A method, device, computer equipment and storage medium for recommending boarding points in a specific area
By setting areas on both sides of the road, collecting vehicle and pedestrian parameters, generating impact coefficients, dynamically comparing the congestion coefficient threshold, and recommending the boarding point in real time, solving the problem that static rules in the existing technology cannot adapt to real-time traffic changes, and improving boarding Point the recommended accuracy and optimization effect.
Patent Information
- Application Number
- CN202410484382.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-22
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-04-22
AI Technical Summary
The static rules of the existing online car-hailing site optimization methods cannot adapt to changes in real-time traffic conditions in a timely manner, resulting in the inability to fully utilize the optimization effect and may misjudgment of congestion.
By setting the main area and waiting area on both sides of the road, collecting vehicle and pedestrian parameters, generating impact coefficients, dynamically comparing the congestion coefficient threshold, and recommending the boarding point in real time.
Improve the accuracy of the recommended point of the car, avoid misjudgment of congestion, and enhance the dynamicity of the optimization effect.
Smart Images

Figure CN118262524B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of boarding point recommendation, and in particular to a method, device, computer equipment and storage medium for recommending boarding points in a specific area. Background Art
[0002] Online ride-hailing has gradually become part of people's lives. With the development of online ride-hailing technology, online rides have become the preferred way for people to travel. After a passenger places an order to generate a travel order, the driver who provides the service will accept the order and provide travel services. The online ride-hailing platform will generate a pick-up route based on the driver's current location and the pick-up point of the travel order, and send it to the passenger and driver's client respectively. The driver will go to the pick-up point according to the pick-up route, and the passenger will wait for the driver to arrive at the pick-up point.
[0003] In the prior art, the publication number CN116167539A discloses a method for optimizing the pick-up point of an online car-hailing service based on the real-time road conditions of the pick-up. The method includes the following steps: obtaining the pick-up route and pick-up point of the travel order, and monitoring whether the pick-up route is congested; identifying the continuous congested sections in the pick-up route, and the end point of the continuous congested section is the pick-up point; calculating the estimated first travel time based on the continuous congested section; when the continuous congested section or the first travel time meets the first preset rule, obtaining the optimized pick-up point according to the pick-up point and the real-time road conditions; and pushing the optimized pick-up point to the passenger end of the travel order. The present invention calculates whether there is a better pick-up point around the original pick-up point according to the real-time road conditions when the driver drives to the passenger pick-up point to pick up the passenger, and optimizes the pick-up point to enable the driver to arrive at the location faster to pick up the passenger.
[0004] However, there are still the following deficiencies. It can be seen from the above statements that when the continuous congested road section or the first travel time meets the first preset rule, the optimized boarding point is obtained according to the pick-up point and the real-time road conditions. It can be seen that the first preset rule is a statically set rule, which is not dynamically adjusted according to the real-time traffic conditions or passenger demand. Traffic congestion may occur in a certain period of time, but due to special circumstances or traffic control, the congestion situation may change rapidly. If the preset rule is statically set, it cannot adapt to such changes in time, resulting in the inability to fully exert the optimization effect, and may even misjudge the congestion situation.
[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0006] The purpose of the present invention is to provide a method, device, computer equipment and storage medium for recommending boarding points in a specific area to solve the problems raised in the above-mentioned background technology.
[0007] To achieve the above object, the present invention provides the following technical solutions:
[0008] A method for recommending a boarding point in a specific area, the specific steps comprising:
[0009] S1. Set a main area and a waiting area at relative positions on both sides of the road, set a main boarding point in the main area, set a waiting boarding point in the waiting area, collect vehicle parameters, pedestrian parameters and peak traffic flow during peak hours M meters before and after the main boarding point and the waiting boarding point, the vehicle parameters include vehicle flow, vehicle speed and road width, and the pedestrian parameters include pedestrian flow and travel speed;
[0010] S2. Process the vehicle flow, vehicle speed and road width of the main boarding point, and perform correlation analysis to generate the main vehicle influence coefficient; process the pedestrian flow and travel speed of the main boarding point, and perform correlation analysis to generate the main pedestrian influence coefficient; process the vehicle flow, vehicle speed and road width of the waiting boarding point, and perform correlation analysis to generate the waiting vehicle influence coefficient; process the pedestrian flow and travel speed of the waiting boarding point, and perform correlation analysis to generate the waiting pedestrian influence coefficient;
[0011] S3. The peak traffic flow rate of the main boarding point during the peak period is set as the main congestion coefficient threshold, and the peak traffic flow rate of the waiting boarding point during the peak period is set as the waiting congestion coefficient threshold;
[0012] S4. The main vehicle influence coefficient and the main pedestrian influence coefficient are processed and correlated to generate the main congestion coefficient, and the waiting vehicle influence coefficient and the waiting pedestrian influence coefficient are processed and correlated to generate the waiting congestion coefficient;
[0013] S5. Compare the main congestion coefficient with a preset main congestion coefficient threshold, compare the pending congestion coefficient with a preset pending congestion coefficient threshold, and recommend a boarding point based on the comparison results.
[0014] Furthermore, the vehicle flow, vehicle speed and road width of the main boarding point are processed and correlated to generate the main vehicle influence coefficient according to the following formula:
[0015]
[0016] in, is the main vehicle influence coefficient, The vehicle flow at the main pick-up point, is the vehicle speed at the main boarding point, The road width of the main pick-up point, The mutual influence of vehicle flow and vehicle speed at the main boarding point, The interaction between vehicle flow and road width at the main boarding point, The interaction between vehicle speed and road width at the main boarding point, is the factor coefficient of vehicle flow at the main boarding point, is the factor coefficient of the vehicle speed at the main boarding point, is the factor coefficient of the road width of the main pick-up point, The factor coefficient of the mutual influence between the vehicle flow and vehicle speed at the main boarding point, is the factor coefficient of the interaction between the vehicle flow and road width at the main boarding point, is the factor coefficient of the interaction between vehicle speed and road width at the main boarding point, is a constant correction factor, ,and .
[0017] Furthermore, the pedestrian flow and travel speed at the main boarding point are processed and correlation analyzed to generate the main pedestrian influence coefficient according to the following formula:
[0018]
[0019] in, is the main pedestrian influence coefficient, For pedestrian traffic, is the travel speed, is the intercept, is the factor coefficient of pedestrian flow at the main boarding point, is the factor coefficient of the travel speed of the main boarding point, is the error term, ,and .
[0020] Furthermore, the vehicle flow, vehicle speed and road width of the waiting boarding point are processed and correlation analyzed to generate the waiting vehicle influence coefficient, according to the following formula:
[0021]
[0022] in, is the main vehicle influence coefficient, The vehicle flow at the main pick-up point, is the vehicle speed at the main boarding point, The road width of the main pick-up point, The mutual influence of vehicle flow and vehicle speed at the main boarding point, The interaction between vehicle flow and road width at the main boarding point, The interaction between vehicle speed and road width at the main boarding point, is the factor coefficient of vehicle flow at the main boarding point, is the factor coefficient of the vehicle speed at the main boarding point, is the factor coefficient of the road width of the main pick-up point, The factor coefficient of the mutual influence between the vehicle flow and vehicle speed at the main boarding point, is the factor coefficient of the interaction between the vehicle flow and road width at the main boarding point, is the factor coefficient of the interaction between vehicle speed and road width at the main boarding point, is a constant correction factor, ,and .
[0023] Furthermore, the pedestrian flow and travel speed at the boarding point are processed and correlation analyzed to generate the pedestrian influence coefficient, according to the following formula:
[0024]
[0025] in, is the pedestrian impact coefficient, For pedestrian traffic, is the travel speed, is the intercept, is the factor coefficient of pedestrian flow at the main boarding point, is the factor coefficient of the travel speed of the main boarding point, is the error term, ,and .
[0026] Furthermore, the main vehicle influence coefficient and the main pedestrian influence coefficient are subjected to data processing and correlation analysis to generate a main congestion coefficient according to the following formula:
[0027]
[0028] in, is the main congestion coefficient, is the main vehicle influence coefficient, is the main pedestrian influence coefficient, is the factor coefficient of the main vehicle influence coefficient, is the factor coefficient of the main pedestrian influence coefficient, ,and ;
[0029] The vehicle impact coefficient and pedestrian impact coefficient are processed and correlated to generate a congestion coefficient. The formula is as follows:
[0030]
[0031] in, is the main congestion coefficient, is the main vehicle influence coefficient, is the main pedestrian influence coefficient, is the factor coefficient of the main vehicle influence coefficient, is the factor coefficient of the main pedestrian influence coefficient, ,and .
[0032] Furthermore, the peak traffic flow rate at the main boarding point during the peak period is set as the main congestion coefficient threshold, and the peak traffic flow rate at the waiting boarding point during the peak period is set as the waiting congestion coefficient threshold, according to the following formula:
[0033]
[0034] in, The peak traffic volume at the main boarding point during peak hours. is the main congestion coefficient threshold, The peak traffic volume at the main boarding point during peak hours. is the main congestion coefficient threshold;
[0035] The main congestion coefficient is compared with a preset main congestion coefficient threshold, and the pending congestion coefficient is compared with a preset pending congestion coefficient threshold. According to the comparison results, the process of recommending a boarding point is as follows:
[0036] If and only if,
[0037] , When the waiting point is set as the boarding point,
[0038] , When the main boarding point is used, the boarding point is recommended.
[0039] A device for recommending a boarding point in a specific area, the device being used to execute the above-mentioned method for recommending a boarding point in a specific area, comprising:
[0040] A data acquisition module is used to set a main area and a waiting area at relative positions on both sides of the road, set a main boarding point in the main area, set a waiting boarding point in the waiting area, and collect vehicle parameters, pedestrian parameters and peak traffic flow during peak hours M meters before and after the main boarding point and the waiting boarding point, wherein the vehicle parameters include vehicle flow, vehicle speed and road width, and the pedestrian parameters include pedestrian flow and travel speed;
[0041] a data processing module, for processing the vehicle flow, vehicle speed and road width of the main boarding point, and performing correlation analysis to generate a main vehicle influence coefficient; processing the pedestrian flow and travel speed of the main boarding point, and performing correlation analysis to generate a main pedestrian influence coefficient; processing the vehicle flow, vehicle speed and road width of the waiting boarding point, and performing correlation analysis to generate a waiting vehicle influence coefficient; processing the pedestrian flow and travel speed of the waiting boarding point, and performing correlation analysis to generate a waiting pedestrian influence coefficient;
[0042] A threshold setting module, used to set the peak value of the traffic flow at the main boarding point during the peak period as the main congestion coefficient threshold, and set the peak value of the traffic flow at the waiting boarding point during the peak period as the waiting congestion coefficient threshold;
[0043] A data analysis module, used for processing the main vehicle influence coefficient and the main pedestrian influence coefficient, and performing correlation analysis to generate a main congestion coefficient, processing the waiting vehicle influence coefficient and the waiting pedestrian influence coefficient, and performing correlation analysis to generate a waiting congestion coefficient;
[0044] The comparison module is used to compare the main congestion coefficient with a preset main congestion coefficient threshold, compare the pending congestion coefficient with a preset pending congestion coefficient threshold, and recommend a boarding point based on the comparison results.
[0045] A computer device comprising:
[0046] Memory, used to store computer programs;
[0047] A processor is used to execute the computer program to implement the above-mentioned method for recommending boarding points in a specific area.
[0048] A readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method for recommending a boarding point in a specific area is implemented.
[0049] Compared with the prior art, the present invention has the following beneficial effects:
[0050] The present invention collects vehicle parameters, pedestrian parameters and peak traffic volume in the M meters before and after the main boarding point and the waiting boarding point, processes and analyzes the vehicle parameters to generate the main vehicle influence coefficient, processes and analyzes the pedestrian parameters to generate the main pedestrian influence coefficient, processes and analyzes the vehicle parameters to generate the waiting vehicle influence coefficient, processes and analyzes the pedestrian parameters to generate the waiting pedestrian influence coefficient, processes and analyzes the main vehicle influence coefficient and the main pedestrian influence coefficient to generate the main congestion coefficient, and processes and analyzes the waiting vehicle influence coefficient and the waiting pedestrian influence coefficient. The peak value of the traffic flow at the main boarding point during the peak period is set as the main congestion coefficient threshold, and the peak value of the traffic flow at the waiting boarding point during the peak period is set as the waiting congestion coefficient threshold. The main congestion coefficient and the waiting congestion coefficient are obtained by real-time collection of vehicle parameters and pedestrian parameters at the main boarding point and the waiting boarding point. The main congestion coefficient is compared with the preset main congestion coefficient threshold, and the waiting congestion coefficient is compared with the preset waiting congestion coefficient threshold. According to the comparison result, the boarding point is recommended, so that the set rules can be dynamically adjusted to exert the optimization effect, thereby improving the accuracy of boarding point recommendation and avoiding misjudgment of congestion conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 It is a schematic diagram of the overall method flow of the present invention;
[0052] Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION
[0053] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.
[0054] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0055] Example:
[0056] See also Figure 1, the present invention provides a technical solution:
[0057] A method for recommending boarding points in a specific area, such as Figure 1 As shown, the specific steps include:
[0058] S1. Set a main area and a waiting area at relative positions on both sides of the road, set a main boarding point in the main area, set a waiting boarding point in the waiting area, collect vehicle parameters, pedestrian parameters and peak traffic flow during peak hours M meters before and after the main boarding point and the waiting boarding point, the vehicle parameters include vehicle flow, vehicle speed and road width, and the pedestrian parameters include pedestrian flow and travel speed;
[0059] S2. Process the vehicle flow, vehicle speed and road width of the main boarding point, and perform correlation analysis to generate the main vehicle influence coefficient; process the pedestrian flow and travel speed of the main boarding point, and perform correlation analysis to generate the main pedestrian influence coefficient; process the vehicle flow, vehicle speed and road width of the waiting boarding point, and perform correlation analysis to generate the waiting vehicle influence coefficient; process the pedestrian flow and travel speed of the waiting boarding point, and perform correlation analysis to generate the waiting pedestrian influence coefficient;
[0060] S3. The peak traffic flow rate of the main boarding point during the peak period is set as the main congestion coefficient threshold, and the peak traffic flow rate of the waiting boarding point during the peak period is set as the waiting congestion coefficient threshold;
[0061] S4. The main vehicle influence coefficient and the main pedestrian influence coefficient are processed and correlated to generate the main congestion coefficient, and the waiting vehicle influence coefficient and the waiting pedestrian influence coefficient are processed and correlated to generate the waiting congestion coefficient;
[0062] S5. Compare the main congestion coefficient with a preset main congestion coefficient threshold, compare the pending congestion coefficient with a preset pending congestion coefficient threshold, and recommend a boarding point based on the comparison results.
[0063] In this embodiment, the main boarding point is the first choice. When the congestion coefficient of the main boarding point exceeds the set threshold, the boarding point is changed to the waiting boarding point. The vehicle parameters, pedestrian parameters and peak traffic flow during peak hours are collected M meters before and after the main boarding point and the waiting boarding point, where M is 50 meters.
[0064] In this embodiment, the main area and the waiting area are both circular areas with the same radius.
[0065] The values of vehicle flow, vehicle speed, and road width will affect the choice of pick-up point for the following reasons:
[0066] Vehicle flow:
[0067] Vehicle flow density: Areas with high vehicle flow density usually indicate high traffic congestion. Choosing such areas as pick-up points may result in increased passenger waiting time and trip delays.
[0068] Service capacity: Excessive vehicle flow around the boarding point may affect the convenience of passengers boarding the bus and the space for vehicle parking, reducing the service capacity of the boarding point.
[0069] Vehicle speed:
[0070] Traffic efficiency: Areas with lower vehicle speeds often represent traffic congestion or traffic jams. Choosing such areas as pick-up points may result in increased passenger waiting time and longer travel times.
[0071] Safety: Choosing areas with higher vehicle speeds as pick-up points can improve passenger safety because it is safer to board and alight on roads with higher speeds.
[0072] Road width:
[0073] Capacity: Areas with narrow road widths may limit vehicle capacity, causing traffic congestion and slow movement. Choosing such areas as pick-up points may affect traffic flow and the convenience of passengers getting on and off the bus.
[0074] Stopping space: Areas with sufficiently wide roads can provide ample stopping space, making it easier for vehicles to stop and passengers to get on and off, thus improving the service efficiency and convenience of the boarding point.
[0075] In summary, the values of vehicle flow, vehicle speed and road width will directly affect the selection of the boarding point. Selecting a suitable boarding point requires comprehensive consideration of the above parameters.
[0076] Similarly, the values of pedestrian flow and travel speed will affect the choice of boarding point. The following are the specific reasons:
[0077] Pedestrian flow:
[0078] Boarding and alighting efficiency: Areas with high pedestrian traffic may cause crowding around the boarding point, affecting the efficiency of passenger boarding and alighting, especially during peak hours or congested traffic scenarios.
[0079] Safety considerations: Excessive pedestrian flow may increase the risk of traffic accidents. Choosing a boarding point with moderate pedestrian flow can improve passenger safety.
[0080] Travel speed:
[0081] Travel time: Areas with lower travel speeds often indicate dense crowds or traffic congestion, and choosing such areas as pick-up points may increase passengers' travel time.
[0082] Convenience: Higher travel speed zones mean pedestrians can reach their boarding points faster, improving passenger convenience, especially when traffic is light.
[0083] In summary, comprehensive consideration of pedestrian flow and travel speed values can help choose a suitable boarding point.
[0084] On the basis of the above embodiment, the vehicle flow, vehicle speed and road width of the main boarding point are processed and correlation analyzed to generate the main vehicle influence coefficient according to the following formula:
[0085]
[0086] in, is the main vehicle influence coefficient, The vehicle flow at the main pick-up point, is the vehicle speed at the main boarding point, The road width of the main pick-up point, The mutual influence of vehicle flow and vehicle speed at the main boarding point, The interaction between vehicle flow and road width at the main boarding point, The interaction between vehicle speed and road width at the main boarding point, is the factor coefficient of vehicle flow at the main boarding point, is the factor coefficient of the vehicle speed at the main boarding point, is the factor coefficient of the road width of the main pick-up point, The factor coefficient of the mutual influence between the vehicle flow and vehicle speed at the main boarding point, is the factor coefficient of the interaction between the vehicle flow and road width at the main boarding point, is the factor coefficient of the interaction between vehicle speed and road width at the main boarding point, is a constant correction factor, ,and .
[0087] In the case of road congestion, the impact coefficient of vehicle flow may be high. When the vehicle flow on the road increases, the road capacity is approached or exceeded, and the distance between vehicles is reduced, resulting in increased interaction and competition between vehicles, which aggravates the road congestion. In general, higher vehicle speeds may have a smaller impact coefficient on road congestion. This is because higher vehicle speeds mean that vehicles can pass through road sections faster, reducing mutual interference and competition between vehicles and allowing for smoother driving. The impact coefficient of vehicle speed may be negative, indicating that the higher the speed, the smaller the impact on congestion. In general, the impact coefficient of road width on road congestion may be large. Wider roads can accommodate more vehicles and provide vehicles with more driving space, reducing interference and competition between vehicles, thereby alleviating congestion. The impact coefficient of road width may be negative, indicating that the larger the width, the smaller the impact on congestion. However, the normal road width will not be infinitely wide and is a fixed value, so the factor coefficient of vehicle speed is larger than the factor coefficient of road width.
[0088] Due to the mutual influence of vehicle flow and vehicle speed, part of the influence of vehicle flow and vehicle speed on road congestion will be offset, making the mutual influence factor coefficient of vehicle flow and vehicle speed at the main boarding point smaller than the factor coefficient of road width at the main boarding point. Since the factor coefficient of vehicle speed at the main boarding point is larger than the factor coefficient of road width at the main boarding point, the mutual influence factor coefficient of vehicle flow and vehicle speed at the main boarding point is larger than the factor coefficient of vehicle flow and road width at the main boarding point. Since the factor coefficient of vehicle flow at the main boarding point is larger than the factor coefficient of vehicle speed at the main boarding point, the mutual influence factor coefficient of vehicle flow and road width at the main boarding point is larger than the factor coefficient of vehicle speed and road width at the main boarding point. Therefore, it is set , without considering other parameters, .
[0089] The relationship between vehicle flow, vehicle speed and road width and road congestion is usually nonlinear. Polynomial functions can capture nonlinear relationships more flexibly. By describing their respective influences through quadratic terms and cross terms, polynomial functions can more accurately reflect the complex influence of vehicle flow, vehicle speed and road width on road congestion. Polynomial functions can also determine the values of each coefficient by fitting actual data, thereby establishing a specific functional relationship between vehicle flow, vehicle speed, road width and the main vehicle influence coefficient. By collecting and analyzing a large amount of traffic data, more accurate function fitting results can be obtained to predict and analyze road congestion under different conditions.
[0090] In summary, using polynomial functions to express the functional relationship among vehicle flow, vehicle speed, road width and main vehicle influence coefficient can better capture nonlinear relationships, has good model interpretability, and can obtain specific function forms and parameter estimation results through data fitting, which is helpful to understand and predict road congestion.
[0091] On the basis of the above embodiment, the pedestrian flow and travel speed at the main boarding point are processed and correlation analyzed to generate the main pedestrian influence coefficient, according to the following formula:
[0092]
[0093] in, is the main pedestrian influence coefficient, For pedestrian traffic, is the travel speed, is the intercept, is the factor coefficient of pedestrian flow at the main boarding point, is the factor coefficient of the travel speed of the main boarding point, is the error term, ,and .
[0094] An increase in pedestrian flow may mean that there is more population density in the surrounding environment, which will increase the interaction and competition between people, thus affecting the behavior and speed of the main pedestrian. Even if the travel speed is faster, pedestrians may still be crowded and obstructed in a high-density crowd, resulting in the main pedestrian impact coefficient being greatly affected by pedestrian flow. In addition, an increase in pedestrian flow may lead to reduced traffic fluidity, causing the main pedestrian to encounter more obstacles and delays during travel. Even if the travel speed is faster, due to the influence of congestion and obstruction, the main pedestrian's travel speed may still be restricted by pedestrian flow. Overall, the pedestrian flow has a greater impact on the main pedestrian impact coefficient than the travel speed, which may be the result of the combined effect of increased population density and reduced traffic fluidity. Therefore, setting , without considering other parameters, .
[0095] The multivariate linear regression equation assumes that there is a linear relationship between the main pedestrian influence coefficient and the pedestrian flow and travel speed at the main boarding point, that is, the relationship between them can be expressed by a linear equation. By minimizing the sum of squares of the prediction errors, the factor coefficients of the pedestrian flow at the main boarding point, the factor coefficients of the travel speed at the main boarding point and the value of the intercept in the equation can be estimated. The above coefficients describe the degree of influence of the independent variable on the dependent variable. By fitting the model using actual observation data, the degree of fit of the model can be evaluated.
[0096] On the basis of the above embodiment, similarly, the vehicle flow, vehicle speed and road width of the waiting boarding point are processed and correlation analysis is performed to generate the waiting vehicle influence coefficient, based on the following formula:
[0097]
[0098] in, is the main vehicle influence coefficient, The vehicle flow at the main pick-up point, is the vehicle speed at the main boarding point, The road width of the main pick-up point, The mutual influence of vehicle flow and vehicle speed at the main boarding point, The interaction between vehicle flow and road width at the main boarding point, The interaction between vehicle speed and road width at the main boarding point, is the factor coefficient of vehicle flow at the main boarding point, is the factor coefficient of the vehicle speed at the main boarding point, is the factor coefficient of the road width of the main pick-up point, The factor coefficient of the mutual influence between the vehicle flow and vehicle speed at the main boarding point, is the factor coefficient of the interaction between the vehicle flow and road width at the main boarding point, is the factor coefficient of the interaction between vehicle speed and road width at the main boarding point, is a constant correction factor, ,and .
[0099] Similarly, polynomial functions can be used to characterize the complex impact of vehicle flow, vehicle speed and road width on road congestion. The values of each coefficient can also be determined by fitting actual data, thereby establishing a specific functional relationship between vehicle flow, vehicle speed, road width and the impact coefficient of the vehicle to be affected.
[0100] On the basis of the above embodiment, similarly, the pedestrian flow and travel speed at the waiting boarding point are processed and correlation analysis is performed to generate the waiting pedestrian influence coefficient, based on the following formula:
[0101]
[0102] in, is the pedestrian impact coefficient, For pedestrian traffic, is the travel speed, is the intercept, is the factor coefficient of pedestrian flow at the main boarding point, is the factor coefficient of the travel speed of the main boarding point, is the error term, ,and .
[0103] Similarly, the linear relationship between the pedestrian impact coefficient and the pedestrian flow and travel speed at the boarding point can be characterized by using a multivariate linear regression equation, that is, the relationship between them can be expressed by a linear equation. By minimizing the sum of squares of the prediction error, the factor coefficient of the pedestrian flow at the boarding point, the factor coefficient of the travel speed at the boarding point and the value of the intercept in the equation can be estimated. The above coefficients describe the degree of influence of the independent variable on the dependent variable. By fitting the model using actual observation data, the degree of fit of the model can be evaluated.
[0104] On the basis of the above embodiment, the main vehicle influence coefficient and the main pedestrian influence coefficient are subjected to data processing and correlation analysis to generate a main congestion coefficient, according to the following formula:
[0105]
[0106] in, is the main congestion coefficient, is the main vehicle influence coefficient, is the main pedestrian influence coefficient, is the factor coefficient of the main vehicle influence coefficient, is the factor coefficient of the main pedestrian influence coefficient, ,and .
[0107] Because vehicles usually need more space and time to move, especially in high-density traffic, which will cause road capacity saturation and traffic congestion. In contrast, the impact of pedestrian flow on traffic congestion may be relatively small, especially in vehicle-dominated traffic systems. Pedestrians are usually more flexible in adapting to and bypassing traffic congestion, while the movement of vehicles is more significantly affected by road conditions and other vehicles. Therefore, setting .
[0108] The above equation is a simplified function that only considers the influence of the main vehicle influence coefficient and the main pedestrian influence coefficient on the main congestion coefficient. Since there is a linear relationship between the main vehicle influence coefficient and the main pedestrian influence coefficient and the main congestion coefficient, respectively, the above function can be used to represent the relationship between the three.
[0109] Similarly, the vehicle impact coefficient and pedestrian impact coefficient are processed and correlated to generate a congestion coefficient according to the following formula:
[0110]
[0111] in, is the main congestion coefficient, is the main vehicle influence coefficient, is the main pedestrian influence coefficient, is the factor coefficient of the main vehicle influence coefficient, is the factor coefficient of the main pedestrian influence coefficient, ,and .
[0112] On the basis of the above embodiment, the peak traffic flow rate at the main boarding point during the peak period is set as the main congestion coefficient threshold, and the peak traffic flow rate at the waiting boarding point during the peak period is set as the waiting congestion coefficient threshold, according to the following formula:
[0113]
[0114] in, The peak traffic volume at the main boarding point during peak hours. is the main congestion coefficient threshold, The peak traffic volume at the main boarding point during peak hours. The main congestion coefficient threshold.
[0115] Among them, the peak traffic flow peak acquisition process during peak hours:
[0116] Data collection: Collect real-time or historical data on the traffic flow at the main boarding point and waiting boarding point. These data come from traffic monitoring equipment and traffic cameras.
[0117] Determine the observation period: determine the peak time period of the main boarding point and the waiting boarding point. Usually the peak time is the time of the day when the traffic volume is the largest, such as the morning rush hour or the time after get off work;
[0118] Data screening: Filter the collected data and only keep the data within the peak period;
[0119] Traffic flow statistics: Statistics and analysis of traffic flow data during peak hours to find the peak traffic flow can be achieved by calculating the traffic flow in each time interval and finding the maximum value.
[0120] On the basis of the above embodiment, the main congestion coefficient is compared with a preset main congestion coefficient threshold, and the pending congestion coefficient is compared with a preset pending congestion coefficient threshold. According to the comparison results, the process of recommending a boarding point is as follows:
[0121] If and only if,
[0122] , When the waiting point is set as the boarding point,
[0123] , When the main boarding point is used, the boarding point is recommended.
[0124] In the formula , , , , , , , , , , , , , , , , , , and The specific value of is generally determined by those skilled in the art according to actual conditions. The essence of this formula is a comprehensive analysis by weighted summation. The technicians in this field collect multiple groups of sample data, set corresponding preset proportional coefficients for each group of sample data, substitute the preset proportional coefficients and the collected sample data into the formula, observe the accuracy of the model output and the rationality of the results through repeated experiments and parameter adjustments, gradually adjust these factor coefficients, and compare the performance and effect of the model under different parameter settings to find the optimal coefficient combination, screen the calculated factor coefficients and take the average, and obtain , , , , , , , , , , , , , , , , , , and The value of .
[0125] In addition, the size of the preset factor coefficient is to quantify each parameter to obtain a specific value. In order to facilitate subsequent comparison, the size of the coefficient depends on the amount of sample data and the preset proportional coefficient initially set by technical personnel in this field for each set of sample data. It is not unique as long as it does not affect the proportional relationship between the parameter and the quantized value.
[0126] A device for recommending boarding points in a specific area, the device is used to execute the above-mentioned method for recommending boarding points in a specific area, such as Figure 2 As shown, including:
[0127] A data acquisition module is used to set a main area and a waiting area at relative positions on both sides of the road, set a main boarding point in the main area, set a waiting boarding point in the waiting area, and collect vehicle parameters, pedestrian parameters and peak traffic flow during peak hours M meters before and after the main boarding point and the waiting boarding point, wherein the vehicle parameters include vehicle flow, vehicle speed and road width, and the pedestrian parameters include pedestrian flow and travel speed;
[0128] a data processing module, for processing the vehicle flow, vehicle speed and road width of the main boarding point, and performing correlation analysis to generate a main vehicle influence coefficient; processing the pedestrian flow and travel speed of the main boarding point, and performing correlation analysis to generate a main pedestrian influence coefficient; processing the vehicle flow, vehicle speed and road width of the waiting boarding point, and performing correlation analysis to generate a waiting vehicle influence coefficient; processing the pedestrian flow and travel speed of the waiting boarding point, and performing correlation analysis to generate a waiting pedestrian influence coefficient;
[0129] A threshold setting module, used to set the peak value of the traffic flow at the main boarding point during the peak period as the main congestion coefficient threshold, and set the peak value of the traffic flow at the waiting boarding point during the peak period as the waiting congestion coefficient threshold;
[0130] A data analysis module, used for processing the main vehicle influence coefficient and the main pedestrian influence coefficient, and performing correlation analysis to generate a main congestion coefficient, processing the waiting vehicle influence coefficient and the waiting pedestrian influence coefficient, and performing correlation analysis to generate a waiting congestion coefficient;
[0131] The comparison module is used to compare the main congestion coefficient with a preset main congestion coefficient threshold, compare the pending congestion coefficient with a preset pending congestion coefficient threshold, and recommend a boarding point based on the comparison results.
[0132] A computer device comprising:
[0133] Memory, used to store computer programs;
[0134] A processor is used to execute the computer program to implement the above-mentioned method for recommending boarding points in a specific area.
[0135] A readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method for recommending a boarding point in a specific area is implemented.
[0136] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0137] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.
[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0139] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. A method for recommending boarding points in a specific area, characterized in that: The specific steps include: S1. Set a main area and a waiting area at relative positions on both sides of the road, set a main boarding point in the main area, set a waiting boarding point in the waiting area, collect vehicle parameters, pedestrian parameters and peak traffic flow during peak hours M meters before and after the main boarding point and the waiting boarding point, the vehicle parameters include vehicle flow, vehicle speed and road width, and the pedestrian parameters include pedestrian flow and travel speed; S2. Process the vehicle flow, vehicle speed and road width of the main boarding point, and perform correlation analysis to generate the main vehicle influence coefficient; process the pedestrian flow and travel speed of the main boarding point, and perform correlation analysis to generate the main pedestrian influence coefficient; process the vehicle flow, vehicle speed and road width of the waiting boarding point, and perform correlation analysis to generate the waiting vehicle influence coefficient; process the pedestrian flow and travel speed of the waiting boarding point, and perform correlation analysis to generate the waiting pedestrian influence coefficient; S3. The peak traffic flow rate of the main boarding point during the peak period is set as the main congestion coefficient threshold, and the peak traffic flow rate of the waiting boarding point during the peak period is set as the waiting congestion coefficient threshold; S4. The main vehicle influence coefficient and the main pedestrian influence coefficient are processed and correlated to generate the main congestion coefficient, and the waiting vehicle influence coefficient and the waiting pedestrian influence coefficient are processed and correlated to generate the waiting congestion coefficient; S5. Compare the main congestion coefficient with a preset main congestion coefficient threshold, compare the pending congestion coefficient with a preset pending congestion coefficient threshold, and recommend a boarding point based on the comparison result; The vehicle flow, vehicle speed and road width of the main boarding point are processed and correlated to generate the main vehicle influence coefficient according to the following formula: Among them, XS zc is the main vehicle influence coefficient, CL zd The vehicle flow at the main boarding point, CS zd The vehicle speed at the main boarding point, DK zd The road width of the main boarding point, CL zd CS zd The mutual influence of vehicle flow and vehicle speed at the main boarding point, CL zd ·DK zd The interaction between the vehicle flow and road width at the main boarding point, CS zd ·DK zd The mutual influence of the vehicle speed and road width at the main boarding point, α1 is the factor coefficient of the vehicle flow at the main boarding point, β1 is the factor coefficient of the vehicle speed at the main boarding point, γ1 is the factor coefficient of the road width at the main boarding point, η1 is the factor coefficient of the mutual influence of the vehicle flow and vehicle speed at the main boarding point, ε1 is the factor coefficient of the mutual influence of the vehicle flow and road width at the main boarding point, is the factor coefficient of the interaction between the vehicle speed and road width at the main boarding point, C1 is the constant correction coefficient, and The pedestrian flow and travel speed at the main boarding point are processed and correlated to generate the main pedestrian impact coefficient, based on the following formula: XS zr =b1+δ1LL zr +λ1SD zr +ε1 Among them, XS zr is the main pedestrian influence coefficient, LL zr For pedestrian traffic, SD zr is the travel speed, b1 is the intercept, δ1 is the factor coefficient of the pedestrian flow at the main boarding point, λ1 is the factor coefficient of the travel speed at the main boarding point, ε1 is the error term, δ1>λ1>0, and δ1+λ1=1.
2. The method for recommending boarding points in a specific area according to claim 1, characterized in that: The vehicle flow, vehicle speed and road width of the boarding point are processed and correlated to generate the impact coefficient of the boarding vehicle, according to the following formula: Among them, XS dc is the main vehicle influence coefficient, CL dd The vehicle flow at the main boarding point, CS dd The vehicle speed at the main boarding point, DK dd The road width of the main boarding point, CL dd CS dd The mutual influence of vehicle flow and vehicle speed at the main boarding point, CL dd ·DK dd The interaction between the vehicle flow and road width at the main boarding point, CS dd ·DK dd The mutual influence of the vehicle speed and road width at the main boarding point, α2 is the factor coefficient of the vehicle flow at the main boarding point, β2 is the factor coefficient of the vehicle speed at the main boarding point, γ2 is the factor coefficient of the road width at the main boarding point, η2 is the factor coefficient of the mutual influence of the vehicle flow and vehicle speed at the main boarding point, ε2 is the factor coefficient of the mutual influence of the vehicle flow and road width at the main boarding point, is the factor coefficient of the interaction between the vehicle speed and road width at the main boarding point, C2 is the constant correction coefficient, and 3. The method for recommending boarding points in a specific area according to claim 1, characterized in that: The pedestrian flow and travel speed at the boarding point are processed and correlation analyzed to generate the pedestrian impact coefficient, based on the following formula: XS dr =b2+δ2LL dr +λ2SD dr +ε2 Among them, XS dr is the pedestrian influence coefficient, LL dr For pedestrian traffic, SD dr is the travel speed, b2 is the intercept, δ2 is the factor coefficient of the pedestrian flow at the main boarding point, λ2 is the factor coefficient of the travel speed at the main boarding point, ε2 is the error term, δ2>λ2>0, and δ2+λ2=1.
4. The method for recommending boarding points in a specific area according to claim 1, characterized in that: The main vehicle influence coefficient and the main pedestrian influence coefficient are processed and correlated to generate a main congestion coefficient according to the following formula: XS zy =μ1XS zc +θ1XS zr Among them, XS zy The main congestion coefficient, XS zc is the main vehicle influence coefficient, XS zr is the main pedestrian influence coefficient, μ1 is the factor coefficient of the main vehicle influence coefficient, θ1 is the factor coefficient of the main pedestrian influence coefficient, μ1>θ1>0, and μ1+θ1=1; The vehicle impact coefficient and pedestrian impact coefficient are processed and correlated to generate a congestion coefficient. The formula is as follows: XS dy =μ2XS dc +θ2XS dr Among them, XS dy The main congestion coefficient, XS dc is the main vehicle influence coefficient, XS dr is the main pedestrian influence coefficient, μ2 is the factor coefficient of the main vehicle influence coefficient, θ2 is the factor coefficient of the main pedestrian influence coefficient, μ2>θ2>0, and μ2+θ2=1.
5. The method for recommending boarding points in a specific area according to claim 1, characterized in that: The peak traffic flow rate at the main boarding point during the peak period is set as the main congestion coefficient threshold, and the peak traffic flow rate at the waiting boarding point during the peak period is set as the waiting congestion coefficient threshold, according to the following formula: Among them, CL zg The peak traffic volume at the main boarding point during peak hours, YZ zy is the main congestion coefficient threshold, CL dg The peak traffic volume at the main boarding point during peak hours, YZ dy is the main congestion coefficient threshold; The main congestion coefficient is compared with a preset main congestion coefficient threshold, and the pending congestion coefficient is compared with a preset pending congestion coefficient threshold. According to the comparison results, the process of recommending a boarding point is as follows: If and only if, XS zy ≥YZ zy , XS dy <YZ dy When the waiting point is set as the boarding point, XS zy <YZ zy , XS dy ≥YZ dy When the main boarding point is used, the boarding point is recommended.
6. A device for recommending a boarding point in a specific area, the device executing the method for recommending a boarding point in a specific area according to any one of claims 1 to 5, comprising: A data acquisition module is used to set a main area and a waiting area at relative positions on both sides of the road, set a main boarding point in the main area, set a waiting boarding point in the waiting area, and collect vehicle parameters, pedestrian parameters and peak traffic flow during peak hours M meters before and after the main boarding point and the waiting boarding point, wherein the vehicle parameters include vehicle flow, vehicle speed and road width, and the pedestrian parameters include pedestrian flow and travel speed; a data processing module, for processing the vehicle flow, vehicle speed and road width of the main boarding point, and performing correlation analysis to generate a main vehicle influence coefficient; processing the pedestrian flow and travel speed of the main boarding point, and performing correlation analysis to generate a main pedestrian influence coefficient; processing the vehicle flow, vehicle speed and road width of the waiting boarding point, and performing correlation analysis to generate a waiting vehicle influence coefficient; processing the pedestrian flow and travel speed of the waiting boarding point, and performing correlation analysis to generate a waiting pedestrian influence coefficient; A threshold setting module, used to set the peak value of the traffic flow at the main boarding point during the peak period as the main congestion coefficient threshold, and set the peak value of the traffic flow at the waiting boarding point during the peak period as the waiting congestion coefficient threshold; A data analysis module, used for processing the main vehicle influence coefficient and the main pedestrian influence coefficient, and performing correlation analysis to generate a main congestion coefficient, processing the waiting vehicle influence coefficient and the waiting pedestrian influence coefficient, and performing correlation analysis to generate a waiting congestion coefficient; The comparison module is used to compare the main congestion coefficient with a preset main congestion coefficient threshold, compare the pending congestion coefficient with a preset pending congestion coefficient threshold, and recommend a boarding point based on the comparison results.
7. A computer device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the method for recommending a boarding point in a specific area as described in any one of claims 1 to 5.
8. A readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the method for recommending a boarding point in a specific area as described in any one of claims 1 to 5.
