Order management method based on cloud computing service

Abstract

The invention belongs to the technical field of order management, and discloses an order management method based on cloud computing service. The method comprises the steps that the cloud platform receives a passenger position sent by a passenger terminal; acquiring real-time traffic data, defining a screening radius, and generating an order dispatching area for passenger positions; driver positions sent by all driver ends in the order sending area are received; road traffic information is obtained, the road traffic information, the passenger position and all driver positions are fused, the shortest driving time from each driver position to the passenger position is calculated, and a time sorting table is generated; the order is sent to the driver end with the shortest receiving time, and if the driver end does not receive the order, the order is sent to the driver end in sequence according to the time sorting table; according to the invention, cloud computing and big data analysis technologies are fully utilized, intelligent optimization and dynamic adjustment of order distribution are realized, the waiting time of passengers and the unloaded driving rate of drivers can be effectively reduced, the user experience is effectively improved, and the overall operation efficiency is improved.

Description

Technical Field

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

[0002] With the rise of the sharing economy, online car-hailing services have become an important way of urban travel; during the operation of online car-hailing platforms, real-time dispatching of orders is the key to improving service efficiency; traditional dispatching methods usually rely on fixed area division or simple distance matching algorithms, and cannot fully consider dynamic factors such as real-time road conditions and drivers' driving trajectories, resulting in uneven order distribution, unreasonable dispatching, long waiting times for users, etc., affecting the passenger experience and driver income; therefore, there is an urgent need for an intelligent online car-hailing order management method.

[0003] The patent with the publication number CN117522530B discloses an online car-hailing travel order management method; including: when the online car-hailing management center receives a user's travel order based on a wireless network, first locate the user's position, and then use the user's location as the center of a circle to generate a dispatching area A for the user with a preset radius r1, obtain the number of online car-hailing vehicles in the dispatching area A that are in the order-receiving state, if the number of online car-hailing vehicles in the dispatching area A that are in the order-receiving state is greater than 1, then after obtaining multiple data of all online car-hailing vehicles, sort all online car-hailing vehicles based on a sorting algorithm, and assign the travel order to the online car-hailing vehicle ranked first; thus effectively improving the uniformity of order dispatching by the online car-hailing management center and the efficiency of travel order management.

[0004] However, although the above technology can achieve order management of online car-hailing, during the order dispatching process, it mainly comprehensively considers multiple data of online car-hailing, including the number of orders received during a specified time period, mileage index, vehicle idle time, and vehicle failure frequency, and does not consider the time it takes for the online car-hailing to reach the passenger's location, resulting in the driver having to drive a long distance to reach the passenger's location after receiving the order, increasing the driver's empty driving rate and reducing the operation efficiency; at the same time, it prolongs the passenger's waiting time 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 object, the present invention provides the following technical solution: An order management method based on cloud computing services, which is applied to a cloud platform and includes:

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

[0008] S2: The cloud platform obtains real-time traffic data, defines a screening radius using a dynamic radius algorithm based on the real-time traffic data, and generates a dispatching area for the passenger location based on the screening radius;

[0009] S3: The cloud platform receives the driver locations sent by all driver terminals within the dispatching area;

[0010] S4: The cloud platform obtains road traffic information, fuses the road traffic information, the 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;

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

[0012] Furthermore, the passenger location is the geographical coordinate where the passenger is located, and the driver location is the geographical coordinate where the driver is located;

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

[0014] The steps of defining the screening radius include:

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

[0016] Step S202: Preset a radius range;

[0017] Step S203: Construct a population S. The population S includes m individuals. The position of each individual corresponds one-to-one with the values within the radius range. The initial iteration count t corresponding to the population S is 0;

[0018] Step S204: Define an improvement degree function;

[0019] Step S205: Divide the population S into h sub-populations. Each sub-population includes k individuals, and 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 iteration number t with the iteration threshold a; if t ≥ a, then go to step S210; if t < a, then 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 the said step S203, the population S = {X1, X2, …, X m}, X m is the m-th individual; the position of each individual in the population S is defined in a one-dimensional search space, and 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: In the formula, 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 the said step S204, the expression of the improvement degree function is: In the formula, f is the improvement degree, jd is the order receiving time, and ds is the waiting time; among them, the order receiving time is the time elapsed from when the passenger posts an order to when the driver receives the order, and the waiting time is the time elapsed from when the passenger posts an order to when the driver arrives at the passenger's location; the obtaining methods of the order receiving time and the waiting time are: using the real-time traffic data and the value corresponding to the individual position as the analysis data, inputting the analysis data into the trained first time model to predict the corresponding order receiving 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 the said step S205, the method of dividing the population S into h sub-populations includes:

[0028] Calculate the improvement degree corresponding to each individual in the population S, and sort them from large to small; set an increasing serial number for each individual in ascending order according to the sorting, and the serial number range is [1, m]; according to the h sub-populations, perform a modulo operation on the serial number of each individual to obtain the corresponding sub-serial number; the expression of the sub-serial number is: l = u % h; in the formula, l is the sub-serial number, u is the serial number, and % is the modulo function; if the sub-serial number is not 0, then assign the corresponding individual to the l-th sub-population; if the sub-serial number is 0, then assign the corresponding individual to the h-th sub-population;

[0029] In the said step S206, the expression of the flight probability is: In the formula, 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 one with the largest improvement degree in population S, and the worst individual is the one with the smallest improvement degree in population S;

[0030] The method for determining the flight mode corresponding to an individual includes:

[0031] Preset a probability threshold, and compare the flight probability corresponding to each individual with the probability threshold respectively; 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 the step S207, the method for updating the position 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] In the formula, is the position of the i-th individual after update, is the position of the i-th individual before 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 previous iteration process;

[0036] The expression of the flight speed is: In the formula, 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] In the formula, is the position of the optimal individual in the sub-population where the i-th individual is located, and the optimal individual is the one with the largest improvement degree in the sub-population.

[0040] Further, in the step S208, the expression of the attraction coefficient is as follows: In the formula, is the attraction coefficient of the i'-th individual to the i-th individual in the sub-population where the i-th individual is located. exp is the exponential function, is the improvement degree corresponding to the i'-th individual in the sub-population where the i-th individual is located, i ≠ i', i' ∈ [1, k];

[0041] The method for updating the position of each individual again includes:

[0042]

[0043] In the formula, is the position of the i-th individual after being updated again, is the position of the i'-th individual in the sub-population where the i-th individual is located before being updated again;

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

[0045] Further, 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 order dispatch area; according to the passenger's position, the driver's position, and the intersections, obtain P pick-up routes from each driver's position to the passenger's position; calculate the pick-up time corresponding to each pick-up route, compare the pick-up times corresponding to each driver's position, and take the shortest pick-up time as the shortest pick-up time for the corresponding driver's position.

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

[0048] Step S401: Randomly select a driver's position that is not marked as a selected position and mark it as the current position;

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

[0050] Step S403: Determine whether the passenger's position is adjacent to the successor intersection. If so, take the current position, the selected intersection, and the passenger's position as a pick-up route. If not, go 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 the selected intersection;

[0052] Step S405: Determine whether the passenger's location is adjacent to the successor intersection. If so, use the current location, the selected intersection, and the passenger's location as a pick-up path. If not, proceed to Step S406;

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

[0054] Step S407: Loop through Steps S402 to S406 until P pick-up paths are obtained. When the loop ends, proceed to Step S408;

[0055] Step S408: Loop through Steps S401 to S407 until all driver locations are marked as the current location. When the loop ends, obtain P pick-up paths from each driver location to the passenger location.

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

[0057] Take the intersections corresponding to each pick-up path as an intersection set, and the intersection sets correspond one-to-one with the pick-up paths; take two adjacent intersections in each intersection set as an adjacent set, obtain the road segments corresponding to each adjacent set, and mark them as pick-up road segments; obtain the traffic parameters corresponding to each pick-up road segment from the real-time traffic data and mark them as pick-up parameters; obtain the road traffic information, which includes path length data and signal light status data; the path length data includes the path length corresponding to each pick-up path; the signal light status data includes the light status and the corresponding duration of each passed intersection in the direction of each pick-up path; set different digital labels for different light statuses and mark them as light labels; replace the light statuses in the signal light status data with the corresponding light labels; take the pick-up parameters, path lengths, and signal light status data corresponding to each pick-up path as a set of calculation data, and the calculation data corresponds one-to-one with the pick-up paths; input each set of calculation data into the trained time prediction model respectively to predict the corresponding pick-up time, and the time prediction model is a deep neural network model;

[0058] The method for generating a time sorting table includes:

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

[0060] Further, if the driver side has not accepted the order, dispatch the driver side in ascending order according to the time sorting table. If all driver sides have not accepted the order, multiply the screening radius by a preset expansion coefficient to obtain an expanded radius, generate a dispatch area for the passenger location based on the expanded radius, and re-dispatch the order.

[0061] Technical effects and advantages of an order management method based on cloud computing services according to the present invention:

[0062] By obtaining the passenger location and real-time traffic data, using the dynamic radius algorithm to adaptively generate the order dispatch area, realizing the dynamic adjustment of the order dispatch scope, and improving the accuracy of order dispatch; calculating in real time the shortest pick-up time from each driver's location to the passenger location, and preferentially dispatching orders to the driver closest to the passenger, thereby reducing the passenger waiting time and the empty driving rate of the driver, and further effectively improving the user experience; making full use of cloud computing and big data analysis technologies to realize the intelligent optimization and dynamic adjustment of order dispatch, improving the overall operation efficiency, and meeting the travel needs under the background of the sharing economy. Brief Description of the Drawings

[0063] Figure 1 It is a flowchart of an order management method based on cloud computing services according to Embodiment 1 of the present invention; Detailed Embodiments

[0064] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0065] Embodiment 1

[0066] Please refer to Figure 1 As shown, an 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 institution based on cloud computing technology, usually including components such as servers, storage, databases, and application programs, and is used to process and manage data; the passenger terminal is an application program used by passengers;

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

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

[0071] The real-time traffic data includes traffic parameters corresponding to each road segment within the screening range. The traffic parameters include traffic density and traffic speed. The screening range is a circular area centered at the passenger's location with a preset screening distance as the radius. The screening distance is preset by those skilled in the art according to the actual situation. The real-time traffic data is obtained through the API of map service providers (such as AutoNavi Map, Baidu Map, Tencent Map, etc.).

[0072] The traffic density is the number of vehicles traveling on different road segments, and the traffic speed is the average driving speed of vehicles on different road segments. It should be understood that the higher the traffic density, the slower the traffic speed, indicating that there are more vehicles in the screening area and the slower the vehicle driving speed, that is, the more congested the screening area is. Therefore, the screening radius should be reduced to preferentially match nearby drivers, reducing the driving distance of the driver and the waiting time of the passenger. On the contrary, the lower the traffic density, the faster the traffic speed, indicating that there are fewer vehicles in the screening area and the faster the vehicle driving speed. Therefore, the screening radius should be expanded to cover a larger area, which helps to match more drivers, improve the order acceptance rate, and prevent passengers from waiting for a long time due to insufficient drivers.

[0073] The steps for defining the screening radius include:

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

[0075] Step S202: Preset the radius range, which is preset by those skilled in the art according to the actual situation;

[0076] Step S203: Construct a population S, where the population S includes m individuals, and the position of each individual corresponds one-to-one with the values within the radius range. The population S corresponds to the initial iteration number t = 0;

[0077] Step S204: Define the improvement degree function;

[0078] Step S205: Divide the population S into h sub-populations, each sub-population includes k individuals, and 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 iteration number t with the iteration threshold a; if t ≥ a, go to step S210; if t < a, let 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. During the process of historically defining the screening radius, multiple groups of different real-time traffic data are collected; for each group of real-time traffic data, multiple groups of different definition parameters are set, and the definition parameters include the iteration threshold a, step size factor b, adjustment factor d, and intensity factor g; for the same group of real-time traffic data corresponding to different groups of definition parameters, the corresponding screening radius is obtained through the dynamic radius algorithm of steps 1 - 10, and the corresponding improvement degree is calculated. The definition parameters corresponding to the screening radius with the largest improvement degree are used as the definition parameters corresponding to the corresponding real-time traffic data; and so on to obtain the definition parameters corresponding to multiple groups of different real-time traffic data; the mean values of the multiple groups of definition parameters (i.e., the mean iteration threshold, mean step size factor, mean adjustment factor, and mean intensity factor) are 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 m-th individual; the position of each individual in the population S is defined in a one-dimensional search space, and 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: In the formula, 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 degree function is: In the formula, f is the improvement degree, jd is the order receiving time, and ds is the waiting time; among them, the order receiving time is the time elapsed from when the passenger issues an order to when the driver receives the order, and the waiting time is the time elapsed from when the passenger issues an order to when the driver arrives at the passenger's location; the methods for obtaining the order receiving time and the waiting time are: using the real-time traffic data and the value corresponding to the individual position as analysis data, inputting the analysis data into the trained first time model to predict the corresponding order receiving 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, and the deep neural network model is prior art, and the specific training process will not be elaborated here.

[0087] In the above step S205, the method for dividing the population S into h sub-populations includes:

[0088] Calculate the improvement degree corresponding to each individual in population S, and sort them from largest to smallest; set an increasing number for each individual in ascending order according to the sorting, and the serial number range is [1, m]; according to h sub-populations, perform a modulo operation on the number of each individual to obtain the corresponding sub-number; the expression for the sub-number is: l = u % h; where l is the sub-number, u is the number, and % is the modulo function; if the sub-number is not 0, assign the corresponding individual to the l-th sub-population; if the sub-number is 0, assign the corresponding individual to the h-th sub-population.

[0089] Exemplarily, population S includes 3 individuals and is divided into 3 sub-populations. Since 1 % 3 = 1, the first individual is assigned to the first sub-population. Since 2 % 3 = 2, the second individual is assigned to the second sub-population. Since 3 % 3 = 0, the third individual is assigned to the third sub-population.

[0090] In the above step S206, the expression for the 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] The method for judging the flight mode corresponding to an individual includes:

[0092] Preset a probability threshold, which is preset by those skilled in the art according to the actual situation; compare the flight probability corresponding to each individual with the probability threshold respectively; 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 position of each individual includes:

[0094] If the flight mode corresponding to an 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 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 previous iteration process;

[0097] The expression of the flight speed is: In the formula, 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] In the formula, is the position of the optimal individual in the sub-population where the i-th individual is located. The optimal individual is the individual with the largest improvement degree in the sub-population.

[0101] In the above step S208, the expression of the attraction coefficient is: In the formula, is the attraction coefficient of the i'-th individual to the i-th individual in the sub-population where the i-th individual is located. exp is the exponential function. is the improvement degree corresponding to the i'-th individual in the sub-population where the i-th individual is located, i ≠ i', i' ∈ [1, k].

[0102] The method for updating the position of each individual again includes:

[0103]

[0104] In the formula, is the position of the i-th individual after being updated again. is the position of the i'-th individual in the sub-population where the i-th individual is located before being updated again.

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

[0106] It should be noted that the above 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., enabling individuals to converge towards the optimal solution. Among them, global flight is guided by the global best individual and is used to explore new one-dimensional search spaces to avoid local optima. Local flight is guided by the optimal individual of the subpopulation to ensure that individuals can conduct fine-grained searches near the local optimal solution and enhance local exploration capabilities. When calculating the attraction coefficient, an exponential decay function is used to measure the mutual attraction between individuals. When the difference in improvement degrees between individuals is small, the attraction coefficient is larger; when the difference in improvement degrees between individuals is large, the attraction coefficient is smaller. By introducing the attraction coefficient into the subpopulation, it is possible to prevent individuals from converging to the same solution in the one-dimensional search space, resulting in the loss of search diversity. The attraction coefficient provides different search paths 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 positions sent by all driver terminals within the dispatched area.

[0108] The driver terminal is an application used by the driver; the driver position is the geographical coordinate where the driver is located, and the driver position is obtained by the driver terminal requesting access to the GPS of the second device, and the second device is a mobile device used by the driver.

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

[0110] The method for calculating the shortest pick-up time from each driver position to the passenger position includes:

[0111] Obtain all intersections within the dispatched area through the API of a map software (such as Amap, Baidu Map, etc.); obtain P pick-up paths from each driver position to the passenger position based on the passenger position, driver position, and intersections; calculate the pick-up time corresponding to each pick-up path, compare the pick-up times corresponding to each driver position, and take the shortest pick-up time as the shortest pick-up time for the corresponding driver position.

[0112] The steps for obtaining P pick-up paths from each driver position to the passenger position include:

[0113] Step S401: Randomly select a driver position that is not marked as a selected position and mark it as the current position.

[0114] Step S402: Explore all adjacent intersections of the current position, randomly select one of the adjacent intersections as the successor intersection, and mark it as the selected intersection.

[0115] Step S403: Determine whether the passenger's location is adjacent to the successor intersection. If so, use the current location, the selected intersection, and the passenger's location as a pick-up path. If not, proceed to Step S404;

[0116] Step S404: Explore all adjacent intersections of the successor intersection, randomly select one adjacent intersection 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 the successor intersection. If so, use the current location, the selected intersection, and the passenger's location as a pick-up path. If not, proceed to Step S406;

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

[0119] Step S407: Loop Steps S402 to S406 until P pick-up paths are obtained. The loop ends and proceed to Step S408;

[0120] Step S408: Loop Steps S401 to S407 until all driver locations are marked as the current location. The loop ends and obtain P pick-up paths from each driver location to the passenger location.

[0121] The method for calculating the pick-up time corresponding to each pick-up path includes:

[0122] Take the intersections corresponding to each pick-up path as an intersection set, and the intersection sets and the pick-up paths correspond one by one; take two adjacent intersections in each intersection set as an adjacent set, obtain the road segments corresponding to each adjacent set, and mark them as pick-up road segments; obtain the traffic parameters corresponding to each pick-up road segment from the real-time traffic data and mark them as pick-up parameters; through the map software API, obtain the road traffic information, 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 path; the signal light status data includes the light status (such as red light on, green light on) and the corresponding duration of each passed intersection in the direction of each pick-up path; set different digital tags for different light statuses and mark them as light tags; replace the light statuses in the signal light status data with the corresponding light tags; take the pick-up parameters, path lengths, and signal light status data corresponding to each pick-up path as a set of calculation data, and the calculation data and the pick-up paths correspond one by one; input each set of calculation data into the trained time prediction model respectively to predict the corresponding pick-up time, and the time prediction model is a deep neural network model.

[0123] The method for generating a time sorting table includes:

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

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

[0126] If the driver terminal does not accept the order, the driver terminals are dispatched sequentially in ascending order according to the time sorting table. If all driver terminals do not accept the order, multiply the screening radius by a preset expansion coefficient to obtain an expanded radius, generate a dispatching area for the passenger location again based on the expanded radius, and re-dispatch the order; the expansion coefficient is preset by those skilled in the art according to the actual situation.

[0127] In this embodiment, by obtaining the passenger location and real-time traffic data, using the dynamic radius algorithm to adaptively generate a dispatching area, the dynamic adjustment of the dispatching range is realized, and the accuracy of dispatching is improved; the shortest pick-up time from each driver location to the passenger location is calculated in real time, and the order is preferentially dispatched to the driver closest to the passenger, thereby reducing the passenger waiting time and the driver's empty driving rate, and effectively improving the user experience; making full use of cloud computing and big data analysis technologies, realizing the intelligent optimization and dynamic adjustment of order dispatching, improving the overall operation efficiency, and meeting the travel needs under the background of the sharing economy.

[0128] Embodiment 2

[0129] This application also provides an electronic device. The electronic device may include one or more processors and one or more memories. Among them, computer-readable code is stored in the memory, and when the computer-readable code is run by one or more processors, it can execute an order management method based on cloud computing services as described above.

[0130] The method or system according to the embodiment of the present application can also be implemented by means of the architecture of the electronic device shown in the present application. The electronic device may include a bus, one or more CPUs, a ROM, a RAM, a communication port connected to the network, an 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 by the present application. Further, the electronic device may also include a user interface. Of course, the architecture shown in the present application is only exemplary, and when implementing different devices, one or more components shown in the electronic device of the present application can be omitted according to actual needs.

[0131] Embodiment 3

[0132] Referring to the illustration, an 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 run by a processor, a method for order management based on cloud computing services according to an embodiment of the present application as described with reference to the above drawings can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disks, flash memory, etc.

[0133] In addition, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be run by a processor to execute instructions corresponding to the method steps provided by 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 functions defined in the method of the present application are executed.

[0134] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0135] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should all be included within the protection scope of the present invention.

Claims

1. An order management method based on cloud computing services, characterized in that, Applied to the cloud platform, including: S1: The cloud platform receives the passenger's location sent by the passenger terminal. S2: The cloud platform obtains real-time traffic data, defines a screening radius using a dynamic radius algorithm based on the real-time traffic data, and generates a dispatching area for the passenger's location based on the screening radius. S3: The cloud platform receives the driver's locations sent by all driver terminals within the dispatching area. S4: The cloud platform obtains road traffic information, fuses the road traffic information, the passenger's 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. S5: The cloud platform sends the order to the driver terminal with the shortest pick-up time. If the driver terminal does not accept the order, the cloud platform dispatches the order to the driver terminals in sequence according to the time sorting table.

2. The order management method based on cloud computing service according to claim 1, characterized in that, The passenger's location is the geographical coordinate where the passenger is located, and the driver's location is the geographical coordinate where the driver is located. The real-time traffic data includes traffic parameters corresponding to each road section within the screening range. The traffic parameters include traffic density and traffic speed. The screening range is a circular area with the passenger's location as the center and a preset screening distance as the radius. The steps for defining the screening radius include: Step S201: Define the iteration threshold a, step factor b, adjustment factor d, and intensity factor g. Step S202: Preset the radius range. Step S203: Construct a population S. The population S includes m individuals, and the position of each individual corresponds one-to-one with the values within the radius range. The population S corresponds to the initial iteration count t = 0. Step S204: Define the improvement degree function. Step S205: Divide the population S into h sub-populations, each sub-population includes k individuals, and 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 iteration count t with the iteration threshold a. If t ≥ a, go 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 maximum improvement degree as the screening radius.

3. The order management method based on cloud computing service according to claim 2, characterized in that, In the step S203, the population S = {X1, X2, …, X m}, where X m is the m-th individual; the position of each individual in the population S is defined in a one-dimensional search space, and 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: In the formula, 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 the step S204, the expression of the improvement degree function is as follows: In the formula, f is the improvement degree, jd is the order receiving time, and ds is the waiting time. Among them, the order receiving time is the time elapsed from when the passenger issues an order to when the driver receives the order, and the waiting time is the time elapsed from when the passenger issues an order to when the driver arrives at the location of the passenger. The methods for obtaining the order receiving time and the waiting time are as follows: taking the real-time traffic data and the values corresponding to the individual positions as analysis data, inputting the analysis data into the trained first time model to predict the corresponding order receiving 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.

4. A method for order management based on cloud computing services according to claim 3, characterized in that, In step S205, the method of dividing the population S into h sub-populations includes: Calculate the improvement degree corresponding to each individual in the population S, and sort them from large to small. Set an increasing serial number for each individual in ascending order according to the sorting. The serial number range is [1, m]. According to the h sub-populations, perform a modulo operation on the serial number of each individual to obtain the corresponding sub-serial number. The expression for the sub-serial number is: l = u % h; where l is the sub-serial number, u is the serial number, and % is the modulo function. If the sub-serial number is not 0, assign the corresponding individual to the l-th sub-population. If the sub-serial number is 0, assign the corresponding individual to the h-th sub-population. In the step S206, the expression of the flight probability is as follows: In the formula, 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 the population S, and the worst individual is the individual with the smallest improvement degree in the population S; The method of determining the flight mode corresponding to an individual includes: A preset probability threshold is used to compare the flight probability corresponding to each individual with the probability threshold respectively. 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.

5. The order management method based on cloud computing service according to claim 4, wherein In step S207, the method for updating the position of each individual includes: If the flight mode corresponding to the individual is global flight, the method for updating the position includes: Wherein, is the position of the i-th individual after update, is the position of the i-th individual before 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 previous iteration process; The expression for the flight speed is as follows: 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: wherein, is the position of the optimal individual in the sub-population where the i-th individual is located, and the optimal individual is the individual with the largest improvement degree in the sub-population.

6. The order management method based on cloud computing service according to claim 5, characterized in that In the step S208, the expression of the attraction coefficient is as follows: In the formula, is the attraction coefficient of the i'-th individual to the i-th individual in the sub-population where the i-th individual is located. exp is the exponential function, is the improvement degree corresponding to the i'-th individual in the sub-population where the i-th individual is located, i≠i', i'∈[1,k]; The method for updating the position of each individual again includes: wherein, is the position of the i-th individual after the second update, is the position of the i'-th individual in the sub-population where the i-th individual is located before the second update; The order assignment area is a circular area with the passenger's position as the center and the screening radius as the radius.

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

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

9. The order management method based on cloud computing service according to claim 8, wherein, The method for calculating the pick-up time corresponding to each pick-up route includes: Take the intersections corresponding to each pick-up route as an intersection set, and the intersection set corresponds to the pick-up route one by one; take two adjacent intersections in each intersection set as an adjacent set, obtain the road section corresponding to each adjacent set, and mark it as a pick-up road section; obtain the traffic parameters corresponding to each pick-up road section from the real-time traffic data, and mark them as pick-up parameters; obtain the road traffic information, and the road traffic information includes the path length data and the 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 and the corresponding duration of each passed intersection in the direction of each pick-up route; set different digital tags for different light statuses, and mark them as light tags; replace all the light statuses in the signal light status data with the corresponding light tags; take the pick-up parameters, path length, and signal light status data corresponding to each pick-up route as a set of calculation data, and the calculation data corresponds to the pick-up route one by one; input each set of calculation data into the trained time prediction model respectively, and predict the corresponding pick-up time, and the time prediction model is a deep neural network model; The method for generating a time sorting table includes: Sort all the shortest pick-up times from short to long to generate a time sorting table.

10. The order management method based on cloud computing service according to claim 9, characterized in that, If the driver side has not accepted the order, then dispatch the driver side in ascending order according to the time sorting table. If all driver sides have not accepted the order, then multiply the screening radius by a preset expansion coefficient to obtain an expanded radius, and generate a dispatching area for the passenger location based on the expanded radius, and dispatch the order again.

Images