Traffic state discrimination system based on big data acquisition and analysis

Abstract

The invention belongs to the field of traffic state discrimination, relates to a big data analysis technology, is used for solving the problem that the accuracy and applicability of a traffic discrimination result cannot be improved through a refined segmentation mode in the prior art, and particularly relates to a traffic state discrimination system based on big data acquisition and analysis. Comprising a traffic road segment segmentation module, a state fusion discrimination module and a multivariate feature analysis module which are connected in sequence. The state fusion judgment module and the multivariate feature analysis module are both in communication connection with the database; according to the invention, road segment segmentation can be carried out on the traffic management area to obtain a plurality of management road segments, and then differentiation marking is carried out on the management road segments according to the position relation between the segmentation reference objects and the management road segments. Different discrimination modes are adopted to carry out traffic state discrimination on the reference road section and the conventional road section, so that the accuracy of a discrimination result can be improved, the periodic traffic state of the traffic management area is evaluated in combination with the time characteristics and the space characteristics, and the traffic state optimization efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the field of traffic state discrimination, relates to big data analysis technology, and specifically is a traffic state discrimination system based on big data collection and analysis. Background Art

[0002] Traffic state discrimination refers to judging the operating state of the current traffic system through the analysis of traffic flow characteristics, including different states such as traffic congestion and smoothness. Traffic flow characteristics include parameters such as traffic volume, speed, and density, and the changes of these parameters can directly reflect the changes of traffic states.

[0003] The invention patent with the publication number CN106056923B discloses a method for discriminating the traffic state of a road section based on a traffic scene radar. This method divides the traffic state interval based on the equivalent traffic volume as the basic parameter, so as to accurately discriminate the traffic state of the road section; the present invention avoids the problem of not considering the vehicle type and size when considering traffic flow in the traditional method, and its discrimination is more accurate and scientific, which can effectively improve the traffic passing efficiency; The invention patent with the publication number CN106846816B discloses a method for discriminating discrete traffic states based on deep learning. This method can comprehensively and truly describe the traffic state, does not require experts to participate in the selection of traffic state features, and can semi-supervised automatically realize the construction of a traffic state discrimination model; However, the above existing technologies have not refined the segmentation of the traffic state discrimination area from the perspective of road section segmentation, resulting in that the above existing technologies can only perform traffic state discrimination analysis from the overall or incompletely segmented perspective, resulting in the discrimination results being unable to reflect the traffic states of each specific road section. Based on this, the above existing technologies also do not have the function of optimizing decision-making analysis according to the discrimination results after refined segmentation, resulting in the traffic state discrimination results being only used to reflect the overall traffic passing pressure, and the application scenarios are single. Summary of the Invention

[0004] The purpose of the present invention is to provide a traffic state discrimination system based on big data collection and analysis, which is used to solve the problem that the prior art cannot improve the accuracy and applicability of traffic discrimination results through refined segmentation; The technical problem to be solved by the present invention is: how to provide a traffic state discrimination system based on big data collection and analysis that can improve the accuracy and applicability of traffic discrimination results through refined segmentation.

[0005] The purpose of the present invention can be achieved by the following technical solutions: A traffic status discrimination system based on big data collection and analysis, including a traffic section segmentation module, a status fusion discrimination module, and a multi-feature analysis module connected in sequence. The status fusion discrimination module includes a reference discrimination unit and a conventional discrimination unit. The multi-feature analysis module includes a time feature analysis unit, a space feature analysis unit, and a non-habit feature analysis unit. Both the status fusion discrimination module and the multi-feature analysis module are communicatively connected to the database; The traffic section segmentation module segments the traffic management area into several management sections, and marks the management sections as reference sections or conventional sections according to the segmentation reference objects; The status fusion discrimination module generates a discrimination period of R1 natural days, divides the complete natural days within the discrimination period into several discrimination time periods and numbers them in chronological order; The reference discrimination unit obtains the traffic flow of the reference section during the discrimination time period and marks it as traffic flow data, obtains the traffic flow discrimination value through the database, and marks the reference section with traffic flow data less than the traffic flow discrimination value as an unobstructed section; marks the reference section with traffic flow data not less than the traffic flow discrimination value as a congested section; The conventional discrimination unit calculates the average value of the driving speeds of all vehicles in the conventional section in real time and marks it as vehicle speed data, marks the ratio of the vehicle speed data to the maximum speed limit value of the conventional section as the vehicle speed evaluation value, and marks the conventional section as an unobstructed section or a congested section through the vehicle speed evaluation value; The multi-feature analysis module performs feature analysis according to the congestion discrimination results of the conventional sections and reference sections within the discrimination period.

[0006] Furthermore, the specific section segmentation process includes: extracting and marking traffic lights, elevated entrance ramps, elevated exit ramps, loop entrance ramps, and loop exit ramps in the traffic management area as segmentation reference objects, and extending and segmenting on all traffic roads intersecting with them with the segmentation reference objects as endpoints in the traffic management area to obtain several management sections. The longest segmentation distance of each management section is set to K1 meters. Mark the management section with any endpoint containing the segmentation reference object as a reference section, and mark the management section with all endpoints not containing the segmentation reference object as a conventional section.

[0007] Further, the specific process of marking a regular road section as a smooth road section or a congested road section includes: obtaining a vehicle speed evaluation range through a database, and comparing the vehicle speed evaluation value with the vehicle speed evaluation range. If there is a vehicle speed evaluation value less than the minimum boundary value of the vehicle speed evaluation range during the discrimination period, the regular road section is marked as a congested road section; otherwise, the ratio of the duration during which the vehicle speed evaluation value is within the vehicle speed evaluation range to the duration of the discrimination period during the discrimination period is marked as the vehicle speed measurement coefficient. The vehicle speed measurement threshold is obtained through the database. When the vehicle speed measurement coefficient is less than the vehicle measurement threshold, the regular road section is marked as a smooth road section, and when the vehicle speed measurement coefficient is greater than or equal to the vehicle measurement threshold, the regular road section is marked as a congested road section.

[0008] Further, at the end of the discrimination period, the time feature analysis unit marks the ratio of the number of times the congested road section is marked during the discrimination period to the number of management road sections as the congestion coefficient of the discrimination period. The congestion threshold and the congestion marking threshold are obtained through the database. The discrimination period with a congestion coefficient less than the congestion threshold is marked as a smooth marking period, and the discrimination period with a congestion coefficient not less than the congestion threshold is marked as a congestion marking period. The ratio of the number of congestion marking periods to the total number of discrimination periods within the discrimination cycle is marked as the congestion marking value. When the congestion marking value is less than the congestion marking threshold, the time feature of the traffic management area is marked as S1; when the congestion marking value is not less than the congestion marking threshold, the time feature of the traffic management area is marked as S2, and the time feature of the traffic management area is sent to the space feature analysis unit.

[0009] Further, the space feature analysis unit marks the number of times the management road section is marked as a congested road section as the spatial distribution value of the management road section, calculates the variance of the spatial distribution values of all management road sections to obtain the spatial distribution coefficient of the traffic management area, obtains the spatial distribution threshold through the database, marks the spatial feature of the traffic management area as L1 when the spatial distribution coefficient is less than the spatial distribution threshold, and marks the spatial feature of the traffic management area as L2 when the spatial distribution coefficient is not less than the spatial distribution threshold.

[0010] Further, it is determined whether the periodic traffic state of the traffic management area meets the requirements through the time feature and the spatial feature: if the time feature of the traffic management area is S1, it is determined that the periodic traffic state of the traffic management area meets the requirements; if the time feature and the spatial feature of the traffic management area are S2 and L1 respectively, it is determined that the periodic traffic state of the traffic management area does not meet the requirements, a system optimization signal is generated and the system optimization signal is sent to the mobile terminal of the management personnel; if the time feature and the spatial feature of the traffic management area are S2 and L2 respectively, it is determined that the local traffic state of the traffic management area does not meet the requirements, the K2 management road sections with the largest spatial distribution value are marked as inclined road sections, and at the same time, a non-habit analysis signal is generated and the non-habit analysis signal is sent to the non-habit feature analysis unit.

[0011] Further, when receiving the non - habitual analysis signal, the non - habitual feature analysis unit analyzes the non - habitual features of the traffic management area: marks the number of times the discrimination time period with the same time period number is marked as a congestion - marked time period as the habitual analysis value of the time period number, marks the K3 time period numbers with the largest habitual analysis values as habitual numbers; marks the remaining time period numbers as non - habitual numbers, marks the number of times the management road section is marked as a congested road section within the discrimination time period corresponding to the non - habitual number as the non - habitual congestion value, marks the K4 management road sections with the largest non - habitual congestion values as inclined road sections; generates an inclined management signal and sends the inclined management signal and the inclined road sections to the mobile terminal of the management personnel.

[0012] The present invention has the following beneficial effects: Through the traffic road section segmentation module, the traffic management area can be segmented into several management road sections, and then the management road sections are differentially marked according to the positional relationship between the segmentation reference object and the management road sections. Due to geographical particularity, the traffic bearing pressure of the reference road section is generally higher than that of the conventional road section. Therefore, using different discrimination methods to respectively discriminate the traffic states of the reference road section and the conventional road section can improve the accuracy of the discrimination results; Through the state fusion discrimination module, traffic state discrimination analysis can be carried out on the traffic management area. The traffic state of the reference road section is discriminated by means of vehicle flow monitoring, the traffic state of the conventional road section is discriminated by means of average vehicle speed monitoring, and at the same time, the traffic discrimination results are recorded in a periodic time - segmented monitoring manner, providing data support for the multi - feature analysis process; Through the multi - feature analysis module, feature analysis can be carried out according to the congestion discrimination results of the conventional road section and the reference road section within the discrimination period, and the periodic traffic state of the traffic management area can be evaluated by combining time features and space features, so as to carry out optimization decision - making analysis according to the evaluation results and improve the efficiency of traffic state optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0014] Figure 1 is the overall system block diagram of the present invention; Figure 2 is the schematic diagram of road section segmentation of the present invention; Figure 3 is the working block diagram of the multi - feature analysis module of the present invention. Detailed implementation manners

[0015] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0016] As Figure 1 shown, a traffic state discrimination system based on big data collection and analysis includes a traffic section segmentation module, a state fusion discrimination module, and a multi-feature analysis module that are connected in sequence. The state fusion discrimination module includes a reference discrimination unit and a conventional discrimination unit. The multi-feature analysis module includes a time feature analysis unit, a space feature analysis unit, and a non-habit feature analysis unit. Both the state fusion discrimination module and the multi-feature analysis module are communicatively connected to the database.

[0017] The traffic section segmentation module is used to segment the traffic management area into several management sections. The specific section segmentation process includes: extracting and marking traffic lights, elevated entrance ramps, elevated exit ramps, loop entrance ramps, and loop exit ramps in the traffic management area as segmentation reference objects, and extending and segmenting on all traffic roads intersecting with the segmentation reference objects in the traffic management area to obtain several management sections. The longest segmentation distance of each management section is set to K1 meters. The management section with any endpoint including the segmentation reference object is marked as a reference section, and the management section with all endpoints not including the segmentation reference object is marked as a conventional section. According to the positional relationship between the segmentation reference object and the management section, the management section is differentially marked. Due to geographical particularity, the traffic carrying pressure of the reference section is generally higher than that of the conventional section. Therefore, using different discrimination methods to discriminate the traffic states of the reference section and the conventional section respectively can improve the accuracy of the discrimination results.

[0018] It should be noted that the segmentation reference object is shared by all the management sections intersecting with it. Exemplarily, such as Figure 2As shown in the figure, there is an existing viaduct G extending in parallel with the ground road D. The ground road D accesses the viaduct G through the elevated entrance ramp. The elevated entrance ramp is marked as the segmentation reference object F. After extending bidirectionally by K1 meters in the forward direction of the viaduct G with the segmentation reference object F, the first management section 1 and the second management section 2 are obtained by segmentation. After extending bidirectionally by K1 meters in the forward direction of the ground road D with the segmentation reference object F, the third management section 3 and the fourth management section 4 are obtained by segmentation; the endpoints of the obtained first management section 1, second management section 2, third management section 3, and fourth management section 4 all contain the segmentation reference object F, that is, the segmentation reference object F is shared by the first management section 1, second management section 2, third management section 3, and fourth management section 4, and the first management section 1, second management section 2, third management section 3, and fourth management section 4 are all reference sections; when the first management section 1 is extended and segmented again from the endpoint far from the segmentation reference object F to obtain the fifth management section 5, neither of the two endpoints of the fifth management section 5 contains the segmentation reference object F, that is, the fifth management section 5 is a regular section.

[0019] The traffic state fusion discrimination module is used to conduct traffic state discrimination and analysis on the traffic management area: generate a discrimination cycle with a duration of R1 natural days, where R1 is a numerical constant, and the specific value of R1 is set by the management personnel themselves; divide the complete natural days within the discrimination cycle into several discrimination time periods and number them in chronological order; During the discrimination time period, conduct traffic state discrimination and analysis on the reference section through the reference discrimination unit: obtain the traffic flow of the reference section during the discrimination time period and mark it as traffic flow data, obtain the traffic flow discrimination value through the database, and mark the reference section with traffic flow data less than the traffic flow discrimination value as an unobstructed section; mark the reference section with traffic flow data not less than the traffic flow discrimination value as a congested section; During the discrimination time period, conduct traffic state discrimination and analysis on the regular section through the regular discrimination unit: calculate the average value of the driving speeds of all vehicles within the regular section in real time and mark it as vehicle speed data, mark the ratio of the vehicle speed data to the maximum speed limit value of the regular section as the vehicle speed evaluation value, obtain the vehicle speed evaluation range through the database, and compare the vehicle speed evaluation value with the vehicle speed evaluation range: if there is a vehicle speed evaluation value less than the minimum boundary value of the vehicle speed evaluation range during the discrimination time period, then mark the regular section as a congested section; otherwise, mark the ratio of the duration during which the vehicle speed evaluation value is within the vehicle speed evaluation range to the duration of the discrimination time period as the vehicle speed measurement coefficient, obtain the vehicle speed measurement threshold through the database, mark the regular section as an unobstructed section when the vehicle speed measurement coefficient is less than the vehicle measurement threshold, and mark the regular section as a congested section when the vehicle speed measurement coefficient is greater than or equal to the vehicle measurement threshold; Perform traffic status discrimination and analysis on the traffic management area. Use the method of traffic flow monitoring to discriminate the traffic status of the reference section, and use the method of average vehicle speed monitoring to discriminate the traffic status of the regular section. At the same time, record the traffic discrimination results in the way of periodic time-segment monitoring to provide data support for the multi-feature analysis process.

[0020] The multi-feature analysis module is used to perform feature analysis according to the congestion discrimination results of the regular section and the reference section within the discrimination period.

[0021] As Figure 3 shown, the time feature analysis unit, the space feature analysis unit, and the non-habit feature analysis unit are connected for communication in sequence.

[0022] At the end of the discrimination period, analyze the time features of the traffic management area through the time feature analysis unit: Mark the ratio of the number of times the blocked section is marked during the discrimination period to the number of management sections as the congestion coefficient of the discrimination period. Obtain the congestion threshold and the congestion marking threshold through the database. Mark the discrimination period with a congestion coefficient less than the congestion threshold as the smooth marking period, and mark the discrimination period with a congestion coefficient not less than the congestion threshold as the congestion marking period. Mark the ratio of the number of congestion marking periods to the total number of discrimination periods within the discrimination period as the congestion marking value. When the congestion marking value is less than the congestion marking threshold, mark the time feature of the traffic management area as S1; when the congestion marking value is not less than the congestion marking threshold, mark the time feature of the traffic management area as S2, and send the time feature of the traffic management area to the space feature analysis unit; At the end of the discrimination period, analyze the space features of the traffic management area through the space feature analysis unit: Mark the number of times the management section is marked as a blocked section as the spatial distribution value of the management section. Calculate the variance of the spatial distribution values of all management sections to obtain the spatial distribution coefficient of the traffic management area. Obtain the spatial distribution threshold through the database. When the spatial distribution coefficient is less than the spatial distribution threshold, mark the spatial feature of the traffic management area as L1, and when the spatial distribution coefficient is not less than the spatial distribution threshold, mark the spatial feature of the traffic management area as L2; If the time feature of the traffic management area is S1, it is determined that the periodic traffic status of the traffic management area meets the requirements; If the time feature and the space feature of the traffic management area are S2 and L1 respectively, it is determined that the periodic traffic status of the traffic management area does not meet the requirements, generate a system optimization signal and send the system optimization signal to the mobile terminal of the management personnel; If the time feature and the spatial feature of the traffic management area are S2 and L2 respectively, it is determined that the local traffic state of the traffic management area does not meet the requirements. The K2 management road sections with the largest spatial distribution values are marked as inclined road sections. At the same time, a non-habit analysis signal is generated and sent to the non-habit feature analysis unit; At the end of the discrimination period, the non-habit features of the traffic management area are analyzed by the non-habit feature analysis unit: the number of times the discrimination time periods with the same time period number are marked as blocked marked time periods is marked as the habit analysis value of the time period number, and the K3 time period numbers with the largest habit analysis values are marked as habitual numbers; the remaining time period numbers are marked as non-habitual numbers, and the number of times the management road sections are marked as blocked road sections during the discrimination time periods corresponding to the non-habitual numbers is marked as the non-habit block value, and the K4 management road sections with the largest non-habit block values are marked as inclined road sections; it should be noted that K1, K2, K3, and K4 are all numerical constants, and the specific values of K1, K2, K3, and K4 are set by the management personnel themselves; an inclined management signal is generated and the inclined management signal and the inclined road sections are sent to the mobile terminal of the management personnel; according to the congestion discrimination results of the conventional road sections and the reference road sections during the discrimination period, feature analysis is carried out, and the periodic traffic state of the traffic management area is evaluated by combining the time feature and the spatial feature, so as to carry out optimization decision-making analysis according to the evaluation results and improve the traffic state optimization efficiency.

[0023] A traffic state discrimination system based on big data collection and analysis, when working, divides the traffic management area into several management road sections, marks the management road sections as reference road sections or conventional road sections, generates a discrimination period with a duration of R1 natural days, divides the complete natural days within the discrimination period into several discrimination time periods and numbers them in chronological order, and conducts traffic state discrimination analysis on the reference road sections through the reference discrimination unit and marks the reference road sections as blocked road sections or unblocked road sections; conducts traffic state discrimination analysis on the conventional road sections through the conventional discrimination unit and marks the conventional road sections as blocked road sections or unblocked road sections; according to the congestion discrimination results of the conventional road sections and the reference road sections during the discrimination period, feature analysis is carried out, and the periodic traffic state of the traffic management area is evaluated by combining the time feature and the spatial feature, so as to carry out optimization decision-making analysis according to the evaluation results and improve the traffic state optimization efficiency.

[0024] The above content is only an example and explanation of the structure of the present invention. Those skilled in the art of this technology make various modifications or supplements to the described specific embodiments or use similar methods to replace them. As long as they do not deviate from the structure of the invention or exceed the scope defined by this claim book, they should all belong to the protection scope of the present invention.

[0025] In the description of this specification, the descriptions referring to the terms "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0026] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only the specific embodiments. Obviously, according to the content of this specification, many modifications and changes can be made. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A traffic status discrimination system based on big data collection and analysis, characterized in that, It includes a traffic section segmentation module, a state fusion discrimination module, and a multi - feature analysis module connected in sequence. The state fusion discrimination module includes a reference discrimination unit and a conventional discrimination unit. The multi - feature analysis module includes a time - feature analysis unit, a space - feature analysis unit, and an unconventional - feature analysis unit. Both the state fusion discrimination module and the multi - feature analysis module are communicatively connected to the database; The traffic section segmentation module segments the traffic management area into several management sections, and marks the management sections as reference sections or conventional sections according to the segmentation reference objects; The state fusion discrimination module generates a discrimination period of R1 natural days, divides the complete natural days within the discrimination period into several discrimination time periods and numbers them in chronological order; The reference discrimination unit obtains the traffic flow of the reference section during the discrimination time period and marks it as traffic flow data, obtains the traffic flow discrimination value through the database, and marks the reference section with traffic flow data less than the traffic flow discrimination value as a smooth section; Marks the reference section with traffic flow data not less than the traffic flow discrimination value as a congested section; The conventional discrimination unit calculates the average value of the driving speeds of all vehicles in the conventional section in real - time and marks it as vehicle speed data, marks the ratio of the vehicle speed data to the maximum speed limit value of the conventional section as the vehicle speed evaluation value, and marks the conventional section as a smooth section or a congested section through the vehicle speed evaluation value; The multi - feature analysis module conducts feature analysis based on the congestion discrimination results of the conventional sections and reference sections within the discrimination period.

2. The traffic state discrimination system based on big data collection and analysis according to claim 1, characterized in that, The specific section segmentation process includes: extracting and marking traffic lights, elevated - road entrance ramps, elevated - road exit ramps, loop - road entrance ramps, and loop - road exit ramps in the traffic management area as segmentation reference objects, extending and segmenting on all traffic roads intersecting with them with the segmentation reference objects as endpoints in the traffic management area to obtain several management sections. The maximum segmentation distance of each management section is set to K1 meters. Mark the management section with any endpoint containing a segmentation reference object as a reference section, and mark the management sections with all endpoints not containing segmentation reference objects as conventional sections.

3. The traffic state discrimination system based on big data collection and analysis according to claim 2, characterized in that, The specific process of marking the conventional section as a smooth section or a congested section includes: obtaining the vehicle speed evaluation range through the database, and comparing the vehicle speed evaluation value with the vehicle speed evaluation range. If there is a vehicle speed evaluation value less than the minimum boundary value of the vehicle speed evaluation range during the discrimination time period, mark the conventional section as a congested section; otherwise, mark the ratio of the duration of the vehicle speed evaluation value within the vehicle speed evaluation range to the duration of the discrimination time period during the discrimination time period as the vehicle speed measurement coefficient. Obtain the vehicle speed measurement threshold through the database. When the vehicle speed measurement coefficient is less than the vehicle measurement threshold, mark the conventional section as a smooth section; when the vehicle speed measurement coefficient is greater than or equal to the vehicle measurement threshold, mark the conventional section as a congested section.

4. The traffic state discrimination system based on big data collection and analysis according to claim 3, characterized in that, The time feature analysis unit, at the end of the discrimination period, marks the ratio of the number of times the blocked road sections in the discrimination period to the number of management road sections as the congestion coefficient of the discrimination period. It obtains the congestion threshold and the congestion marking threshold through the database. It marks the discrimination period with a congestion coefficient less than the congestion threshold as the unblocked marking period, marks the discrimination period with a congestion coefficient not less than the congestion threshold as the blocked marking period, and marks the ratio of the number of blocked marking periods to the total number of discrimination periods in the discrimination cycle as the blocked marking value. When the blocked marking value is less than the blocked marking threshold, it marks the time feature of the traffic management area as S1; when the blocked marking value is not less than the blocked marking threshold, it marks the time feature of the traffic management area as S2, and sends the time feature of the traffic management area to the space feature analysis unit.

5. The traffic state discrimination system based on big data collection and analysis according to claim 4, characterized in that The space feature analysis unit marks the number of times the management road sections are marked as blocked road sections as the spatial distribution value of the management road sections, calculates the variance of the spatial distribution values of all management road sections to obtain the spatial distribution coefficient of the traffic management area, obtains the spatial distribution threshold through the database, marks the spatial feature of the traffic management area as L1 when the spatial distribution coefficient is less than the spatial distribution threshold, and marks the spatial feature of the traffic management area as L2 when the spatial distribution coefficient is not less than the spatial distribution threshold.

6. The traffic state discrimination system based on big data collection and analysis according to claim 5, characterized in that It determines whether the periodic traffic state of the traffic management area meets the requirements through the time feature and the spatial feature: If the time feature of the traffic management area is S1, it determines that the periodic traffic state of the traffic management area meets the requirements; if the time feature and the spatial feature of the traffic management area are S2 and L1 respectively, it determines that the periodic traffic state of the traffic management area does not meet the requirements, generates a system optimization signal and sends the system optimization signal to the mobile terminal of the management personnel; if the time feature and the spatial feature of the traffic management area are S2 and L2 respectively, it determines that the local traffic state of the traffic management area does not meet the requirements, marks the K2 management road sections with the largest spatial distribution value as the inclined road sections, and at the same time generates a non-habit analysis signal and sends the non-habit analysis signal to the non-habit feature analysis unit.

7. The traffic state discrimination system based on big data collection and analysis according to claim 6, characterized in that The non-habit feature analysis unit, when receiving the non-habit analysis signal, analyzes the non-habit feature of the traffic management area: It marks the number of times the discrimination periods with the same period number are marked as blocked marking periods as the habit analysis value of the period number, and marks the K3 period numbers with the largest habit analysis value as the habitual numbers; it marks the remaining period numbers as non-habitual numbers, marks the number of times the management road sections are marked as blocked road sections in the discrimination periods corresponding to the non-habitual numbers as the non-habitual congestion value, and marks the K4 management road sections with the largest non-habitual congestion value as the inclined road sections; It generates an inclined management signal and sends the inclined management signal and the inclined road sections to the mobile terminal of the management personnel.

Images