CN108491951A - A kind of prediction technique, device and electronic equipment for taking out distribution time - Google Patents
A kind of prediction technique, device and electronic equipment for taking out distribution time Download PDFInfo
- Publication number
- CN108491951A CN108491951A CN201810073747.8A CN201810073747A CN108491951A CN 108491951 A CN108491951 A CN 108491951A CN 201810073747 A CN201810073747 A CN 201810073747A CN 108491951 A CN108491951 A CN 108491951A
- Authority
- CN
- China
- Prior art keywords
- stand
- period
- order
- order information
- sample
- 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
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
Abstract
The present invention provides it is a kind of take out distribution time prediction technique, device and electronic equipment, the method includes:Receive order information;The order number being connected to based on the corresponding businessman of the order information, the currently outstanding order number of the businessman and dispatching person, pass through the first prediction model, the first stand-by period for the order information is obtained, the first stand-by period of the order information is that the order information was generated to the stand-by period prepared between dispensing;Based on first stand-by period, the corresponding dispatching distance of the order information, pass through the second prediction model, the second stand-by period for the order information is obtained, the second stand-by period of the order information is that the order information was generated to the stand-by period being distributed between destination.It solves and does not consider businessman in first technology and go out to eat influence of the stand-by period to total distribution time of time and dispatching person, the problem of to be unable to Accurate Prediction total distribution time, it can predict that businessman goes out to eat time and the stand-by period of dispatching person, improve the prediction accuracy of total distribution time.
Description
Technical field
The present embodiments relate to field of computer technology more particularly to a kind of prediction technique for taking out distribution time, dresses
It sets and electronic equipment.
Background technology
With the rapid development of network, suscribes to take-away on the net and facilitate people’s lives.However, the distribution time taken out is often
Directly affect scoring of the people to businessman.Therefore, prediction distribution time can alleviate user and wait for when taking out to prompt user
Anxiety.
In first technology, distribution time is predicted by two schemes.The first scheme manually extracts tune according to dispatching scene
Feature takes out distribution time using RF (Random Forest, random forest) and linear regression algorithm prediction.Second scheme,
Go out the prediction model of time of eating for businessman by machine learning and deep learning structure, when predicting that the businessman of each order goes out to eat
Between.
As can be seen that above two scheme do not consider businessman go out to eat time and dispatching person stand-by period to always matching
The influence for sending the time, to be unable to the total distribution time of Accurate Prediction.
Invention content
The present invention provides a kind of prediction technique, device and electronic equipment for taking out distribution time, to solve in the prior art
Take out the above problem of distribution time prediction.
According to the first aspect of the invention, a kind of prediction technique for taking out distribution time is provided, the method includes:
Receive order information;
It is connected to based on the corresponding businessman of the order information, the currently outstanding order number of the businessman and dispatching person
Order number obtains the first stand-by period for the order information by the first prediction model, and the of the order information
One stand-by period was that the order information was generated to the stand-by period prepared between dispensing;
It is obtained by the second prediction model based on first stand-by period, the corresponding dispatching distance of the order information
For the second stand-by period of the order information, the second stand-by period of the order information be the order information generate to
The stand-by period being distributed between destination.
According to the second aspect of the invention, a kind of prediction meanss for taking out distribution time are provided, described device includes:
Order information receiving module, for receiving order information;
First stand-by period prediction module, for currently not complete based on the corresponding businessman of the order information, the businessman
At the order number that is connected to of order number and dispatching person for the order information is obtained by the first prediction model
The first stand-by period of one stand-by period, the order information are that the order information is generated to when preparing the waiting between dispensing
Between;
Second stand-by period prediction module, for based on first stand-by period, the corresponding dispatching of the order information
Distance obtains the second stand-by period for the order information by the second prediction model, and second etc. of the order information
Wait for that the time is that the order information was generated to the stand-by period being distributed between destination.
According to the third aspect of the invention we, a kind of electronic equipment is provided, including:
Processor, memory and it is stored in the computer journey that can be run on the memory and on the processor
Sequence, which is characterized in that the processor realizes the aforementioned prediction technique for taking out distribution time when executing described program.
According to the fourth aspect of the invention, a kind of readable storage medium storing program for executing is provided, which is characterized in that when the storage medium
In instruction by electronic equipment processor execute when so that electronic equipment be able to carry out it is aforementioned take out distribution time prediction side
Method.
An embodiment of the present invention provides a kind of prediction technique, device and electronic equipment for taking out distribution time, the methods
Including:Receive order information;Based on the corresponding businessman of the order information, the currently outstanding order number of the businessman and match
The order number that the person of sending is connected to obtains the first stand-by period for the order information by the first prediction model, described to order
First stand-by period of single information is that the order information was generated to the stand-by period prepared between dispensing;Based on described first etc.
It waits for time, the order information corresponding dispatching distance, by the second prediction model, obtains second for the order information
The second stand-by period of stand-by period, the order information are that the order information is generated to the waiting being distributed between destination
Time.Solve do not consider in first technology businessman go out to eat time and dispatching person stand-by period to total distribution time
It influences, the problem of to be unable to Accurate Prediction total distribution time, can predict that businessman goes out to eat time and the stand-by period of dispatching person,
Improve the prediction accuracy of total distribution time.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of prediction technique specific steps of take-away distribution time under system architecture provided in an embodiment of the present invention
Flow chart;
Fig. 2 is that another prediction technique for taking out distribution time under system architecture provided in an embodiment of the present invention specifically walks
Rapid flow chart;
Fig. 3 is a kind of structure chart of prediction meanss for taking out distribution time provided in an embodiment of the present invention;
Fig. 4 is the structure chart of another prediction meanss for taking out distribution time provided in an embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained without creative efforts
Example, shall fall within the protection scope of the present invention.
Embodiment one
Referring to Fig.1, it illustrates a kind of step flow charts of the mobile prediction technique for taking out distribution time, including:
Step 101, order information is received.
Wherein, order information includes:Destination, order contents, Business Information, order price etc..
In practical applications, user can place an order to businessman by the application platform of such as " U.S. rolls into a ball ".
Specifically, first, user entered keyword scans for, and obtains at least one businessman;Then, for each businessman's
Details determine final target businessman, and place an order to target businessman, to which platform can detect the behaviour that places an order of user
Make.
Step 102, the corresponding businessman of the order information, the currently outstanding order number of the businessman and dispatching are based on
The order number that member is connected to obtains the first stand-by period for the order information, the order by the first prediction model
First stand-by period of information is that the order information was generated to the stand-by period prepared between dispensing.
The embodiment of the present invention is suitable for estimating the distribution time for taking out order.In practical applications, user place an order to
It includes two periods to take out the time being distributed between destination mainly:User place an order to dispatching person take take-away between
The period of period, order on the way.
Wherein, user places an order takes the period between taking out as first etc. of concern of the embodiment of the present invention to dispatching person
Wait for the time, it is related to the order number for coming the backlog number of front, dispatching person is connected to.The period of order on the way
It is mainly related to food delivery distance, traffic, weather conditions etc. for the distribution time of order.
In practical applications, since to go out speed of eating also different by different businessmans, hence for different businessmans, the first prediction model
Also different.
For order information, comes the unfinished order number in front and also directly affected for the first stand-by period.Normal conditions
Under, come that the unfinished order number in front is more, and the first stand-by period of order information is longer;What is do not completed before coming orders
Singular mesh is fewer, and the first stand-by period of order information is shorter.
The order number that dispatching person is connected to also directly affects the first stand-by period of order information.Under normal conditions, order
Number is more, and the first stand-by period is longer;Order number is fewer, and the first stand-by period is shorter.
In embodiments of the present invention, the input of the first prediction model is that the corresponding businessman of order information, the businessman are current
The order number that unfinished order number and dispatching person are connected to exports the first stand-by period for order information.
Wherein, the first prediction model can first pass through deep learning in advance and acquire.
Step 103, it is based on first stand-by period, the corresponding dispatching distance of the order information, passes through the second prediction
Model obtains the second stand-by period for the order information, and the second stand-by period of the order information is the order
Information was generated to the stand-by period being distributed between destination.
In practical applications, the first stand-by period was included in the second stand-by period, and the first stand-by period is bigger, and second etc.
Wait for that the time is bigger;First stand-by period is smaller, and the second stand-by period is smaller.
The corresponding dispatching of order information is apart from the distance between corresponding merchant to order destination.Order information is corresponding to match
Send distance bigger, the second stand-by period is longer;For the corresponding dispatching of order information apart from smaller, the second stand-by period is shorter.
Weather conditions can also influence to dispense speed, to influence for the second stand-by period.For example, for fine day, speed is dispensed
Comparatively fast, to which the second stand-by period is shorter;For sleety weather, dispatching speed is slower, to which the second stand-by period is longer.
Traffic can also influence to dispense speed, to influence for the second stand-by period.For example, traffic is good, dispatching
Speed, to which the second stand-by period is shorter;Traffic jam, dispatching speed is slower, to which the second stand-by period is longer.
In embodiments of the present invention, the input of the second prediction model is order information corresponding first stand-by period, order
The corresponding dispatching distance of information, weather conditions and traffic, export the second stand-by period for order information.
Wherein, the second prediction model can first pass through deep learning in advance and acquire.
In conclusion an embodiment of the present invention provides a kind of prediction technique for taking out distribution time, the method includes:It connects
Receive order information;It is connect based on the corresponding businessman of the order information, the currently outstanding order number of the businessman and dispatching person
The order number arrived obtains the first stand-by period for the order information, the order information by the first prediction model
The first stand-by period be the order information generate to prepare dispense between stand-by period;When being waited for based on described first
Between, the corresponding dispatching distance of the order information, by the second prediction model, obtain for the order information second wait for
The second stand-by period of time, the order information are that the order information is generated to when the waiting being distributed between destination
Between.The stand-by period that the first stand-by period of businessman and dispatching person are not considered in first technology is solved to total distribution time
Influence, the problem of to be unable to Accurate Prediction total distribution time, can predict the first stand-by period of businessman and dispatching person etc.
It waits for the time, improves the prediction accuracy of total distribution time.
Embodiment two
The embodiment of the present application is described the prediction technique for optionally taking out distribution time from the level of system architecture.
With reference to Fig. 2, it illustrates the specific steps flow charts of another prediction technique for taking out distribution time.
Step 201, the order sample set based on specified businessman, training obtain the first prediction mould for the first stand-by period
Type, the one of which order sample in the order sample set include at least:Not not completing before current order of lower list time
The order number and the sample value of the first stand-by period that order number, dispatching person are connected to.
Specifically, the embodiment of the present invention passes through GRU (Gated Recurrent Units, the gate in depth learning technology
Cycling element) model, order sample set is trained to obtain the first prediction model.GRU is extensive in sequence and time data
Using.
Wherein, order sample set can be from collection in the application of actual motion.For example, for the application of group of U.S., can collect
The order sample of specified businessman, and according to lower single time count backlog number before each order and record place an order to
Order leaves the period between businessman, and obtains and dispense the order number that the dispatching person of the order is connected to.
Optionally, in another embodiment of the invention, step 201 includes sub-step 2011 to 2014:
Sub-step 2011 initializes the parameter group of the first prediction model.
Specifically, parameter group can be initialized as empirical value.If can not determine empirical value, it can tentatively judge to select
Preferably parameter group.
Sub-step 2012, each order sample in order sample set for specifying businessman order lower single time currently
The order number that backlog number before list, dispatching person are connected to is input to the first prediction model, obtains the order sample
The predicted value of corresponding first stand-by period.
In practical applications, it can be trained by job order sample, batch size can be according to practical application field
Scape is set, and the embodiment of the present invention does not limit it.
When batch size is N, by backlog of N number of order sample corresponding lower single time before current order
The order number that number, dispatching person are connected to, is input to the first prediction model, obtains each order sample corresponding first stand-by period
Predicted value.
Sub-step 2013 determines penalty values according to the predicted value of first stand-by period and sample value.
In practical applications, penalty values are weighed generally according to the mean square deviation of predicted value and sample value.Specific formula is as follows:
Wherein, N is the batch size of sample, f (xi) be i-th of order sample the first stand-by period predicted value, yiFor
The sample value of first stand-by period of i-th of order sample.
Sub-step 2014, if the penalty values are unsatisfactory for preset condition, according to the penalty values adjusting parameter group with after
Continuous training obtains the first prediction model for first stand-by period until the penalty values meet preset condition.
Specifically, when penalty values are less than or equal to preset value, penalty values is represented and meet preset condition;Otherwise, penalty values are represented
It is unsatisfactory for preset condition.
Preset condition can be set according to practical application scene.It is appreciated that when penalty values meet preset condition, determine
Training has restrained, to which corresponding parameter group is target component group at this time;When penalty values are unsatisfactory for preset condition, adjustment ginseng
Each parameter value in array, and new a collection of order sample is obtained to continue to train, until penalty values meet preset condition.
It is appreciated that training is exactly the parameter group in training pattern, so that prediction model prediction is most accurate.
Step 202, it is directed to different weather situation, traffic respectively, is based on the order sample set and described first
The first stand-by period that prediction model obtains each order sample predictions in the order sample set, training obtain being directed to second
The second prediction model of stand-by period, the one of which order sample in the order sample set include at least:Current order pair
The dispatching distance and the sample value of the second stand-by period answered.
Specifically, the embodiment of the present invention passes through DNN (Deep neural network, the depth god in depth learning technology
Through network) model, it is trained to obtain the second prediction model.
Prediction result of the training of second prediction model based on the first prediction model, to train it in the first prediction model
After carry out.
The embodiment of the present invention is trained by typical weather conditions, the sample data of traffic, is obtained not on the same day
The second prediction model under vaporous condition, traffic.For example, weather conditions include two kinds of fine day, sleet sky, traffic includes
It is smooth, slightly block, it is super block three kinds, so as to respectively by fine day and road is smooth, fine day and road slightly block, fine day and
Road surpasses blocking, sample data, sleet sky and road is smooth, sleet sky and road slightly blocks, sleet sky and road are super blocks
The sample data of six kinds of scenes, training obtain six kind of second prediction model.
Optionally, in another embodiment of the invention, step 202 includes sub-step 2021 to 2024:
Sub-step 2021 initializes the parameter group of the second prediction model.
Specifically, parameter group can be initialized as empirical value.If can not determine empirical value, it can tentatively judge to select
Preferably parameter group.
Sub-step 2022, for each order sample in the order sample set, by the order sample corresponding first
Stand-by period and dispatching distance input obtain the order sample corresponding second stand-by period to second prediction model
Predicted value.
In practical applications, it can be trained by job order sample, batch size can be according to practical application field
Scape is set, and the embodiment of the present invention does not limit it.
When batch size is N, by N number of order sample corresponding first stand-by period and dispatching distance, it is input to the
Two prediction models obtain the predicted value of each order sample corresponding second stand-by period.
Sub-step 2023 determines loss according to the predicted value of the second stand-by period of all order samples and sample value
Value.
The embodiment of the present invention increases punishment of the predicted value less than sample value when on the basis of the penalty values that mean-square value determines
Dynamics, so as to meet the in-mind anticipation of user as far as possible, by the total distribution time estimated as possible close to the base of actual value
Larger predicted value is biased on plinth.
Optionally, in another embodiment of the invention, step 2023 includes sub-step 20231 to 20234:
Sub-step 20231 calculates the sample value of the order corresponding second stand-by period and pre- for each order sample
The quadratic power of difference between measured value, obtains the first difference.
It is appreciated that the first difference corresponds to the mean square deviation between sample value and predicted value.
Specifically, for i-th of order sample, the first mathematic interpolation formula is as follows:
c1=(zi-φ(xi))2 (2)
Wherein, φ (xi) be i-th of order sample the second stand-by period predicted value, ziIt is the of i-th of order sample
The sample value of two stand-by period.
Sub-step 20232 calculates the difference between the sample value and predicted value of second stand-by period, and takes the difference
Value and zero maximum value, obtain the second difference.
It is appreciated that the second difference corresponds to the punishment dynamics increased.
Specifically, for i-th of order sample, the second mathematic interpolation formula is as follows:
c2=max (0, (zi-φ(xi))) (3)
Wherein, max can take the maximum value between the difference and zero between the sample value and predicted value of the second stand-by period,
To, when the sample value of the second stand-by period be more than or equal to predicted value when, the second difference take the second stand-by period sample value and
Difference between predicted value;When the sample value of the second stand-by period is less than predicted value, the second difference takes zero.
First difference and second difference value are obtained third difference by sub-step 20233.
Specifically, for i-th of order sample, the formula of third difference is as follows:
c3=c1+c2=(zi-φ(xi))2+max(0,(zi-φ(xi))) (4)
When the sample value of the second stand-by period be more than or equal to predicted value when, third difference by sample value and predicted value difference
Difference between quadratic sum sample value and predicted value determines;When the sample value of the second stand-by period is less than predicted value, third is poor
Value is determined by the squared difference of sample value and predicted value.
Sub-step 20234 counts the average value of the corresponding third difference of all order samples, obtains penalty values.
Specifically, penalty values can be calculated according to following formula:
It is appreciated that M can be identical with N, can also be different, the embodiment of the present invention does not limit it.
Sub-step 2024, if the penalty values are unsatisfactory for preset condition, according to the penalty values adjusting parameter group with after
Continuous training obtains the second prediction model for second stand-by period until the penalty values meet preset condition.
The step is referred to the detailed description of sub-step 2014, and details are not described herein.
Step 203, order information is received.
The step is referred to the detailed description of sub-step 101, and details are not described herein.
Step 204, the corresponding businessman of the order information, the currently outstanding order number of the businessman and dispatching are based on
The order number that member is connected to obtains the first stand-by period for the order information, the order by the first prediction model
First stand-by period of information is that the order information was generated to the stand-by period prepared between dispensing.
The step is referred to the detailed description of step 102, and details are not described herein.
Step 205, it is based on first stand-by period, the corresponding dispatching distance of the order information, passes through the second prediction
Model obtains the second stand-by period for the order information, and the second stand-by period of the order information is the order
Information was generated to the stand-by period being distributed between destination.
The step is referred to the detailed description of step 103, and details are not described herein.
It should be noted that according to the detailed description in step 202, different weather situation, traffic tune can be directed to
With different models, determined for the second stand-by period.For example, weather conditions include two kinds of fine day, sleet sky, traffic includes suitable
Freely, slightly block, it is super block three kinds, so as to respectively by fine day and road is smooth, fine day and road slightly block, fine day and road
Road is super to be blocked, sleet sky and road are smooth, sleet sky and road slightly block, the super blocking of sleet sky and road is six kind second corresponding
Prediction model obtains the second stand-by period under different weather situation, traffic.
In conclusion an embodiment of the present invention provides a kind of prediction technique for taking out distribution time, the method includes:It connects
Receive order information;It is connect based on the corresponding businessman of the order information, the currently outstanding order number of the businessman and dispatching person
The order number arrived obtains the first stand-by period for the order information, the order information by the first prediction model
The first stand-by period be the order information generate to prepare dispense between stand-by period;When being waited for based on described first
Between, the corresponding dispatching distance of the order information, by the second prediction model, obtain for the order information second wait for
The second stand-by period of time, the order information are that the order information is generated to when the waiting being distributed between destination
Between.Solve do not consider in first technology businessman go out to eat time and dispatching person stand-by period to the shadow of total distribution time
It rings, the problem of to be unable to Accurate Prediction total distribution time, can predict that businessman goes out to eat time and the stand-by period of dispatching person, carry
The high prediction accuracy of total distribution time.Further, it is also possible to train prediction model in advance, and loss function is adjusted, so that
Total distribution time is biased to larger predicted value on the basis of as possible close to actual value.
Embodiment three
It is specific as follows it illustrates a kind of structure chart of prediction meanss that taking out distribution time with reference to Fig. 3.
Order information receiving module 301, for receiving order information.
First stand-by period prediction module 302, for being based on the corresponding businessman of the order information, the businessman currently not
The order number that the order number of completion and dispatching person are connected to is obtained by the first prediction model for the order information
The first stand-by period of first stand-by period, the order information are that the order information is generated to the waiting prepared between dispensing
Time.
Second stand-by period prediction module 303, for being based on, first stand-by period, the order information is corresponding matches
Distance is sent, by the second prediction model, obtains the second stand-by period for the order information, the second of the order information
Stand-by period is that the order information was generated to the stand-by period being distributed between destination.
In conclusion an embodiment of the present invention provides a kind of prediction meanss for taking out distribution time, described device includes:It orders
Single information receiving module, for receiving order information;First stand-by period prediction module, for being corresponded to based on the order information
The order number that is connected to of businessman, the currently outstanding order number of the businessman and dispatching person obtained by the first prediction model
The first stand-by period to the first stand-by period for the order information, the order information generates for the order information
To the stand-by period prepared between dispensing;Second stand-by period prediction module, for being based on first stand-by period, described ordering
The corresponding dispatching distance of single information obtains the second stand-by period for the order information by the second prediction model, described
Second stand-by period of order information is that the order information was generated to the stand-by period being distributed between destination.It solves
Do not consider businessman in first technology to go out to eat influence of the stand-by period to total distribution time of time and dispatching person, to cannot
The problem of Accurate Prediction total distribution time, it can predict that businessman goes out to eat time and the stand-by period of dispatching person, improve total dispatching
The prediction accuracy of time.
Example IV
It is specific as follows it illustrates the structure chart of another prediction meanss for taking out distribution time with reference to Fig. 4.
First prediction model training module 401, is used for the order sample set based on specified businessman, and training obtains being directed to first
The first prediction model of stand-by period, the one of which order sample in the order sample set include at least:The lower list time will exist
The order number and the sample value of the first stand-by period that backlog number before current order, dispatching person are connected to.
Optionally, in another embodiment of the invention, above-mentioned first prediction model training module 401, including:
First parameter group initialization submodule, the parameter group for initializing the first prediction model.
First stand-by period predicted submodule, will for each order sample in the order sample set for specifying businessman
The order number that lower backlog number of the list time before current order, dispatching person are connected to is input to the first prediction model,
Obtain the predicted value of the order sample corresponding first stand-by period.
First-loss value determination sub-module is damaged for being determined according to the predicted value and sample value of first stand-by period
Mistake value.
First parameter group adjusts submodule, if being unsatisfactory for preset condition for the penalty values, according to the penalty values
Adjusting parameter group is to continue to train, until the penalty values meet preset condition, obtains for first stand-by period
One prediction model.
Second prediction model training module 402 is directed to different weather situation, traffic respectively, is based on the order sample
When the first waiting that this collection and first prediction model obtain each order sample predictions in the order sample set
Between, training obtains the second prediction model for the second stand-by period, the one of which order sample in the order sample set
It includes at least:The corresponding dispatching distance of current order and the sample value of the second stand-by period.
Optionally, in another embodiment of the invention, above-mentioned second prediction model training module 402, including:
Second parameter group initialization submodule, the parameter group for initializing the second prediction model.
Second stand-by period predicted submodule, for for each order sample in the order sample set, being ordered described
Single sample corresponding first stand-by period and dispatching distance input obtain the order sample pair to second prediction model
The predicted value for the second stand-by period answered.
Second penalty values determination sub-module is used for the predicted value and sample of the second stand-by period according to all order samples
This value determines penalty values.
Optionally, in another embodiment of the invention, above-mentioned second penalty values determination sub-module, including:
First difference computational unit, for for each order sample, calculating the order corresponding second stand-by period
The quadratic power of difference between sample value and predicted value, obtains the first difference.
Second difference computational unit, the difference between sample value and predicted value for calculating second stand-by period,
And the difference and zero maximum value are taken, obtain the second difference.
Third difference computational unit, for by first difference and second difference value, obtaining third difference;
Penalty values determination unit, the average value for counting the corresponding third difference of all order samples, obtains penalty values.
Second parameter group adjusts submodule, if being unsatisfactory for preset condition for the penalty values, according to the penalty values
Adjusting parameter group is to continue to train, until the penalty values meet preset condition, obtains for second stand-by period
Two prediction models.
Order information receiving module 403, for receiving order information.
First stand-by period prediction module 404, for being based on the corresponding businessman of the order information, the businessman currently not
The order number that the order number of completion and dispatching person are connected to is obtained by the first prediction model for the order information
The first stand-by period of first stand-by period, the order information are that the order information is generated to the waiting prepared between dispensing
Time.
Second stand-by period prediction module 405, for being based on, first stand-by period, the order information is corresponding matches
Distance is sent, by the second prediction model, obtains the second stand-by period for the order information, the second of the order information
Stand-by period is that the order information was generated to the stand-by period being distributed between destination.
In conclusion an embodiment of the present invention provides a kind of prediction meanss for taking out distribution time, described device includes:The
One prediction model training module, is used for the order sample set based on specified businessman, and training obtains for the first stand-by period
One prediction model, the one of which order sample in the order sample set include at least:The lower list time is before current order
Backlog number, the order number that is connected to of dispatching person and the sample value of the first stand-by period;Second prediction model is instructed
Practice module, be directed to different weather situation, traffic respectively, is based on the order sample set and first prediction model
To the first stand-by period that each order sample predictions in the order sample set obtain, training obtains being directed to for the second stand-by period
The second prediction model, the one of which order sample in the order sample set includes at least:The corresponding dispatching of current order
Distance and the sample value of the second stand-by period;Order information receiving module, for receiving order information;First stand-by period is pre-
Module is surveyed, is connect for being based on the corresponding businessman of the order information, the currently outstanding order number of the businessman and dispatching person
The order number arrived obtains the first stand-by period for the order information, the order information by the first prediction model
The first stand-by period be the order information generate to prepare dispense between stand-by period;Second stand-by period predicted mould
Block, for being obtained by the second prediction model based on first stand-by period, the corresponding dispatching distance of the order information
For the second stand-by period of the order information, the second stand-by period of the order information be the order information generate to
The stand-by period being distributed between destination.It solves and does not consider businessman in first technology and go out to eat time and dispatching person
Influence of the stand-by period to total distribution time the problem of to be unable to Accurate Prediction total distribution time, can predict that businessman goes out meal
The stand-by period of time and dispatching person improve the prediction accuracy of total distribution time.Further, it is also possible to the mould of training prediction in advance
Type, and loss function is adjusted, so that total distribution time is biased to larger predicted value on the basis of as possible close to actual value.
The embodiment of the present invention additionally provides a kind of electronic equipment, including:Processor, memory and it is stored in the storage
On device and the computer program that can run on the processor, which is characterized in that the processor executes real when described program
The prediction technique of the take-away distribution time of existing previous embodiment.
The embodiment of the present invention additionally provides a kind of readable storage medium storing program for executing, when the instruction in the storage medium is by electronic equipment
Processor execute when so that electronic equipment be able to carry out previous embodiment take-away distribution time prediction technique.
For device embodiments, since it is basically similar to the method embodiment, so fairly simple, the correlation of description
Place illustrates referring to the part of embodiment of the method.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention:It is i.e. required to protect
Shield the present invention claims the more features of feature than being expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific implementation mode are expressly incorporated in the specific implementation mode, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in the one or more equipment different from the embodiment.It can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it may be used any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, abstract and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
It replaces.
The all parts embodiment of the present invention can be with hardware realization, or to run on one or more processors
Software module realize, or realized with combination thereof.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) realize the pre- measurement equipment according to the ... of the embodiment of the present invention for taking out distribution time
In some or all components some or all functions.The present invention is also implemented as described herein for executing
Some or all equipment or program of device of method.It is such to realize that the program of the present invention be stored in computer
On readable medium, or can be with the form of one or more signal.Such signal can be above and below internet website
Load obtains, and either provides on carrier signal or provides in any other forms.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be by the same hardware branch
To embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and be run after fame
Claim.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement etc., should all be included in the protection scope of the present invention made by within refreshing and principle.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (10)
1. a kind of prediction technique for taking out distribution time, which is characterized in that the method includes:
Receive order information;
The order being connected to based on the corresponding businessman of the order information, the currently outstanding order number of the businessman and dispatching person
Number obtains the first stand-by period for the order information by the first prediction model, and first etc. of the order information
Wait for that the time is that the order information was generated to the stand-by period prepared between dispensing;
It is directed to by the second prediction model based on first stand-by period, the corresponding dispatching distance of the order information
The second stand-by period of second stand-by period of the order information, the order information are that the order information is generated to dispatching
To the stand-by period between destination.
2. according to the method described in claim 1, it is characterized in that, the method further includes:
Order sample set based on specified businessman, training obtain the first prediction model for the first stand-by period, the order
One of which order sample in sample set includes at least:Lower backlog number of the list time before current order is matched
The order number and the sample value of the first stand-by period that the person of sending is connected to.
3. according to the method described in claim 2, it is characterized in that, the order sample set based on specified businessman, trained
The step of to the first prediction model for the first stand-by period, including:
Initialize the parameter group of the first prediction model;
Each order sample in order sample set for specifying businessman orders unfinished before current order of lower single time
Odd number, the order number that is connected to of dispatching person are input to the first prediction model, when obtaining the order sample corresponding first and waiting for
Between predicted value;
Penalty values are determined according to the predicted value of first stand-by period and sample value;
If the penalty values are unsatisfactory for preset condition, according to the penalty values adjusting parameter group to continue to train, until described
Penalty values meet preset condition, obtain the first prediction model for first stand-by period.
4. according to the method in claim 2 or 3, which is characterized in that the method further includes:
It is directed to different weather situation, traffic respectively, based on the order sample set and first prediction model to institute
State the first stand-by period that each order sample predictions in order sample set obtain, training obtains for the second stand-by period
Two prediction models, the one of which order sample in the order sample set include at least:The corresponding dispatching distance of current order
And second the stand-by period sample value.
5. according to the method described in claim 4, it is characterized in that, predicted based on first prediction model
The step of one waits for time samples collection, and training obtains the second prediction model for the second stand-by period, including:
Initialize the parameter group of the second prediction model;
For each order sample in the order sample set, by the order sample corresponding first stand-by period and dispatching
Distance input obtains the predicted value of the order sample corresponding second stand-by period to second prediction model;
Penalty values are determined according to the predicted value of the second stand-by period of all order samples and sample value;
If the penalty values are unsatisfactory for preset condition, according to the penalty values adjusting parameter group to continue to train, until described
Penalty values meet preset condition, obtain the second prediction model for the second stand-by period.
6. according to the method described in claim 5, it is characterized in that, second stand-by period according to all order samples
The step of predicted value and sample value determine penalty values, including:
For each order sample, two of difference between the sample value and predicted value of the order corresponding second stand-by period are calculated
Power obtains the first difference;
The difference between the sample value and predicted value of second stand-by period is calculated, and takes the difference and zero maximum value,
Obtain the second difference;
By first difference and second difference value, third difference is obtained;
The average value for counting the corresponding third difference of all order samples, obtains penalty values.
7. a kind of prediction meanss for taking out distribution time, which is characterized in that described device includes:
Order information receiving module, for receiving order information;
First stand-by period prediction module, for currently outstanding based on the corresponding businessman of the order information, the businessman
The order number that order number and dispatching person are connected to obtains first etc. for the order information by the first prediction model
It waits for the time, the first stand-by period of the order information is that the order information was generated to the stand-by period prepared between dispensing;
Second stand-by period prediction module, for being based on first stand-by period, the corresponding dispatching distance of the order information,
By the second prediction model, the second stand-by period for the order information is obtained, the second of the order information when waiting for
Between be that the order information was generated to the stand-by period being distributed between destination.
8. the apparatus according to claim 1, which is characterized in that described device further includes:
First prediction model training module is used for the order sample set based on specified businessman, when training obtains waiting for for first
Between the first prediction model, the one of which order sample in the order sample set includes at least:The lower list time will order currently
The order number and the sample value of the first stand-by period that backlog number before list, dispatching person are connected to.
9. a kind of electronic equipment, which is characterized in that including:
Processor, memory and it is stored in the computer program that can be run on the memory and on the processor,
It is characterized in that, the processor realizes the take-away dispatching as described in one or more in claim 1-6 when executing described program
The prediction technique of time.
10. a kind of readable storage medium storing program for executing, which is characterized in that when the instruction in the storage medium is held by the processor of electronic equipment
When row so that electronic equipment is able to carry out the pre- of the take-away distribution time as described in one or more in claim to a method 1-6
Survey method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810073747.8A CN108491951A (en) | 2018-01-25 | 2018-01-25 | A kind of prediction technique, device and electronic equipment for taking out distribution time |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810073747.8A CN108491951A (en) | 2018-01-25 | 2018-01-25 | A kind of prediction technique, device and electronic equipment for taking out distribution time |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108491951A true CN108491951A (en) | 2018-09-04 |
Family
ID=63343723
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810073747.8A Pending CN108491951A (en) | 2018-01-25 | 2018-01-25 | A kind of prediction technique, device and electronic equipment for taking out distribution time |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108491951A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109063935A (en) * | 2018-09-27 | 2018-12-21 | 北京三快在线科技有限公司 | A kind of method, apparatus and storage medium of prediction task processing time |
CN109146203A (en) * | 2018-09-28 | 2019-01-04 | 北京顺丰同城科技有限公司 | Order distribution information prediction technique, device, electronic equipment and storage medium |
CN109377144A (en) * | 2018-12-14 | 2019-02-22 | 北京顺丰同城科技有限公司 | Logistics order processing method and device |
CN109993367A (en) * | 2019-04-04 | 2019-07-09 | 拉扎斯网络科技(上海)有限公司 | Dispense estimation method, estimation device, storage medium and the electronic equipment of duration |
CN110363352A (en) * | 2019-07-15 | 2019-10-22 | 武汉金康高科技有限公司 | A kind of take-away delivery management method and device |
CN110490356A (en) * | 2019-07-02 | 2019-11-22 | 北京星选科技有限公司 | Interface display method, device, electronic equipment |
CN110689177A (en) * | 2019-09-17 | 2020-01-14 | 北京三快在线科技有限公司 | Method and device for predicting order preparation time, electronic equipment and storage medium |
CN110956294A (en) * | 2018-09-26 | 2020-04-03 | 北京嘀嘀无限科技发展有限公司 | Queuing time estimation method and device |
CN110969319A (en) * | 2018-09-28 | 2020-04-07 | 北京三快在线科技有限公司 | Assessment duration determination method and device |
CN111435293A (en) * | 2019-01-11 | 2020-07-21 | 丰田自动车株式会社 | Information processing apparatus, information processing method, and program |
CN111932043A (en) * | 2020-10-12 | 2020-11-13 | 广州赛特智能科技有限公司 | Early warning method for robot distribution time |
WO2021017609A1 (en) * | 2019-07-30 | 2021-02-04 | 北京三快在线科技有限公司 | Determination of estimated time of arrival |
WO2021073237A1 (en) * | 2019-10-15 | 2021-04-22 | 北京三快在线科技有限公司 | Order assignment |
CN112802269A (en) * | 2020-12-31 | 2021-05-14 | 成都希福生物科技有限公司 | Ice powder online sale system and method |
CN112906994A (en) * | 2021-04-19 | 2021-06-04 | 拉扎斯网络科技(上海)有限公司 | Order meal delivery time prediction method and device, electronic equipment and storage medium |
CN112907011A (en) * | 2019-12-04 | 2021-06-04 | 北京三快在线科技有限公司 | Distribution scheduling method, device, storage medium and electronic equipment |
CN113205229A (en) * | 2021-05-29 | 2021-08-03 | 五八到家有限公司 | Commuting prediction time calculation method and system, electronic device and storage medium |
CN113537676A (en) * | 2020-04-20 | 2021-10-22 | 北京京东振世信息技术有限公司 | Method and device for determining completion time of transportation task |
CN113592407A (en) * | 2021-08-10 | 2021-11-02 | 深圳职业技术学院 | Commodity selling and distributing method and system |
EP3861522A4 (en) * | 2018-11-15 | 2022-04-20 | Doordash, Inc. | Depot dispatch protocol for autonomous last-mile deliveries |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170098264A1 (en) * | 2015-10-02 | 2017-04-06 | Seth Priebatsch | Cross-platform ordering and payment-processing system and method |
CN107230014A (en) * | 2017-05-15 | 2017-10-03 | 浙江仟和网络科技有限公司 | A kind of intelligent dispatching system of the instant logistics in end |
-
2018
- 2018-01-25 CN CN201810073747.8A patent/CN108491951A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170098264A1 (en) * | 2015-10-02 | 2017-04-06 | Seth Priebatsch | Cross-platform ordering and payment-processing system and method |
CN107230014A (en) * | 2017-05-15 | 2017-10-03 | 浙江仟和网络科技有限公司 | A kind of intelligent dispatching system of the instant logistics in end |
Non-Patent Citations (1)
Title |
---|
王倩影: "外卖O2O行业配送模式选择研究", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110956294B (en) * | 2018-09-26 | 2021-03-23 | 北京嘀嘀无限科技发展有限公司 | Queuing time estimation method and device |
CN110956294A (en) * | 2018-09-26 | 2020-04-03 | 北京嘀嘀无限科技发展有限公司 | Queuing time estimation method and device |
CN109063935A (en) * | 2018-09-27 | 2018-12-21 | 北京三快在线科技有限公司 | A kind of method, apparatus and storage medium of prediction task processing time |
CN109063935B (en) * | 2018-09-27 | 2020-11-03 | 北京三快在线科技有限公司 | Method, device and storage medium for predicting task processing time |
CN109146203A (en) * | 2018-09-28 | 2019-01-04 | 北京顺丰同城科技有限公司 | Order distribution information prediction technique, device, electronic equipment and storage medium |
CN110969319A (en) * | 2018-09-28 | 2020-04-07 | 北京三快在线科技有限公司 | Assessment duration determination method and device |
EP3861522A4 (en) * | 2018-11-15 | 2022-04-20 | Doordash, Inc. | Depot dispatch protocol for autonomous last-mile deliveries |
US11783282B2 (en) | 2018-11-15 | 2023-10-10 | DoorDash, Inc. | Depot dispatch protocol for autonomous last-mile deliveries |
CN109377144A (en) * | 2018-12-14 | 2019-02-22 | 北京顺丰同城科技有限公司 | Logistics order processing method and device |
CN111435293A (en) * | 2019-01-11 | 2020-07-21 | 丰田自动车株式会社 | Information processing apparatus, information processing method, and program |
CN111435293B (en) * | 2019-01-11 | 2023-10-10 | 丰田自动车株式会社 | Information processing apparatus, information processing method, and non-transitory computer-readable storage medium |
CN109993367A (en) * | 2019-04-04 | 2019-07-09 | 拉扎斯网络科技(上海)有限公司 | Dispense estimation method, estimation device, storage medium and the electronic equipment of duration |
CN110490356A (en) * | 2019-07-02 | 2019-11-22 | 北京星选科技有限公司 | Interface display method, device, electronic equipment |
CN110363352A (en) * | 2019-07-15 | 2019-10-22 | 武汉金康高科技有限公司 | A kind of take-away delivery management method and device |
WO2021017609A1 (en) * | 2019-07-30 | 2021-02-04 | 北京三快在线科技有限公司 | Determination of estimated time of arrival |
CN110689177A (en) * | 2019-09-17 | 2020-01-14 | 北京三快在线科技有限公司 | Method and device for predicting order preparation time, electronic equipment and storage medium |
WO2021073237A1 (en) * | 2019-10-15 | 2021-04-22 | 北京三快在线科技有限公司 | Order assignment |
CN112907011A (en) * | 2019-12-04 | 2021-06-04 | 北京三快在线科技有限公司 | Distribution scheduling method, device, storage medium and electronic equipment |
CN113537676A (en) * | 2020-04-20 | 2021-10-22 | 北京京东振世信息技术有限公司 | Method and device for determining completion time of transportation task |
CN113537676B (en) * | 2020-04-20 | 2023-11-03 | 北京京东振世信息技术有限公司 | Method and device for determining completion time of transportation task |
CN111932043B (en) * | 2020-10-12 | 2021-05-18 | 广州赛特智能科技有限公司 | Early warning method for robot distribution time |
CN111932043A (en) * | 2020-10-12 | 2020-11-13 | 广州赛特智能科技有限公司 | Early warning method for robot distribution time |
CN112802269A (en) * | 2020-12-31 | 2021-05-14 | 成都希福生物科技有限公司 | Ice powder online sale system and method |
CN112906994A (en) * | 2021-04-19 | 2021-06-04 | 拉扎斯网络科技(上海)有限公司 | Order meal delivery time prediction method and device, electronic equipment and storage medium |
CN112906994B (en) * | 2021-04-19 | 2023-04-07 | 拉扎斯网络科技(上海)有限公司 | Order meal delivery time prediction method and device, electronic equipment and storage medium |
CN113205229A (en) * | 2021-05-29 | 2021-08-03 | 五八到家有限公司 | Commuting prediction time calculation method and system, electronic device and storage medium |
CN113592407A (en) * | 2021-08-10 | 2021-11-02 | 深圳职业技术学院 | Commodity selling and distributing method and system |
CN113592407B (en) * | 2021-08-10 | 2022-03-29 | 深圳职业技术学院 | Commodity selling and distributing method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108491951A (en) | A kind of prediction technique, device and electronic equipment for taking out distribution time | |
Gkiotsalitis et al. | Reliable frequency determination: Incorporating information on service uncertainty when setting dispatching headways | |
CN107392512B (en) | Grouped task method and apparatus | |
CN110119847A (en) | A kind of prediction technique, device, storage medium and electronic equipment dispensing duration | |
CN110414731A (en) | Method, apparatus, computer readable storage medium and the electronic equipment of Order splitting | |
US6516301B1 (en) | Order-based material management system | |
Bayoumi et al. | Dynamic pricing for hotel revenue management using price multipliers | |
Dissanayaka et al. | Comparing contributors to time and cost performance in building projects | |
CN103593479B (en) | Application program menu recommendation method and device | |
CN109389431A (en) | Distribution method, device, electronic equipment and the readable storage medium storing program for executing of discount coupon | |
CN109873712A (en) | A kind of network flow prediction method and device | |
RU2670610C1 (en) | Method and device for processing data of user operation | |
CN103546583B (en) | Group intellectual perception system and group intellectual perception method | |
CN110362377A (en) | The dispatching method and device of virtual machine | |
CN109598576A (en) | Service recommendation method, device and equipment | |
CN109815980A (en) | Prediction technique, device, electronic equipment and the readable storage medium storing program for executing of user type | |
CN109214739A (en) | order processing method and device | |
JP2012524340A (en) | Travel price optimization (TPO) | |
CN107909392A (en) | Stimulation behavior susceptibility Forecasting Methodology, device, equipment and readable storage medium storing program for executing | |
CN108550090A (en) | A kind of processing method and system of determining source of houses pricing information | |
CN109995837A (en) | A kind of service package recommended method, device and server | |
EP1518201A2 (en) | Method system and computer program product for dynamic construction of packages and optimal assignement of generated packages to shopping categories | |
CN108446944A (en) | A kind of the determination method, apparatus and electronic equipment in resident city | |
CN109547546A (en) | A kind of dispatching method and control centre's server of request task | |
CN104428807A (en) | Information processing system, information processing method, information processing device, and control method and control program therefor |
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: 20180904 |
|
RJ01 | Rejection of invention patent application after publication |