Heterogeneous initial pricing method and device for long-range autonomous valet parking service in parking lots

Abstract

The present invention discloses a parking lot heterogeneous initial pricing method and device for long-range autonomous valet parking service, which belongs to the field of parking service management in intelligent transportation systems. In long-range autonomous valet parking, the parking demand of the parking lot is estimated by analyzing the geographical topological relationship between the parking lot and the unloading point. For parking lots with high parking demand, the initial parking price is increased by analyzing the characteristics of the unloading point near the parking lot, and the parking demand is induced to the parking lot with lower demand. The heterogeneous initial pricing technology can effectively alleviate the parking difficulty problem by balancing the parking demand between parking lots, reducing parking costs and reducing traffic congestion.

Description

Technical Field

[0001] The present invention relates to the technical field of parking service management in an intelligent transportation system, and in particular to a parking lot heterogeneous initial pricing method and device for long-distance autonomous valet parking services. Background Art

[0002] In recent years, the number of cars on the road has continued to rise, while the pace of parking resources (parking spaces) has far outstripped the growth in the number of cars. This has made parking a major challenge in urban transportation. Research suggests that 30% of traffic congestion is caused by cars constantly cruising along roads and parking lots in search of available spaces. Consequently, parking has become a major research priority. With the development of self-driving cars, autonomous valet parking has become an advanced technological solution to this problem.

[0003] Based on the vehicle's level of autonomy, autonomous valet parking can be divided into short-range autonomous valet parking and long-range autonomous valet parking. In short-range autonomous valet parking, users get off / on at the parking lot entrance, and the vehicle then autonomously completes the parking / driving behavior. Long-range autonomous valet parking can expand autonomous valet parking to a larger area, allowing the vehicle to drop off / on the user closer to the final destination (unloading / loading point) rather than at the parking lot entrance, as shown in the following figure. Figure 2 shown.

[0004] In most existing long-range autonomous valet parking studies, parking lots are initially priced fixed, leading to an imbalance in parking demand across lots, which in turn increases parking costs and causes traffic congestion. A parking pricing adjustment project by the San Francisco Department of Transportation showed that fixed parking prices lead to significant heterogeneity in parking demand across the geographic distribution of parking lots. Specifically, parking lots located in central areas with more and closer destinations experience greater parking demand, primarily because passengers (drivers) tend to walk from the parking lot to their destination as quickly as possible. In contrast, in long-range autonomous valet parking studies, fixed parking prices lead to greater parking demand in lots with more and closer drop-off points, as vehicles tend to drive from drop-off points to the parking lot as quickly as possible to reduce vehicle energy consumption. This imbalance in parking demand leads to overuse of parking lots with higher demand, resulting in traffic congestion in the surrounding areas, while leaving spaces unused in lots with lower demand. Summary of the Invention

[0005] The present invention addresses the imbalance in parking demand caused by fixed parking prices in parking lots, which in turn leads to problems such as increased parking costs and road traffic congestion. By analyzing the geographical topological relationship between parking lots and unloading points, the present invention establishes heterogeneous initial pricing for parking lots, thereby balancing parking demand.

[0006] In order to achieve the above object, the technical solution of the present invention is:

[0007] The first aspect provides a parking lot heterogeneous initial pricing method for long-range autonomous valet parking services, including:

[0008] S1: Determine the ideal number of adjacent unloading points for each parking lot when the parking demand is in equilibrium. A nearby unloading point is a point whose parking cost is no less than the cost of parking lot i for any parking lot i′ in the parking lot set, where i′ is a different parking lot from i.

[0009] S2: Based on the estimated parking cost from the unloading point to the parking lot in the initial state, analyze the current distribution of the adjacent unloading points in each parking lot;

[0010] S3: For all parking lots, determine whether the parking lot needs to adjust its pricing based on the relationship between the current number of adjacent unloading points and the ideal number of adjacent unloading points for each parking lot;

[0011] S4: For parking lots that require pricing adjustments, determine the pricing increment based on their proximity to unloading points;

[0012] S5: Adjust the initial pricing of the parking lot based on the pricing increment.

[0013] In one embodiment, when the parking demand is in equilibrium in step S1, the number of ideal adjacent unloading points in each parking lot is within the interval [D min ,D max ], D nin and D max Determined by the following formula:

[0014]

[0015] where Ω pl and Ω dp denote the parking lot set and the unloading point set respectively, |Ω pl | and |Ω dp | represents the total number of parking lots and unloading points, and |Ω pl |Not greater than|Ω dp |, floor(*) is the floor rounding function, and ceil(*) is the ceiling rounding function.

[0016] In one embodiment, in step S2, the parking cost from the unloading point to the parking lot in the initial state is estimated according to the following formula:

[0017]

[0018] Among them, C ij represents the expected parking cost from unloading point j to parking lot i, T ijrepresents the driving time cost from unloading point j to parking lot i, in seconds; F i The cost of parking at parking lot i is in yuan; α is the unit time value, which is used to convert currency units into time units;

[0019] The proximity to the unloading point has the following properties:

[0020]

[0021] Among them, Ω pl Represents a parking lot collection.

[0022] In one embodiment, step S3 includes:

[0023] Determine the number of unloading points D adjacent to parking lot i i Is it greater than the ideal number of unloading points? If so, it indicates that parking lot i faces a high parking demand and needs to adjust the pricing; otherwise, no pricing adjustment is required.

[0024] In one embodiment, the pricing increment in step S4 is determined as follows:

[0025] For parking lot i that needs to adjust pricing, estimate the second minimum parking cost C between the unloading point and other parking lots. kj :

[0026]

[0027] Calculate the cost difference Diff between the nearest unloading point to parking lot i and the parking lot with the second smallest cost j :

[0028] Diff j =C kj -C ij

[0029] Round up the minimum cost difference among all adjacent unloading points of parking lot i to get the pricing increment ε of parking lot i i :

[0030]

[0031] Among them, Ω pl represents the parking lot set, C i′j C represents the expected cost of parking at each parking lot i′ after unloading at unloading point j, except parking lot i. kj represents the expected parking cost corresponding to parking lot k with the minimum parking cost among all parking lots i′ except parking lot i, C ijrepresents the expected parking cost from unloading point j to parking lot i, i.e. parking lot i has the first smallest parking cost, parking lot k has the second smallest parking cost, Λ i Gather at the nearest unloading point of parking lot i.

[0032] In one embodiment, after step S5, the method further includes:

[0033] Based on the adjusted pricing, re-estimate the parking cost from the unloading point to the parking lot and update the distribution of nearby unloading points;

[0034] Based on the updated distribution of nearby unloading points, determine whether all parking lots meet the ideal number of unloading points. If so, output the adjusted pricing of each parking lot at this time as the optimal solution. If not, repeat steps S2 to S5. If the maximum number of iterations is reached, evaluate the solutions recorded in each iteration and output the suboptimal solution, ending the iteration.

[0035] In one embodiment, if not all parking lots meet the ideal number of unloading points, and if an optimal solution cannot be obtained, a suboptimal solution is evaluated. After each round of iteration, the solution generated by that round of iteration is recorded, and the number of parking lots meeting the ideal conditions and the number of price adjustments corresponding to the solution are calculated. Ultimately, the solution with the largest number of parking lots meeting the ideal conditions and the fewest price adjustments is selected as the suboptimal solution for output.

[0036] Based on the same inventive concept, the second aspect of the present invention provides a parking lot heterogeneous initial pricing device for long-range autonomous valet parking services, comprising:

[0037] The module for determining the number of ideal adjacent unloading points is used to determine the ideal number of adjacent unloading points for each parking lot when parking demand is in equilibrium. The adjacent unloading points for parking lot i are those unloading points whose parking costs are no less than the cost of parking lot i for any parking lot i′ in the parking lot set, where i′ and i are different parking lots.

[0038] A module for analyzing the distribution of adjacent unloading points, which is used to analyze the current distribution of adjacent unloading points at each parking lot based on the estimated parking cost from the unloading point to the parking lot in the initial state;

[0039] A pricing adjustment determination module is used to determine whether the parking lot needs to adjust its pricing based on the relationship between the current number of adjacent unloading points and the ideal number of adjacent unloading points for each parking lot.

[0040] A pricing increment determination module is used to determine the pricing increment for parking lots that need pricing adjustment based on their distribution near the unloading points;

[0041] The initial pricing adjustment module is used to adjust the initial pricing of the parking lot according to the pricing increment.

[0042] Based on the same inventive concept, the third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the method described in the first aspect when the program is executed.

[0043] Based on the same inventive concept, the fourth aspect of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0044] Compared with the prior art, the advantages and beneficial technical effects of the present invention are as follows:

[0045] This invention provides a heterogeneous initial pricing method for long-distance autonomous valet parking services. This method estimates parking demand by analyzing the geographic topology of parking lots and drop-off points. For parking lots with high parking demand, the initial parking price is increased by analyzing the distribution of these drop-off points, thereby directing parking demand to parking lots with lower demand. This heterogeneous initial pricing technology balances parking demand across parking lots, reduces parking costs, and alleviates traffic congestion, effectively alleviating parking difficulties. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 1 is a schematic diagram of an implementation flow of a method for heterogeneous initial pricing of parking lots for long-range autonomous valet parking services according to an embodiment of the present invention;

[0048] Figure 2 This is a flowchart of the long-range autonomous valet parking workflow in an embodiment of the present invention;

[0049] Figure 3 This is a distribution example diagram in an embodiment of the present invention;

[0050] Figure 4 3 is a performance comparison chart after experiments in a simulator in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In response to the technical problems existing in the existing technology, the present invention designs a parking lot heterogeneous initial pricing technology for long-distance autonomous valet parking services. By setting different initial parking prices for parking lots, it balances the parking demand from surrounding drop-off points, thereby reducing parking costs and alleviating traffic congestion.

[0052] The main inventive concepts of the present invention are as follows:

[0053] By analyzing the geographic topological relationship between parking lots and drop-off points, parking demand is estimated. For parking lots with high demand, initial parking prices are increased by analyzing the proximity of these drop-off points, thereby diverting demand to parking lots with lower demand. This heterogeneous initial pricing technology effectively alleviates parking difficulties by balancing parking demand across parking lots, reducing parking costs and traffic congestion.

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0055] Example 1

[0056] The present invention provides a parking lot heterogeneous initial pricing method for long-range autonomous valet parking services, comprising:

[0057] S1: Determine the ideal number of adjacent unloading points for each parking lot when the parking demand is in equilibrium. The adjacent unloading points for parking lot i are those unloading points whose parking costs are no less than the cost of parking lot i for any parking lot i′ in the set of parking lots, where i′ and i are different parking lots.

[0058] S2: Based on the estimated parking cost from the unloading point to the parking lot in the initial state, analyze the current distribution of the adjacent unloading points in each parking lot;

[0059] S3: For all parking lots, determine whether the parking lot needs to adjust its pricing based on the relationship between the current number of adjacent unloading points and the ideal number of adjacent unloading points for each parking lot;

[0060] S4: For parking lots that require pricing adjustments, determine the pricing increment based on their proximity to unloading points;

[0061] S5: Adjust the initial pricing of the parking lot based on the pricing increment.

[0062] Specifically, before explaining the technical solution of the present invention, the workflow of long-range autonomous valet parking is first introduced, as shown in the attached figure. Figure 2 As shown:

[0063] Step 1: The autonomous vehicle picks up the passenger and drives to the drop-off point;

[0064] Step 2: After arriving at the unloading point, the passenger gets off the bus and walks to the destination;

[0065] Step 3: After unloading the passengers, the dispatch center estimates the parking cost of each candidate parking lot, selects the parking lot with the minimum parking cost, and recommends it to the autonomous vehicle;

[0066] Step 4: The autonomous vehicle drives from the unloading point to the recommended parking lot and finally completes autonomous parking at the recommended parking lot.

[0067] In order to reasonably define the problem, the present invention proposes the following premises:

[0068] (1) Each parking lot is publicly operated, and its pricing strategy is determined by the government or public managers. Compared with private parking lots, the pricing management goal of public parking lots is to meet parking needs and alleviate parking problems, rather than just for profit;

[0069] (2) The dispatch center can monitor the status of each parking lot through cellular networks, vehicle networks, or other technologies to evaluate the parking cost of each parking lot. The parking cost consists of three parts: the driving time cost from the unloading point to the parking lot, the waiting time cost at the parking lot (i.e., the expected time to wait for an available parking space), and the parking fee cost. Each self-driving car is rational, that is, it always tends to choose the parking lot with the lowest parking cost to complete parking. Therefore, the parking lot always recommends the parking lot with the lowest parking cost to the vehicle;

[0070] (3) Since the autonomous vehicle first arrives at the unloading point and starts the parking journey after unloading the passengers, the parking demand of the parking lot comes from the adjacent unloading points. The adjacent unloading points of parking lot i are defined as follows: for unloading point j, if the parking cost of any parking lot i′ in the parking lot set is not less than the cost of parking lot i (the vehicle unloading at unloading point j has the minimum expected parking cost at parking lot i), then unloading point j is called the adjacent unloading point of parking lot i. Since each vehicle is rational, the vehicle that chooses to unload at a certain adjacent unloading point of parking lot i will receive a recommendation for parking lot i (with the lowest parking cost) from the dispatch center;

[0071] (4) In the initial state, a large number of parking spaces in the parking lot are vacant, so the waiting time cost is estimated to be zero, and vehicles do not need to wait for occupied parking spaces to become available. As the traffic system operates, parking spaces are continuously occupied, and the dispatch center will further estimate the parking waiting time based on the occupancy status of parking spaces in the parking lot. Because the present invention only considers the parking lot heterogeneous pricing technology in the initial state, the initial parking waiting time is estimated to be zero in the following parking cost calculations.

[0072] For specific implementation, please refer to Figure 1 , which is a schematic diagram of the implementation flow of a heterogeneous initial pricing method for a long-distance autonomous valet parking service in an embodiment of the present invention. The distribution of adjacent drop-off points includes the number and distribution ratio of adjacent drop-off points.

[0073] In one embodiment, when the parking demand is in equilibrium in step S1, the number of ideal adjacent unloading points in each parking lot is within the interval [D min ,max], D min and D max Determined by the following formula:

[0074]

[0075]

[0076] where Ω pl and Ω dp denote the parking lot set and the unloading point set respectively, |Ω pl | and |Ω dp | represents the total number of parking lots and unloading points, and |Ω pl |Not greater than|Ω dp |, floor(*) is the floor rounding function, and ceil(*) is the ceiling rounding function.

[0077] Specifically, by balancing the number of adjacent unloading points in a parking lot, the parking demand can be further balanced, because the parking demand of a parking lot comes from the adjacent unloading points (based on premise (3)).

[0078] In one embodiment, in step S2, the parking cost from the unloading point to the parking lot in the initial state is estimated according to the following formula:

[0079]

[0080] Among them, C ij represents the expected parking cost from unloading point j to parking lot i, T ij F represents the driving time cost from unloading point j to parking lot i, in seconds; iThe cost of parking at parking lot i is in yuan; α is the unit time value, which is used to convert monetary units into time units;

[0081] The adjacent unloading point j has the following properties:

[0082]

[0083] Among them, Ω pl Represents a parking lot collection.

[0084] Specifically, in the initial state, since each parking lot has a large number of vacant parking spaces, the waiting time cost is estimated to be zero (based on the premise (4)).

[0085] In one embodiment, step S3 includes:

[0086] Determine the number of unloading points D adjacent to parking lot i i Is it greater than the ideal number of unloading points? If so, it indicates that parking lot i faces a high parking demand and needs to adjust pricing; otherwise, no pricing adjustment is required.

[0087] Specifically, by traversing all parking lots in the parking lot set, we determine whether the number of adjacent unloading points of the parking lot meets the ideal unloading point number requirement. If the number of adjacent unloading points of parking lot i is greater than the ideal unloading point number (D i >D max ), it means that the parking lot faces high parking demand and needs to further increase its parking pricing:

[0088]

[0089] ε i Pricing increments.

[0090] In one embodiment, the pricing increment in step S4 is determined as follows:

[0091] For parking lot i that needs to adjust pricing, calculate the second minimum parking cost C between the nearest unloading point and other parking lots. kj :

[0092]

[0093] Calculate the cost difference Diff between the nearest unloading point to parking lot i and the parking lot with the second smallest cost j :

[0094] Diff j =C kj -C ij (7)

[0095] Round up the minimum cost difference among all adjacent unloading points of parking lot i to get the pricing increment ε of parking lot i i :

[0096]

[0097] Among them, Ω pl represents the parking lot set, C i′j C represents the expected cost of parking at each parking lot i′ after unloading at unloading point j, except parking lot i. kj represents the expected parking cost corresponding to parking lot k with the minimum parking cost among all parking lots i′ except parking lot i, C ij represents the expected parking cost from unloading point j to parking lot i, i.e. parking lot i has the first smallest parking cost, parking lot k has the second smallest parking cost, Λ i Gather at the nearest unloading point of parking lot i.

[0098] Specifically, step S4 determines the pricing increment for parking lot i. For parking lots that do not require pricing adjustment (i.e., meet the ideal number of unloading points), the pricing increment is zero. For parking lot i that requires pricing adjustment, the second-lowest parking cost of parking at other parking lots near the unloading point is estimated (the first-lowest parking cost is the cost of parking at parking lot i).

[0099] By increasing the initial parking price of a parking lot by the minimum cost difference, the parking demand for the adjacent unloading point of the minimum cost difference will be balanced to another parking lot, thereby reducing the number of adjacent unloading points of parking lot i with the minimum cost increase and balancing the parking demand.

[0100] After traversing all parking lots in the set and completing price adjustments, the round of iteration is completed. i ′, update the set and number of adjacent unloading points for each parking lot. If the number of adjacent unloading points for all parking lots meets the ideal number of unloading points, the iteration ends and the pricing for each parking lot at this point is output as the optimal solution, i.e., the heterogeneous initial pricing under parking demand equilibrium.

[0101] In one embodiment, after step S5, the method further includes:

[0102] Based on the adjusted pricing, re-estimate the parking cost from the unloading point to the parking lot and update the distribution of nearby unloading points;

[0103] Based on the updated distribution of nearby unloading points, determine whether all parking lots meet the ideal number of unloading points. If so, output the adjusted pricing of each parking lot at this time as the optimal solution. If not, repeat steps S2 to S5. If the maximum number of iterations is reached, evaluate the solutions recorded in each iteration and output the suboptimal solution, ending the iteration.

[0104] In one embodiment, if not all parking lots meet the ideal number of unloading points, and if an optimal solution cannot be obtained, a suboptimal solution is evaluated. After each round of iteration, the solution generated by that round of iteration is recorded, and the number of parking lots meeting the ideal conditions and the number of price adjustments corresponding to the solution are calculated. Ultimately, the solution with the largest number of parking lots meeting the ideal conditions and the fewest price adjustments is selected as the suboptimal solution for output.

[0105] During the specific implementation process, if the iteration is not completed, steps S2 to S5 are repeated. If the maximum number of iterations is reached but there are still parking lots that do not meet the ideal number of adjacent unloading points, a suboptimal solution is output. After each round of iteration, the solution generated by that round is recorded, and the number of parking lots that meet the ideal conditions and the number of price adjustments corresponding to the solution are evaluated. Ultimately, the solution with the largest number of parking lots that meet the ideal conditions and the fewest price adjustments is selected as the suboptimal solution output to maximize the balance of parking demand and avoid excessive increases in parking fees due to multiple price adjustments.

[0106] The above technical solution is for when the number of parking lots is not greater than the number of drop-off points. If the number of parking lots is greater than the number of drop-off points, a phylogenetic clustering method in MATLAB is used to cluster parking lots with similar distance characteristics to the drop-off points into parking areas. The cluster centers (parking areas) are virtualized as "parking lots," and the above solution is applied to determine the heterogeneous initial pricing for these virtual "parking lots" (parking areas).

[0107] The following is combined with the attached Figure 3 As an example, the specific implementation of the present invention is further described. Figure 3 There are three parking lots and five unloading points in total. The road map comes from the city center of Helsinki, Finland. Each parking lot initially has 100 vacant parking spaces. Figure 4 3 is a performance comparison chart after experiments in a simulator in an embodiment of the present invention.

[0108] Step 1: Determine the ideal number of adjacent parking spots in the parking lot when parking demand is balanced. In this example, |Ω pl |(number of parking lots) is 3, |Ω dp |(number of unloading points) is 5, according to formula (1) and formula (2), we can calculate D min is 1, D max is 2;

[0109] Step 2: Determine the set of adjacent drop-off points for each parking lot. China's per capita income in 2021 is 35,100 yuan. Assuming each person works 20 hours per week, four weeks per month, and ten months per year, or 800 hours, the unit time value (α) for Chinese users is calculated to be 43.875 yuan / hour. Therefore, the basic fixed parking price for each parking lot is set to 0.5 yuan (approximately 1% of the unit time value):

[0110] Table 1: Parking lot fixed base pricing

[0111] parking lot Parking Lot 1 Parking Lot 2 Parking Lot 3 Fixed basic parking fee (yuan / hour) 0.5 0.5 0.5

[0112] Assuming the average parking time for an autonomous vehicle is two hours, and the parking price at each parking lot is fixed, the parking fee cost at each parking lot is 0.5*2=1 yuan. Using the unit time value to convert to the time cost, we get 82.0513 seconds.

[0113] The driving time costs from each unloading point to each parking lot are shown in Table 2 below (in seconds, assuming a vehicle speed of 40 km / h):

[0114] Table 2: Driving time from the drop-off point to the parking lot

[0115] Driving time (seconds) Parking Lot 1 Parking Lot 2 Parking Lot 3 Unloading point 1 99.9029 197.3149 173.0507 Unloading point 2 37.3090 218.9115 216.1271 Unloading point 3 58.3291 161.0168 223.4078 Unloading point 4 163.3792 93.7815 245.2769 Unloading point 5 141.4040 80.8718 248.0706

[0116] According to formula (3), the parking cost of each parking lot is calculated as shown in Table 3:

[0117] Table 3: Parking costs from the drop-off point to the parking lot

[0118] Parking cost (seconds) Parking Lot 1 Parking Lot 2 Parking Lot 3 Unloading point 1 181.9542 279.3662 <![CDATA[ 255.1020 ]]> Unloading point 2 119.3603 300.9628 <![CDATA[ 298.1784 ]]> Unloading point 3 140.3804 <![CDATA[ 243.0681 ]]> 305.4591 Unloading point 4 <![CDATA[ 245.4305 ]]> 175.8328 327.3282 Unloading point 5 <![CDATA[ 223.4553 ]]> 162.9231 330.1219

[0119] According to formula (4), the nearest unloading point for each parking lot is determined (the unloading point with the lowest parking cost in the parking lot, i.e., the bold cost in Table 3) as shown in Table 4:

[0120] Table 4: Parking lots near unloading points

[0121] parking lot Meet near the unloading point Number of nearby unloading points Parking Lot 1 Unloading point 1, unloading point 2, unloading point 3 3 Parking Lot 2 Unloading point 4, unloading point 5 2 Parking Lot 3 empty set 0

[0122] Step 3: Traverse all parking lots and determine whether the number of adjacent unloading spots in each parking lot meets the ideal number of unloading spots (i.e., greater than or equal to 1 and less than or equal to 2). Since the number of adjacent unloading spots in parking lot 1 is greater than 2, the price of parking lot 1 needs to be increased to balance the parking demand from adjacent unloading spots.

[0123] Step 4: Determine the price increase for parking lot 1. For each adjacent drop-off point in parking lot 1, calculate the cost difference between parking in parking lot 1 (the first lowest cost) and the second lowest cost parking lot (the underlined cost in Table 3), as shown in Table 5:

[0124] Table 5: Cost differences near unloading points

[0125] Near the unloading point The second cheapest parking lot Parking cost difference (seconds) Unloading point 1 Parking Lot 3 73.1478 Unloading point 2 Parking Lot 3 178.8181 Unloading point 3 Parking Lot 2 102.6877

[0126] The smallest cost difference is 73.1478, which is rounded up to 74. Therefore, the parking fee for parking lot 1 should be increased by 74 seconds. Using the unit time value conversion, it should be increased by 0.4509 yuan / hour. The parking pricing of the parking lot at this time is shown in Table 6:

[0127] Table 6: Adjusted parking lot heterogeneity pricing

[0128] parking lot Parking Lot 1 Parking Lot 2 Parking Lot 3 Heterogeneous parking fee (yuan / hour) 0.9509 0.5 0.5

[0129] Step 5: Based on the adjusted heterogeneous parking fees, update the parking cost from the unloading point to the parking lot as shown in Table 7:

[0130] Table 7: Parking costs under heterogeneous pricing

[0131] Parking cost (seconds) Parking Lot 1 Parking Lot 2 Parking Lot 3 Unloading point 1 <![CDATA[ 255.9542 ]]> 279.3662 255.1020 Unloading point 2 193.3603 300.9628 <![CDATA[ 298.1784 ]]> Unloading point 3 214.3804 <![CDATA[ 243.0681 ]]> 305.4591 Unloading point 4 <![CDATA[ 319.4305 ]]> 175.8328 327.3282 Unloading point 5 <![CDATA[ 297.4553 ]]> 162.9231 330.1219

[0132] Based on the updated parking cost table, the nearest drop-off points for each parking lot are updated as shown in Table 8:

[0133] Table 8: Proximity to drop-off points under heterogeneous pricing

[0134]

[0135]

[0136] According to Table 8, the number of adjacent unloading points in each parking lot already meets the ideal number of unloading points. By increasing the price of Parking Lot 1, the parking demand for Unloading Point 1 will be balanced from Parking Lot 1 to Parking Lot 3, thus reducing excessive competition for parking spaces in Parking Lot 1.

[0137] Step 6: Since the number of adjacent unloading points at each parking lot meets the requirements, the iteration is completed and the heterogeneous pricing of each parking lot is output, as shown in Table 6.

[0138] This example was simulated in the Opportunistic Open Network Simulator (ONE). 300 autonomous vehicles were deployed in the network, with speeds uniformly distributed between 30km / h and 50km / h, and parking times of two hours. The simulation results are shown in the attached figure. Figure 4As shown. By determining the heterogeneous initial pricing of parking lots, it is possible to effectively balance parking demand, reduce excessive competition for parking spaces in high-demand parking lots, and thus reduce the average waiting time cost. At the same time, traffic congestion is further alleviated, and the average parking cost (i.e., parking fee + parking waiting time + driving time) is significantly reduced compared to the fixed pricing scheme. Although the heterogeneous initial pricing scheme leads to an increase in parking fees, the increase is small and does not cause irrational charges, and the additional fees can be further used for the management and maintenance of public parking lots. In this example, the average parking fee increases by approximately 29 seconds (converted to approximately 0.36 yuan), while the average total parking cost decreases by approximately 252 seconds (converted to approximately 3.07 yuan).

[0139] Example 2

[0140] Based on the same inventive concept, the present invention discloses a parking lot heterogeneous initial pricing device for long-range autonomous valet parking services, comprising:

[0141] The module for determining the number of ideal adjacent unloading points is used to determine the ideal number of adjacent unloading points for each parking lot when parking demand is in equilibrium. The adjacent unloading points for parking lot i are those unloading points whose parking costs are no less than the cost of parking lot i for any parking lot i′ in the parking lot set, where i′ and i are different parking lots.

[0142] A module for analyzing the distribution of adjacent unloading points, which is used to analyze the current distribution of adjacent unloading points at each parking lot based on the estimated parking cost from the unloading point to the parking lot in the initial state;

[0143] A pricing adjustment determination module is used to determine whether the parking lot needs to adjust its pricing based on the relationship between the current number of adjacent unloading points and the ideal number of adjacent unloading points for each parking lot.

[0144] A pricing increment determination module is used to determine the pricing increment for parking lots that need pricing adjustment based on their distribution near the unloading points;

[0145] The initial pricing adjustment module is used to adjust the initial pricing of the parking lot according to the pricing increment.

[0146] Since the device described in Example 2 of the present invention is used to implement the parking lot heterogeneous initial pricing method for long-range autonomous valet parking services described in Example 1 of the present invention, the specific structure and variations of this device are readily apparent to those skilled in the art based on the method described in Example 1 of the present invention, and thus will not be further described here. All devices used in the method described in Example 1 of the present invention are within the scope of protection of the present invention.

[0147] Example 3

[0148] Based on the same inventive concept, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed, the method described in the first embodiment is implemented.

[0149] Since the computer-readable storage medium introduced in the third embodiment of the present invention is the computer-readable storage medium used to implement the parking lot heterogeneous initial pricing method for long-range autonomous valet parking services in the first embodiment of the present invention, based on the method introduced in the first embodiment of the present invention, those skilled in the art can understand the specific structure and deformation of the computer-readable storage medium, so it will not be described in detail here. All computer-readable storage media used in the method of the first embodiment of the present invention fall within the scope of protection of the present invention.

[0150] Based on the same inventive concept, the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method in the first embodiment is implemented.

[0151] Since the computer device described in Example 4 of the present invention is used to implement the parking lot heterogeneous initial pricing method for long-range autonomous valet parking services described in Example 1 of the present invention, the specific structure and variations of this computer device are readily apparent to those skilled in the art based on the method described in Example 1 of the present invention, and thus will not be further described here. All computer devices used in the method described in Example 1 of the present invention are within the scope of protection of the present invention.

[0152] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0153] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0154] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic inventive concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. Obviously, those skilled in the art may make various changes and modifications to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, the present invention is intended to include such changes and modifications to the embodiments of the present invention if they fall within the scope of the claims and their equivalents.

Claims

1. A parking lot heterogeneous initial pricing method for long-range autonomous valet parking service, characterized in that: include: S1: Determine the ideal number of adjacent unloading points for each parking lot when the parking demand is in equilibrium. The nearest unloading point is any parking lot in the parking lot set. , the parking cost is no less than the parking lot The cost of the unloading point, and For different parking lots; S2: Based on the parking cost estimation from the unloading point to the parking lot in the initial state, analyze the current distribution of the adjacent unloading points in each parking lot; S3: For all parking lots, based on the relationship between the current number of unloading points near each parking lot and the ideal number of unloading points near each parking lot, determine whether the parking lot needs to adjust its pricing; S4: For parking lots that need to adjust pricing, determine the pricing increment based on the distribution of parking lots near unloading points; S5: adjusting the initial pricing of the parking lot according to the pricing increment; In step S2, the parking cost from the unloading point to the parking lot in the initial state is estimated according to the following formula: in, Indicates the unloading point Parking lot The expected parking cost, Indicates the unloading point Parking lot The driving time cost in seconds; For parking lot The cost of parking fees, in yuan; It is the unit time value, which is used to convert the monetary unit into the time unit; Near the drop-off point It has the following properties: in, Indicates parking lot collection; The pricing increment in step S4 is determined as follows: For parking lots that need to adjust pricing , estimate the second smallest parking cost of parking near the unloading point to other parking lots : Calculate the distance from the nearest unloading point to the parking lot The difference between the cost of parking at the parking lot with the second lowest cost : Parking lot The minimum cost difference among all adjacent unloading points is rounded up to get the parking lot Pricing increments : in, Indicates the parking lot collection, Indicates at the unloading point After unloading passengers, vehicles shall be parked in the parking lot except Every other parking lot except The expected cost of completing parking, Indicates that except parking lot Every other parking lot except The parking lot with the minimum parking cost in The corresponding expected parking cost is Indicates the unloading point Parking lot The expected parking cost of the parking lot With the first small parking cost, parking lot Has the second smallest parking cost, For parking lot Meet at the nearest unloading point.

2. The parking lot heterogeneous initial pricing method for long-range autonomous valet parking service as claimed in claim 1, characterized in that: When the parking demand is in equilibrium in step S1, the number of ideal adjacent unloading points in each parking lot is in the interval [ ]middle, Determined by the following formula: in and represents the total number of parking lots and unloading points, and No more than , is the floor function, is the ceiling function.

3. The parking lot heterogeneous initial pricing method for long-range autonomous valet parking service as claimed in claim 1, characterized in that: Step S3 includes: Determine parking lot Number of nearby unloading points Is it greater than the ideal number of unloading points? If so, it indicates that the parking lot In the face of higher parking demand, pricing needs to be adjusted; otherwise, no pricing adjustment is required.

4. The parking lot heterogeneous initial pricing method for long-range autonomous valet parking service as claimed in claim 1, characterized in that: After step S5, the method further comprises: Based on the adjusted pricing, re-estimate the parking cost from the unloading point to the parking lot and update the distribution of nearby unloading points; Based on the updated distribution of nearby unloading points, determine whether all parking lots meet the ideal number of unloading points. If so, output the adjusted pricing of each parking lot at this time as the optimal solution. If not, repeat steps S2 to S5. If the maximum number of iterations is reached, evaluate the solutions recorded in each iteration and output the suboptimal solution, and end the iteration.

5. The parking lot heterogeneous initial pricing method for long-range autonomous valet parking service as claimed in claim 4, characterized in that: In the case where not all parking lots meet the ideal number of unloading points, if the optimal solution cannot be obtained, the suboptimal solution is evaluated; after each round of iteration, the solution generated by the iteration is recorded, and the number of parking lots that meet the ideal conditions and the number of price adjustments corresponding to the solution are calculated. Finally, the solution with the largest number of parking lots that meet the ideal conditions and the least number of price adjustments is selected as the suboptimal solution output.

6. A parking lot heterogeneous initial pricing device for long-range autonomous valet parking service, characterized in that: include: The module for determining the number of ideal adjacent unloading points is used to determine the number of ideal adjacent unloading points for each parking lot when the parking demand is in a balanced state. The nearest unloading point is any parking lot in the parking lot set. , the parking cost is no less than the parking lot The cost of the unloading point, and For different parking lots; A module for analyzing the distribution of adjacent unloading points, used to analyze the current distribution of adjacent unloading points in each parking lot based on the estimated parking cost from the unloading point to the parking lot in the initial state; A pricing adjustment judgment module is used to judge whether the parking lot needs to adjust the pricing according to the relationship between the current number of unloading points near each parking lot and the ideal number of unloading points near each parking lot for all parking lots; A pricing increment determination module, for determining the pricing increment for parking lots that need to adjust pricing according to the distribution of parking lots near unloading points; An initial pricing adjustment module, used to adjust the initial pricing of the parking lot according to the pricing increment; In the distribution analysis module of nearby unloading points, the parking cost from the unloading point to the parking lot in the initial state is estimated according to the following formula: in, Indicates the unloading point Parking lot The expected parking cost, Indicates the unloading point Parking lot The driving time cost in seconds; For parking lot The cost of parking fees, in yuan; It is the unit time value, which is used to convert the monetary unit into the time unit; Near the drop-off point It has the following properties: in, Indicates parking lot collection; The pricing increment in the pricing increment determination module is determined as follows: For parking lots that need to adjust pricing , estimate the second smallest parking cost of parking near the unloading point to other parking lots : Calculate the distance from the nearest unloading point to the parking lot The difference between the cost of parking at the parking lot with the second lowest cost : Parking lot The minimum cost difference among all adjacent unloading points is rounded up to get the parking lot Pricing increments : in, Indicates the parking lot collection, Indicates at the unloading point After unloading passengers, vehicles shall be parked in the parking lot except Every other parking lot except The expected cost of completing parking, Indicates that except parking lot Every other parking lot except The parking lot with the minimum parking cost in The corresponding expected parking cost is Indicates the unloading point Parking lot The expected parking cost of the parking lot With the first small parking cost, parking lot Has the second smallest parking cost, For parking lot Meet at the nearest unloading point.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed, the method according to any one of claims 1 to 5 is implemented.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

Images