Passenger car space distribution method and device on online booked car

Abstract

The invention provides a method and device for distributing passenger spaces on an online booked car, and relates to the technical field of intelligent traffic management, and the method comprises the steps: calculating multi-dimensional scores through obtaining the comprehensive information of the parking spaces, including a path complexity score and a parking space idle time window score; performing weighted summation according to the multi-dimensional score and a preset weight coefficient to obtain a comprehensive score of the parking space; and according to the comprehensive score of the parking space, allocating the passenger parking space for the order. According to the method, the problem that the distribution and management of the boarding parking spaces are difficult to meet the requirements of high-density passenger flow and complex scenes due to the fact that the multi-dimensional information such as path complexity and parking space idle time windows is difficult to consider to comprehensively evaluate the parking space matching degree in the prior art is solved. The multi-dimensional score also considers the passenger arrival time score and the parking space load rate score, thereby achieving the optimal distribution of the parking space load, and reducing the waiting time of passengers. In addition, the weight coefficient is adjusted according to a preset rule, and the flexibility and accuracy of parking space distribution are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation management, and particularly to a method and device for allocating boarding positions for online car-hailing vehicles. Background Art

[0002] In transportation hubs such as airports and railway stations, as well as in large commercial complex scenarios, scientifically and reasonably allocating and managing boarding positions for online car-hailing vehicles is the key to improving operational efficiency and optimizing the user experience. However, it is undeniable that there are many limitations in the existing technologies during actual application. When facing high-density passenger flows and complex and changeable scenarios, it is difficult to meet the actual needs.

[0003] At the allocation mode level, traditional online car-hailing scheduling mostly adopts static allocation, fixed parking space allocation, and first-come-first-served queuing mechanisms. Due to the lack of consideration of factors such as the complexity of the passenger's dynamic movement path and the free time window of the parking space, the utilization rate of the parking space is low, and the waiting time of passengers increases significantly. In terms of the scheduling dimension, the existing system has a single dimension, relying only on the order receiving time or simple distance calculation to allocate parking spaces, completely ignoring key information such as the real-time location of passengers, predicted walking time, and the load status of parking spaces. These deficiencies directly lead to resource waste problems. The uneven allocation of parking spaces results in some parking spaces being idle for a long time, while others are overloaded with queues. Drivers and passengers need to communicate and coordinate repeatedly, greatly increasing the operating cost and management difficulty. At the same time, the existing technologies lack the ability of dynamic adjustment and rely too much on manual management. They cannot dynamically adjust the parking space allocation strategy according to real-time passenger flow changes such as flight delays and sudden traffic jams, resulting in poor adaptability of the entire system. Summary of the Invention

[0004] An embodiment of the present invention provides a method for allocating boarding positions for online car-hailing vehicles, aiming to solve the problem that it is difficult for the existing technologies to comprehensively evaluate the matching degree of parking spaces by considering multi-dimensional information such as path complexity and free time window of the parking space, resulting in the allocation and management of boarding positions being difficult to meet the needs of high-density passenger flows and complex scenarios.

[0005] To achieve the above object, a method for allocating boarding positions for online car-hailing vehicles includes the following steps: After receiving a passenger's car-hailing order, obtain the comprehensive information of all parking spaces, where the comprehensive information includes: passenger check-in time, passenger check-in location, passenger's historical walking speed, parking space location, path complexity score, and free time window of the parking space; Calculate the multi-dimensional scores of all parking spaces according to the comprehensive information, where the multi-dimensional scores include: path complexity score and free time window score of the parking space; where: The path complexity score is calculated by the following formula: , In the formula, is the path complexity score for the th parking space; is the path complexity score for the th parking space set according to the path characteristics. Among them, when the path characteristic is a direct path, it is set to a predetermined first path complexity score; when the path characteristic is that an elevator needs to be transferred, it is set to a predetermined second path complexity score; when the path characteristic is that a long detour is required, it is set to a predetermined third path complexity score; when the path characteristic is that luggage needs to be waited for, it is set to a predetermined fourth path complexity score; the first path complexity score is less than the second path complexity score, the second path complexity score is less than the third path complexity score, and the third path complexity score is less than the fourth path complexity score; The parking space idle time window score is calculated by the following formula: , , , In the formula, is the parking space idle time window score for the th parking space; t a is the expected arrival time of the passenger; t ws is the start time of the parking space idle time window, configured as the current system time or the time when the previous passenger finishes getting on the vehicle; t sig is the passenger check-in time; is the path distance between the passenger check-in location and the parking space location of the th parking space; v is the historical walking speed of the passenger; is the correction time introduced according to the path complexity; Z is the coincidence degree between the expected arrival time of the passenger and the parking space idle time window; t end is the end time of the parking space idle time window, configured as the expected start time of the next order; is the th parking space's said coincidence degree; Z min is the minimum value of the said coincidence degrees of all boarding parking spaces; Z max is the maximum value of the said coincidence degrees of all boarding parking spaces; The comprehensive score of the parking space is obtained by weighted summation of the multi-dimensional score and the preset weight coefficient; The boarding parking space is allocated for the order according to the comprehensive score of the parking space.

[0006] Furthermore, the comprehensive information further includes the number of queued parking spaces and the parking space capacity, and the multi-dimensional score further includes: a passenger arrival time score and / or a parking space load rate score; wherein, the passenger arrival time score is calculated by the following formula: , In the formula, is the passenger arrival time score of the th parking space; The parking space load rate score is calculated by the following formula: , , , In the formula, is the parking space load rate score of the th parking space; L a is the load rate of the current parking space; is the historical order completion rate of the th parking space; n a is the number of queued parking spaces; N a is the parking space capacity; is the number of historical completed orders of the th parking space; O sum is the th parking space of the total number of historical orders.

[0007] Furthermore, the parking space comprehensive score is calculated by the following formula: , , In the formula, is the parking space comprehensive score of the th parking space; k 1 is the preset weight of the passenger arrival time score; k 2 is the preset weight of the parking space load rate score; k 3 is the preset weight of the path complexity score; k 4 is the preset weight of the parking space idle time window score.

[0008] Furthermore, it further includes adjusting the weight coefficient according to a preset rule, and the rule includes: When the trigger condition is that the passenger flow exceeds the preset passenger flow threshold, increase the weight of the parking space load rate score and decrease the weight of the path complexity score; When the trigger condition is that the number of queuing spaces is greater than 80% of the capacity of the boarding spaces, reduce the scoring weight of the load rate of the boarding spaces; When the trigger condition is that the average waiting time of passengers is greater than the preset waiting time threshold, increase the scoring weight of the parking space idle time window and reduce the scoring weight of the path complexity; When the trigger condition is that there are parking spaces that are malfunctioning and closed, set all the weight coefficients of the malfunctioning parking spaces to 0; When the trigger condition is that there are obstacles on the path, increase the scoring weight of the path complexity of the boarding spaces affected by the path obstacles; When the trigger condition is that passengers arrive concentratedly, increase the scoring weight of the parking space idle time window. The concentrated arrival of passengers is determined by the preset passenger arrival conditions; for example, the number of passengers arriving within a predetermined period exceeds the predetermined number; for example, the concentrated arrival of passengers due to flight delays.

[0009] Furthermore, pre-configure a predetermined priority for each rule; when the trigger conditions of multiple rules are reached simultaneously, adjust the weights according to the order of the predetermined priorities.

[0010] Furthermore, it also includes using evaluation indicators to verify whether the weight adjustment meets the standards. The evaluation indicators include: the average waiting time of passengers, the rendezvous failure rate of the driver and passengers within the designated parking space idle time window, and / or the parking space load balance degree. The parking space load balance degree is the standard deviation of all the parking space load rate scores; when the weight adjustment does not meet the standards or there are abnormalities, handle it in one or more of the following ways: Automatic rollback. If any of the evaluation indicators fails to meet the standards after the weight adjustment, automatically restore to the weights at the previous time when the standards were met, and record the abnormal log; Manual intervention. After three consecutive automatic rollbacks, push an alarm to the administrator to manually adjust the parameter thresholds or weight parameters of the rule library; Fault isolation. For the parking space equipment failure scenario, automatically isolate the faulty parking space, and reset the weights through the interface signal after repair.

[0011] Furthermore, the passenger check-in time and the passenger check-in location are obtained through the passenger's check-in on the APP or mini-program.

[0012] Furthermore, the allocation of boarding spaces for orders includes one or more of the following: For each order, allocate the parking space with the highest comprehensive score of the parking space as the candidate boarding space; When the comprehensive scores of multiple parking spaces are the same, preferentially allocate the parking space with the highest load rate score as the candidate boarding space; When all parking spaces are overloaded, a dynamic adjustment mechanism is triggered, including extending the parking space idle time window and / or enabling alternative parking spaces.

[0013] Further, after allocating a boarding parking space for an order, the parking space number and the parking space idle time window information of the boarding parking space are sent to the passenger and the driver through the APP or the mini-program, and at the same time, the parking space queuing number and the parking space idle time window information of the boarding parking space are updated.

[0014] In a second aspect, the present invention provides a boarding parking space allocation device for online car-hailing, including a memory and a processor. The memory stores at least one segment of program, and the at least one segment of program is executed by the processor to implement the boarding parking space allocation method for online car-hailing as described above.

[0015] The above technical solution has the following technical effects: By obtaining the comprehensive information of the parking space, multi-dimensional scores are calculated, including the path complexity score and the parking space idle time window score; according to the weighted sum of the multi-dimensional scores and the preset weight coefficients, the comprehensive score of the parking space is obtained; and the boarding parking space is allocated for the order according to the comprehensive score of the parking space. The present invention solves the problem that it is difficult for the prior art to comprehensively evaluate the parking space matching degree considering multi-dimensional information such as path complexity and parking space idle time window, resulting in the allocation and management of boarding parking spaces being difficult to meet the needs of high-density passenger flow and complex scenarios.

[0016] In a further embodiment, the multi-dimensional score also considers the passenger arrival time score and the parking space load rate score to achieve the optimal allocation of the parking space load and reduce the passenger waiting time.

[0017] In a further embodiment, the weight coefficients are adjusted according to the preset rules, realizing the adjustment of the multi-dimensional comprehensive score according to the real-time operation situation, and improving the flexibility and accuracy of the parking space allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flowchart of the boarding parking space allocation method for an embodiment of the present invention; Figure 2 is a schematic structural diagram of the rule for adjusting the weight coefficient of the multi-dimensional score in an embodiment of the present invention; Figure 3 is a schematic structural diagram of the boarding parking space allocation device for an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0019] To further illustrate each embodiment, the present invention provides accompanying drawings. These drawings are part of the disclosure of the present invention, mainly used to illustrate the embodiments, and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are usually used to represent similar components.

[0020] The present invention will be further described below in conjunction with the accompanying drawings and specific implementation manners.

[0021] Embodiment 1: Figure 1 The flowchart of the method for allocating pick-up positions for online car-hailing in an embodiment of the present invention is shown. The method of this embodiment includes the following steps: After receiving a passenger's car-hailing order, obtain the comprehensive information of all positions, including the passenger's check-in time, passenger's check-in location, passenger's historical walking speed, position of the pick-up position, path complexity score, number of people queuing at the pick-up position, capacity of the pick-up position, and idle time window of the pick-up position. Among them, the idle time window of the pick-up position is defined as the time period from the current system time or the time when the previous passenger completed getting on the car to the expected start time of the next order. In a specific implementation, the passenger's check-in time and the passenger's check-in location are obtained by the passenger scanning a dedicated QR code in the outbound corridor of the hub and starting the dedicated APP or mini-program of the hub for check-in. Calculate the multi-dimensional scores of all pick-up positions according to the comprehensive information, including: path complexity score, idle time window score of the pick-up position, passenger arrival time score, and / or load rate score of the pick-up position. Among them: The path complexity score is calculated by the following formula: , In the formula, is the path complexity score of the th pick-up position; is the path complexity score of the th pick-up position set according to the path characteristics. Among them, when the path characteristic is a direct path, it is set to a predetermined first path complexity score; when the path characteristic is that an elevator needs to be transferred, it is set to a predetermined second path complexity score; when the path characteristic is that a long-distance detour is required, it is set to a predetermined third path complexity score; when the path characteristic is that luggage needs to be waited for, it is set to a predetermined fourth path complexity score; the first path complexity score is less than the second path complexity score, the second path complexity score is less than the third path complexity score, and the third path complexity score is less than the fourth path complexity score. In a specific implementation, the first path complexity score is 1; the second path complexity score is 2; the third path complexity score is 3; the fourth path complexity score is 4. The higher the path complexity score, the lower the path complexity score. The parking space idle time window score is calculated by the following formula: , , In the formula, is the parking space idle time window score of the th parking space; Z is the coincidence degree between the expected passenger arrival time and the parking space idle time window; t end is the end time of the parking space idle time window, configured as the expected start time of the next order. In a specific implementation, if there is no subsequent order, it is set to a relatively large value, such as 24:00; is the th coincidence degree of the parking space; Z min is the minimum value of the coincidence degrees of all boarding parking spaces; Z max is the maximum value of the coincidence degrees of all boarding parking spaces; The passenger arrival time score is calculated by the following formula: , , In the formula, is the passenger arrival time score of the th parking space; t a is the expected passenger arrival time; t ws is the start time of the parking space idle time window, configured as the current system time or the time when the previous passenger completed boarding. In a specific implementation, the larger value between the two is taken; t sig is the passenger check-in time; is the path distance between the passenger check-in location and the parking space location of the th parking space; v is the passenger's historical walking speed; is a predetermined correction time introduced according to the path complexity. In a specific implementation, when the path feature is that an elevator needs to be transferred, the correction time is 20 seconds; this specific time is only exemplary, and the specific correction time is preset according to the specific scenario and situation; The parking space load rate score is calculated by the following formula: , , , In the formula, is the Load rate score of a parking space L a is the load rate of the current parking space; is the historical order completion rate of the n a is the number of parked cars waiting in line for the parking space; N a is the capacity of the parking space; is the number of historical completed orders of the O sum is the total number of historical orders of the The comprehensive score of the parking space is obtained by weighted summation of the multi-dimensional scores and the preset weight coefficients, and is calculated by the following formula: , , In the formula, is the comprehensive score of the th parking space; k 1 is the preset weight of the passenger arrival time score; k 2 is the preset weight of the parking space load rate score; k 3 is the preset weight of the path complexity score; k 4 is the preset weight of the parking space idle time window score. In a specific implementation, the initialized weights are k1 = 0.4, k2 = 0.3, k3 = 0.2, k4 = 0.1; The boarding parking space is allocated for the order according to the comprehensive score of the parking space, including one or more of the following: For each order, the parking space with the highest comprehensive score of the parking space is allocated as the candidate boarding parking space; When the comprehensive scores of multiple parking spaces are the same, the parking space with the highest load rate score is preferentially allocated as the candidate boarding parking space; When all parking spaces are overloaded, a dynamic adjustment mechanism is triggered, including extending the parking space idle time window and / or enabling spare parking spaces.

[0022] In a specific implementation, after allocating the boarding parking space for the order, the parking space number and the idle time window information of the boarding parking space are sent to the passenger and the driver through the APP or the mini program, and at the same time, the parking space queuing number and the parking space idle time window information of the boarding parking space are updated.

[0023] Embodiment 2: This embodiment of the present invention further includes adjusting the weight coefficients of each score in the comprehensive score according to a preset rule. For example, a corresponding weight coefficient adjustment strategy is set according to a predetermined rule. Figure 2Schematic diagram of the rule structure for adjusting multi-dimensional scoring weight coefficients in an embodiment of the present invention. In this embodiment, combined with the typical scenario of a transportation hub, the weight adjustment rule design covers typical scenarios such as peak hours, parking space congestion, extremely long waiting times, equipment failures, external events, etc., and clarifies the weight adjustment strategies and priorities in each scenario. For example, Figure 2 as shown, the preset rules include one or more of the following: When the trigger condition is that the passenger flow exceeds the preset passenger flow threshold, increase the scoring weight of the parking space load rate and decrease the scoring weight of the path complexity. The priority of this rule is configured as the first priority; When the trigger condition is that there is a boarding parking space where the number of queuing vehicles is greater than 80% of the parking space capacity, decrease the scoring weight of the parking space load rate of this boarding parking space. The priority of this rule is configured as the second priority; When the trigger condition is that the average waiting time of passengers is greater than the preset waiting time threshold, increase the scoring weight of the parking space idle time window and decrease the scoring weight of the path complexity. The priority of this rule is configured as the second priority; When the trigger condition is that there is a parking space that has failed due to a fault, set all weight coefficients of this faulty parking space to 0. The priority of this rule is configured as the third priority; When the trigger condition is that there is an obstacle on the path, increase the scoring weight of the path complexity of the boarding parking space affected by the path obstacle. The priority of this rule is configured as the third priority; When the trigger condition is that passengers arrive concentratedly due to flight delays, increase the scoring weight of the parking space idle time window. The priority of this rule is configured as the third priority; In a specific implementation, a predetermined priority is configured for each rule in advance; when the trigger conditions of multiple rules are reached simultaneously, weight adjustment is performed according to the order of the predetermined priorities from high to low, where the first priority is lower than the second priority, and the second priority is lower than the third priority.

[0024] In other implementations, according to specific situations, such as the specific situation of the airport, more or different weight coefficient adjustment rules are set; more or fewer priorities are set according to the settings of the rules.

[0025] In a specific implementation, it also includes using evaluation indicators to verify whether the weight adjustment meets the standard. The evaluation indicators include: the average waiting time of passengers, the failure rate of the meeting between the driver and the passengers within the specified parking space idle time window, and / or the parking space load balance. In a specific implementation, the parking space load balance is the standard deviation of all parking space load rate scores; when the weight adjustment does not meet the standard or there are abnormalities, one or more of the following methods are used for processing: Automatic rollback. If any of the above-mentioned evaluation indicators fails to meet the standard after the weight adjustment, automatically restore to the weight at the previous time when the standard was met, and record the exception log; Manual intervention: After three consecutive automatic rollbacks, an alarm is pushed to the administrator to manually adjust the parameter thresholds or weight parameters of the rule library. Fault isolation: For the scenario of parking space equipment failure, the faulty parking space is automatically isolated, and the weight is reset through the interface signal after repair.

[0026] Embodiment 3: Figure 3 The following is a schematic structural diagram of the on-demand car-hailing boarding parking space allocation device according to an embodiment of the present invention. As Figure 3 shown, the device includes a processor 301, a memory 302, a bus 303, and a computer program stored in the memory 302 and executable on the processor 301. The processor 301 includes one or more processing cores. The memory 302 is connected to the processor 301 through the bus 303. The memory 302 is used to store program instructions. When the processor executes the computer program, the steps in the above method embodiment of Embodiment 1 of the present invention are implemented.

[0027] Furthermore, as an executable solution, the on-demand car-hailing boarding parking space allocation device may be a computer unit, and the computer unit may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer unit may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above composition structure of the computer unit is only an example of the computer unit, and does not constitute a limitation on the computer unit. It may include more or fewer components than the above, or combine some components, or different components. For example, the computer unit may further include input / output devices, network access devices, a bus, etc. The embodiments of the present invention do not make limitations in this regard.

[0028] Furthermore, as an executable solution, the so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the computer unit, and connects various parts of the entire computer unit through various interfaces and lines.

[0029] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory, the processor realizes various functions of the computer unit. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system and application programs required for at least one function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include high-speed random access memory and can also include non-volatile memory, such as hard disks, memory, plug-in hard disks, smart media cards (SMC), secure digital (SD) cards, flash cards, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0030] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, those skilled in the art should understand that various changes can be made to the present invention in terms of form and details without departing from the spirit and scope of the present invention defined by the appended claims, and all such changes are within the protection scope of the present invention.

Claims

1. A method for allocating parking spaces for online car-hailing vehicles, characterized in that: The following steps are involved: After receiving a passenger's car booking order, obtain comprehensive information of all parking spaces, including: passenger check-in time, passenger check-in location, passenger historical walking speed, parking space location, path complexity score and parking space free time window; The multi-dimensional scores of all parking spaces are calculated based on the comprehensive information, and the multi-dimensional scores include: path complexity score and parking space free time window score; wherein: The path complexity score is calculated using the following formula: ， In the formula, For the The path complexity score of each parking space; The first The path complexity score of each parking space is set, wherein when the path feature is a direct path, it is set to a predetermined first path complexity score; when the path feature is that an elevator transfer is required, it is set to a predetermined second path complexity score; when the path feature is that a long-distance detour is required, it is set to a predetermined third path complexity score; when the path feature is that luggage needs to be waited for, it is set to a predetermined fourth path complexity score; the first path complexity score is less than the second path complexity score, the second path complexity score is less than the third path complexity score, and the third path complexity score is less than the fourth path complexity score; The parking space idle time window score is calculated using the following formula: ， ， ， In the formula, For the The parking space free time window score of each parking space; t a Estimated arrival time for passengers; t ws The starting time of the parking space free time window is configured as the current system time or the time when the last passenger completed boarding; t sig Check-in time for passengers; Check in the passenger's location and The path distance between the parking spaces; v The historical walking speed of the passenger; is the scheduled correction time introduced according to the path complexity; Z The overlap between the passenger's estimated arrival time and the parking space free time window; t end The end time of the parking space free time window is configured as the estimated start time of the next order; For the The overlap of the parking spaces; Z min is the minimum value of the overlap of all the boarding spaces; Z max is the maximum value of the overlap of all the boarding spaces; Obtaining a comprehensive parking space score based on a weighted sum of the multi-dimensional scores and a preset weight coefficient; A pickup parking space is allocated for the order based on the comprehensive parking space score.

2. The method for allocating parking spaces for online car-hailing passengers according to claim 1, characterized in that: The comprehensive information also includes the number of parking queues and parking capacity, and the multi-dimensional score also includes: passenger arrival time score and / or parking load rate score; wherein the passenger arrival time score is calculated by the following formula: ， In the formula, For the The passenger arrival time score of each parking space; The parking space load rate score is calculated using the following formula: ， ， ， In the formula, For the Parking space load factor score for each parking space; L a is the load rate of the current parking space; For the Historical order completion rate for parking spaces; n a The number of queues for parking spaces; N a is the parking capacity; For the The number of historical completed orders for parking spaces; O sum For the The total number of historical orders for parking spaces.

3. The method for allocating parking spaces for online car-hailing passengers according to claim 2, characterized in that: The comprehensive parking space score is calculated using the following formula: ， ， In the formula, For the Comprehensive parking rating for each parking space; k 1 is the preset passenger arrival time scoring weight; k 2 is the preset parking space load rate scoring weight; k 3 is the preset path complexity scoring weight; k 4 is the preset parking space idle time window scoring weight.

4. The method for allocating parking spaces for online car-hailing passengers according to claim 3, characterized in that: The method further includes adjusting the weight coefficient according to a preset rule, wherein the rule includes one or more of the following: When the trigger condition is that the passenger flow exceeds the preset passenger flow threshold, the parking space load rate score weight is increased and the path complexity score weight is reduced; When the trigger condition is that there is a parking space with a queue number greater than 80% of the parking space capacity, the parking load rate score weight of the parking space is reduced; When the trigger condition is that the average waiting time of passengers is greater than the preset waiting time threshold, the parking space idle time window score weight is increased and the path complexity score weight is reduced; When the trigger condition is that there is a parking space closed due to a fault, all weight coefficients of the parking space with the fault are adjusted to 0; When the trigger condition is an obstacle on the path, the path complexity score weight of the boarding spaces affected by the obstacle is increased; When the trigger condition is the concentrated arrival of passengers, the scoring weight of the parking space idle time window is increased.

5. The method for allocating parking spaces for online car-hailing passengers according to claim 4, characterized in that: A predetermined priority is configured for each rule in advance; when the triggering conditions of multiple rules are met at the same time, the weights are adjusted according to the order of the predetermined priorities.

6. The method for allocating parking spaces for online car-hailing passengers according to claim 5, characterized in that: It also includes using evaluation indicators to verify whether the weight adjustment meets the standards, the evaluation indicators include: average waiting time of passengers, failure rate of meeting drivers and passengers within the designated parking space free time window and / or parking space load balance, the parking space load balance is the standard deviation of all parking space load rate scores; when the weight adjustment does not meet the standards or there is an abnormality, one or more of the following methods are used to handle it: Automatic rollback: if any of the evaluation indicators fail to meet the standard after the weight adjustment, the weight will be automatically restored to the last standard-reaching weight, and the abnormal log will be recorded; Manual intervention: after three consecutive automatic rollbacks, an alarm is pushed to the administrator to manually adjust the rule base parameter threshold or weight parameter; Fault isolation: For parking equipment failure scenarios, the faulty parking space is automatically isolated and the weight is reset through interface signals after repair.

7. The method for allocating parking spaces for online car-hailing passengers according to claim 1, characterized in that: The passenger check-in time and the passenger check-in location are obtained when the passenger checks in on the APP or mini program.

8. The method for allocating parking spaces for online car-hailing passengers according to claim 1, characterized in that: The allocation of a pickup space for an order may include one or more of the following: For each order, the parking space with the highest comprehensive score is assigned as a candidate pickup space; When the comprehensive scores of multiple parking spaces are the same, the parking space with the highest parking load rate score will be prioritized as a candidate for passenger pickup; When all parking spaces are overloaded, a dynamic adjustment mechanism is triggered, including extending the parking space idle time window and / or activating spare parking spaces.

9. The method for allocating parking spaces for online car-hailing passengers according to claim 1, characterized in that: After allocating a pick-up space for an order, the parking space number and free time window information of the pick-up space will be sent to the passenger and driver through the APP or mini program, and the number of parking spaces in the queue and the free time window information of the pick-up space will be updated at the same time.

10. A parking space allocation device for online car-hailing, characterized in that: It includes a memory and a processor, the memory stores at least one program, and the at least one program is executed by the processor to implement the method for allocating passenger parking spaces on an online car-hailing vehicle as described in any one of claims 1 to 9.

Images