Congestion data fusion method based on Internet map

Abstract

The invention discloses a fusion method based on Internet map congestion data. The fusion method comprises the following steps: acquiring congestion data according to different Internet map companies; performing parameter data cleaning on the acquired congestion data to obtain cleaned data; respectively inputting one piece of congestion data and one piece of corresponding cleaned data into a fusion algorithm according to a sequence, and judging until a repeatedly congested road section is obtained; and fusing the repeatedly congested road sections to obtain a fusion result. According to the invention, multi-party navigation map congestion data can be fused, false information is eliminated, and a standardized congestion road condition result is identified and output in real time.

Description

Technical Field

[0001] The present invention belongs to the technical field of data fusion, and in particular relates to a fusion method based on Internet map congestion data. Background Art

[0002] At present, traffic management departments need to use the congestion data of Internet maps to carry out traffic condition perception, abnormal event detection and other tasks. Internet maps obtain information such as congestion location, time, speed, distance, etc. based on the floating car data of their navigation users. The mainstream Internet maps include Baidu, AutoNavi, Tencent and other maps, which have different floating car users, and thus the congestion information is also different. The congestion information output by a single navigation map is prone to errors with the actual road conditions. Most of the existing technologies are congestion perception and prediction methods, which analyze the road traffic conditions based on floating car data, GPS trajectory data, video surveillance data, sensor data, etc., and obtain traffic congestion conditions. Congestion is often determined based on only one data source, and multiple data sources are not integrated and verified. The data sources are independent of each other, resulting in large congestion identification errors. At the same time, different data sources are identified separately, resulting in repeated warnings of congestion events, and there is a waste of congestion monitoring and disposal resources. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a fusion method based on Internet map congestion data, which can fuse the congestion data of multiple navigation maps, eliminate false information, and identify and output standardized congested road conditions in real time.

[0004] To achieve the above object, the present invention provides a fusion method based on Internet map congestion data, including: obtaining congestion data according to different Internet map companies;

[0005] Perform parameter data cleaning on the acquired congestion data to obtain cleaned data;

[0006] Inputting the congestion data and the corresponding cleaned data into the fusion algorithm in order, and making a judgment until a repeated congested road section is obtained;

[0007] The repeated congested road sections are merged to obtain a fusion result.

[0008] Optionally, obtaining congestion data includes:

[0009] Obtain data through relevant service interfaces of Internet map companies or by crawling maps.

[0010] Optionally, the parameters include but are not limited to a unified city code, a province code, a coordinate system type, a congestion level, and congestion levels of different intervals representing congested road sections.

[0011] Optionally, inputting one of the congestion data and a corresponding one of the cleaned data into a fusion algorithm in order to determine whether they are the same congested road section until a repeated congested road section is obtained includes:

[0012] At the beginning, data source B is empty, and the first data extracted from data source A is directly stored in data source B; wherein data source A is a congestion information data source that aggregates various Internet maps, and data source B is a fusion table;

[0013] Continue to extract one line from the data source A, and match it with the data from the data source B one by one to determine whether they are the same congested road section;

[0014] If it is the same congested road section, it is further determined whether to replace and update the existing data in data source B, or not store it in data source B;

[0015] If they are not the same congested road section, they are directly stored in the data source B.

[0016] Optionally, merging the repeated congested road sections includes:

[0017] String concatenation is performed on the repeated congested road sections to obtain a fusion result.

[0018] Optionally, the data input into the fusion algorithm also includes any two congestion data, and further determines whether the any two congestion data are for the same congested road section.

[0019] Optionally, determining whether any two pieces of congestion data are for the same congested road section includes:

[0020] A piece of data is extracted from the congestion information data source that aggregates various Internet maps, and a piece of data is extracted from the fusion table. The data extracted from the congestion information data source are judged with all the data in the fusion table in turn, and the data extracted from the congestion information data source that does not meet the judgment conditions is stored in the fusion table. A piece of data is continuously extracted from the congestion information data source and judged with all the data in the fusion table, wherein a piece of data extracted from the congestion information data source is recorded as congested route A, and a piece of data extracted from the fusion table is recorded as congested route B;

[0021] Determine the city dimensions where the congested route A and the congested route B are located respectively;

[0022] Performing position-related judgment on the congested route A and the congested route B in the same city;

[0023] Determine the starting point distance of the congested route A and the congested route B that are related to the directions;

[0024] For the congested route A and the congested route B whose starting point distance is not greater than a preset distance, a longitude and latitude sequence arranged in sequence according to the starting and ending points is constructed, and a curve segment function corresponding to the sequence is further constructed;

[0025] Determining whether the congested route A and the congested route B intersect according to the constructed corresponding curve segment function;

[0026] Calculating the length of the corresponding curve segment for the intersecting congested route A and the congested route B;

[0027] If the curve segment length of the congested route B is greater than that of the congested route A, the data fields in the fusion table are updated based on the newly input data, and the event IDs of the two data sources are concatenated based on the event ID;

[0028] If the curve segment length of the congested route B is not greater than that of the congested route A, the event IDs are string concatenated.

[0029] Optionally, judging whether the congested route A and the congested route B intersect according to the constructed corresponding curve segment function includes:

[0030] In space, if the congested route A and the congested route B are located in the same section, there will be a line segment intersection;

[0031] If the congested route A and the congested route B do not intersect, it is determined that the two congested routes are only in the same spatial area but do not belong to the same road section.

[0032] Technical effect of the invention: The invention discloses a fusion method based on Internet map congestion data, which can fuse the congestion data of multiple navigation maps, eliminate false information, identify and output standardized congested road conditions in real time, and provide the traffic management department of the public security organ with highly accurate and reliable road condition information, solving the problem of needing to connect to different navigation maps and make manual judgments, and congestion is difficult to accurately identify. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0034] Figure 1 It is a flow chart of a method for integrating Internet map congestion data according to an embodiment of the present invention;

[0035] Figure 2 A schematic diagram of a process of determining whether two pieces of congestion data in the same data source are from the same road section according to an embodiment of the present invention;

[0036] Figure 3The figure is a flow chart of determining whether any two pieces of congestion data are from the same road section and merging and updating them in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0038] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] like Figure 1 As shown, this embodiment provides a fusion method based on Internet map congestion data, including:

[0040] Obtain congestion data from different Internet mapping companies;

[0041] Perform parameter data cleaning on the acquired congestion data to obtain cleaned data;

[0042] Input a piece of congestion data and a corresponding piece of cleaned data into the fusion algorithm in order, and make a judgment until a repeated congested road section is obtained;

[0043] The repeated congested road sections are fused to obtain the fusion results.

[0044] Furthermore, obtaining congestion data includes:

[0045] Obtain data through relevant service interfaces of Internet map companies or by crawling maps.

[0046] Optionally, the parameters include but are not limited to a unified city code, a province code, a coordinate system type, a congestion level, and congestion levels of different intervals representing congested road sections.

[0047] Further, such as Figure 2 As shown, a congestion data and a corresponding cleaned data are input into the fusion algorithm in order to determine whether they are the same congested road section until a repeated congested road section is obtained, including:

[0048] At the beginning, data source B is empty, and the first data extracted from data source A is directly stored in data source B; wherein data source A is a congestion information data source that aggregates various Internet maps, and data source B is a fusion table;

[0049] Continue to extract one line from the data source A, and match it with the data from the data source B one by one to determine whether they are the same congested road section;

[0050] If it is the same congested road section, it is further determined whether to replace and update the existing data in data source B, or not store it in data source B;

[0051] If they are not the same congested road section, they are directly stored in the data source B.

[0052] Furthermore, the fusion of repeated congested sections includes:

[0053] Perform string concatenation on repeated congested road sections to obtain fusion results.

[0054] Specifically, the data is fused and stored. Specifically, when it is calculated that two congestion data belong to the same road section, the string is concatenated according to the event ID. For example, the event ID of event A is BD_YD01, and the event ID of event B is GD_02. The event ID after the string concatenation can be concatenated into BD_YD01&GD_02. The function of this is that the next time the congestion data is obtained, it can be judged according to its event ID whether it is the same event as the fused data calculated in the previous period, so as to update the congestion information of the event in time.

[0055] Furthermore, the data input into the fusion algorithm also includes any two congestion data, and further determines whether the any two congestion data are for the same congested road section.

[0056] Further, such as Figure 3 The method for determining whether any two pieces of congestion data are of the same congested road section includes:

[0057] A piece of data is extracted from the congestion information data source that aggregates various Internet maps, and a piece of data is extracted from the fusion table. The data extracted from the congestion information data source are judged with all the data in the fusion table in turn, and the data extracted from the congestion information data source that does not meet the judgment conditions is stored in the fusion table. A piece of data is continuously extracted from the congestion information data source and judged with all the data in the fusion table, wherein a piece of data extracted from the congestion information data source is recorded as congested route A, and a piece of data extracted from the fusion table is recorded as congested route B;

[0058] Determine the city dimensions of congested route A and congested route B respectively;

[0059] Make position-related judgments on congested routes A and B in the same city;

[0060] Determine the starting point distance of the congested route A and the congested route B related to the location;

[0061] For the congested routes A and B whose starting point distance is not greater than the preset distance, a longitude and latitude sequence arranged in the order of starting and ending points is constructed, and a curve segment function corresponding to the sequence is further constructed;

[0062] Determine whether the congested route A and the congested route B intersect according to the corresponding constructed curve segment function;

[0063] Calculate the length of the corresponding curve segment for the intersecting congested routes A and B;

[0064] If the curve segment length of congested route B is greater than that of congested route A, the data fields in the fusion table are updated based on the newly input data, and the event IDs of the two data sources are concatenated based on the event ID;

[0065] If the curve segment length of the congested line B is not greater than that of the congested line A, the event IDs are string concatenated.

[0066] Specifically, city judgment mainly relies on the citycode field of congestion data. By judging whether the values ​​are the same, it is determined whether they belong to the same city. If they do not belong to the same city, the two data must not belong to the same congested section, so they can be directly stored in the fused data table. If they belong to the same city, further calculations are carried out. For orientation correlation judgment, specifically, for different Internet map companies, congestion data all contain orientation fields, but the expressions are different. For example, Baidu expresses it as east to west, but Gaode may express it as southeast to northwest. To this end, it is necessary to construct the following related data calculation table 1.

[0067] Table 1

[0068]

[0069] According to the corresponding table of the above directions and related directions, calculate whether the directions are consistent. If the two data are not related, it can be judged that they do not belong to the same section, and the related data can be directly stored in the fusion table. If the directions of the two data are related, further calculation is required.

[0070] Starting point distance judgment is used to determine whether two congestion data are close in space. The reason why road names and other information are not used for judgment here is that different Internet map companies have inconsistent ways of expressing road names on the same road section. For this reason, it is necessary to directly use the spatial distance of the congestion starting point to determine whether they are located in the same spatial area. If the starting point distance is greater than 500 meters, it is considered that the two data do not belong to the same area in space, and they are directly stored in the fusion table. If the starting point distance is less than 500 meters, the congestion information expressed by the two data is in the same spatial area, and there is a possibility that they belong to the same road section, and further fusion calculation is required.

[0071] Construct a longitude and latitude sequence that can be arranged in the order of starting and ending points. The specific implementation logic is as follows. At present, the congestion data provided by Internet map companies contains two fields, location and link_state. The location field is the starting point coordinates, and link_state is the congestion level represented by the longitude and latitude strings of different intervals in the congestion data. The sample data is as follows (sample data, because the sample size is too large, only a small part of the data is retained as an example):

[0072] #point1:

[0073] #location_point='116.776473,27.874752'

[0074] #linkstate="{

[0075] '4':'116.776492,27.873715,116.776476,27.874258;116.776485,27.873455,116.776492,27.873715;

[0076] '3':'116.776476,27.874258,116.776476,27.874293;116.776476,27.874293,116.776473,27.874752116.773969,27.863493,

[0077] '2':

[0078] '116.776437,27.876609,116.776473,27.874752;116.776388,27.879654,116.776401,27.878965;116.776388,27.879828,116.776388,27.879654;

[0079] }"

[0080] In the above example, the core data in the link_state field is in dictionary format, which contains three levels of congestion intervals including "4", "3" and "2". Each interval is composed of a longitude and latitude coordinate string, and ";" in the coordinate string represents other unconnected intervals with the same congestion level. Therefore, although the link_state field can project congested sections on the map, its data is a discontinuous coordinate string, lacking a continuous longitude and latitude coordinate string from the starting point to the end point. To this end, a continuous longitude and latitude trajectory must be calculated for further fusion calculations in the lower part.

[0081] The function of the curve segment representing the sequence is constructed by constructing a curve segment function fitting the coordinate string according to the calculated longitude and latitude coordinate string of the start and end points. The function mentioned here can be a specific fitting curve equation, or it can be directly represented by a data object representing the curve segment calculated based on the longitude and latitude.

[0082] Judging whether the congested route A and the congested route B intersect according to the constructed corresponding curve segment function includes: in space, if the congested route A and the congested route B are located in the same section, then the line segments intersect; if the congested route A and the congested route B do not intersect, then it is determined that the two congested routes are only in the same spatial area, but do not belong to the same section.

[0083] The length of each curve segment constructed based on the two data sources is calculated. In order to further integrate the congestion data of two roads on the same section, the length of the curve segment needs to be calculated for the lower calculation.

[0084] Based on the length of the curve segment, the data items to be updated are determined. By comparing the lengths of two curve segments, the shortest congestion data is taken, which represents the congestion data obtained from the Internet map company, the congestion on a certain road segment, and the minimum length. The shortest congestion data is taken here to improve the overall availability of congestion data. After determining the shortest curve segment, the different field information corresponding to the curve segment is updated into the fusion table, and the event ID is concatenated as a string.

[0085] The present invention discloses a fusion method based on Internet map congestion data, which can fuse the congestion data of multiple navigation maps, eliminate false information, identify and output standardized congested road condition results in real time, and provide the traffic management department of the public security agency with highly accurate and reliable road condition information, solving the problem of needing to connect to different navigation maps and make manual judgments, and difficulty in accurately identifying congestion.

[0086] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A fusion method based on Internet map congestion data, characterized in that: include: Obtain congestion data from different Internet mapping companies; Perform parameter data cleaning on the acquired congestion data to obtain cleaned data; Inputting one of the congestion data and the corresponding one of the cleaned data into the fusion algorithm in order, and making a judgment until a repeated congested road section is obtained; The repeated congested road sections are merged to obtain a fusion result.

2. The method for merging Internet map congestion data according to claim 1, characterized in that: Obtaining congestion data includes: Obtain data through relevant service interfaces of Internet map companies or by crawling data from maps.

3. The method for merging Internet map congestion data according to claim 1, characterized in that: The parameters include but are not limited to a unified city code, a province code, a coordinate system type, a congestion level, and congestion levels of different intervals representing congested road sections.

4. The method for merging Internet map congestion data according to claim 1, characterized in that: Inputting the congestion data and the corresponding cleaned data into the fusion algorithm in order to determine whether they are the same congested road section until a repeated congested road section is obtained includes: At the beginning, data source B is empty, and the first data extracted from data source A is directly stored in data source B; wherein data source A is a congestion information data source that aggregates various Internet maps, and data source B is a fusion table; Continue to extract one line from the data source A, and match it with the data from the data source B one by one to determine whether they are the same congested road section; If it is the same congested road section, it is further determined whether to replace and update the existing data in data source B, or not store it in data source B; If they are not the same congested road section, they are directly stored in the data source B.

5. The method for merging Internet map congestion data according to claim 1, characterized in that: Merging the repeated congested road sections includes: String concatenation is performed on the repeated congested road sections to obtain a fusion result.

6. The method for merging Internet map congestion data according to claim 1, characterized in that: The data input into the fusion algorithm also includes any two congestion data, and further determines whether the any two congestion data are for the same congested road section.

7. The method for merging Internet map congestion data according to claim 6, characterized in that: Determining whether any two congestion data are for the same congested road section includes: A piece of data is extracted from the congestion information data source that aggregates various Internet maps, and a piece of data is extracted from the fusion table. The data extracted from the congestion information data source are judged with all the data in the fusion table in turn, and the data extracted from the congestion information data source that does not meet the judgment conditions is stored in the fusion table. A piece of data is continuously extracted from the congestion information data source and judged with all the data in the fusion table, wherein a piece of data extracted from the congestion information data source is recorded as congested route A, and a piece of data extracted from the fusion table is recorded as congested route B; Determine the city dimensions where the congested route A and the congested route B are located respectively; Performing position-related judgment on the congested route A and the congested route B in the same city; Determine the starting point distance of the congested route A and the congested route B that are related to the directions; For the congested route A and the congested route B whose starting point distance is not greater than a preset distance, a longitude and latitude sequence arranged in sequence according to the starting and ending points is constructed, and a curve segment function corresponding to the sequence is further constructed; Determining whether the congested route A and the congested route B intersect according to the constructed corresponding curve segment function; Calculating the length of the corresponding curve segment for the intersecting congested route A and the congested route B; If the curve segment length of the congested route B is greater than that of the congested route A, the data fields in the fusion table are updated based on the newly input data, and the event IDs of the two data sources are concatenated based on the event ID; If the curve segment length of the congested route B is not greater than that of the congested route A, the event IDs are string concatenated.

8. The method for merging Internet map congestion data according to claim 7, characterized in that: Judging whether the congested route A and the congested route B intersect according to the constructed corresponding curve segment function includes: In space, if the congested route A and the congested route B are located in the same section, there will be a line segment intersection; If the congested route A and the congested route B do not intersect, it is determined that the two congested routes are only in the same spatial area but do not belong to the same road section.

Images