An integrated information fusion management system for road transportation
Through the data acquisition and analysis module, the vehicle transportation time in the road transportation system is classified and the impact factor calculation is calculated, and different types of vehicles are distinguished, which solves the problem of large error in the transportation time estimate in the existing system and improves the accuracy of transportation management .
Patent Information
- Application Number
- CN202410673590.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-28
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-05-28
AI Technical Summary
The existing integrated road transport information integration management system estimates transportation time due to factors such as weather and traffic jams, which reduces the accuracy of management.
The data acquisition module is used to obtain the vehicle's transportation time and driving speed. The data analysis module divides the transportation time into normal and abnormal clusters. The weather impact factor of each marked vehicle is calculated, and the weather marking vehicle, congestion marking vehicle and reference vehicle are distinguished. , thereby optimizing transportation time estimates and management.
It improves the accuracy of vehicle driving speed change analysis and transportation time distinction, improves the accuracy of transportation time estimates and the accuracy of road transport integrated information fusion management.
Smart Images

Figure CN118552105B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of logistics transportation vehicle data management, and in particular to a road transportation integrated information fusion management system. Background Art
[0002] Integrated road transport information fusion management refers to a comprehensive management model that uses information technology and data fusion technology to integrate, manage and utilize various information resources in the field of road transport to achieve efficient operation, intelligent monitoring and optimized management of the transportation system. That is, by estimating the time used for transportation within a certain distance, the transportation plan is arranged to optimize vehicle scheduling and route planning to improve transportation efficiency.
[0003] When conventionally estimating the transportation time of a road section, the transportation plan is arranged by taking the average value of all the transportation times in the historical data of the road section as a reference for the estimated transportation time; however, in the actual transportation process, the transportation time is affected by weather and traffic jams, so the estimated transportation time obtained by conventional methods has a large error and is not accurate enough, which reduces the accuracy of integrated road transportation information fusion management. Summary of the invention
[0004] The present invention provides a road transport integrated information fusion management system to solve the existing problems.
[0005] A road transport integrated information fusion management system of the present invention adopts the following technical solution:
[0006] An embodiment of the present invention provides a road transport integrated information fusion management system, which includes the following modules:
[0007] A data acquisition module is used to obtain the transportation time of all vehicles and the driving speed of each vehicle at several spatial locations;
[0008] The data analysis module is used to divide the transportation time of all vehicles into normal clusters and abnormal clusters, record the vehicles corresponding to the time in the abnormal clusters as marked vehicles, obtain the driving speed sequence of each marked vehicle, obtain the speed similarity between each marked vehicle and all other marked vehicles based on the correlation between the driving speed sequences of each marked vehicle and other marked vehicles, and obtain the possibility that each marked vehicle is a vehicle traveling under the influence of weather based on the distribution of data in the driving speed sequence of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles;
[0009] The influence factor calculation module is used to obtain the time interval when each marked vehicle passes through two adjacent spatial positions, and obtain the weather influence factor of each marked vehicle according to the stability of the elements in the driving speed sequence of each marked vehicle, the time interval when each marked vehicle passes through two adjacent spatial positions, and the possibility that each marked vehicle is a vehicle traveling under the influence of weather.
[0010] The transportation management module is used to carry out integrated information fusion management of road transportation based on normal clusters and weather influencing factors of each marked vehicle.
[0011] Furthermore, the transportation time of all vehicles is divided into normal clusters and abnormal clusters, including:
[0012] The minimum and maximum data in the time series are selected as the two initial cluster centers, and the transportation time of all vehicles is clustered by the K-means clustering algorithm to obtain two clusters;
[0013] The mean of all data in each cluster is calculated, and the cluster with the smallest mean among the two clusters is recorded as a normal cluster, and the cluster with the largest mean among the two clusters is recorded as an abnormal cluster.
[0014] Furthermore, the step of obtaining the driving speed sequence of each marked vehicle includes:
[0015] According to the order in which the freight vehicles encounter spatial positions during their travel, the travel speeds of each marked vehicle at all spatial positions are sorted to form a set of sequences, which are recorded as the travel speed sequence of each marked vehicle.
[0016] Furthermore, the speed similarity between each marked vehicle and all other marked vehicles is obtained based on the correlation between the driving speed sequences of each marked vehicle and other marked vehicles, including:
[0017] The average of the correlation coefficients between the driving speed sequence of each marked vehicle and the driving speed sequences of all other marked vehicles is recorded as the first value of each marked vehicle; the speed similarity between each marked vehicle and all other marked vehicles is obtained according to the first value of each marked vehicle, wherein the first value of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles are positively correlated.
[0018] Furthermore, the possibility of each marked vehicle being a vehicle traveling under the influence of weather is obtained according to the distribution of data in the driving speed sequence of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles, including:
[0019] According to the information entropy of the data in the driving speed sequence of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles, the possibility of each marked vehicle being a vehicle driving under the influence of weather is obtained;
[0020] Among them, the information entropy of the data in the driving speed sequence of each marked vehicle is positively correlated with the possibility that each marked vehicle is a vehicle traveling under the influence of weather; the speed similarity between each marked vehicle and all other marked vehicles is positively correlated with the possibility that each marked vehicle is a vehicle traveling under the influence of weather.
[0021] Furthermore, the method for obtaining the element stability is:
[0022] The slope between two adjacent data in the driving speed sequence of each marked vehicle is obtained, and the absolute value of the slope is negatively correlated and averaged to obtain the element stability.
[0023] Furthermore, the weather influence factor of each marked vehicle is obtained according to the stability of the elements in the driving speed sequence of each marked vehicle, the time interval when each marked vehicle passes through two adjacent spatial positions, and the possibility that each marked vehicle is a vehicle driving under the influence of weather, including:
[0024] The time intervals when each marked vehicle passes through two adjacent spatial positions are counted to obtain the time difference between adjacent time intervals; the overall time difference is obtained according to the cumulative sum of all time differences; the weather influence factor of each marked vehicle is obtained according to the stability of the elements in the driving speed sequence of each marked vehicle, the overall time difference, and the possibility that each marked vehicle is a vehicle traveling under the influence of weather;
[0025] Among them, there is a positive correlation between the stability of the elements in the driving speed sequence of each marked vehicle and the weather influencing factor of each marked vehicle, a negative correlation between the overall time difference of each marked vehicle and the weather influencing factor of each marked vehicle, and a positive correlation between the possibility that each marked vehicle is a vehicle traveling under the influence of weather and the weather influencing factor of each marked vehicle.
[0026] Furthermore, the integrated road transport information fusion management is performed according to the normal cluster and the weather impact factor of each marked vehicle, including:
[0027] Differentiate weather-marked vehicles, congestion-marked vehicles, and reference vehicles based on the normal cluster and the weather impact factor of each marked vehicle;
[0028] Integrated road transport information fusion management is carried out through the transportation times corresponding to weather-tagged vehicles, congestion-tagged vehicles and reference vehicles.
[0029] Furthermore, the method of distinguishing weather marked vehicles, congestion marked vehicles and reference vehicles according to the normal cluster and the weather impact factor of each marked vehicle includes:
[0030] All marked vehicles whose weather impact factors are greater than the preset threshold ε are recorded as weather marked vehicles; all marked vehicles whose weather impact factors are less than or equal to the preset threshold ε are recorded as congestion marked vehicles; and the vehicles corresponding to the time in the normal cluster are recorded as reference vehicles.
[0031] Furthermore, the integrated road transport information fusion management is performed by using the transport times corresponding to the weather-marked vehicles, the congestion-marked vehicles and the reference vehicles, including:
[0032] Select any route for transporting goods and record it as the analysis route; record the average time of all reference vehicles passing through the analysis route as the first reference time, record the average time of all weather-marked vehicles passing through the analysis route as the second reference time, and record the average time of all congestion-marked vehicles passing through the analysis route as the third reference time;
[0033] The transportation time of the vehicle in each case corresponding to the transportation process of the analyzed route is estimated by using the first reference time, the second reference time and the third reference time;
[0034] By analyzing the process of obtaining the transportation reference time on the route, all the transportation reference times on other routes can be obtained, and the transportation plan can be arranged according to the transportation reference time on all routes.
[0035] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains the speed similarity between each marked vehicle and all other marked vehicles based on the correlation between the driving speed sequences of each marked vehicle and other marked vehicles, obtains the possibility that each marked vehicle is a vehicle traveling under the influence of weather based on the distribution of data in the driving speed sequence of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles, and improves the accuracy of analyzing the change in vehicle driving speed through the possibility that each marked vehicle is a vehicle traveling under the influence of weather; obtains the weather influence factor of each marked vehicle based on the stability of elements in the driving speed sequence of each marked vehicle, the time interval when each marked vehicle passes through two adjacent spatial positions, and the possibility that each marked vehicle is a vehicle traveling under the influence of weather, and improves the accuracy of distinguishing vehicle transportation time under different situations through the weather influence factor of each marked vehicle; and performs integrated road transportation information fusion management based on normal clusters and the weather influence factor of each marked vehicle, thereby improving the accuracy of transportation time estimation and the accuracy of integrated road transportation information fusion management. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0037] Figure 1 A module flow chart of a road transport integrated information fusion management system of the present invention;
[0038] Figure 2 This is a flow chart for integrated information fusion management of road transport. DETAILED DESCRIPTION
[0039] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, features and effects of a road transport integrated information fusion management system proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0040] 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 invention belongs.
[0041] The specific scheme of a road transport integrated information fusion management system provided by the present invention is described in detail below with reference to the accompanying drawings.
[0042] See also Figure 1 , which shows a module flow chart of a road transport integrated information fusion management system provided by an embodiment of the present invention, the system includes the following modules:
[0043] Module 101: Data acquisition module.
[0044] It should be noted that in the process of transporting goods, due to factors such as weather or congestion, the transportation time used for transportation on the same road is different. Therefore, in order to analyze the degree of interference for different situations, it is necessary to collect the time required for all vehicles to pass through the road section and the speed at each location in the road section for subsequent analysis.
[0045] Specifically, select any route for transporting goods and record it as the analysis route; obtain the time required for all vehicles to pass through the analysis route within a month and record it as the transportation time of all vehicles. On the analysis route, obtain several spatial positions at intervals of 500 meters; install a speed sensor on each vehicle and obtain the driving speed of a vehicle every 500 meters; that is, the driving speed of each spatial position.
[0046] At this point, the transportation time of all vehicles and the driving speed of all vehicles corresponding to each spatial position are obtained.
[0047] Module 102: Data analysis module.
[0048] It should be noted that, when there is no weather influence and traffic jam interference, the time required for each vehicle to pass the analysis route is relatively short; when affected by weather and traffic jam interference, the time required for each vehicle to pass the analysis route is relatively long; therefore, the analysis is performed based on the time required for all vehicles to pass the analysis route.
[0049] It should be further explained that, since the vehicle driving times under normal circumstances and those under weather influences and congestion interference are different and there are certain differences between them, the vehicle driving times under normal circumstances and the vehicle driving times under influences and interferences can be analyzed based on the differences between the data in the time series.
[0050] Specifically, the minimum data and the maximum data in the time series are selected as two initial clustering centers, and the transportation time of all vehicles is clustered by the K-means clustering algorithm to obtain two clusters; wherein, the K-means clustering algorithm is a well-known technology and will not be described in detail here.
[0051] The mean of all data in each cluster is calculated, and the cluster with the smallest mean among the two clusters is recorded as a normal cluster, and the cluster with the largest mean among the two clusters is recorded as an abnormal cluster.
[0052] At this point, normal clusters and abnormal clusters are obtained.
[0053] It should be noted that in rainy and snowy days, truck drivers generally drive at low speeds throughout the analysis route to prevent tires from slipping, thereby ensuring safety. In normal weather, during peak traffic periods such as holidays, trucks may experience congestion during driving. When there is congestion without weather impact, it is usually in a specific section of the road rather than throughout the entire analysis route. Therefore, when the weather is normal and there is congestion, the truck's driving speed is sometimes fast and sometimes slow, that is, the truck's speed is unstable.
[0054] It should be further explained that, in rainy, snowy or foggy days, the speed of freight trucks is low and relatively stable; while during the peak period of vehicles on holidays, the speed of freight trucks is sometimes fast and sometimes slow, that is, the corresponding speed of freight trucks is unstable. There is a certain positive correlation between the speeds of all vehicles on the analysis route corresponding to rainy, snowy or foggy days, while there is generally no correlation between the speeds of all vehicles on the analysis route corresponding to the peak period of vehicles on holidays. Therefore, analysis can be performed based on the correlation between the speeds of all vehicles on the analysis route.
[0055] Specifically, the driving speed corresponding to each marked vehicle at all spatial positions is obtained, and the driving speeds of each marked vehicle at all spatial positions are sorted according to the order in which the freight vehicle encounters the spatial positions during its driving process to form a set of sequences, which are recorded as the driving speed sequence of each marked vehicle.
[0056] The vehicles corresponding to the time in the abnormal cluster are recorded as marked vehicles, and the driving speed sequence of all marked vehicles is obtained; based on the correlation between the driving speed sequence of each marked vehicle and the driving speed sequence of all other marked vehicles, the speed similarity between each marked vehicle and all other marked vehicles is obtained. As an embodiment, the specific calculation method is: the mean of the correlation coefficient between the driving speed sequence of each marked vehicle and the driving speed sequence of all other marked vehicles is recorded as the first value of each marked vehicle; the speed similarity between each marked vehicle and all other marked vehicles is obtained based on the first value of each marked vehicle, wherein the first value of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles are positively correlated. It is specifically expressed as:
[0057]
[0058] Where, X i,j represents the correlation coefficient between the speed sequence of the i-th marked vehicle and the speed sequence of the j-th marked vehicle, n represents the number of all marked vehicles, Q i represents the speed similarity between the i-th marked vehicle and all other marked vehicles, and norm() represents a linear normalization function. The correlation coefficient between the two driving speed sequences is obtained by the Pearson correlation coefficient; the Pearson correlation coefficient is a well-known technology and will not be described in detail here.
[0059] Among them, the greater the speed similarity between each marked vehicle and all other marked vehicles, the greater the possibility that the marked vehicle is the vehicle corresponding to rainy or snowy days; conversely, the smaller the speed similarity between each marked vehicle and all other marked vehicles, the greater the possibility that the marked vehicle is the vehicle corresponding to the holiday peak.
[0060] At this point, the speed similarity between each marked vehicle and all other marked vehicles is obtained.
[0061] It should be noted that, because when the vehicle is driving steadily, the difference between the driving speeds corresponding to all its spatial positions is small, that is, the distribution of the driving speeds corresponding to all spatial positions is relatively concentrated. Therefore, the information entropy of the driving speeds of all spatial positions of each vehicle can be used to further determine which situation each marked vehicle belongs to.
[0062] It should be further explained that, in the above-mentioned similarity analysis process, the higher the similarity corresponding to the slow and stable marked vehicle, that is, when analyzing the information entropy of the driving speeds of all spatial positions of the marked vehicles corresponding to rainy and snowy days, the similarity is used as the weight of the information entropy for analysis.
[0063] Specifically, according to the information entropy of the data in the driving speed sequence of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles, the possibility of each marked vehicle being a vehicle traveling under the influence of weather is obtained. As an embodiment, the specific calculation method is: according to the information entropy of the data in the driving speed sequence of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles, the possibility of each marked vehicle being a vehicle traveling under the influence of weather is obtained; wherein, the information entropy of the data in the driving speed sequence of each marked vehicle and the possibility of each marked vehicle being a vehicle traveling under the influence of weather are positively correlated; the speed similarity between each marked vehicle and all other marked vehicles and the possibility of each marked vehicle being a vehicle traveling under the influence of weather are positively correlated. Specifically, it is expressed as:
[0064] W i =Q i ×exp(-E i )
[0065] In the formula, Q i Indicates the speed similarity between the i-th marked vehicle and all other marked vehicles, E i represents the information entropy of the data in the driving speed sequence of the i-th marked vehicle, W i It represents the possibility that the i-th marked vehicle is a vehicle traveling under the influence of weather, and exp() represents an exponential function with a natural constant as the base.
[0066] Among them, when the information entropy of the data in the driving speed sequence of each marked vehicle is smaller, it means that the data in the driving speed sequence of the marked vehicle is more concentrated, that is, the driving speed of the vehicle is more stable, and the possibility that each marked vehicle is a vehicle traveling under the influence of weather is greater; conversely, it means that the data in the driving speed sequence of the marked vehicle is more dispersed, that is, the driving speed of the vehicle is more unstable, and the possibility that each marked vehicle is a vehicle traveling under the influence of weather is smaller. i ×exp(-E i ) i The information entropy is used as the weight for analysis, that is, the greater the speed similarity between each marked vehicle and all other marked vehicles, the greater the possibility that each marked vehicle is a vehicle traveling under the influence of weather; conversely, the smaller the possibility that each marked vehicle is a vehicle traveling under the influence of weather.
[0067] At this point, the possibility that each marked vehicle is a vehicle traveling under the influence of weather is obtained.
[0068] Module 103: Impact factor calculation module.
[0069] It should be noted that due to the different goods transported by freight vehicles, the corresponding speeds in different situations are also different. That is, when a truck is pulling heavier goods, its driving speed will be lower. Moreover, due to the reduction in speed, the driving speed of the truck on holidays is relatively stable compared to that of a truck carrying lighter goods. Therefore, this situation may make the driving speed of the truck similar to that under the influence of rainy and snowy weather. Although there is a certain similarity, the speed difference between adjacent spatial positions also reduces the similarity between the driving speed of heavy goods in the above situation and the driving speed of the truck under the influence of weather.
[0070] Specifically, in this embodiment, the data in the driving speed sequence of each marked vehicle are marked with serial numbers in order, and a reference coordinate system is constructed with the serial number of the data in the driving speed sequence as the horizontal axis and the driving speed of the truck as the vertical axis. The data in the driving speed sequence of each marked vehicle is mapped in the reference coordinate system, so as to characterize the stability of the elements in the driving speed sequence by the slope of the data points corresponding to two adjacent serial numbers. The slope between two adjacent data in the driving speed sequence of each marked vehicle is obtained, and the absolute value of the slope is negatively correlated and averaged to obtain the stability of the element. As an embodiment, the specific calculation formula is:
[0071]
[0072] In the formula, k i,r,r+1represents the slope between the rth data and the r+1th data in the speed sequence of the i-th marked vehicle, || is the absolute value symbol, tanh() represents the hyperbolic tangent function, m represents the number of all spatial positions on the analysis route, and U i Indicates the stability of the elements in the driving speed sequence of the i-th marked vehicle.
[0073] Among them, when the absolute value of the slope between two adjacent data in the driving speed sequence of each marked vehicle is smaller, it means that the difference between the two data is smaller, which means that the data in the driving speed sequence of the marked vehicle is more stable; otherwise, it means that the data in the driving speed sequence of the marked vehicle is more unstable.
[0074] This means that the marked vehicle is more likely to be driven under the influence of weather, that is, the weather influence factor of each marked vehicle is larger; conversely, the weather influence factor of each marked vehicle is smaller.
[0075] Obtain the time interval when each marked vehicle passes through two adjacent spatial positions; obtain the time difference between adjacent time intervals; and obtain the overall time difference based on the cumulative sum of all time differences. As an embodiment, the specific calculation formula is:
[0076]
[0077] Where, T i,s,s+1 represents the time interval between the i-th marked vehicle passing the s-th spatial position and the s+1-th spatial position, T i,s,s-1 represents the time interval between the i-th marked vehicle passing the s-th spatial position and the s-1-th spatial position, m represents the number of all spatial positions on the analysis route, || is the absolute value symbol, exp() represents the exponential function with a natural constant as the base, and R i represents the overall time difference of the i-th marked vehicle.
[0078] Among them, when the difference between adjacent time intervals between spatial positions is smaller, it means that the overall time difference is smaller; when the difference between adjacent time intervals between spatial positions is larger, it means that the overall time difference is larger.
[0079] According to the stability of the elements in the driving speed sequence of each marked vehicle, the overall time difference, and the possibility that each marked vehicle is a vehicle traveling under the influence of weather, the weather influence factor of each marked vehicle is obtained. Among them, there is a positive correlation between the stability of the elements in the driving speed sequence of each marked vehicle and the weather influence factor of each marked vehicle, a negative correlation between the overall time difference of each marked vehicle and the weather influence factor of each marked vehicle, and a positive correlation between the possibility that each marked vehicle is a vehicle traveling under the influence of weather and the weather influence factor of each marked vehicle. As an embodiment, the specific calculation formula is:
[0080] P i =U i ×exp(-R i )×W i
[0081] Where U i Indicates the stability of the elements in the driving speed sequence of the i-th marked vehicle, R i represents the overall time difference of the i-th marked vehicle, W i represents the possibility that the i-th marked vehicle is a vehicle traveling under the influence of weather, exp() represents an exponential function with a natural constant as the base, P i Represents the weather impact factor of the i-th marked vehicle.
[0082] Among them, when the data in the driving speed sequence of each marked vehicle is more stable, it means that the marked vehicle is more likely to be driven under the influence of weather, that is, the weather impact factor of each marked vehicle is larger; otherwise, the weather impact factor of each marked vehicle is smaller. When the overall time difference of each marked vehicle is smaller, it means that the possibility of the freight vehicle running smoothly is greater, which means that the marked vehicle is more likely to be driven under the influence of weather, that is, the weather impact factor of each marked vehicle is larger; otherwise, the weather impact factor of each marked vehicle is smaller. When the possibility of each marked vehicle being a vehicle driving under the influence of weather is greater, the weather impact factor of each marked vehicle is larger, otherwise, the weather impact factor of each marked vehicle is smaller.
[0083] At this point, the weather impact factor of each marked vehicle is obtained.
[0084] A threshold ε is preset, wherein this embodiment is described by taking ε=0.5 as an example, and this embodiment is not specifically limited, wherein ε may be determined according to specific implementation conditions.
[0085] All marked vehicles whose weather impact factors are greater than a preset threshold ε are recorded as weather marked vehicles; all marked vehicles whose weather impact factors are less than or equal to the preset threshold ε are recorded as congestion marked vehicles.
[0086] The vehicle corresponding to the time in the normal cluster is recorded as the reference vehicle.
[0087] So far, we have obtained the reference vehicles corresponding to normal weather and no congestion, the weather-marked vehicles affected by the weather, and the congestion-marked vehicles in congested conditions.
[0088] Module 104: Transportation management module.
[0089] The mean time taken by all reference vehicles to pass through the analysis route is recorded as the first reference time, the mean time taken by all weather-marked vehicles to pass through the analysis route is recorded as the second reference time, and the mean time taken by all congestion-marked vehicles to pass through the analysis route is recorded as the third reference time.
[0090] The transportation time of the vehicle in each case corresponding to the transportation process of the analyzed route is estimated by using the first reference time, the second reference time and the third reference time;
[0091] According to the process of analyzing the route to obtain the transportation reference time, all the transportation reference times on other routes can be obtained, and the transportation plan can be arranged according to the transportation reference time on all routes, so as to complete the management of road transportation information. Among them, the road transportation integrated information fusion management flow chart is as follows Figure 2 shown.
[0092] It should be noted that the exp(-x) model used in this embodiment is only used to indicate that the negative correlation and the result of the constraint model output are in the interval (0,1). In specific implementation, it can be replaced with other models with the same purpose. This embodiment only uses the exp(-x) model as an example for description without making specific limitations on it, where x refers to the input of the model.
[0093] At this point, this embodiment is completed.
[0094] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A road transport integrated information fusion management system, characterized in that: The system includes the following modules: A data acquisition module is used to obtain the transportation time of all vehicles and the driving speed of each vehicle at several spatial locations; The data analysis module is used to divide the transportation time of all vehicles into normal clusters and abnormal clusters, record the vehicles corresponding to the time in the abnormal clusters as marked vehicles, obtain the driving speed sequence of each marked vehicle, obtain the speed similarity between each marked vehicle and all other marked vehicles based on the correlation between the driving speed sequences of each marked vehicle and other marked vehicles, and obtain the possibility that each marked vehicle is a vehicle traveling under the influence of weather based on the distribution of data in the driving speed sequence of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles; The influence factor calculation module is used to obtain the time interval when each marked vehicle passes through two adjacent spatial positions, and obtain the weather influence factor of each marked vehicle according to the stability of the elements in the driving speed sequence of each marked vehicle, the time interval when each marked vehicle passes through two adjacent spatial positions, and the possibility that each marked vehicle is a vehicle traveling under the influence of weather. The transport management module is used to integrate the information management of road transport according to the normal cluster and the weather influencing factors of each marked vehicle; The method for obtaining the element stability is: The slope between two adjacent data in the driving speed sequence of each marked vehicle is obtained, and the absolute value of the slope is negatively correlated and averaged to obtain the element stability.
2. According to claim 1, a road transport integrated information fusion management system is characterized in that: The transportation time of all vehicles is divided into normal clusters and abnormal clusters, including: The minimum and maximum data in the time series are selected as the two initial cluster centers, and the transportation time of all vehicles is clustered by the K-means clustering algorithm to obtain two clusters; The mean of all data in each cluster is calculated, and the cluster with the smallest mean among the two clusters is recorded as a normal cluster, and the cluster with the largest mean among the two clusters is recorded as an abnormal cluster.
3. The road transport integrated information fusion management system according to claim 1, characterized in that: The step of obtaining the driving speed sequence of each marked vehicle comprises: According to the order in which the freight vehicles encounter spatial positions during their travel, the travel speeds of each marked vehicle at all spatial positions are sorted to form a set of sequences, which are recorded as the travel speed sequence of each marked vehicle.
4. The road transport integrated information fusion management system according to claim 1, characterized in that: The method of obtaining the speed similarity between each marked vehicle and all other marked vehicles according to the correlation between the driving speed sequences of each marked vehicle and other marked vehicles includes: The average of the correlation coefficients between the driving speed sequence of each marked vehicle and the driving speed sequences of all other marked vehicles is recorded as the first value of each marked vehicle; the speed similarity between each marked vehicle and all other marked vehicles is obtained according to the first value of each marked vehicle, wherein the first value of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles are positively correlated.
5. The road transport integrated information fusion management system according to claim 1, characterized in that: The method of obtaining the possibility that each marked vehicle is a vehicle traveling under the influence of weather according to the distribution of the data in the driving speed sequence of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles includes: According to the information entropy of the data in the driving speed sequence of each marked vehicle and the speed similarity between each marked vehicle and all other marked vehicles, the possibility of each marked vehicle being a vehicle driving under the influence of weather is obtained; Among them, the information entropy of the data in the driving speed sequence of each marked vehicle is positively correlated with the possibility that each marked vehicle is a vehicle traveling under the influence of weather; the speed similarity between each marked vehicle and all other marked vehicles is positively correlated with the possibility that each marked vehicle is a vehicle traveling under the influence of weather.
6. The road transport integrated information fusion management system according to claim 1, characterized in that: The weather influence factor of each marked vehicle is obtained according to the stability of the elements in the driving speed sequence of each marked vehicle, the time interval when each marked vehicle passes through two adjacent spatial positions, and the possibility that each marked vehicle is a vehicle driving under the influence of weather, including: The time intervals when each marked vehicle passes through two adjacent spatial positions are counted to obtain the time difference between adjacent time intervals; the overall time difference is obtained according to the cumulative sum of all time differences; the weather influence factor of each marked vehicle is obtained according to the stability of the elements in the driving speed sequence of each marked vehicle, the overall time difference, and the possibility that each marked vehicle is a vehicle traveling under the influence of weather; Among them, there is a positive correlation between the stability of the elements in the driving speed sequence of each marked vehicle and the weather influencing factor of each marked vehicle, a negative correlation between the overall time difference of each marked vehicle and the weather influencing factor of each marked vehicle, and a positive correlation between the possibility that each marked vehicle is a vehicle traveling under the influence of weather and the weather influencing factor of each marked vehicle.
7. The road transport integrated information fusion management system according to claim 1, characterized in that: The integrated information fusion management of road transport according to the normal cluster and the weather influencing factor of each marked vehicle includes: Differentiate weather-marked vehicles, congestion-marked vehicles, and reference vehicles based on the normal cluster and the weather impact factor of each marked vehicle; Integrated road transport information fusion management is carried out through the transportation times corresponding to weather-tagged vehicles, congestion-tagged vehicles and reference vehicles.
8. A road transport integrated information fusion management system according to claim 7, characterized in that: The method of distinguishing weather marked vehicles, congestion marked vehicles and reference vehicles according to the normal cluster and the weather impact factor of each marked vehicle includes: All marked vehicles whose weather impact factors are greater than the preset threshold ε are recorded as weather marked vehicles; all marked vehicles whose weather impact factors are less than or equal to the preset threshold ε are recorded as congestion marked vehicles; and the vehicles corresponding to the time in the normal cluster are recorded as reference vehicles.
9. The road transport integrated information fusion management system according to claim 7, characterized in that: The integrated road transport information fusion management is performed by using the transport times corresponding to the weather-marked vehicles, the congestion-marked vehicles and the reference vehicles, including: Select any route for transporting goods and record it as the analysis route; record the average time of all reference vehicles passing through the analysis route as the first reference time, record the average time of all weather-marked vehicles passing through the analysis route as the second reference time, and record the average time of all congestion-marked vehicles passing through the analysis route as the third reference time; The transportation time of the vehicle in each case corresponding to the transportation process of the analyzed route is estimated by using the first reference time, the second reference time and the third reference time; According to the process of obtaining the transportation reference time on the analyzed route, all the transportation reference times on other routes are obtained, and the transportation plan is arranged according to the transportation reference time on all routes.
Citation Information
Patent Citations
Calculating method for journey time on basis of soft set
CN108922191A
Driving time estimation method and system
CN109377758A
Vehicle service system based on cloud computing and data analysis
CN112071061A
Expressway pavement abnormity monitoring method and system
CN115762155A
Intelligent traffic management system based on big data
CN117251722A
