region code, a geocoding knowledge graph is constructed, including: Splitting the region code into multiple levels of administrative region codes; Use similarity algorithm to obtain the similarity value between any two levels of administrative area codes; The two-level administrative region codes whose similarity values ​​are greater than a preset threshold are added to the parent-child relationship indication information to obtain the geographic coding knowledge graph.

3. The method according to claim 2, characterized in that Utilizing the geocoding knowledge graph and the geographic data to be matched, obtaining updated information of the geographic data includes: Splitting the region code corresponding to the geographic data to be matched into multiple levels of administrative region codes to be matched; Obtaining updated information of the geographic data according to the administrative region code to be matched at each level and the geographic coding knowledge graph; The update information of the geographic data includes one of the following instructions: New administrative regions are added to the geographic data; Incorporating administrative regions into the geographic data; Administrative regions are deleted from the geographic data.

4. The method according to claim 1, wherein The method further comprises: Obtain training space-time coding and training address information corresponding to the business scenario; Based on the bidirectional encoder representation method BERT model, the training spatiotemporal coding and the training address information are trained to obtain the scene similarity model.

5. A geographic data management device, characterized in that: include: The first acquisition module is used to obtain geographic data in different business scenarios; The first processing module is configured to perform at least one of the following management operations on the geographic data: Obtaining a time update period for the geographic data, and performing a version update on the geographic data according to the time update period; Acquiring update information of the geographic data, and determining transformation information of the geographic data according to the update information; Classifying the geographic data to obtain business scenarios corresponding to the geographic data; Wherein, the first processing module includes: A first processing unit is configured to obtain time update information of the data according to the historical update time of the geographic data by using a long short-term memory model (LSTM) and a gating mechanism; a second processing unit, configured to obtain the time update period according to the time update information using a timing encoder; Wherein, the first processing module includes: A first acquiring unit, configured to acquire a region code corresponding to the geographic data; A third processing unit is configured to construct a geocoding knowledge graph based on the region code, wherein the geocoding knowledge graph includes multi-level administrative region codes corresponding to the geographic data; A second acquisition unit is used to acquire geographic data to be matched; a fourth processing unit, configured to obtain update information of the geographic data using the geocoding knowledge graph and the geographic data to be matched; Wherein, the first processing module includes: a third acquiring unit, configured to acquire a spatiotemporal code corresponding to the geographic data, wherein the spatiotemporal code is used to indicate address information corresponding to the geographic data; a fifth processing unit, configured to input the spatiotemporal code into a scene similarity model to obtain address information corresponding to the business scene output by the similarity model; wherein the scene similarity model is used to indicate a correspondence between the spatiotemporal code and the address information corresponding to the business scene; The sixth processing unit is configured to determine the business scenario according to the address information corresponding to the business scenario.

6. A geographic data management device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the geographic data management method according to any one of claims 1 to 4.

7. A readable storage medium, characterized in that: The readable storage medium stores a program, and when the program is executed by a processor, the steps in the geographic data management method according to any one of claims 1 to 4 are implemented.

8. A computer program product, characterized in that The method comprises computer instructions, which implement the steps of the geographic data management method according to any one of claims 1 to 4 when the computer instructions are executed by a processor.

Images