An order management method based on cloud computing services

Abstract

The application belongs to the technical field of order management, and discloses an order management method based on cloud computing services; the method comprises the following steps: a cloud platform receives a passenger position sent by a passenger terminal; real-time traffic data is acquired, a screening radius is defined, and a dispatching area is generated for the passenger position; all driver positions sent by driver terminals in the dispatching area are received; road traffic information is acquired, the road traffic information, the passenger position and all the driver positions are fused, the shortest pickup time from each driver position to the passenger position is calculated, and a time sorting table is generated; an order is sent to the driver terminal with the shortest shortest pickup time, and if the driver terminal does not accept the order, the driver terminals are dispatched in sequence according to the time sorting table; the application fully utilizes cloud computing and big data analysis technology, realizes intelligent optimization and dynamic adjustment of order dispatching, can effectively reduce passenger waiting time and driver empty running rate, and thus effectively improves user experience and improves overall operation efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of order management, and more particularly, to an order management method based on cloud computing services. Background Art

[0002] With the rise of the sharing economy, online ride-hailing services have become an important mode of urban transportation. In the operation of online ride-hailing platforms, real-time scheduling of orders is the key to improving service efficiency. Traditional scheduling methods usually rely on fixed area divisions or simple distance matching algorithms, which cannot fully consider dynamic factors such as real-time road conditions and driver driving trajectories. Problems such as uneven order distribution, unreasonable scheduling, and long user waiting times exist, which affect passenger experience and driver income. Therefore, an intelligent online ride-hailing order management method is urgently needed.

[0003] The patent with announcement number CN117522530B discloses a method for managing online car-hailing travel orders; it includes: when the online car-hailing management center receives a user's travel order based on a wireless network, it first locates the user's position, and then uses the user's position as the center of a circle and generates an order dispatch area A for the user through a preset radius r1, and obtains the number of online car-hailing vehicles in the order-accepting status within the order dispatch area A. If the number of online car-hailing vehicles in the order-accepting status within the order dispatch area A is greater than 1, then after obtaining multiple data of all online car-hailing vehicles, all online car-hailing vehicles are sorted based on a sorting algorithm, and the travel order is assigned to the online car-hailing vehicle ranked first; thereby effectively improving the uniformity of the order dispatch of the online car-hailing management center and the efficiency of travel order management.

[0004] However, although the above-mentioned technology can realize the order management of online ride-hailing, in the process of dispatching orders, it mainly considers a variety of data of online ride-hailing, including the number of orders received in a specified time period, mileage index, vehicle idle time and vehicle failure frequency, and does not take into account the time it takes for the online ride-hailing to reach the passenger's location. As a result, the driver needs to travel a long distance to reach the passenger's location after receiving the order, which increases the driver's idle rate and reduces operational efficiency. At the same time, it prolongs the waiting time of passengers and affects the travel experience. Especially during peak hours or in bad weather, long waiting times will lead to user loss and reduce the user stickiness of the platform.

[0005] In view of this, the present invention proposes an order management method based on cloud computing services to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions: an order management method based on cloud computing services, applied in a cloud platform, comprising:

[0007] S1: The cloud platform receives the passenger location sent by the passenger terminal;

[0008] S2: The cloud platform obtains real-time traffic data, uses a dynamic radius algorithm to define a filtering radius based on the real-time traffic data, and generates a dispatch area based on the filtering radius for the passenger location;

[0009] S3: The cloud platform receives the driver locations sent by all drivers in the dispatch area;

[0010] S4: The cloud platform obtains road traffic information, integrates the road traffic information, passenger location, and all driver locations, calculates the shortest pick-up time from each driver location to the passenger location, and generates a time ranking table;

[0011] S5: The cloud platform sends the order to the driver with the shortest pick-up time. If the driver does not accept the order, the cloud platform assigns the order to the driver in sequence according to the time sorting table.

[0012] Furthermore, the passenger location is the geographical coordinates of the passenger, and the driver location is the geographical coordinates of the driver;

[0013] Real-time traffic data includes traffic parameters corresponding to each road section within the screening range, including traffic density and traffic speed. The screening range is a circular area with the passenger's location as the center and the preset screening distance as the radius.

[0014] The steps to define the screening radius are:

[0015] Step S201: defining an iteration threshold a, a step size factor b, an adjustment factor d, and an intensity factor g;

[0016] Step S202: Preset radius range;

[0017] Step S203: construct a population S, which includes m individuals. The position of each individual corresponds to a value within the radius. The initial number of iterations t for the population S is 0.

[0018] Step S204: defining an improvement function;

[0019] Step S205: Divide the population S into h subpopulations, each subpopulation includes k individuals, m=hk;

[0020] Step S206: Calculate the flight probability corresponding to each individual and determine the corresponding flight mode;

[0021] Step S207: Update the position of each individual;

[0022] Step S208: Calculate the attraction coefficient corresponding to each individual and update the position of each individual again;

[0023] Step S209: Compare the number of iterations t with the iteration threshold a; if t≥a, proceed to step S210; if t<a, set t=t+1 and return to step S206;

[0024] Step S210: Calculate the improvement degree corresponding to each individual, and use the value corresponding to the individual with the largest improvement degree as the screening radius.

[0025] Furthermore, in step S203, the population S={X1, X2,…, X m}, X m is the mth individual; the position of each individual in the population S is defined in a one-dimensional search space, the range of the one-dimensional search space is the radius range; the expression of the position of each individual in the population S is: Where, is the position of the i-th individual, P i is the random coefficient of the i-th individual, P i ∈[0,1], i∈[1,m];

[0026] In step S204, the expression of the improvement function is: Where f is the improvement, jd is the order acceptance time, and ds is the waiting time. The order acceptance time is the time from when the passenger posts the order to when the driver accepts the order, and the waiting time is the time from when the passenger posts the order to when the driver arrives at the passenger's location. The order acceptance time and waiting time are obtained by using the real-time traffic data and the values ​​corresponding to the individual location as analysis data, inputting the analysis data into the trained first time model to predict the corresponding order acceptance time, and inputting the analysis data into the trained second time model to predict the corresponding waiting time. Both the first time model and the second time model are deep neural network models.

[0027] Furthermore, in step S205, the method of dividing the population S into h subpopulations includes:

[0028] Calculate the improvement degree corresponding to each individual in population S and sort them from large to small; assign an increasing number to each individual in the positive order of sorting, with the sequence number range being [1, m]; perform a modulo operation on the number of each individual according to the number of h subpopulations to obtain the corresponding subnumber; the expression for the subnumber is: l = u%h; where l is the subnumber, u is the number, and % is the modulo function; if the subnumber is not 0, assign the corresponding individual to the lth subpopulation; if the subnumber is 0, assign the corresponding individual to the hth subpopulation;

[0029] In step S206, the expression of flight probability is: Where, is the flight probability corresponding to the i-th individual, is the improvement degree corresponding to the best individual, f i t is the improvement degree corresponding to the i-th individual, is the improvement degree corresponding to the worst individual; the best individual is the individual with the largest improvement degree in population S, and the worst individual is the individual with the smallest improvement degree in population S;

[0030] Methods for determining an individual's corresponding flight mode include:

[0031] A probability threshold is preset, and the flight probability corresponding to each individual is compared with the probability threshold; if the flight probability is greater than or equal to the probability threshold, the flight mode of the corresponding individual is global flight; if the flight probability is less than the probability threshold, the flight mode of the corresponding individual is local flight.

[0032] Furthermore, in step S207, the method of updating the location of each individual includes:

[0033] If the flight mode corresponding to the individual is global flight, the method for updating the position includes:

[0034]

[0035] Where, is the position of the i-th individual after update, is the position of the i-th individual before the update, b t is the step size factor in the t-th iteration process, is the position of the best individual, d t is the adjustment factor in the t-th iteration process, C1 is a random number between [0,1], is the flight speed of the i-th individual, g t is the intensity factor in the t-th iteration process, is the flight speed of the i-th individual in the last iteration;

[0036] The expression of flight speed is: Where C2 is a random number between [0,1];

[0037] If the flight mode corresponding to the individual is local flight, the method for updating the position includes:

[0038]

[0039] Where, is the position of the best individual in the subpopulation where the i-th individual is located. The best individual is the individual with the greatest improvement in the subpopulation.

[0040] Furthermore, in step S208, the expression of the attraction coefficient is: Where, is the attraction coefficient of the i′th individual to the i′th individual in the subpopulation where the i′th individual is located, exp is an exponential function, is the improvement degree corresponding to the i′th individual in the subpopulation where the i′th individual is located, i≠i′, i′∈[1,k];

[0041] The methods for updating the position of each individual again include:

[0042]

[0043] Where, is the position of the i-th individual after updating again, To update the position of the i′th individual in the subpopulation where the i-th individual is located;

[0044] The dispatch area is a circular area with the passenger's location as the center and the screening radius as the radius.

[0045] Furthermore, the method for calculating the shortest pick-up time from each driver's position to the passenger's position includes:

[0046] Obtain all intersections within the dispatch area; based on the passenger location, driver location, and intersection, obtain P pick-up routes from each driver location to the passenger location; calculate the pick-up time corresponding to each pick-up route, compare the pick-up time corresponding to each driver location, and use the shortest pick-up time as the shortest pick-up time for the corresponding driver location.

[0047] Furthermore, the step of obtaining P pick-up routes from each driver's location to the passenger's location includes:

[0048] Step S401: randomly selecting a driver position that is not marked as a selected position and marking it as the current position;

[0049] Step S402: Explore all adjacent intersections of the current location, randomly select one of the adjacent intersections as the subsequent intersection, and mark it as the selected intersection;

[0050] Step S403: Determine whether the passenger's location is adjacent to a subsequent intersection. If so, use the current location, the selected intersection, and the passenger's location as a pickup route. If not, proceed to step S404.

[0051] Step S404: Explore all adjacent intersections of the successor intersection, randomly select one of the adjacent intersections that is not marked as a selected intersection as the successor intersection, and mark it as a selected intersection;

[0052] Step S405: Determine whether the passenger's location is adjacent to a subsequent intersection. If so, use the current location, the selected intersection, and the passenger's location as a pickup route. If not, proceed to step S406.

[0053] Step S406: Determine whether all adjacent intersections of the subsequent intersection are marked as selected intersections. If so, unmark all intersections marked as selected intersections in step S404 and proceed to step S407. If not, return to step S404.

[0054] Step S407: looping through steps S402 to S406 until P pick-up routes are obtained, then the loop ends and the process proceeds to step S408;

[0055] Step S408: Loop steps S401 to S407 until all driver positions are marked as current positions. The loop ends and P pick-up paths from each driver position to the passenger position are obtained.

[0056] Furthermore, the method for calculating the pick-up time corresponding to each pick-up route includes:

[0057] The intersections corresponding to each pick-up route are taken as an intersection set, and the intersection sets correspond to the pick-up routes one-to-one; the two adjacent intersections in each intersection set are taken as an adjacent set, and the road sections corresponding to each adjacent set are obtained and marked as pick-up sections; the traffic parameters corresponding to each pick-up section are obtained from the real-time traffic data and marked as pick-up parameters; road traffic information is obtained, and the road traffic information includes path length data and signal light status data; the path length data includes the path length corresponding to each pick-up route; the signal light status data includes the light status of each intersection passed in the direction of each pick-up route and the corresponding duration; different digital labels are set for different light statuses, and marked as light labels; the light status in the signal light status data is replaced with the corresponding light label; the pick-up parameters, path length and signal light status data corresponding to each pick-up route are taken as a set of calculation data, and the calculation data correspond to the pick-up route one-to-one; each set of calculation data is input into the trained time prediction model to predict the corresponding pick-up time, and the time prediction model is a deep neural network model;

[0058] Methods for generating a time-sorted table include:

[0059] Sort all the shortest pick-up times from shortest to longest and generate a time sorting table.

[0060] Furthermore, if the driver side does not accept the order, the order will be dispatched to the driver side in positive order according to the time sorting table. If all driver sides do not accept the order, the screening radius will be multiplied by the preset expansion coefficient to obtain the expanded radius. Based on the expanded radius, the dispatch area will be generated for the passenger position again, and the order will be dispatched again.

[0061] The technical effects and advantages of the order management method based on cloud computing services of the present invention are as follows:

[0062] By obtaining passenger location and real-time traffic data, and using a dynamic radius algorithm to adaptively generate dispatch areas, the dispatch range can be dynamically adjusted to improve dispatch accuracy. The shortest pick-up time from each driver's location to the passenger's location is calculated in real time, and dispatches are given priority to drivers closest to the passengers, thereby reducing passenger waiting time and driver idle rates, and effectively improving user experience. Cloud computing and big data analysis technologies are fully utilized to achieve intelligent optimization and dynamic adjustment of order dispatch, improve overall operational efficiency, and adapt to travel needs in the context of the sharing economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a flow chart of an order management method based on cloud computing services according to embodiment 1 of the present invention; DETAILED DESCRIPTION

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 are within the scope of protection of the present invention.

[0065] Example 1

[0066] See also Figure 1 As shown, the order management method based on cloud computing services described in this embodiment includes:

[0067] S1: The cloud platform receives the passenger location sent by the passenger terminal.

[0068] The cloud platform is a service organization based on cloud computing technology, which usually includes components such as servers, storage, databases and applications for processing and managing data; the passenger terminal is an application used by passengers;

[0069] The passenger location is the geographic coordinates of the passenger, and the passenger location is obtained by the passenger terminal requesting access to the GPS of the first device, where the first device is the mobile device used by the passenger.

[0070] S2: The cloud platform obtains real-time traffic data, defines a screening radius based on the real-time traffic data using a dynamic radius algorithm, and generates a dispatch area for the passenger location based on the screening radius.

[0071] Real-time traffic data includes traffic parameters corresponding to each road section within the screening range, and traffic parameters include traffic density and traffic speed; the screening range is a circular area with the passenger position as the center and a preset screening distance as the radius. The screening distance is pre-set by technical personnel in this field based on actual conditions; real-time traffic data is obtained through the API of map service providers (such as AutoNavi Maps, Baidu Maps, Tencent Maps, etc.).

[0072] Traffic density refers to the number of vehicles traveling on different road sections, and traffic speed refers to the average speed of vehicles on different road sections. It should be understood that the higher the traffic density and the slower the traffic speed, the more vehicles there are in the screening area and the slower the vehicles are traveling, that is, the more congested the screening area is. Therefore, the screening radius should be narrowed, and nearby drivers should be matched first to reduce the driver's driving distance and the passenger's waiting time. Conversely, the lower the traffic density and the faster the traffic speed, the fewer vehicles there are in the screening area and the faster the vehicles are traveling. Therefore, the screening radius should be expanded to cover a larger area, which will help match more drivers, increase the order acceptance rate, and avoid passengers waiting for a long time due to insufficient drivers.

[0073] The steps to define the screening radius are:

[0074] Step S201: defining an iteration threshold a, a step size factor b, an adjustment factor d, and an intensity factor g;

[0075] Step S202: Preset the radius range. The radius range is preset by those skilled in the art based on actual conditions.

[0076] Step S203: construct a population S, which includes m individuals. The position of each individual corresponds to a value within the radius. The initial number of iterations t for the population S is 0.

[0077] Step S204: defining an improvement function;

[0078] Step S205: Divide the population S into h subpopulations, each subpopulation includes k individuals, m=hk;

[0079] Step S206: Calculate the flight probability corresponding to each individual and determine the corresponding flight mode;

[0080] Step S207: Update the position of each individual;

[0081] Step S208: Calculate the attraction coefficient corresponding to each individual and update the position of each individual again;

[0082] Step S209: Compare the number of iterations t with the iteration threshold a; if t≥a, proceed to step S210; if t<a, set t=t+1 and return to step S206;

[0083] Step S210: Calculate the improvement degree corresponding to each individual, and use the value corresponding to the individual with the largest improvement degree as the screening radius.

[0084] In the above step S201, the iteration threshold a, step size factor b, adjustment factor d and intensity factor g are determined by those skilled in the art by collecting multiple sets of different real-time traffic data in the process of historically defining the screening radius; multiple sets of definition parameters are set for each set of real-time traffic data, and the definition parameters include the iteration threshold a, step size factor b, adjustment factor d and intensity factor g; for the same set of real-time traffic data corresponding to different sets of definition parameters, the corresponding screening radius is obtained through the dynamic radius algorithm of steps 1 to 10, and the corresponding improvement degree is calculated, and the definition parameter corresponding to the screening radius with the largest improvement degree is used as the definition parameter corresponding to the corresponding real-time traffic data; and the definition parameters corresponding to multiple sets of different real-time traffic data are obtained in this way; the mean of the multiple sets of definition parameters (i.e., the mean of the iteration threshold, the mean of the step size factor, the mean of the adjustment factor and the mean of the intensity factor) is used as the iteration threshold a, step size factor b, adjustment factor d and intensity factor g defined in step 1.

[0085] In the above step S203, the population S={X1, X2,…, X m}, X m is the mth individual; the position of each individual in the population S is defined in a one-dimensional search space, the range of the one-dimensional search space is the radius range; the expression of the position of each individual in the population S is: Where, is the position of the i-th individual, P i is the random coefficient of the i-th individual, P i ∈[0,1], i∈[1,m].

[0086] In the above step S204, the expression of the improvement function is: Where f is the improvement, jd is the order acceptance time, and ds is the waiting time. The order acceptance time is the time from when the passenger posts the order to when the driver accepts the order, and the waiting time is the time from when the passenger posts the order to when the driver arrives at the passenger's location. The order acceptance time and waiting time are obtained by using the real-time traffic data and the values ​​corresponding to the individual location as analysis data, inputting the analysis data into the trained first time model to predict the corresponding order acceptance time, and inputting the analysis data into the trained second time model to predict the corresponding waiting time. Both the first time model and the second time model are deep neural network models. The deep neural network model is an existing technology, and the specific training process will not be described in detail here.

[0087] In step S205, the method of dividing the population S into h subpopulations includes:

[0088] Calculate the improvement degree corresponding to each individual in population S and sort them from large to small; set an increasing number for each individual in the positive order of sorting, and the serial number range is [1, m]; according to the h subpopulations, perform a modulo operation on the number of each individual to obtain the corresponding subnumber; the expression of the subnumber is: l = u%h; where l is the subnumber, u is the number, and % is the modulo function; if the subnumber is not 0, the corresponding individual is assigned to the lth subpopulation; if the subnumber is 0, the corresponding individual is assigned to the hth subpopulation.

[0089] For example, population S includes 3 individuals, which are divided into 3 subpopulations. Since 1%3=1, the first individual is assigned to the first subpopulation. Since 2%3=2, the second individual is assigned to the second subpopulation. Since 3%3=0, the third individual is assigned to the third subpopulation.

[0090] In the above step S206, the expression of flight probability is: Where, is the flight probability corresponding to the i-th individual, is the improvement degree corresponding to the best individual, f i t is the improvement degree corresponding to the i-th individual, is the improvement degree corresponding to the worst individual; the best individual is the individual with the largest improvement degree in population S, and the worst individual is the individual with the smallest improvement degree in population S.

[0091] Methods for determining an individual's corresponding flight mode include:

[0092] A probability threshold is preset, and the probability threshold is pre-set by technical personnel in this field based on actual conditions; the flight probability corresponding to each individual is compared with the probability threshold; if the flight probability is greater than or equal to the probability threshold, the flight mode of the corresponding individual is global flight; if the flight probability is less than the probability threshold, the flight mode of the corresponding individual is local flight.

[0093] In the above step S207, the method for updating the location of each individual includes:

[0094] If the flight mode corresponding to the individual is global flight, the method for updating the position includes:

[0095]

[0096] Where, is the position of the i-th individual after update, is the position of the i-th individual before the update, b t is the step size factor in the t-th iteration process, is the position of the best individual, d tis the adjustment factor in the t-th iteration process, C1 is a random number between [0,1], is the flight speed of the i-th individual, g t is the intensity factor in the t-th iteration process, is the flight speed of the i-th individual in the last iteration;

[0097] The expression of flight speed is: Where C2 is a random number between [0,1].

[0098] If the flight mode corresponding to the individual is local flight, the method for updating the position includes:

[0099]

[0100] Where, is the position of the best individual in the subpopulation where the i-th individual is located. The best individual is the individual with the greatest improvement in the subpopulation.

[0101] In the above step S208, the expression of the attraction coefficient is: Where, is the attraction coefficient of the i′th individual to the i′th individual in the subpopulation where the i′th individual is located, exp is an exponential function, is the improvement degree corresponding to the i′th individual in the subpopulation where the i′th individual is located, i≠i′, i′∈[1,k].

[0102] The methods for updating the position of each individual again include:

[0103]

[0104] Where, is the position of the i-th individual after updating again, To update the position of the i′th individual in the subpopulation where the previous i-th individual is located.

[0105] The dispatch area is a circular area with the passenger's location as the center and the screening radius as the radius.

[0106] It should be noted that the above-mentioned individual position update formula guides the movement of individuals by considering factors such as the best individual position, its own historical position, flight speed, random numbers, etc., so that the individuals converge towards the optimal solution; among them, the global flight is guided by the global best individual and is used to explore the new one-dimensional search space to avoid local optimality; the local flight is guided by the best individual in the subpopulation to ensure that the individual can conduct a fine search near the local optimal solution and improve the local exploration ability; when calculating the attraction coefficient, the exponential decay function is used to measure the mutual attraction between individuals. When the difference in improvement between individuals is small, the attraction coefficient is larger, and when the difference in improvement between individuals is large, the attraction coefficient is smaller; by introducing the attraction coefficient to the subpopulation, it is possible to avoid individuals converging to the same solution in the one-dimensional search space, resulting in a loss of search diversity. The attraction coefficient provides a different search path for each subpopulation, thereby enhancing the global search ability of the algorithm and reducing the risk of premature convergence.

[0107] S3: The cloud platform receives the driver locations sent by all drivers in the dispatch area.

[0108] The driver side is an application used by the driver; the driver location is the driver's geographic coordinates, which is obtained by the driver side requesting access to the GPS of a second device, which is a mobile device used by the driver.

[0109] S4: The cloud platform obtains road traffic information, integrates the road traffic information, passenger location and all driver locations, calculates the shortest pick-up time from each driver location to the passenger location, and generates a time sorting table.

[0110] Methods for calculating the shortest pickup time from each driver location to the passenger location include:

[0111] Obtain all intersections within the dispatch area through the API of map software (such as AutoNavi Maps, Baidu Maps, etc.); obtain P pick-up routes from each driver's location to the passenger's location based on the passenger's location, driver's location, and intersection; calculate the pick-up time corresponding to each pick-up route, compare the pick-up time corresponding to each driver's location, and use the shortest pick-up time as the shortest pick-up time for the corresponding driver's location.

[0112] The steps for obtaining P pick-up routes from each driver's location to the passenger's location include:

[0113] Step S401: randomly selecting a driver position that is not marked as a selected position and marking it as the current position;

[0114] Step S402: Explore all adjacent intersections of the current location, randomly select one of the adjacent intersections as the subsequent intersection, and mark it as the selected intersection;

[0115] Step S403: Determine whether the passenger's location is adjacent to a subsequent intersection. If so, use the current location, the selected intersection, and the passenger's location as a pickup route. If not, proceed to step S404.

[0116] Step S404: Explore all adjacent intersections of the successor intersection, randomly select one of the adjacent intersections that is not marked as a selected intersection as the successor intersection, and mark it as a selected intersection;

[0117] Step S405: Determine whether the passenger's location is adjacent to a subsequent intersection. If so, use the current location, the selected intersection, and the passenger's location as a pickup route. If not, proceed to step S406.

[0118] Step S406: Determine whether all adjacent intersections of the subsequent intersection are marked as selected intersections. If so, unmark all intersections marked as selected intersections in step S404 and proceed to step S407. If not, return to step S404.

[0119] Step S407: looping through steps S402 to S406 until P pick-up routes are obtained, then the loop ends and the process proceeds to step S408;

[0120] Step S408: Loop steps S401 to S407 until all driver positions are marked as current positions. The loop ends and P pick-up paths from each driver position to the passenger position are obtained.

[0121] Methods for calculating the pick-up time corresponding to each pick-up route include:

[0122] The intersections corresponding to each pick-up route are regarded as an intersection set, and the intersection sets correspond to the pick-up routes one-to-one; two adjacent intersections in each intersection set are regarded as an adjacent set, and the road sections corresponding to each adjacent set are obtained and marked as pick-up sections; the traffic parameters corresponding to each pick-up section are obtained from real-time traffic data and marked as pick-up parameters; road traffic information is obtained through the map software API, and the road traffic information includes path length data and signal light status data; the path length data includes the path length corresponding to each pick-up route; the signal light status data includes the light status (such as red light, green light) and the corresponding duration of each intersection passed in the direction of each pick-up route; different digital labels are set for different light statuses and marked as light labels; the light status in the signal light status data is replaced with the corresponding light label; the pick-up parameters, path length and signal light status data corresponding to each pick-up route are regarded as a set of calculation data, and the calculation data correspond to the pick-up route one-to-one; each set of calculation data is input into the trained time prediction model to predict the corresponding pick-up time, and the time prediction model is a deep neural network model.

[0123] Methods for generating a time-sorted table include:

[0124] Sort all the shortest pick-up times from short to long and generate a time sorting table.

[0125] S5: The cloud platform sends the order to the driver with the shortest pick-up time. If the driver does not accept the order, the cloud platform assigns the order to the driver in sequence according to the time sorting table.

[0126] If the driver side does not accept the order, the order will be dispatched to the driver side in positive order according to the time sorting table. If all driver sides do not accept the order, the screening radius will be multiplied by the preset expansion coefficient to obtain the expanded radius. Based on the expanded radius, the dispatch area will be generated for the passenger position again and the order will be dispatched again; the expansion coefficient is pre-set by technical personnel in this field according to actual conditions.

[0127] This embodiment obtains passenger location and real-time traffic data, and uses a dynamic radius algorithm to adaptively generate a dispatch area, thereby achieving dynamic adjustment of the dispatch range and improving the accuracy of dispatch. It calculates the shortest pick-up time from each driver's location to the passenger's location in real time, and prioritizes dispatching to drivers closest to the passengers, thereby reducing passenger waiting time and driver idle rate, thereby effectively improving user experience. It makes full use of cloud computing and big data analysis technologies to achieve intelligent optimization and dynamic adjustment of order dispatch, improve overall operational efficiency, and adapt to travel needs in the context of the sharing economy.

[0128] Example 2

[0129] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories may store computer-readable code that, when executed by the one or more processors, may execute the above-described order management method based on cloud computing services.

[0130] The method or system according to the embodiment of the present application can also be implemented with the aid of the architecture of the electronic device shown in this application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. The storage device in the electronic device, such as a ROM or a hard disk, can store an order management method based on cloud computing services provided in this application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in this application is only exemplary. When implementing different devices, one or more components in the electronic device shown in this application may be omitted according to actual needs.

[0131] Example 3

[0132] As shown, one embodiment of the present application discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by a processor, a cloud computing service-based order management method according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc.

[0133] In addition, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be executed by a processor to perform instructions corresponding to the steps of the method provided in the present application, such as a method for order management based on cloud computing services. When the computer program is executed by a central processing unit (CPU), the above-mentioned functions defined in the method of the present application are performed.

[0134] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0135] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An order management method based on cloud computing services, characterized in that: Applied in cloud platforms, including: S1: The cloud platform receives the passenger location sent by the passenger terminal; S2: The cloud platform obtains real-time traffic data, uses a dynamic radius algorithm to define a filtering radius based on the real-time traffic data, and generates a dispatch area based on the filtering radius for the passenger location; S3: The cloud platform receives the driver locations sent by all drivers in the dispatch area; S4: The cloud platform obtains road traffic information, integrates the road traffic information, passenger location, and all driver locations, calculates the shortest pick-up time from each driver location to the passenger location, and generates a time ranking table; S5: The cloud platform sends the order to the driver with the shortest pickup time. If the driver does not accept the order, the cloud platform assigns the order to the driver in order according to the time sorting table. The passenger location is the geographical coordinates of the passenger, and the driver location is the geographical coordinates of the driver; Real-time traffic data includes traffic parameters corresponding to each road section within the screening range, including traffic density and traffic speed. The screening range is a circular area with the passenger's location as the center and the preset screening distance as the radius. The steps to define the screening radius are: Step S201: defining an iteration threshold a, a step size factor b, an adjustment factor d, and an intensity factor g; Step S202: Preset radius range; Step S203: construct a population S, which includes m individuals. The position of each individual corresponds to a value within the radius. The initial number of iterations t for the population S is 0. Step S204: defining an improvement function; Step S205: Divide the population S into h subpopulations, each subpopulation includes k individuals, m=hk; Step S206: Calculate the flight probability corresponding to each individual and determine the corresponding flight mode; Step S207: Update the position of each individual; Step S208: Calculate the attraction coefficient corresponding to each individual and update the position of each individual again; Step S209: Compare the number of iterations t with the iteration threshold a; if t≥a, proceed to step S210; if t<a, set t=t+1 and return to step S206; Step S210: Calculate the improvement degree corresponding to each individual, and use the value corresponding to the individual with the largest improvement degree as the screening radius.

2. The order management method based on cloud computing services according to claim 1, characterized in that: In step S203, population S={X1, X2, ..., X m }, X m is the mth individual; the position of each individual in the population S is defined in a one-dimensional search space, the range of the one-dimensional search space is the radius range; the expression of the position of each individual in the population S is: Where, is the position of the i-th individual, P i is the random coefficient of the i-th individual, P i ∈[0,1], i∈[1,m]; In step S204, the expression of the improvement function is: Where f is the improvement, jd is the order acceptance time, and ds is the waiting time. The order acceptance time is the time from when the passenger posts the order to when the driver accepts the order, and the waiting time is the time from when the passenger posts the order to when the driver arrives at the passenger's location. The order acceptance time and waiting time are obtained by using the real-time traffic data and the values ​​corresponding to the individual location as analysis data, inputting the analysis data into the trained first time model to predict the corresponding order acceptance time, and inputting the analysis data into the trained second time model to predict the corresponding waiting time. Both the first time model and the second time model are deep neural network models.

3. The order management method based on cloud computing services according to claim 2, characterized in that: In step S205, the method of dividing the population S into h subpopulations includes: Calculate the improvement degree corresponding to each individual in population S and sort them from large to small; assign an increasing number to each individual in the positive order of sorting, with the sequence number range being [1, m]; perform a modulo operation on the number of each individual according to the number of h subpopulations to obtain the corresponding subnumber; the expression for the subnumber is: l = u%h; where l is the subnumber, u is the number, and % is the modulo function; if the subnumber is not 0, assign the corresponding individual to the lth subpopulation; if the subnumber is 0, assign the corresponding individual to the hth subpopulation; In step S206, the expression of flight probability is: Where, is the flight probability corresponding to the i-th individual, is the improvement degree corresponding to the best individual, is the improvement degree corresponding to the i-th individual, is the improvement degree corresponding to the worst individual; the best individual is the individual with the largest improvement degree in population S, and the worst individual is the individual with the smallest improvement degree in population S; Methods for determining an individual's corresponding flight mode include: A probability threshold is preset, and the flight probability corresponding to each individual is compared with the probability threshold; if the flight probability is greater than or equal to the probability threshold, the flight mode of the corresponding individual is global flight; if the flight probability is less than the probability threshold, the flight mode of the corresponding individual is local flight.

4. The order management method based on cloud computing services according to claim 3, characterized in that: In step S207, the method for updating the location of each individual includes: If the flight mode corresponding to the individual is global flight, the method for updating the position includes: Where, is the position of the i-th individual after update, is the position of the i-th individual before the update, b t is the step size factor in the t-th iteration process, is the position of the best individual, d t is the adjustment factor in the t-th iteration process, C1 is a random number between [0,1], is the flight speed of the i-th individual, g t is the intensity factor in the t-th iteration process, is the flight speed of the i-th individual in the last iteration; The expression of flight speed is: Where C2 is a random number between [0,1]; If the flight mode corresponding to the individual is local flight, the method for updating the position includes: Where, is the position of the best individual in the subpopulation where the i-th individual is located. The best individual is the individual with the greatest improvement in the subpopulation.

5. The order management method based on cloud computing services according to claim 4, characterized in that: In step S208, the expression of the attraction coefficient is: Where, is the attraction coefficient of the i′th individual to the i′th individual in the subpopulation where the i′th individual is located, exp is an exponential function, is the improvement degree corresponding to the i′th individual in the subpopulation where the i′th individual is located, i≠i′, i′∈[1,k]; The methods for updating the position of each individual again include: Where, is the position of the i-th individual after updating again, To update the position of the i′th individual in the subpopulation where the i-th individual is located; The dispatch area is a circular area with the passenger's location as the center and the screening radius as the radius.

6. The order management method based on cloud computing services according to claim 5, characterized in that: The method for calculating the shortest pickup time from each driver's position to the passenger's position includes: Obtain all intersections within the dispatch area; based on the passenger location, driver location, and intersection, obtain P pick-up routes from each driver location to the passenger location; calculate the pick-up time corresponding to each pick-up route, compare the pick-up time corresponding to each driver location, and use the shortest pick-up time as the shortest pick-up time for the corresponding driver location.

7. The order management method based on cloud computing services according to claim 6, characterized in that: The step of obtaining P pick-up routes from each driver's location to the passenger's location includes: Step S401: randomly selecting a driver position that is not marked as a selected position and marking it as the current position; Step S402: Explore all adjacent intersections of the current location, randomly select one of the adjacent intersections as the subsequent intersection, and mark it as the selected intersection; Step S403: Determine whether the passenger's location is adjacent to a subsequent intersection. If so, use the current location, the selected intersection, and the passenger's location as a pickup route. If not, proceed to step S404. Step S404: Explore all adjacent intersections of the successor intersection, randomly select one of the adjacent intersections that is not marked as a selected intersection as the successor intersection, and mark it as a selected intersection; Step S405: Determine whether the passenger's location is adjacent to a subsequent intersection. If so, use the current location, the selected intersection, and the passenger's location as a pickup route. If not, proceed to step S406. Step S406: Determine whether all adjacent intersections of the subsequent intersection are marked as selected intersections. If so, unmark all intersections marked as selected intersections in step S404 and proceed to step S407. If not, return to step S404. Step S407: looping through steps S402 to S406 until P pick-up routes are obtained, then the loop ends and the process proceeds to step S408; Step S408: Loop steps S401 to S407 until all driver positions are marked as current positions. The loop ends and P pick-up paths from each driver position to the passenger position are obtained.

8. The order management method based on cloud computing services according to claim 7, characterized in that: The method for calculating the pick-up time corresponding to each pick-up route includes: The intersections corresponding to each pick-up route are taken as an intersection set, and the intersection sets correspond to the pick-up routes one-to-one; the two adjacent intersections in each intersection set are taken as an adjacent set, and the road sections corresponding to each adjacent set are obtained and marked as pick-up sections; the traffic parameters corresponding to each pick-up section are obtained from the real-time traffic data and marked as pick-up parameters; road traffic information is obtained, and the road traffic information includes path length data and signal light status data; the path length data includes the path length corresponding to each pick-up route; the signal light status data includes the light status of each intersection passed in the direction of each pick-up route and the corresponding duration; different digital labels are set for different light statuses, and marked as light labels; the light status in the signal light status data is replaced with the corresponding light label; the pick-up parameters, path length and signal light status data corresponding to each pick-up route are taken as a set of calculation data, and the calculation data correspond to the pick-up route one-to-one; each set of calculation data is input into the trained time prediction model to predict the corresponding pick-up time, and the time prediction model is a deep neural network model; Methods for generating a time-sorted table include: Sort all the shortest pick-up times from short to long and generate a time sorting table.

9. The order management method based on cloud computing services according to claim 8, characterized in that: If the driver side does not accept the order, the order will be dispatched to the driver side in positive order according to the time sorting table. If all driver sides do not accept the order, the screening radius will be multiplied by the preset expansion coefficient to obtain the expanded radius. Based on the expanded radius, the dispatch area will be generated for the passenger location again and the order will be dispatched again.

Images