CN116955853A

CN116955853A - Method, device, equipment and storage medium for predicting and inquiring order signing time

Info

Publication number: CN116955853A
Application number: CN202310928482.6A
Authority: CN
Inventors: 谢伟; 李波涛
Original assignee: Dongpu Software Co Ltd
Current assignee: Dongpu Software Co Ltd
Priority date: 2023-07-26
Filing date: 2023-07-26
Publication date: 2023-10-27

Abstract

The invention relates to the technical field of information processing, in particular to an order signing time prediction query method, device, equipment and storage medium.

Description

Method, device, equipment and storage medium for predicting and inquiring order signing time

Technical Field

The present invention relates to the field of information processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for predicting and querying order receiving time.

Background

With the continuous development of the e-commerce network, the business collaborative combination mode of 'logistics + internet' is widely applied and popularized in a logistics comprehensive service platform, logistics industry is an important service link for realizing product circulation at present, irreplaceable effects are exerted on commodity circulation and material allocation, along with the continuous maturity of the e-commerce field, the informatization of the logistics field is continuously perfected, the demand of the logistics field on logistics data processing is increasingly greater, the signing time of a logistics order is usually accompanied with the end of the logistics order and bill calculation of the logistics order, but because the logistics business needs to be subcontracting layer by layer, the whole tracking link of logistics information is overlong, the precise prediction of the logistics order signing time is difficult to be carried out after the increasingly-growing logistics data or the multiple subcontracting and subcontracting of the logistics business, the whole settlement efficiency and the company operation efficiency of the logistics order are reduced, the predicted arrival time of a express item after the change of the adjustment of the transportation network is not timely provided only according to the history data estimation at present, the express item predicted arrival time possibly encounters the condition of insufficient hands or due to weather retention in the actual transportation, and the like, the predicted arrival time of the existing scheme is only can not be updated accurately, and the predicted arrival time of users is low due to the fact is only one-time.

Disclosure of Invention

In order to overcome the defects of the prior art, the invention aims to provide an order signing time prediction query method, an apparatus, a device and a storage medium, which can dynamically update the predicted signing time of a logistics order according to actual transportation conditions, improve the prediction accuracy of the logistics order signing time, improve the overall settlement efficiency of the logistics order and the operation efficiency of a company, improve the experience of both users and network sites, and simultaneously have the advantages of signing time spam prediction and increase the prediction reliability of the order signing time.

The first aspect of the present invention provides a method for predicting and querying order signing time, comprising: acquiring the waybill number information sent by the query terminal, and inputting the waybill number information into a preset logistics track model for query to obtain an initial logistics track query result; identifying the initial time information of the initial logistics track query result, and calculating according to the initial time information to obtain the spam predicted signing time; judging whether the initial logistics track inquiry result has an updated state or not; if yes, updating the initial logistics track inquiry result in real time to obtain a latest logistics track inquiry result, and calculating according to the latest logistics track inquiry result to obtain the latest expected signing time; and replacing the spam expected signing time with the latest expected signing time, and sending the latest expected signing time to the query terminal.

Optionally, in a first implementation manner of the first aspect of the present invention, the acquiring the waybill number information sent by the query terminal, inputting the waybill number information to a preset logistics track model for query, and obtaining an initial logistics track query result includes: acquiring waybill number information sent by a query terminal, and acquiring historical logistics track data; extracting logistics track characteristic data from the historical logistics track data, wherein the logistics track characteristic data at least comprises track segment characteristics and operation period characteristics; generating a plurality of track samples, wherein each track sample comprises logistics track characteristic data and logistics track arrival time; training the track sample into a logistics track model; and calling a logistics track model, and inputting the waybill information into the logistics track model for inquiring to obtain an initial logistics track inquiring result.

Optionally, in a second implementation manner of the first aspect of the present invention, the identifying start time information of the initial logistics track query result, and calculating according to the start time information, to obtain a spam expected signing time includes: identifying a plurality of track nodes of the initial logistics track query result, and predicting a plurality of execution durations corresponding to the track nodes respectively; respectively acquiring the table calendar information of each track node, and identifying the fake-releasing information in the table calendar information; and accumulating the fake-release information and a plurality of execution time lengths based on the starting time information to obtain the spam predicted signing time.

Optionally, in a third implementation manner of the first aspect of the present invention, the identifying a plurality of track nodes of the initial logistics track query result and predicting a plurality of execution durations corresponding to a plurality of track nodes respectively include: identifying a plurality of track nodes of the initial logistics track query result; collecting historical order data between two adjacent track nodes, and calculating historical average distribution time length according to the historical order data; and respectively predicting a plurality of execution time lengths corresponding to the track nodes according to the historical average distribution time lengths.

Optionally, in a fourth implementation manner of the first aspect of the present invention, if yes, updating the initial logistics track query result in real time to obtain a latest logistics track query result, and calculating according to the latest logistics track query result to obtain a latest expected signing time, including: if yes, acquiring logistics scanning record information transmitted in real time by a scanning terminal in a logistics track model, wherein the logistics scanning record information comprises scanning time and scanning network points; sorting a plurality of logistics scanning record information corresponding to the waybill information according to the scanning time, and identifying the logistics scanning record information with the latest scanning time to obtain target scanning record information; generating a latest logistics track query result according to the target scanning record information; and calculating the latest logistics track inquiry result according to the scanning time corresponding to the target scanning record information to obtain the latest expected signing time.

Optionally, in a fifth implementation manner of the first aspect of the present invention, the calculating the latest logistics track query result according to the scanning time corresponding to the target scanning record information to obtain the latest expected signing time includes: acquiring speed influence characteristic data in real time, wherein the speed influence characteristic data comprises real-time weather data and real-time road condition data, and calculating the latest logistics track inquiry result according to the scanning time corresponding to the target scanning record information to obtain initial expected signing time; identifying current back bill state information and carrying force information of the scanning network points, calculating first time supplementing information according to the back bill state information and the carrying force information, and calculating second time supplementing information according to the real-time weather data; updating path information according to the real-time road condition data to obtain latest path information, and correcting the original track distance of the scanning network point according to the latest path information to obtain corrected track distance; and calculating third time supplementing information according to the original track distance and the corrected track distance, and iterating the initial estimated signing time according to the first time supplementing information, the second time supplementing information and the third time supplementing information to obtain the latest estimated signing time.

Optionally, in a sixth implementation manner of the first aspect of the present invention, after the determining whether the initial logistics track query result has an updated state, the method further includes: if not, generating a logistics track map according to the initial logistics track query result; drawing the estimated signing time of the spam in the logistics track graph to obtain an estimated signing time graph of the logistics track; and sending the logistics track expected signing time chart to the query terminal.

The second aspect of the present invention provides an order sign-up time prediction query device, comprising: the system comprises an acquisition and query module, a query module and a control module, wherein the acquisition and query module is used for acquiring the waybill information sent by a query terminal, inputting the waybill information into a preset logistics track model for query, and obtaining an initial logistics track query result; the identification calculation module is used for identifying the initial time information of the initial logistics track query result, and calculating according to the initial time information to obtain the spam estimated signing time; the judging module is used for judging whether the initial logistics track inquiry result has an updated state or not; the updating calculation module is used for updating the initial logistics track inquiry result in real time if yes, obtaining a latest logistics track inquiry result, and calculating according to the latest logistics track inquiry result to obtain latest expected signing time; and the replacement sending module is used for replacing the spam expected signing time with the latest expected signing time and sending the latest expected signing time to the query terminal.

Optionally, in a first implementation manner of the second aspect of the present invention, the acquiring query module includes: the first acquisition unit is used for acquiring the waybill number information sent by the query terminal and acquiring historical logistics track data; the extraction unit is used for extracting logistics track characteristic data from the historical logistics track data, wherein the logistics track characteristic data at least comprises track segment characteristics and operation period characteristics; the first generation unit is used for generating a plurality of track samples, wherein each track sample comprises logistics track characteristic data and logistics track arrival time; the training unit is used for training the track sample into a logistics track model; and the calling input unit is used for calling the logistics track model, inputting the waybill number information into the logistics track model for inquiring, and obtaining an initial logistics track inquiring result.

Optionally, in a second implementation manner of the second aspect of the present invention, the identification calculation module includes: the identification prediction unit is used for identifying a plurality of track nodes of the initial logistics track query result and predicting a plurality of execution durations corresponding to the track nodes respectively; the acquisition and identification unit is used for respectively acquiring the table calendar information of each track node and identifying the fake-release information in the table calendar information; and the accumulation unit is used for accumulating the fake release information and the execution time lengths based on the starting time information to obtain the spam estimated signing time.

Optionally, in a third implementation manner of the second aspect of the present invention, the identifying predicting unit is specifically configured to identify a plurality of track nodes of the initial logistic track query result; collecting historical order data between two adjacent track nodes, and calculating historical average distribution time length according to the historical order data; and respectively predicting a plurality of execution time lengths corresponding to the track nodes according to the historical average distribution time lengths.

Optionally, in a fourth implementation manner of the second aspect of the present invention, the update calculation module includes: the second acquisition unit is used for acquiring logistics scanning record information transmitted by the scanning terminal in real time in a logistics track model if the logistics scanning record information is positive, wherein the logistics scanning record information comprises scanning time and scanning network points; the sorting identification unit is used for sorting the plurality of logistics scanning record information corresponding to the waybill number information according to the scanning time, and identifying the logistics scanning record information with the latest scanning time to obtain target scanning record information; the second generation unit is used for generating a latest logistics track query result according to the target scanning record information; and the calculating unit is used for calculating the latest logistics track inquiry result according to the scanning time corresponding to the target scanning record information to obtain the latest expected signing time.

Optionally, in a fifth implementation manner of the second aspect of the present invention, the computing unit is specifically configured to obtain, in real time, speed-affecting feature data, where the speed-affecting feature data includes real-time weather data and real-time road condition data, and calculate, according to a scanning time corresponding to the target scanning record information, the latest logistics track query result to obtain an initial expected signing time; identifying current back bill state information and carrying force information of the scanning network points, calculating first time supplementing information according to the back bill state information and the carrying force information, and calculating second time supplementing information according to the real-time weather data; updating path information according to the real-time road condition data to obtain latest path information, and correcting the original track distance of the scanning network point according to the latest path information to obtain corrected track distance; and calculating third time supplementing information according to the original track distance and the corrected track distance, and iterating the initial estimated signing time according to the first time supplementing information, the second time supplementing information and the third time supplementing information to obtain the latest estimated signing time.

Optionally, in a sixth implementation manner of the second aspect of the present invention, the method further includes: the generation module is used for generating a logistics track map according to the initial logistics track query result if not; the drawing module is used for drawing the estimated closing time of the spam in the logistics track graph to obtain a logistics track estimated closing time graph; and the sending module is used for sending the logistics track expected signing time chart to the query terminal.

A third aspect of the present invention provides an order issuance time prediction inquiry apparatus, comprising: a memory and at least one processor, the memory having instructions stored therein; at least one of the processors invokes the instructions in the memory to cause the order placement time forecast query device to perform the steps of the order placement time forecast query method of any of the above.

A fourth aspect of the present invention provides a computer readable storage medium having instructions stored thereon which when executed by a processor implement the steps of the order placement time prediction query method of any one of the above.

According to the technical scheme, the latest logistics track inquiry result is obtained by updating the initial logistics track inquiry result in real time, the latest expected signing time is obtained by calculating according to the latest logistics track inquiry result, the expected signing time of a logistics order can be dynamically updated according to the actual transportation condition, the expected accuracy of the logistics order signing time is improved, the spam expected signing time is obtained by calculating the starting time information, the spam expected signing time is provided, and when the initial logistics track inquiry result has no updated state, the spam expected signing time is sent to the inquiry terminal, the expected reliability of the order signing time is improved, the overall settlement efficiency and the company operation efficiency of the logistics order are improved, and the experience of both users and network points is improved.

Drawings

FIG. 1 is a first flowchart of an order entry time prediction query method according to an embodiment of the present invention;

FIG. 2 is a second flowchart of an order placement time prediction query method according to an embodiment of the present invention;

FIG. 3 is a third flowchart of a method for predicting and querying an order placement time according to an embodiment of the present invention;

FIG. 4 is a fourth flowchart of a method for predicting and querying order placement time according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a device for predicting and querying order receiving time according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of another configuration of an apparatus for predicting and querying an order placement time according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of an order sign-up time prediction query device according to an embodiment of the present invention.

Detailed Description

The invention provides a method, a device, equipment and a storage medium for predicting and inquiring order signing time, which can dynamically update the predicting and signing time of a logistics order according to actual transportation conditions, improve the predicting accuracy of the logistics order signing time, improve the overall settlement efficiency of the logistics order and the operation efficiency of a company, improve the experience of both users and network sites, simultaneously have the predicting of signing time and the predicting reliability of the order signing time.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, a specific flow of an embodiment of the present invention is described below, referring to fig. 1, and an embodiment of an order placement time prediction query method in an embodiment of the present invention includes:

101. acquiring the waybill number information sent by the query terminal, inputting the waybill number information into a preset logistics track model for query, and obtaining an initial logistics track query result;

In this embodiment, the waybill information input by the user is acquired from the query terminal, the preset logistics track model is used, the acquired waybill information is used as input, the query operation is performed, the logistics track model is a model trained in advance, and generally based on historical data and an algorithm, the corresponding logistics information can be deduced according to the waybill number, and the initial logistics track query result is obtained.

102. Identifying the initial time information of the initial logistics track query result, and calculating according to the initial time information to obtain the estimated signature time of the spam;

in this embodiment, the time information of the first scan record is extracted from the initial logistics track query result as the starting time, if the query result is time-ordered, the time of the first scan record can be directly obtained, if the query result is not time-ordered, all scan records need to be traversed, the earliest time is found as the starting time, the starting time is used as the reference, and the relevant transportation data and the experience rules are combined to predict and calculate, so as to obtain the spam predicted signing time, and the calculation formula is: the method for setting the preset time can comprise the steps of estimating the average transportation time of the goods among different transportation nodes and considering factors such as distance, transportation mode, traffic condition and the like; taking common delay conditions such as weather influence, flight cancellation, customs clearance and the like into consideration, and giving corresponding adjustment; the service level, the historical data and the index of the logistics express company are considered, and evaluation and correction are carried out, so that the preset time is set.

103. Judging whether the initial logistics track inquiry result has an updated state or not;

in this embodiment, the obtained latest logistics track query result is compared with the last query result stored previously, the time and information of each scan record are identified, if a new scan record appears in the latest query result, the logistics track is updated, and besides the scan record, the change of the transportation state can be compared, for example, if the transportation state in the query result is changed from "in-transit" to "in-transit", the logistics track is updated, whether the update state exists is judged according to the comparison result of the scan record and the transportation state, and if any one of the scan record or the transportation state changes, the logistics track can be considered to be updated.

104. If yes, updating the initial logistics track inquiry result in real time to obtain a latest logistics track inquiry result, and calculating according to the latest logistics track inquiry result to obtain the latest expected signing time;

in this embodiment, the initial logistics track query result is updated in real time, the latest logistics track query result is obtained according to the process of real-time update, the acquired data is ensured to be the latest updated information, and the latest expected signing time is calculated based on the latest logistics track query result and related information.

105. Replacing the spam predicted signing time with the latest predicted signing time, and sending the latest predicted signing time to the query terminal;

in this embodiment, first, an original spam expected signing time needs to be obtained, which is an initial estimated time provided in a logistics track query result, and according to a latest logistics track query result and related information, the latest expected signing time is calculated, the latest estimated signing time obtained by calculation replaces the original spam expected signing time, the latest estimated signing time after update is sent to a query terminal, and notification can be performed by means of a short message, an email, a mobile phone application program, and the like.

In the embodiment of the invention, the latest logistics track inquiry result is obtained by updating the initial logistics track inquiry result in real time, the latest expected signing time is obtained by calculating according to the latest logistics track inquiry result, the expected signing time of a logistics order can be dynamically updated according to the actual transportation condition, the expected accuracy of the logistics order signing time is improved, the spam expected signing time is obtained by calculating the starting time information, the spam expected signing time is provided, and when the initial logistics track inquiry result has no updated state, the spam expected signing time is sent to the inquiry terminal, the reliability of the order signing time is improved, the overall settlement efficiency of the logistics order and the operation efficiency of a company are improved, and the experience of both users and sites is improved.

Referring to fig. 2, a second embodiment of the method for predicting an order placement time according to the present invention includes:

201. acquiring waybill number information sent by a query terminal, and acquiring historical logistics track data;

in this embodiment, the waybill information input by the user is obtained, and the logistics company records and manages the logistics transportation process through its own information system, including the scanning information and the storage information of each link, so that the historical logistics track data can be obtained by data interaction with the system of the logistics company.

202. Extracting logistics track characteristic data from historical logistics track data, wherein the logistics track characteristic data at least comprises track segment characteristics and operation period characteristics;

in this embodiment, the track segment features refer to a continuous time and space transport path in the logistics track, and in order to extract track segment feature data, the following aspects can be considered: distance characteristics: and calculating the total distance or the average distance of the track fragments to measure the running condition of the goods on the journey, and the time characteristics are as follows: calculating the total time or average time of the track segments to represent the time-consuming condition of the cargo on the stretch of travel, and the speed characteristics: the change of the transport speed of the goods on different road sections is known by calculating the running speed of the track section, such as the average speed, the maximum speed and the minimum speed, and the path characteristics are as follows: extracting road or geographic position information of the track segment for analyzing a specific path of cargo transportation;

Operating time period characteristics: the operation period feature mainly refers to a feature of an operation period in a logistics track, and in order to extract operation period feature data, the following aspects can be considered: start time and end time: recording the start time and the end time of each track segment so as to determine the transportation condition of goods in different time periods, and operating time windows: dividing a day into a plurality of time periods, and counting the transportation condition of goods in each time period, such as the morning, noon, afternoon or evening, and the like, wherein the peak transportation period is as follows: identifying a time period with a higher freight volume for analyzing the transportation condition of the freight under high load;

by extracting the track segment characteristic data and the operation time period characteristic data, the driving distance, time consumption, speed change and distribution condition of the transportation time period in the logistics transportation process can be better known.

203. Generating a plurality of track samples, wherein each track sample comprises logistics track characteristic data and logistics track arrival time;

in this embodiment, according to the historical logistics track data and the extracted track feature data, a plurality of track samples may be generated, where the track samples may include a series of feature data, such as distance features, time features, speed features, path features, and the like, each track sample represents a transportation process of a cargo, reflects a movement track of the cargo in space and time, and includes, in addition to the logistics track feature data, a delivery duration of the logistics track, where the delivery duration refers to a total time elapsed from the cargo being sent to a final delivery destination, and may be used as a target variable or tag for measuring efficiency and accuracy of logistics transportation;

The process of generating a plurality of track samples needs to use historical logistics data and related characteristics to carry out training and model establishment, a machine learning method such as a regression model or a deep learning model can be adopted, the delivering time of an unknown track sample is predicted through modeling of the characteristic data and delivering time, and the generated plurality of track samples can be used for logistics planning, prediction, optimization and other applications.

204. Training a logistics track model by utilizing a track sample;

in this embodiment, a certain amount of sample data of the logistics track needs to be collected, where the sample data includes feature data of the logistics track and corresponding labels (for example, the delivering time length), the data can be obtained from a historical logistics record, so as to ensure quality and accuracy of the data, before model training is performed, feature engineering processing needs to be performed on the sample data of the logistics track, which includes selecting proper features, preprocessing and converting the features so as to better express information of the logistics track, selecting proper machine learning algorithm or deep learning model according to requirements of tasks and features of the data to construct a logistics track model, and a common machine learning algorithm includes linear regression, decision tree, random forest, support vector machine, and the like, where structures such as a cyclic neural network (RNN) or long-short term memory network (LSTM) can be considered in the deep learning model, so as to adapt to features of sequence data modeling;

The method comprises the steps of dividing prepared track sample data into a training set and a verification set, training a selected model by using the training set, continuously adjusting model parameters according to a loss function and an optimization algorithm in the training process to minimize the difference between a predicted value and an actual label, simultaneously evaluating and optimizing the model by using the verification set to ensure good generalization capability of the model, evaluating the performance of the model by using the verification set, optimizing the model, including adjusting the super parameters of the model, trying different characteristic combinations, model structures and the like, commonly used evaluation indexes comprise Root Mean Square Error (RMSE), average absolute percentage error (MAPE) and the like, selecting proper evaluation indexes according to the requirements of specific tasks, and after the model training is completed and the model is fully evaluated, applying the model parameters to the prediction and the inference of unknown track data, and outputting corresponding prediction results, such as predicting the delivery time length of the track sample by inputting new track sample data.

205. Invoking a logistics track model, inputting the waybill number information into the logistics track model for inquiring, and obtaining an initial logistics track inquiring result;

in this embodiment, first, the information of the waybill to be queried needs to be obtained, the user may provide the corresponding waybill number by inputting or other modes, the obtained information of the waybill number is input into the trained logistics track model to perform query operation, the query process involves an inference stage of the model, the model outputs a predicted logistics track result according to the input information of the waybill number, and the query result may include some information related to the waybill, such as the current position, the transportation state, the predicted arrival time, etc. of the goods according to the design and training of the logistics track model.

206. Identifying a plurality of track nodes of the initial logistics track query result;

in this embodiment, first, an initial logistics track query result needs to be parsed, where the query result includes information of a plurality of track nodes, in the logistics field, the track nodes generally refer to key events or state changes in the cargo transportation process, for example, shipping, transit, arrival, etc., each track node includes related time, place and description information, by parsing the query result, a plurality of track nodes in the track nodes can be identified one by one, each node can appear in the query result in the form of independent records or entries, so that information of different nodes can be extracted through corresponding data processing technologies, such as text segmentation, regular expression matching, etc., once the plurality of track nodes are identified, information of each node can be analyzed, including time, place and description information in the interpretation nodes, and by comparing time sequence and place changes between the nodes, specific path and state changes of the cargo in the transportation process can be known.

207. Collecting historical order data between two adjacent track nodes, and calculating historical average distribution time length according to the historical order data;

In this embodiment, first, historical order data between two adjacent track nodes needs to be collected, which includes a plurality of order distribution records from a certain initial track node to a next track node, the order data can be obtained from a streaming system, a database or other related records, the time information of distribution is extracted from the historical order data, each order record generally includes time stamps such as order creation time and order distribution completion time, the distribution duration of each order can be obtained by calculating the difference between the two time stamps, the historical order distribution duration between all the two adjacent track nodes is accumulated and divided by the number of orders, and the historical average distribution duration can be calculated, which reflects the time required for averaging between adjacent nodes in the past order distribution process, and the calculated historical average distribution duration is based on the calculated historical average distribution duration.

208. Respectively predicting a plurality of execution time lengths corresponding to a plurality of track nodes according to a plurality of historical average distribution time lengths;

in this embodiment, a plurality of historical average delivery durations are respectively allocated to a plurality of track nodes correspondingly, and each track node obtains a corresponding execution duration.

209. Respectively acquiring the table calendar information of each track node, and identifying the fake-putting information in the table calendar information;

in this embodiment, for each track node, the corresponding table calendar information needs to be acquired, where the table calendar information may include specific arrangements such as a working day, a rest day, and a special date, and after the table calendar information is acquired, further analysis needs to be performed on the information to identify the vacation information therein, which may include a legal holiday of the country, a holiday additionally arranged by a company, or other special holidays.

210. Accumulating the fake release information and the execution time periods based on the initial time information to obtain the spam predicted signing time;

in this embodiment, first, a starting time and a plurality of execution durations are acquired, and for each execution duration, the starting time is accumulated to obtain an estimated completion time, then, the estimated completion time is eliminated, according to calendar information or other related information of the shift table, which dates are rest days or special holidays are determined, and these dates are eliminated from the estimated completion time, and finally, the obtained result is an estimated signature time of the spam, i.e. the estimated completion time after the holiday date and the execution duration are considered.

According to the embodiment of the invention, the logistics track model is called to inquire the initial logistics track inquiry result, the execution time can be estimated according to the historical average distribution time, the receipt time can be estimated according to the execution time and the fake release information, and the reliability of the order receipt time estimation is improved.

Referring to fig. 3, a third embodiment of a method for predicting an order placement time according to an embodiment of the present invention includes:

301. judging whether the initial logistics track inquiry result has an updated state or not;

302. If yes, acquiring logistics scanning record information transmitted in real time by a scanning terminal in a logistics track model, wherein the logistics scanning record information comprises scanning time and scanning network points;

in this embodiment, the logistics track model is used for tracking the logistics transportation process, the logistics scanning record information can be obtained in real time in the logistics network through the logistics track model, and help to track the position and state change of goods, the scanning terminal refers to equipment for scanning logistics packages or goods labels, the scanning terminal can read the related information of the packages through scanning bar codes, two-dimensional codes or other identification technologies and transmit the related information of the packages to the logistics system, the scanning terminal can transmit the scanned logistics package information to the logistics system or cloud server in real time, so that the logistics information can be updated in time, and can be further processed and queried, and the logistics scanning record information comprises two main aspects: scanning time: the time stamp of the scanning operation is recorded, the time point of each scanning is recorded, and the mesh point is scanned: the physical distribution network point or site where the scanning operation is located records the geographical position or specific network point number of each scanning.

303. Sorting a plurality of logistics scanning record information corresponding to the waybill number information according to the scanning time, and identifying the logistics scanning record information with the latest scanning time to obtain target scanning record information;

In this embodiment, each logistics package has a unique waybill number for identification, in the logistics system, the logistics scanning record information of the package can be queried according to the waybill number, for a specific waybill number, there may be multiple pieces of logistics scanning record information, which represent the situation that the package is scanned at different time points, in order to determine the latest logistics scanning record information, the multiple pieces of logistics scanning record information corresponding to the waybill number need to be sorted according to the scanning time, the latest records are sorted according to the sequence of the date and the time, so that the latest records are ensured to be sorted at the end, and the last record after sorting is the latest logistics scanning record information of the scanning time, which is the target scanning record information, and the latest scanned time and the scanning website information of the package can be obtained therefrom.

304. Generating a latest logistics track query result according to the target scanning record information;

in this embodiment, the target scan record information includes the latest logistics scan time and scan dot information, assuming that the scan time is T and the scan dot is N, the logistics track query result is generated according to the scan record information of the logistics package, it can show the whole process from sending the logistics package to the last scan, and reflect the transportation state and the position change of the package, in order to generate the latest logistics track query result, the target scan record information can be used as a starting point, and the logistics scan record information after the waybill number is sequentially searched from the scan time T of the target scan record, and these records are arranged according to the sequence of the scan time, so as to obtain the latest transportation track of the logistics package.

305. Acquiring speed influence characteristic data in real time, wherein the speed influence characteristic data comprises real-time weather data and real-time road condition data, and calculating a latest logistics track inquiry result according to the scanning time corresponding to target scanning record information to obtain initial expected signing time;

in this embodiment, the real-time weather data refer to the weather conditions of the current area, such as temperature, precipitation, wind power, etc., and these data may be obtained by a weather forecast service or a weather station, the real-time road condition data refer to the traffic conditions of the road, such as traffic flow, congestion, accidents, etc., these data may be obtained by a traffic management department or a traffic navigation application program, the target scan record information includes the last scan time of the logistic package, and the initial expected sign-on time is calculated according to the scan time corresponding to the target scan record information.

306. Identifying current back bill state information and carrying force information of a scanning net point, calculating first time compensating information according to the back bill state information and the carrying force information, and calculating second time compensating information according to real-time weather data;

in this embodiment, the back form status information refers to the current back form status of the express package of the scanning website, the carrying capacity information refers to the current capability of the scanning website for carrying the logistic package, usually, the carrying quantity or weight is taken as a measurement standard, the first time supplementing information is the first predicted supplementing time of the scanning website calculated according to the back form status information and the carrying capacity information, the specific calculation method can be estimated based on factors such as the number of back forms of the package, the carrying capacity of the website, and the service processing efficiency, the real-time weather data refers to the current weather conditions of the area where the scanning website is located, such as temperature, precipitation, wind power, etc., the data can be acquired through weather forecast service or weather stations, the second time supplementing information is the second predicted supplementing time of the scanning website calculated according to the real-time weather data, the specific calculation method can be determined according to different service requirements, for example, the express delivery speed or the processing time is adjusted according to the weather conditions.

307. Updating the path information according to the real-time road condition data to obtain the latest path information, and correcting the original track distance of the scanning network point according to the latest path information to obtain a corrected track distance;

in this embodiment, the real-time road condition data refers to real-time information of road traffic conditions, including congestion degree, traffic flow condition, and the like, and these data may be obtained through channels such as a monitoring system or navigation software of a traffic management department, the path information refers to route planning information of an original track of a scanning website, which may be generated according to preset conditions or historical data, the path information generally includes a starting position, a passing place, a final destination, and the like, the path information is updated according to the real-time road condition data, that is, the route is re-planned according to the actual road condition, so as to obtain more accurate path information, the original track distance of the scanning website is corrected according to the latest path information, which means that the actual running route is compared with the original route, so as to calculate the corrected track distance, and the corrected track distance can more accurately reflect the actual mileage undergone by the express package in the transportation process.

308. Calculating third time supplementing information according to the original track distance and the corrected track distance, and iterating the initial estimated signing time according to the first time supplementing information, the second time supplementing information and the third time supplementing information to obtain the latest estimated signing time;

In this embodiment, third time-compensating information is calculated according to the original track distance and the corrected track distance, and the latest expected signing time is obtained by iterative calculation based on the first time-compensating information, the second time-compensating information and the third time-compensating information.

In the embodiment of the invention, the specific calculation method of the latest expected signing time is based on the initial expected signing time and further estimated according to the average speed and the path length of the logistics transportation and real-time weather and road condition factors, so that the expected accuracy of the logistics order signing time is improved, the overall settlement efficiency and the company operation efficiency of the logistics order are improved, and the experience of both users and network points is improved.

Referring to fig. 4, a fourth embodiment of the method for predicting an order placement time according to the present invention includes:

401. judging whether the initial logistics track inquiry result has an updated state or not;

in this embodiment, it is checked whether the initial logistic track query result has new scan record information or status update.

402. If not, generating a logistics track map according to the initial logistics track query result;

in this embodiment, if there is no update, the scan record information and the related data in the initial logistics track query result are used to generate a logistics track map, where the logistics track map is used to show the track and nodes of the goods in the transportation process, and the logistics track map may include information such as the number of the bill, the scan time, the scan site, and the like.

403. Drawing the estimated signing time of the spam in the logistics track graph to obtain an estimated signing time graph of the logistics track;

in this embodiment, the calculated spam expected receipt time information is drawn and added to the corresponding position in the logistic track diagram.

404. Sending the logistics track expected signing time chart to a query terminal;

in this embodiment, the generated expected signing time map of the logistics track is sent to the query terminal, so that the user can view the logistics track and the expected signing time information.

In the embodiment of the invention, when the initial logistics track inquiry result has no updated state, the logistics track expected signing time chart is sent to the inquiry terminal, so that the reliability of the order signing time is improved, a user can check the logistics track and the expected signing time information, the overall settlement efficiency and the company operation efficiency of the logistics order are improved, and the experience of the user and the two parties of the website is improved.

The method for inquiring the expected order receiving time in the embodiment of the present invention is described above, and the apparatus for inquiring the expected order receiving time in the embodiment of the present invention is described below, referring to fig. 5, an embodiment of the apparatus for inquiring the expected order receiving time in the embodiment of the present invention includes:

The acquiring and inquiring module 501 is configured to acquire waybill number information sent by an inquiring terminal, input the waybill number information into a preset logistics track model for inquiry, and obtain an initial logistics track inquiring result;

the identifying and calculating module 502 is configured to identify starting time information of an initial logistics track query result, and calculate according to the starting time information to obtain a spam predicted signing time;

a judging module 503, configured to judge whether the initial logistics track query result has an update status;

the update calculation module 504 is configured to update the initial logistics track query result in real time if yes, obtain a latest logistics track query result, and calculate according to the latest logistics track query result to obtain a latest expected signing time;

the replacement sending module 505 is configured to replace the spam expected signing time with the latest expected signing time, and send the latest expected signing time to the query terminal.

In this embodiment, the latest logistics track query result is obtained by updating the initial logistics track query result in real time, and calculating is performed according to the latest logistics track query result to obtain the latest expected signing time, so that the expected signing time of a logistics order can be dynamically updated according to the actual transportation condition, the expected accuracy of the logistics order signing time is improved, the spam expected signing time is obtained by calculating the starting time information, the spam expected signing time is provided, and when the initial logistics track query result has no updated state, the spam expected signing time is sent to the query terminal, the reliability of the order signing time is improved, the overall settlement efficiency of the logistics order and the operation efficiency of a company are improved, and the experience of both users and sites is improved.

Referring to fig. 6, another embodiment of the apparatus for predicting an order placement time according to an embodiment of the present invention includes:

a replacement sending module 505, configured to replace the spam expected signing time with the latest expected signing time, and send the latest expected signing time to the query terminal;

in this embodiment, the acquisition inquiry module 501 includes: the first obtaining unit 5011 is used for obtaining the waybill number information sent by the query terminal and obtaining historical logistics track data; an extracting unit 5012 for extracting logistics track characteristic data from the historical logistics track data, wherein the logistics track characteristic data at least comprises track segment characteristics and operation period characteristics; a first generating unit 5013, configured to generate a plurality of track samples, where each track sample includes logistics track feature data and a logistics track arrival duration; a training unit 5014 for training as a logistic track model using the track samples; the calling input unit 5015 is used for calling the logistics track model, inputting the waybill number information into the logistics track model for inquiring, and obtaining an initial logistics track inquiring result.

In this embodiment, the identification calculation module 502 includes: the identifying and predicting unit 5021 is used for identifying a plurality of track nodes of the initial logistics track query result and predicting a plurality of execution durations corresponding to the track nodes respectively; the acquiring and identifying unit 5022 is used for respectively acquiring the table calendar information of each track node and identifying the fake-putting information in the table calendar information; the accumulating unit 5023 is configured to accumulate the spurious information and the execution time periods based on the start time information to obtain the spam expected signing time.

In this embodiment, the identifying predicting unit 5021 is specifically configured to identify a plurality of track nodes of the initial logistics track query result; collecting historical order data between two adjacent track nodes, and calculating historical average distribution time length according to the historical order data; and respectively predicting a plurality of execution time lengths corresponding to the track nodes according to the historical average distribution time lengths.

In this embodiment, the update calculation module 504 includes: the second obtaining unit 5041 is configured to obtain, if yes, physical distribution scanning record information transmitted in real time by the scanning terminal in the physical distribution track model, where the physical distribution scanning record information includes a scanning time and a scanning website; the sorting identification unit 5042 is configured to sort the plurality of logistics scanning record information corresponding to the waybill number information according to the scanning time, and identify the logistics scanning record information with the latest scanning time to obtain target scanning record information; a second generating unit 5043, configured to generate a latest logistics track query result according to the target scan record information; the calculating unit 5044 is configured to calculate a latest logistics track query result according to the scanning time corresponding to the target scanning record information, so as to obtain a latest expected signing time.

In this embodiment, the calculating unit 5044 is specifically configured to obtain, in real time, speed-affecting feature data, where the speed-affecting feature data includes real-time weather data and real-time road condition data, and calculate, according to a scan time corresponding to the target scan record information, a latest logistics track query result, to obtain an initial expected signing time; identifying current back bill state information and carrying force information of a scanning net point, calculating first time compensating information according to the back bill state information and the carrying force information, and calculating second time compensating information according to real-time weather data; updating the path information according to the real-time road condition data to obtain the latest path information, and correcting the original track distance of the scanning network point according to the latest path information to obtain a corrected track distance; and calculating third time supplementing information according to the original track distance and the corrected track distance, and iterating the initial estimated signing time according to the first time supplementing information, the second time supplementing information and the third time supplementing information to obtain the latest estimated signing time.

In this embodiment, further comprising: a generating module 506, configured to generate a logistics trajectory graph according to the initial logistics trajectory query result if not; the drawing module 507 is configured to draw the spam predicted signing time in the logistic track map, so as to obtain a logistic track predicted signing time map; and the sending module 508 is used for sending the logistics track expected signing time chart to the query terminal.

The order placement time prediction query device in the embodiment of the present invention is described in detail above in terms of the modularized functional entity in fig. 5 and fig. 6, and the order placement time prediction query device in the embodiment of the present invention is described in detail below in terms of hardware processing.

Fig. 7 is a schematic diagram of an order placement time prediction query device according to an embodiment of the present invention, where the order placement time prediction query device 600 may have a relatively large difference due to different configurations or capabilities, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing applications 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored on the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the order placement time forecast query device 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the order entry time forecast query device 600 to implement the steps of the order entry time forecast query method provided by the above-described method embodiments.

The order placement time forecast query device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, etc. It will be appreciated by those skilled in the art that the order entry time forecast query apparatus structure illustrated in FIG. 7 is not limiting of an order entry time forecast query apparatus, and may include more or fewer components than illustrated, or may be combined with certain components, or a different arrangement of components.

The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, or a volatile computer readable storage medium, having stored therein instructions that, when executed on a computer, cause the computer to perform the steps of a method for predicting an order pick-up time.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system or apparatus and unit described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Finally, it should be noted that: the foregoing is merely a preferred example of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An order sign-up time prediction query method, comprising:

acquiring the waybill number information sent by the query terminal, and inputting the waybill number information into a preset logistics track model for query to obtain an initial logistics track query result;

identifying the initial time information of the initial logistics track query result, and calculating according to the initial time information to obtain the spam predicted signing time;

judging whether the initial logistics track inquiry result has an updated state or not;

if yes, updating the initial logistics track inquiry result in real time to obtain a latest logistics track inquiry result, and calculating according to the latest logistics track inquiry result to obtain the latest expected signing time;

and replacing the spam expected signing time with the latest expected signing time, and sending the latest expected signing time to the query terminal.

2. The method for predicting and inquiring order signing time according to claim 1, wherein said obtaining the waybill number information sent by the inquiring terminal, inputting the waybill number information into a preset logistics track model for inquiring, obtaining an initial logistics track inquiring result, comprises:

Acquiring waybill number information sent by a query terminal, and acquiring historical logistics track data;

extracting logistics track characteristic data from the historical logistics track data, wherein the logistics track characteristic data at least comprises track segment characteristics and operation period characteristics;

generating a plurality of track samples, wherein each track sample comprises logistics track characteristic data and logistics track arrival time;

training the track sample into a logistics track model;

and calling a logistics track model, and inputting the waybill information into the logistics track model for inquiring to obtain an initial logistics track inquiring result.

3. The method for predicting and inquiring order receiving time according to claim 1, wherein said identifying the start time information of the initial logistics track inquiring result, and calculating according to the start time information, obtaining the spam predicted receiving time, comprises:

identifying a plurality of track nodes of the initial logistics track query result, and predicting a plurality of execution durations corresponding to the track nodes respectively;

respectively acquiring the table calendar information of each track node, and identifying the fake-releasing information in the table calendar information;

And accumulating the fake-release information and a plurality of execution time lengths based on the starting time information to obtain the spam predicted signing time.

4. The method for predicting and querying order placement time as recited in claim 3, wherein said identifying a plurality of trace nodes of said initial logistics trace query result and predicting a plurality of execution durations respectively corresponding to a plurality of said trace nodes comprises:

identifying a plurality of track nodes of the initial logistics track query result;

collecting historical order data between two adjacent track nodes, and calculating historical average distribution time length according to the historical order data;

and respectively predicting a plurality of execution time lengths corresponding to the track nodes according to the historical average distribution time lengths.

5. The method for predicting and inquiring the order signing time according to claim 1, wherein if yes, updating the initial logistics track inquiring result in real time to obtain a latest logistics track inquiring result, and calculating according to the latest logistics track inquiring result to obtain the latest predicted signing time, comprising:

if yes, acquiring logistics scanning record information transmitted in real time by a scanning terminal in a logistics track model, wherein the logistics scanning record information comprises scanning time and scanning network points;

Sorting a plurality of logistics scanning record information corresponding to the waybill information according to the scanning time, and identifying the logistics scanning record information with the latest scanning time to obtain target scanning record information;

generating a latest logistics track query result according to the target scanning record information;

and calculating the latest logistics track inquiry result according to the scanning time corresponding to the target scanning record information to obtain the latest expected signing time.

6. The method for predicting and inquiring the order receiving time according to claim 5, wherein the calculating the latest logistics track inquiring result according to the scanning time corresponding to the target scanning record information to obtain the latest predicted receiving time comprises:

acquiring speed influence characteristic data in real time, wherein the speed influence characteristic data comprises real-time weather data and real-time road condition data, and calculating the latest logistics track inquiry result according to the scanning time corresponding to the target scanning record information to obtain initial expected signing time;

identifying current back bill state information and carrying force information of the scanning network points, calculating first time supplementing information according to the back bill state information and the carrying force information, and calculating second time supplementing information according to the real-time weather data;

Updating path information according to the real-time road condition data to obtain latest path information, and correcting the original track distance of the scanning network point according to the latest path information to obtain corrected track distance;

and calculating third time supplementing information according to the original track distance and the corrected track distance, and iterating the initial estimated signing time according to the first time supplementing information, the second time supplementing information and the third time supplementing information to obtain the latest estimated signing time.

7. The method of claim 1, wherein after determining whether the initial logistic track query result has an updated status, further comprising:

if not, generating a logistics track map according to the initial logistics track query result;

drawing the estimated signing time of the spam in the logistics track graph to obtain an estimated signing time graph of the logistics track;

and sending the logistics track expected signing time chart to the query terminal.

8. An order placement time prediction inquiry apparatus, comprising:

the system comprises an acquisition and query module, a query module and a control module, wherein the acquisition and query module is used for acquiring the waybill information sent by a query terminal, inputting the waybill information into a preset logistics track model for query, and obtaining an initial logistics track query result;

The identification calculation module is used for identifying the initial time information of the initial logistics track query result, and calculating according to the initial time information to obtain the spam estimated signing time;

the judging module is used for judging whether the initial logistics track inquiry result has an updated state or not;

the updating calculation module is used for updating the initial logistics track inquiry result in real time if yes, obtaining a latest logistics track inquiry result, and calculating according to the latest logistics track inquiry result to obtain latest expected signing time;

and the replacement sending module is used for replacing the spam expected signing time with the latest expected signing time and sending the latest expected signing time to the query terminal.

9. An order placement time prediction inquiry apparatus, characterized in that the order placement time prediction inquiry apparatus comprises: a memory and at least one processor, the memory having instructions stored therein;

at least one of the processors invokes the instructions in the memory to cause the order placement time forecast query device to perform the steps of the order placement time forecast query method of any of claims 1-7.

10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the steps of the order placement time prediction query method of any of claims 1-7.