Method, device, computer equipment and storage medium for identifying priority delivery of waybills

Abstract

The present application relates to a method, device, computer equipment and storage medium for identifying a waybill for priority delivery, wherein the method includes: obtaining waybill information of a vehicle dispatched from a terminal transfer station in a distribution network, and judging whether the waybill can arrive at a terminal outlet in the distribution network on time based on the waybill information and a preset time efficiency prediction model; if not, adding a non-priority delivery mark to the waybill, and not giving priority delivery to the waybill; if yes, obtaining the predicted time for the waybill to arrive at the terminal outlet, adding a priority delivery mark to the waybill, and adjusting the waybill commitment time to the sum of the predicted time and a preset fixed overtime, so as to give priority delivery to the waybill. During the entire process, based on the preset time efficiency prediction model, it is accurately judged whether the waybill can be delivered to the terminal outlet on time, priority delivery is only performed for waybill pieces that can be delivered on time, the waybill commitment time is adjusted, and it is accurately identified whether priority delivery is performed, which brings convenience to users.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and in particular to a method, device, computer equipment and storage medium for identifying waybill priority delivery. Background Art

[0002] As people's living standards improve, online shopping has become a fashion, and more and more goods are purchased through online shopping. With the rise of online shopping, the pressure on express delivery is also increasing, especially during several major shopping festivals, when a large number of express deliveries need to be delivered. On the user side, most users hope that the goods they purchased can arrive as soon as possible.

[0003] In the above situation, at the delivery end of the waybill, some users usually have certain urging needs, requiring the waybill to be delivered to them as soon as possible after arriving at the terminal outlet. At present, there are two ways for users to initiate urging: the first is to click on the urging on the APP or mini program end and feedback the urging request. If the express is still within the promised time limit, the urging is invalid. If the express has exceeded the promised time limit, the urging will take effect; the second is to call customer service for manual urging. Under this method, the number of waybills to be dispatched increases and the delivery scenario is complicated.

[0004] Based on the above situation, logistics companies have adopted a priority delivery mechanism, and have given priority to some waybills that meet the requirements and delivered them to users as soon as possible. However, most of the current plans for whether to give priority delivery are based on manual experience, which is unreasonable and unfair, and cannot maximize the technical advantages of the priority delivery mechanism and bring convenience to users. Therefore, how to accurately identify waybills for priority delivery has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] Based on this, it is necessary to provide an accurate waybill priority delivery identification method, device, computer equipment and storage medium to address the above technical issues.

[0006] A method for identifying a waybill for priority delivery, the method comprising:

[0007] Obtain the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network;

[0008] Based on the waybill information and the preset time prediction model, determine whether the waybill can arrive at the terminal point in the distribution network on time;

[0009] If not possible, add a no priority delivery mark to the waybill;

[0010] If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, add a priority delivery mark to the waybill, and adjust the waybill promised time to the sum of the predicted time and the preset fixed overtime. The preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user.

[0011] In one embodiment, obtaining the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network includes:

[0012] Get real-time waybill information;

[0013] Monitor the dispatching operation of the transfer yard in the distribution network based on the real-time waybill information, and extract the initial waybill information of the dispatching vehicle;

[0014] The initial waybill information of the vehicle is filtered according to the preset restriction conditions to obtain the waybill information of the vehicle.

[0015] In one embodiment, the initial waybill information of the vehicle is screened according to the preset restriction condition, and the waybill information of the vehicle is obtained, including:

[0016] Using the Spark Streaming stream processing framework, we can filter the waybill data in real time according to the initial waybill information of the vehicle, cache the waybill that meets the preset restrictions, and obtain the waybill information of the vehicle.

[0017] In one embodiment, before judging whether the waybill can arrive at the terminal point in the distribution network on time based on the waybill information and the preset time prediction model, the method further includes:

[0018] Get historical waybill data;

[0019] According to the historical waybill data, the first type of historical waybill data that arrived at the terminal outlet on time and the second type of historical waybill data that failed to arrive at the terminal outlet on time are obtained. On time means that the difference between the actual arrival time at the terminal outlet and the expected arrival time at the terminal outlet is not greater than a preset threshold;

[0020] Add an on-time arrival mark to the first category of historical waybill data, and add a not-on-time arrival mark to the second category of historical waybill data;

[0021] The identification of the terminal outlets that arrive on time and the identification of the terminal outlets that do not arrive on time are used as outputs, and the historical waybill data are used as input to train the initial binary classification model and obtain the timeliness prediction model.

[0022] In one embodiment, obtaining the predicted time for the waybill to arrive at the terminal outlet includes:

[0023] Based on the waybill information and the preset time prediction model, the predicted time for the waybill to arrive at the terminal outlet is obtained.

[0024] In one embodiment, before obtaining the predicted time for the waybill to arrive at the terminal outlet based on the waybill information and the time prediction model, the method further includes:

[0025] Get historical waybill data;

[0026] Extract the real time when the waybill arrives at the terminal outlets and the feature data in the historical waybill data. The feature data includes the basic features of the waybill, the numerical features of the waybill, and the time series features of the waybill.

[0027] With real time as output and extracted feature data as input, the logistic regression model layer and the integrated model layer are trained separately, and the model parameters are adjusted through the grid search method to obtain the preset time prediction model.

[0028] In one embodiment, the predicted time for the waybill to arrive at the terminal outlet is obtained, a priority delivery mark is added to the waybill, and the waybill commitment time is adjusted to the sum of the predicted time and a preset fixed overtime, where the preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user, including:

[0029] If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, and determine whether the sum of the predicted time and the preset fixed overtime is greater than the original promised time of the waybill;

[0030] If it is not greater, a priority delivery mark will be added to the waybill and the waybill promised time will be adjusted to the sum of the predicted time and the preset fixed overtime.

[0031] A device for identifying a waybill for priority delivery, the device comprising:

[0032] Waybill acquisition module, used to obtain waybill information of vehicles dispatched from the terminal transfer station in the distribution network;

[0033] The judgment module is used to judge whether the waybill can arrive at the terminal point in the distribution network on time based on the waybill information and the preset time prediction model;

[0034] The first processing module is used to add a non-priority delivery mark to the waybill item when the waybill item cannot arrive at the terminal outlet in the distribution network on time;

[0035] The second processing module is used to obtain the predicted time for the waybill to arrive at the terminal outlet in the distribution network when the waybill can arrive at the terminal outlet in the distribution network on time, add a priority delivery mark to the waybill, and adjust the waybill promised time to the sum of the predicted time and the preset fixed overtime. The preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user.

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

[0037] Obtain the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network;

[0038] Based on the waybill information and the preset time prediction model, determine whether the waybill can arrive at the terminal point in the distribution network on time;

[0039] If not possible, add a no priority delivery mark to the waybill;

[0040] If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, add a priority delivery mark to the waybill, and adjust the waybill promised time to the sum of the predicted time and the preset fixed overtime. The preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user.

[0041] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0042] Obtain the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network;

[0043] Based on the waybill information and the preset time prediction model, determine whether the waybill can arrive at the terminal point in the distribution network on time;

[0044] If not possible, add a no priority delivery mark to the waybill;

[0045] If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, add a priority delivery mark to the waybill, and adjust the waybill promised time to the sum of the predicted time and the preset fixed overtime. The preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user.

[0046] The above-mentioned waybill priority delivery identification method, device, computer equipment and storage medium obtain the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network, and judge whether the waybill can arrive at the terminal outlet in the distribution network on time based on the waybill information and the preset time prediction model; if not, a no priority delivery mark is added to the waybill, and the waybill is not given priority delivery; if it can, the predicted time for the waybill to arrive at the terminal outlet is obtained, and a priority delivery mark is added to the waybill, and the waybill commitment time is adjusted to the sum of the predicted time and the preset fixed overtime, so as to give priority delivery to the waybill. During the whole process, based on the preset time prediction model, it is accurately judged whether the waybill can be delivered to the terminal outlet on time, and priority delivery is only performed for the waybill that can be delivered on time, and the waybill commitment time is adjusted to accurately identify whether priority delivery is performed, which brings convenience to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a diagram of an application environment of a method for identifying a shipping order with priority delivery in one embodiment;

[0048] Figure 2 It is a flowchart of a method for identifying a shipping order with priority delivery in one embodiment;

[0049] Figure 3 It is a flowchart of a method for identifying a shipping order with priority delivery in another embodiment;

[0050] Figure 4 A schematic diagram of the technical framework of a method for identifying a waybill for priority delivery in an application example;

[0051] Figure 5 It is a structural block diagram of a device for identifying a shipping order for priority delivery in one embodiment;

[0052] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] The method for identifying the priority delivery of shipping documents provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The server 104 accesses the entire logistics online distribution network, obtains the waybill information of the terminal transfer station in the distribution network, and judges whether the waybill can arrive at the terminal outlet in the distribution network on time according to the waybill information and the preset time prediction model; if not, then add a no priority delivery mark to the waybill, and do not give priority delivery to the waybill; if yes, then obtain the predicted time for the waybill to arrive at the terminal outlet, add a priority delivery mark to the waybill, and adjust the waybill commitment time to the sum of the predicted time and the preset fixed overtime, so as to give priority delivery to the waybill. The server 104 can push the final priority delivery mark and the re-determined waybill commitment time to the terminal 102, wherein the terminal 102 can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented with an independent server or a server cluster composed of multiple servers.

[0055] In one embodiment, Figure 2 As shown, a method for identifying a waybill for priority delivery is provided, comprising the following steps:

[0056] S200: Acquire the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network.

[0057] Distribution network refers to the logistics distribution network, such as Figure 1 As shown in , a general simple distribution network includes terminal (collection) outlets, transfer yards, terminal (delivery) outlets, etc. Express delivery is collected by salesmen at terminal collection outlets, and then transported to transfer yards for unified transfer and distribution to terminal delivery outlets, and then delivered to users by salesmen at terminal delivery outlets. In the distribution network, based on the complexity of the delivery path, transfer yards may be set up at multiple levels, that is, they may need to go through multiple transfers. Among the multi-level transfer yards, the last level of transfer yard is the terminal transfer yard. The waybills collected at the terminal transfer yard are sent from the terminal transfer yard to the terminal outlet, and the server obtains the waybill information of the entire terminal transfer yard. If necessary, the waybill information can be filled in according to a unified format. Specifically, a series of waybill-related information can be associated and stored with the departure schedule as the primary key.

[0058] S400: Based on the waybill information and a preset time prediction model, determine whether the waybill item can arrive at the terminal point in the distribution network on time.

[0059] The preset time efficiency prediction model is a pre-built model, which can be understood as a trained binary classification model. Its output is only two results: on time and not on time. Its input is the waybill information. If necessary, the initial binary classification model can be trained based on the historical waybill data to obtain the preset time efficiency prediction model. The above-mentioned on time can be that the time when the waybill arrives at the terminal outlet is exactly equal to the time when it is planned to arrive at the terminal outlet, or it can be that the difference between the time when the waybill arrives at the terminal outlet and the time when it is planned to arrive at the terminal outlet is less than the preset threshold. The planned time to arrive at the terminal outlet refers to the planned time set based on this freight task. It is generally set based on experience and actual logistics distribution time efficiency requirements. For example, for a waybill, its overall planned delivery takes 48 hours, and the planned time from the terminal transfer station to the terminal outlet is 24 hours. The preset threshold can be adjusted according to the actual needs. For example, it can be set to 10 minutes, that is, the time when the waybill arrives at the terminal outlet does not exceed 10 minutes of the planned time, and the waybill arrives at the terminal outlet on time.

[0060] S620: If not possible, a non-priority delivery mark is added to the waybill.

[0061] If the waybill cannot be delivered to the terminal outlet on time, it means that the waybill does not meet the prerequisites for priority delivery. Therefore, a no priority delivery mark is added to the waybill, and the waybill enters the normal logistics distribution process. If a reminder request for changing the waybill is received, the reminder of the waybill will be completed according to the normal reminder business process. If necessary, after adding a no priority delivery mark to the waybill, the information can be pushed to the terminal. The terminal can be a handheld terminal of the distribution network clerk, or a fixed terminal of the terminal outlet of the distribution network, such as a business computer at the terminal outlet. The no priority delivery mark is used to indicate that the waybill does not implement the priority delivery mechanism. Specifically, it can be a simple "×", which is associated with the identity identification mark such as the waybill number corresponding to the waybill.

[0062] S640: If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, add a priority delivery mark to the waybill, and adjust the waybill commitment time to the sum of the predicted time and the preset fixed overtime. The preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user.

[0063] The predicted time for the waybill to arrive at the terminal outlet can be predicted based on historical experience data. For example, if the waybill is a small waybill from transfer yard A to terminal outlet B, based on historical data analysis, the average time taken for small items from transfer yard A to terminal outlet B in the historical records is 10 hours, so the predicted time for the waybill to arrive at the terminal outlet is 10 hours. Further, in order to improve the accuracy of the prediction, the historical waybill information data can be analyzed by big data to extract the feature information corresponding to each waybill, and then a deep learning model or a neural network model with self-learning and updating is trained based on the feature information and the corresponding delivery time to obtain a time prediction model, and then the predicted time for the waybill to arrive at the terminal outlet is obtained based on the trained time prediction model. Adding a priority delivery mark to the waybill indicates that the preferred delivery mechanism is activated for the waybill, and the waybill commitment time is updated to be the sum of the predicted time and the preset fixed overtime, that is, the earlier estimated delivery time is updated. This time can be actively pushed to the user terminal to let the user know that the waybill can be delivered faster, which brings convenience to the user and has a good user experience. In addition, the waybill information with the priority delivery mark can also be pushed to the terminal of the terminal outlet or the salesperson's handheld terminal, so that the terminal outlet or the salesperson can prepare for priority delivery.

[0064] The preset fixed overtime refers to the estimated fixed time from the terminal outlet to the user's hands. This data can be the average of historical experience data, for example, 90 minutes of overtime can be added. The following will use an example to briefly describe the processing process of S640. Assume that after being processed in S400, the waybill X is identified as expired and can be delivered to the terminal outlet B on time. At this time, the estimated time for waybill X from transfer yard A to terminal outlet B is 10 hours. A priority delivery mark "√" is added to waybill X. The original promised time for waybill X is 15 hours. The promised time is updated from 15 hours to 10 hours + 90 minutes of preset fixed overtime, and the new promised time is pushed to the user.

[0065] The above-mentioned method for identifying the priority delivery of waybills obtains the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network, and judges whether the waybill can arrive at the terminal outlet in the distribution network on time based on the waybill information and the preset time prediction model; if not, a non-priority delivery mark is added to the waybill, and the waybill is not given priority delivery; if it can, the predicted time for the waybill to arrive at the terminal outlet is obtained, a priority delivery mark is added to the waybill, and the waybill commitment time is adjusted to the sum of the predicted time and the preset fixed overtime, so as to give priority delivery to the waybill. During the whole process, the preset time prediction model is used to accurately judge whether the waybill can be delivered to the terminal outlet on time, and priority delivery is only performed for the waybill that can be delivered on time, and the waybill commitment time is adjusted to accurately identify whether priority delivery is performed, which brings convenience to users.

[0066] like Figure 3 As shown, in one embodiment, S200 includes:

[0067] S220: Obtain real-time waybill information.

[0068] S240: Monitor the dispatching operation of the transfer yard in the distribution network according to the real-time waybill information, and extract the initial waybill information of the dispatching.

[0069] S260: Filter the initial waybill information of the vehicle according to the preset restriction conditions to obtain the waybill information of the vehicle.

[0070] The server is connected to the online distribution network to obtain real-time waybill information, and monitors the dispatching operation of the transfer station in the distribution network based on the obtained real-time waybill information, that is, the initial waybill information of the dispatching is extracted every time the transfer station dispatches a vehicle. Specifically, a new dispatching number will be generated each time the transfer station dispatches a vehicle. The server can use the dispatching number as the primary key to extract the initial waybill information of the relevant dispatching vehicle, and remove some waybill information that does not meet the preset restrictions in the initial waybill information of the dispatching vehicle according to the preset restrictions to obtain the dispatching waybill information. The preset restrictions are mainly to filter out a waybill that is obviously not eligible for priority delivery, such as the terminal outlet corresponding to the waybill is a remote outlet, the waybill is a heavy cargo, and the waybill contains parent and child parts, and the parent and child parts need to be delivered at one time. The waybill in the above cases is interfered by other factors, which makes it impossible to achieve priority delivery. Therefore, it is necessary to extract it in the initial waybill information of the dispatching vehicle according to the preset restrictions to obtain the dispatching waybill information. Specifically, the preset restrictions include that the waybill delivery points are not remote points, the waybill is not heavy cargo, and the waybill does not contain parent or child items. The specific judgment criteria for "remote" and "heavy" here can be determined based on the public knowledge and industry standards of the logistics industry.

[0071] In one of the embodiments, the initial waybill information of the vehicle is filtered according to preset restrictions to obtain the waybill information of the vehicle, including: using the Spark Streaming stream processing framework to filter the waybill data in real time according to the initial waybill information of the vehicle, caching the waybill data that meets the preset restrictions, and obtaining the waybill information of the vehicle.

[0072] Use the Spark Streaming stream processing framework to filter the waybill data in real time according to the waybill information, and cache the waybill that meets the preset restrictions to Hbase. If necessary, you can also use the Spark Streaming stream processing framework to monitor the Kafka data of the Bargun operation code. Once the waybill is dispatched from the terminal transfer yard to the outlet, the basic information of the waybill can be obtained from Hbase through the waybill number to achieve real-time monitoring of the waybill status. In actual applications, the Spark real-time computing framework and the Kafka real-time message queue of the Bargun operation code are used to filter and monitor the waybill status in real time, and filter out the waybill that is dispatched from the terminal transfer yard and meets the preset restrictions.

[0073] In one embodiment, before judging whether the waybill can arrive at the terminal point in the distribution network on time based on the waybill information and the preset time prediction model, the method further includes:

[0074] Obtain historical waybill data; based on the historical waybill data, obtain the first type of historical waybill data that arrived at the terminal outlet on time and the second type of historical waybill data that failed to arrive at the terminal outlet on time in the historical records, where on time means that the difference between the actual arrival time at the terminal outlet and the expected arrival time at the terminal outlet is no greater than a preset threshold; add an on-time arrival mark to the first type of historical waybill data, and add an untimely arrival mark to the second type of historical waybill data; use the mark of on-time arrival at the terminal outlet and the mark of untimely arrival at the terminal outlet as outputs, respectively, and use the historical waybill data as input to train an initial two-class classification model to obtain a timeliness prediction model.

[0075] The preset timeliness prediction model is a binary classification model, and its output results are only two results, "yes (1)" and "no (0)", that is, the output is "can arrive on time" and "cannot arrive on time". In this embodiment, training is performed based on historical waybill data, and the first type of historical waybill data that can arrive on time and the second type of historical waybill data that cannot be delivered on time are obtained. The on-time arrival mark (√) and the failure to arrive on time mark (×) are added by annotation to obtain sample data. The initial binary classification model is trained with the historical waybill data as input, with the marks of on-time arrival at the terminal outlet and the marks of failure to arrive at the terminal outlet in the sample data as output. Optionally, the sample data obtained above can be divided into a training set and a test set, and the initial binary classification model is trained using the training set, and the obtained timeliness prediction model is tested using the test set to ensure that the timeliness prediction model can predict accurately. Furthermore, the training set and the test set can be divided in a ratio of 8:2.

[0076] In actual application, take out the historical waybill data for a period of time and compare the estimated arrival time after departure from the terminal transfer yard given by the system with the actual arrival time:

[0077]

[0078] Where T real Indicates the actual arrival time at the outlet, T preIndicates the estimated time of arrival at the outlet. If it arrives on time, label = 1 is marked, otherwise label = 0 is marked, and the label value is used as the target value y for model training, and the processed waybill data is used as the training set of the model. Further, the corresponding features can be extracted for the historical waybill data. This feature can be multiple dimensions. The multi-dimensional feature method is used to characterize each waybill data in the historical record, and the multi-dimensional feature is used as the input of the model. Specifically, the features mainly include basic waybill features, numerical features, and time series features. Among them, the basic waybill features include the departure transfer yard code, departure time, departure date, delivery outlet code, city code, etc. of the departure shift; the numerical features include the average length of the historical overtime of the departure shift, the median of the historical overtime, the historical overtime ratio, etc.; the time series features include whether the departure shift was on time today last week or whether the corresponding day of last month was on time, that is, assuming that today is Wednesday (the 10th), the time series features include whether the departure shift was on time last Wednesday or whether it was on time on the 10th of last month.

[0079] In one embodiment, before obtaining the predicted time for the waybill to arrive at the terminal outlet based on the waybill information and the time prediction model, the method further includes:

[0080] Obtain historical waybill data; extract the real time when the waybill items arrive at the terminal outlets in the historical waybill data and the feature data in the historical waybill data, the feature data includes the basic features of the waybill, the numerical features of the waybill and the time series features of the waybill; use the real time as the output and the extracted feature data as the input to train the logistic regression model layer and the integrated model layer respectively, and adjust the model parameters through the grid search method to obtain the preset time prediction model.

[0081] As described before, the feature data mainly includes the basic features of the waybill, numerical features and time series features. Based on these features, in addition to training the preset time prediction model, the preset time prediction model can also be trained. Among them, for the basic features of the waybill, after analysis, the transfer yard to the outlet (i.e., the route), the departure time period, and the departure date are all strongly correlated with whether the departure from the transfer yard to the outlet is on time. The category features such as the departure transfer yard, the delivery outlet, and the city code are processed using the One-Hot Encoding method. The input of the preset time prediction model is the feature data in the historical waybill data, and the output is the real time of the waybill from the terminal transfer yard to the terminal outlet in the historical records. The preset time prediction model is constructed based on the logistic regression model and the integrated model. The two model layers are trained respectively with the real time as the output and the extracted feature data as the input, and the model parameters are adjusted using grid search to obtain the preset time prediction model. Optionally, the preset time prediction model and the preset time efficiency prediction model can be integrated into one model. The preset time prediction model and the preset time efficiency prediction model serve as two layers of the integrated model respectively. The integrated model can identify whether the waybill can be delivered to the terminal outlet on time, and can also predict the predicted time for the waybill to arrive at the terminal outlet.

[0082] In one embodiment, the predicted time for the waybill to arrive at the terminal outlet is obtained, a priority delivery mark is added to the waybill, and the waybill commitment time is adjusted to the sum of the predicted time and a preset fixed overtime, where the preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user, including:

[0083] If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, and determine whether the sum of the predicted time and the preset fixed overtime is greater than the original promised time of the waybill; if not, add a priority delivery mark to the waybill and adjust the promised time of the waybill to the sum of the predicted time and the preset fixed overtime.

[0084] In this embodiment, after obtaining the predicted time for the waybill to arrive at the terminal outlet, it is further determined whether the sum of the predicted time and the preset fixed overtime is greater than the original promised time of the waybill. If it is greater, it means that after the priority delivery is executed, the waybill may be delivered to the user later. Therefore, the priority delivery mechanism is not activated and the priority delivery mark is not added. Only when it is not greater, the priority delivery mark is added to the waybill, the priority delivery mechanism is activated, and the promised time of the waybill is adjusted to the sum of the predicted time and the preset fixed overtime. Continuing with the above embodiment as an example, assuming that the predicted time for the waybill to arrive at the terminal outlet is 10 hours, and the sum of the waybill and the preset fixed time is 10 hours + 90 minutes, if the original promised time of the waybill is 11 hours, it means that after the priority delivery is activated, the waybill may be delivered to the user later, and there is no need to activate the priority delivery mechanism. The priority delivery mark is not added, and the waybill can be marked as an abnormal waybill; if the original promised time of the waybill is 12 hours, the priority delivery mechanism is activated, and the priority delivery mark is added to represent the promised time of the waybill from 12 hours to 10 hours + 90 minutes.

[0085] The specific technical framework of the priority delivery identification method for waybills in this application can be found in Figure 4 ,like Figure 4 As shown in the figure, it mainly includes two aspects: time efficiency model training and priority delivery identification of waybills. Based on the time efficiency model obtained through training, it is judged whether the waybill can be delivered with priority. If it can be delivered with priority, the priority delivery mechanism is activated and the promised time is adjusted to the predicted time of arrival at the terminal outlet + the preset fixed overtime (90 minutes).

[0086] It should be understood that, although the steps in the above-mentioned flowcharts are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above-mentioned flowcharts may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0087] In one embodiment, Figure 5 As shown, the present application also provides a waybill priority delivery identification device, comprising:

[0088] Waybill acquisition module 200, used to obtain waybill information of vehicles dispatched from the terminal transfer station in the distribution network;

[0089] The judgment module 400 is used to judge whether the waybill can arrive at the terminal point in the distribution network on time according to the waybill information and the preset time prediction model;

[0090] The first processing module 620 is used to add a non-priority delivery mark to the waybill item when the waybill item cannot arrive at the terminal outlet in the distribution network on time;

[0091] The second processing module 640 is used to obtain the predicted time for the waybill to arrive at the terminal outlet in the distribution network when the waybill can arrive at the terminal outlet in the distribution network on time, add a priority delivery mark to the waybill, and adjust the waybill promised time to the sum of the predicted time and the preset fixed overtime, where the preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user.

[0092] The above-mentioned waybill priority delivery identification device obtains the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network, and determines whether the waybill can arrive at the terminal outlet in the distribution network on time based on the waybill information and the preset time prediction model; if not, a no priority delivery mark is added to the waybill, and the waybill is not given priority delivery; if it can, the predicted time for the waybill to arrive at the terminal outlet is obtained, a priority delivery mark is added to the waybill, and the waybill commitment time is adjusted to the sum of the predicted time and the preset fixed overtime, so as to give priority delivery to the waybill. During the whole process, the preset time prediction model is used to accurately judge whether the waybill can be delivered to the terminal outlet on time, and priority delivery is only performed for the waybill that can be delivered on time, and the waybill commitment time is adjusted to accurately identify whether priority delivery is performed, which brings convenience to users.

[0093] In one of the embodiments, the waybill acquisition module 200 is also used to obtain real-time waybill information; monitor the dispatching operation of the transfer yard in the distribution network according to the real-time waybill information, and extract the initial waybill information of the dispatching; filter the initial waybill information of the dispatching according to preset restrictions to obtain the dispatching waybill information.

[0094] In one of the embodiments, the waybill acquisition module 200 is also used to use the Spark Streaming stream processing framework to filter the waybill data in real time according to the initial waybill information of the vehicle, cache the waybill that meets the preset restrictions, and obtain the waybill information of the vehicle.

[0095] In one of the embodiments, the above-mentioned waybill priority delivery identification device also includes a timeliness prediction model training module, which is used to obtain historical waybill data; based on the historical waybill data, obtain the first type of historical waybill data that arrived at the terminal outlet on time and the second type of historical waybill data that failed to arrive at the terminal outlet on time in the historical records, where on time means that the difference between the actual arrival time at the terminal outlet and the expected arrival time at the terminal outlet is not greater than a preset threshold; add an on-time arrival mark to the first type of historical waybill data, and add a not-on-time arrival mark to the second type of historical waybill data; use the mark of arriving at the terminal outlet on time and the mark of not arriving at the terminal outlet on time as outputs, respectively, and use the historical waybill data as input to train an initial two-classification model to obtain a timeliness prediction model.

[0096] In one embodiment, the second processing module 800 is further used to obtain the predicted time for the waybill to arrive at the terminal outlet according to the waybill information and a preset time prediction model.

[0097] In one of the embodiments, the above-mentioned waybill priority delivery identification device also includes a time prediction model training module, which is used to obtain historical waybill data; extract the real time when the waybill arrives at the terminal outlet in the historical waybill data and the feature data in the historical waybill data, the feature data including the basic features of the waybill, the numerical features of the waybill and the time series features of the waybill; use the real time as the output and the extracted feature data as the input to train the logistic regression model layer and the integrated model layer respectively, and adjust the model parameters through the grid search method to obtain a preset time prediction model.

[0098] In one of the embodiments, the second processing module 800 is also used to obtain the predicted time for the waybill to arrive at the terminal outlet in the distribution network when the waybill can arrive at the terminal outlet on time, and determine whether the sum of the predicted time and the preset fixed overtime is greater than the original promised time of the waybill; if not, a priority delivery mark is added to the waybill, and the promised time of the waybill is adjusted to the sum of the predicted time and the preset fixed overtime.

[0099] For the specific limitations of the waybill priority delivery identification device, please refer to the limitations of the waybill priority delivery identification method above, which will not be repeated here. Each module in the above-mentioned waybill priority delivery identification device can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0100] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory and a network interface connected via 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 data such as a preset time prediction model and historical waybill information data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for identifying priority delivery of waybills is implemented.

[0101] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0102] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0103] Obtain the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network;

[0104] Based on the waybill information and the preset time prediction model, determine whether the waybill can arrive at the terminal point in the distribution network on time;

[0105] If not possible, add a no priority delivery mark to the waybill;

[0106] If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, add a priority delivery mark to the waybill, and adjust the waybill promised time to the sum of the predicted time and the preset fixed overtime. The preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user.

[0107] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0108] Obtain real-time waybill information; monitor the dispatching operation of the transfer yard in the distribution network according to the real-time waybill information, and extract the initial waybill information of the dispatching; filter the initial waybill information of the dispatching according to the preset restriction conditions to obtain the dispatching waybill information.

[0109] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0110] Using the Spark Streaming stream processing framework, we can filter the waybill data in real time according to the initial waybill information of the vehicle, cache the waybill that meets the preset restrictions, and obtain the waybill information of the vehicle.

[0111] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0112] Obtain historical waybill data; based on the historical waybill data, obtain the first type of historical waybill data that arrived at the terminal outlet on time and the second type of historical waybill data that failed to arrive at the terminal outlet on time in the historical records, where on time means that the difference between the actual arrival time at the terminal outlet and the expected arrival time at the terminal outlet is no greater than a preset threshold; add an on-time arrival mark to the first type of historical waybill data, and add an untimely arrival mark to the second type of historical waybill data; use the mark of on-time arrival at the terminal outlet and the mark of untimely arrival at the terminal outlet as outputs, respectively, and use the historical waybill data as input to train an initial two-class classification model to obtain a timeliness prediction model.

[0113] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0114] Based on the waybill information and the preset time prediction model, the predicted time for the waybill to arrive at the terminal outlet is obtained.

[0115] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0116] Obtain historical waybill data; extract the real time when the waybill items arrive at the terminal outlets in the historical waybill data and the feature data in the historical waybill data, the feature data includes the basic features of the waybill, the numerical features of the waybill and the time series features of the waybill; use the real time as the output and the extracted feature data as the input to train the logistic regression model layer and the integrated model layer respectively, and adjust the model parameters through the grid search method to obtain the preset time prediction model.

[0117] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0118] If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, and determine whether the sum of the predicted time and the preset fixed overtime is greater than the original promised time of the waybill; if not, add a priority delivery mark to the waybill and adjust the promised time of the waybill to the sum of the predicted time and the preset fixed overtime.

[0119] 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 following steps are implemented:

[0120] Obtain the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network;

[0121] Based on the waybill information and the preset time prediction model, determine whether the waybill can arrive at the terminal point in the distribution network on time;

[0122] If not possible, add a no priority delivery mark to the waybill;

[0123] If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, add a priority delivery mark to the waybill, and adjust the waybill promised time to the sum of the predicted time and the preset fixed overtime. The preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user.

[0124] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0125] Obtain real-time waybill information; monitor the dispatching operation of the transfer yard in the distribution network according to the real-time waybill information, and extract the initial waybill information of the dispatching; filter the initial waybill information of the dispatching according to the preset restriction conditions to obtain the dispatching waybill information.

[0126] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0127] Using the Spark Streaming stream processing framework, we can filter the waybill data in real time according to the initial waybill information of the vehicle, cache the waybill that meets the preset restrictions, and obtain the waybill information of the vehicle.

[0128] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0129] Obtain historical waybill data; based on the historical waybill data, obtain the first type of historical waybill data that arrived at the terminal outlet on time and the second type of historical waybill data that failed to arrive at the terminal outlet on time in the historical records, where on time means that the difference between the actual arrival time at the terminal outlet and the expected arrival time at the terminal outlet is no greater than a preset threshold; add an on-time arrival mark to the first type of historical waybill data, and add an untimely arrival mark to the second type of historical waybill data; use the mark of on-time arrival at the terminal outlet and the mark of untimely arrival at the terminal outlet as outputs, respectively, and use the historical waybill data as input to train an initial two-class classification model to obtain a timeliness prediction model.

[0130] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0131] Based on the waybill information and the preset time prediction model, the predicted time for the waybill to arrive at the terminal outlet is obtained.

[0132] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0133] Obtain historical waybill data; extract the real time when the waybill items arrive at the terminal outlets in the historical waybill data and the feature data in the historical waybill data, the feature data includes the basic features of the waybill, the numerical features of the waybill and the time series features of the waybill; use the real time as the output and the extracted feature data as the input to train the logistic regression model layer and the integrated model layer respectively, and adjust the model parameters through the grid search method to obtain the preset time prediction model.

[0134] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0135] If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, and determine whether the sum of the predicted time and the preset fixed overtime is greater than the original promised time of the waybill; if not, add a priority delivery mark to the waybill and adjust the promised time of the waybill to the sum of the predicted time and the preset fixed overtime.

[0136] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0137] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0138] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for identifying the priority delivery of shipping documents, characterized in that: The method comprises: Obtain the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network; Based on the waybill information and the preset time prediction model, determine whether the waybill can arrive at the terminal point in the distribution network on time; If not possible, add a no priority delivery mark to the waybill; If possible, the predicted time for the waybill to arrive at the terminal outlet is obtained, a priority delivery mark is added to the waybill, and the waybill commitment time is adjusted to the sum of the predicted time and the preset fixed overtime, where the preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user; Before judging whether the waybill can arrive at the terminal point in the distribution network on time according to the waybill information and the preset time prediction model, the method further includes: Get historical waybill data; According to the historical waybill data, first-category historical waybill data that arrived at the terminal outlet on time and second-category historical waybill data that failed to arrive at the terminal outlet on time in the historical records are obtained, where on time means that the difference between the actual arrival time at the terminal outlet and the expected arrival time at the terminal outlet is not greater than a preset threshold; Adding an on-time arrival mark to the first category of historical waybill data, and adding a not-on-time arrival mark to the second category of historical waybill data; The identification of the terminal outlets that arrive on time and the identification of the terminal outlets that do not arrive on time are used as outputs, and the historical waybill data are used as input to train the initial binary classification model and obtain the timeliness prediction model.

2. The method according to claim 1, characterized in that The method of obtaining the waybill information of the vehicle dispatched from the terminal transfer station in the distribution network includes: Get real-time waybill information; Monitor the dispatching operation of the transfer yard in the distribution network based on the real-time waybill information, and extract the initial waybill information of the dispatching vehicle; The initial waybill information of the vehicle is filtered according to the preset restriction conditions to obtain the waybill information of the vehicle.

3. The method according to claim 2, characterized in that The filtering of the initial waybill information of the vehicle according to the preset restriction condition to obtain the waybill information of the vehicle includes: The Spark Streaming stream processing framework is used to filter the waybill data in real time according to the initial waybill information of the vehicle, cache the waybill that meets the preset restriction conditions, and obtain the waybill information of the vehicle.

4. The method according to claim 1, characterized in that: The method of obtaining the predicted time for the waybill to arrive at the terminal outlet includes: Based on the waybill information and the preset time prediction model, the predicted time for the waybill to arrive at the terminal outlet is obtained.

5. The method according to claim 4, characterized in that Before obtaining the predicted time for the waybill to arrive at the terminal outlet according to the waybill information and the time prediction model, the method further includes: Get historical waybill data; Extract the real time when the waybill item arrives at the terminal outlet in the historical waybill data and the feature data in the historical waybill data, wherein the feature data includes the basic features of the waybill, the numerical features of the waybill and the time series features of the waybill; Taking the real time as output and the extracted feature data as input, the logistic regression model layer and the integrated model layer are trained respectively, and the model parameters are adjusted by the grid search method to obtain the preset time prediction model.

6. The method according to claim 1, characterized in that The method of obtaining the predicted time for the waybill to arrive at the terminal outlet, adding a priority delivery mark to the waybill, and adjusting the waybill commitment time to the sum of the predicted time and a preset fixed overtime, wherein the preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user, includes: If possible, obtain the predicted time for the waybill to arrive at the terminal outlet, and determine whether the sum of the predicted time and the preset fixed overtime is greater than the original promised time of the waybill; If it is not greater, a priority delivery mark will be added to the waybill and the waybill promised time will be adjusted to the sum of the predicted time and the preset fixed overtime.

7. A device for identifying the priority delivery of shipping documents, characterized in that: The device comprises: Waybill acquisition module, used to obtain waybill information of vehicles dispatched from the terminal transfer station in the distribution network; The judgment module is used to judge whether the waybill can arrive at the terminal point in the distribution network on time based on the waybill information and the preset time prediction model; The first processing module is used to add a non-priority delivery mark to the waybill item when the waybill item cannot arrive at the terminal outlet in the distribution network on time; The second processing module is used to obtain the predicted time for the waybill to arrive at the terminal outlet in the distribution network when the waybill can arrive at the terminal outlet in the distribution network on time, add a priority delivery mark to the waybill, and adjust the waybill commitment time to the sum of the predicted time and a preset fixed overtime, where the preset fixed overtime is the standard time for delivery from the terminal outlet in the distribution network to the user; A timeliness prediction model training module is used to obtain historical waybill data; based on the historical waybill data, obtain the first type of historical waybill data that arrived at the terminal outlet on time and the second type of historical waybill data that failed to arrive at the terminal outlet on time in the historical records, where on time means that the difference between the actual arrival time at the terminal outlet and the expected arrival time at the terminal outlet is not greater than a preset threshold; add an on-time arrival mark to the first type of historical waybill data, and add a not-on-time arrival mark to the second type of historical waybill data; use the mark of on-time arrival at the terminal outlet and the mark of not-on-time arrival at the terminal outlet as outputs, respectively, and use the historical waybill data as input to train an initial two-category model to obtain a timeliness prediction model.

8. The device according to claim 7, characterized in that The waybill acquisition module is also used to obtain real-time waybill information; monitor the dispatching operation of the transfer yard in the distribution network according to the real-time waybill information, and extract the initial waybill information of the dispatching; and filter the initial waybill information of the dispatching according to preset restriction conditions to obtain the dispatching waybill information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 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 6 are implemented.

Images