CN109948983A - Logistics price prediction technique, device, electronic equipment, storage medium - Google Patents

Logistics price prediction technique, device, electronic equipment, storage medium Download PDF

Info

Publication number
CN109948983A
CN109948983A CN201910216638.1A CN201910216638A CN109948983A CN 109948983 A CN109948983 A CN 109948983A CN 201910216638 A CN201910216638 A CN 201910216638A CN 109948983 A CN109948983 A CN 109948983A
Authority
CN
China
Prior art keywords
price
prediction
piecewise interval
logistics
iteration
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910216638.1A
Other languages
Chinese (zh)
Inventor
刘乃广
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Manyun Software Technology Co Ltd
Original Assignee
Jiangsu Manyun Software Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Manyun Software Technology Co Ltd filed Critical Jiangsu Manyun Software Technology Co Ltd
Priority to CN201910216638.1A priority Critical patent/CN109948983A/en
Publication of CN109948983A publication Critical patent/CN109948983A/en
Pending legal-status Critical Current

Links

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention provides a kind of logistics price prediction technique, device, electronic equipment, storage medium, and logistics price prediction technique includes: according to history logistics order data training logistics price prediction model；Obtain the departure place and destination in real-time logistics order data；Segment iteration is carried out based on the departure place and destination, in each segment iteration, it is fixed a price based on logistics price prediction model according to the prediction of the segment iteration and the secondary iteration of at least partly real-time logistics order data prediction, so that it is determined that the prediction unit distance in the piecewise interval of the secondary segment iteration and the piecewise interval is fixed a price；And at least provide each piecewise interval for corresponding to the real-time logistics order data, the prediction unit distance price in each piecewise interval and total prediction price.Method and device provided by the invention improves the accuracy and flexibility of Forecast of Logistics price.

Description

Logistics price prediction technique, device, electronic equipment, storage medium
Technical field
The present invention relates to Internet technical field more particularly to a kind of logistics price prediction technique, device, electronic equipment, Storage medium.
Background technique
It is universal with intelligent terminal with the development of internet technology, it has come into being various convenient for people's life Service business, such as shipping dispense business.The price that shipping dispenses business is generated generally according to dispatching apart from this dimension, or It is generated according to the history average price of current route.
However, in practical applications, there are many factor for influencing price, fix a price according only to distance or history average price pre- Survey, to each feature of history conclusion of the business order sample, utilization rate is lower, can not also restore well route price it is each because Element.In addition, the route sparse for sample, history does not have the transport order of current route, and this method just places one's entire reliance upon Artificial backstage operation configuration, can not intelligently, accurately provide Recommended Price.Secondly, current price prediction dynamic compared with It is weak, also can not automatically derived segmentation price, number of fragments, segmentation unit price etc., to be difficult to Accurate Prediction logistics unit price, thus Logistics platform operation difficulty is caused to increase.
Summary of the invention
The present invention provides a kind of logistics price prediction technique, device, electricity to overcome defect existing for above-mentioned the relevant technologies Sub- equipment, storage medium, and then one is overcome caused by the limitation and defect due to the relevant technologies at least to a certain extent Or multiple problems.
According to an aspect of the present invention, a kind of logistics price prediction technique is provided, comprising:
According to history logistics order data training logistics price prediction model；
Obtain the departure place and destination in real-time logistics order data；
Segment iteration is carried out based on the departure place and destination, in each segment iteration, is fixed a price based on the logistics Prediction model is fixed a price according to the prediction of the segment iteration and the secondary iteration of at least partly real-time logistics order data prediction, from And it determines the prediction unit distance in the piecewise interval and the piecewise interval of the secondary segment iteration and fixes a price；And
Each piecewise interval corresponding to the real-time logistics order data, the prediction in each piecewise interval are at least provided Unit distance price and total prediction price.
Optionally, in each segment iteration:
The piecewise interval of the secondary segmentation is determined according to the secondary segment iteration；
The maximum distance of at least partly real-time logistics order data and the departure place to the secondary piecewise interval is inputted into institute State the prediction price that logistics price prediction model obtains the secondary iteration；
By the secondary iteration prediction price with previous iteration prediction fix a price difference divided by the piecewise interval segmentation away from From as the prediction unit distance price in this time segmentation.
Optionally, when i is more than or equal to 3 and is less than or equal to total the number of iterations, in i-th segment iteration, according to i-th Segment iteration determines that i-th of piecewise interval includes:
Determine the difference of the starting point and ending point of piecewise interval in (i-1)-th segment iteration as (i-1)-th piecewise interval Segmentation distance；
Using the terminating point of the piecewise interval in (i-1)-th segment iteration as the starting point of i-th of piecewise interval；
The terminating point of i-th of piecewise interval be i-th of piecewise interval starting point and (i-1)-th piecewise interval segmentation away from The sum of from.
Optionally, in the 1st segment iteration, determine that the 1st piecewise interval includes: according to the 1st segment iteration
The first centre distance where city where determining departure place and destination between the most similar area Liang Ge in city；
The starting point of 1st piecewise interval is determined as 0, the terminating point of the 1st piecewise interval is determined as described first Centre distance.
Optionally, in the 2nd segment iteration, determine that the 2nd piecewise interval includes: according to the 2nd segment iteration
Average distance where each district center in city where determining departure place and destination between each district center in city Using as the second centre distance；
The starting point of 2nd piecewise interval is determined as to the terminating point of the piecewise interval in the 1st segment iteration；
The terminating point of 2nd piecewise interval is determined as second centre distance.
Optionally, when i is more than or equal to 2 and is less than or equal to total the number of iterations, in i-th iteration, if in i-th segmentation Prediction unit distance price be greater than (i-1)-th time segmentation in prediction unit distance price, then re-start (i-1)-th time segmentation The determination of piecewise interval.
Optionally, the determination of piecewise interval for re-starting (i-1)-th segmentation includes:
The terminating point of the piecewise interval of former (i-1)-th segmentation is set to subtract pre- fixed step size as updated (i-1)-th time point The terminating point of the piecewise interval of section, and the piecewise interval being segmented with updated (i-1)-th time is re-executed (i-1)-th segmentation and changed Generation.
Optionally, if in the secondary segment iteration, when the terminating point of the piecewise interval of the secondary segmentation is greater than third centre distance, Stop iteration, the third centre distance is the farthest area Liang Ge where city where departure place and destination between city The distance between center.
Optionally, each piecewise interval, each piecewise interval for corresponding to the real-time logistics order data are at least provided After interior prediction unit distance price and total prediction price further include:
Obtain the departure place and destination updated；
According to correspond to each piecewise interval of the real-time logistics order data, the prediction unit in each piecewise interval Distance price updates total prediction price.
Optionally, the practical price based on each real-time logistics order data carries out increment instruction to logistics price prediction model Practice.
According to another aspect of the invention, a kind of logistics price prediction meanss are also provided, comprising:
Training module, for according to history logistics order data training logistics price prediction model；
Module is obtained, for obtaining departure place and destination in real-time logistics order data；
Iteration module is based in each segment iteration for carrying out segment iteration based on the departure place and destination The logistics price prediction model is according to the segment iteration and the secondary iteration of at least partly real-time logistics order data prediction Prediction price, so that it is determined that the prediction unit distance in the piecewise interval of the secondary segment iteration and the piecewise interval is fixed a price；With And
Module is provided, at least providing each piecewise interval corresponding to the real-time logistics order data, each point Prediction unit distance price and total prediction price in section section.
According to another aspect of the invention, a kind of electronic equipment is also provided, the electronic equipment includes: processor；Storage Medium, is stored thereon with computer program, and the computer program executes step as described above when being run by the processor.
According to another aspect of the invention, a kind of storage medium is also provided, computer journey is stored on the storage medium Sequence, the computer program execute step as described above when being run by processor.
Compared with prior art, present invention has an advantage that
The present invention trains logistics price prediction model using the multidimensional data of history logistics order data, so as to provide The influence that reduction multi-dimensional factors fix a price to logistics；Route few for sample size, even without sample, can intelligently, it is calibrated Prediction price really is provided；Dynamic is strong, and incremental study can obtain piecewise interval, number of fragments, in piecewise interval Predict unit distance price etc. information；It is provided with the price of piecewise interval, in order to which iteration is persistently runed and continued to platform.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other feature of the invention and advantage will become It is more obvious.
Fig. 1 shows the flow chart of logistics price prediction technique according to an embodiment of the present invention.
Fig. 2 shows the flow charts of a segment iteration according to an embodiment of the present invention.
Fig. 3 shows the general flow chart of segment iteration according to an embodiment of the present invention.
Fig. 4 shows the module map of logistics price prediction meanss according to an embodiment of the present invention.
Fig. 5 schematically shows a kind of computer readable storage medium schematic diagram in exemplary embodiment of the present.
Fig. 6 schematically shows a kind of electronic equipment schematic diagram in exemplary embodiment of the present.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the present invention will more Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.
In addition, attached drawing is only schematic illustrations of the invention, it is not necessarily drawn to scale.Identical attached drawing mark in figure Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place These functional entitys are realized in reason device device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all steps.For example, the step of having It can also decompose, and the step of having can merge or part merges, therefore, the sequence actually executed is possible to according to the actual situation Change.
Fig. 1 shows the flow chart of logistics price prediction technique according to an embodiment of the present invention.Logistics price prediction technique Include the following steps:
Step S110: according to history logistics order data training logistics price prediction model.
Specifically, history logistics order data may include the departure place of the history logistics order, destination, current oil Valence, delivery availability, goods weight, cargo type, lorry type, lorry vehicle commander, particular/special requirement (such as not walk high speed, needs Follow the bus etc.) and logistics price.
Logistics price prediction model of the present invention can be any machine learning model.Preferably, some implementations In example, the Machine learning tools such as xgboost can be used and carry out higher-dimension statistical modeling, system is not limited thereto in the present invention.Having Body can train the algorithm model of python language in realizing through the above way, and eventually by pmml, (prediction model is marked Language (Predictive Model Markup Language)) file, it carries out for the project of java language across language call, this Place only schematically describes a specific implementation of the invention, and system is not limited thereto in the present invention.
Further, the present invention is also configured with the step of model evaluation test, can use history logistics order data pair Trained model is assessed, when the logistics price of the price predicted and history logistics order data is closer, then model Accuracy rate is higher.Accuracy rate threshold value is set, further to control the accuracy rate of model.
Step S120: the departure place and destination in real-time logistics order data are obtained.
In various embodiments of the present invention, departure place and destination can be city, area and/or specific address, the present invention System is not limited thereto.
Step S130: carrying out segment iteration based on the departure place and destination, in each segment iteration, based on described Logistics fix a price prediction model according to the segment iteration and at least partly real-time logistics order data prediction the secondary iteration it is pre- Measurement valence, so that it is determined that the prediction unit distance in the piecewise interval of the secondary segment iteration and the piecewise interval is fixed a price.
Specifically, segment iteration may refer to Fig. 2 every time, Fig. 2 shows primary segmentations according to an embodiment of the present invention The flow chart of iteration.
Step S210: the piecewise interval of the secondary segmentation is determined according to the secondary segment iteration；
Step S220: by least partly real-time logistics order data and the destination to the secondary piecewise interval it is maximum away from It fixes a price from the prediction that the logistics price prediction model obtains the secondary iteration is inputted；
Step S230: by the difference of the prediction price of the secondary iteration and the prediction price of previous iteration divided by the piecewise interval Segmentation distance as this time be segmented in prediction unit distance fix a price.
For example, this segment iteration determines that the piecewise interval of the secondary segmentation is (Di-1, Di), by departure place to the secondary segmentation Section (Di-1, Di) maximum distance (i.e. Di) input the prediction price P that the logistics price prediction model obtains the secondary iterationi, The then prediction unit distance price KP in this time segmentationi=(Pi-Pi-1)/(Di-Di-1)。
Further, complete iterative scheme provided by the invention is described in conjunction with Fig. 3.
Step S301 is first carried out: making i 1.
Step S302: i-th of piecewise interval (D is determined according to i-th segment iterationi-1, Di), if i=1, i-th point Section section (0, D1)；
Step S303: judge whether the terminating point of i-th of piecewise interval is greater than third centre distance.The third center away from The distance between center from the farthest area Liang Ge where the city where departure place and destination between city.For example, can To calculate in the A of city, each area A1-AnCenter and city B in, each area B1-BnThe distance between center, by maximum distance As the third centre distance.City A and city B can be same city.
Stop iteration if step S303 is judged as YES.
If step S303 is judged as NO, step S304 is continued to execute: will at least partly real-time logistics order data and i-th The terminating point (maximum distance of the destination to the secondary piecewise interval) of a piecewise interval inputs the logistics price prediction mould Type obtains the prediction price P of i-th iterationi。
Step S305: the prediction of the prediction price of i-th iteration and (i-1)-th iteration is fixed a price (if i-1 is the 0, the 0th The prediction of secondary iteration is priced at prediction list of the difference 0) divided by the segmentation distance of i-th of piecewise interval as i-th of piecewise interval Position distance price KPi=(Pi-Pi-1)/(Di-Di-1)。
Step S306: judge whether i is greater than 1.
If step S306 is judged as YES, S307 is thened follow the steps, judges the prediction unit distance price in i-th segmentation KPiThe prediction unit distance price KP whether being greater than in (i-1)-th segmentationi-1。
If step S307 is judged as YES, S308 is thened follow the steps, makes the segmentation distance=the (i-1)-th of (i-1)-th piecewise interval Segmentation distance-pre- fixed step size of a piecewise interval.For example, the terminating point D of the piecewise interval of former (i-1)-th segmentation can be madei-1Subtract The terminating point D for the piecewise interval that pre- fixed step size s is removed to be segmented as updated (i-1)-th timei-1=Di-1-s.Predetermined backoff s It such as can be 5 kilometers, 10 kilometers, 15 kilometers, 20 kilometers, system is not limited thereto in the present invention.Step is executed after step S308 S309 makes i=i-1.It is then return to step S304, to re-execute (i-1)-th iteration.
If step S306 be judged as NO/if step S307 is judged as NO, and thens follow the steps S310, obtain i-th segmentation and change The piecewise interval and prediction unit distance price in generation.Then step S311 is executed, makes i=1+1, is then return to step S302, with Carry out i+1 time iteration.
Further, piecewise interval is determined according to following steps in each secondary iteration:
In the 1st segment iteration, determine that the 1st piecewise interval comprises determining that departure place institute according to the 1st segment iteration The first centre distance between the most similar area Liang Ge in city where city and destination；By the starting of the 1st piecewise interval Point is determined as 0, and the terminating point of the 1st piecewise interval is determined as first centre distance.For example, can calculate in the A of city, Each area A1-AnCenter and city B in, each area B1-BnThe distance between center, will the smallest distance as in described first Heart distance D1.1st piecewise interval is (0, D1)。
In the 2nd segment iteration, determine that the 2nd piecewise interval comprises determining that departure place institute according to the 2nd segment iteration Average distance between each district center in city where each district center in city and destination is using as the second centre distance；It will The starting point of 2nd piecewise interval is determined as the terminating point of the piecewise interval in the 1st segment iteration；By the 2nd piecewise interval Terminating point be determined as second centre distance.For example, can calculate in the A of city, each area A1-AnCenter and city B In, each area B1-BnThe distance between center, using average distance as the second centre distance D2.2nd piecewise interval be (D1, D2)。
When i is more than or equal to 3 and is less than or equal to total the number of iterations, in i-th segment iteration, changed according to i-th segmentation In generation, determines that i-th of piecewise interval comprises determining that the difference conduct of the starting point and ending point of piecewise interval in (i-1)-th segment iteration The segmentation distance of (i-1)-th piecewise interval；It is segmented the terminating point of the piecewise interval in (i-1)-th segment iteration as i-th The starting point in section；The terminating point of i-th of piecewise interval is the starting point and (i-1)-th piecewise interval of i-th of piecewise interval It is segmented sum of the distance.I-th of piecewise interval is (Di-1, Di), and Di-Di-1=Di-1-Di-2.In ideal conditions (before not carrying out State the adjustment of S308), Di-Di-1=D2-D1。
Step S140: each piecewise interval, each segment identifier for corresponding to the real-time logistics order data are at least provided Interior prediction unit distance price and total prediction price.
In certain embodiments, the step S140 is at least provided corresponding to each of the real-time logistics order data It can also include: to obtain more after prediction unit distance price and total prediction price in the piecewise interval, each piecewise interval New departure place and destination；According to each piecewise interval, each piecewise interval for corresponding to the real-time logistics order data Interior prediction unit distance price updates total prediction price.As a result, due to having generated the pricing rule of prediction, without carrying out again Model prediction reduces system-computed amount.
In some embodiments of the invention, for same city route, since departure place and destination are located at same city City, the first centre distance above-mentioned can be by being manually arranged (such as obtaining by investigation), can also be by model prediction, so Above-mentioned segment iteration is used afterwards, calculates the prediction unit distance price of piecewise interval.
The each embodiment of the present invention utilizes the training and heuristic iteration of model.It can be according to different history logistics orders Data combine situation of the multiple model of (can be according to vehicle commander, region, province) training to be applicable under different parameters, to accelerate to be Processing speed of uniting and the accuracy of model output.Furthermore.With the use of this model, the present invention can be constantly to new deal Order sample carries out incremental learning and training, Optimized model and is iterated also according to foregoing manner, dynamically each described divide Prediction unit distance price and total prediction price in section section, each piecewise interval.It is also possible to according to cargo weight Amount obtains the prediction unit distance weight price (i.e. prediction unit distance price/goods weight) in each piecewise interval.
In some embodiments of the invention, manual deviation rectification can be introduced, it can to finally obtained each piecewise interval It is adjusted, to ensure that certain uncontrollabilities of machine learning model still manually can be limited controllably.
In some embodiments of the invention, machine learning platform (model training), pricing service platform separation solution Coupling, the data that algorithm model provides can be stored in pricing service platform, and with external offer service, the two is not interfered with each other.
In each specific embodiment of the invention, () in piecewise interval can refer to the data comprising the both ends, can also Not include, system is not limited thereto in the present invention.
In logistics provided by the invention price prediction technique, the present invention utilizes the multidimensional data of history logistics order data Training logistics price prediction model, so as to provide the reduction influence that multi-dimensional factors fix a price to logistics；Few for sample size, Even without the route of sample, prediction price can intelligently, be accurately provided；Dynamic is strong, and incremental study can obtain Piecewise interval, number of fragments, prediction unit distance price in piecewise interval etc. information；It is provided with the valence of piecewise interval Lattice, in order to which iteration is persistently runed and continued to platform.
Fig. 4 shows the module map of logistics price prediction meanss according to an embodiment of the present invention.Logistics price prediction meanss 400 include training module 410, acquisition module 420, iteration module 430, offer module 440.
Training module 410 is used for prediction model of fixing a price according to the training logistics of history logistics order data；
Module 420 is obtained to be used to obtain the departure place and destination in real-time logistics order data；
Iteration module 430 is used to carry out segment iteration, in each segment iteration, base based on the departure place and destination It is changed in logistics price prediction model according to this time of the segment iteration and at least partly real-time logistics order data prediction The prediction in generation is fixed a price, so that it is determined that the prediction unit distance in the piecewise interval of the secondary segment iteration and the piecewise interval is fixed a price； And
Module 440 is provided at least providing each piecewise interval, each for corresponding to the real-time logistics order data Prediction unit distance price and total prediction price in piecewise interval.
In logistics provided by the invention price prediction meanss, the present invention utilizes the multidimensional data of history logistics order data Training logistics price prediction model, so as to provide the reduction influence that multi-dimensional factors fix a price to logistics；Few for sample size, Even without the route of sample, prediction price can intelligently, be accurately provided；Dynamic is strong, and incremental study can obtain Piecewise interval, number of fragments, prediction unit distance price in piecewise interval etc. information；It is provided with the valence of piecewise interval Lattice, in order to which iteration is persistently runed and continued to platform.
Fig. 4 is only to show schematically logistics provided by the invention price prediction meanss 400, without prejudice to structure of the present invention Under the premise of think of, the fractionation of module, increases all within protection scope of the present invention merging.Logistics price provided by the invention Prediction meanss 400 can be realized that the present invention is not with this by software, hardware, firmware, plug-in unit and any combination between them It is limited.
In an exemplary embodiment of the present invention, a kind of computer readable storage medium is additionally provided, meter is stored thereon with Calculation machine program, the program may be implemented electronic prescription described in any one above-mentioned embodiment and circulate when being executed by such as processor The step of processing method.In some possible embodiments, various aspects of the invention are also implemented as a kind of program production The form of product comprising program code, when described program product is run on the terminal device, said program code is for making institute It states terminal device and executes described in this specification above-mentioned logistics price prediction technique part various exemplary realities according to the present invention The step of applying mode.
Refering to what is shown in Fig. 5, describing the program product for realizing the above method of embodiment according to the present invention 700, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device, Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages Code, described program design language include object oriented program language-Java, C++ etc., further include conventional Procedural programming language-such as " C " language or similar programming language.Program code can be fully in tenant It calculates and executes in equipment, partly executed in tenant's equipment, being executed as an independent software package, partially in tenant's calculating Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network (WAN), it is connected to tenant and calculates equipment, or, it may be connected to external computing device (such as utilize ISP To be connected by internet).
In an exemplary embodiment of the present invention, a kind of electronic equipment is also provided, which may include processor, And the memory of the executable instruction for storing the processor.Wherein, the processor is configured to via described in execution Executable instruction is come the step of executing the circulation processing method of electronic prescription described in any one above-mentioned embodiment.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here Referred to as circuit, " module " or " system ".
The electronic equipment 500 of this embodiment according to the present invention is described referring to Fig. 6.The electronics that Fig. 6 is shown Equipment 500 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 6, electronic equipment 500 is showed in the form of universal computing device.The component of electronic equipment 500 can wrap It includes but is not limited to: at least one processing unit 510, at least one storage unit 520, (including the storage of the different system components of connection Unit 520 and processing unit 510) bus 530, display unit 540 etc..
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 510 Row, so that the processing unit 510 executes described in this specification above-mentioned logistics price prediction technique part according to the present invention The step of various illustrative embodiments.For example, the processing unit 510 can execute step as shown in Figure 1 to Figure 3.
The storage unit 520 may include the readable medium of volatile memory cell form, such as random access memory Unit (RAM) 5201 and/or cache memory unit 5202 can further include read-only memory unit (ROM) 5203.
The storage unit 520 can also include program/practical work with one group of (at least one) program module 5205 Tool 5204, such program module 5205 includes but is not limited to: operating system, one or more application program, other programs It may include the realization of network environment in module and program data, each of these examples or certain combination.
Bus 530 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures Local bus.
Electronic equipment 500 can also be with one or more external equipments 600 (such as keyboard, sensing equipment, bluetooth equipment Deng) communication, the equipment that also tenant can be enabled interact with the electronic equipment 500 with one or more communicates, and/or with make Any equipment (such as the router, modulation /demodulation that the electronic equipment 500 can be communicated with one or more of the other calculating equipment Device etc.) communication.This communication can be carried out by input/output (I/O) interface 550.Also, electronic equipment 500 can be with By network adapter 560 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, Such as internet) communication.Network adapter 560 can be communicated by bus 530 with other modules of electronic equipment 500.It should Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 500, including but unlimited In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number According to backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the present invention The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating Equipment (can be personal computer, server or network equipment etc.) executes the above-mentioned electronics of embodiment according to the present invention Prescription circulation processing method.
Compared with prior art, present invention has an advantage that
The present invention trains logistics price prediction model using the multidimensional data of history logistics order data, so as to provide The influence that reduction multi-dimensional factors fix a price to logistics；Route few for sample size, even without sample, can intelligently, it is calibrated Prediction price really is provided；Dynamic is strong, and incremental study can obtain piecewise interval, number of fragments, in piecewise interval Predict unit distance price etc. information；It is provided with the price of piecewise interval, in order to which iteration is persistently runed and continued to platform.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to of the invention its Its embodiment.This application is intended to cover any variations, uses, or adaptations of the invention, these modifications, purposes or Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the present invention Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by appended Claim is pointed out.

Claims (13)

  1. The prediction technique 1. a kind of logistics is fixed a price characterized by comprising
    According to history logistics order data training logistics price prediction model；
    Obtain the departure place and destination in real-time logistics order data；
    Segment iteration is carried out based on the departure place and destination, in each segment iteration, based on logistics price prediction Model is fixed a price according to the prediction of the segment iteration and the secondary iteration of at least partly real-time logistics order data prediction, thus really The piecewise interval of the fixed secondary segment iteration and the prediction unit distance price in the piecewise interval；And
    Each piecewise interval corresponding to the real-time logistics order data, the prediction unit in each piecewise interval are at least provided Distance price and total prediction price.
  2. The prediction technique 2. logistics as described in claim 1 is fixed a price, which is characterized in that in each segment iteration:
    The piecewise interval of the secondary segmentation is determined according to the secondary segment iteration；
    The maximum distance of at least partly real-time logistics order data and the departure place to the secondary piecewise interval is inputted into the object Stream price prediction model obtains the prediction price of the secondary iteration；
    The difference of the prediction price of the secondary iteration and the prediction price of previous iteration is made divided by the segmentation distance of the piecewise interval For the prediction unit distance price in this time segmentation.
  3. The prediction technique 3. logistics as claimed in claim 2 is fixed a price, which is characterized in that when i is more than or equal to 3 and is less than or equal to total change When generation number, in i-th segment iteration, determine that i-th of piecewise interval includes: according to i-th segment iteration
    Determine point of the difference of the starting point and ending point of piecewise interval in (i-1)-th segment iteration as (i-1)-th piecewise interval Section distance；
    Using the terminating point of the piecewise interval in (i-1)-th segment iteration as the starting point of i-th of piecewise interval；
    The terminating point of i-th of piecewise interval is the starting point of i-th of piecewise interval and the segmentation of (i-1)-th piecewise interval apart from it With.
  4. The prediction technique 4. logistics as claimed in claim 3 is fixed a price, which is characterized in that in the 1st segment iteration, according to the 1st Secondary segment iteration determines that the 1st piecewise interval includes:
    The first centre distance where city where determining departure place and destination between the most similar area Liang Ge in city；
    The starting point of 1st piecewise interval is determined as 0, the terminating point of the 1st piecewise interval is determined as first center Distance.
  5. The prediction technique 5. logistics as claimed in claim 3 is fixed a price, which is characterized in that in the 2nd segment iteration, according to the 2nd Secondary segment iteration determines that the 2nd piecewise interval includes:
    Average distance where each district center in city where determining departure place and destination between each district center in city is to make For the second centre distance；
    The starting point of 2nd piecewise interval is determined as to the terminating point of the piecewise interval in the 1st segment iteration；
    The terminating point of 2nd piecewise interval is determined as second centre distance.
  6. The prediction technique 6. logistics as claimed in claim 2 is fixed a price, which is characterized in that when i is more than or equal to 2 and is less than or equal to total change When generation number, in i-th iteration, if the prediction unit distance price in i-th segmentation is greater than the prediction in (i-1)-th segmentation Unit distance price, then re-start the determination of the piecewise interval of (i-1)-th segmentation.
  7. The prediction technique 7. logistics as claimed in claim 6 is fixed a price, which is characterized in that described to re-start (i-1)-th segmentation The determination of piecewise interval includes:
    The terminating point of the piecewise interval of former (i-1)-th segmentation is set to subtract pre- fixed step size to be segmented as updated (i-1)-th time The terminating point of piecewise interval, and the piecewise interval being segmented with updated (i-1)-th time re-executes (i-1)-th segment iteration.
  8. The prediction technique 8. logistics as described in any one of claim 1 to 7 is fixed a price, which is characterized in that if in the secondary segment iteration, When the terminating point of the piecewise interval of the secondary segmentation is greater than third centre distance, stop iteration, the third centre distance is to set out The distance between the center in the farthest area Liang Ge where city where ground and destination between city.
  9. The prediction technique 9. logistics as described in any one of claim 1 to 7 is fixed a price, which is characterized in that at least provide and correspond to institute State each piecewise interval, the prediction unit distance price in each piecewise interval and the total prediction price of real-time logistics order data Later further include:
    Obtain the departure place and destination updated；
    According to correspond to each piecewise interval of the real-time logistics order data, the prediction unit distance in each piecewise interval Price updates total prediction price.
  10. The prediction technique 10. logistics as described in any one of claim 1 to 7 is fixed a price, which is characterized in that ordered based on each real-time logistics The practical price of forms data carries out incremental training to logistics price prediction model.
  11. The prediction meanss 11. a kind of logistics is fixed a price characterized by comprising
    Training module, for according to history logistics order data training logistics price prediction model；
    Module is obtained, for obtaining departure place and destination in real-time logistics order data；
    Iteration module, for carrying out segment iteration based on the departure place and destination, in each segment iteration, based on described Logistics fix a price prediction model according to the segment iteration and at least partly real-time logistics order data prediction the secondary iteration it is pre- Measurement valence, so that it is determined that the prediction unit distance in the piecewise interval of the secondary segment iteration and the piecewise interval is fixed a price；And
    Module is provided, at least providing each piecewise interval, each segment identifier corresponding to the real-time logistics order data Interior prediction unit distance price and total prediction price.
  12. 12. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
    Processor；
    Memory is stored thereon with computer program, is executed when the computer program is run by the processor as right is wanted Seek 1 to 10 described in any item steps.
  13. 13. a kind of storage medium, which is characterized in that be stored with computer program, the computer program on the storage medium Step as described in any one of claim 1 to 10 is executed when being run by processor.
CN201910216638.1A 2019-03-20 2019-03-20 Logistics price prediction technique, device, electronic equipment, storage medium Pending CN109948983A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910216638.1A CN109948983A (en) 2019-03-20 2019-03-20 Logistics price prediction technique, device, electronic equipment, storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910216638.1A CN109948983A (en) 2019-03-20 2019-03-20 Logistics price prediction technique, device, electronic equipment, storage medium

Publications (1)

Publication Number Publication Date
CN109948983A true CN109948983A (en) 2019-06-28

Family

ID=67010463

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910216638.1A Pending CN109948983A (en) 2019-03-20 2019-03-20 Logistics price prediction technique, device, electronic equipment, storage medium

Country Status (1)

Country Link
CN (1) CN109948983A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112862413A (en) * 2021-03-30 2021-05-28 普洛斯科技(重庆)有限公司 Checking method and device for carrying orders, electronic equipment and storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112862413A (en) * 2021-03-30 2021-05-28 普洛斯科技(重庆)有限公司 Checking method and device for carrying orders, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
US20230169448A1 (en) Delivery prediction generation system
US20230342708A1 (en) Integrated multi-location scheduling, routing, and task management
US11416787B2 (en) Parallel processing for solution space partitions
Goh et al. Distributionally robust optimization and its tractable approximations
CN108154420A (en) Products Show method and device, storage medium, electronic equipment
CN107169534A (en) Model training method and device, storage medium, electronic equipment
CN109242044A (en) Training method, device, storage medium and the electronic equipment of vehicle and goods matching model
CN107766987A (en) Scheduled Flight delay information method for pushing, system, storage medium and electronic equipment
US20160171440A1 (en) Method and system for freight management
CN108122052A (en) Method for pushing, system, storage medium and the electronic equipment of flight delay information
CN109658033A (en) Source of goods route similarity calculating method, system, equipment and storage medium
US20140149321A1 (en) Electronic revenue managment for transportation networks
CN109991963A (en) Speed planning method and terminal device
CN110232535A (en) Information matching method and device, storage medium and electric terminal
CN114862209A (en) Transport capacity scheduling method and device, electronic equipment and storage medium
CN110348636B (en) Path plan prediction method, apparatus, device and computer readable storage medium
CN109948983A (en) Logistics price prediction technique, device, electronic equipment, storage medium
CN112785111A (en) Production efficiency prediction method, device, storage medium and electronic equipment
CN109190837A (en) The method, apparatus of Optimizing Transport route, electronic equipment, storage medium
CN109917781A (en) For dispatching the method, apparatus and system of automated guided vehicle
CN109472708A (en) Nursing insurance measuring method, device, electronic equipment, storage medium
US20220300002A1 (en) Methods and systems for path planning in a known environment
CN111754154B (en) Information processing method and device, storage medium and electronic equipment
WO2023084847A1 (en) Information output method, program, and information output system
CN109840609A (en) Picking point data method of calibration and device, storage medium, electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20190628

RJ01 Rejection of invention patent application after publication