CN109934387A - For estimating the method, apparatus and electronic equipment of time - Google Patents
For estimating the method, apparatus and electronic equipment of time Download PDFInfo
- Publication number
- CN109934387A CN109934387A CN201910108700.5A CN201910108700A CN109934387A CN 109934387 A CN109934387 A CN 109934387A CN 201910108700 A CN201910108700 A CN 201910108700A CN 109934387 A CN109934387 A CN 109934387A
- Authority
- CN
- China
- Prior art keywords
- order
- target
- history
- estimation
- stroke
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a kind of for estimating the method, apparatus and electronic equipment of time, and a specific embodiment of the method includes: to obtain initially estimating result using the completion moment of the corresponding stroke of preset rules estimation target order;Determine that the corresponding target information of the target order, the target information include the history estimation deviation information of the personalized coefficient of the corresponding service provider of the target order, the maximum order volume of holding of the service provider and the corresponding coverage of the target order;The target information is input in model trained in advance;Initially estimated described in data correction using model output as a result, obtaining target estimation result.The embodiment has fully considered some potential factors of the corresponding service provider of target order and the corresponding coverage of target order on initially estimating resulting influence, and initial estimation result is modified, so that higher by revised target estimation result precision.
Description
Technical field
It is this application involves technical field of internet application, in particular to a kind of for estimating the method, apparatus and electricity of time
Sub- equipment.
Background technique
With the continuous development of Internet technology, many services Internet-based are come into being.Internet-based
In service, it usually needs estimate to the time, referred to being pushed to user, or serviced with reference to the time estimated
Resource allocation and smoothing.Therefore, the time estimate having very important significance.By taking immediate distribution as an example, generally require to taking
The goods moment is estimated, or estimates etc. constantly to being sent to.For at present, usually according to the path of planning and service
The general speed of service of provider estimates the time.But since the stroke of service provider will receive the shadow of factors
It rings, therefore, the time accuracy estimated through the above way is lower.
Summary of the invention
One of in order to solve the above-mentioned technical problem, the application provides a kind of for estimating the method, apparatus and electronics of time
Equipment.
According to the embodiment of the present application in a first aspect, providing a kind of for estimating the method for time, comprising:
Using the completion moment of the corresponding stroke of preset rules estimation target order, obtain initially estimating result;
Determine that the corresponding target information of the target order, the target information include the corresponding service of the target order
The personalized coefficient of provider, the maximum order volume of holding of the service provider and the corresponding service area of the target order
The history in domain estimates deviation information;
The target information is input in model trained in advance;
Initially estimated described in data correction using model output as a result, obtaining target estimation result.
Optionally, it is determined as follows the personalized coefficient of the corresponding service provider of the target order:
Determine the service provider corresponding first History Order data in the first preset period of time;
Based on the first History Order data, multiple first history rows that the first History Order data are related to are determined
In journey each first history stroke actually accomplish duration and duration is completed in estimation, the estimation completes duration and is based on described preset
Rule and determine;
Determine the corresponding target ratio of each first history stroke, wherein the corresponding mesh of any first history stroke
Mark ratio is the ratio for actually accomplishing duration and estimation completion duration of the first history stroke;
According to the corresponding target ratio of each first history stroke, the personalized system of the service provider is determined
Number.
Optionally, the personalized coefficient of the service provider is determined using following formula:
Wherein, A indicates the personalized coefficient of the service provider;N is positive integer, indicates that the first preset period of time is corresponding
Number of days;T is positive integer, αTIndicate the T days corresponding average target ratios in the first preset period of time;MTFor positive integer, institute is indicated
State the T days of service provider in the first preset period of time, the number of the first history stroke of completion;βi TIndicate that the service provides
Square the T days in the first preset period of time, the corresponding target ratio of i-th the first history stroke of completion.
Optionally, it is determined as follows the maximum order volume of holding of the service provider:
If it is determined that the corresponding accumulation service duration of the service provider is less than or equal to preset threshold, then it will be preassigned
Quantity is determined as the maximum order volume of holding of the service provider;
If it is determined that the corresponding accumulation service duration of the service provider is greater than preset threshold, it is determined that the service offer
The completed order number in side, and the corresponding preset quantity of the completed order number is determined as the service provider
The maximum order volume of holding.
Optionally, it is determined as follows the history estimation deviation information of the corresponding coverage of the target order:
Determine the coverage in the corresponding second History Order data of the second preset period of time;
Based on the second History Order data, multiple second history rows that the second History Order data are related to are determined
Journey and each second history stroke actually accomplish the moment and estimation is completed the moment, the estimation completes the moment and is based on described preset
Rule and determine;
Determine the corresponding estimation deviation of each second history stroke, wherein any second history stroke is corresponding to be estimated
Survey the difference for actually accomplishing moment and estimation completion moment that deviation is the second history stroke;
According to the corresponding estimation deviation of each second history stroke, the history estimation deviation information is determined.
Optionally, the history estimation deviation information includes: average deviation and mean absolute deviation;
Wherein, the average deviation is determined by following formula:
The mean absolute deviation is determined by following formula:
Wherein, ME indicates the average deviation;MAE indicates the mean absolute deviation;N is positive integer, indicates the clothes
The number for the second history stroke that the order that business region generates in the second preset period of time is related to;J is positive integer, ΔjIndicate institute
State estimation deviation corresponding to the second history stroke of jth time that the order that coverage generates in the second preset period of time is related to.
Optionally, the target information further includes following one or more:
The target order corresponding worksheet processing moment;
The corresponding spending amount of the target order;
The distance of the corresponding stroke of the target order;
The stroke for the target order estimated based on the preset rules completes the moment;
The target order corresponding order moment;
The target order distributes attribute, and the attribute that distributes includes directly sending attribute and reassigning attribute;
Order production quantity of the corresponding coverage of the target order in default historical period;
Estimation production quantity of the corresponding coverage of the target order in the order being currently located in timeslice;
Estimation per capita load capacity of the corresponding coverage of target order in the order being currently located in timeslice;
The averaged power spectrum moment that the corresponding coverage of target order is completed in the order stroke being currently located in timeslice.
According to the second aspect of the embodiment of the present application, provide a kind of for estimating the device of time, comprising:
Estimating module is initially estimated for the completion moment using the corresponding stroke of preset rules estimation target order
Survey result;
Determining module, for determining that the corresponding target information of the target order, the target information include the target
The personalized coefficient of the corresponding service provider of order, the maximum order volume of holding of the service provider and the target are ordered
The history of single corresponding coverage estimates deviation information;
Input module, for the target information to be input in model trained in advance;
Correction module, described in the data correction for being exported using the model initially estimation as a result, obtaining target estimation
As a result.
According to the third aspect of the embodiment of the present application, a kind of computer readable storage medium is provided, the storage medium is deposited
Computer program is contained, the computer program realizes side described in any one of above-mentioned first aspect when being executed by processor
Method.
According to the fourth aspect of the embodiment of the present application, a kind of electronic equipment is provided, including memory, processor and be stored in
On memory and the computer program that can run on a processor, the processor realize above-mentioned first party when executing described program
Method described in any one of face.
The technical solution that embodiments herein provides can include the following benefits:
The method and apparatus for being used to estimate the time that embodiments herein provides, by estimating target using preset rules
The completion moment of the corresponding stroke of order is initially estimated as a result, determining that the corresponding target information of target order, the target are believed
Breath include the personalized coefficient of the corresponding service provider of target order, the service provider the maximum order volume of holding and should
The history of the corresponding coverage of target order estimates deviation information, target information is input in model trained in advance, and
Initially estimated using the data correction that the model exports as a result, obtaining target estimation result.Since the present embodiment at least uses mesh
Mark the personalized coefficient of the corresponding service provider of order, the maximum order volume of holding and the target order of the service provider
Therefore the history estimation deviation information of corresponding coverage, has fully considered the corresponding clothes of target order as target information
Some potential factors of business provider and the corresponding coverage of target order are on initially estimating resulting influence, and to first
The estimation result that begins is modified, so that higher by revised target estimation result precision.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The application can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the application
Example, and together with specification it is used to explain the principle of the application.
Fig. 1 is that the application is shown according to an exemplary embodiment a kind of for estimating the flow chart of the method for time;
Fig. 2 is that the application is shown according to an exemplary embodiment another for estimating the flow chart of the method for time;
Fig. 3 is that the application is shown according to an exemplary embodiment another for estimating the flow chart of the method for time;
Fig. 4 is that the application is shown according to an exemplary embodiment a kind of for estimating the block diagram of the device of time;
Fig. 5 is that the application is shown according to an exemplary embodiment another for estimating the block diagram of the device of time;
Fig. 6 is that the application is shown according to an exemplary embodiment another for estimating the block diagram of the device of time;
Fig. 7 is that the application is shown according to an exemplary embodiment another for estimating the block diagram of the device of time;
Fig. 8 is the structural schematic diagram of the application a kind of electronic equipment shown according to an exemplary embodiment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the application.
It is only to be not intended to be limiting the application merely for for the purpose of describing particular embodiments in term used in this application.
It is also intended in the application and the "an" of singular used in the attached claims, " described " and "the" including majority
Form, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein refers to and wraps
It may be combined containing one or more associated any or all of project listed.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not departing from
In the case where the application range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination ".
As shown in Figure 1, Fig. 1 is shown according to an exemplary embodiment a kind of for estimating the process of the method for time
Figure, this method can be applied in terminal device, also can be applied in server.Method includes the following steps:
In a step 101, using the completion moment of the corresponding stroke of preset rules estimation target order, initially estimated
As a result.
In the present embodiment, related service can be to servicing under line on line Internet-based, for example, matching immediately
Take business etc., it will be understood that the application does not limit the concrete type aspect of related service.Target order can be customer
The issued order for carrying service request, the corresponding stroke of target order can be stroke involved in target order.With
For immediate distribution service, the corresponding stroke of target order can be picking stroke involved in target order, be also possible to mesh
Delivery stroke involved in order etc. is marked, therefore, it is corresponding that the completion moment of the corresponding stroke of target order can be target order
Picking to shop at the time of, be also possible to the corresponding kinds of goods of target order and be sent to the moment.
In the present embodiment, it at the completion moment that the corresponding stroke of target order can be estimated first with preset rules, obtains
To initial estimation result.Wherein, preset rules can be any rule that the moment is completed for estimating stroke.For example, default rule
It then can be according to the general speed of service of the path of planning and service provider and what the moment was estimated completed to stroke
Rule is also possible to based on the corresponding start of a run of target order and terminal, to row and the statistics to historical data calculates
Journey completes the rule estimated at the moment.It is appreciated that preset rules can also be other any reasonable rules, the application couple
It is not limited in terms of the particular content of preset rules.
In a step 102, determine that the corresponding target information of target order, the target information include the corresponding clothes of target order
The personalized coefficient of business provider, the maximum order volume of holding of the service provider and the corresponding coverage of target order
History estimate deviation information.
In the present embodiment, it can determine that target information corresponding with target order, the target information at least can wrap
Include the personalized coefficient of the corresponding service provider of target order, the maximum order volume of holding of the service provider and the target
The history of the corresponding coverage of order estimates deviation information.Wherein, the corresponding service provider of target order, which can be, is connected to
Target order simultaneously provides for the service of serve.Even if the corresponding service of target order provides by taking delivery service as an example
Side can be the dispatching person for being connected to target order and dispensing kinds of goods for customer.The corresponding coverage of target order can be target
Coverage where the corresponding businessman of order.Even if by taking delivery service as an example some clothes can be divided for businessman in advance
Business region, each coverage are responsible for by specified dispatching person, and the corresponding coverage of target order is what target order was related to
The coverage divided in advance where businessman.
In the present embodiment, the personalized coefficient of service provider, which can be, can arbitrarily embody service provider individual
The coefficient of efficiency of service feature, can be true and carrying out analytical calculation to the corresponding history service data of the service provider
It is fixed.It is appreciated that the application does not limit the specific method of determination aspect of the personalized coefficient of service provider.
In the present embodiment, the maximum order volume of holding of service provider can be what the service provider can be held
The upper limit of quantity on order can embody the empirical features of the service provider.The maximum order volume of holding of service provider with should
It is related to the quantity that Service Order is completed that service provider accumulates service duration.It is appreciated that the application is to service provider
The maximum order volume of holding specific method of determination in terms of do not limit.
In the present embodiment, the history estimation deviation information of the corresponding coverage of target order can be and can embody
The characteristic information of the precision of time is estimated for the coverage by above-mentioned preset rules.It can be corresponding based on the target order
Coverage History Order data determine the coverage history estimation deviation information.It is appreciated that the application is to clothes
It is not limited in terms of the specific method of determination of the history estimation deviation information in business region.
Optionally, target information can also include following one or more: the target order corresponding worksheet processing moment;Target is ordered
Single corresponding spending amount;The distance of the corresponding stroke of target order;The stroke for the target order estimated based on preset rules
Complete the moment;The target order corresponding order moment;Target order distributes attribute, this, which distributes attribute and can be, directly sends attribute
If (target order is the order directly distributed, belongs to and directly sends attribute), is also possible to reassign attribute (if target order is to reassign
Order, then belong to and reassign attribute);Order production quantity of the corresponding coverage of target order in default historical period;Mesh
The corresponding coverage of order is marked in the estimation production quantity for the order being currently located in timeslice;The corresponding service area of target order
Estimation per capita load capacity (e.g., order volume that average each dispatching person be connected to) of the domain in the order being currently located in timeslice;Mesh
The averaged power spectrum moment that the corresponding coverage of mark order is completed in the order stroke being currently located in timeslice.
Wherein it is possible to will be divided into multiple timeslices daily in advance, the duration of each timeslice can be equal.Currently
Place timeslice can be timeslice corresponding to current time, and the estimation production quantity for the order being currently located in timeslice is ordered
Single estimation averaged power spectrum moment that load capacity and order stroke are completed per capita may each be and the statistics to historical data
Determining.For example, can incite somebody to action in current period the last week, in timeslice identical with timeslice corresponding to current time,
Order production quantity is weighted and averaged, and the load capacity per capita of order is weighted and averaged, order stroke complete the average moment into
Row weighted average, thus obtain being currently located the estimation production quantity of the order in timeslice, order estimation per capita load capacity and
The averaged power spectrum moment that order stroke is completed.
In step 103, target information is input in model trained in advance.
In the present embodiment, a model can be trained in advance, which can be any reasonable regression model, example
Such as, which can include but is not limited to linear regression model (LRM), Logic Regression Models, polynomial regression model etc..It is appreciated that
The application does not limit the concrete type aspect of the model.
Specifically, in the training model, History Order data can be acquired first, and true based on History Order data
Determine the corresponding historical information of each History Order.The historical information at least may include the corresponding service provider of History Order
The history estimation of personalized coefficient, the maximum order volume of holding of the service provider and the corresponding coverage of History Order is inclined
Poor information.Next it may be determined that actually accomplishing the moment and estimating the moment for the corresponding stroke of each History Order (utilizes default rule
Then estimation is at the time of obtain) difference.Using the corresponding historical information of each History Order as one group of sample data, with above-mentioned difference
Value is used as label, is labeled to every group of sample data, to obtain sample set, can use the sample set training pattern.It can
To understand, the method for any training model that is as known in the art and being likely to occur in the future can be applied to this Shen
Please, the application does not limit the detailed process aspect of training pattern.
At step 104, initially estimated using the data correction that the model exports as a result, obtaining target estimation result.
In the present embodiment, target information is input to the model of training in advance, the data of model output are to use
In the adjusting parameter of the initial estimation result of amendment.By the adjusting parameter and initial estimation results added, accuracy can be obtained more
High target estimates result.
The application's is provided by the above embodiment for estimating the method for time, is ordered by estimating target using preset rules
The completion moment of single corresponding stroke is initially estimated as a result, determining the corresponding target information of target order, the target information
The maximum order volume of holding and the mesh of personalized coefficient, the service provider including the corresponding service provider of target order
The history for marking the corresponding coverage of order estimates deviation information, target information is input in model trained in advance, and benefit
Initially estimated with the data correction that the model exports as a result, obtaining target estimation result.Since the present embodiment at least uses target
The personalized coefficient of the corresponding service provider of order, the maximum order volume of holding of the service provider and the target order pair
Therefore the history estimation deviation information for the coverage answered, has fully considered the corresponding service of target order as target information
Some potential factors of provider and the corresponding coverage of target order are on initially estimating resulting influence, and to initial
Estimation result is modified, so that higher by revised target estimation result precision.
As shown in Fig. 2, Fig. 2 is shown according to an exemplary embodiment another for estimating the process of the method for time
Figure, This embodiment describes the process for the personalized coefficient for determining service provider, this method be can be applied in terminal device,
Also it can be applied in server, comprising the following steps:
In step 201, determine that the corresponding service provider of target order corresponding first is gone through in the first preset period of time
History order data.
In the present embodiment, the first preset period of time can be preset any historical period, for example, first it is default when
Section can be it is current before one week, it is perhaps current before one month or currently before 1 year etc..It is appreciated that this
Apply not limiting in terms of the specific setting to the first preset period of time.
In the present embodiment, it is default first to can be the corresponding service provider of target order for the first History Order data
The order data of multiple History Orders of completion is connected to and handled in period.
In step 202, the first History Order data are based on, determine the first History Order data are related to multiple first
In history stroke each first history stroke actually accomplish duration and duration is completed in estimation, the estimation complete duration be based on it is default
Rule and determine.
In the present embodiment, the first history stroke can be the corresponding service provider of target order in the first preset period of time
It is inside connected to and handles history stroke involved in the History Order of completion (for example, picking stroke or delivery stroke etc.).Its
In, preset rules are identical with preset rules involved in Fig. 1 embodiment.
In step 203, the corresponding target ratio of each first history stroke is determined, wherein any first history stroke
Corresponding target ratio is the ratio for actually accomplishing duration and estimation completion duration of the first history stroke.
In step 204, according to the corresponding target ratio of each first history stroke, the individual character of the service provider is determined
Change coefficient.
In the present embodiment, which can be determined according to the corresponding target ratio of each first history stroke
Personalized coefficient.For example, the corresponding target ratio of each first history stroke can be carried out average computation, to be somebody's turn to do
The personalized coefficient of service provider.
Optionally, the personalized coefficient of the service provider can also be determined using following formula:
Wherein, A indicates the personalized coefficient of the service provider;N is positive integer, indicates the corresponding day of the first preset period of time
Number;T is positive integer, αTIndicate the T days corresponding average target ratios in the first preset period of time;MTFor positive integer, the clothes are indicated
It is engaged in the T days in the first preset period of time of provider, the number of the first history stroke of completion;βi TIndicate service provider first
The T days of preset period of time, target ratio corresponding to i-th the first history stroke of completion.
The application's is provided by the above embodiment for estimating the method for time, by determining the corresponding service of target order
Provider's corresponding first History Order data in the first preset period of time are based on the first History Order data, determine first
Each first history stroke actually accomplishes duration and estimation completion in multiple first history strokes that History Order data are related to
Duration, the estimation are completed duration and are determined based on preset rules, determine the corresponding target ratio of each first history stroke,
In, the corresponding target ratio of any first history stroke be the first history stroke actually accomplish duration and duration is completed in estimation
Ratio determine the personalized coefficient of the service provider and according to the corresponding target ratio of each first history stroke.To
The personalized coefficient of service provider is enabled more accurately to embody the feature of the service provider individual service efficiency.
In some optional embodiments, the maximum order volume of holding of service provider can be determined as follows:
First, it is determined that whether the corresponding accumulation service duration of service provider is less than or equal to preset threshold, however, it is determined that service provider pair
The accumulation service duration answered is less than or equal to preset threshold, then preassigned quantity can be determined as to the maximum of service provider
The order volume of holding.If it is determined that the corresponding accumulation service duration of service provider is greater than preset threshold, then it can determine that service provides
The completed order number in side, and the corresponding preset quantity of the completed order number is determined as to the maximum of service provider
The order volume of holding.
The present embodiment determines service provider based on quantity service provider accumulation service duration and order is completed
The maximum order volume of holding enables the maximum order volume of holding of service provider more accurately to embody the warp of the service provider
Test feature.
As shown in figure 3, Fig. 3 is shown according to an exemplary embodiment another for estimating the process of the method for time
The process of the history estimation deviation information of the corresponding coverage of determining target order, the party is described in detail in figure, the embodiment
Method can be applied in terminal device, also can be applied in server, comprising the following steps:
In step 301, determine that the corresponding coverage of destination service is ordered in corresponding second history of the second preset period of time
Forms data.
In the present embodiment, the second preset period of time can be preset any historical period, for example, second it is default when
Section can be it is current before one day, it is perhaps current before two days or it is current before one week etc..It is appreciated that this Shen
Please the specific setting aspect of the second preset period of time is not limited.
In the present embodiment, the second History Order data can be the corresponding coverage of target order when second is default
The order data of the multiple History Orders generated in section.
In step 302, the second History Order data are based on, determine the second History Order data are related to multiple second
History stroke and each second history stroke actually accomplish the moment and estimation is completed the moment, the estimation complete the moment be based on it is described
Preset rules and determine.
In the present embodiment, the second history stroke can be the corresponding coverage of target order in the second preset period of time
History stroke involved in the History Order of generation (for example, picking stroke or delivery stroke etc.).Wherein, preset rules
It is identical with preset rules involved in Fig. 1 embodiment.
In step 303, the corresponding estimation deviation of each second history stroke is determined, wherein any second history stroke
Corresponding estimation deviation is the difference for actually accomplishing moment and estimation completion moment of the second history stroke.
In step 304, according to the corresponding estimation deviation of each second history stroke, determine that history estimates deviation information.
In the present embodiment, the history estimation deviation information of the corresponding coverage of target order include: average deviation with
And mean absolute deviation.
It is alternatively possible to determine above-mentioned average deviation by following formula:
Above-mentioned mean absolute deviation can be determined by following formula:
Wherein, ME indicates above-mentioned average deviation;MAE indicates above-mentioned mean absolute deviation;N is positive integer, indicates above-mentioned clothes
The number for the second history stroke that the order that business region generates in the second preset period of time is related to;J is positive integer, ΔjIn expression
State estimation deviation corresponding to the second history stroke of jth time that the order that coverage generates in the second preset period of time is related to.
The application's is provided by the above embodiment for estimating the method for time, by determining the corresponding service of destination service
Region is based on the second History Order data, determines the second history in the corresponding second History Order data of the second preset period of time
Multiple second history strokes that order data is related to and each second history stroke actually accomplish the moment and the moment is completed in estimation,
The estimation completion moment is determined based on the preset rules, determines the corresponding estimation deviation of each second history stroke, wherein
The corresponding estimation deviation of any second history stroke be the second history stroke actually accomplish the moment and estimation complete the moment it
Difference, and according to the corresponding estimation deviation of each second history stroke, determine that history estimates deviation information.So that coverage
History estimation deviation information can more accurately embody by above-mentioned preset rules for coverage estimate the time precision
Feature.
Although should be noted that in the above-described embodiments, the operation of the application method is described with particular order, this
These operations must be executed in this particular order by not requiring that or implying, or is had to carry out and operated just shown in whole
It is able to achieve desired result.On the contrary, the step of describing in flow chart can change and execute sequence.It additionally or alternatively, can be with
Certain steps are omitted, multiple steps are merged into a step and are executed, and/or a step is decomposed into execution of multiple steps.
Corresponding with the estimation embodiment of the method for time is previously used for, present invention also provides the devices for estimating the time
Embodiment.
As shown in figure 4, Fig. 4 is that the application is shown according to an exemplary embodiment a kind of for estimating the device frame of time
Figure, the apparatus may include: estimating module 401, determining module 402, input module 403 and correction module 404.
Wherein, estimating module 401 are obtained for the completion moment using the corresponding stroke of preset rules estimation target order
To initial estimation result.
Determining module 402, for determining that the corresponding target information of target order, the target information include that target order is corresponding
The personalized coefficient of service provider, the maximum order volume of holding of the service provider and the corresponding service area of target order
The history in domain estimates deviation information.
Input module 403, for target information to be input in model trained in advance.
Correction module 404, the data correction for being exported using above-mentioned model are initially estimated as a result, obtaining target estimation knot
Fruit.
As shown in figure 5, Fig. 5 is that the application is shown according to an exemplary embodiment another for estimating the device of time
Block diagram, for the embodiment on the basis of aforementioned embodiment illustrated in fig. 4, determining module 402 may include: the first determining submodule
501。
Wherein, it first determines that submodule 501 is configured for: determining that above-mentioned service provider is right in the first preset period of time
The the first History Order data answered.Based on the first History Order data, the first History Order data are related to multiple first are determined
In history stroke each first history stroke actually accomplish duration and duration is completed in estimation, the estimation complete duration be based on it is default
Rule and determine.Determine the corresponding target ratio of each first history stroke, wherein the corresponding target of any first history stroke
Ratio is the ratio for actually accomplishing duration and estimation completion duration of the first history stroke.The first history stroke is stated according to each
Corresponding target ratio determines the personalized coefficient of the service provider.
In some optional embodiments, the personalized coefficient of the service provider can be determined using following formula:
Wherein, A indicates the personalized coefficient of service provider;N is positive integer, indicates the corresponding day of the first preset period of time
Number;T is positive integer, αTIndicate the T days corresponding average target ratios in the first preset period of time;MTFor positive integer, service is indicated
The T days in the first preset period of time of provider, the number of the first history stroke of completion;βi TIndicate that service provider is pre- first
If the T days of the period, the corresponding target ratio of i-th the first history stroke of completion.
As shown in fig. 6, Fig. 6 is that the application is shown according to an exemplary embodiment another for estimating the device of time
Block diagram, for the embodiment on the basis of aforementioned embodiment illustrated in fig. 4, determining module 402 may include: the second determining submodule
502。
Wherein, second determine that submodule 502 is configured for: if it is determined that the corresponding accumulation service duration of service provider is small
In being equal to preset threshold, then preassigned quantity is determined as to the maximum order volume of holding of service provider.If it is determined that service
The corresponding accumulation service duration of provider is greater than preset threshold, it is determined that the completed order number of service provider, and will
The corresponding preset quantity of order number of completion is determined as the maximum order volume of holding of service provider.
As shown in fig. 7, Fig. 7 is that the application is shown according to an exemplary embodiment another for estimating the device of time
Block diagram, for the embodiment on the basis of aforementioned embodiment illustrated in fig. 4, determining module 402 may include: that third determines submodule
503。
Wherein, third determines that submodule 503 is configured for: determining coverage in the second preset period of time
Corresponding second History Order data.Based on the second History Order data, the second History Order data are related to multiple are determined
Two history strokes and each second history stroke actually accomplish the moment and estimation is completed the moment, which completes the moment and is based on institute
It states preset rules and determines.Determine the corresponding estimation deviation of each second history stroke, wherein any second history stroke is corresponding
Estimation deviation be the second history stroke actually accomplish the moment and estimation completion the moment difference.According to each second history row
The corresponding estimation deviation of journey determines above-mentioned history estimation deviation information.
In other optional embodiments, above-mentioned history estimation deviation information may include: average deviation and be averaged
Absolute deviation.
Wherein it is possible to determine the average deviation by following formula:
The mean absolute deviation can be determined by following formula:
Wherein, ME indicates above-mentioned average deviation;MAE indicates above-mentioned mean absolute deviation;N is positive integer, indicates above-mentioned clothes
The number for the second history stroke that the order that business region generates in the second preset period of time is related to;J is positive integer, ΔjIn expression
State estimation deviation corresponding to the second history stroke of jth time that the order that coverage generates in the second preset period of time is related to.
In other optional embodiments, target information can also include following one or more: target order is corresponding
The worksheet processing moment;The corresponding spending amount of target order;The distance of the corresponding stroke of target order;Estimated based on preset rules
Target order stroke complete the moment;The target order corresponding order moment;Target order distributes attribute, this distributes attribute
Can be and directly send attribute (if target order is the order directly distributed, belonging to straight attribute of sending), be also possible to reassign attribute (if
Target order is the order reassigned, then belongs to and reassign attribute);The corresponding coverage of target order is in default historical period
Order production quantity;Estimation production quantity of the corresponding coverage of target order in the order being currently located in timeslice;Target is ordered
In the estimation for the order being currently located in timeslice, (e.g., average each dispatching person connects load capacity per capita for single corresponding coverage
The order volume arrived);The averaged power spectrum that the corresponding coverage of target order is completed in the order stroke being currently located in timeslice
Moment.
It should be appreciated that above-mentioned apparatus can be set in advance in terminal device or server, the side such as downloading can also be passed through
Formula and be loaded into terminal device or server.Corresponding module in above-mentioned apparatus can be with the mould in terminal device or server
Block cooperates to realize the scheme for estimating the time.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
The purpose for needing to select some or all of the modules therein to realize application scheme.Those of ordinary skill in the art are not paying
Out in the case where creative work, it can understand and implement.
The embodiment of the present application also provides a kind of computer readable storage medium, which is stored with computer journey
Sequence, computer program can be used for executing the method for being used to estimate the time that above-mentioned Fig. 1 is provided to Fig. 3 any embodiment.
Corresponding to above-mentioned for estimating the method for time, the embodiment of the present application also proposed shown in Fig. 8 according to this Shen
The schematic configuration diagram of the electronic equipment of an exemplary embodiment please.Referring to FIG. 8, in hardware view, which includes
Processor, internal bus, network interface, memory and nonvolatile memory are also possible that certainly required for other business
Hardware.Processor is from the then operation into memory of corresponding computer program is read in nonvolatile memory, in logical layer
The device for estimating the time is formed on face.Certainly, other than software realization mode, other realization sides are not precluded in the application
Formula, such as logical device or the mode of software and hardware combining etc., that is to say, that the executing subject of following process flow is simultaneously unlimited
Due to each logic unit, it is also possible to hardware or logical device.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the application
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or
Person's adaptive change follows the general principle of the application and including the undocumented common knowledge in the art of the application
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the application are by following
Claim is pointed out.
It should be understood that the application is not limited to the precise structure that has been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.Scope of the present application is only limited by the accompanying claims.
Claims (10)
1. a kind of for estimating the method for time, which is characterized in that the described method includes:
Using the completion moment of the corresponding stroke of preset rules estimation target order, obtain initially estimating result;
Determine that the corresponding target information of the target order, the target information include that the corresponding service of the target order provides
The personalized coefficient of side, the maximum order volume of holding of the service provider and the target order corresponding coverage
History estimates deviation information;
The target information is input in model trained in advance;
Initially estimated described in data correction using model output as a result, obtaining target estimation result.
2. the method according to claim 1, wherein being determined as follows the corresponding clothes of the target order
The personalized coefficient of business provider:
Determine the service provider corresponding first History Order data in the first preset period of time;
Based on the first History Order data, determine in multiple first history strokes that the first History Order data are related to
Each first history stroke actually accomplishes duration and estimation completion duration, and the estimation completion duration is based on the preset rules
And it determines;
Determine the corresponding target ratio of each first history stroke, wherein the corresponding target ratio of any first history stroke
Value is the ratio for actually accomplishing duration and estimation completion duration of the first history stroke;
According to the corresponding target ratio of each first history stroke, the personalized coefficient of the service provider is determined.
3. according to the method described in claim 2, it is characterized in that, determining the individual character of the service provider using following formula
Change coefficient:
Wherein, A indicates the personalized coefficient of the service provider;N is positive integer, indicates the corresponding day of the first preset period of time
Number;T is positive integer, αTIndicate the T days corresponding average target ratios in the first preset period of time;MTFor positive integer, described in expression
The T days in the first preset period of time of service provider, the number of the first history stroke of completion;βi TIndicate the service provider
At the T days of the first preset period of time, the corresponding target ratio of i-th the first history stroke of completion.
4. the method according to claim 1, wherein being determined as follows the maximum of the service provider
The order volume of holding:
If it is determined that the corresponding accumulation service duration of the service provider is less than or equal to preset threshold, then by preassigned quantity
It is determined as the maximum order volume of holding of the service provider;
If it is determined that the corresponding accumulation service duration of the service provider is greater than preset threshold, it is determined that the service provider is
The order number of completion, and the corresponding preset quantity of the completed order number is determined as the service provider most
The big order volume of holding.
5. the method according to claim 1, wherein being determined as follows the corresponding clothes of the target order
The history in business region estimates deviation information:
Determine the coverage in the corresponding second History Order data of the second preset period of time;
Based on the second History Order data, determine multiple second history strokes that the second History Order data are related to and
Each second history stroke actually accomplishes moment and estimation completion moment, and the estimation completes the moment based on the preset rules
And it determines;
Determine the corresponding estimation deviation of each second history stroke, wherein any second history stroke is corresponding to be estimated partially
Difference is the difference for actually accomplishing moment and estimation completion moment of the second history stroke;
According to the corresponding estimation deviation of each second history stroke, the history estimation deviation information is determined.
6. according to the method described in claim 5, it is characterized in that, history estimation deviation information include: average deviation with
And mean absolute deviation;
Wherein, the average deviation is determined by following formula:
The mean absolute deviation is determined by following formula:
Wherein, ME indicates the average deviation;MAE indicates the mean absolute deviation;N is positive integer, indicates the service area
The number for the second history stroke that the order that domain generates in the second preset period of time is related to;J is positive integer, ΔjIndicate the clothes
Estimation deviation corresponding to the second history stroke of jth time that the order that business region generates in the second preset period of time is related to.
7. any method in -6 according to claim 1, which is characterized in that the target information further include with the next item down or
It is multinomial:
The target order corresponding worksheet processing moment;
The corresponding spending amount of the target order;
The distance of the corresponding stroke of the target order;
The stroke for the target order estimated based on the preset rules completes the moment;
The target order corresponding order moment;
The target order distributes attribute, and the attribute that distributes includes directly sending attribute and reassigning attribute;
Order production quantity of the corresponding coverage of the target order in default historical period;
Estimation production quantity of the corresponding coverage of the target order in the order being currently located in timeslice;
Estimation per capita load capacity of the corresponding coverage of target order in the order being currently located in timeslice;
The averaged power spectrum moment that the corresponding coverage of target order is completed in the order stroke being currently located in timeslice.
8. a kind of for estimating the device of time, which is characterized in that described device includes:
Estimating module obtains initially estimating knot for the completion moment using the corresponding stroke of preset rules estimation target order
Fruit;
Determining module, for determining that the corresponding target information of the target order, the target information include the target order
The personalized coefficient of corresponding service provider, the maximum order volume of holding of the service provider and the target order pair
The history for the coverage answered estimates deviation information;
Input module, for the target information to be input in model trained in advance;
Correction module, described in the data correction for being exported using the model initially estimation as a result, obtaining target estimation result.
9. a kind of computer readable storage medium, which is characterized in that the storage medium is stored with computer program, the calculating
Method described in any one of the claims 1-7 is realized when machine program is executed by processor.
10. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes side described in any one of the claims 1-7 when executing described program
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910108700.5A CN109934387A (en) | 2019-02-03 | 2019-02-03 | For estimating the method, apparatus and electronic equipment of time |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910108700.5A CN109934387A (en) | 2019-02-03 | 2019-02-03 | For estimating the method, apparatus and electronic equipment of time |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109934387A true CN109934387A (en) | 2019-06-25 |
Family
ID=66985588
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910108700.5A Pending CN109934387A (en) | 2019-02-03 | 2019-02-03 | For estimating the method, apparatus and electronic equipment of time |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109934387A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110472891A (en) * | 2019-08-26 | 2019-11-19 | 上海蔚来汽车有限公司 | It is powered on service ability or the assessment or management method of resource, system and storage medium |
CN111832789A (en) * | 2019-09-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Position determination method, model training method, device, equipment and storage medium |
CN112862133A (en) * | 2019-11-12 | 2021-05-28 | 北京三快在线科技有限公司 | Order processing method and device, readable storage medium and electronic equipment |
-
2019
- 2019-02-03 CN CN201910108700.5A patent/CN109934387A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110472891A (en) * | 2019-08-26 | 2019-11-19 | 上海蔚来汽车有限公司 | It is powered on service ability or the assessment or management method of resource, system and storage medium |
CN110472891B (en) * | 2019-08-26 | 2023-10-17 | 上海蔚来汽车有限公司 | Method, system and storage medium for evaluating or managing power-up service capability or resource |
CN111832789A (en) * | 2019-09-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Position determination method, model training method, device, equipment and storage medium |
CN112862133A (en) * | 2019-11-12 | 2021-05-28 | 北京三快在线科技有限公司 | Order processing method and device, readable storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106528280B (en) | A kind of method for allocating tasks and system | |
CN109934387A (en) | For estimating the method, apparatus and electronic equipment of time | |
CN103971170B (en) | The method and apparatus that a kind of change being used for characteristic information is predicted | |
WO2019071930A1 (en) | Method and apparatus for sorting goods | |
CN110083528A (en) | Distribution method, device, computer equipment and the storage medium of test assignment | |
CN106020966A (en) | Systems and methods for intelligently distributing tasks received from clients among a plurality of worker resources | |
CN110232537A (en) | Distribute method, apparatus, equipment and the storage medium of data object | |
CN110414731A (en) | Method, apparatus, computer readable storage medium and the electronic equipment of Order splitting | |
CN109961198B (en) | Associated information generation method and device | |
CN105719221A (en) | Path cooperation programming method and device aiming at multitask | |
CN109343942A (en) | Method for scheduling task based on edge calculations network | |
CN109543890A (en) | Power grid based on load estimation equilibrium takes control Optimization Scheduling, apparatus and system | |
CN109003011A (en) | The distribution method and device of delivery service resource, electronic equipment | |
CN108764699A (en) | Scheduling method, server and computer readable storage medium | |
CN109697637A (en) | Object type determines method, apparatus, electronic equipment and computer storage medium | |
CN110222996A (en) | Method for allocating tasks and device | |
CN110209467A (en) | A kind of flexible resource extended method and system based on machine learning | |
CN108920281A (en) | Extensive image processing method and system | |
CN108874520A (en) | Calculation method and device | |
CN111813524A (en) | Task execution method and device, electronic equipment and storage medium | |
CN106407007B (en) | Cloud resource configuration optimization method for elastic analysis process | |
Lee | Estimating order lead times in hybrid flowshops with different scheduling rules | |
CN115129481B (en) | Computing resource allocation method and device and electronic equipment | |
CN108874805A (en) | The treating method and apparatus of data | |
CN107844496A (en) | Statistical information output intent and device |
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 |