Cut-off Time Determination Method, Device, Computer Equipment and Storage Medium

Abstract

The present application relates to a cut-off time determination method, apparatus, computer device, and storage medium. The method includes: obtaining historical express delivery transportation information from the same origin to the same destination; according to the historical express delivery transportation information, obtaining route estimation probabilities corresponding to multiple preset arrival time intervals at each transfer network point; the route estimation probability represents the probability of transferring to the next transfer network point through any route when arriving at the corresponding transfer network point within the preset arrival time interval; according to the route estimation probabilities, obtaining the timeliness achievement rates of each transportation shift from the same origin to the same destination; according to the timeliness achievement rates of each transportation shift, determining the cut-off time from the departure times of each transportation shift at the same origin. Using this method can maximize the delay of the cut-off time while ensuring the timeliness achievement rate, thereby improving the timeliness of express delivery.

Description

Technical Field

[0001] The present application relates to the technical field of logistics, and particularly to a method, device, computer device and storage medium for determining cut-off time. Background Art

[0002] Currently, in the logistics transportation network, the receipt and mailing of express deliveries are generally as Figure 1 shown. The courier collects the express deliveries at the origin network point, sends them from the origin network point to the transfer station, and then the transfer station passes through multiple transfer network points to reach the destination network point, and finally delivers the parcels.

[0003] However, due to the influence of uncertain factors such as traffic conditions and climate conditions during the transportation process, even if the route from the origin of receipt to the destination of delivery is planned, it is still difficult to accurately estimate the time when the express delivery arrives at each transfer network point, resulting in a conservative time estimate for the routes of time-sensitive products at each transfer network point, thereby advancing the cut-off time and reducing the timeliness of express delivery.

[0004] Therefore, the cut-off time determined by the traditional method has the technical problem of being too early, resulting in low timeliness of express delivery. Summary of the Invention

[0005] Based on this, it is necessary to provide a method, device, computer device and storage medium for determining cut-off time to solve the above technical problem of too early cut-off time, resulting in low timeliness of express delivery.

[0006] A method for determining cut-off time, the method includes:

[0007] Obtain the historical express delivery transportation information from the same origin to the same destination; the historical express delivery transportation information includes the departure time, departure network point, route code of each express delivery, and the time when the vehicle is released from the seal at each transfer network point;

[0008] According to the departure time, departure network point, route code and the time when the vehicle is released from the seal of each express delivery, obtain the route prediction probabilities corresponding to multiple preset arrival time intervals at each transfer network point; the route prediction probability represents the probability of transferring from the corresponding transfer network point to the next transfer network point through any route when arriving at the corresponding transfer network point within the preset arrival time interval;

[0009] According to the route prediction probabilities, obtain the timeliness achievement rates of each transportation shift from the same origin to the same destination;

[0010] According to the timeliness achievement rates of each transportation shift, determine the cut-off time from the departure times of each transportation shift at the same origin.

[0011] In one embodiment, obtaining the route prediction probabilities corresponding to multiple preset arrival time intervals at each transfer network according to the departure time, the departure network point, the route code, and the vehicle unlocking time of each express delivery includes:

[0012] Determine the initial expected path function according to preset conditions;

[0013] Use the departure time, the departure network point, the route code, and the vehicle unlocking time to fit with the initial expected path function to obtain the target expected path function;

[0014] According to the target expected path function, determine the route prediction probabilities corresponding to different arrival time intervals at each transfer network.

[0015] In one embodiment, the using the departure time, the departure network point, the route code, and the vehicle unlocking time to fit with the expected path function to obtain the target path function includes:

[0016] According to the departure time, the departure network point, the route code, and the vehicle unlocking time, obtain the number of express deliveries that reach the transfer network at different arrival time intervals and are sent to the next transfer network through different routes; the different routes include the expected route and the alternate route, and the number of express deliveries includes the number of expected express deliveries passing through the expected route and the number of alternate express deliveries passing through the alternate route;

[0017] Obtain the total number of express deliveries of the expected number of express deliveries and the number of alternate express deliveries, and calculate the ratio of the expected number of express deliveries to the total number of express deliveries as the expected achievement rate of the transfer network;

[0018] Determine the expected achievement rates corresponding to different arrival time intervals, and fit each arrival time interval with the corresponding expected achievement rate to obtain the target expected path function.

[0019] In one embodiment, before obtaining the route prediction probabilities, it further includes:

[0020] For any arrival time interval, obtain the historical route probabilities of the express deliveries at each transfer network reaching the next transfer network through the expected route in the historical multiple days;

[0021] Obtain the probability mean of the historical route probabilities in the historical multiple days as the route prediction probability of the expected route;

[0022] According to the route prediction probability of the expected route, obtain the route prediction probability of the alternate route, and use the route prediction probability of the expected route and the route prediction probability of the alternate route as the route prediction probabilities corresponding to each transfer network in any arrival time interval.

[0023] In one embodiment, obtaining the timeliness achievement rate of each transportation schedule from the same origin to the same destination according to the estimated probability of the route includes:

[0024] Obtaining multiple estimated probabilities of flow directions corresponding to each transportation schedule according to the estimated probability of the route; the estimated probability of the flow direction is the estimated probability of completing the flow direction before the preset destination cut-off delivery time point;

[0025] Respectively obtaining the sum of the flow probabilities of the multiple estimated probabilities of flow directions corresponding to each transportation schedule as the timeliness achievement rate of each transportation schedule from the same origin to the same destination.

[0026] In one embodiment, obtaining multiple estimated probabilities of flow directions corresponding to each transportation schedule according to the estimated probability of the route includes:

[0027] Respectively calculating the product of the estimated probabilities of the routes of adjacent transfer nodes in each flow direction to obtain the estimated probabilities of each flow direction corresponding to each transportation schedule.

[0028] In one embodiment, determining the cut-off order time from the departure times of each transportation schedule at the same origin according to the timeliness achievement rate of each transportation schedule includes:

[0029] Screening out multiple target transportation schedules from each transportation schedule whose timeliness achievement rate meets the requirements of the achievement rate threshold;

[0030] Determining the latest departure time from the departure times corresponding to each target transportation schedule as the cut-off order time.

[0031] A cut-off order time determination device, the device includes:

[0032] A transportation information acquisition module, configured to acquire historical express transportation information from the same origin to the same destination; the historical express transportation information includes the departure time, departure network point, route code of each express, and the vehicle release time at each transfer node;

[0033] An estimated probability acquisition module, configured to obtain the estimated probabilities of routes corresponding to multiple preset arrival time intervals at each transfer node according to the departure time, departure network point, route code, and vehicle release time of each express; the estimated probability of the route represents the probability of transferring from the corresponding transfer node to the next transfer node through any route when arriving at the corresponding transfer node within the preset arrival time interval;

[0034] The timeliness achievement rate acquisition module is used to obtain the timeliness achievement rate of each transportation shift from the same origin to the same destination according to the estimated probability of the route;

[0035] The cut-off time determination module is used to determine the cut-off time from the departure times of each transportation shift at the same origin according to the timeliness achievement rate of each transportation shift.

[0036] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0037] Obtain the historical express delivery transportation information from the same origin to the same destination; the historical express delivery transportation information includes the departure time, departure network point, route code of each express delivery, and the vehicle release time at each transfer network point;

[0038] According to the departure time, departure network point, route code, and vehicle release time of each express delivery, obtain the route estimated probability corresponding to multiple preset arrival time intervals at each transfer network point; the route estimated probability represents the probability of transferring from the corresponding transfer network point to the next transfer network point through any route when arriving at the corresponding transfer network point within the preset arrival time interval;

[0039] According to the route estimated probability, obtain the timeliness achievement rate of each transportation shift from the same origin to the same destination;

[0040] According to the timeliness achievement rate of each transportation shift, determine the cut-off time from the departure times of each transportation shift at the same origin.

[0041] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0042] Obtain the historical express delivery transportation information from the same origin to the same destination; the historical express delivery transportation information includes the departure time, departure network point, route code of each express delivery, and the vehicle release time at each transfer network point;

[0043] According to the departure time, departure network point, route code, and vehicle release time of each express delivery, obtain the route estimated probability corresponding to multiple preset arrival time intervals at each transfer network point; the route estimated probability represents the probability of transferring from the corresponding transfer network point to the next transfer network point through any route when arriving at the corresponding transfer network point within the preset arrival time interval;

[0044] Based on the estimated probability of the route, obtain the timeliness achievement rate of each transportation flight from the same origin to the same destination;

[0045] Based on the timeliness achievement rate of each transportation flight, determine the cut-off time from the departure times of each transportation flight at the same origin.

[0046] The above cut-off time determination method, device, computer device and storage medium obtain the route estimated probability corresponding to multiple preset arrival time intervals at each transfer network point through the historical express delivery transportation information from the same origin to the same destination. Based on the route estimated probability, obtain the timeliness achievement rate of each transportation flight from the same origin to the same destination. Based on the timeliness achievement rate of each transportation flight, determine the cut-off time from the departure times of each transportation flight at the same origin. This method effectively combines the network point and the route by constructing two dimensions of the route and the network point, constructs a controllable Markov chain model, and can make a better prediction of the arrival time using a small amount of historical data, so as to accurately estimate the timeliness achievement rate from the receiving end to the delivery end of the entire network at different times, achieving the maximum delay of the cut-off time while ensuring the timeliness achievement rate, thereby improving the timeliness of express delivery. Brief Description of the Drawings

[0047] Figure 1 Is a schematic diagram of a logistics transportation network in the prior art;

[0048] Figure 2 Is a schematic flowchart of the cut-off time determination method in an embodiment;

[0049] Figure 3 Is a schematic diagram of the graph of the initial expected path function in an embodiment;

[0050] Figure 4 Is a schematic diagram of fitting the initial expected path function in an embodiment;

[0051] Figure 5 Is a schematic diagram of the flow direction estimated probability calculation step in an embodiment;

[0052] Figure 6 Is a schematic flowchart of the cut-off time determination method in another embodiment;

[0053] Figure 7 Is a structural block diagram of the cut-off time determination device in an embodiment;

[0054] Figure 8 Is an internal structure diagram of a computer device in an embodiment. Detailed Description of the Invention

[0055] To make the objectives, technical solutions and advantages of this application more clear and understandable, the following further elaborates on this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for explaining this application and are not used to limit this application.

[0056] In one embodiment, as Figure 2 shown, a cut-off time determination method is provided. In this embodiment, taking the application of this method to a server as an example, it can be understood that this method can also be applied to a terminal, or to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0057] Step S202, obtain historical express delivery transportation information from the same origin to the same destination; the historical express delivery transportation information includes the departure time, departure network point, route code of each express delivery, and the vehicle unsealing time at each transfer network point.

[0058] Among them, the departure time can represent the time when the transportation vehicle departs after completing vehicle sealing at the origin or each transfer network point.

[0059] Among them, the route code can represent the code of the route that the transportation vehicle loaded with express deliveries passes from one transfer network point to the next transfer network point.

[0060] Among them, the vehicle unsealing time can represent the time when the transportation vehicle arrives at the transfer network point of the logistics, and the vehicle is unsealed by scanning the vehicle sealing barcode at the transfer network point using a barcode gun.

[0061] Step S204, based on the departure time, departure network point, route code, and vehicle unsealing time of each express delivery, obtain the route estimation probabilities corresponding to multiple preset arrival time intervals at each transfer network point; the route estimation probability represents the probability of transferring from the corresponding transfer network point to the next transfer network point via any route within the preset arrival time interval.

[0062] Specifically, the routes for transferring from a transfer network point to the next transfer network point may include an expected route and an alternative route. Among them, the expected route can represent the route that starts from the current transfer network point and can catch the expected departure schedule of the next transfer network point. The expected route can be generated by inputting the origin and destination into a preset path planning model. In practical applications, to improve the loading rate of the vehicle, there will be a unique expected route between the same origin and the same destination. Among them, the alternative route can be selected from the actual paths corresponding to the waybills of historical express deliveries, and the alternative route can also be set to one.

[0063] Among them, the route estimation probability may include an expected route estimation probability and an alternative route estimation probability.

[0064] In the specific implementation, first, the departure time from the current network point to the next network point and the route to pass through are set, which are only related to the state of the current network point and have nothing to do with the previous network point and the network points before that. The relationship is expressed by the Markov chain model as follows:

[0065] P(X t+1 |X t ) = P(x zone , x dest , x time )

[0066] Among them, zone represents the current network point (including the departure network point, transfer network point and destination), dest represents the destination, and time represents the time.

[0067] Among them, X t+1 represents the next state after transfer, that is, the expected departure time from the current network point to the next network point and the (expected) selected route.

[0068] Among them, X t represents the current state, that is, the current network point, the time to reach the current network point (i.e., the vehicle release time of the current network point) and the next destination.

[0069] Based on the above relationship, for each arrival time interval, calculate the probability that the historical express delivery passes through different routes from the current transfer network point to the next transfer network point respectively, and obtain the route prediction probability corresponding to each transfer network point in different preset arrival time intervals. Among them, the arrival time interval can be determined according to the departure time of the transportation shifts of each transfer network point. For example, multiple arrival time intervals can be set as: arriving within 30 minutes before departure, arriving within 1 hour before departure, etc.

[0070] Furthermore, step S204 specifically includes: determining the initial expected path function according to the preset conditions; using the departure time, the departure network point, the route code and the vehicle release time to fit with the initial expected path function to obtain the target expected path function; and determining the route prediction probability corresponding to each transfer network point in different arrival time intervals according to the target expected path function.

[0071] Among them, the preset conditions can be: when the time (i.e., the vehicle release time) T for the express delivery to reach a certain transfer network point ≥ the departure time of the expected route, that is, the arrival time is later than the departure time of the expected route of this transfer network point, it is determined that the achievement rate of the expected route is 0%. For example, if the departure time of the expected route is 15:00, but the actual arrival time is 15:00 or later than 15:00, then the expected route shift cannot be caught up, and the achievement rate of the expected route is 0%.

[0072] When the arrival time T of an express delivery at a certain transfer point << the departure time of the expected route, that is, the arrival time is much earlier than the departure time of the expected route at this transfer point, the achievement rate of the expected route is determined to be x%, where x% is the achievement rate after excluding extreme situations such as express delivery loss and express delivery return. For example, if the departure time of the expected route is 15:00, but the actual arrival time is much earlier than 15:00, for example, it arrives at this transfer point at 10:00, it is determined that the express delivery can definitely catch the expected route shift under the condition that there is no express delivery loss or return.

[0073] Based on the above preset conditions, an initial expected path function can be determined. For example, the sigmoid function, denoted as P(x). The function graph of the initial expected path function is as Figure 3 shown. The horizontal axis represents the express delivery unsealing vehicle (i.e., the arrival time x), and the vertical axis represents the achievement rate of the expected route. It can be seen from the figure that when the express delivery unsealing vehicle time is later than the departure time of the expected route, the achievement rate of the expected route is 0. When the arrival time of the express delivery is much earlier than the departure time of the expected route, the achievement rate of the expected route is x%.

[0074] After determining the initial expected path function, the expected achievement rate of passing through the expected route corresponding to different arrival time intervals can be obtained according to the express delivery volume passing through the expected route and the alternative route in the historical express delivery transportation information. According to the arrival time of the express delivery and the expected achievement rate, fit with the initial expected path function to obtain the target path function, and further obtain the route prediction probability corresponding to each transfer point in different arrival time intervals.

[0075] Step S206, according to the route prediction probability, obtain the timeliness achievement rate of each transportation shift from the same origin to the same destination.

[0076] Among them, the timeliness achievement rate can be expressed as the ratio of the total express delivery volume arriving at the destination before the preset destination cut-off delivery time to the express delivery volume when departing from the origin.

[0077] In specific implementation, since the route estimation probability represents the probability of reaching the next transfer point through any route at each transfer point, which is equivalent to the transfer probability between adjacent transfer points, based on the Markov chain principle, the probability of reaching the destination through different transfer points from the origin can be calculated according to the transfer probabilities between adjacent transfer points. If the route formed by each transfer point passed through each time from the origin to the destination is regarded as a flow direction, then the product of the route estimation probabilities of adjacent transfer points in each flow direction can be calculated, and thus multiple flow direction estimation probabilities of transportation shifts at different departure times from the origin to the destination through different flow directions can be obtained. Among them, the calculated flow direction estimation probabilities of each transportation shift only include the flow directions that reach the destination before the preset destination cut-off delivery time. Since the express deliveries loaded by the transportation shifts departing from the origin may reach the destination through different flow directions, therefore, the sum of the probabilities of the flow direction estimation probabilities corresponding to each transportation shift can be calculated to obtain the ratio of the total number of express deliveries that reach the destination before the preset destination cut-off delivery time in the express deliveries loaded by each transportation shift to the total number of express deliveries loaded when departing from the origin, which is used as the timeliness achievement rate of each transportation shift.

[0078] It can be understood that since the express deliveries need to be sorted and loaded at multiple transfer points during the transportation process, the transportation shifts in this embodiment are not the same transportation vehicle, but include the vehicles of the originating shifts departing from the origin and the vehicles of the transfer shifts at each transfer point. All the vehicles in each flow direction form a transportation shift, and the departure time of each transportation shift is based on the departure time at the origin.

[0079] Step S208: Determine the cut-off time from the departure times of each transportation shift at the same origin according to the timeliness achievement rates of each transportation shift.

[0080] Among them, the cut-off time can represent the time when the network stops the outbound distribution of orders after this time.

[0081] In specific implementation, after obtaining the timeliness achievement rates of each transportation shift, the timeliness achievement rates of each transportation shift can be compared with a preset achievement rate threshold, and multiple target transportation shifts with timeliness achievement rates greater than the achievement rate threshold can be selected from each transportation shift. The latest departure time among the departure times of each target transportation shift is used as the cut-off time of the network.

[0082] It should be noted that only the expected route and the alternative route are used to illustrate the route in this embodiment. In practical applications, it may also include the third route, the fourth route, etc. to estimate the timeliness achievement rate of the express deliveries. The present application does not limit the specific number of routes.

[0083] In the above cut-off time determination method, based on the historical express delivery transportation information from the same origin to the same destination, the route estimation probabilities corresponding to multiple preset arrival time intervals at each transfer network point are obtained. According to the route estimation probabilities, the timeliness achievement rates of each transportation shift from the same origin to the same destination are obtained. Based on the timeliness achievement rates of each transportation shift, the cut-off time is determined from the departure times of each transportation shift at the same origin. This method effectively combines the network points and routes by constructing two dimensions of routes and network points, constructs a controllable Markov chain model, and can use a small amount of historical data to make a good prediction of the arrival time, thereby accurately estimating the timeliness achievement rates from the receiving end to the delivery end of the entire network at different times, achieving the maximum delay of the cut-off time while ensuring the timeliness achievement rate. In addition, by setting different arrival time intervals corresponding to different route estimation probabilities, the dynamic estimation of the route estimation probabilities is realized, effectively ensuring the consistency between the actual transportation situation and the plan. Moreover, for the completion situation of the overall network flow from network point to network point, there are also visual data results, so that logistics enterprises can facilitate the opening of different timeliness products according to different transport capacities and different routes.

[0084] In one embodiment, the steps for determining the target path function include: according to the departure time, departure network point, route code, and vehicle unsealing time, obtaining the number of express deliveries that reach the transfer network point at different arrival time intervals and are sent to the next transfer network point through different routes; the different routes include the expected route and the alternative route, and the number of express deliveries includes the number of expected express deliveries passing through the expected route and the number of alternative express deliveries passing through the alternative route; obtaining the total number of express deliveries of the expected express deliveries and the alternative express deliveries, calculating the ratio of the number of expected express deliveries to the total number of express deliveries as the expected achievement rate of the transfer network point; determining the expected achievement rates corresponding to different arrival time intervals, and fitting each arrival time interval with the corresponding expected achievement rate to obtain the target expected path function.

[0085] In specific implementation, as Figure 4 shown, it is a schematic diagram for fitting the initial expected path function in Figure 3 . If the number of express deliveries that reach each transfer network point at any arrival time interval and reach the next transfer network point through the expected route is denoted as M, and the number of express deliveries that reach the next transfer network point through the alternative route is denoted as N, then the expected achievement rate can be expressed as: M / (M + N), and thus the expected achievement rates corresponding to different arrival time intervals can be obtained. Taking different arrival time intervals as the x variable and the expected achievement rate as the y variable, fitting according to each arrival time interval and the corresponding expected achievement rate with the initial expected path function. For example, Figure 4Each point on the curve represents the expected achievement rate corresponding to different arrival times, and finally the target expected path function is obtained by fitting. After obtaining the target expected path function, if you want to obtain the route prediction probability for any arrival time, you can input the arrival time into the target expected path function to obtain the route prediction probabilities of reaching the next transfer network point through the expected route and the alternative route respectively at this arrival time, and thus determine the probability of catching the shift on the expected route.

[0086] In this embodiment, by obtaining the number of expected express items reaching the next network point through the expected route and the number of alternative express items reaching the next network point through the alternative route, the total number of express items reaching the next network point is obtained, and further the ratio of the number of expected express items to the total number of express items is calculated as the expected achievement rate of the network point. By fitting the arrival time and the expected achievement rate, the target expected path function is obtained, which realizes the correction of the initial expected path function, improves the fitting degree of the expected path function to the actual express transportation situation, and thus improves the accuracy of determining the route prediction probability according to the expected path function.

[0087] In one embodiment, the steps for obtaining the route prediction probability include: for any arrival time interval, obtaining the historical route probabilities of the express items at each transfer network point reaching the next transfer network point through the expected route in the past multiple days; obtaining the probability mean of the historical route probabilities in the past multiple days as the route prediction probability of the expected route; obtaining the route prediction probability of the alternative route according to the route prediction probability of the expected route, and taking the route prediction probability of the expected route and the route prediction probability of the alternative route as the route prediction probabilities corresponding to each transfer network point in any arrival time interval.

[0088] In the specific implementation, after obtaining the route prediction probabilities for different arrival times, denoted as P(x zone , x dest , x time ), the arrival time can be converted into another dimension - the route of the previous vehicle, that is, converting P(x zone , x dest , x time ) to P(x zone , x dest , x 路线编码 ). More specifically, the historical expected route probabilities of reaching the next transfer network point through the expected route within the recent set time (such as the recent 30 days) can be obtained for each arrival time interval at each transfer network point, and then the mean of the historical expected route probabilities within the recent set time is calculated as the route prediction probability of the expected route. Among them, the historical expected route probability can be obtained by inputting the historical arrival time into the target path function P(x) obtained by fitting, and the relational expression for calculating the route prediction probability can be expressed as:

[0089] E[P(x|route)] = (P(arrival time of route|route, a certain day)) / number of days

[0090] For example, if within the last 30 days, after arriving at the transfer network within 30 minutes before the departure time of the expected route, the route probabilities of catching the flights of the expected route are 60%, 55%, 65%,..., 45% in sequence. Then the expected route probability for this arrival time interval within the last 30 days can be expressed as: (60% + 55% + 65% +... + 45%) / 30.

[0091] Since it is set in this application that the express delivery only reaches the next transfer network through the expected route and the alternative route, therefore, the sum of the route estimation probabilities of the expected route and the alternative route is 1. Thus, after obtaining the route estimation probability of the expected route, calculate the difference between 1 and the route estimation probability of the expected route, that is, obtain the route estimation probability of the alternative route, and thereby obtain the route estimation probabilities of the expected route and the alternative route corresponding to any arrival time interval of each transfer network.

[0092] Furthermore, for the real-time nature of the route estimation probability, the moving average method can also be used to update the historical express delivery transportation information of the recent multiple days at regular intervals.

[0093] In this embodiment, by obtaining the historical route probabilities of the expected route in different arrival time intervals within the historical multiple days, and taking the probability mean within the historical multiple days as the route estimation probability of the expected route. This method takes the mean of the route probabilities of other historical transportation flights as the route estimation probability for the future. Through the application of the Markov chain in the spatial dimension, it is convenient to perform probability calculations based on the historical data of other transportation flights when the historical data samples are insufficient, so as to achieve a reasonable estimation of the route estimation probability, and thus achieve a reasonable estimation of the timeliness achievement rate.

[0094] In one embodiment, the above step S206 specifically includes: obtaining multiple flow estimation probabilities corresponding to each transportation flight according to the route estimation probability; the flow estimation probability is the estimated probability of completing the flow before the preset cut-off delivery time point at the destination; respectively obtaining the sum of the flow probabilities of the multiple flow estimation probabilities corresponding to each transportation flight, and taking it as the timeliness achievement rate of each transportation flight from the same origin to the same destination.

[0095] Furthermore, obtaining multiple flow estimation probabilities corresponding to each transportation flight according to the route estimation probability further includes: respectively calculating the product of the route estimation probabilities of adjacent network points in each flow to obtain each flow estimation probability corresponding to each transportation flight.

[0096] In specific implementation, such as Figure 5As shown in the figure, it is a schematic diagram of the flow prediction probability calculation steps. In the figure, line 1 can represent the expected route, and line 2 can represent the alternative route. P(x1) represents the route prediction probability of reaching network point 1 via the expected route (i.e., line 1) after receiving the package, and 1 - P(x1) represents the route prediction probability of reaching network point 1 via the alternative route (i.e., line 2) after receiving the package. [P(x1|line 1) represents the probability of reaching transfer network point 1 via the expected route again under the condition that the package reaches network point 1 via the expected route after receiving the package. [P(x2|line 1) represents the probability of reaching transfer network point 1 via the alternative route under the condition that the package reaches network point 1 via the expected route after receiving the package. Since there is a probability that the express delivery passes through different routes to reach the next transfer network point after reaching any transfer network point, taking the first flow of delivery and pickup shift 1 where all reach the next transfer network point via the expected route as an example, the calculation relationship of the flow prediction probability of this flow can be expressed as:

[0097] P(delivery and pickup shift 1) = E[P(x1)] × E[P(x1|line 1)] × …

[0098] Among them, E[P(x1)] represents the mean value of the route prediction probability of reaching network point 1 via the expected route (i.e., line 1) after receiving the package within multiple historical days, and E[1 - P(x1)] represents the mean value of the route prediction probability of reaching network point 1 via the alternative route (i.e., line 2) after receiving the package within multiple historical days.

[0099] Similarly, the flow prediction probabilities corresponding to each transportation shift can be obtained. Among them, the flows corresponding to the flow prediction probabilities are all the flows that reach the destination before the cut-off delivery time at the destination, that is, the flows determined to be able to complete the delivery before the cut-off delivery time. After obtaining the flow prediction probabilities corresponding to each transportation shift (i.e., the probabilities of the express deliveries loaded at the origin of each transportation shift reaching the destination through different flows), calculate the sum of the probabilities of the flow prediction probabilities corresponding to each transportation shift to obtain the ratio of the number of express deliveries reaching the destination to the total number of express deliveries loaded at the origin as the timeliness achievement rate of each transportation shift. This calculation process can be expressed by the relationship:

[0100] Timeliness achievement rate (delivery and pickup shift x) = E[P(delivery and pickup shift x, flow 1)] + E[P(delivery and pickup shift x, flow 2)] + … E[P(delivery and pickup shift x, flow n)]

[0101] Among them, n represents the total number of flows corresponding to delivery and pickup shift x.

[0102] In this embodiment, by first calculating the flow prediction probabilities corresponding to each transportation shift, and then calculating the sum of the probabilities of the flow prediction probabilities as the timeliness achievement rate of each transportation shift, it is convenient to further determine the cut-off order time from the departure times of each transportation shift according to this timeliness achievement rate.

[0103] In one embodiment, the above-mentioned step S208 specifically includes: screening out a plurality of target transport schedules whose timeliness achievement rates meet the requirements of the achievement rate threshold from each of the transport schedules; determining the latest departure time from the departure times corresponding to each of the target transport schedules as the cut-off time.

[0104] Specifically, for example, if the set achievement rate threshold is 95%, and several transport schedules are set as:

[0105] Transport schedule 1 - departure time 8:00, timeliness achievement rate 97%;

[0106] Transport schedule 2 - departure time 8:30, timeliness achievement rate 94.8%;

[0107] Transport schedule 3 - departure time 9:00, timeliness achievement rate 96%.

[0108] Then, transport schedule 1 and transport schedule 3 with a timeliness achievement rate greater than 95% can be screened out from each transport schedule as the target transport schedules, and then the latest departure time is determined from the departure times 8:00 and 9:00 corresponding to each target transport schedule, that is, the departure time 9:00 is used as the cut-off time for the departure network point.

[0109] In this embodiment, multiple target transport schedules are determined through the timeliness achievement rates of each transport schedule and the achievement rate threshold, and then the latest departure time among the departure times of each target transport schedule is used as the cut-off time. This method can determine the latest cut-off time while ensuring the timeliness achievement rate, can deliver the express parcels as early as possible, thus can ensure the timeliness of express parcel delivery with the highest probability, and can also save transportation costs.

[0110] In another embodiment, as Figure 6 shown, a method for determining the cut-off time is provided, including:

[0111] Step S602, obtaining historical express parcel transportation information from the same origin to the same destination; the historical express parcel transportation information includes the departure time, departure network point, route code of each express parcel, and the vehicle release time at each transfer network point;

[0112] Step S604, determining an initial expected path function according to preset conditions;

[0113] Step S606, using the departure time, departure network point, route code and vehicle release time to fit with the initial expected path function to obtain a target expected path function;

[0114] Step S608, determining the route estimation probability corresponding to different arrival time intervals of each transfer network point according to the target expected path function;

[0115] Step S610: Obtain multiple flow prediction probabilities corresponding to each transportation shift according to the route prediction probability; the flow prediction probability is the predicted probability of completing the flow before the preset destination cut-off delivery time point.

[0116] Step S612: Obtain the sum of the flow probabilities of the multiple flow prediction probabilities corresponding to each transportation shift respectively, as the timeliness achievement rate of each transportation shift from the same origin to the same destination.

[0117] Step S614: Screen out multiple target transportation shifts from each transportation shift whose timeliness achievement rate meets the requirement of the achievement rate threshold.

[0118] Step S616: Determine the latest departure time from the departure times corresponding to each target transportation shift as the cut-off order time.

[0119] In this embodiment, a general model is established through the Markov chain method. This model comprehensively considers the constraints of actual business. To ensure that the express delivery can reach the user's hands quickly, it can be stipulated that the daily departure shifts, departure flows, and departure times are fixed, and the timeliness of the express delivery is ensured as much as possible, with the highest probability to ensure the timeliness of the delivered express delivery, and the transportation cost can also be saved.

[0120] It should be understood that although Figure 1 and Figure 6 the steps in the flowcharts of Figure 1 and Figure 6 are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover,

[0121] In one embodiment, as Figure 7 shown, a cut-off order time determination device is provided, including: a transportation information acquisition module 702, a prediction probability acquisition module 704, a timeliness achievement rate acquisition module 706, and a cut-off order time determination module 708, where:

[0122] The transportation information acquisition module 702 is used to acquire the historical express delivery transportation information from the same origin to the same destination; the historical express delivery transportation information includes the departure time, departure network point, route code of each express delivery, and the vehicle release time at each transfer network point.

[0123] The estimated probability obtaining module 704 is configured to obtain the route estimated probabilities corresponding to multiple preset arrival time intervals at each transfer point according to the departure time, departure network point, route code, and vehicle unsealing time of each express delivery; the route estimated probability represents the probability of transferring from the corresponding transfer point to the next transfer point through any route when arriving at the corresponding transfer point within the preset arrival time interval.

[0124] The timeliness achievement rate obtaining module 706 is configured to obtain the timeliness achievement rates of each transportation shift from the same origin to the same destination according to the route estimated probabilities.

[0125] The cut-off time determining module 708 is configured to determine the cut-off time from the departure times of each transportation shift at the same origin according to the timeliness achievement rates of each transportation shift.

[0126] In one embodiment, the above-mentioned estimated probability obtaining module 704 is specifically configured to determine an initial expected path function according to preset conditions; use the departure time, departure network point, route code, and vehicle unsealing time to fit with the initial expected path function to obtain a target expected path function; and determine the route estimated probabilities corresponding to different arrival time intervals at each transfer point according to the target expected path function.

[0127] In one embodiment, the above-mentioned estimated probability obtaining module 704 is further configured to obtain the number of express deliveries that reach the next transfer point through different routes when arriving at the transfer point within different arrival time intervals according to the departure time, departure network point, route code, and vehicle unsealing time; different routes include the expected route and the alternate route, and the number of express deliveries includes the number of expected express deliveries passing through the expected route and the number of alternate express deliveries passing through the alternate route; obtain the total number of express deliveries of the expected express deliveries and the alternate express deliveries, calculate the ratio of the number of expected express deliveries to the total number of express deliveries as the expected achievement rate of the transfer point; determine the expected achievement rates corresponding to different arrival time intervals, and fit each arrival time interval with the corresponding expected achievement rate to obtain a target expected path function.

[0128] In one embodiment, the above-mentioned estimated probability obtaining module 704 is further configured to, for any arrival time interval, obtain the historical route probabilities of the express deliveries at each transfer point reaching the next transfer point through the expected route within multiple historical days; obtain the probability mean of the historical route probabilities within multiple historical days as the route estimated probability of the expected route; obtain the route estimated probability of the alternate route according to the route estimated probability of the expected route, and use the route estimated probability of the expected route and the route estimated probability of the alternate route as the route estimated probabilities corresponding to each transfer point in any arrival time interval.

[0129] In one embodiment, the above-mentioned aging achievement rate acquisition module 706 is specifically configured to obtain multiple flow prediction probabilities corresponding to each transportation shift according to the route prediction probability; the flow prediction probability is the predicted probability of completing the flow before the preset destination cut-off delivery time point; the flow probability sum of the multiple flow prediction probabilities corresponding to each transportation shift is obtained respectively as the aging achievement rate of each transportation shift from the same origin to the same destination.

[0130] In one embodiment, the above-mentioned aging achievement rate acquisition module 706 is further configured to calculate the product of the route prediction probabilities of adjacent transfer nodes in each flow respectively to obtain the flow prediction probabilities corresponding to each transportation shift.

[0131] In one embodiment, the above-mentioned cut-off time determination module 708 is specifically configured to screen out multiple target transportation shifts from each transportation shift whose aging achievement rate meets the requirement of the achievement rate threshold; determine the latest departure time from the departure times corresponding to each target transportation shift as the cut-off time.

[0132] It should be noted that the cut-off time determination device of the present application corresponds one-to-one with the cut-off time determination method of the present application. The technical features and beneficial effects described in the embodiments of the above-mentioned cut-off time determination method are all applicable to the embodiments of the cut-off time determination device. For specific content, reference can be made to the description in the method embodiments of the present application, which will not be repeated here. This is hereby declared.

[0133] In addition, each module in the above-mentioned cut-off time determination device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in the processor in the computer device in the form of hardware or independent of it, or stored in the memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above-mentioned modules.

[0134] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 8 shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data generated during the cut-off time determination process. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a cut-off time determination method is implemented.

[0135] Those skilled in the art can understand,Figure 8 The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0136] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0137] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0138] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it may include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application may include at least one of non-volatile and volatile memories. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0139] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0140] The above-described embodiments only represent several implementation manners of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of the patent of this application should be subject to the appended claims.

Claims

1. A cut-off time determination method, characterized in that, The method includes: Obtaining historical express delivery transportation information from the same origin to the same destination; the historical express delivery transportation information includes the departure time, departure network point, route code of each express delivery, and the vehicle unsealing time at each transfer network point; According to the departure time, departure network point, route code, and vehicle unsealing time of each express delivery, obtaining route estimation probabilities corresponding to multiple preset arrival time intervals at each transfer network point; the route estimation probability represents the probability of starting from the corresponding transfer network point and reaching the next transfer network point through any route when arriving at the corresponding transfer network point within the preset arrival time interval; According to the route estimation probabilities, obtaining multiple flow direction estimation probabilities corresponding to each transportation shift from the same origin to the same destination; each flow direction estimation probability is obtained by calculating the product of the route estimation probabilities of adjacent transfer network points in each flow direction; the flow direction estimation probability is the estimated probability of completing the corresponding flow direction before the preset destination cut-off delivery time point; Respectively obtaining the sum of the flow direction probabilities of multiple flow direction estimation probabilities corresponding to each transportation shift, and obtaining the timeliness achievement rate of each transportation shift; According to the timeliness achievement rate of each transportation shift, determining the cut-off order time from the departure times of each transportation shift at the same origin.

2. The method according to claim 1, characterized in that The obtaining of the route estimation probabilities corresponding to multiple preset arrival time intervals at each transfer network point according to the departure time, departure network point, route code, and vehicle unsealing time of each express delivery includes: Determining an initial expected path function according to preset conditions; Using the departure time, departure network point, route code, and vehicle unsealing time to fit with the initial expected path function to obtain a target expected path function; According to the target expected path function, determining the route estimation probabilities corresponding to different arrival time intervals at each transfer network point.

3. The method according to claim 2, wherein The using of the departure time, departure network point, route code, and vehicle unsealing time to fit with the initial expected path function to obtain a target expected path function includes: According to the departure time, departure network point, route code, and vehicle unsealing time, obtaining the number of express deliveries that reach the transfer network point at different arrival time intervals and are sent to the next transfer network point through different routes; the different routes include the expected route and the alternative route, and the number of express deliveries includes the number of expected express deliveries passing through the expected route and the number of alternative express deliveries passing through the alternative route; Obtaining the total number of express deliveries of the expected express deliveries and the alternative express deliveries, calculating the ratio of the number of expected express deliveries to the total number of express deliveries, and using it as the expected achievement rate of the transfer network point; Determining the expected achievement rates corresponding to different arrival time intervals, and fitting each arrival time interval with the corresponding expected achievement rate to obtain a target expected path function.

4. The method according to claim 2, wherein The determining of the route estimation probabilities corresponding to different arrival time intervals at each transfer network point according to the target expected path function includes: For any of the arrival time intervals, obtain the historical expected route probabilities of the express parcels at each transfer network reaching the next transfer network via the expected route within multiple historical days; wherein, the historical expected route probabilities are calculated by inputting the historical arrival times into the target expected path function; Obtain the probability mean of the historical expected route probabilities within the multiple historical days as the route estimation probability of the expected route; According to the route estimation probability of the expected route, obtain the route estimation probability of the alternative route, and use the route estimation probability of the expected route and the route estimation probability of the alternative route as the route estimation probabilities corresponding to each transfer network in any of the arrival time intervals.

5. The method according to any one of claims 2-4, characterized in that, The preset conditions are as follows: when the arrival time of an express parcel at a certain transfer network is later than the departure time of the expected route of the transfer network, it is determined that the achievement rate of the expected route is 0%; when the arrival time of an express parcel at a certain transfer network is earlier than the departure time of the expected route of the transfer network, it is determined that the achievement rate of the expected route is x%; where x% is the achievement rate after excluding lost and returned express parcels.

6. The method according to claim 5, wherein The initial expected path function is a function with the arrival time of the express parcel as the independent variable and the achievement rate of the expected route as the dependent variable.

7. The method according to claim 1, characterized in that The determining of the cut-off time from the departure times of each of the transport shifts at the same origin according to the achievement rates of the timeliness of each of the transport shifts includes: Screen out multiple target transport shifts from each of the transport shifts whose timeliness achievement rates meet the requirements of the achievement rate threshold; Determine the latest departure time from the departure times corresponding to each of the target transport shifts as the cut-off time.

8. A cut-off time determination device, characterized in that, The device includes: A transport information acquisition module, configured to acquire historical express parcel transport information from the same origin to the same destination; the historical express parcel transport information includes the departure time, departure network, route code of each express parcel, and the vehicle release time at each transfer network; An estimation probability acquisition module, configured to obtain the route estimation probabilities corresponding to multiple preset arrival time intervals at each transfer network according to the departure time, departure network, route code, and vehicle release time of each express parcel; the route estimation probability represents the probability of starting from the corresponding transfer network via any route to the next transfer network when arriving at the corresponding transfer network within the preset arrival time interval; A timeliness achievement rate acquisition module, configured to obtain multiple flow direction estimation probabilities corresponding to each of the transport shifts from the same origin to the same destination according to the route estimation probabilities; respectively obtain the sum of the flow direction probabilities of the multiple flow direction estimation probabilities corresponding to each transport shift to obtain the timeliness achievement rate of each transport shift; the flow direction estimation probability is the estimated probability of completing the corresponding flow direction before the preset destination cut-off delivery time point; each of the flow direction estimation probabilities is obtained by calculating the product of the route estimation probabilities of adjacent transfer networks in each flow direction; A cut-off time determination module, configured to determine the cut-off time from the departure times of each of the transport shifts at the same origin according to the timeliness achievement rate of each of the transport shifts.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images