Method and System for Precise Highway Toll Collection Based on Analysis of Prone-to-Error Judgment Vehicle Types

Abstract

This application relates to the technical field of highway toll management, and discloses a method and system for precise highway toll collection based on the analysis of error-prone vehicle types. The method includes calculating feature vectors, calculating dispute indexes, and determining vehicle types. The system corresponds to the method. In this application, multi-source data of vehicles are collected and feature vectors are calculated, and the dynamic changes of toll collection and dispute data are analyzed in combination with time series to calculate dispute indexes, so as to capture error-prone vehicles; the vehicle information is updated to the error-prone vehicle type information database and shared, and at the same time, real-time highway data is collected and associated with the feature vectors, and the types of error-prone vehicle types are determined in combination with the driving scenario and surrounding vehicle information. Finally, the final vehicle type is determined based on the analysis of the dispute index, realizing the accuracy of vehicle type judgment, not only improving the accuracy and fairness of toll collection, but also providing a reliable basis for subsequent management and auditing, and improving the overall efficiency and quality of highway toll management.

Description

Technical Field

[0001] This application relates to the technical field of highway toll management, and specifically, to a method and system for precise highway tolling based on the analysis of error-prone vehicle types. Background Art

[0002] In the field of highway toll management, accurate vehicle type discrimination is crucial for toll collection. Currently, highway tolls for passenger cars are classified into types one to four for charging. For critical vehicle types such as eight- and nine-seat passenger cars, due to their unclear vehicle type characteristics, it is difficult to quickly and accurately determine the toll vehicle type at the toll collection site. This problem has led to many adverse consequences, frequent toll disputes, and additional disputes caused by different toll standards in different sections, greatly disturbing the traffic efficiency of highways. At the same time, handling these disputes increases the operation and management costs, reducing the economic benefits and management efficiency of highway operations.

[0003] Although existing technologies have explored vehicle identification, there are obvious deficiencies. For example, the highway non-inductive toll collection system and method based on Beidou positioning proposed in Chinese Patent Application No. CN202411913545.1 mainly focuses on vehicle identity verification and passing route review to achieve non-inductive toll collection and abnormal behavior alarm, and is not specifically designed for identifying error-prone vehicle types, making it difficult to accurately judge the toll vehicle type. For example, the vehicle identity automatic recognition method and system based on multi-source data fusion disclosed in Chinese Patent Application No. CN202411147156.2 do not emphasize using multi-source data to accurately analyze error-prone vehicle types. The data comparison may only stay on surface features and lacks the dynamics and coordination of information management. Facing complex vehicle type data, it is difficult to accurately distinguish error-prone vehicle types and update information in a timely manner, resulting in the inability to guarantee the accuracy and timeliness of toll management.

[0004] Therefore, there is an urgent need for a new technical solution for precise highway tolling based on the analysis of error-prone vehicle types to solve these problems and achieve precise highway tolling. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for precise highway tolling based on the analysis of error-prone vehicle types to solve the technical problems raised in the above background art.

[0006] To achieve the above purpose, this application discloses the following technical solutions:

[0007] In the first aspect, this application discloses a method for precise highway tolling based on the analysis of error-prone vehicle types, and the method includes the following steps:

[0008] Collect multi-source data of vehicles, fuse the multi-source data, and calculate the feature vector. The multi-source data includes basic data, management data, toll data, dispute data, internal structure feature data, and electronic system configuration data;

[0009] Combine time series analysis to analyze the dynamic changes of toll data and dispute data, calculate the dispute index of the vehicle, and use it to automatically capture vehicles prone to misjudgment;

[0010] When the dispute index reaches the preset dispute index threshold, update the vehicle information to the preset information database of vehicle types prone to misjudgment and share it; Collect real-time highway data and associate it with the feature vector, traverse the information database of vehicle types prone to misjudgment, determine the types of vehicle types prone to misjudgment in combination with the driving scenario and surrounding vehicle information, and determine the final vehicle type based on the analysis of the dispute index.

[0011] Preferably, when fusing multi-source data to calculate the feature vector, based on the preset data level, clarify the key items under each data category, and analyze the internal logical relationship between the key items; Among them, the data level is used to characterize the importance of multi-source data;

[0012] Based on the actual situation of historical vehicles and the corresponding toll dispute cases, count the occurrence frequency and mutual influence degree of each key item in different dispute situations, assign corresponding weights to each key item based on the statistical results and the internal logical relationship, and generate a feature vector based on the weights. The feature vector is used to reflect the key information related to vehicle types prone to misjudgment in multi-source data.

[0013] Preferably, when combining time series analysis to analyze the dynamic changes of toll data and dispute data to calculate the dispute index of the vehicle, arrange the toll data and the dispute data in chronological order respectively to form corresponding toll time series and dispute time series;

[0014] Calculate the fluctuation of toll vehicle types and amounts in the toll time series and the frequency of disputes and amount differences in the dispute time series, construct a dispute status classification standard, correspond the status of the vehicle in different time periods to the corresponding levels in the dispute status classification standard, and calculate the dispute index based on the proportion of the vehicle in each level of status. The dispute index is used to reflect the possibility of toll disputes of the vehicle.

[0015] Preferably, when collecting real-time highway data and associating it with the feature vector, extract the key content in the real-time highway data based on the key content in the feature vector, and generate a real-time feature corresponding to the feature vector;

[0016] Calculate the matching degree between the feature vector and the real-time feature, and adjust the determination standard of the matching degree based on the current dispute index of the vehicle. The adjustment is as follows:

[0017] When the dispute index is greater than or equal to a preset adjustment threshold, increase the judgment criterion for the matching degree; when the dispute index is less than the adjustment threshold, decrease the judgment criterion for the matching degree.

[0018] Preferably, when traversing the error-prone misjudgment vehicle type information database, sort the vehicles in the error-prone misjudgment vehicle type information database in descending order of the dispute index, start from the vehicle with the largest dispute index, and sequentially perform the associated matching of the vehicle information with the real-time highway data, count the number of matching items. When the proportion of the number of matching items to all feature numbers is greater than or equal to a preset matching degree threshold, determine that the vehicle is an error-prone misjudgment vehicle type and perform the corresponding error-prone misjudgment vehicle type analysis.

[0019] Preferably, the error-prone misjudgment vehicle type analysis includes:

[0020] Combine the driving scenario and surrounding vehicle information to determine the types of error-prone misjudgment vehicle types. Collect the driving scenario information and surrounding vehicle information of the current vehicle, integrate them, and compare them with the characteristic performances of various vehicle types in the error-prone misjudgment vehicle type information database under different scenarios. Combine the dispute index of the vehicle itself to comprehensively judge a candidate set of the types of error-prone misjudgment vehicle types, and at least two types of vehicle types that the vehicle is likely to be misjudged as are included in the candidate set.

[0021] Preferably, when determining the final vehicle type based on the dispute index analysis, list multiple attributes that affect the vehicle type judgment, count the actual occurrence frequency and toll dispute situation of each vehicle type under the historical dispute index analysis, and configure corresponding weights for each attribute;

[0022] For each candidate vehicle type, multiply the performance value of the vehicle type on each attribute by the corresponding weight and sum to obtain a comprehensive score, and select the vehicle type with the highest score as the final vehicle type.

[0023] Preferably, when the vehicle has the real-time highway data and calculates the dispute index, define the vehicles within the same time period and on the same road section on the highway as a set, take each vehicle in the set as a node, and analyze the association relationship between the vehicles to construct an association network;

[0024] Check the position of the vehicle in the association network, count the dispute index of its neighbor nodes, and correct the dispute index of the vehicle based on the vehicle position and the dispute index situation of the neighbor nodes.

[0025] Preferably, after determining the final vehicle type, adjust the confidence interval of the toll vehicle type based on the dispute index of the vehicle, record the determination process of the toll vehicle type, the applicable toll standard, and the reasons and specific ranges for the adjustment of the confidence interval and output them; among them, the adjustment of the confidence interval is:

[0026] When the dispute index is greater than a preset first confidence threshold, expand the confidence interval;

[0027] When the dispute index is less than a preset second confidence threshold, narrow the confidence interval; wherein, the second confidence threshold is less than the first confidence threshold.

[0028] In a second aspect, the present application discloses a system for accurate highway toll collection based on error-prone vehicle type analysis. This system is applicable to the method for accurate highway toll collection based on error-prone vehicle type analysis as described above. The system includes a feature vector module, a dispute index module, and a vehicle type determination module that are communicatively connected in sequence;

[0029] The feature vector module is used to collect multi-source data of the vehicle, fuse the multi-source data, and calculate the feature vector. The multi-source data includes basic data, management data, toll data, dispute data, internal structure feature data, and electronic system configuration data;

[0030] The dispute index module is used to combine time series analysis to analyze the dynamic changes of toll data and dispute data, calculate the dispute index of the vehicle, and is used to automatically capture error-prone vehicles;

[0031] The vehicle type determination module is used to update the vehicle information to a preset error-prone vehicle type information database and share it when the dispute index reaches a preset dispute index threshold; collect real-time highway data and associate it with the feature vector, traverse the error-prone vehicle type information database, combine the driving scenario and surrounding vehicle information to determine the types of error-prone vehicles, and determine the final vehicle type based on the analysis of the dispute index.

[0032] Beneficial effects: The method and system for accurate highway toll collection based on error-prone vehicle type analysis of the present application utilize the collection of multi-source data of the vehicle and calculate the feature vector, combine time series analysis to analyze the dynamic changes of toll and dispute data to calculate the dispute index, so as to capture error-prone vehicles; when the dispute index reaches the threshold, update the vehicle information to the error-prone vehicle type information database and share it. At the same time, collect real-time highway data and associate it with the feature vector, combine the driving scenario and surrounding vehicle information to determine the types of error-prone vehicles, and finally determine the final vehicle type based on the analysis of the dispute index, realizing the accuracy of highway toll collection; calculate the toll amount according to the final vehicle type and record the output process, which not only improves the accuracy and fairness of the toll collection, but also provides a reliable basis for subsequent management and auditing, and improves the overall efficiency and quality of highway toll collection management. Description of the Drawings

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application 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 drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0034] Figure 1It is a flowchart of a method for accurate highway toll collection based on error-prone vehicle type analysis provided by an embodiment of the present application;

[0035] Figure 2 It is a structural block diagram of a system for accurate highway toll collection based on error-prone vehicle type analysis provided by an embodiment of the present application. Specific embodiments

[0036] Next, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0037] In this article, the term "including" is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article, or device. Without more limitations, the elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article, or device including the said elements.

[0038] The first aspect of this embodiment discloses a method for accurate highway toll collection based on error-prone vehicle type analysis as shown in Figure 1 The method includes the following steps:

[0039] S1: Collect multi-source data of the vehicle, fuse the multi-source data, and calculate the feature vector. The multi-source data includes basic data, management data, toll data, dispute data, internal structure feature data, and electronic system configuration data;

[0040] S2: Combine time series analysis to analyze the dynamic changes of toll data and dispute data, calculate the dispute index of the vehicle and use it to automatically capture error-prone vehicles;

[0041] S3: When the dispute index reaches the preset dispute index threshold, update the vehicle information to the preset error-prone vehicle type information library and share it; collect real-time highway data and associate it with the feature vector, traverse the error-prone vehicle type information library, determine the types of error-prone vehicle types in combination with the driving scenario and surrounding vehicle information, and determine the final vehicle type based on the analysis of the dispute index.

[0042] It should be noted that the basic data of the multi-source data in this embodiment includes at least vehicle information, the management data includes at least issuance data, the toll data includes at least transaction data, and the dispute data includes at least real-time passing vehicle data, image data, and audit data.

[0043] With the above, this embodiment utilizes the multi-source data collected by the vehicle. The multi-source data covers various aspects of data such as basic, management, toll collection, disputes, internal structural characteristics, and electronic system configuration. These data are fused and the feature vectors are calculated. By combining time series analysis with the dynamic changes of toll collection and dispute data, the dispute index is calculated to capture vehicles that are prone to misjudgment. When the dispute index reaches the threshold, the vehicle information is updated to the information database of vehicles prone to misjudgment and shared. At the same time, the real-time highway data is collected and associated with the feature vectors. By combining the driving scenario and the surrounding vehicle information, the types of vehicles prone to misjudgment are determined. Finally, based on the analysis of the dispute index, the final vehicle type is determined, achieving the accuracy of highway toll collection. Calculating the toll amount according to the final vehicle type and recording the output process not only improves the accuracy and fairness of toll collection, but also provides a reliable basis for subsequent management and auditing, enhancing the overall efficiency and quality of highway toll management.

[0044] Specifically, when fusing multi-source data to calculate the feature vectors, based on the preset data levels, the key items under each data category are clarified, and the internal logical relationships between the key items are analyzed; among them, the data levels are used to represent the importance of the multi-source data;

[0045] Based on the actual situation of historical vehicles and the corresponding toll dispute cases, the occurrence frequencies and the degree of mutual influence of each key item in different dispute situations are statistically analyzed. Based on the statistical results and the internal logical relationships, corresponding weights are assigned to each key item, and the feature vectors are generated based on the weights. The feature vectors are used to reflect the key information related to the vehicles prone to misjudgment in the multi-source data.

[0046] As a preferred implementation manner of this embodiment, in the preset data levels, the multi-source data is divided into multi-source data of key items , and the corresponding weights are , then the feature vector . In a specific example, the multi-source data includes 3 key items, namely the number of vehicle seats , the number of past toll disputes , and the complexity of the electronic system configuration , and their weights are , , . If , , , then the feature vector .

[0047] With the above, this embodiment uses the preset data levels to clarify key items, analyzes their internal logical relationships, and based on historical cases, counts the occurrence frequencies and mutual influence degrees of each item in different dispute situations, assigns weights to each key item to generate a feature vector, achieving the effective integration of multi-source data. This enables the feature vector to accurately reflect the key information related to error-prone judgment vehicle models, providing a more targeted and accurate data basis for subsequent calculation of the dispute index and analysis of error-prone judgment vehicle models.

[0048] Specifically, when calculating the dispute index of a vehicle by combining the time series analysis of the dynamic changes of toll data and dispute data, the toll data and dispute data are respectively arranged in chronological order to form corresponding toll time series and dispute time series.

[0049] Calculate the fluctuations of the toll vehicle type and amount in the toll time series and the occurrence frequency and amount difference of disputes in the dispute time series, construct a dispute status classification standard, map the status of the vehicle in different time periods to the corresponding levels in the dispute status classification standard, and calculate the dispute index based on the proportion of the vehicle in each level of status. The dispute index is used to reflect the possibility of vehicle toll disputes.

[0050] As a preferred implementation manner of this embodiment, the amount fluctuation in the toll time series is collected as , the occurrence frequency of disputes in the dispute time series is , the amount difference is , the dispute status is divided into levels, the proportion of the vehicle in each level of status is , the dispute index , where is the coefficient corresponding to each level. In a specific example, there are 2 values for the amount fluctuation in the toll time series, , , the occurrence frequency of disputes in the dispute time series , the amount difference , the dispute status is divided into 3 levels, and the proportions of the vehicle in each level of status are respectively , , , the corresponding coefficients , , , then the dispute index .

[0051] With the above, in this embodiment, by arranging the toll data and dispute data in chronological order to form a time series, calculating the amount fluctuation, dispute frequency, and amount difference, constructing a standard for dividing dispute status, and calculating the dispute index based on the status proportion of each level of the vehicle, a dynamic assessment of the possibility of vehicle toll disputes is achieved. This method fully considers the time dimension and dynamic changes of the data, enabling the dispute index to more accurately reflect the actual toll dispute risk of the vehicle and providing a strong basis for automatically capturing vehicles prone to misjudgment.

[0052] Specifically, when collecting real-time highway data and associating it with the feature vector, based on the key content in the feature vector, extract the key content in the real-time highway data to generate real-time features corresponding to the feature vector.

[0053] Calculate the matching degree between the feature vector and the real-time feature, and adjust the determination standard of the matching degree based on the current dispute index of the vehicle. The adjustment is as follows:

[0054] When the dispute index is greater than or equal to the preset adjustment threshold, increase the determination standard of the matching degree; when the dispute index is less than the adjustment threshold, decrease the determination standard of the matching degree.

[0055] As a preferred implementation manner of this embodiment, calculate the matching degree between the feature vector and the real-time feature through any existing matching degree calculation method as , the preset adjustment threshold is , the original matching degree determination standard is , and the adjusted matching degree determination standard is . When the dispute index , ; when , , where and are preset adjustment amounts. In a specific example, the original matching degree determination standard , the preset adjustment threshold , , . When the dispute index of a certain vehicle , at this time, , then the adjusted matching degree determination standard ; when the dispute index of another vehicle , at this time, , then the adjusted matching degree determination standard .

[0056] With the above, this embodiment generates real-time features by extracting the key content of real-time high-speed data according to the eigenvector, calculates the matching degree, and adjusts the judgment criterion of the matching degree based on the current dispute index of the vehicle, achieving dynamic adjustment when collecting real-time high-speed data and associating with the eigenvector. It can flexibly adjust the strictness of the association according to the dispute risk of the vehicle, improve the accuracy of data association, avoid misjudgment caused by a unified standard, and provide a more reliable data association basis for subsequent traversing the information database of error-prone misjudged vehicle models.

[0057] Specifically, when traversing the information database of error-prone misjudged vehicle models, the vehicles in the information database of error-prone misjudged vehicle models are sorted from the largest to the smallest according to the dispute index. Starting from the vehicle with the largest dispute index, the vehicle information is sequentially associated and matched with the real-time high-speed data, and the number of matching items is counted. When the proportion of the number of matching items to all feature numbers is greater than or equal to the preset matching degree threshold, it is determined that the vehicle is an error-prone misjudged vehicle model and corresponding analysis of the error-prone misjudged vehicle model is carried out.

[0058] As a preferred implementation manner of this embodiment, the total number of all features of the vehicle in the information database of error-prone misjudged vehicle models is , the number of matching items between the vehicle information and the real-time high-speed data is , and the preset matching degree threshold is . When , it is determined that the vehicle is an error-prone misjudged vehicle model. In a specific example, the total number of all features of a certain vehicle in the information database of error-prone misjudged vehicle models, the preset matching degree threshold , the number of matching items between the vehicle information and the real-time high-speed data of this vehicle, then at this time , it is determined that the vehicle is an error-prone misjudged vehicle model.

[0059] With the above, this embodiment sorts the vehicles in the information database of error-prone misjudged vehicle models from the largest to the smallest according to the dispute index, sequentially performs association and matching, counts the number of matching items and compares it with the preset matching degree threshold, achieving efficient and accurate screening of error-prone misjudged vehicle models. Processing the vehicles with high dispute index first reduces the blindness of traversal, improves the efficiency of finding error-prone misjudged vehicle models, and provides a clear object for subsequent analysis of error-prone misjudged vehicle models.

[0060] Specifically, the analysis of error-prone misjudged vehicle models includes:

[0061] Determine the types of error-prone misjudged vehicle models in combination with the driving scenario and surrounding vehicle information. Collect the driving scenario information and surrounding vehicle information of the current vehicle, integrate them, and compare them with the feature performances of various vehicle models in different scenarios in the information database of error-prone misjudged vehicle models. Combining the vehicle's own dispute index, comprehensively judge the candidate set of the types of error-prone misjudged vehicle models, and at least two types of vehicle models that the vehicle is likely to be misjudged as are included in the candidate set.

[0062] As a preferred implementation manner of this embodiment, based on any existing matching method, the matching score between the driving scenario information and the vehicle model features in the information database is , the matching score between the surrounding vehicle information and the vehicle model features is, and the vehicle's own dispute index is , and the comprehensive score is , , and are preset weight coefficients, and a candidate set of vehicle model types prone to misjudgment is determined based on the ranking of this comprehensive score. In a specific example, , , , for a certain vehicle model, the matching score of the driving scenario information is , the matching score of the surrounding vehicle information is , and the vehicle's own dispute index is , then the comprehensive score is , and a candidate set of vehicle model types prone to misjudgment is determined based on this comprehensive score.

[0063] Through the above, this embodiment uses the collected driving scenarios and surrounding vehicle information, compares them with the characteristic performances of various vehicle models in the information database of vehicle models prone to misjudgment in different scenarios, and combines the vehicle's own dispute index for comprehensive judgment, realizing a more comprehensive and accurate determination of the candidate set of vehicle model types prone to misjudgment. It fully considers the actual driving environment and the vehicle's own dispute situation, avoids the limitations of single-factor judgment, and provides a more reasonable selection range for subsequent determination of the final vehicle model.

[0064] Specifically, when determining the final vehicle model based on the analysis of the dispute index, list multiple attributes that affect the vehicle model judgment, count the actual occurrence frequency and toll dispute situation of each vehicle model under the historical dispute index analysis, and configure corresponding weights for each attribute;

[0065] For each candidate vehicle model, multiply the performance values of each attribute by the corresponding weights and sum them to obtain a comprehensive score, and select the vehicle model with the highest score as the final vehicle model.

[0066] As a preferred implementation manner of this embodiment, collect attributes that affect the vehicle model judgment , the corresponding weights are , the performance values of a certain candidate vehicle model on each attribute are , and the comprehensive score is , and select the vehicle model with the highest comprehensive score as the final vehicle model. In a specific example, there are 3 attributes that affect the vehicle model judgment, namely the dispute index, the driving scenario matching degree, and the surrounding vehicle similarity, and the weights are respectively , , The performance values of a certain candidate vehicle model in various attributes are respectively , , , then the comprehensive score .

[0067] Through the above, in this embodiment, multiple attributes affecting vehicle model judgment are listed, historical data is statistically analyzed to configure weights for each attribute, the comprehensive score of the candidate vehicle model is calculated, and the vehicle model with the highest score is selected as the final vehicle model, realizing scientific decision-making based on multiple attributes. Various factors affecting vehicle model judgment are comprehensively considered, the accuracy and reliability of the determination of the final vehicle model are improved, and the rationality of highway tolls is ensured.

[0068] Specifically, when there is real-time highway data for the vehicle and the dispute index is calculated, vehicles on the same section of the highway during the same time period are defined as a set. Taking each vehicle in this set as a node, the association relationship between vehicles is analyzed to construct an association network;

[0069] Check the position of the vehicle in the association network, count the dispute indexes of its neighbor nodes, and correct the dispute index of the vehicle based on the vehicle position and the dispute index situation of the neighbor nodes.

[0070] As a preferred implementation manner of this embodiment, the original dispute index of the vehicle is calculated as , the position coefficient of the vehicle in the association network is , the average dispute index of the neighbor nodes is , and the corrected dispute index . In a specific example, the original dispute index of the vehicle , the position coefficient of the vehicle in the association network , the average dispute index of the neighbor nodes , then the corrected dispute index .

[0071] Through the above, in this embodiment, vehicles on the same section of the highway during the same time period are defined as a set, an association network is constructed, and the dispute index of the vehicle is corrected according to the vehicle's position in the network and the dispute index of the neighbor nodes, realizing further optimization of the dispute index. The association relationship between vehicles and overall environmental factors are considered, making the dispute index more capable of reflecting the real toll dispute possibility of the vehicle in actual traffic, and providing a more accurate basis for subsequent vehicle model analysis and toll decision-making.

[0072] Specifically, after determining the final vehicle model, the confidence interval of the toll vehicle model is adjusted based on the dispute index of the vehicle, and the determination process of the toll vehicle model, the applicable toll standard, and the reasons and specific ranges for the adjustment of the confidence interval are recorded and output; among them, the adjustment of the confidence interval is as follows:

[0073] When the dispute index is greater than the preset first confidence threshold, expand the confidence interval;

[0074] When the dispute index is less than the preset second confidence threshold, narrow the confidence interval; where the second confidence threshold is less than the first confidence threshold.

[0075] As a preferred implementation manner of this embodiment, the confidence interval of the original toll model is , the preset first confidence threshold is , the second confidence threshold is , and , the expansion coefficient is , the reduction coefficient is . When the dispute index , the new confidence interval is ; when , the new confidence interval is . In a specific example, the confidence interval corresponding to the original toll model is , the first confidence threshold , the second confidence threshold , the expansion coefficient , the reduction coefficient . The dispute index of a vehicle , at this time , then the new confidence interval is ; the dispute index of another vehicle , at this time , then the new confidence interval is .

[0076] Through the above, this embodiment adjusts the confidence interval of the toll model according to the dispute index of the vehicle after determining the final model, and records the relevant processes and information, realizing the dynamic adjustment and transparent management of the toll model. It can flexibly adjust the toll range according to the dispute risk of the vehicle, ensuring the rationality of the toll while reducing the occurrence of toll disputes. At the same time, the recorded information provides convenience for subsequent auditing and querying.

[0077] In the specific application of this embodiment, based on the basic trusted data sources of vehicle data, the trusted information sources can be, but are not limited to, the vehicle information database of the provincial traffic management bureau, the provincial ETC issuance data, etc. Based on this, the accurate verification of the vehicle toll models is completed in the system background, and a vehicle model library prone to misjudgment is successfully constructed. This authoritative and reliable data source lays a solid foundation for subsequent accurate toll collection. On this basis, with the help of the existing toll collection system network, the vehicle model library prone to misjudgment in the cloud is distributed to the lane systems across the province in real time. The front-end toll collection system relies on these real-time data of the vehicle model library prone to misjudgment to more accurately determine and identify the toll models, thereby realizing accurate toll collection, effectively reducing toll errors, and improving operational efficiency. The specific implementation method of this application is as follows:

[0078] 1. The provincial center analyzes and calculates to form a license plate vehicle model library to be verified; the provincial center forms a license plate vehicle model library to be verified daily according to vehicle transaction records, using the existing data, including basic data, historical transaction record data, historical image data, etc.; the basic data includes, but is not limited to, the information registered by the vehicle at the vehicle management office and the issuance data of ETC products;

[0079] 2. The road section checks the license plate vehicle model library one by one to form an accurate vehicle model library; the provincial center distributes the license plate vehicle model library to be verified to the road section units through the existing audit system, and the road section units verify this part of the data through real-time vehicle passing conditions and data such as the logs and pictures of the vehicle's travel, and form a vehicle model library after verification;

[0080] 3. The provincial center adds the vehicle model library to the key attention list and distributes it to each toll lane system in the province using the original data;

[0081] 4. The road section accurately judges the vehicle model using the key attention list, and the lane toll collection system realizes accurate toll collection without adding any hardware devices and software.

[0082] In a simple example of this embodiment, there is a passenger car that often travels on the highway network of a certain province. Through a series of steps, the vehicle is analyzed based on the change of the dispute index to determine whether it is a vehicle prone to misjudgment and determine the final toll-related matters. Specifically:

[0083] Data collection and feature vector generation:

[0084] 1. Multi-source data collection:

[0085] Basic data: The vehicle registration shows that its brand is X, model is Y, approved seating capacity is 9 people, vehicle length is 5.5 meters, etc.

[0086] Management data: The vehicle annual inspection record is normal, and there was a minor illegal record of overloading once in the past, but it has been dealt with in a timely manner.

[0087] Toll data: In the past six months, the vehicle has traveled 20 times on different sections of the road, with the toll amount fluctuating between 50 yuan and 150 yuan each time. On three occasions, the toll amount was significantly higher or lower than the average toll for the same type of vehicles on the same section of the road.

[0088] Disputed data: We have received two inquiries from car owners regarding the judgment of the toll model, reflecting that they believe the toll model may be wrong.

[0089] Internal structure characteristic data: The seat layout in the car is relatively flexible and can be adjusted according to needs.

[0090] Electronic system configuration data: equipped with advanced on-board navigation and vehicle monitoring systems, etc.

[0091] 2. Fusion of multi-source data to calculate feature vectors:

[0092] According to the preset data level, the system sorts out the key items under each data category, such as the number of seats and vehicle length in the basic data, the violation record in the management data, and the fluctuation of the toll amount in the toll data. Analyze the internal logical connection between these key items. For example, when the number of seats is close to the critical value (such as 8-9 seats) and the toll amount fluctuates greatly, the vehicle is more likely to have a toll dispute. Based on the actual situation of a large number of vehicles in the past and the corresponding toll dispute cases, the frequency of occurrence and degree of mutual influence of each key item in different dispute situations are counted, and each key item is assigned a corresponding weight. Assume that the weight of the number of seats is 0.3, the weight of the violation record is 0.1, the weight of the toll amount fluctuation is 0.4, and the weight of the dispute data is 0.2. After weighted summation, the feature vector of the vehicle is generated for subsequent analysis.

[0093] Dispute index calculation, combining time series analysis of the dynamic changes in charging data and dispute data to calculate the dispute index of the vehicle:

[0094] 1. Data collation and sequence formation: Arrange the toll data in chronological order to form a toll time series, and also collate the dispute data in the corresponding chronological order to form a dispute time series. For example, the toll time series shows that the toll amount is generally high during holidays and relatively stable on weekdays; the dispute data time series shows that the frequency of disputes has increased after the toll policy of certain sections of the road has been changed.

[0095] 2. Analyze data characteristics and classify levels: Calculate the fluctuations in the toll amounts in the toll time series, mark the time periods with relatively large fluctuations and the corresponding changes in amounts, and at the same time count the frequencies of disputes occurring in the dispute time series and the amount differences involved in each dispute. Based on these elements, establish a classification standard for dispute status, which is divided into three dispute levels: low, medium, and high. For example, when the toll amount fluctuates within 10% and the frequency of disputes is less than 1 time per month, it is identified as a low dispute level; when the fluctuation is between 10% - 30% and the frequency of disputes is between 1 - 3 times per month, it is identified as a medium dispute level; when the fluctuation exceeds 30% and the frequency of disputes is higher than 3 times per month, it is identified as a high dispute level.

[0096] 3. Calculate the dispute index: Observe the proportion of the vehicle's status in different dispute levels in each time period in the past six months. Assume that the proportion of time in the low dispute level is 30%, the medium dispute level is 40%, and the high dispute level is 30%. The corresponding level coefficients are set to 1, 2, and 3 respectively. By calculating (30%×1 + 40%×2 + 30%×3), the dispute index of this vehicle is obtained as 2.2, indicating that there is a certain possibility of toll disputes for the vehicle.

[0097] Update the information database and associate real - time data based on the dispute index:

[0098] 1. Information database update: The preset dispute index threshold in the system is 1.5. Since the vehicle's dispute index of 2.2 is greater than the threshold, the information of this vehicle is updated to the preset information database of error - prone judgment vehicle types and shared, so that relevant toll stations and management departments can obtain the vehicle's situation in a timely manner.

[0099] 2. Real - time data association: When this vehicle enters the highway again, collect its real - time highway data, such as obtaining the vehicle's current appearance characteristics (consistent with the registration), driving speed (within the normal driving speed range), lane position (in the driving lane), etc. key contents in real - time, and calculate the matching degree between the two based on the corresponding feature descriptions in the previously generated feature vector. Assume that the initial matching degree judgment standard is 0.8. Since the vehicle's dispute index of 2.2 is greater than the preset adjustment threshold (assumed to be 1.8), the judgment standard for the matching degree is increased, and it is required that the matching degree of each key content with the feature vector reaches 0.9 to be considered associated.

[0100] Traverse the information database of error - prone judgment vehicle types and determine the types of error - prone judgment vehicles:

[0101] 1. Information database traversal: When traversing the information database of vehicles with error-prone judgment models, the system has sorted all the vehicles in the information database from the largest to the smallest according to the dispute index. Starting from the vehicle with the highest dispute index, vehicle information is taken out in turn and associated and matched with the real-time highway data of the vehicle, and the number of matching items is counted. Suppose when the vehicle is matched with the vehicle information in the information database, the total number of features is 10 items, and the number of matching items reaches 7 items, while the preset matching degree threshold is 0.6 (i.e., 6 items), then it is determined that the vehicle is a possible vehicle with an error-prone judgment model and enters the analysis process of vehicles with error-prone judgment models.

[0102] 2. Determine the types of vehicles with error-prone judgment models: Collect the driving scenario information of the current vehicle. For example, when it is currently on a mountain highway section during the peak tourist season, there are mostly small passenger cars and tourist buses among the surrounding vehicles, etc. At the same time, count the types, quantities, speeds, etc. of the surrounding vehicles. After integrating this information, compare it with the characteristic performances of various vehicle models in the information database of vehicles with error-prone judgment models in similar scenarios, combined with the dispute index 2.2 of the vehicle itself. Through comprehensive judgment, it is found that in the current scenario, this vehicle is likely to be misjudged as an eight-seat passenger car or a seven-seat passenger car, forming a candidate set of the types of vehicles with error-prone judgment models.

[0103] Determine the final vehicle model based on the dispute index:

[0104] List multiple attributes that affect vehicle model judgment, including the dispute index, driving scenario matching degree (determined by comparing the coincidence degree of the current vehicle driving scenario with the standard scenario characteristics of the corresponding vehicle model), similarity of surrounding vehicles (comparing the similarity of the surrounding vehicles with the common surrounding vehicle distribution of the corresponding vehicle model), etc. Review the actual occurrence frequencies of various vehicle models and the corresponding toll disputes in past similar driving scenarios and surrounding vehicle distribution situations, and assign corresponding weights to the above-mentioned attributes respectively. Suppose the weight of the dispute index is 0.4, the weight of the driving scenario matching degree is 0.3, and the weight of the similarity of surrounding vehicles is 0.3. For the two candidate vehicle models of eight-seat passenger cars and seven-seat passenger cars, calculate their comprehensive scores respectively. Suppose the dispute index matching degree of the eight-seat passenger car is 0.8 (compared with the current vehicle's dispute index situation), the driving scenario matching degree is 0.7 (the degree of compliance with the mountain tourist peak season scenario), and the similarity of surrounding vehicles is 0.6 (comparison of the surrounding vehicle distribution situation), then its comprehensive score is calculated as (0.4×0.8 + 0.3×0.7 + 0.3×0.6) = 0.71. The dispute index matching degree of the seven-seat passenger car is 0.6, the driving scenario matching degree is 0.8, and the similarity of surrounding vehicles is 0.7. The comprehensive score is calculated as (0.4×0.6 + 0.3×0.8 + 0.3×0.7) = 0.7. Comparing the comprehensive scores of the two candidate vehicle models, the eight-seat passenger car has a higher score, so the final vehicle model is determined to be an eight-seat passenger car.

[0105] Through such a complete vehicle analysis process based on the change of the dispute index, the highway management department can manage vehicle tolls more accurately, reduce toll disputes, and improve operational efficiency.

[0106] The second aspect of this embodiment discloses a Figure 2 highway precise toll collection system based on error-prone vehicle type analysis as shown. This system is applicable to the highway precise toll collection method based on error-prone vehicle type analysis as described above. The system includes a feature vector module, a dispute index module, a vehicle type determination module, and a toll collection module that are sequentially communicatively connected;

[0107] The feature vector module is used to collect multi-source data of the vehicle, fuse the multi-source data, and calculate the feature vector. The multi-source data includes basic data, management data, toll collection data, dispute data, internal structure feature data, and electronic system configuration data;

[0108] The dispute index module is used to combine time series analysis of the dynamic changes of toll collection data and dispute data, calculate the dispute index of the vehicle, and use it to automatically capture error-prone vehicles;

[0109] The vehicle type determination module is used to update the vehicle information to a preset error-prone vehicle type information database and share it when the dispute index reaches the preset dispute index threshold; collect real-time highway data and associate it with the feature vector, traverse the error-prone vehicle type information database, determine the types of error-prone vehicle types in combination with the driving scenario and surrounding vehicle information, and determine the final vehicle type based on the dispute index analysis;

[0110] The toll collection module is used to calculate the toll amount according to the final vehicle type, and record and output the determination process and calculation process.

[0111] It should be noted that the highway precise toll collection system based on error-prone vehicle type analysis in this embodiment corresponds to the aforementioned highway precise toll collection method based on error-prone vehicle type analysis. Therefore, for the content not specifically described in the highway precise toll collection system based on error-prone vehicle type analysis in this embodiment, it can, but is not limited to, function definitions, working principles, technical effects, etc., and can refer to the records in the aforementioned highway precise toll collection method based on error-prone vehicle type analysis. This text will not elaborate here.

[0112] In summary, the method and system for precise highway toll collection based on error-prone vehicle type analysis in this embodiment utilize the collection of multi-source data of vehicles and the calculation of feature vectors, and combine time series analysis to calculate the dynamic changes of toll and dispute data to calculate the dispute index, so as to capture error-prone vehicles; when the dispute index reaches the threshold, update the vehicle information to the error-prone vehicle type information library and share it, and at the same time collect real-time highway data and associate it with the feature vector, combine the driving scenario and the surrounding vehicle information to determine the types of error-prone vehicle types, and finally determine the final vehicle type based on the analysis of the dispute index, realizing the precision of highway toll collection; calculate the toll amount according to the final vehicle type and record the output process, which not only improves the accuracy and fairness of toll collection, but also provides a reliable basis for subsequent management and auditing, and improves the overall efficiency and quality of highway toll management.

[0113] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, or other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiments can be completed by a computer program instructing the relevant hardware. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. The computer-readable storage medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transfer of a computer program from one place to another. The storage media can be any available medium that can be accessed by a computer. The computer-readable storage medium can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM, or other optical disc storage, magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0114] Finally, it should be noted that the above are only the preferred embodiments of the present application and are not used to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for accurate toll collection on expressways based on the analysis of vehicle types prone to misjudgment, characterized in that, The method includes the following steps: Collect multi-source data of the vehicle, fuse the multi-source data, and calculate the feature vector. The multi-source data includes basic data, management data, toll data, dispute data, internal structure feature data, and electronic system configuration data; Combine time series analysis to analyze the dynamic changes of toll data and dispute data, calculate the dispute index of the vehicle and use it to automatically capture vehicles prone to misjudgment; When the dispute index reaches the preset dispute index threshold, update the vehicle information to the preset information database of vehicle types prone to misjudgment and share it; collect real-time highway data and associate it with the feature vector, traverse the information database of vehicle types prone to misjudgment, determine the types of vehicles prone to misjudgment in combination with the driving scenario and surrounding vehicle information, and determine the final vehicle type based on the analysis of the dispute index; When fusing multi-source data to calculate the feature vector, clarify the key items under each data category based on the preset data level, and analyze the internal logical relationship between the key items; wherein, the data level is used to represent the importance of the multi-source data; Based on the actual situation of historical vehicles and the corresponding toll dispute cases, count the occurrence frequency and mutual influence degree of each key item in different dispute situations, assign corresponding weights to each key item based on the statistical results and the internal logical relationship, and generate a feature vector based on the weights. The feature vector is used to reflect the key information related to vehicles prone to misjudgment in the multi-source data; When combining time series analysis to analyze the dynamic changes of toll data and dispute data to calculate the dispute index of the vehicle, arrange the toll data and the dispute data in chronological order respectively to form the corresponding toll time series and dispute time series; Calculate the fluctuation of the toll vehicle type and amount in the toll time series and the occurrence frequency and amount difference of disputes in the dispute time series, construct a dispute status classification standard, map the status of the vehicle in different time periods to the corresponding level in the dispute status classification standard, and calculate the dispute index based on the proportion of the vehicle in each level status. The dispute index is used to reflect the possibility of toll disputes of the vehicle.

2. The method for precise highway toll collection based on error-prone vehicle type analysis according to claim 1, characterized in that When collecting real-time highway data and associating it with the feature vector, extract the key content in the real-time highway data based on the key content in the feature vector to generate a real-time feature corresponding to the feature vector; Calculate the matching degree between the feature vector and the real-time feature, and adjust the determination standard of the matching degree based on the current dispute index of the vehicle. The adjustment is as follows: When the dispute index is greater than or equal to the preset adjustment threshold, increase the determination standard of the matching degree; when the dispute index is less than the adjustment threshold, decrease the determination standard of the matching degree.

3. The method for accurate highway toll collection based on error-prone vehicle type analysis according to claim 2, wherein, When traversing the information database of vehicles prone to misjudgment, sort the vehicles in the information database of vehicles prone to misjudgment in descending order of the dispute index, start from the vehicle with the largest dispute index, and sequentially perform the association matching between the vehicle information and the real-time highway data, count the number of matching items. When the proportion of the number of matching items to all feature numbers is greater than or equal to the preset matching degree threshold, determine that the vehicle is a vehicle prone to misjudgment and perform the corresponding analysis of the vehicle type prone to misjudgment.

4. The method for accurate highway toll collection based on error-prone vehicle type analysis according to claim 3, characterized in that, The analysis of vehicles prone to misjudgment includes: Determine the types of vehicles prone to misjudgment by combining the driving scenario and information of surrounding vehicles. Collect the driving scenario information and information of surrounding vehicles of the current vehicle, integrate them, and compare them with the characteristic performances of various vehicle types in different scenarios in the information database of vehicles prone to misjudgment. Combine the controversy index of the vehicle itself to comprehensively judge the candidate set of vehicle types prone to misjudgment, and the candidate set includes at least two types of vehicle types that the vehicle is likely to be misjudged as.

5. The method for precise highway toll collection based on error-prone vehicle type analysis according to claim 4, wherein, When determining the final vehicle type based on the analysis of the controversy index, list multiple attributes that affect the vehicle type judgment, count the actual occurrence frequency and toll controversy situation of each vehicle type under the historical controversy index analysis, and configure corresponding weights for each attribute; For each candidate vehicle type, multiply the performance values of each attribute by the corresponding weights and sum them to obtain a comprehensive score, and select the vehicle type with the highest score as the final vehicle type.

6. The method for precise highway toll collection based on error-prone vehicle type analysis according to claim 1, characterized in that, When the vehicle has the real-time highway data and calculates the controversy index, define the vehicles on the same highway section in the same time period as a set, take each vehicle in the set as a node, and analyze the association relationship between vehicles to construct an association network; Check the position of the vehicle in the association network, count the controversy index of its neighbor nodes, and correct the controversy index of the vehicle based on the vehicle position and the controversy index situation of the neighbor nodes.

7. The method for precise highway toll collection based on error-prone vehicle type analysis according to claim 5, characterized in that, After determining the final vehicle type, adjust the confidence interval of the toll vehicle type based on the controversy index of the vehicle, record the determination process of the toll vehicle type, the applicable toll standard, and the reasons and specific ranges for the adjustment of the confidence interval and output them; among them, the adjustment of the confidence interval is as follows: When the controversy index is greater than the preset first confidence threshold, expand the confidence interval; When the controversy index is less than the preset second confidence threshold, narrow the confidence interval; where the second confidence threshold is less than the first confidence threshold.

8. A highway precise toll collection system based on error-prone vehicle type analysis, the system is applicable to the method for highway precise toll collection based on error-prone vehicle type analysis as described in any one of claims 1-7, characterized in that, The system includes a feature vector module, a controversy index module, and a vehicle type determination module that are sequentially communicatively connected; The feature vector module is used to collect multi-source data of the vehicle, fuse the multi-source data, and calculate the feature vector. The multi-source data includes basic data, management data, toll data, controversy data, internal structure feature data, and electronic system configuration data; The controversy index module is used to combine time series analysis of the dynamic changes of toll data and controversy data, calculate the controversy index of the vehicle, and is used to automatically capture vehicles prone to misjudgment; The vehicle type determination module is used to update the vehicle information to the preset information database of vehicles prone to misjudgment and share it when the controversy index reaches the preset controversy index threshold; Collect real-time highway data and associate it with the feature vector, traverse the information database of vehicles prone to misjudgment, determine the types of vehicles prone to misjudgment by combining the driving scenario and information of surrounding vehicles, and determine the final vehicle type based on the analysis of the controversy index; Among them, when fusing multi-source data to calculate the feature vector, clarify the key items under each data category based on the preset data level, and analyze the internal logical relationship between the key items; where the data level is used to represent the importance of the multi-source data. Based on the actual situations of historical vehicles and the corresponding toll dispute cases, count the occurrence frequencies and the degree of mutual influence of each of the key items under different dispute situations, assign corresponding weights to each key item based on the statistical results and the inherent logical connections, and generate a feature vector based on the weights, where the feature vector is used to reflect the key information related to error-prone vehicle types in multi-source data; When calculating the dispute index of a vehicle by combining time series analysis of the dynamic changes of toll data and dispute data, arrange the toll data and the dispute data in chronological order respectively to form corresponding toll time series and dispute time series; Calculate the fluctuations of the toll vehicle types and amounts in the toll time series and the occurrence frequencies and amount differences of disputes in the dispute time series, construct a dispute status classification standard, map the status of the vehicle in different time periods to the corresponding levels in the dispute status classification standard, and calculate the dispute index based on the proportion of the vehicle in each level of status, where the dispute index is used to reflect the possibility of vehicle toll disputes.

Images