Simulated waybill data generation method and device, computer equipment and storage medium

Abstract

The embodiment of the invention provides a simulated waybill data generation method and device, computer equipment and a storage medium. The method comprises the steps that predicted waybill quantities corresponding to multiple time sub-segments of a designated area are acquired; wherein the specified time period is divided into a plurality of time sub-segments; according to the predicted waybill amount corresponding to the time sub-segment, determining a historical base period corresponding to the time sub-segment; wherein the historical base period corresponds to a first historical actual waybill data set; the first historical actual waybill data sets corresponding to different historical base periods are different; the first historical actual waybill data set comprises waybill data generated in a corresponding historical base period; and according to the first historical actual waybill data sets of the historical base periods of the plurality of time sub-periods, generating a simulated waybill data set of the specified area in the specified time period. And the accuracy of the simulated waybill data can be improved to a certain extent.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of logistics data processing, and in particular, to a method, device, computer equipment and storage medium for generating simulated waybill data. Background Art

[0002] At present, staff in the logistics or express delivery industry usually obtain information on the expected waybill volume in a certain period of time in the future based on market research, and select similar historical base periods as references based on their own experience to simulate the waybill volume in each business area and outlet. Then, based on the simulated waybill data, staff can make reasonable plans and decisions on the allocation of resources such as manpower and transportation capacity for that period of time, so as to improve the overall operational efficiency and service quality of the logistics network.

[0003] However, relying on the staff's experience to simulate waybill data in future time periods has the problem of low accuracy. Summary of the invention

[0004] In view of this, multiple implementations in this specification are dedicated to providing a method, apparatus, computer equipment and storage medium for generating simulated waybill data, so as to improve the accuracy of the simulated waybill data to a certain extent.

[0005] One embodiment of the present specification provides a method for generating simulated waybill data, the method comprising: obtaining predicted waybill quantities corresponding to a specified area relative to a plurality of time sub-segments; wherein the specified time period is divided into the plurality of time sub-segments; determining a historical base period corresponding to the time sub-segments according to the predicted waybill quantities corresponding to the time sub-segments; wherein the historical base period corresponds to a first historical actual waybill data set; the first historical actual waybill data sets corresponding to different historical base periods are different; the first historical actual waybill data set includes waybill data generated in the corresponding historical base period; and generating a simulated waybill data set for the specified area in the specified time period according to the first historical actual waybill data set of the historical base periods of the plurality of time sub-segments.

[0006] One embodiment of the present specification provides a device for generating simulated waybill data, the device comprising: an acquisition module, used to obtain predicted waybill quantities corresponding to a specified area relative to multiple time sub-segments; wherein the specified time period is divided into the multiple time sub-segments; a determination module, used to determine the historical base period corresponding to the time sub-segment according to the predicted waybill quantities corresponding to the time sub-segments; wherein the historical base period corresponds to a first historical actual waybill data set; the first historical actual waybill data sets corresponding to different historical base periods are different; the first historical actual waybill data set includes waybill data generated in the corresponding historical base period; a generation module, used to generate a simulated waybill data set for the specified area in the specified time period according to the first historical actual waybill data set of the historical base period of the multiple time sub-segments.

[0007] One embodiment of the present specification provides a computer device, which includes a memory and a processor. The memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the method described in the above embodiment.

[0008] One embodiment of the present specification provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program, and when the at least one computer program is executed by a processor, the method described in the above embodiment can be implemented.

[0009] The multiple implementation methods provided in this specification obtain the predicted waybill volumes corresponding to the specified area with respect to multiple time sub-segments, and determine the historical base period corresponding to the time sub-segment according to the predicted waybill volumes corresponding to the time sub-segments, and then generate a simulated waybill data set for the specified time period formed in the specified area in multiple time sub-segments according to the first historical actual waybill data set formed by the historical waybill data corresponding to each historical base period. This makes it unnecessary to rely on manual experience in the process of simulating waybill data for the specified time period, and each time sub-segment corresponds to a similar historical base period, which makes the selection of the base period more accurate, and then makes the historical actual waybill data corresponding to the base period more referenceable for simulating waybill data for the specified time period, so as to improve the accuracy of the simulated waybill data to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a method for generating simulated waybill data provided in accordance with one embodiment of this specification.

[0011] Figure 2 A schematic diagram of a leading reference period provided for one embodiment of the present specification.

[0012] Figure 3A schematic diagram of a device for generating simulated waybill data provided in accordance with one embodiment of the present specification.

[0013] Figure 4 A schematic diagram of a computer device is provided for one embodiment of the present specification. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0015] In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0016] For express delivery or logistics companies, it is very important to make reasonable resource allocation plans in advance for some future time periods. For example, during some shopping festivals or promotional seasons, the demand for express delivery business is very large. If the company does not make a good allocation plan for human resources, transportation capacity, facilities and other resources every day in advance, it may be difficult to guarantee its service quality during this period, and even the entire logistics network may be paralyzed for a short time due to problems with certain logistics nodes. Therefore, logistics or express delivery companies need to make reasonable plans for the use of resources such as transportation vehicles, manpower, and storage facilities in advance to improve resource utilization and distribution efficiency, thereby improving service quality and customer satisfaction.

[0017] In order to make reasonable plans for resource allocation in a certain period of time in the future, it is usually necessary to simulate the waybill data such as the number, weight, volume, and timeliness of each logistics or express delivery outlet within that period of time. Then the staff can use the relevant forecast information of the simulated waybill data to make corresponding plans and decisions.

[0018] In related technologies, in order to simulate the waybill data of a certain time period in the future, the staff usually collects the expected waybill volume of each business area in the time period through market research, and then selects a historical time period similar to the time period as the historical base period based on their own experience, and predicts the waybill data of the time period with reference to the historical data of the base period to obtain the corresponding simulated waybill data. However, the accuracy of selecting the historical base period based on the staff's experience will be affected by the staff's subjective cognition, ability and experience. In addition, the historical base period selected by the staff is usually a continuous period of time in history as a reference for the time period to be simulated. However, when the time span of the time period to be simulated is large, such as 10 days or 15 days, the demand for waybill business every other day or a few days may change greatly. In this case, it is difficult to find a historical time period that is relatively similar to the entire time period to be simulated, resulting in the final simulation result may deviate greatly from the real data and have low accuracy.

[0019] Therefore, it is necessary to provide a method for generating simulated waybill data, which can obtain the predicted waybill volume corresponding to the specified area relative to multiple time sub-segments, and determine the historical base period corresponding to the time sub-segment according to the predicted waybill volume corresponding to the time sub-segment, and then generate a simulated waybill data set for the specified time period formed in multiple time sub-segments in the specified area according to the first historical actual waybill data set formed by the historical waybill data corresponding to each historical base period. The process of simulating waybill data for the specified time period does not need to rely on manual experience, and by dividing the specified time period to be predicted into multiple continuous time sub-segments, a similar historical base period is determined for each time sub-segment, which can make the selection of the base period more accurate, and then make the historical actual waybill data corresponding to the base period more reference-oriented relative to the specified time period, so as to improve the accuracy of the simulated waybill data to a certain extent.

[0020] See also Figure 1. One embodiment of this specification provides a method for generating simulated waybill data. The method for generating simulated waybill data can be applied to a client or a server. The client can be an electronic device with network access capability. Specifically, for example, the client can be a desktop computer, a tablet computer, a laptop computer, a smart phone, a digital assistant, a smart wearable device, a shopping guide terminal, a television, a smart speaker, a microphone, etc. Among them, smart wearable devices include but are not limited to smart bracelets, smart watches, smart glasses, smart helmets, smart necklaces, etc. Alternatively, the client can also be software that can run in the electronic device. The server can be an electronic device with certain computing and processing capabilities. It can have a network communication module, a processor, and a memory, etc. Of course, the server can also refer to software running in the electronic device. The server can also be a distributed server, which can be a system with multiple processors, memories, network communication modules, etc. operating in collaboration. Alternatively, the server can also be a server cluster formed by several servers. Alternatively, with the development of science and technology, the server can also be a new technical means that can realize the corresponding functions of the implementation method of the specification. For example, it can be a new form of "server" based on quantum computing.

[0021] The method for generating simulated waybill data may include the following steps.

[0022] Step S110: Obtain the predicted waybill volumes corresponding to the specified area respectively with respect to a plurality of time sub-segments; wherein the specified time period is divided into the plurality of time sub-segments.

[0023] In some cases, in order to simulate the waybill data such as the number, weight, volume, and timeliness of waybills in a specified area in a certain time period in the future, so as to make targeted resource allocation plans and decisions, it is necessary to first understand the business volume demand in that time period. The predicted waybill volume for that time period can be collected through market research and other means. Then, based on the market expectation information, the waybill data can be analyzed and predicted in a fine-grained manner from multiple dimensions to realize the simulation of the waybill data.

[0024] In this embodiment, the designated area can be the geographical scope for predicting the number of waybills, and can also be understood as the location or region for which the staff makes resource allocation plans and decisions. Specifically, the coverage of the designated area can also be different depending on the needs of the staff. The designated area can include the geographical scope covered by the entire logistics network, or it can only include the scope covered by a logistics node. Specifically, for example, the designated area can be a country, a city, a business area, a transit site, or a network point.

[0025] In this embodiment, the specified time period may be the time period to be simulated, and the simulated waybill data may be simulated data generated by predicting the waybill data within the specified time period, so as to provide a basis and data support for the staff to plan or arrange. The specified time period may be any continuous time interval in the future. The specified time period may be divided into a plurality of continuous time sub-segments, and the time spans between the time sub-segments may be the same or different. Specifically, for example, the specified time period may be November 1st to November 30th, and the time sub-segments may be every day within this date interval. The specified time period may also be 8:00-18:00 on November 5th, and the time sub-segments may be 8:00-9:00, 9:00-12:00, 12:00-15:00, and 15:00-18:00.

[0026] In this embodiment, the predicted quantity of waybills can represent the number of waybills expected by the market, so as to be used as the basis for simulating waybill data. Specifically, the predicted quantity of waybills can be derived from the expected data fed back by market personnel based on the results of market research, reflecting the market demand for waybill business. The waybills can be in different business links within the life cycle of the waybills. For example, the predicted quantity of waybills can be the expected number of collection orders, the expected number of transit orders, or the expected number of delivery waybills. The predicted quantity of waybills can be the expected total quantity of waybills in a specified area in a time sub-segment. The predicted quantity of waybills can be divided into multiple groups of sub-predicted quantity of waybills. Specifically, the predicted quantity of waybills can be divided according to sub-areas such as cities and business areas included in the specified area, or it can be divided according to the business sectors corresponding to the waybills. For example, timeliness, e-commerce, cold transportation, international and other business sectors each correspond to a certain number of waybills.

[0027] In this embodiment, the predicted waybill volume corresponding to the specified area for the multiple time sub-segments can be obtained by retrieving the predicted waybill volume data from a local database storing the market research feedback data, or by sending a data acquisition request to a server or a third-party database to receive the feedback predicted waybill volume data. In some embodiments, the predicted waybill volume data can also be obtained by the staff directly entering the data in real time in the system, or by sending or transmitting the data in real time on the terminal device.

[0028] Step S120: Determine the historical base period corresponding to the time sub-segment according to the predicted waybill volume corresponding to the time sub-segment; wherein the historical base period corresponds to a first historical actual waybill data set; the first historical actual waybill data sets corresponding to different historical base periods are different; the first historical actual waybill data set includes the waybill data generated in the corresponding historical base period.

[0029] In some cases, determining the corresponding historical base period for each time sub-segment can make the base period selection more accurate. In this way, the actual historical waybill data corresponding to each base period is more useful for simulating the waybill data of the specified time period, thereby improving the accuracy of the simulated waybill data.

[0030] In this embodiment, the historical base period can be used as a reference time period selected when performing data analysis, comparison or prediction. A historical base period with strong representativeness and reference is very important for the accuracy of data analysis and prediction. Specifically, the historical base period can be used as a reference benchmark for sub-time periods in the process of simulating waybill data, providing a reference and basis for predicting waybill information within a specified time period. By integrating and analyzing the historical actual waybill data of the historical base period, the possible trends and changes of waybill data in the future can be better simulated. Specifically, for example, to simulate the waybill data on November 11 this year, due to the particularity of the demand for waybills during this period, November 11 or November 12 last year can be used as the corresponding historical base period as a data reference.

[0031] In this embodiment, the first historical actual waybill data set represents the historical waybill data set generated in the selected historical base period. The historical waybill data may include historical operation records during the life cycle of the waybill, specifically, detailed data of each waybill link such as collection, transfer to the item, dispatch, and delivery. Taking collection as an example, the historical waybill data of the collection link may include the collection time, outlets, venues, item weight, volume, business level and sector to which the waybill belongs, and other information. The first historical actual waybill data set can be understood as a data set obtained by aggregating historical waybill data with the historical base period as the time condition.

[0032] In this embodiment, the historical base period corresponding to the time sub-segment is determined based on the predicted waybill volume corresponding to the time sub-segment. The time series analysis method can be used to select a historical time period with high representativeness as the historical base period by comparing the data change trend and related characteristics of the predicted waybill volume of the time sub-segment with the waybill volume in different historical time periods.

[0033] In some embodiments, the steps of determining the historical base period corresponding to the time sub-segment according to the predicted waybill volume corresponding to the time sub-segment include: obtaining the corresponding first feature vector according to the predicted waybill volume corresponding to the time sub-segment; wherein the first feature vector expresses multiple specified dimensional features of the time sub-segment; based on the vector similarity measure, respectively selecting the second feature vector matching the first feature vector from the historical time sub-segment; wherein the historical time period is divided into multiple historical time sub-segments; the second feature vector expresses the multiple specified dimensional features of the historical time sub-segment; and respectively determining the historical time sub-segments represented by the second feature vector as the historical base period corresponding to the time sub-segment.

[0034] In some cases, by setting characteristic conditions of multiple dimensions in combination with the predicted waybill volume, the time sub-segments are vectorized, and then historical time sub-segments with higher similarity are screened out from the historical time periods based on vector similarity matching to serve as the historical base period. By quantifying the similarity between the historical base period and the time sub-segments, the intervention of subjective factors can be reduced, thereby improving the stability and accuracy of the historical base period screening.

[0035] In some embodiments, obtaining the corresponding first feature vector according to the predicted waybill volume corresponding to the time sub-segment may be a process of vectorizing the time sub-segment to obtain the first feature vector used to characterize the time sub-segment. Specifically, for example, the time sub-segment may be expressed as a first feature vector from multiple specified dimensional features such as the time sub-segment type, the scale of the predicted waybill volume corresponding to the time sub-segment, the business segment structure, and the capacity allocation of the logistics network. For example, the first feature vector may be a 29-dimensional vector, and each dimensional feature corresponds to multiple dimensions in the first feature vector.

[0036] In some embodiments, the type characteristics of the time sub-segment can be used to express the time characteristics of the time sub-segment. For example, time sub-segments in different periods such as holidays, public holidays, and e-commerce festivals can be expressed as different types. The predicted scale of waybills and the structure of business segments can be understood as the expected number of waybills and the proportion of the number in each business segment, that is, the structural composition of the predicted number of waybills. It can be understood that each time sub-segment should maintain a high degree of similarity with the corresponding historical base period in the number of waybills and their composition, which can be used as a feature of expressing the time sub-segment for screening the base period. The capacity allocation of the logistics network can be understood as the distribution or configuration of capacity resources in a specified area. It can be understood that each time sub-segment should also maintain a high degree of similarity with the corresponding historical base period in capacity allocation, so it is also used as one of the feature dimensions. Specifically, take the type feature vectorization of a time subsegment as an example. For example, if the time subsegment is a day, the type feature of each time subsegment can be the date type of a certain day. Multihot combination encoding can be used to take the date type of a certain day and the date types of the two days before and after to vectorize the date type of the day. As shown in Table 1, lag0 represents the date type of a certain day, lag1 and lag2 represent the one day before and after and the two days respectively.

[0037] Table 1

[0038] lag2 lag1 lag0 lag1 lag2 Saturday 1 1 2 2 1 Sunday 1 2 2 1 1 Wednesday 1 1 1 1 1 The second day of the holiday 1 3 3 3 1 The last day of the long holiday 4 4 4 1 1

[0039] Multihot encoding can vectorize the date type of a certain day to obtain a 5-dimensional combination vector, where 1 represents a working day, 2 represents a two-day holiday, 3 represents a three-day short holiday, and 4 represents a long holiday. In addition, this vector can not only distinguish the date type, but also distinguish the temporal relationship in the date type. It can be seen that the similarity between the 5-dimensional vectors also shows that "Monday" and "Wednesday" are more similar than "Monday" and "Saturday". In this way, the date type of any day can be expressed in vector form.

[0040] In some embodiments, the historical time period may be a relatively long historical time interval as a set of time sub-segment historical samples for screening the historical base period. The historical time sub-segment may be a plurality of time-continuous time sub-segment historical samples obtained by dividing the historical time period. The time span of the historical time sub-segment may be the same as the time span of the time sub-segment. Specifically, for example, the historical time period may be the time interval from January 1, 2020 to the present, and each day in this period may be used as a time sub-segment.

[0041] In some implementations, the second feature vector may be used to characterize the historical time sub-segment. Specifically, the historical time sub-segment may be vectorized based on the feature conditions of multiple dimensions that are the same as the time sub-segment, so as to be used for vector similarity calculation.

[0042] In some embodiments, when feature vectorizing historical time sub-segments, the multiple specified dimensional features may also include: a timeliness feature of the historical time sub-segment relative to the time sub-segment; the timeliness feature is used to characterize the reference weight of the time difference between the historical time sub-segment and the time sub-segment for the time sub-segment.

[0043] In some embodiments, the historical time sub-segment, as a historical sample, has a time series effect. The closer the sample is to the time sub-segment, the higher its representativeness and reference degree. For example, taking into account market changes, as a historical time sub-segment of November 1 this year, a certain day one year ago and a certain day three years ago have different reference values ​​for predicting the waybill data on November 1 this year. Specifically, in order to quantify the difference in sample reference value caused by this time series effect, a time attenuation coefficient can be determined by constructing a decreasing function to characterize the reference weight of the time difference between the historical time sub-segment and the time sub-segment for the time sub-segment, and then expressed in the first eigenvector and the second eigenvector as a constraint condition. Specifically, for example, when the time sub-segment and the historical time sub-segment are both one day, the attenuation factor of the historical date relative to the target date can be represented by the following function: F(x i )=ln(180-d i )+ln(26-w i ), where x i Indicates historical date, di Indicates the date offset, w i Indicates the weekly offset.

[0044] In some embodiments, based on the vector similarity measure, a second feature vector matching the first feature vector is screened out from the historical time sub-segment. The second feature vector can be screened by calculating the cosine similarity between the first feature vector and the second feature vector, or by calculating the Euclidean distance or Manhattan distance between the first feature vector and the second feature vector.

[0045] In some embodiments, before calculating the similarity between the first eigenvector and the second eigenvector, different weights can be assigned to features of different dimensions in the eigenvector according to different scenarios (such as flat peak and peak period) to obtain an optimized combined vector, and then the similarity is calculated for the combined vector, so that the selected historical base period can be more in line with the actual scenario.

[0046] In some implementations, a similarity list may be obtained based on the result of the vector similarity calculation. Further, the second feature vectors may be sorted and the one with the highest similarity may be selected, and the historical time sub-segment represented by the second feature vector may be used as the historical base period.

[0047] In some embodiments, in order to avoid the situation where the actual number of waybills in the historical base period is insufficient relative to the predicted number of waybills in the time sub-segment, the top K in the similarity list can be selected, and the historical time sub-segments other than the historical time sub-segment with the highest similarity can be used as alternative historical base periods to fill the gap when the actual number of waybills in the historical base period is insufficient.

[0048] Step S130: generating a simulated waybill dataset of the designated area in the designated time period according to the first historical actual waybill dataset of the historical base period of the multiple time sub-segments.

[0049] In this embodiment, the simulated waybill data set can be used as a prediction result of the waybill information for a specified area in a specified time period, so as to provide a reference and basis for the staff to make targeted resource allocation plans and decisions. Specifically, the simulated waybill data set may include the simulated waybill data of each city, business area, outlet, transfer site, etc. in the specified area in each time sub-segment, and the information dimensions represented by the waybill data may be consistent with the historical waybill data, including multiple dimensional information such as timeliness, quantity, weight, volume, level, and plate distribution.

[0050] In this embodiment, the simulated waybill data set may also be a result data set obtained by aggregating and summarizing the historical actual waybill data in the first historical actual waybill data set for different links of the waybill life cycle. The simulated waybill data set for the specified area in the specified time period is generated based on the first historical actual waybill data set of the historical base period of the multiple time sub-segments. The historical actual waybill data set may be respectively collected and summarized for the collection, transfer, and delivery links of the waybill to obtain the simulated waybill data of each city, business area, and outlet, so as to form a simulated waybill data set for the specified area in the specified time period according to the time correspondence. In this way, since the simulated waybill data set contains multiple dimensions and fine-grained waybill data of the specified area in the specified time period, the staff can understand the dynamic distribution and change trend of the collection, transfer, and delivery data of each business area and outlet in the specified area in the specified time period. Compared with the predicted waybill volume, the amount of information is very sufficient, so that the staff can make more reasonable plans and decisions based on the simulated waybill data set, thereby improving work efficiency.

[0051] In this embodiment, based on the first historical actual waybill dataset of the historical base period of the multiple time sub-segments, a simulated waybill dataset of the specified area in the specified time period is generated. It can also be for information dimensions different from those in the historical waybill data. A third-party or trained deep learning-based prediction model is used to take the first historical actual waybill dataset as input to obtain corresponding prediction results, and the simulated waybill data of the specified area in the specified time period under the information dimension is obtained to form a simulated waybill dataset.

[0052] See also Figure 2 . In some embodiments, the predicted waybill volume is the predicted collection volume; the first historical actual waybill data set corresponding to the historical base period includes the historical actual collection data of the historical base period; the method further comprises: obtaining the predicted collection volume of a preceding reference period earlier than the specified time period; wherein the preceding reference period is continuous with the specified time period in time; determining the historical reference base period corresponding to the preceding reference period according to the predicted collection volume of the preceding reference period; the historical reference base period corresponds to a second historical actual waybill data set; accordingly, generating a simulated waybill data set for the specified area in the specified time period according to the first historical actual waybill data set and the second historical actual waybill data set.

[0053] In some cases, when the predicted waybill volume is the predicted collection volume, the corresponding historical base period can be determined based on the predicted collection volume corresponding to the time sub-segment and the historical actual collection data of each historical time sub-segment, and then the simulated waybill data set for the specified area in the specified time period can be generated based on the full life cycle record data from collection to successful delivery of the historical actual waybill corresponding to the historical actual collection data of the historical base period. However, the time sub-segments that are relatively early in the specified time period may be due to the historical actual waybill of the corresponding base period still being in the collection stage. In this case, the simulated data of the transit waybill and the simulated data of the delivery waybill of these time sub-segments are difficult to simulate accurately. Therefore, considering the interval time of the time conversion of each link of the waybill, the historical base period can be selected for the predicted collection volume of the preceding reference period earlier than the specified time period, and the simulated data of the transit waybill and the simulated data of the delivery waybill of these early time sub-segments can be generated according to the historical actual waybill data corresponding to the corresponding historical reference base period, thereby improving the accuracy of the simulated waybill data.

[0054] In some embodiments, the preceding reference period can be used as an extension of the specified time period on the timeline to predict part of the waybill data in the time sub-segment that is closer to the front of the specified time period, such as the transit waybill data, the delivery waybill data, etc. The time span of the preceding reference period can be determined according to the time interval from the receipt of the waybill to the successful delivery. Specifically, for example, the time span of the preceding reference period can be 3 days.

[0055] In some implementations, the pre-reference period can also be divided into multiple pre-reference sub-periods, each of which corresponds to a corresponding predicted order collection volume. Accordingly, the historical reference base period corresponding to the pre-reference sub-period can be determined based on the predicted order collection volume of the pre-reference sub-period.

[0056] In some embodiments, the second historical actual waybill data set can be used to simulate the transit waybill data and delivery waybill data of the time sub-segment in the previous time period in the specified time period to generate corresponding simulated waybill data. Specifically, the second historical actual waybill data set can represent the set of historical waybill data generated in the historical reference base period corresponding to the previous reference sub-period. Similar to the first historical actual waybill data, the historical waybill data in the second historical actual waybill data set can also include historical operation records during the life cycle of the waybill. Specifically, for example, it can include detailed data of each waybill link such as collection, transit to shipment, shipment, and delivery. Specifically, the data can include multiple information dimensions such as collection time, outlets, venues, item weight, volume, business level and sector to which the waybill belongs, etc.

[0057] In some embodiments, the step of generating a simulated waybill dataset for the designated area in the designated time period based on the first historical actual waybill dataset and the second historical actual waybill dataset may include: simulating a first intermediate transfer waybill dataset and / or a first delivery waybill dataset for the designated area in at least part of the time sub-segment based on the second historical actual waybill dataset; generating a simulated waybill dataset for the designated area in the designated time period based on the first historical actual waybill dataset, the first intermediate transfer waybill dataset and / or the first delivery waybill dataset.

[0058] In some embodiments, based on the second historical actual waybill data set, the first transit transit waybill data set and / or the first delivery waybill data set of the designated area in at least part of the time sub-segment are simulated, and the flow distribution and time efficiency information of the waybill in the second historical actual waybill data set can be used, and the historical actual waybill data corresponding to the time sub-segment can be aligned for the designated time period, and the historical actual waybill data corresponding to the time sub-segment is used as the corresponding simulated waybill data. Since there is a time interval for conversion efficiency between the waybill links, for example, it may take one day from receipt to arrival at the transit site, and it may take two or three days to deliver the goods, it can be understood that the historical actual receipt data in the second historical actual waybill data set occurs in the historical reference base period corresponding to the previous reference time period, so the simulated waybill data can be the transit link waybill data and / or the delivery link waybill data in at least part of the time sub-segment. Specifically, for example, the first time sub-segment in the specified time period may be November 1, 2023, the preceding reference sub-period may be October 31, 2023, and the historical base period corresponding to the preceding reference sub-period may be October 29, 2021. According to the record data of historical actual waybills, a waybill collected on the same day arrives at a transfer site on October 30, 2021. Based on the corresponding relationship of the interval of this one day, the waybill information can be determined as the simulated waybill information on November 1, 2023.

[0059] In some implementations, the at least part of the time subsegments may be the part of the time subsegments that is the earliest in time among the time subsegments, for example, the first time subsegment or the first two time subsegments.

[0060] In some embodiments, a simulated waybill dataset for the designated area in the designated time period is generated based on the first historical actual waybill dataset, the first intermediate transfer waybill dataset and / or the first delivery waybill dataset. The simulated waybill data for each time subsegment can be determined based on the flow distribution and timeliness information of the historical actual waybills in the first historical actual waybill dataset, and together with the first intermediate transfer waybill dataset and the first delivery waybill dataset, a simulated waybill dataset for the designated area in the designated time period is formed.

[0061] In some embodiments, the designated area includes a plurality of designated business areas; corresponding to the plurality of designated business areas, the predicted waybill volume corresponding to each time sub-segment is divided into a plurality of groups of sub-predicted waybill volumes; accordingly, the step of determining the historical base period corresponding to the time sub-segment according to the predicted waybill volume corresponding to the time sub-segment respectively includes: for each designated business area, determining the historical base period corresponding to the time sub-segment according to the sub-predicted waybill volume corresponding to the time sub-segment respectively;

[0062] In some cases, there may be multiple designated business areas within a designated area. By dividing the predicted waybill volume corresponding to each time sub-segment into multiple groups of sub-predicted waybill volumes according to multiple business areas, and then determining the matching historical base period for each designated business area based on the sub-predicted waybill volume of the time sub-segment, each business area within the designated area can have a corresponding similar historical base period as a reference in each time sub-segment for simulating waybill data. Since the selection of the historical base period is more refined, the historical actual waybill data corresponding to the historical base period can be more referenceable, so that the simulated waybill data can be more accurate.

[0063] In some embodiments, for each designated business area, the steps of determining the historical base period corresponding to the time sub-segment based on the sub-predicted waybill volume corresponding to the time sub-segment are similar to those in the aforementioned embodiments, and the same parts are not repeated here. In this embodiment, in the process of determining the historical base period using the vector similarity calculation method, when the time sub-segments and the historical time sub-segments are vectorized, in addition to being based on multiple specified dimensional features in the aforementioned embodiments, the business area type or the type of region to which the business area belongs can also be used as a dimensional feature, so that the waybill data in the first historical actual waybill data set corresponding to the filtered historical base period is generated in the designated business area.

[0064] In some embodiments, the step of generating a simulated waybill data set for the designated area in the designated time period based on the first historical actual waybill data set of the historical base period of the multiple time sub-segments includes: determining the simulated waybill data corresponding to each time sub-segment based on the flow direction information and timeliness information of the historical actual waybills in the first historical actual waybill data set corresponding to the historical base period; wherein the simulated waybill data at least includes waybill quantity information; generating a simulated waybill data set for the designated area in the designated time period based on the simulated waybill data corresponding to each time sub-segment.

[0065] In some embodiments, the flow direction information of the historical actual waybill can indicate the flow of the historical waybill during the entire life cycle from receipt to successful delivery. The timeliness information of the historical actual waybill can indicate the timeliness distribution of the historical waybill during the entire life cycle from receipt to successful delivery. Specifically, the flow direction information of the historical actual waybill can be the routing information of the waybill during the transportation process, and the corresponding time information can be understood as timeliness information. For example, a parcel is received in Shanghai, passes through Jiangsu, Guangxi, Fujian, Guangdong, and is finally delivered in Shenzhen. This waybill route can be the flow direction information of the historical actual waybill, and the time when the parcel arrives at each node on this waybill route and is sent out can be the timeliness information of the historical actual waybill.

[0066] In some embodiments, based on the simulated waybill data corresponding to the each time sub-segment, a simulated waybill data set is generated for the specified area in the specified time period. The simulated waybill data can be directly aggregated to obtain the simulated waybill data set, or, similar to the aforementioned embodiment, the simulated waybill data can be aggregated for multiple waybill links and then aggregated to form a simulated waybill data set. Of course, other conditions can also be selected to aggregate and integrate the data to obtain the corresponding simulated waybill data set.

[0067] In some embodiments, the step of generating a simulated waybill data set for the specified area in the specified time period based on the simulated waybill data corresponding to each time sub-segment includes: determining a simulation scale factor based on the waybill quantity information in the simulated waybill data corresponding to each time sub-segment and the predicted waybill quantity for the specified area; and scaling the simulated waybill data proportionally based on the simulation scale factor to obtain the simulated waybill data set.

[0068] In some cases, the number of historical actual waybills in the first historical actual waybill data set corresponding to the historical base period may be different from the predicted waybill volume of the corresponding time sub-segment, which may cause the final simulated waybill data to not match the market expected waybill volume in terms of total waybill volume, affecting the accuracy of the simulated waybill data. By determining the simulation scale factor between the waybill volume of the simulated waybill data and the predicted waybill volume, and then scaling the simulated waybill data in proportion, the final generated simulated waybill data set can be made to better match the market expected information and improve accuracy.

[0069] In some embodiments, the simulation proportional factor is determined based on the waybill quantity information in the simulated waybill data corresponding to each time sub-segment and the predicted waybill quantity in the specified area. The simulation proportional factor can be obtained by dividing the total predicted waybill quantity in the specified area in each time sub-segment by the total waybill quantity in the simulated waybill data corresponding to each time sub-segment.

[0070] In some embodiments, based on the simulation scale factor, the simulated waybill data is scaled proportionally to obtain the simulated waybill data set. The simulated waybill data can be multiplied by the simulation scale factor to achieve proportional scaling relative to market expectation information, thereby obtaining the simulated waybill data set.

[0071] See also Figure 3 One embodiment of the present specification also provides a device for generating simulated waybill data. The device for generating simulated waybill data may include:

[0072] An acquisition module, used to acquire predicted waybill volumes corresponding to a specified area and a plurality of time subsegments respectively; wherein the specified time period is divided into the plurality of time subsegments;

[0073] A determination module, configured to determine a historical base period corresponding to a time sub-segment according to the predicted waybill volume corresponding to the time sub-segment, wherein the historical base period corresponds to a first historical actual waybill data set; the first historical actual waybill data sets corresponding to different historical base periods are different; and the first historical actual waybill data sets include waybill data generated in the corresponding historical base period;

[0074] A generating module is used to generate a simulated waybill dataset for the specified area in the specified time period based on a first historical actual waybill dataset of the historical base period of the multiple time sub-segments.

[0075] Regarding the specific functions and effects achieved by the device for generating simulated waybill data, please refer to other embodiments of this specification for reference and explanation, and will not be repeated here. Each module in the device for generating simulated waybill data can be implemented in whole or in part by software, hardware, and a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0076] The embodiments of this specification also provide a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a computer, the computer executes the method for generating simulated waybill data in any of the above embodiments.

[0077] The embodiments of this specification also provide a computer program product including instructions, which, when executed by a computer, enables the computer to execute the method for generating simulated waybill data in any of the above embodiments.

[0078] See also Figure 4The present description embodiment may provide an electronic device, the electronic device comprising: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, the instructions are executed by the one or more processors, so that the one or more processors implement the method in any of the above embodiments.

[0079] In some embodiments, the electronic device may include a processor, a non-volatile storage medium, an internal memory, a communication interface, a display device, and an input device connected by a system bus. The non-volatile storage medium may store an operating system and related computer programs.

[0080] The user information or user account information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, etc.) involved in multiple implementation methods of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0081] It should be understood that the specific examples herein are only intended to help those skilled in the art to better understand the embodiments of the present specification, rather than to limit the scope of the present invention.

[0082] It can be understood that in the various implementations of this specification, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation methods of this specification.

[0083] It can be understood that the various embodiments described in this specification can be implemented individually or in combination, and the embodiments of this specification are not limited to this.

[0084] Unless otherwise specified, all technical and scientific terms used in the embodiments of this specification have the same meaning as those generally understood by those skilled in the art of the technical field of this specification. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the scope of this specification. The term "and / or" used in this specification includes any and all combinations of one or more related listed items. The singular forms of "a", "above", and "the" used in the embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0085] It can be understood that the processor of the embodiment of this specification can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method implementation can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiment of this specification can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of this specification can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0086] It is understood that the memory in the embodiments of this specification may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (programmable ROM, PROM), an erasable programmable read-only memory (erasablePROM, EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0087] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this specification.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method implementation methods and will not be repeated here.

[0089] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0091] In addition, each functional unit in each embodiment of the present specification may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0092] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0093] The above is only a specific implementation of this specification, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in this specification, which should be included in the protection scope of this specification. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for generating simulated waybill data, characterized in that: The method comprises: Obtaining predicted waybill volumes corresponding to a specified area and a plurality of time subsegments respectively; wherein the specified time period is divided into the plurality of time subsegments; Determine the historical base period corresponding to the time sub-segment according to the predicted waybill volume corresponding to the time sub-segment respectively; wherein the historical base period corresponds to a first historical actual waybill data set; the first historical actual waybill data sets corresponding to different historical base periods are different; the first historical actual waybill data sets include waybill data generated in the corresponding historical base period; A simulated waybill dataset for the designated area in the designated time period is generated according to a first historical actual waybill dataset of the historical base period of the multiple time sub-segments.

2. The method according to claim 1, characterized in that The predicted waybill volume is the predicted waybill collection volume; the first historical actual waybill data set corresponding to the historical base period includes the historical actual waybill collection data of the historical base period; the method further includes: Obtaining a predicted amount of collected orders for a preceding reference period earlier than the specified time period; wherein the preceding reference period is continuous with the specified time period in time; Determine a historical reference base period corresponding to the preceding reference period according to the predicted collection volume of the preceding reference period; the historical reference base period corresponds to a second historical actual waybill data set; Correspondingly, a simulated waybill data set of the designated area in the designated time period is generated according to the first historical actual waybill data set and the second historical actual waybill data set.

3. The method according to claim 2, characterized in that The step of generating a simulated waybill data set for the designated area in the designated time period according to the first historical actual waybill data set and the second historical actual waybill data set includes: Based on the second historical actual waybill dataset, simulate and obtain a first intermediate transfer waybill dataset and / or a first dispatch waybill dataset for the designated area in at least part of the time subsegment; A simulated waybill dataset for the designated area in the designated time period is generated according to the first historical actual waybill dataset, the first intermediate transfer waybill dataset and / or the first delivery waybill dataset.

4. The method according to claim 1, characterized in that: The designated area includes a plurality of designated business areas; corresponding to the plurality of designated business areas, the predicted waybill volume corresponding to each time sub-segment is divided into a plurality of groups of sub-predicted waybill volumes; Correspondingly, the steps of determining the historical base period corresponding to the time sub-segment according to the predicted waybill volume corresponding to the time sub-segment include: for each designated business area, determining the historical base period corresponding to the time sub-segment according to the sub-predicted waybill volume corresponding to the time sub-segment.

5. The method according to claim 4, characterized in that The step of generating a simulated waybill dataset for the designated area in the designated time period according to the first historical actual waybill dataset of the historical base period of the multiple time sub-segments comprises: Determine the simulated waybill data corresponding to each time subsegment according to the flow direction information and time efficiency information of the historical actual waybill in the first historical actual waybill data set corresponding to the historical base period; wherein the simulated waybill data at least includes waybill quantity information; A simulated waybill data set for the designated area in the designated time period is generated according to the simulated waybill data corresponding to each time sub-segment.

6. The method according to claim 4, characterized in that The step of generating a simulated waybill data set for the designated area in the designated time period according to the simulated waybill data corresponding to each time sub-segment includes: Determine a simulation scale factor based on the waybill quantity information in the simulated waybill data corresponding to each time sub-segment and the predicted waybill quantity in the specified area; Based on the simulation scale factor, the simulated waybill data is scaled proportionally to obtain the simulated waybill data set.

7. The method according to claim 1, characterized in that The steps of determining the historical base period corresponding to the time sub-segment according to the predicted waybill volume corresponding to the time sub-segment respectively include: Obtain corresponding first feature vectors according to the predicted waybill quantities corresponding to the time sub-segments, respectively; wherein the first feature vectors express multiple specified dimensional features of the time sub-segments; Based on the vector similarity measure, second feature vectors matching the first feature vectors are respectively selected from the historical time sub-segments; wherein the historical time period is divided into a plurality of historical time sub-segments; and the second feature vectors express the plurality of specified dimensional features of the historical time sub-segments; The historical time sub-segments represented by the second eigenvectors are respectively determined as the historical base periods corresponding to the time sub-segments.

8. The method according to claim 7, characterized in that The multiple specified dimensional features include: a timeliness feature of a historical time sub-segment relative to a time sub-segment; the timeliness feature is used to characterize a reference weight of a time difference between a historical time sub-segment and a time sub-segment for a time sub-segment.

9. A device for generating simulated waybill data, characterized in that: The device comprises: An acquisition module, used to acquire predicted waybill volumes corresponding to a specified area and a plurality of time subsegments respectively; wherein the specified time period is divided into the plurality of time subsegments; A determination module, configured to determine a historical base period corresponding to a time sub-segment according to the predicted waybill volume corresponding to the time sub-segment, wherein the historical base period corresponds to a first historical actual waybill data set; the first historical actual waybill data sets corresponding to different historical base periods are different; and the first historical actual waybill data sets include waybill data generated in the corresponding historical base period; A generating module is used to generate a simulated waybill dataset for the specified area in the specified time period based on a first historical actual waybill dataset of the historical base period of the multiple time sub-segments.

10. A computer device, characterized in that: The computer device includes a memory and a processor, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one computer program, and when the at least one computer program is executed by a processor, the method according to any one of claims 1 to 8 can be implemented.

Images