Geographic information processing method and device, computer device and storage medium

Abstract

The application relates to a geographic information processing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring user address information, and identifying the field types of the user address information; determining standard address information corresponding to the user address information according to the field identification result; performing character matching on the fields of the standard address information and the corresponding fields of building address information in a database; when the character matching fails, performing synonym matching on a reference field in the fields of the standard address information and the corresponding fields of the building address information in the database to obtain a synonym matching result; performing semantic analysis on a target field in the reference field and the corresponding fields of the building address information in the database according to the synonym matching result to obtain a semantic analysis result; and determining the association between the user address information and the corresponding building address information based on the synonym matching result and the semantic analysis result. The method can effectively improve the address matching efficiency.

Description

Geographic information processing methods, devices, computer equipment and storage media Technical Field

[0001] This application relates to the technical field, and in particular to a geographic information processing method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the development of computer technology, the method of using geographic information technology to compare and associate user-input address information with addresses in a standard address database to determine the specific building or location of the user is of great significance to the business operations of various industries. For example, it can help improve delivery efficiency, reduce mismatch costs, improve data quality, and reduce business risks.

[0003] In existing technologies, geographic address matching relies on search engines. For similar, duplicate, or non-standard addresses, tedious scoring and sorting are required, resulting in low accuracy of address matching. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, and storage medium for geographic information processing to address the aforementioned technical problems, which can effectively improve the efficiency of address matching.

[0005] Firstly, this application provides a geographic information processing method, including:

[0006] Obtain user address information and identify the type of each field in the user address information;

[0007] Based on the field recognition results, the standard address information corresponding to the user address information is determined. The standard address information is the address information represented in a preset structured manner.

[0008] Match the characters of each field of the standard address information with the corresponding fields of the building address information in the database;

[0009] When a character match fails, the reference field at the first level of granularity in the standard address information field is compared with the corresponding field of the building address information in the database to obtain the synonym matching result.

[0010] Based on the synonym matching results, semantic analysis is performed on the target field of the second level granularity in the reference field and the corresponding field of the building address information in the database to obtain the semantic analysis results. The second level granularity is smaller than the first level granularity.

[0011] Based on the synonym matching results and semantic analysis results, the association between user address information and corresponding building address information is determined.

[0012] In one embodiment, determining the standard address information corresponding to the user address information based on the field recognition result includes:

[0013] When the field recognition result indicates that the user address information is incomplete, the address information is searched in the address database based on the recognized fields, and the corresponding relevant fields are determined based on the search results.

[0014] Based on the relevant fields and the identified fields, they are combined and arranged in a preset structured manner to obtain the standard address information corresponding to the user address information.

[0015] In one embodiment, when a character match fails, a synonym match is performed between the first-level granularity reference field in the standard address information field and the corresponding field of the building address information in the database to obtain the synonym match result, including:

[0016] Retrieve the corresponding thesaurus, which contains the fields of address information and the correspondence between their respective synonyms;

[0017] The system queries the correspondence between reference fields and corresponding fields based on the thesaurus, and obtains the corresponding thesaurus matching results based on the thesaurus query results.

[0018] In one embodiment, when a character match fails, a synonym match is performed between the first-level granularity reference field in the standard address information field and the corresponding field of the building address information in the database to obtain the synonym match result, including:

[0019] The reference fields are the cell name field and the user name field in the user address information;

[0020] The corresponding field for building address information is the building name field;

[0021] The community name field and user name field in the standard address information are compared with the building name field in the building address information to obtain the synonym matching results.

[0022] In one embodiment, based on the synonym matching results, semantic analysis is performed between the target field at the second level granularity in the reference field and the corresponding field of building address information in the database to obtain semantic analysis results, including:

[0023] When synonym matching fails, the target field at the second level of granularity in the reference field and the corresponding fields of each building address information in the database are input into the semantic analysis model to obtain the semantic similarity between the target field and the corresponding fields of each building address information.

[0024] In one embodiment, based on synonym matching results and semantic analysis results, the association between user address information and corresponding building address information is determined, including:

[0025] The semantic analysis result is semantic similarity;

[0026] When the synonym matching result is successful, the relationship between the user address information and the corresponding building address information is determined to be a synonym match.

[0027] When the synonym matching result is a failure and the semantic similarity is greater than the threshold, the relationship between the user address information and the corresponding building address information is determined as a semantic similarity match.

[0028] The confidence level for synonym matching is higher than that for semantic similarity matching.

[0029] In one embodiment, the above-described geographic information processing method further includes:

[0030] Based on the correlation between user address information and corresponding building address information, determine the electricity service data of the electricity users corresponding to each building object;

[0031] Based on electricity consumption data, statistical information on electricity consumption data is determined with buildings as the main objects. This statistical information on electricity consumption data is used to assist the power management system in carrying out electricity consumption management work.

[0032] Secondly, this application also provides a geographic information processing apparatus, comprising:

[0033] The acquisition module is used to acquire user address information and identify the type of each field in the user address information; based on the field identification results, it determines the standard address information corresponding to the user address information, which is address information represented in a preset structured manner;

[0034] The matching module is used to perform character matching between each field of the standard address information and the corresponding field of the building address information in the database. When the character matching fails, the reference field of the first level granularity in the fields of the standard address information is matched with the corresponding field of the building address information in the database to obtain the synonym matching result. Based on the synonym matching result, the target field of the second level granularity in the reference field is semantically analyzed with the corresponding field of the building address information in the database to obtain the semantic analysis result. The second level granularity is smaller than the first level granularity.

[0035] The determination module is used to determine the association between user address information and corresponding building address information based on synonym matching results and semantic analysis results.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0037] Obtain user address information and identify the type of each field in the user address information;

[0038] Based on the field recognition results, the standard address information corresponding to the user address information is determined. The standard address information is the address information represented in a preset structured manner.

[0039] Match the characters of each field of the standard address information with the corresponding fields of the building address information in the database;

[0040] When a character match fails, the reference field at the first level of granularity in the standard address information field is compared with the corresponding field of the building address information in the database to obtain the synonym matching result.

[0041] Based on the synonym matching results, semantic analysis is performed on the target field of the second level granularity in the reference field and the corresponding field of the building address information in the database to obtain the semantic analysis results. The second level granularity is smaller than the first level granularity.

[0042] Based on the synonym matching results and semantic analysis results, the association between user address information and corresponding building address information is determined.

[0043] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0044] Obtain user address information and identify the type of each field in the user address information;

[0045] Based on the field recognition results, the standard address information corresponding to the user address information is determined. The standard address information is the address information represented in a preset structured manner.

[0046] Match the characters of each field of the standard address information with the corresponding fields of the building address information in the database;

[0047] When a character match fails, the reference field at the first level of granularity in the standard address information field is compared with the corresponding field of the building address information in the database to obtain the synonym matching result.

[0048] Based on the synonym matching results, semantic analysis is performed on the target field of the second level granularity in the reference field and the corresponding field of the building address information in the database to obtain the semantic analysis results. The second level granularity is smaller than the first level granularity.

[0049] Based on the synonym matching results and semantic analysis results, the association between user address information and corresponding building address information is determined.

[0050] The aforementioned geographic information processing methods, devices, computer equipment, and storage media utilize a professional word segmentation dictionary to semantically split addresses, extracting basic matching conditions and dictionaries to obtain standard address information corresponding to user address information. This enables accurate identification and standardized expression of non-standard, incomplete, inaccurate, and ambiguous user address information. Furthermore, string comparison, a thesaurus, and semantic analysis are used to match standard address information with building address information. Based on the matching results and semantic analysis results, the association between user address information and corresponding building address information is determined, thereby achieving effective identification and accurate matching of user address information and improving the accuracy of address matching. Attached Figure Description

[0051] Figure 1 is a flowchart illustrating a geographic information processing method in one embodiment;

[0052] Figure 2 is a flowchart illustrating the process of determining standard address information based on user address information in one embodiment;

[0053] Figure 3 is a flowchart illustrating the process of determining synonym matching results in one embodiment;

[0054] Figure 4 is a flowchart illustrating the process of determining the semantic relationship between user address information and building address information in one embodiment;

[0055] Figure 5 is a flowchart illustrating the application of electricity service data statistics based on the correlation between user address information and building address information in one embodiment.

[0056] Figure 6 is a structural block diagram of a geographic information processing device in one embodiment;

[0057] Figure 7 is an internal structure diagram of a computer device in one embodiment;

[0058] Figure 8 is an internal structure diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] In one embodiment, as shown in Figure 1, a geographic information processing method is provided. This embodiment uses the application of the method to a terminal as an example for illustration. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and can be implemented through the interaction between the terminal and the server.

[0061] In this embodiment, the method includes the following steps:

[0062] Step S102: Obtain user address information and identify the type of each field in the user address information.

[0063] Among them, user address information refers to the address information of the objects served by a specific business, such as the address information of electricity users, passenger address information, and buyer address information; user address information can be address information pre-stored in the database or address information currently entered by the user.

[0064] Specifically, the computer device retrieves pre-stored user address information from the database. However, due to potential differences in the collection and statistical methods of this pre-stored user address information, or issues such as non-standard statistical methods, some user address information may be non-standard, incomplete, inaccurate, or ambiguous, making it difficult to identify and locate the user's true location. Therefore, the computer device further identifies the types of each field in the user address information to obtain fields with independent meanings (such as province, city, district, street, etc.).

[0065] Step S104: Determine the standard address information corresponding to the user address information based on the field recognition results.

[0066] The standard address information is address information represented in a preset structured manner.

[0067] Specifically, the computer device obtains the editing template corresponding to the standard address information, and then, based on the recognition results of each field corresponding to the user address information determined in the aforementioned steps, replaces or rearranges the recognition results of each field according to the structured expression method corresponding to the editing template, thereby obtaining the standard address information corresponding to the user address information.

[0068] Step S106: Match the characters of each field of the standard address information with the corresponding fields of the building address information in the database.

[0069] The matching process can be based on the type of each field, matching fields of the same type one by one in a predetermined order.

[0070] Specifically, the computer device matches each field of the standard address information corresponding to the user address information determined in the aforementioned steps with the corresponding fields of each building address information in the database to obtain a matching result. The matching result may include a complete match, a complete mismatch, or a partial match. When the matching result is a partial match, the matching result specifically includes the fields in the standard address information that were successfully matched and the fields that were not matched.

[0071] Step S108: When character matching fails, perform synonym matching between the reference field of the first level granularity in the standard address information field and the corresponding field of the building address information in the database to obtain the synonym matching result.

[0072] In this context, a character match failure indicates that the character match was either a partial match or a complete mismatch.

[0073] Specifically, after the computer device fails to match the standard address information with the building address information according to the aforementioned steps, it determines the corresponding unmatched field based on the matching failure result, and then determines the first-level granularity reference field from the unmatched fields. The reference field is then matched with the corresponding field of the building address information in the database to obtain the synonym matching result. When the character match is successful, it indicates that the standard address information and the corresponding building address information are completely consistent, and the association relationship between the user address information and the corresponding building address information is directly output as a complete match.

[0074] Step S110: Based on the synonym matching results, perform semantic analysis on the target field of the second level granularity in the reference field and the corresponding field of the building address information in the database to obtain the semantic analysis results.

[0075] The second-level granularity is smaller than the first-level granularity.

[0076] Specifically, when the computer device fails to match the reference field in the standard address information with the building address information according to the aforementioned steps, it determines the target field of the second level granularity in the field corresponding to the failed synonym match, performs semantic analysis on the target field and the corresponding field of the building address information in the database, and obtains the semantic analysis result between the target field and the corresponding field. The semantic analysis result can be the semantic similarity between the two fields.

[0077] Step S112: Based on the synonym matching results and semantic analysis results, determine the association between user address information and corresponding building address information.

[0078] Specifically, when the synonym matching result is successful, the computer device determines that the association between the user address information and the corresponding building address information is a synonym match; when the synonym matching result is unsuccessful, the association between the user address information and the corresponding building address information is determined based on the semantic analysis result. Specifically, when the semantic analysis result shows that the association between the user address information and the corresponding building address information is semantically similar, the association is output as a similarity match; otherwise, the user address information is output as unmatched / unrecognized.

[0079] In this embodiment, by using a professional word segmentation dictionary to semantically split the address, the basic matching conditions and dictionary are extracted to obtain the standard address information corresponding to the user address information. This enables accurate identification and standardized expression of non-standard, incomplete, inaccurate, and ambiguous user address information. Then, string comparison, thesaurus, and semantic analysis are used to match the standard address information with the building address information. Based on the matching results and semantic analysis results, the association between the user address information and the corresponding building address information is determined, thereby achieving effective identification and accurate matching of user address information and improving the accuracy of address matching.

[0080] In one embodiment, as shown in Figure 2, determining the standard address information corresponding to the user address information based on the field recognition result includes:

[0081] Step S202: When the field recognition result is that the user address information is incomplete, the address information is searched in the address database based on the recognized fields, and the corresponding relevant fields are determined based on the search results.

[0082] The database pre-stores complete address information for all landmarks in the target area, and this complete address information is stored using a structured representation of standard address information.

[0083] Specifically, the computer equipment analyzes the field recognition results. When the field recognition results show that the corresponding user address information is incomplete, it is necessary to supplement the incomplete user address information.

[0084] Step S204: Based on the relevant fields and the identified fields, combine and arrange them according to a preset structured method to obtain the standard address information corresponding to the user address information.

[0085] In this embodiment, when the field identification result indicates that the user address information is incomplete, the address information is searched in the address database based on the identified fields. The corresponding related fields are determined based on the search results. Based on the related fields and the identified fields, they are combined and arranged in a preset structured manner to obtain the standard address information corresponding to the user address information. This allows for the accurate supplementation of related fields for incomplete user address information, improving the accuracy of locating user address information based on building address information in subsequent steps.

[0086] In one embodiment, as shown in Figure 3, when character matching fails, a synonym matching is performed between the first-level granularity reference field in the standard address information field and the corresponding field of the building address information in the database to obtain the synonym matching result, including:

[0087] Step S302: Obtain the corresponding thesaurus.

[0088] The thesaurus contains the correspondence between each field of the address information and its corresponding synonyms. In addition, the thesaurus contains location terms that are highly relevant to specific businesses. For example, in the application scenario corresponding to the power system, in order to adapt to the characteristics of the power field, the thesaurus can contain power-related terms and abbreviations (such as substation, distribution room, high-voltage line, etc.).

[0089] Specifically, computer devices can obtain a pre-set thesaurus from local storage or obtain the corresponding thesaurus from a server via a communication network.

[0090] Step S304: Query the correspondence between the reference field and the corresponding field according to the thesaurus, and obtain the corresponding thesaurus matching result based on the thesaurus query result.

[0091] Specifically, the computer device uses the reference field and its corresponding field determined in the aforementioned steps as query conditions to perform a query in the thesaurus and obtain query results. When the reference field and its corresponding field are found to be synonyms in the thesaurus, it indicates that the two are synonyms and the thesaurus matching result is output as a synonym association; otherwise, the reference field and its corresponding field are subjected to semantic analysis in subsequent steps.

[0092] In this embodiment, by obtaining the corresponding thesaurus, querying the correspondence between the reference field and the corresponding field according to the thesaurus, and obtaining the corresponding thesaurus matching result based on the thesaurus query result, the synonym relationship between the reference field in the standard address information and the corresponding field in the building address information can be quickly and accurately determined, thereby improving the accuracy of determining the association between the user address information and the corresponding building address information.

[0093] In one embodiment, when a character match fails, a synonym match is performed between the first-level granularity reference field in the standard address information field and the corresponding field in the building address information in the database to obtain the synonym match result, including:

[0094] The reference fields are the community name field and the user name field in the user address information; the corresponding field for the building address information is the building name field.

[0095] The community name field and user name field in the standard address information are compared with the building name field in the building address information to obtain the synonym matching results.

[0096] Specifically, the computer device uses the community name field and user name field in the standard address information and the building name field in the building address information as query conditions to perform a query in the thesaurus and obtain the query results. When the community name field, user name field and building name field are found to be synonyms in the thesaurus, it indicates that the two are synonymous and the thesaurus matching result is output as a synonym association; otherwise, the community name field, user name field and building name field are subjected to semantic analysis in subsequent steps.

[0097] In this embodiment, by obtaining the corresponding thesaurus, querying the correspondence between the community name field, user name field, and building name field according to the thesaurus, and obtaining the corresponding thesaurus matching results based on the thesaurus query results, the synonym relationship between the community name field and user name field in the standard address information and the building name field in the building address information can be quickly and accurately determined, thereby improving the accuracy of determining the association between user address information and corresponding building address information.

[0098] In one embodiment, based on the synonym matching results, semantic analysis is performed on the target field at the second level granularity in the reference field and the corresponding field of building address information in the database to obtain the semantic analysis results, including:

[0099] When synonym matching fails, the target field at the second level of granularity in the reference field and the corresponding fields of each building address information in the database are input into the semantic analysis model to obtain the semantic similarity between the target field and the corresponding fields of each building address information.

[0100] The semantic analysis model can employ neural networks or deep learning models, such as the BERT model. Semantic similarity is used to characterize the degree of similarity between the meanings expressed by the research fields. The higher the semantic similarity value, the closer the meanings expressed by the research fields are.

[0101] Specifically, when the computer device determines that a synonym match has failed, it inputs the target field at the second level of granularity in the reference field and the corresponding fields of the building address information in the database into the semantic analysis model, and outputs the semantic similarity between the target field and the corresponding fields of the building address information.

[0102] In this embodiment, a semantic analysis model is used to analyze the semantic similarity between the target field that failed to match synonyms and the corresponding field of the building address. This yields the semantic similarity between different fields, effectively solving the problem of accurately determining the semantic similarity between the target field and the corresponding field when the thesaurus does not cover them. This improves the accuracy of determining the association between user address information and corresponding building address information.

[0103] In one embodiment, as shown in Figure 4, based on synonym matching results and semantic analysis results, the association between user address information and corresponding building address information is determined, including:

[0104] The semantic analysis result is semantic similarity.

[0105] Step S402: When the synonym matching result is successful, the relationship between the user address information and the corresponding building address information is determined to be a synonym match.

[0106] Step S404: When the synonym matching result is a failure and the semantic similarity is greater than the threshold, the relationship between the user address information and the corresponding building address information is determined to be a semantic similarity match.

[0107] Among them, the confidence level of synonym matching is higher than that of semantic similarity matching; the priority of synonym matching is higher than that of semantic analysis.

[0108] In this embodiment, by comprehensively judging the synonym matching results and semantic analysis results of various types of fields in the standard address information and the corresponding building address information, the association between the user address information and the corresponding building address information can be determined more accurately, thereby improving the accuracy of determining the association between the user address information and the corresponding building address information.

[0109] In one embodiment, as shown in Figure 5, the above-mentioned geographic information processing method further includes:

[0110] Step S502: Based on the association between user address information and corresponding building address information, determine the electricity service data of the electricity users corresponding to each building object.

[0111] Electricity consumption data can include electricity consumption, electricity demand, and electricity consumption patterns for a specific period or all periods.

[0112] Specifically, the computer equipment compiles statistics on the user address information corresponding to each building address information, and accumulates the electricity service data corresponding to all user address information corresponding to the same building address information to obtain the electricity service data of the electricity users corresponding to each building object.

[0113] Step S504: Determine the statistical information of electricity consumption data with buildings as the main objects based on the electricity consumption data.

[0114] Among them, the statistical information on electricity consumption data is used to assist the power management system in carrying out electricity consumption management.

[0115] In this embodiment, by determining the electricity service data of electricity users corresponding to each building object based on the association between user address information and corresponding building address information, statistical information of electricity service data with buildings as the main objects is determined based on the electricity service data, thereby realizing efficient management of electricity service data with buildings as the statistical unit, avoiding the manual input and matching of user address information and building address information in traditional methods, and improving the accuracy of electricity service data statistics.

[0116] This application also provides an application scenario in which the above-mentioned geographic information processing method is applied to a scenario of statistical analysis of electricity consumption data with buildings as the main objects. Specifically, the geographic information processing method is applied in this scenario as follows:

[0117] The specific system optimization and operation method is as follows:

[0118] (1) Constructing specialized word segments for the power sector

[0119] To improve the accuracy and efficiency of matching, user addresses and building addresses need to be segmented into different semantic units, such as province, city, district, street, community, and building number. This facilitates subsequent matching and comparison. To adapt to the characteristics of the power industry, a specialized segmentation dictionary needs to be built, containing power-related terms and abbreviations, such as substation, distribution room, and high-voltage line.

[0120] (2) Extract data at the provincial, municipal, and district / community level for roads.

[0121] Based on the above steps involving specialized word segmentation in the power sector, further data at the province, city, district, neighborhood committee, and road levels are extracted from user addresses and building addresses. This data can serve as the basis for matching or as part of the matching dictionary. For example, if user addresses and building addresses are both under the same province, city, district, neighborhood committee, and road, they can be considered to have a high degree of similarity; if they are under different provinces, cities, districts, neighborhood committees, and roads, they can be considered to have a low degree of similarity.

[0122] (3) Concatenate building address data

[0123] The goal is to process the remaining strings that did not match completely after matching the user address string and the building string. Specifically, after extracting the data at the province, city, district, neighborhood committee, and road levels, the building address data needs to be concatenated into a complete string. This facilitates a complete match with the user address string, i.e., determining whether the two strings are identical. If they are identical, they are considered a complete match; otherwise, the remaining strings that did not match completely need to be processed.

[0124] (4) First-level precise matching

[0125] The purpose is to perform data matching where the building name is exactly the same as the community name and user name in the user address data. Specifically, based on a perfect match, the matching range is further narrowed down to improve the accuracy. For example, if the community name, user name, and building name in the user address are exactly the same as the building name in the building address, they can be considered a first-level exact match; similarly, if the community name, user name, and building name in the user address are exactly the same as the building name in the building address, they can also be considered a first-level exact match, as shown in Formula 1 below:

[0126] M1=(u,b)∈U×B|u n =b n or u c =b c , Formula 1

[0127] Where U is the set of user addresses, B is the set of building addresses, and u n It is the name of the community in the user's address, u c It is the username in the user address, b n It is the building name in the building address, b c M1 is the building number in the building address, and M1 is the first-level exact match set.

[0128] (5) Second-level synonym matching

[0129] The purpose is to identify situations where data is incomplete, such as the presence of abbreviations, incorrect spelling, and typos, and to perform synonym matching. The challenge here is to build a thesaurus and organize the mapping relationships between various abbreviations and incorrect spelling. Specifically, based on first-level precise matching, the matching scope is further expanded to improve the coverage. For example, if the name of the community in the user's address and the name of the building in the building address are synonyms, they can be considered as second-level synonym matches; if the user's name in the user's address and the name of the building in the building address are synonyms, they can also be considered as second-level synonym matches, as shown in Formula 2 below:

[0130] M2=(u,b)∈U×B|u n ~b n or u c ~b c , Formula 2

[0131] Where ~ represents a synonym relationship, M2 represents the second-level synonym matching set, U is the user address set, B is the building address set, and u n It is the name of the community in the user's address, u c It is the username in the user address, b n It is the building name in the building address, b c It is the building number in the building address.

[0132] (6) Three-level similarity matching

[0133] The goal is to perform a third-level matching process on data that fails to match in the first two levels of matching. This involves using the BERT model from natural language processing to calculate semantic similarity, and selecting the record with the highest similarity (greater than 0.85) for output. Specifically, based on the second-level synonym matching, deep learning technology is further utilized to improve the intelligence of the matching. For example, if the community name, user name, and building name in a user address are not completely identical or synonymous, but have high semantic similarity, they can be considered a third-level similarity match; similarly, if the user name and building name in a user address are not completely identical or synonymous, but have high semantic similarity, they can also be considered a third-level similarity match. The formula is as follows:

[0134] M3=(u,b)∈U×b|sim(u n ,b n )>0.85 or sim(u c ,b c )>0.85, formula 3

[0135] Where U is the set of user addresses, B is the set of building addresses, and sim(u n ,b n ) represents the semantic similarity calculated by the BERT model, and M3 is the three-level similarity matching set.

[0136] Based on the above steps, the association between user address information and corresponding building address information is output. Then, based on the association between user address information and corresponding building address information, the electricity service data of the electricity users corresponding to each building object is determined. Based on the electricity service data, statistical information on electricity service data with buildings as the main objects is determined, thereby achieving efficient management of electricity service data with buildings as the statistical unit. This avoids the manual input and matching of user address information and building address information in traditional methods, and improves the accuracy of electricity service data statistics.

[0137] In this embodiment, by using a professional word segmentation dictionary to semantically split the address, the basic matching conditions and dictionary are extracted to obtain the standard address information corresponding to the user address information. This enables accurate identification and standardized expression of non-standard, incomplete, inaccurate, and ambiguous user address information. Then, string comparison, thesaurus, and semantic analysis are used to match the standard address information with the building address information. Based on the matching results and semantic analysis results, the association between the user address information and the corresponding building address information is determined, thereby achieving effective identification and accurate matching of user address information and improving the accuracy of address matching.

[0138] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0139] In one embodiment, as shown in FIG6, a network data processing device is provided. This device can be a software module, a hardware module, or a combination of both, integrated into a computer device. Specifically, the device includes: an acquisition module 602, a matching module 604, and a determination module 606, wherein:

[0140] The acquisition module 602 is used to acquire user address information and identify the type of each field of the user address information; based on the field identification results, it determines the standard address information corresponding to the user address information, which is address information represented in a preset structured manner;

[0141] The matching module 604 is used to perform character matching between each field of the standard address information and the corresponding field of the building address information in the database; when the character matching fails, the reference field of the first level granularity in the fields of the standard address information is matched with the corresponding field of the building address information in the database to obtain the synonym matching result; based on the synonym matching result, the target field of the second level granularity in the reference field is semantically analyzed with the corresponding field of the building address information in the database to obtain the semantic analysis result, wherein the second level granularity is smaller than the first level granularity;

[0142] The determination module 606 is used to determine the association between user address information and corresponding building address information based on synonym matching results and semantic analysis results.

[0143] In one embodiment, the acquisition module 602 is further configured to, when the field identification result is that the user address information is incomplete, search for address information in the address database based on the identified fields, determine the corresponding related fields based on the search results, and combine and arrange the related fields and the identified fields in a preset structured manner to obtain the standard address information corresponding to the user address information.

[0144] In one embodiment, the matching module 604 is further configured to obtain a corresponding thesaurus, which contains the correspondence between each field of the address information and its corresponding synonyms; query the correspondence between the reference field and the corresponding field according to the thesaurus, and obtain the corresponding thesaurus matching result based on the thesaurus query result.

[0145] In one embodiment, the matching module 604 is further configured to perform synonym matching between the cell name field and user name field in the standard address information and the building name field in the building address information to obtain a synonym matching result, wherein the reference fields are the cell name field and user name field in the user address information; and the corresponding field in the building address information is the building name field.

[0146] In one embodiment, the matching module 604 is further configured to input the target field of the second level granularity in the reference field and the corresponding field of each building address information in the database into the semantic analysis model when the synonym matching fails, so as to obtain the semantic similarity between the target field and the corresponding field of each building address information.

[0147] In one embodiment, the determining module 606 is further configured to determine the semantic analysis result as semantic similarity; when the synonym matching result is a successful match, the relationship between the user address information and the corresponding building address information is determined to be a synonym match; when the synonym matching result is a failed match and the semantic similarity is greater than the threshold, the relationship between the user address information and the corresponding building address information is determined to be a semantic similarity match; the confidence level corresponding to the synonym match is greater than the confidence level corresponding to the semantic similarity match.

[0148] In one embodiment, the determining module 606 is further configured to determine the electricity service data of the electricity user corresponding to each building object based on the association between the user address information and the corresponding building address information; and to determine the electricity service data statistics information with the building as the main object based on the electricity service data. The electricity service data statistics information is used to assist the power management system in carrying out electricity management work.

[0149] The aforementioned geographic information processing device uses a professional word segmentation dictionary to semantically split addresses, extracting basic matching conditions and dictionaries to obtain standard address information corresponding to user address information. This enables accurate identification and standardized expression of non-standard, incomplete, inaccurate, and ambiguous user address information. Furthermore, it uses string comparison, a thesaurus, and semantic analysis to match standard address information with building address information. Based on the matching results and semantic analysis results, it determines the association between user address information and corresponding building address information, thereby achieving effective identification and accurate matching of user address information and improving the accuracy of address matching.

[0150] Specific limitations regarding the geographic information processing device can be found in the limitations of the geographic information processing method described above, and will not be repeated here. Each module in the aforementioned geographic information processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0151] In one embodiment, a computer device, which may be a server, is provided, and its internal structure is shown in Figure 7. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data such as user address information and building address information. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a geographic information processing method.

[0152] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in Figure 8. The computer device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with external terminals. Wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a geographic information processing method. The display screen of the computer device may be a liquid crystal display screen or an e-ink display screen. The input device of the computer device may be a touch layer covering the display screen, or buttons, a trackball, or a touchpad located on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0153] Those skilled in the art will understand that the structures shown in Figures 7 and 8 are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements.

[0154] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0155] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0156] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.

[0157] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0158] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0159] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A geographic information processing method, characterized in that, The method includes: acquiring user address information and identifying the type of each field of the user address information; determining the standard address information corresponding to the user address information based on the field identification results, wherein the standard address information is address information represented in a preset structured manner; performing character matching between each field of the standard address information and the corresponding fields of building address information in the database; when character matching fails, performing synonym matching between the first-level granularity reference field in the fields of the standard address information and the corresponding field of the building address information in the database to obtain a synonym matching result; and, based on the synonym matching result, matching the second-level granularity target field in the reference field with the building address information in the database. Semantic analysis is performed on the corresponding fields of the information to obtain semantic analysis results, where the second level granularity is smaller than the first level granularity. Based on the synonym matching results and the semantic analysis results, the association between the user address information and the corresponding building address information is determined. The semantic analysis results are semantic similarity. When the synonym matching result is successful, the relationship between the user address information and the corresponding building address information is determined to be synonym matching. When the synonym matching result is unsuccessful and the semantic similarity is greater than a threshold, the relationship between the user address information and the corresponding building address information is determined to be semantic similarity matching. Furthermore, the confidence level corresponding to the synonym matching is greater than the confidence level corresponding to the semantic similarity matching.

2. The method according to claim 1, characterized in that, The step of determining the standard address information corresponding to the user address information based on the field recognition result includes: when the field recognition result indicates that the user address information is incomplete, searching for address information in the address database based on the identified fields, and determining the corresponding related fields based on the search results; and combining and arranging the related fields and the identified fields according to a preset structured method to obtain the standard address information corresponding to the user address information.

3. The method according to claim 1, characterized in that, When character matching fails, the first-level granularity reference field in the standard address information is compared with the corresponding field of the building address information in the database to obtain a synonym matching result. This includes: obtaining the corresponding thesaurus, which contains the correspondence between each field of the address information and its corresponding synonyms; querying the correspondence between the reference field and the corresponding field according to the thesaurus, and obtaining the corresponding synonym matching result based on the synonym query result.

4. The method according to claim 1, characterized in that, When character matching fails, the reference field at the first level of granularity in the field of the standard address information is matched with the corresponding field of the building address information in the database to obtain a synonym matching result. This includes: the reference field being the community name field and the user name field in the user address information; the corresponding field of the building address information being the building name field; and the community name field and the user name field in the field of the standard address information being matched with the building name field in the building address information to obtain a synonym matching result.

5. The method according to claim 1, characterized in that, The step of performing semantic analysis on the target field at the second level of granularity in the reference field and the corresponding field of the building address information in the database based on the synonym matching result to obtain the semantic analysis result includes: when the synonym matching fails, inputting the target field at the second level of granularity in the reference field and the corresponding field of each building address information in the database into the semantic analysis model to obtain the semantic similarity between the target field and the corresponding field of each building address information.

6. The method according to claim 1, characterized in that, The method further includes: determining the electricity service data of electricity users corresponding to each building object based on the association between user address information and corresponding building address information; determining electricity service data statistics information with buildings as the main objects based on the electricity service data, wherein the electricity service data statistics information is used to assist the power management system in carrying out electricity management work.

7. The method according to claim 6, characterized in that, The electricity consumption data includes electricity consumption, electricity demand, and electricity consumption patterns for a certain period or all periods. The step of determining the electricity consumption data of each building object based on the correlation between user address information and corresponding building address information includes: statistically analyzing the user address information corresponding to each building address information, and accumulating the electricity consumption data corresponding to all user address information of the same building address information to obtain the electricity consumption data of each building object.

8. A geographic information processing device, characterized in that, The device includes: an acquisition module, configured to acquire user address information and identify the type of each field of the user address information; determine standard address information corresponding to the user address information based on the field identification results, wherein the standard address information is address information represented in a preset structured manner; and a matching module, configured to perform character matching between each field of the standard address information and the corresponding fields of building address information in a database; when character matching fails, perform synonym matching between the first-level granularity reference field in the fields of the standard address information and the corresponding field of the building address information in the database to obtain a synonym matching result; and, based on the synonym matching result, match the second-level granularity target field in the reference field with the building address information in the database. Semantic analysis is performed on the corresponding fields of the building address information to obtain semantic analysis results, where the second level granularity is smaller than the first level granularity. A determination module is used to determine the association between the user address information and the corresponding building address information based on the synonym matching results and the semantic analysis results. The semantic analysis results are semantic similarity. When the synonym matching result is successful, the relationship between the user address information and the corresponding building address information is determined to be a synonym match. When the synonym matching result is unsuccessful and the semantic similarity is greater than a threshold, the relationship between the user address information and the corresponding building address information is determined to be a semantic similarity match. Furthermore, the confidence level corresponding to the synonym match is greater than the confidence level corresponding to the semantic similarity match.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

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

Images