Data fusion method and system based on multi-source heterogeneous geographic information data

Abstract

The invention relates to the technical field of geographic information data fusion, in particular to a data fusion method and system based on multi-source heterogeneous geographic information data, and the method comprises the steps: obtaining a source data set and a to-be-updated data set of the geographic information data, and carrying out the same-name entity matching according to the geometric features of road entities in the two data sets, fusing all data information of unmatched road entities in the source data set into the to-be-updated data set to obtain a second generation to-be-updated data set; fusing the common part and the difference part of the numerical data of the two road entities in the same-name road entities to obtain a third-generation to-be-updated data set; and performing fusion according to the similarity of the character type data of the two road entities in the same-name road entities to obtain a final fusion data set. The method aims at fusing the geometric features and the attribute features of the geographic information data, so that the fused data set information is richer and more comprehensive.

Description

Technical Field

[0001] The present application relates to the technical field of geographic information data fusion, and in particular to a data fusion method and system based on multi-source heterogeneous geographic information data. Background Art

[0002] Due to the different requirements for geographic information data in different scenarios and tasks, different standards are used in the collection process of geographic information data in the same area, resulting in differences in semantic information, data structure and expression of the collected data. When this information needs to be used, due to the large amount of original data and poor compatibility, there is too much redundant and repeated information in the data set, which is not conducive to the rapid and effective use of these geographic information data. In order to improve data quality, it is necessary to fuse these multi-source heterogeneous geographic information data to improve the use effect of multi-source heterogeneous geographic information data.

[0003] Different geographic information data have differences in data accuracy, collection indicators, data stratification, etc., and the difficulty of multi-source data fusion lies in the integration of differences between data, including differences in data foundation, spatial location and data structure. The essence of data fusion is to retain different data and eliminate duplicate data. Current research mainly focuses on one aspect of geographic information data fusion, usually only processing geometric features or attribute features, and rarely considering the fusion of these two types of features at the same time. Moreover, when the geometric features and attribute features are fused at the same time, the accuracy of data fusion is generally low. Summary of the invention

[0004] In view of the above, it is necessary to provide a data fusion method and system based on multi-source heterogeneous geographic information data to solve the above problems.

[0005] The first aspect of the present application provides a data fusion method based on multi-source heterogeneous geographic information data, the method comprising: Obtain two multivariate heterogeneous geographic information datasets to be fused, use any one of the datasets as the source dataset, and the other dataset as the dataset to be updated; According to the similarity of the location distribution characteristics of the road data in the two data sets, several pairs of road entities with the same name are obtained; the road data of the non-road entities with the same name in the source data set are added to the data set to be updated, so as to obtain the second generation data set to be updated; For numerical data, the source data set is merged with the second generation data set to be updated based on the acquisition time of the road data to obtain the third generation data set to be updated; For character data, the similarity between the character data of the road entities with the same name is obtained based on the character data features of each pair of road entities with the same name in the source data set and the third-generation data set to be updated; the character data in the two data sets are fused based on the similarity to obtain the final fused data set.

[0006] The process of obtaining a plurality of pairs of road entities with the same name is as follows: Scale the road data in the two datasets to the same scale, and map the scaled road data to the same rectangular coordinate system when the orientation is consistent; The data points in the rectangular coordinate system are segmented to obtain a road entity; a vector composed of equally spaced points of the road entity in the rectangular coordinate system is used as a position vector of the road entity; Based on the distance measurement between the position vectors, the road entities in the source data set are matched with the road entities in the data set to be updated; a road entity in the source data set and the road entity in the data set to be updated that matches it form a pair of road entities with the same name in the two data sets.

[0007] Wherein, the step of obtaining the road entity is: The points where at least two roads pass through are regarded as road nodes, the road nodes are used as segmentation points to segment the roads, and each segmented road is regarded as a road entity.

[0008] The matching of the road entities of the source data set with the road entities of the data set to be updated is specifically as follows: The position vector in the to-be-updated data set with the position vector of each road entity in the source data set having the smallest distance metric and the distance metric being less than a preset value is used as a matching entity for each road entity in the source data set.

[0009] The third generation of the to-be-updated data set is obtained as follows: For each pair of road entities with the same name in the source data set and the second-generation data set to be updated, for each value type, the value of the latest acquisition time in the source data set and the second-generation data set to be updated is retained to obtain a new data set to be updated; for each pair of road entities with the same name, the value type and the corresponding value are added to the new data set to be updated to obtain the third-generation data set to be updated.

[0010] The similarity between the character data of the road entities with the same name is obtained as follows: According to the similar features between the character data of the same-named road entities in the source dataset and the third-generation dataset to be updated, the weight adjustment factor between the character data is obtained; Based on the weight adjustment factor between the character data, a scaling factor between the character data is obtained; For each pair of road entities with the same name, the i-th character data of the road entity in the source dataset is recorded as , the jth character data of the road entity of the third generation of the updated data set is recorded as ,Will and The similarity is recorded as , its formula form is: ;in, express and The edit distance of Indicates the preset common prefix character length; express and The scaling factor between Among them, if and If the length of the common prefix character between is greater than the first preset value, the preset common prefix character length is equal to the first preset value; otherwise, and The common prefix character length between is used as the preset common prefix character length.

[0011] The process of obtaining the weight adjustment factor between character data is specifically as follows: For each pair of road entities with the same name, the ratio of the length of the common prefix character of the i-th character data of the road entity in the source data set and the j-th character data of the road entity in the third-generation data set to be updated to the sum of the corresponding character lengths is obtained as the weight adjustment factor between the i-th character data of the road entity in the source data set and the j-th character data of the road entity in the third-generation data set to be updated.

[0012] The scaling factor between the character data is specifically a value obtained by scaling the weight adjustment factor to a preset range.

[0013] The final fusion data set is obtained as follows: If there is character data in the road entities of the third-generation dataset to be updated whose similarity with the character data of the road entities in the source dataset in each pair of road entities with the same name is greater than a second preset value, the corresponding character data in the source dataset is discarded; otherwise, the character data corresponding to the road entities in the source dataset are added to the third-generation dataset to be updated to obtain the final fused dataset.

[0014] In the second aspect, an embodiment of the present application also provides a data fusion system based on multi-source heterogeneous geographic information data, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above methods are implemented.

[0015] In the above scheme, firstly, several pairs of road entities with the same name are obtained according to the geometric features of the road entities in the two geographic information data sets to be fused; and all data information of the road entities in the source data set that are not road entities with the same name are merged into the data set to be updated to obtain the second generation of data sets to be updated; its beneficial effect is to find out the geographic information data of the same road entity in the two data sets to be fused, and supplement the road data of the data set to be updated based on the road data of the source data set; merge the numerical data of the two road entities in the road entities with the same name according to the commonalities and differences, and obtain the third generation of data sets to be updated; its beneficial effect is to update the numerical data of the same type of road entities with the same name to the latest data according to the acquisition time, and integrate the numerical data of different types; merge the character data of the two road entities in the road entities with the same name according to the similarity, and obtain the final fused new data set. This geographic information data fusion method not only merges the geometric features of geographic information data, but also integrates the attribute features, so that the information of the merged data set is richer and more comprehensive, and improves the accuracy of the data after the fusion of the geometric features and attribute features of multi-source heterogeneous geographic information data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a data fusion method based on multi-source heterogeneous geographic information data provided by an embodiment of the present application; Figure 2 A flowchart for obtaining road entities with the same name provided for one embodiment of the present application. DETAILED DESCRIPTION

[0017] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0019] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of protection of the present application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0021] The following is a detailed description of a data fusion method and system based on multi-source heterogeneous geographic information data provided by the present application with reference to the accompanying drawings.

[0022] See also Figure 1 , which shows a flowchart of a data fusion method based on multi-source heterogeneous geographic information data provided by an embodiment of the present application, the method comprising the following steps: The first step is to obtain two multivariate heterogeneous geographic information datasets to be fused, and use any one of the datasets as the source dataset and the other dataset as the dataset to be updated.

[0023] Two multi-source heterogeneous geographic information datasets of a certain city area with different sources and formats at different times are obtained from the Geographic Information System (GIS). One of the multi-source heterogeneous geographic information datasets is selected as the source dataset, and the other is selected as the dataset to be updated. The sources of geographic information data include map data, satellite remote sensing data, ground measurement data, and road historical maintenance data. The data formats are GML data, SHP data, and json data. The data exists in the form of vector data, which contains the geometric features and attribute features of the road network.

[0024] Since each data set contains data in various formats, the data format needs to be unified. The format converter in the spatial data conversion system FME (Feature Manipulate Engine) tool is used to convert the collected data into a unified data format and a unified coordinate system.

[0025] The second step: according to the similarity of the location distribution characteristics of the road data in the two data sets, several pairs of road entities with the same name are obtained; the road data in the source data set that are not road entities with the same name are added to the data set to be updated to obtain the second generation data set to be updated.

[0026] Geographic entities refer to indivisible units in nature, natural phenomena, and socio-economic events, with spatial and attribute characteristics. Entities with the same name refer to geographic entities that reflect the same feature or feature set in two datasets. Entities with the same name usually differ in datasets from different sources. In order to merge the repeated features of entities with the same name in two datasets, it is necessary to first match the entities with the same name to determine whether the two geographic entities in the two datasets are entities with the same name.

[0027] The purpose of geographic information data fusion in this application is to improve the efficiency of urban road management, maintenance and planning, so the main purpose is to match the road entities in the two datasets. By comparing the geometric features of the road entities in the two datasets, the road entities with similar geometric features can be regarded as entities with the same name.

[0028] In the two datasets, the geometric features of roads are presented as a crisscross linear network, which includes straight lines and curves. The road data in the two datasets are scaled to the same scale according to their scale size, and mapped in the same rectangular coordinate system with the same orientation. Points that are passed by at least two roads are regarded as road nodes; according to the road nodes in the two datasets, all roads in the rectangular coordinate system are disconnected and split into separate road segments at the road nodes, and each road segment represents a road entity.

[0029] In each road segment, starting from the road node, a point is selected every unit distance to obtain a set of coordinate points for each road segment. The position of each road segment is represented by the coordinates of a set of coordinate points in the rectangular coordinate system. For example, the position vector of road segment a can be expressed as ,in, , Represents the coordinates of the first, second and tth points in road segment a in the rectangular coordinate system. Calculate the Fréchet distance between the position vector of road segment a in the source data set and the position vectors of all road segments in the data set to be updated, and take the road entity with the smallest Fréchet distance and less than the threshold value x as the matching entity of road segment a. The two mutually matching road entities are regarded as a pair of road entities with the same name. The calculation of Fréchet distance is a well-known technology, and the specific process will not be repeated. Among them, the threshold value x is 0.5; the implementer can adjust it according to the actual situation, and this application does not limit it.

[0030] Among them, the acquisition flow chart of the road entity with the same name is as follows: Figure 2 shown.

[0031] The geometric features and attribute features of all unmatched road entities in the source dataset are added to the dataset to be updated to obtain the second generation dataset to be updated, wherein the second generation dataset to be updated includes all the features of all the road entities that can be matched and the road entities that cannot be matched in the two datasets.

[0032] It should be noted that since road entities with the same name can match each other in two different data sets, it means that both data sets contain information about the corresponding road entities, so there is no need to update the information about the corresponding road entities. If there are road entities in the source data set that cannot be matched, it means that there are no matching road entities in the data set to be updated, so it is necessary to add the corresponding road entity information to obtain the second-generation data set to be updated.

[0033] The third step: for the numerical data in the two data sets, the source data set is merged with the second generation data set to be updated based on the acquisition time of the road data to obtain the third generation data set to be updated.

[0034] In the road entities with the same name, the attribute characteristics of the two road entities include numerical data and character data. Numerical data mainly include integer, floating point and double integer, which may involve data collection time, road width, road length, speed limit and maintenance times. Character data mainly include road name, road construction type such as cement road and asphalt road, road level such as national road, provincial road, municipal road and county road, and road type such as expressway, urban road, rural road and mountain road.

[0035] When fusing the numerical data of a pair of road entities with the same name, we must first determine the commonalities and differences between the numerical data of the two road entities. Since the geographic information data of the same road entity in different data sets are acquired at different times, this application fuses the data of the same road entity according to the acquisition time, and only retains the latest data of each data type of the same road entity. For example: the road data contained in the source data set of the s pair of road entities with the same name is used To indicate that the road data contained in the road entity in the second generation of the updated data set is To represent. Among them, Indicates the name of the data type, such as "road width"; , Respectively , Data type name The specific value corresponding to and When performing data fusion, if and Contains , then the method of retaining the data of the latest collection time is adopted and to merge; if only Contains or only Contains , then or is retained in the fused data. , , The collection time is relatively late, then the fused data is . Use the fused Replace the second generation of the dataset to be updated , and obtain the third generation of data set to be updated after the numerical data is updated.

[0036] The fourth step: for the character data in the two data sets, based on the character data features of each pair of road entities with the same name in the source data set and the third-generation data set to be updated, obtain the similarity between the character data of the road entities with the same name; based on the similarity, fuse the character data in the two data sets to obtain the final fused data set.

[0037] The character data of the road entities with the same name are merged. The categories of the character data of the two road entities may be different. When using the Jaro-Winkler distance algorithm to calculate the similarity of the two character data, since the preset common prefix character length l and the scaling factor p determined based on the number of common prefix characters will affect the final similarity result, this application considers adjusting the values ​​of l and p according to the character data characteristics of the road entity. Since the character data of the road entities in this application are mainly short character data, the length of the character data generally does not exceed 6, so the value of l in this embodiment shall not exceed 2, and the value of the scaling factor p shall not exceed 0.5; the implementer can adjust it according to the actual situation.

[0038] Furthermore, it is necessary to determine the specific value of the scaling factor. The larger the scaling factor, the greater the weight of the common prefix. When calculating the similarity of character data of two entities with the same name, the longer the length of the common prefix characters of the two character data, the more similar the two character data are. At this time, a larger scaling factor p should be set to increase the weight of the common prefix. For example, "asphalt road" and "asphalt road" have two common prefix characters, expressing the same semantics, while "asphalt road" and "highway" have no common prefix characters, expressing different semantics; when both character data are short, such as "national highway" and "provincial highway", the number of common prefix characters directly determines whether the two character data are similar, so a larger scaling factor p should be set so that the common prefix occupies a larger proportion in the similarity calculation.

[0039] The character data list of the road entities in the sth pair of road entities with the same name belonging to the source dataset is expressed as ; where z represents the number of character data in the attribute features of the road entity in the source dataset, , and They represent the first, second and zth character data of the road entity in the sth pair of road entities with the same name belonging to the source dataset, such as , Similarly, the character data list of the road entities belonging to the third generation of the to-be-updated data set in the sth pair of road entities with the same name is expressed as ; where y represents the number of character data in the attribute features of the road entity, , and They represent the first, second and yth character data of the road entity in the sth pair of road entities with the same name belonging to the third generation of the updated data set. The i-th character data of the road entity in the source data set is recorded as , the jth character data of the road entity of the third generation of the updated data set is recorded as .

[0040] According to the similar characteristics of the character data between the road entities with the same name in the source dataset and the third-generation dataset to be updated, a weight adjustment factor between the character data is constructed to adjust the scaling factor of the two character data in the similarity calculation process; its formula form is: ; In the formula, express The i-th character data and The weight adjustment factor between the jth character data in The i-th character data and The length of the common prefix character of the jth character data in The i-th character data and The sum of the lengths of the j-th character data in .

[0041] It should be understood that when the length of the common prefix character between character-type data is large, it means that the length of the common prefix character of the two character-type data is long, so a larger scaling factor should be set to make the weight of the common prefix character larger; when the value of H is small, it means that the total length of the two character-type data is short, then the common prefix character is more important in the similarity measurement, so a larger scaling factor should be set to make the weight of the common prefix character larger.

[0042] Based on the weight adjustment factor, adjust the scaling factor between the corresponding character data. and The scaling factor p when calculating similarity is calculated as: ; Where p is the scaling factor; 0.1 is the initial scaling factor value; is the weight adjustment factor; The purpose is to ensure that the magnitude of p does not exceed 0.5, and the preset range of the scaling factor is [0.1, 0.5].

[0043] Further, and The similarity is recorded as , its formula form is: ;in, express and The edit distance is a known technology and will not be described in detail in this application. Indicates the preset common prefix character length; express and The scaling factor between . and If the length of the common prefix character between is greater than or equal to the first preset value, the first preset value is used as the preset common prefix character length; otherwise, and The common prefix character length between is used as the preset common prefix character length. In this embodiment, the first preset value is 2; the implementer can adjust it according to actual conditions.

[0044] If the character data and If the similarity of all character data in is greater than the second preset value, Treat as repeated character data and Abandon, the third generation of data sets to be updated remain unchanged; if the character data and If the similarity of all character data is less than or equal to the second preset value, Treat it as new character data and convert the character data Add to In this embodiment, the second preset value is 0.9, and the implementer can adjust it according to the actual situation.

[0045] Similarly, calculate the sth pair of road entities with the same name All character data in The similarity of each character data in is determined based on the size of the similarity. Should each character data in be discarded or added to In this way, the character data of the third generation of data sets to be updated are updated, and the updated data sets are used as the fourth generation of data sets to be updated. The fourth generation of data sets to be updated is obtained, in which both the numerical data and the character data of the sth pair of road entities with the same name are updated. The fourth generation of data sets to be updated is the final fusion data set.

[0046] Based on the same inventive concept as the above method, an embodiment of the present application also provides a data fusion system based on multi-source heterogeneous geographic information data, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned data fusion methods based on multi-source heterogeneous geographic information data are implemented.

[0047] In summary, the embodiment of the present application first obtains several pairs of road entities with the same name according to the geometric features of the road entities in the two geographic information data sets to be fused; and all data information of the road entities in the source data set that are not road entities with the same name are merged into the data set to be updated to obtain the second generation of the data set to be updated; its beneficial effect is to find out the geographic information data of the same road entity in the two data sets to be fused, and supplement the road data of the data set to be updated based on the road data of the source data set; merge the numerical data of the two road entities in the road entities with the same name according to the commonalities and differences, and obtain the third generation of the data set to be updated; its beneficial effect is to update the numerical data of the same type of the road entities with the same name to the latest data according to the acquisition time, and integrate the numerical data of different types; merge the character data of the two road entities in the road entities with the same name according to the similarity, and obtain the final fused new data set. This geographic information data fusion method not only merges the geometric features of the geographic information data, but also integrates the attribute features, so that the information of the merged data set is richer and more comprehensive, and improves the accuracy of the data after the fusion of the geometric features and attribute features of multi-source heterogeneous geographic information data.

[0048] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two continuous operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0049] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; the technical solutions recorded in the above embodiments are modified, or some of the technical features are replaced by equivalents, which does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A data fusion method based on multi-source heterogeneous geographic information data, characterized in that: The method comprises the following steps: Obtain two multivariate heterogeneous geographic information datasets to be fused, use any one of the datasets as the source dataset, and the other dataset as the dataset to be updated; According to the similarity of the location distribution characteristics of the road data in the two data sets, several pairs of road entities with the same name are obtained; the road data of the non-road entities with the same name in the source data set are added to the data set to be updated, so as to obtain the second generation data set to be updated; For numerical data, the source data set is merged with the second generation data set to be updated based on the acquisition time of the road data to obtain the third generation data set to be updated; For character data, the similarity between the character data of the road entities with the same name is obtained based on the character data features of each pair of road entities with the same name in the source data set and the third-generation data set to be updated; the character data in the two data sets are fused based on the similarity to obtain the final fused data set.

2. A data fusion method based on multi-source heterogeneous geographic information data as claimed in claim 1, characterized in that: The process of obtaining several pairs of road entities with the same name is as follows: Scale the road data in the two datasets to the same scale, and map the scaled road data to the same rectangular coordinate system when the orientation is consistent; The data points in the rectangular coordinate system are segmented to obtain a road entity; a vector composed of equally spaced points of the road entity in the rectangular coordinate system is used as a position vector of the road entity; Based on the distance measurement between the position vectors, the road entities in the source data set are matched with the road entities in the data set to be updated; a road entity in the source data set and the road entity in the data set to be updated that matches it form a pair of road entities with the same name in the two data sets.

3. A data fusion method based on multi-source heterogeneous geographic information data as claimed in claim 2, characterized in that: The steps of obtaining the road entity are: The points where at least two roads pass through are regarded as road nodes, the road nodes are used as segmentation points to segment the roads, and each segmented road is regarded as a road entity.

4. The data fusion method based on multi-source heterogeneous geographic information data as claimed in claim 2, characterized in that: The matching of the road entities of the source data set with the road entities of the data set to be updated is specifically as follows: The position vector in the to-be-updated data set with the position vector of each road entity in the source data set having the smallest distance metric and the distance metric being less than a preset value is used as a matching entity for each road entity in the source data set.

5. The data fusion method based on multi-source heterogeneous geographic information data according to claim 1, characterized in that: The third generation of the to-be-updated data set is obtained as follows: For each pair of road entities with the same name in the source data set and the second-generation data set to be updated, for each value type, the value of the latest acquisition time in the source data set and the second-generation data set to be updated is retained to obtain a new data set to be updated; for each pair of road entities with the same name, the value type and the corresponding value are added to the new data set to be updated to obtain the third-generation data set to be updated.

6. The data fusion method based on multi-source heterogeneous geographic information data according to claim 1, characterized in that: The similarity between the character data of the road entities with the same name is obtained, specifically: According to the similar features between the character data of the same-named road entities in the source dataset and the third-generation dataset to be updated, the weight adjustment factor between the character data is obtained; Based on the weight adjustment factor between the character data, a scaling factor between the character data is obtained; For each pair of road entities with the same name, the i-th character data of the road entity in the source dataset is recorded as , the jth character data of the road entity of the third generation of the updated data set is recorded as ,Will and The similarity is recorded as , its formula form is: ;in, express and The edit distance of Indicates the preset common prefix character length; express and The scaling factor between Among them, if and If the length of the common prefix character between is greater than the first preset value, the preset common prefix character length is equal to the first preset value; otherwise, and The common prefix character length between is used as the preset common prefix character length.

7. A data fusion method based on multi-source heterogeneous geographic information data as claimed in claim 6, characterized in that: The process of obtaining the weight adjustment factor between character data is specifically as follows: For each pair of road entities with the same name, the ratio of the length of the common prefix character of the i-th character data of the road entity in the source data set and the j-th character data of the road entity in the third-generation data set to be updated to the sum of the corresponding character lengths is obtained as the weight adjustment factor between the i-th character data of the road entity in the source data set and the j-th character data of the road entity in the third-generation data set to be updated.

8. The data fusion method based on multi-source heterogeneous geographic information data according to claim 6, characterized in that: The scaling factor between the character data is specifically to scale the weight adjustment factor to a value within a preset range.

9. The data fusion method based on multi-source heterogeneous geographic information data according to claim 1, characterized in that: The final fusion data set is obtained as follows: If there is character data in the road entities of the third-generation dataset to be updated whose similarity with the character data of the road entities in the source dataset in each pair of road entities with the same name is greater than a second preset value, the corresponding character data in the source dataset is discarded; otherwise, the character data corresponding to the road entities in the source dataset are added to the third-generation dataset to be updated to obtain the final fused dataset.

10. A data fusion system based on multi-source heterogeneous geographic information data, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images