CN110175724A - Predictor method, computer installation and storage medium is lost in Commodity Transportation - Google Patents
Predictor method, computer installation and storage medium is lost in Commodity Transportation Download PDFInfo
- Publication number
- CN110175724A CN110175724A CN201910471892.6A CN201910471892A CN110175724A CN 110175724 A CN110175724 A CN 110175724A CN 201910471892 A CN201910471892 A CN 201910471892A CN 110175724 A CN110175724 A CN 110175724A
- Authority
- CN
- China
- Prior art keywords
- commodity
- information
- transport
- transportation
- loss
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
Abstract
The present invention provides a kind of Commodity Transportation loss predictor method, computer installation and computer readable storage medium.The present invention passes through historical shipment data training learning model; the transport project of commodity to be transported is inputted into the transport loss that the learning model estimates commodity to be transported automatically; so that the loss of Commodity Transportation estimate it is more intelligent, accurate and quick; and the transport loss for accurately estimating commodity to be transported is more favorable to provide different commodity during transportation the protection of appropriate level; reduce transport loss to the greatest extent, additionally it is possible to user be assisted to formulate more reasonable transaction value.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of Commodity Transportation loss predictor method, computer installation
And computer readable storage medium.
Background technique
It, can be because a variety of causes generates some losses, for example, volatile chemicals is transporting during Commodity Transportation
The abrasion during transportation of volatilization in the process, solid commodity and physical impacts damage, the leakage of liquid commodity etc..Especially
Transport for chemicals, it is volatile based on part chemicals, vulnerable to heat/photodegradation property, it is easier during transportation
It is lost.And the transport protection level of loss and commodity during Commodity Transportation has certain relationship, if can not be reasonable
It estimates transport loss and the protection that commodity are carried out with appropriate level is lost according to estimating, then may be because protecting during Commodity Transportation
It protects improper and increases transport loss, in addition, transport loss also has certain influence to the deal prices of commodity.Therefore, how
Accurate before Commodity Transportation, reasonable prediction transport loss is a problem to be solved for Commodity Transportation field.
Summary of the invention
In view of problem above, the present invention proposes that predictor method, computer installation and storage medium is lost in a kind of Commodity Transportation,
It can be lost according to commodity transportation plan intelligence, accurate Commodity Transportation of estimating.
The first aspect of the application provides a kind of Commodity Transportation loss predictor method, which comprises
Transport project information is received, includes the merchandise news and traffic condition of commodity to be transported in the transport project information
Information；
By the transport project information input to default learning model, obtain that the commodity to be transported are corresponding to estimate transport
Loss value.
Preferably, the merchandise news includes product name, merchandise classification, commodity packaging, specification, quantity, item property
One of or it is a variety of, the traffic condition information includes shipping point of origin and terminal geographical location information, transit information, fortune
One of defeated distance information, weather information are a variety of；The transport loss information includes the loss of commodity during transportation
Value.
Preferably, the method for establishing the learning model includes:
Commodity Transportation data are obtained, Commodity Transportation data set is generated, wherein the Commodity Transportation data include commodity letter
Information is lost in the transport of breath, traffic condition information and commodity；
Learning model is established, and according to the Commodity Transportation data set training learning model, wherein the study mould
The input of type is merchandise news and traffic condition, and the output of the learning model is transport loss information.
Preferably, the geographical location information and transport distance letter of the shipping point of origin in the traffic condition information and terminal
Breath is to receive control instruction automatic positioning by user terminal response to obtain, and the temporal information is to receive the control
It is obtained when system instruction by clock, the weather information is after getting the geographical location information and temporal information, certainly
Weather information of the geographical location that the database of dynamic connection weather site obtains in current time.
Optionally, the learning model is multiple linear regression model, described to establish learning model, and according to the commodity
The transportation data collection training learning model includes:
Establish multiple linear regression model, the multiple linear regression model indicate Commodity Transportation loss and merchandise news,
Corresponding relationship between traffic condition information, wherein the merchandise news, traffic condition information are independent variable, the commodity wastage
For dependent variable；
The Commodity Transportation data set is divided into training sample set and verifying sample set；
The multiple linear regression model is trained using the training sample set, calculates multiple linear regression model
Regression coefficient, obtain equation of linear regression；
Test verifying is carried out to above-mentioned multiple linear regression model according to the verifying sample set.
Optionally, the learning model can also be neural network model, including AlexNet network model, based on VGG's
One of neural network model or BPNN neural network model are a variety of.
Optionally, the method also includes:
The protection level to Commodity Transportation is searched from presetting database according to the transport loss value estimated, transaction is determined
The suggestion of valence.
Optionally, the method also includes:
The corresponding actual shipment loss value of the transport project is obtained, by the transport project information and the practical fortune
Defeated loss value is stored to iterative learning data set, is iterated training to the machine learning model.
Second aspect of the present invention provides a kind of computer installation, and the computer installation includes processor, the processor
Foregoing Commodity Transportation loss predictor method is realized when for executing the computer program stored in memory.
Third aspect present invention provides a kind of computer readable storage medium, is stored thereon with computer program, the meter
Calculation machine program realizes foregoing Commodity Transportation loss predictor method when being executed by processor.
Compared with prior art, the present invention is by historical shipment data training learning model, transport project is inputted described in
Learning model estimates the corresponding Commodity Transportation loss of transport project of commodity to be transported automatically, so that the loss of Commodity Transportation is estimated
It is more intelligent, accurate and quick, and the transport loss for accurately estimating commodity to be transported is more favorable to transporting different commodity
The protection of appropriate level is provided during defeated, reduces transport loss to the greatest extent, additionally it is possible to user be assisted to formulate more reasonable transaction
Price.For example, accurately estimating transport loss for chemicals labile for volatile or heated/light and being conducive to change
Product provide protection level appropriate, reduce the volatilization or decomposition in transportational process to the greatest extent, and formulate reasonable chemicals transaction
Price.
Detailed description of the invention
Fig. 1 is the Commodity Transportation loss predictor method application environment configuration diagram that an embodiment of the present invention provides.
Fig. 2 is the Commodity Transportation loss predictor method flow chart that an embodiment of the present invention provides.
Fig. 3 is the functional block diagram for the Commodity Transportation loss Prediction System that an embodiment of the present invention provides.
Fig. 4 is the computer installation hardware structure schematic diagram that an embodiment of the present invention provides.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying example, the present invention will be described in detail.It should be noted that in the absence of conflict, embodiments herein and embodiment
In feature can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, described embodiment is only
It is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Referring to Fig. 1, the application environment frame of predictor method is lost for the Commodity Transportation that one embodiment of the invention provides
Structure schematic diagram.
It is including computer installation 1 and at least one user terminal that Commodity Transportation loss predictor method in the present invention, which is applied,
In 2 communication system.The computer installation 1 and at least one described user terminal 2 are established by network to be communicated to connect.It is described
Network can be cable network, be also possible to wireless network, for example, radio, Wireless Fidelity (Wireless Fidelity,
WIFI), honeycomb, satellite, broadcast etc..
In present embodiment, the computer installation 1 can be but not limited to personal computer, server etc., wherein institute
Stating server can be single server, server cluster or Cloud Server etc..The user terminal 2, which can be, has display
The various intelligent electronic devices of screen, including but not limited to smart phone, tablet computer, convenient computer on knee, desk-top calculating
Machine etc..
In present embodiment, the computer installation 1 of function is estimated for needing to be implemented Commodity Transportation loss, can directly be existed
The loss of Commodity Transportation provided by method of the invention is integrated on computer installation 1 estimates function, or installation for realizing this
The client of the provided Commodity Transportation loss predictor method of invention.For another example, Commodity Transportation loss provided by the present invention is pre-
The method of estimating, which can also be, operates in service in the form of Software Development Kit (Software Development Kit, SDK)
In the equipment such as device, and Commodity Transportation is provided in the form of SDK, the interface for estimating function, computer installation 1 or other equipment are lost
It can be realized by the interface of offer and Commodity Transportation loss estimated.
Transport project can be sent to the computer installation 1 by the network and carry out commodity by the user terminal 2
Transport loss is estimated, and obtains the estimation results that Commodity Transportation is lost from the computer installation 1.
The computer installation 1 can obtain history from multiple user terminals 2 or from default store path by network
Commodity Transportation data, including merchandise news, traffic condition information and Commodity Transportation loss information etc., to establish commodity fortune
Defeated message data set, and by data set training learning model, it obtains being transported with merchandise news, traffic condition information and commodity
The corresponding relationship of defeated loss.When computer installation 1 connects from the input unit of user terminal 2 or the computer installation 1 itself
After the transport project for receiving commodity to be transported, transport project is inputted into the Commodity Transportation that the learning model is estimated and is lost
Value, such user can estimate the loss value in transportational process in advance before transportation, and then transport can reasonably be specified to protect
Shield measure and the reasonable deal prices of progress.User can also obtain this after transport and transport actual Commodity Transportation
Data are iterated study to the learning model.
Predictor method is lost below with reference to Fig. 2 Commodity Transportation that the present invention will be described in detail provides.Fig. 2 is a reality of the invention
Predictor method flow chart is lost in the Commodity Transportation that the mode of applying provides.In the present embodiment, the side of estimating is lost in the Commodity Transportation
Method includes the following steps that the sequence of step can change in the flow chart according to different requirements, and certain steps can be omitted.
Step S21, Commodity Transportation data are obtained, Commodity Transportation data set is generated.
Wherein, the Commodity Transportation data include the transport loss information of merchandise news, traffic condition information and commodity.
In the present embodiment, the merchandise news includes but is not limited to product name, merchandise classification, commodity packaging, rule
Lattice, quantity, item property.
Wherein, product name is the specific name of institute's transported goods, such as apple, fresh meat, ethyl alcohol, ether, ammonium hydroxide, dense salt
Acid, concentrated nitric acid, formaldehyde etc..Merchandise classification is commodity classification belonging to institute's transported goods, such as the merchandise classification of apple, fresh meat is
Foodstuff, ethyl alcohol, ether, ammonium hydroxide, concentrated hydrochloric acid, concentrated nitric acid, formaldehyde merchandise classification be chemical class etc..The merchandise classification can
Being classified according to ingredient, the purposes etc. of commodity, commodity classification can also be divided into major class, middle class, group according to level
Deng.For example, it is foodstuff, chemical, building material that major class, which can be the trade division according to belonging to commodity production and the field of circulation,
Deng again middle class, which can be, can be divided into vegetables and fruits, meat and meat system to major class further division, such as foodstuff according to commodity category
Product, cream and dairy products etc..Commodity packaging, specification, quantity can be the container for transported goods, specification, quantity etc..Commodity category
Property may include it is volatile, inflammable and explosive, be protected from light, low-temperature transport etc..The attribute that many commodity have its special, in transportational process
In loss easily occur and need special traffic condition, therefore the attribute of commodity is especially heavy for the transport of default commodity loss
It wants.Such as chemicals, many chemicals have special attribute, for example, ethyl alcohol, ether, ammonium hydroxide, concentrated hydrochloric acid, dense
The attribute of the chemicals such as nitric acid, formaldehyde is volatile；Sodium bicarbonate, ammonium chloride, concentrated nitric acid, hypochlorous acid, the chemicals such as nitrate
Attribute be heated easily decompose or volatilization；The attribute of the chemicals such as chlorine water, bromine water, iodine water is light-exposed easy decomposition or volatilization；Fluorination
The easily agglomeration of the substances such as potassium, ammonium hydrogen carbonate, ammonium sulfate, ammonium nitrate, sodium nitrate, potassium nitrate, ammonium chloride, potassium chloride dampness, needs to protect
Hold drying.
The traffic condition information include but is not limited to shipping point of origin and terminal geographical location information, transit information,
Transport distance information, weather information etc..The geographical location information of shipping point of origin and terminal can include but is not limited to longitude and latitude letter
One of breath, city name information, altitude information are a variety of.Transit information may include transport time started, transport
End time, transport total time-consuming length etc..Total kilometer that transport distance information can include but is not limited to transportation route, transport distance
Number etc..Weather information includes but is not limited to temperature, humidity, atmospheric pressure etc..The weather information may include shipping point of origin
One of weather information, the weather information of transportation terminal, weather information in transportational process are a variety of.Haulage time, meteorology
The traffic conditions such as information information can all be lost the transport of commodity and generate large effect, especially for specific properties
For chemicals, influence of the weather informations such as temperature, humidity for transport loss is very big.For example, the commodity of transport are fluorination
When the chemicals that the dampness such as potassium, ammonium hydrogen carbonate, ammonium sulfate, ammonium nitrate, sodium nitrate, potassium nitrate, ammonium chloride, potassium chloride are easily agglomerated,
Cause air humidity big if encountering rainy weather in transportational process, it is easy to which agglomeration is rotten to increase transport loss.Example again
When the commodity of such as transport are sodium bicarbonate, the heated easy decomposition of chlorine water or light-exposed labile chemicals, if in transportational process
Temperature is excessively high, it is easy to cause transport article volatilization that can decompose, to increase transport loss.
The transport loss information includes but is not limited to that volatilization, leakage, oxidation, physical abrasion or physical impacts damage etc. are led
The loss value of the commodity of cause during transportation.It is appreciated that the transport loss information for commodity described in different commodity is different.
In the present embodiment, the traffic condition information is obtained from least one user terminal 2 by communication network
Take, be equipped in the user terminal 2 transport loss estimate software, when commodity transport starting point start transport when, hold
After the conveying people of the user terminal 2 or stock clerk input the initial order that transport starts, 2 sound of user terminal
Answer initial order automatic positioning to obtain geographical location locating for the user terminal 2, and obtain current time information and
Present position current weather information.In present embodiment, the user terminal 2 can pass through GPS (Global Positioning
System global positioning system) geographical location information is obtained, current time letter is obtained by the clock of the user terminal 2
Breath, and after getting the geographical location information and temporal information, the automatic database for connecting weather site obtains describedly
Position is managed in the weather information of current time.When reaching transportation terminal, hold the conveying people or warehouse of the user terminal 2
Administrative staff input the END instruction that transport is completed, and the user terminal 2 responds the END instruction and obtains the user terminal 2
The geographical location information, current time information and weather information, and by it is described transport starting point, transportation terminal geographical position
Confidence breath, temporal information and weather information are sent to the computer installation 1.
It is appreciated that in other embodiments, what the weather information was also possible to be obtained by computer installation 1, it uses
After geographical location information and temporal information are sent to the computer installation 1 by family terminal 2, the computer installation 1 is according to institute
Geographical location information and temporal information are stated by obtaining corresponding weather information in weather site database.
In present embodiment, the merchandise news and Commodity Transportation loss information are that user is manually entered into the use
Family terminal 2 or the computer installation 1.
In other embodiments, the computer installation 1 directly can also obtain history commodity from default store path
Transportation data, such as more history Commodity Transportation data are obtained from other electronic devices such as Cloud Server or local data base.
In present embodiment, the step further includes storing the Commodity Transportation data set to default store path.Institute
Stating includes a large amount of historical shipment data in data set.
Step S22, learning model is established, and according to the Commodity Transportation data set training learning model, wherein institute
The input for stating learning model is merchandise news and traffic condition information, and the output of the learning model is transport loss information.
In one embodiment of the present invention, the learning model is multiple linear regression model, and the step S22 is specifically wrapped
It includes:
(a) multiple linear regression model is established, the multiple linear regression model indicates that Commodity Transportation loss is believed with commodity
Corresponding relationship between breath, traffic condition information, wherein the merchandise news, traffic condition information are independent variable, the commodity
Loss is dependent variable；
In present embodiment, the multiple linear regression model of foundation are as follows:
L=b0+b1x1+b2x2+...+bkxk+e；
Wherein, dependent variable L is that the transport of commodity is lost.Independent variable x1、x2、……xkFor the merchandise news and transport
Conditional information, such as x1 is product name, x2 is item property, x3 is packaging, and x4 is merchandise classification, and x5 is haulage time, x6
For weather information etc..b0、b1、...、bkFor the regression coefficient in model, e is the constant term in model, indicates error variance.
(b) the Commodity Transportation data set is divided into training sample set and verifying sample set；
(c) multiple linear regression model is trained using the training sample set, calculates multiple linear regression
The regression coefficient of model, obtains equation of linear regression；
In present embodiment, the regression coefficient of the multiple linear regression model is calculated using least square method.In reality
In application, the value of error variance e can be ignored.Specifically, available to solve back by taking two variable linear regression as an example
Return the equation group of coefficient are as follows:
According to the data that training sample is concentrated, solution above equation group can be in the hope of b0, b1, these regression coefficients of b2 it is normal
Value, has the constant value of these regression coefficients to obtain corresponding regression equation.By the mass data in data set to described more
First linear regression model (LRM) is constantly trained, and can reject incoherent and dependent variable.
(d) test verifying is carried out to above-mentioned multiple linear regression model according to the verifying sample set.
In other embodiments of the invention, the learning model is also possible to neural network model, such as AlexNet
Network model, the neural network model based on VGG, BPNN (Back Propagation Neural Network, back-propagating
Neural network) model etc..The neural network model includes input layer, hidden layer and output layer.The merchandise news and fortune
Defeated conditional information is used as output layer as the neural network model input layer, the Commodity Transportation loss.The commodity are transported
After transmission of data collection is divided into training sample set and verifying sample set, pass through the training sample set training neural network mould
Type carries out model verifying by the verifying sample set.
Step S23, receive transport project information, include in the transport project information commodity to be transported merchandise news and
Traffic condition information.
The transport project information includes but is not limited to the name of shipping point of origin, transportation terminal, weather information, commodity to be transported
Title, classification, packaging, specification, quantity, item property.
In present embodiment, the transport project information can be what computer installation 1 was got by user terminal 2,
The holder of user terminal 2 is also possible to user and is directly inputted into the calculating by being manually entered the transport project information
Machine device 1.In one embodiment, shipping point of origin, transportation terminal, the title of commodity to be transported, classification, packaging, specification,
Quantity can be what user was manually entered, and item property can be product name and classification according to input in presetting database
Middle Auto-matching.Weather information is also possible to the shipping point of origin inputted according to user and/or transportation terminal from weather site number
According to what is obtained in library.
Step S24, by the transport project information input to the learning model, it is corresponding that the commodity to be transported are obtained
Estimate transport loss value.
Step S25, the transport loss value estimated described in output.
The transport loss value estimated described in output can be the fortune estimated described in display in the display screen of computer installation 1
Defeated loss value can also be that the transport loss value estimated is sent to the user terminal 2 by network by computer installation 1.
It is appreciated that the model after the completion of training, can store in preset path, transport meter is inputted for subsequent user
It draws information and obtains the transport loss value estimated.Model training process and according to transport project information estimate transport loss can be
Two sseparated processes.
Further, in some embodiments, the method can also include the following steps: the fortune estimated according to
Defeated loss value searches the suggestion of the protection level and/or deal prices to Commodity Transportation from presetting database.
The transport loss of usual commodity and commodity protected mode during transportation and protection level have certain association, institute
The suggestion for estimating transport loss value and Commodity Transportation protection level and deal prices can be previously stored with by stating in presetting database,
When the computer installation 1 calculate commodity to be transported it is corresponding estimate transport loss after, by searching in the preset database
With the suggestion of the matched protection level of transport loss value and/or deal prices estimated.Facilitate to need forwarding agent in this way
The user of product takes more suitable safeguard measure to reduce commodity wastage to the greatest extent commodity, and customizes reasonable transaction value.Citing
For, if the commodity transported in the transport project of input are the labile sodium bicarbonate that is heated, and the transport item in transport project
When the temperature of transportation terminal is higher in part information, then the transport loss estimated can be greater than temperature it is low when loss, at this moment can be with
Suitable protection level is provided according to the loss estimated, such as reduces the temperature etc. of shipping container, and provide and build to deal prices
View, such as appropriate be turned up that will fix a price is lost based on transport.
Further, in some embodiments, the method can be the following steps are included: obtain the transport project
Corresponding actual shipment loss value stores the transport project information and the actual shipment loss value to iterative learning number
According to collection, for being iterated the training of study to the machine learning model.
Further, in some embodiments, the method can be the following steps are included: by the transport estimated
Loss value when the transport loss value estimated described in the determination is beyond the threshold value, issues information warning compared with a preset threshold,
The corresponding transport loss of the transport project for prompting user current is excessive, and user is asked to modify transport project.
The information warning can be but not limited to text information, voice messaging etc., such as can be shown and be warned by pop-up
Show text " the corresponding transport loss of current transportation plan is excessive, it is proposed that modification transport project ".In some embodiments, may be used also
The information warning is sent to preset phone number or E-mail address, associated user is prompted to transport loss excessive.
Further, in some embodiments, when the transport loss value estimated described in the determination is beyond the threshold value,
The method can also include the following steps: to correct the transport project automatically until the transport estimated using the learning model
Loss value is lower than the threshold value, and exports revised transport project as amending advice.
Specifically, computer installation, can be to the commodity in transport project when the transport loss value estimated exceeds threshold value
The information such as packaged information, transport initial time modify transport project automatically, and modified transport project is defeated again
Enter to the learning model until transport loss value is less than the threshold value.Wherein, modification transport project information, which can be, passes through machine
What the mode of device study was realized.
For example, being directed to light-exposed labile chemicals, when commodity packaging is colorless and transparent container, it may cause and estimate
Transport loss is more than threshold value, then commodity packaging can be revised as dark opaque containers by the method, to reduce transport damage
Consumption value.In another example being originated when the commodity of transport are perishable chemicals (such as the lime) of dampness when being transported in transport project
Time, corresponding weather information showed heavy rain, and air humidity is larger, when may cause the transport loss estimated more than threshold value, that
The available rainfall of the method stops, the time that air humidity reduces, and by the initial time in the transport project into
Row modification, to reduce the transport loss value estimated.
Predictor method is lost in Commodity Transportation in the present invention, by history Commodity Transportation data training learning model, obtains
Corresponding relationship between merchandise news, traffic condition information and Commodity Transportation loss, by by the merchandise news of commodity to be transported
The transport loss value estimated with traffic condition information input to the learning model, allow user Commodity Transportation it
It is preceding fast and accurately to estimate the issuable loss value of transport in advance, facilitate user to determine to the protection during transported goods
Rank, additionally it is possible to assist the deal prices of user.
Fig. 2 describes Commodity Transportation loss predictor method of the invention in detail, below with reference to Fig. 3 and Fig. 4, described in realization
Commodity Transportation is lost the functional module of the software systems of predictor method and realizes the hard of the Commodity Transportation loss predictor method
Part device architecture is introduced.It should be appreciated that the embodiment is only purposes of discussion, do not tied by this in patent claim
The limitation of structure.
Referring to Fig. 3, the functional module structure of Prediction System is lost for the Commodity Transportation that an embodiment of the present invention provides
Figure.
In some embodiments, the Commodity Transportation loss Prediction System 300 is run in computer installation 1.It is described
It may include multiple functional modules as composed by program code segments that Prediction System 300, which is lost, in Commodity Transportation.The Commodity Transportation
The program code of each program segment in loss Prediction System 300 can store in the memory of computer installation, and by counting
Performed by least one processor in calculation machine device, to realize that function is estimated in foregoing Commodity Transportation loss.
In present embodiment, function of the Prediction System 300 according to performed by it is lost in Commodity Transportation, can be divided into more
A functional module.The functional module of the Commodity Transportation loss Prediction System 300 may include: Commodity Transportation data acquisition module
301, model training module 302, transport project obtain module 303, estimate module 304, output module 305.The present invention is so-called
Module, which refers to, a kind of performed by least one processor and can complete the series of computation machine program of fixed function
Section, storage is in memory.In the present embodiment, it will be described in detail in subsequent embodiment about the function of each module.It is each
The function of functional module will be described in detail in the following embodiments.
The Commodity Transportation data acquisition module 301 is used to obtain Commodity Transportation data, generates Commodity Transportation data set,
In, the Commodity Transportation data include the transport loss information of merchandise news, traffic condition information and commodity.
In the present embodiment, the merchandise news includes but is not limited to product name, merchandise classification, commodity packaging, rule
Lattice, quantity, item property.
The traffic condition information include but is not limited to shipping point of origin and terminal geographical location information, transit information,
Transportation range information, weather information etc..
The transport loss information includes but is not limited to that volatilization, leakage, oxidation, physical abrasion or physical impacts damage etc. are led
The loss value of the commodity of cause during transportation.It is appreciated that the transport loss information for commodity described in different commodity is different.
Model training module 302 trains the study for establishing learning model, and according to the Commodity Transportation data set
Model, wherein the input of the learning model is merchandise news and traffic condition, and the output of the learning model is transport loss
Information.
In one embodiment of the present invention, the learning model is multiple linear regression model, the model training module
302 establish learning model, and are specifically included according to the Commodity Transportation data set training learning model:
(a) multiple linear regression model is established, the multiple linear regression model indicates that Commodity Transportation loss is believed with commodity
Corresponding relationship between breath, traffic condition information, wherein the merchandise news, traffic condition information are independent variable, the commodity
Loss is dependent variable；
(b) the Commodity Transportation data set is divided into training sample set and verifying sample set；
(c) multiple linear regression model is trained using the training sample set, calculates multiple linear regression
The regression coefficient of model, obtains equation of linear regression；
(d) test verifying is carried out to above-mentioned multiple linear regression model according to the verifying sample set.
In other embodiments of the invention, the learning model is also possible to neural network model, such as AlexNet
Network model, the neural network model based on VGG, BP neural network model etc..The neural network model includes input layer, hidden
Hide layer and output layer.The merchandise news and traffic condition information are as the neural network model input layer, the commodity
Transport loss is used as output layer.After the Commodity Transportation data set is divided into training sample set and verifying sample set, pass through institute
The training sample set training neural network model is stated, model verifying is carried out by the verifying sample set.
Transport project obtains module 303 for receiving transport project information, includes to be transported in the transport project information
The merchandise news and traffic condition information of commodity.
The transport project information include but is not limited to shipping point of origin, transportation terminal, the title of commodity to be transported, classification,
Packaging, specification, quantity, item property.
The module 304 of estimating is for obtaining the transport project information input to the learning model described to be shipped
Defeated commodity are corresponding to estimate transport loss value.
The output module 305 is used to export the transport loss value estimated.
Further, the output module 305 is also used to by the transport loss value estimated compared with a preset threshold,
When the transport loss value estimated described in the determination is beyond the threshold value, information warning is issued, the transport meter for prompting user current
It is excessive to draw corresponding transport loss, user is asked to modify transport project.
Further, the transport loss value that the output module 305 is also used to estimate described in determination exceeds the threshold value
When, the transport project is corrected automatically until being lower than the threshold value using the transport loss value that the learning model is estimated, and defeated
Revised transport project is as amending advice out.
Fig. 4 is the functional block diagram for the computer installation that an embodiment of the present invention provides.The computer installation 1
Including memory 101, processor 102 and it is stored in the meter that can be run in the memory 101 and on the processor 102
Estimator is lost in calculation machine program 103, such as Commodity Transportation.The realization when processor 102 executes the computer program 103
Predictor method, such as the step S21-S25 is lost in Commodity Transportation in above method embodiment.Alternatively, the processor 102 is held
The row computer program 103 realizes the function of each module/unit in the above system embodiment, such as the module 301- in Fig. 3
305。
It will be understood by those skilled in the art that the schematic diagram 4 be only computer installation 1 example, constitute pair
The restriction of computer installation 1, computer installation 1 may include components more more or fewer than diagram, or combine certain components,
Or different components, such as the computer installation 1 can also include the power supply (such as battery) powered to all parts, it is excellent
Choosing, power supply can be logically contiguous by electric power controller and at least one described processor 102, to pass through power management
Device realizes the functions such as management charging, electric discharge and power managed.Power supply can also include one or more direct current or
AC power source, recharging device, power failure detection circuit, power adapter or inverter, power supply status indicator etc. are appointed
Meaning component.The computer installation 1 can also include multiple sensors, bluetooth module, Wi-Fi module etc., and details are not described herein.
In some embodiments, alleged processor 102 can be central processing unit (Central Processing
Unit, CPU), can also include other general processors, digital signal processor (Digital Signal Processor,
DSP), specific integrated circuit (Application Specific Integrated Circuit, ASIC), ready-made programmable gate
Array (Field-Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or crystal
Pipe logical device, discrete hardware components etc..General processor can be microprocessor or the processor be also possible to it is any often
The processor etc. of rule.
In some embodiments, the memory 101 can be used for storing the computer program 103 and/or module/mono-
Member, the processor 102 is by operation or executes the computer program that is stored in the memory 101 and/or module/mono-
Member, and the data being stored in memory 101 are called, realize the various functions of the computer installation 1.Memory 101 can
With include include read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), programmable read only memory (Programmable Read-Only Memory, PROM), erasable programmable is read-only deposits
Reservoir (Erasable Programmable Read-Only Memory, EPROM), disposable programmable read-only memory (One-
Time Programmable Read-Only Memory, OTPROM), electronics erasing type can make carbon copies read-only memory
(Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact
Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage or can
For carrying or any other computer-readable medium of storing data.
If the integrated module/unit of the computer installation 1 is realized in the form of SFU software functional unit and as independence
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, of the invention
It realizes all or part of the process in above-described embodiment method, can also instruct relevant hardware come complete by computer program
At the computer program can be stored in a computer readable storage medium, which is being executed by processor
When, it can be achieved that the step of above-mentioned each embodiment of the method.It should be noted that the content that the computer-readable medium includes can
To carry out increase and decrease appropriate according to the requirement made laws in jurisdiction with patent practice, such as in certain jurisdictions, root
It does not include electric carrier signal and telecommunication signal according to legislation and patent practice, computer-readable medium.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " does not exclude other units or steps, and odd number is not excluded for plural number.It is stated in computer installation claim
Multiple units or computer installation can also be implemented through software or hardware by the same unit or computer installation.The
One, the second equal words are used to indicate names, and are not indicated any particular order.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, those skilled in the art should understand that, it can be to of the invention
Technical solution is modified or equivalent replacement, without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. predictor method is lost in a kind of Commodity Transportation, which is characterized in that the described method includes:
Transport project information is received, includes the merchandise news and traffic condition letter of commodity to be transported in the transport project information
Breath；
By the transport project information input to default learning model, obtains corresponding estimate of the commodity to be transported and transport loss
Value.
2. predictor method is lost in Commodity Transportation as described in claim 1, which is characterized in that the merchandise news includes trade name
One of title, merchandise classification, commodity packaging, specification, quantity, item property are a variety of；The traffic condition information includes fortune
One of defeated beginning and end geographical location information, transit information, transport distance information, weather information are a variety of；Institute
Stating transport loss information includes the loss value of commodity during transportation.
3. predictor method is lost in Commodity Transportation as described in claim 1, which is characterized in that the method for establishing the learning model
Include:
Commodity Transportation data are obtained, Commodity Transportation data set is generated, wherein the Commodity Transportation data include merchandise news, fortune
Information is lost in the transport of defeated conditional information and commodity；
Learning model is established, and according to the Commodity Transportation data set training learning model, wherein the learning model
Input is merchandise news and traffic condition, and the output of the learning model is transport loss information.
4. as predictor method is lost in the described in any item Commodity Transportations of Claims 2 or 3, which is characterized in that the traffic condition
The geographical location information and transport distance information of shipping point of origin in information are automatic by the instruction of user terminal response control
What positioning obtained, the temporal information is to be obtained when receiving the control instruction by clock, and the weather information is
After getting the geographical location information and temporal information, the geographical position of the automatic database acquisition for connecting weather site
Set the weather information in current time.
5. predictor method is lost in Commodity Transportation as claimed in claim 3, which is characterized in that the learning model is multiple linear
Regression model, it is described to establish learning model, and include: according to the Commodity Transportation data set training learning model
Multiple linear regression model is established, the multiple linear regression model indicates Commodity Transportation loss and merchandise news, transport
Corresponding relationship between conditional information, wherein the merchandise news, traffic condition information be independent variable, the commodity wastage be because
Variable；
The Commodity Transportation data set is divided into training sample set and verifying sample set；
The multiple linear regression model is trained using the training sample set, calculates returning for multiple linear regression model
Return coefficient, obtains equation of linear regression；
Test verifying is carried out to above-mentioned multiple linear regression model according to the verifying sample set.
6. predictor method is lost in Commodity Transportation as claimed in claim 3, which is characterized in that the learning model is neural network
Model, including one or more in AlexNet network model, the neural network model based on VGG or BPNN neural network model
It is a.
7. predictor method is lost in Commodity Transportation as described in claim 1, which is characterized in that the method also includes:
The protection level to Commodity Transportation, deal prices are searched from presetting database according to the transport loss value estimated
It is recommended that.
8. predictor method is lost in Commodity Transportation as described in claim 1, which is characterized in that the method also includes:
The corresponding actual shipment loss value of the transport project is obtained, the transport project information and the actual shipment are damaged
Consumption value is stored to iterative learning data set, is iterated training to the learning model.
9. a kind of computer installation, which is characterized in that the computer installation includes processor, and the processor is deposited for executing
Realize that predictor method is lost in Commodity Transportation of any of claims 1-8 such as when the computer program stored in reservoir.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Realize that predictor method is lost in Commodity Transportation of any of claims 1-8 such as when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910471892.6A CN110175724A (en) | 2019-05-31 | 2019-05-31 | Predictor method, computer installation and storage medium is lost in Commodity Transportation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910471892.6A CN110175724A (en) | 2019-05-31 | 2019-05-31 | Predictor method, computer installation and storage medium is lost in Commodity Transportation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110175724A true CN110175724A (en) | 2019-08-27 |
Family
ID=67696919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910471892.6A Pending CN110175724A (en) | 2019-05-31 | 2019-05-31 | Predictor method, computer installation and storage medium is lost in Commodity Transportation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110175724A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919787A (en) * | 2021-10-27 | 2022-01-11 | 云舟生物科技（广州）有限公司 | Auxiliary material adding method for biological product transportation, storage medium and electronic equipment |
| CN116882734A (en) * | 2023-06-12 | 2023-10-13 | 上海朗晖慧科技术有限公司 | Supply chain data supervision system and method based on big data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070203759A1 (en) * | 2006-02-27 | 2007-08-30 | Guy Carpenter & Company | Portfolio management system with gradient display features |
| CN108681849A (en) * | 2018-03-29 | 2018-10-19 | 宏图物流股份有限公司 | A kind of method and device that cargo transport is fixed a price automatically |
-
2019
- 2019-05-31 CN CN201910471892.6A patent/CN110175724A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070203759A1 (en) * | 2006-02-27 | 2007-08-30 | Guy Carpenter & Company | Portfolio management system with gradient display features |
| CN108681849A (en) * | 2018-03-29 | 2018-10-19 | 宏图物流股份有限公司 | A kind of method and device that cargo transport is fixed a price automatically |
Non-Patent Citations (1)
| Title |
|---|
| 刘颖: "《考虑损耗的鲜果供应链运作优化》", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919787A (en) * | 2021-10-27 | 2022-01-11 | 云舟生物科技（广州）有限公司 | Auxiliary material adding method for biological product transportation, storage medium and electronic equipment |
| CN116882734A (en) * | 2023-06-12 | 2023-10-13 | 上海朗晖慧科技术有限公司 | Supply chain data supervision system and method based on big data |
| CN116882734B (en) * | 2023-06-12 | 2024-04-26 | 上海朗晖慧科技术有限公司 | Supply chain data supervision system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220343387A1 (en) | Dynamic processing of electronic messaging data and protocols to automatically generate location predictive retrieval using a networked, multi-stack computing environment | |
| US11468457B2 (en) | Logistic demand forecasting | |
| Tsang et al. | Integrating Internet of Things and multi-temperature delivery planning for perishable food E-commerce logistics: A model and application | |
| US20230410030A1 (en) | Systems, methods, and devices for generating a shipment order based on wireless tracker information | |
| EP3350729B1 (en) | Systems and methods for recommending personalized content | |
| US20160042321A1 (en) | Systems and methods for providing logistics data | |
| US8407154B1 (en) | Predicting shipment origin points | |
| US20150046361A1 (en) | Methods and systems for managing shipped objects | |
| US20180322452A1 (en) | Centralized monitoring and coordination of merchandise transportation using shipping containers | |
| CN107767092B (en) | Processing method, display method and device of commodity object information | |
| CN105612540A (en) | A cargo shipment route determination apparatus and method | |
| CN110648096A (en) | Distribution line generation method and device | |
| US20120239493A1 (en) | System and method for inventory tracking | |
| US20120239499A1 (en) | System and method for targeted advertising | |
| US11783281B2 (en) | System and methods for self-adjusting electronic reconciliation of a contribution amount and delivery value | |
| CN110175724A (en) | Predictor method, computer installation and storage medium is lost in Commodity Transportation | |
| US20200051020A1 (en) | Method and system to predict cost of transportation of goods | |
| CN116109252A (en) | Warehouse replenishment management method and device, warehouse management system and storage medium | |
| US10902379B2 (en) | System for customized unrequested item resolution | |
| JP2024060278A (en) | Information processing device, information processing method, and program | |
| US11216780B1 (en) | Systems and methods for coordinating supply efforts | |
| JP2022171577A (en) | Program, method, and information processing device | |
| Figliozzi et al. | E-grocery home delivery impacts on food distribution, access and equity: A Portland case study | |
| TW201415390A (en) | A system and method for immediate business of mobile shop | |
| Yusoff et al. | Adoption of Parcel Locker in Malaysia: Literature Review and Research Agenda. |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190827 |