A truck passage management system based on a traffic internet of things

Abstract

The application discloses a truck passing management system based on a traffic Internet of Things, and belongs to the technical field of traffic management control. The system comprises a collection module, a server terminal and a truck terminal. The collection module is used for collecting passing information of a passing area through a road perception device and transmitting the passing information to the server terminal. The server terminal comprises a determination module, a management module and a feedback module. The determination module is used for determining a target congestion condition of the passing area in a passing period based on the passing information. The management module is used for dynamically adjusting the passing area based on the target congestion condition of the passing area in the passing period. The feedback module is used for feeding back the dynamically adjusted passing area to the truck terminal. The system can timely adjust the area allowing the truck to pass based on the actual traffic condition, and improve the congestion condition of each area in the passing permit authority.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of traffic management control, and particularly relates to a truck passing management system based on a traffic Internet of Things. BACKGROUND

[0002] In the management of city truck passing, a city truck passing certificate is usually applied for by a truck driver, and the passing area and passing time period are limited by the passing certificate, so that the truck is allowed to pass in the city based on the passing certificate authority. Since the existing passing certificate adopts a static limitation mode of fixed area or fixed route, the passing certificate authority is out of touch with the actual traffic condition. When a sudden situation exists in a certain area within the passing certificate authority, causing congestion in the area, it is difficult to manage the truck passing in a timely manner, so that the truck can still enter the congested area, aggravating the congestion condition in the area. Therefore, there is an urgent need for a truck passing management system based on a traffic Internet of Things, which can timely adjust the area allowing the truck to pass based on the actual traffic condition, and improve the congestion condition in each area within the passing certificate authority.

[0003] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present application, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0004] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an overall description of the application, nor is it intended to determine key / important elements or delineate the scope of the embodiments. It is intended as a prelude to the detailed description below.

[0005] The present application provides a truck passing management system based on a traffic Internet of Things, which can timely adjust the area allowing the truck to pass based on the actual traffic condition, and improve the congestion condition in each area within the passing certificate authority.

[0006] In some embodiments, a truck passing management system based on a traffic Internet of Things includes a collection module, a server terminal and a truck terminal, and the server terminal is in communication connection with the collection module and the truck terminal respectively; wherein,

[0007] The collection module is configured to collect passing information of a passing area through a road perception device, and transmit the passing information to the server terminal; wherein, the road perception device is installed along the road, and the passing area represents a passing area allowed by the truck passing certificate;

[0008] The server terminal includes a determination module, a management module and a feedback module; wherein,

[0009] The determining module is configured to determine the target congestion condition of the passing area in the passing period based on the passing information, wherein the passing period represents a passing period allowed by the truck passing permit.

[0010] The management module is configured to dynamically adjust the passing area based on the target congestion condition of the passing area in the passing period.

[0011] The feedback module is configured to feed back the dynamically adjusted passing area to the truck terminal.

[0012] The present application has the following advantages:

[0013] The collection module collects the passing information of the passing area through the road perception device installed along the road in the passing area, and transmits the collected passing information to the server terminal. The determining module of the server terminal then calculates based on the communication information to determine the target congestion condition of the passing area in the passing period, so that the management module of the server terminal dynamically adjusts the passing area, thereby realizing timely adjustment of the area allowed for truck passing based on the actual traffic condition, so as to prevent the truck from entering the congested area. The feedback module of the server terminal feeds back the dynamically adjusted passing area to the truck terminal. In this way, through the traffic Internet of Things among the road perception device, the server terminal and the truck terminal, the passing information is collected by the road perception device and transmitted to the server terminal, which dynamically adjusts the passing area based on the received passing information and feeds back to the truck terminal, so as to timely adjust the area allowed for truck passing based on the actual traffic condition, so as to prevent the truck from entering the congested area, and to improve the congestion condition of each area within the passing permit.

[0014] The foregoing general description and the following description are only exemplary and explanatory, and are not intended to limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0015] One or more embodiments are exemplarily illustrated by corresponding drawings, which are not intended to limit the embodiments, elements with the same reference numerals in the drawings are shown as similar elements, the drawings do not constitute proportional limitation, and wherein:

[0016] Figure 1 is a structural schematic diagram of a truck passing management system based on traffic Internet of Things provided by the present application;

[0017] Figure 2 is a structural schematic diagram of another truck passing management system based on traffic Internet of Things provided by the present application. DETAILED DESCRIPTION

[0018] In order to enable a more detailed understanding of the features and technical content of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure is described in detail below, and the accompanying drawings are used for reference only and do not limit the embodiments of the present disclosure. In the following technical description, for the purpose of convenient explanation, through multiple details, a sufficient understanding of the disclosed embodiments is provided. However, one or more embodiments can still be implemented without these details. In other cases, well-known structures and devices can be simplified to show.

[0019] The terms "first", "second", and the like in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so as to implement the embodiments of the present disclosure described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0020] Unless otherwise specified, the term "a plurality of" means two or more.

[0021] In the embodiments of the present disclosure, the character " / " represents that the objects before and after are in an "or" relationship. For example, A / B represents: A or B.

[0022] The term "and / or" is a description of the association between objects, which means that there can be three relationships. For example, A and / or B, which means: A or B, or, A and B, three relationships.

[0023] The term "corresponding" can refer to an association or binding relationship, A corresponding to B means that there is an association or binding relationship between A and B.

[0024] In combination Figure 1 As shown, Figure 1Provided is a truck passage management system based on a traffic Internet of Things, comprising: a collection module, a server terminal, and a truck terminal, and the server terminal is in communication connection with the collection module and the truck terminal; wherein the collection module, the server terminal, and the truck terminal, and the server terminal is in communication connection with the collection module and the truck terminal; wherein the collection module is used for collecting passage information of a passage area through a road perception device installed along a road in the passage area, and transmitting the passage information to the server terminal; wherein the road perception device is installed along the road, and the passage area represents a passage area allowed by a truck passage certificate; the server terminal comprises a determination module, a management module, and a feedback module; wherein the determination module is used for determining a target congestion condition of the passage area in a passage period based on the passage information; wherein the passage period represents a passage period allowed by the truck passage certificate; the management module is used for dynamically adjusting the passage area based on the target congestion condition of the passage area in the passage period; and the feedback module is used for feeding back the dynamically adjusted passage area to the truck terminal.

[0025] The truck passage management system based on the traffic Internet of Things adopted in the embodiments of the present disclosure collects passage information of a passage area through a road perception device installed along a road in the passage area, and transmits the collected passage information to a server terminal. A determination module of the server terminal then performs calculation based on the communication information to determine a target congestion condition of the passage area in a passage period, so that a management module of the server terminal dynamically adjusts the passage area, thereby realizing timely adjustment of the area allowed for truck passage based on actual traffic conditions, so as to prevent trucks from entering a congested area. The feedback module of the server terminal feeds back the dynamically adjusted passage area to the truck terminal. In this way, the traffic Internet of Things among the road perception device, the server terminal, and the truck terminal collects passage information through the road perception device, and transmits the passage information to the server terminal, which dynamically adjusts the passage area based on the received passage information and feeds back to the truck terminal, thereby being able to timely adjust the area allowed for truck passage based on actual traffic conditions, so as to prevent trucks from entering a congested area, and being able to improve the congestion condition of each area within the authority of the passage certificate.

[0026] Illustratively, the road perception device comprises one or more of a road camera (usually deployed on the roadside or above the road), a geomagnetic coil (buried under the road surface for calculating traffic volume), a radar detector (usually deployed on the roadside), and the like. The road perception device adopted in the embodiments of the present disclosure is mainly a road camera.

[0027] For example, the road perception device can transmit the collected traffic information to the server terminal directly. Alternatively, the road perception device can transmit the collected traffic information to a roadside unit (RSU) which is mainly deployed on the roadside, such as a signal pole, a gantry, or a roadside cabinet, and the roadside unit can transmit the collected traffic information to the server terminal.

[0028] For example, the traffic information includes road image data.

[0029] For example, the traffic capacity represents the congestion degree. The more congested, the worse the traffic capacity, and vice versa.

[0030] For example, the truck terminal includes an electronic device used by a truck driver, such as a mobile phone or a tablet. In this case, no limitation is made.

[0031] Preferably, the determining module is specifically configured to: determine the relationship between the current time and the traffic period; if the current time is earlier than the start time of the traffic period, predict the first congestion conditions of each road in the traffic region in the traffic period based on the traffic information of the target period, and if the current time is in the traffic period, calculate the sub-congestion conditions of each road in the traffic region at the current time based on the traffic information at the current time, until the current time is later than the end time of the traffic period, to obtain each second congestion condition; and take each first congestion condition and each second congestion condition as the target congestion condition of the traffic region in the traffic period.

[0032] It can be understood that one road corresponds to one first congestion condition, and one first congestion condition includes a plurality of first congestion degrees arranged in time sequence; one road corresponds to one second congestion condition, and one second congestion condition includes a plurality of sub-congestion conditions arranged in time sequence.

[0033] In this way, if the current time is earlier than the start time of the traffic period, it means that the truck has not been allowed to enter the traffic region, and at this time, the first congestion conditions of each road in the traffic region are predicted in advance to determine the target congestion condition of the traffic region in the traffic period before the start of the traffic period, so that the server terminal can timely adjust the region allowing the truck to pass through, and achieve pre-planning management. If the current time is in the traffic period, the current traffic capacity (i.e., the sub-congestion condition) of each road in the traffic region can be calculated based on the traffic information at the current time at this time, so that the target congestion condition of the traffic region corresponding to the current time can be determined in the traffic period, so that the server terminal can timely adjust the region allowing the truck to pass through, and achieve in-process adjustment management.

[0034] Preferably, the first congestion condition of each road in the traffic area in the traffic period is predicted based on the traffic information of the target period, including: for each road in the traffic area, performing the following steps: predicting a plurality of first congestion degrees of the road in the traffic period in time sequence based on the traffic information of the road in the target period; determining a deviation compensation value corresponding to each first congestion degree; wherein the deviation compensation value represents the difference between the actual congestion degree and the first congestion degree; respectively compensating each first congestion degree based on the deviation compensation value corresponding to each first congestion degree to obtain each second congestion degree; and taking each second congestion degree in time sequence as the first congestion condition of the road in the traffic period.

[0035] Since the prediction data has errors, the plurality of first congestion degrees are obtained by predicting based on the traffic information of the road in the target period; and the accuracy of each second congestion degree is improved by deviation compensation of the first congestion degree based on the deviation compensation value corresponding to each first congestion degree, so that a more accurate first congestion condition is obtained.

[0036] Illustratively, the target period is a period of n hours before the starting time of the traffic period. n is 1, 2 or 3, etc. The traffic information in the target period represents the traffic information corresponding to the period of n hours before the starting time of the traffic period.

[0037] Illustratively, the traffic information includes road image data. The plurality of first congestion degrees of the road in the traffic period in time sequence are predicted based on the traffic information of the road in the target period, including: dividing the target period into a plurality of sub-periods based on the road image data of the road in the target period. Calculating the traffic volume, weather influence intensity, holiday condition, construction intensity corresponding to each sub-period based on the road image data of each sub-period. Obtaining the road type, number of lanes, and functional area to which the road belongs. For each sub-period, input the corresponding traffic volume, number of lanes, weather influence intensity, holiday condition, construction intensity, road type and functional area to which the road belongs into a pre-trained traffic volume prediction model to obtain the predicted traffic volume corresponding to each sub-period. Wherein one sub-period corresponds to one first congestion degree. The quotient of the predicted traffic volume and the basic traffic capacity of the road is taken as the first congestion degree.

[0038] It can be understood that the traffic volume prediction model in the embodiments of the present disclosure is a conventional traffic volume prediction model, such as LSTM (Long Short-Term Memory Network), which will not be described here.

[0039] Preferably, the determining the deviation compensation value corresponding to each first congestion degree comprises: selecting at least one deviation influencing factor as a target feature from the plurality of deviation influencing factors by using a Pearson correlation coefficient or a Spearman correlation coefficient; constructing a deviation compensation function based on all the target features; and determining the deviation compensation value corresponding to each first congestion degree based on the deviation compensation function. The deviation influencing factor represents an influencing factor that causes a difference between the predicted first congestion degree and the corresponding second actual congestion degree.

[0040] The Pearson correlation coefficient and the Spearman correlation coefficient can quantify the correlation between each deviation influencing factor and the deviation compensation value. In this way, the Pearson correlation coefficient and the Spearman correlation coefficient are used for feature selection, so that a deviation influencing factor that has a greater influence on the deviation compensation value is selected as a target feature from the plurality of deviation influencing factors, so that the deviation compensation function constructed can more accurately capture the deviation compensation value corresponding to each first congestion degree.

[0041] Preferably, the selecting at least one deviation influencing factor as a target feature from the plurality of deviation influencing factors by using a Pearson correlation coefficient or a Spearman correlation coefficient comprises: obtaining a plurality of historical traffic data; wherein the historical traffic data comprises parameter values of the plurality of deviation influencing factors and first historical deviation compensation values, and the deviation influencing factors comprise weather influence intensity, holiday condition, construction intensity, road type, and functional area to which the road belongs; determining a parameter type of each deviation influencing factor; for a deviation influencing factor of a continuous variable type, calculating a Pearson correlation coefficient between the deviation influencing factor and the first historical deviation compensation value based on all the historical traffic data, and for a deviation influencing factor of an ordered variable type, calculating a Spearman correlation coefficient between the deviation influencing factor and the first historical deviation compensation value based on all the historical traffic data; and selecting, as the target feature, a deviation influencing factor whose Pearson correlation coefficient is greater than a first preset threshold value and a deviation influencing factor whose Spearman correlation coefficient is greater than a second preset threshold value.

[0042] In this way, the Pearson correlation coefficient and the Spearman correlation coefficient are used to calculate the correlation coefficient between each deviation influencing factor and the first historical deviation compensation value based on the historical traffic data, so as to quantify the correlation between each deviation influencing factor and the deviation compensation value. Then, the deviation influencing factor whose Pearson correlation coefficient is greater than the first preset threshold value and the deviation influencing factor whose Spearman correlation coefficient is greater than the second preset threshold value are selected as the target feature, so as to select a deviation influencing factor that has a greater influence on the deviation compensation value as the target feature, so as to construct a deviation compensation function that can accurately output the deviation compensation value.

[0043] It can be understood that the historical traffic data refers to historical traffic data of a road. The road should include various roads (not limited to roads in the traffic area) so as to increase the diversity of the sample data set. The first historical deviation compensation value represents the difference between the historical actual congestion degree and the historical predicted congestion degree.

[0044] For example, the plurality of deviation influencing factors in the historical traffic data are determined based on expert experience method. In this way, the influencing factors causing the deviation are analyzed and selected by relying on the expert experience knowledge in the field of traffic management, so that more reasonable and scientific deviation influencing factors can be obtained.

[0045] For example, the weather influence intensity represents an influence intensity value of a weather type on road congestion, such as a weather influence value of 0 for sunny weather, a weather influence value of 0.5 for rain, and a weather influence value of 1 for snow or fog. The holiday condition includes a holiday and a non-holiday. The construction intensity is an intensity value mapped based on the scale of road construction, such as an intensity value of 0 for no road construction, an intensity value of 0.3 for small-scale construction (the number of lanes not occupied by construction is not less than 2), an intensity value of 0.7 for large-scale construction (the number of lanes not occupied by construction is less than 2), and an intensity value of 1 for complete construction (all lanes are occupied by construction). The road type includes a main road, a trunk road, a secondary trunk road, and a branch road. The functional area indicates a functional area to which the current road belongs, such as a commercial area (market or office building intensive), a residential area (small community or school concentrated), an industrial area (factory or warehouse concentrated), and a mixed area (commercial and residential mixed).

[0046] Among them, the parameter types of the weather influence intensity and the construction intensity are continuous variable types, and the parameter types of the holiday condition, the road type, and the functional area are ordered variable types.

[0047] For example, for the deviation influencing factors of the continuous variable type, the Pearson correlation coefficient between the deviation influencing factors and the first historical deviation compensation value is calculated based on all the historical traffic data, including: for the deviation influencing factors of the continuous variable type, the Pearson correlation coefficient between the deviation influencing factors and the first historical deviation compensation value is calculated based on all the historical traffic data by the following formula:

[0048]

[0049] Among them, represents the Pearson correlation coefficient, represents the sample size (i.e., the number of historical traffic data), represents the parameter value of the deviation influencing factor, represents the first historical deviation compensation value.

[0050] For example, for the bias influencing factor of the parameter type of the ordinal variable type, the Spearman correlation coefficient between the bias influencing factor and the first historical bias compensation value is calculated based on all historical traffic data, including: for the bias influencing factor of the parameter type of the ordinal variable type, based on the influence degree of the bias influencing factor on the first historical bias compensation value, the rank is assigned, and the first historical bias compensation value corresponding to the bias influencing factor is assigned (for the same first historical bias compensation value, the average rank is taken). The Spearman correlation coefficient between the bias influencing factor and the first historical bias compensation value is calculated based on all historical traffic data by the following formula:

[0051]

[0052] Wherein, The Spearman correlation coefficient is represented by The sample size (i.e. the number of historical traffic data) is represented by The rank difference value between the bias influencing factor and the first historical bias compensation value corresponding to the i-th sample is represented by

[0053] Preferably, based on all target features, the bias compensation function is constructed, including: taking the target feature as the sample feature, taking the corresponding first historical bias compensation value as the sample label, and obtaining a plurality of samples as the data set; the original linear regression equation is trained by using the data set, and the target linear regression equation is obtained as the bias compensation function.

[0054] In this way, each target feature is taken as a sample feature in the data set, the corresponding first historical bias compensation value is taken as a sample label in the data set, and the original linear regression equation is trained, and the trained target linear regression equation is taken as the bias compensation function. The training efficiency of the linear regression equation is high, and the equation output speed is fast, so as to reduce the training cost while quickly obtaining the bias compensation value output by the bias compensation function.

[0055] For example, the original linear regression equation is:

[0056]

[0057] Wherein, The first historical bias compensation value is The intercept is The regression coefficient of the k-th target feature is represented by The parameter value of the k-th target feature is represented by

[0058] For example, for the same sample, the sample feature is separated from the sample label by a first preset time length, and is earlier than the sample label. That is, the sample feature at time t1, and the corresponding sample label is the first historical deviation compensation value at time t1 plus the first preset time length. The first preset time length is not limited here.

[0059] Preferably, based on the deviation compensation function, the deviation compensation value corresponding to each first congestion degree is determined, comprising: obtaining the parameter value of all target features corresponding to each first congestion degree. For each first congestion degree, the parameter value of all target features corresponding to the first congestion degree is substituted into the deviation compensation function to obtain the output value of the deviation compensation function as the deviation compensation value corresponding to the first congestion degree. The parameter value of all target features corresponding to the first congestion degree represents the parameter value of all target features corresponding to the road pointed to by the first congestion degree at the time before the first preset time length of the target sub-period of the first congestion degree. For example, the first preset time length is 5 hours, and the target sub-period of the first congestion degree is from 10:15 to 30 on the same day, then the parameter value of all target features corresponding to the first congestion degree is from 01:15 to 30 on the same day, and the parameter value of all target features corresponding to the road pointed to by the first congestion degree. That is, the parameter value of the target feature at the historical time is used to predict the deviation compensation value at the future time. The historical time is not limited in relation to the current time compared to the future time.

[0060] Preferably, based on the deviation compensation function, the deviation compensation value corresponding to each first congestion degree is determined, comprising: for each first congestion degree, the following steps are performed: based on the deviation compensation function, the deviation compensation value of the first congestion degree in the target sub-period is determined; wherein the target sub-period represents a sub-period of the date on which the first congestion degree is located; obtaining a plurality of second historical deviation compensation values corresponding to the first congestion degree ; wherein, l representing the deviation compensation value at the time of tracing back from the date on which the first congestion degree is located l days representing the deviation compensation value at the time of tracing back from the target sub-period of the first congestion degree l days; arranging the second historical deviation compensation values in sequence to obtain a historical deviation compensation value sequence; using a sliding window to select M second historical deviation compensation values closest to the date on which the first congestion degree is located from the historical deviation compensation value sequence ; wherein, =1,2,…,M; the mean of the deviation compensation value of the first congestion degree in the target sub-period and the selected M second historical deviation compensation values t as the deviation compensation value corresponding to the first congestion degree.

[0061] ​Thus, the M second historical deviation compensation values of the target sub-period of the distance target sub-period are extracted by the sliding window, and the mean of the first congestion degree deviation compensation value in the target sub-period and the M second historical deviation compensation values is calculated as the deviation compensation value corresponding to the first congestion degree, so as to focus on the recent historical deviation situation, weaken the historical deviation situation of distant dates, and make the deviation compensation value more consistent with the recent traffic rules.

[0062] For example, to predict the first congestion degree of 10:00-15:00 on the 10th, the target sub-period of the first congestion degree is 10:00-15:00 on the 10th. The second historical deviation compensation value is the deviation value of 1 day before 10:00-15:00 on the 10th. It can be understood that the second historical deviation compensation value is only the date different from the first congestion degree, and the sub-period belongs to the target sub-period of the first congestion degree. For example, l 1:00, l which is the deviation compensation value of 1 day before the target sub-period of the first congestion degree. That is 9:00-15:00 on the 9th.

[0063] For example, since the traffic data is easily affected by sudden factors, the deviation compensation value of the single day has a large fluctuation. Therefore, when calculating the mean of the M second historical deviation compensation values, if a second historical deviation compensation value with a large fluctuation is found, the mean of the M second historical deviation compensation values is taken as the correction value of the second historical deviation compensation value with a large fluctuation. The correction value and the mean of the other M-1 second historical deviation compensation values are taken as the corresponding deviation compensation values.

[0064] For example, the first congestion degree corresponding to the plurality of second historical deviation compensation values : The deviation between the actual first congestion degree and the predicted first congestion degree on the date of each second historical deviation compensation value is determined to determine the each second historical deviation compensation value . Alternatively, the deviation compensation function can be directly used to calculate the each second historical deviation compensation value . This is not limited here.

[0065] Preferably, the management module is specifically configured to: when the current time is earlier than the starting time of the traffic period, dynamically adjust the traffic area based on each first congestion situation; and when the current time is within the traffic period, dynamically adjust the traffic area based on each second congestion situation.

[0066] ​​The first congestion situation represents the predicted congestion situation of each road in the passing area when the truck is not allowed to enter the passing area, and the second congestion situation represents the actual congestion situation of each road in the passing area when the truck is allowed to enter the passing area. In this way, when the current time is earlier than the starting time of the passing period, the passing area is dynamically adjusted based on each first congestion situation, so that the server terminal can timely adjust the area where the truck is allowed to pass, and achieve pre-planning management. When the current time is in the passing period, the passing area is dynamically adjusted based on each second congestion situation, so that the server terminal can timely adjust the area where the truck is allowed to pass, and achieve adjustment management. The pre-planning management and the adjustment management are combined to balance the efficiency and quality of managing the truck passing.

[0067] For example, the first congestion situation is a plurality of second congestion degrees arranged in time sequence. When the current time is earlier than the starting time of the passing period, the passing area is dynamically adjusted based on each first congestion situation, including: for each road in the passing area, if the second congestion degree is greater than a third preset threshold, the road corresponding to the second congestion degree is regarded as a congested road, and the target sub-period corresponding to the second congestion degree is regarded as a congested period; and in the congested period, the congested road is excluded from the passing area, and the passing area after the exclusion is regarded as the dynamically adjusted passing area.

[0068] For example, the second congestion situation includes a plurality of sub-congestion situations arranged in time sequence. The sub-congestion situation represents the congestion degree of the road. When the current time is in the passing period, the passing area is dynamically adjusted based on each second congestion situation, including: since the second congestion situation is updated in real time or at intervals of a second preset time length, the sub-congestion situation (sub-congestion degree) of each road in the passing area updated in real time or at intervals of the second preset time length is obtained. For each road in the passing area, the congested road is excluded from the passing area based on the updated sub-congestion situation in real time or at intervals of the second preset time length, and the passing area after the exclusion is regarded as the dynamically adjusted passing area.

[0069] Preferably, in combination with Figure 2 as shown, Figure 2 Another truck passing management system based on traffic Internet of Things is provided. The server terminal of the truck passing management system based on traffic Internet of Things further comprises a suitability module, a score module and an incentive module. The suitability module is configured to determine the truck suitability of each road in the dynamically adjusted passing area in the passing period. The truck suitability represents the suitability score of the truck driving on the road. The score module is configured to accumulate the truck-friendly score based on the truck suitability of the road on which the truck drives when the truck drives in the dynamically adjusted passing area. The incentive module is configured to positively encourage the truck based on the truck-friendly score.

[0070] Thus, the truck suitability degree of the truck driving in each road in the dynamically adjusted passing area is determined by the suitability degree module, and the higher the suitability degree is, the more desirable it is for the truck to drive in the road. Therefore, the truck-friendly score is determined by the score module, and positive incentives are given to the truck based on the truck-friendly score by the incentive module, so as to drive the truck to drive in the road with a higher truck suitability degree.

[0071] For example, the positive incentives include road toll discounts, priority loading and unloading rights, tax exemptions, etc. The positive incentives are given to the truck based on the truck-friendly score, including: if the cumulative truck-friendly score is greater than a fourth preset threshold, the positive incentives are given to the truck.

[0072] For example, the truck-friendly score is accumulated based on the truck suitability degree of the road driven by the truck, including: the truck suitability degrees of the roads driven by the truck in the dynamically adjusted passing area are summed up to obtain the total truck suitability degree of the truck in the current passing period. The truck-friendly score of the current passing period is determined based on the total truck suitability degree. The truck-friendly scores of all passing periods are accumulated to obtain the truck-friendly score.

[0073] Preferably, the suitability degree module is specifically configured to: obtain the noise tolerance, the target congestion condition and the exhaust emission of the truck in the passing period for each road in the dynamically adjusted passing area; for each road in the dynamically adjusted passing area, determine a target congestion score corresponding to the target congestion condition and determine a pollution score corresponding to the exhaust emission of the truck; and for each road in the dynamically adjusted passing area, perform weighted summation on the noise tolerance, the target congestion score and the pollution score to determine the truck suitability degree of the road in the passing period.

[0074] The noise tolerance represents the tolerance of the community group to the noise generated by the truck passing, and the higher the tolerance is, the more willing the community group is to tolerate the truck passing.

[0075] Thus, by performing weighted summation on the noise tolerance, the target congestion score and the pollution score corresponding to each road respectively, the truck suitability degree of the road in the passing period is determined, so as to comprehensively determine the truck suitability degree of the road in the passing period from multiple aspects, so as to obtain a more scientific and reasonable suitability score of the truck driving in the road.

[0076] For example, the more the historical noise complaint situation, the greater the complaint score. The noise tolerance is determined as follows: determine the basic tolerance based on the functional area to which the road belongs; determine the complaint score based on the historical noise complaint situation of the functional area to which the road belongs. The difference between the basic tolerance and the complaint score is the noise tolerance. For example, the functional area to which the road belongs is residential, and the noise tolerance is low, which is 2 points. The historical complaint situation is general complaint, and the complaint score is 1 point. That is, the noise tolerance is the difference between the basic tolerance of 2 points and the complaint score of 1 point, which is 1 point.

[0077] For example, the noise tolerance is determined as follows: obtain the historical noise complaint situation, and construct a city noise heat map. The more serious the historical noise complaint situation, the darker the color of the city area corresponding to the complaint situation on the city noise heat map. The noise tolerance is inversely proportional to the color on the city noise heat map. That is, the darker the color, the lower the noise tolerance; the lighter the color, the higher the noise tolerance.

[0078] Similarly, the basic traffic score is determined based on the target congestion situation, and the congestion score is adjusted according to the first congestion situation or the second congestion situation. The difference between the basic traffic score and the congestion score is the target congestion score. The more congested the first congestion situation or the second congestion situation, the greater the congestion score.

[0079] The pollution score is negative, and the more the exhaust emission of the truck, the greater the absolute value of the negative score.

[0080] Finally, it should be pointed out that the above preferred embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made in form and detail without departing from the scope defined by the claims of the present application.

Claims

1. A truck passage management system based on a traffic Internet of Things, characterized by, include: The system comprises a data acquisition module, a server terminal, and a truck terminal, with the server terminal communicating with both the data acquisition module and the truck terminal. The data acquisition module is used to collect traffic information in the traffic area through road sensing devices and transmit the traffic information to the server terminal; wherein, the road sensing devices are installed along the road, and the traffic area represents the traffic area permitted by the truck pass; The server terminal includes a determination module, a management module, and a feedback module; among which, The determination module is used to determine the target congestion situation in the passage area during the passage period based on the passage information; where the passage period represents the passage period permitted by the truck pass. The management module is used to dynamically adjust the traffic area based on the target congestion situation of the traffic area during the traffic period; The feedback module is used to provide feedback on the dynamically adjusted passage area to the truck terminal. The determining module is specifically used for: determining the relationship between the current time and the traffic period; if the current time is earlier than the start time of the traffic period, predicting the first congestion situation of each road in the traffic area during the traffic period based on the traffic information of the target time period; and if the current time is within the traffic period, calculating the sub-congestion situation of each road in the traffic area at the current time based on the traffic information of the current time, until the current time is later than the end time of the traffic period, to obtain each second congestion situation; and using each first congestion situation and each second congestion situation as the target congestion situation of the traffic area during the traffic period. The method of predicting the first congestion situation of each road within the traffic area based on traffic information during the target time period includes: for each road within the traffic area, performing the following steps: based on the traffic information of the road during the target time period, predicting multiple first congestion levels of the road in chronological order during the traffic period; determining the deviation compensation value corresponding to each first congestion level; wherein, the deviation compensation value represents the difference between the actual congestion level and the first congestion level; based on the deviation compensation value corresponding to each first congestion level, performing deviation compensation on each first congestion level to obtain each second congestion level; and using each second congestion level in chronological order as the first congestion situation of the road during the traffic period. The step of determining the deviation compensation value corresponding to each first congestion level includes: selecting at least one deviation influencing factor as a target feature from multiple deviation influencing factors using Pearson correlation coefficient or Spearman correlation coefficient; constructing a deviation compensation function based on all target features; and determining the deviation compensation value corresponding to each first congestion level based on the deviation compensation function. The method comprises the following steps: obtaining historical traffic data; determining the parameter types of each bias influencing factor; calculating the Pearson correlation coefficient between the bias influencing factor and the first historical bias compensation value based on all historical traffic data for the bias influencing factor of the continuous variable type, and calculating the Spearman correlation coefficient between the bias influencing factor and the first historical bias compensation value based on all historical traffic data for the bias influencing factor of the ordered variable type; selecting the bias influencing factor with the Pearson correlation coefficient greater than a first preset threshold value and the bias influencing factor with the Spearman correlation coefficient greater than a second preset threshold value as the target feature.

2. The system of claim 1, wherein, The method comprises the following steps: obtaining historical traffic data; determining the parameter types of each bias influencing factor; calculating the Pearson correlation coefficient between the bias influencing factor and the first historical bias compensation value based on all historical traffic data for the bias influencing factor of the continuous variable type, and calculating the Spearman correlation coefficient between the bias influencing factor and the first historical bias compensation value based on all historical traffic data for the bias influencing factor of the ordered variable type; selecting the bias influencing factor with the Pearson correlation coefficient greater than a first preset threshold value and the bias influencing factor with the Spearman correlation coefficient greater than a second preset threshold value as the target feature. The method comprises the following steps: obtaining historical traffic data; determining the parameter types of each bias influencing factor; calculating the Pearson correlation coefficient between the bias influencing factor and the first historical bias compensation value based on all historical traffic data for the bias influencing factor of the continuous variable type, and calculating the Spearman correlation coefficient between the bias influencing factor and the first historical bias compensation value based on all historical traffic data for the bias influencing factor of the ordered variable type; selecting the bias influencing factor with the Pearson correlation coefficient greater than a first preset threshold value and the bias influencing factor with the Spearman correlation coefficient greater than a second preset threshold value as the target feature. The method comprises the following steps: obtaining historical traffic data; determining the parameter types of each bias influencing factor; calculating the Pearson correlation coefficient between the bias influencing factor and the first historical bias compensation value based on all historical traffic data for the bias influencing factor of the continuous variable type, and calculating the Spearman correlation coefficient between the bias influencing factor and the first historical bias compensation value based on all historical traffic data for the bias influencing factor of the ordered variable type; selecting the bias influencing factor with the Pearson correlation coefficient greater than a first preset threshold value and the bias influencing factor with the Spearman correlation coefficient greater than a second preset threshold value as the target feature.

3. The system of claim 1, wherein, The management module is specifically configured to: when the current time is earlier than the starting time of the traffic period, dynamically adjusting the traffic area based on the first congestion conditions; and when the current time is within the traffic period, dynamically adjusting the traffic area based on the second congestion conditions. The server terminal further comprises a suitability module, an integral module and an incentive module, wherein: the suitability module is configured to determine the truck suitability of each road in the dynamically adjusted traffic area within the traffic period; the integral module is configured to accumulate the truck-friendly integral based on the truck suitability of the road on which the truck travels when the truck travels in the dynamically adjusted traffic area; and the incentive module is configured to positively encourage the truck based on the truck-friendly integral. The suitability module is specifically configured to: obtain the noise tolerance, the target congestion condition and the exhaust emission of the truck of each road in the dynamically adjusted traffic area within the traffic period; determine the target congestion score corresponding to the target congestion condition and the pollution score corresponding to the exhaust emission of the truck for each road in the dynamically adjusted traffic area; and determine the truck suitability of the road in the traffic period by weighted sum of the noise tolerance, the target congestion score and the pollution score for each road in the dynamically adjusted traffic area. obtaining a plurality of second historical deviation compensation values corresponding to the first congestion degree ; wherein, l characterizing a deviation compensation value for a day preceding the date of the first congestion degree l characterizing a deviation compensation value for a day preceding the target sub-period of the first congestion degree l ;​ the respective second historical deviation compensation values in chronological order, obtaining a sequence of historical deviation compensation values; M second historical deviation compensation values closest to the date where the first congestion degree is located are selected from the historical deviation compensation value sequence by using a sliding window ; wherein t = 1, 2, …, M; The first congestion degree in the target sub-period is compensated by a deviation compensation value, and the selected M second historical deviation compensation values The mean value of the first congestion degree corresponding to the deviation compensation value.

4. The system according to any one of claims 1 to 3, characterized in that, ​ ​ ​ 5. The system of claim 1, wherein, ​ ​ ​ ​ 6. The system of claim 5, wherein, ​ ​ ​ ​

Images