CN109636276A - Assessment dispatching resource capability, Order splitting, dispatching resource regulating method and device - Google Patents
Assessment dispatching resource capability, Order splitting, dispatching resource regulating method and device Download PDFInfo
- Publication number
- CN109636276A CN109636276A CN201811443129.4A CN201811443129A CN109636276A CN 109636276 A CN109636276 A CN 109636276A CN 201811443129 A CN201811443129 A CN 201811443129A CN 109636276 A CN109636276 A CN 109636276A
- Authority
- CN
- China
- Prior art keywords
- maximum
- super
- dispatching resource
- amount
- single amount
- 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
- G06Q10/08—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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Embodiment of the present invention is related to field of communication technology more particularly to a kind of assessment dispatching resource capability, Order splitting, dispatching resource regulating method and device.This method comprises: obtaining conditional information and dispensing the attribute information of resource;According to the conditional information, the attribute information of the dispatching resource and the single capability model of back, back single amount when the maximum of assessment dispatching resource in first time period is non-super, wherein, the corresponding time-out probability of the single amount of back is less than or equal to timeout threshold when the corresponding relationship carried on the back single capability model and be used to characterize back single amount and overtime probability, maximum are non-super.In embodiments of the present invention, by using carrying on the back single capability model, by it is multiple influence dispatching resources carry on the back single abilities factors extrapolate dispatching resource maximum it is non-super when the single amount of back, it is more and relatively comprehensively to consider parameter, it is accurate to assess data more dynamic, keeps assessment result more accurate.
Description
Technical field
The present invention relates to field of communication technology, in particular to a kind of assessment dispatching resource capability, Order splitting, dispatching resource
Dispatching method and device.
Background technique
With the fast development of Internet technology, it is Internet-based application it is more and more, such as take out class application and
Class of doing shopping application etc..Based on these applications, user stays indoors the article that can be obtained needed for oneself.These, which are applied, is just utilizing
While family, it is also faced with order dispatching problem.It is extremely important that each order dispensing is suitably dispensed into resource, and dispenses resource
Maximum to carry on the back single ability be to judge the dispatching resource instantly if appropriate for the key point of order again.
The appraisal procedure that single ability is carried on the back to dispatching resource maximum in the related technology it is main it is wired under make a report on data and according to going through
History carries on the back forms data and calculates two kinds.It is according to the method for making a report on data under line, then too subjective, it cannot objective reaction truth.
The method that forms data calculates is carried on the back according to according to history, the distribution situation that the dispatching resource maximum obtained carries on the back single ability can excessively collect
In, it is larger with gap the case where normal distribution.
Based on this, the maximum list ability of carrying on the back for how relatively accurately assessing dispatching resource is asked as technology urgently to be resolved
Topic.
Summary of the invention
Embodiment of the present invention is designed to provide a kind of assessment dispatching resource capability, Order splitting, dispatching resource tune
Spend method and device, by presetting timeout threshold, can estimate dispatching resource maximum it is non-super when the single amount of back.Also, to influence
The Multiple factors that dispatching resource carries on the back single ability are considered, and keep assessment result more accurate.
A kind of method of assessment dispatching resource capability is provided in embodiments of the present invention, comprising: obtain conditional information
And the attribute information of dispatching resource;According to the conditional information, the attribute information of the dispatching resource and the single ability mould of back
Back single amount when the maximum of type, assessment dispatching resource in first time period is non-super, wherein the single capability model of the back is used for
The corresponding overtime probability of the single amount of back, which is less than or equal to, when the corresponding relationship of characterization back single amount and overtime probability, maximum are non-super surpasses
When threshold value.In embodiments of the present invention, the corresponding different overtime probability of the single amount of different back can by presetting timeout threshold
Estimate the single amount of maximum back of dispatching resource.Also, the Multiple factors for influencing the single ability of dispatching resource back are considered, make to comment
It is more accurate to estimate result.
A kind of method of Order splitting is also provided in embodiments of the present invention, which comprises obtain at the first time
Back single amount when the maximum of dispatching resource is non-super in section, wherein the single amount of back is based on conditional information, the dispatching when maximum is non-super
The single capability model of attribute information and back of resource obtains, and the list capability model of carrying on the back is for characterizing the single amount of back and time-out probability
The corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when corresponding relationship, the maximum are non-super;It is provided according to the dispatching
The single amount of back, carries out Order splitting when the maximum in source is non-super.In embodiments of the present invention, the single amount of back carries out when non-super according to maximum
Order splitting is conducive to balanced carry out Order splitting.
A kind of method for dispensing scheduling of resource is also provided in embodiments of the present invention, which comprises obtain first
Back single amount when the maximum of dispatching resource is non-super in period, wherein the single amount of back is based on conditional information, described when maximum is non-super
It dispenses the attribute information of resource and carries on the back single capability model and obtain, the single capability model of the back is general for characterizing the single amount of back and time-out
The corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the corresponding relationship of rate, the maximum are non-super;Matched according to described
The single amount of back is when sending the maximum of resource non-super to dispatch the dispatching resource.
Embodiments of the present invention also provide a kind of device of the single ability of assessment dispatching resource back, comprising: obtain module, use
In the attribute information for obtaining conditional information and dispatching resource;Evaluation module, for being provided according to the conditional information, the dispatching
The maximum of the single capability model of attribute information and back in source, assessment dispatching resource in first time period is carried on the back single when non-super
Amount, wherein the corresponding relationship carried on the back single capability model and be used to characterize back single amount and overtime probability, maximum carry on the back list when non-super
It measures corresponding overtime probability and is less than or equal to timeout threshold.
A kind of device of Order splitting is also provided in embodiments of the present invention, described device includes obtaining module, is used for
Obtain dispatching resource in first time period maximum it is non-super when the single amount of back, wherein the single amount of back is based on condition when maximum is non-super
Information, the attribute information of the dispatching resource and the single capability model of back obtain, and the single capability model of the back is single for characterization back
The corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the corresponding relationship of amount and overtime probability, maximum are non-super;
Distribution module, back single amount when non-super for the maximum according to the dispatching resource, carries out Order splitting.
A kind of device dispensing scheduling of resource is also provided in embodiments of the present invention, described device includes: acquisition module,
For obtain dispensed in first time period resource maximum it is non-super when the single amount of back, wherein single measure of back is based on when maximum is non-super
Conditional information, the attribute information of the dispatching resource and the single capability model of back obtain, and the single capability model of the back is for characterizing
The corresponding overtime probability of the single amount of back is less than or equal to time-out threshold when the corresponding relationship of back single amount and overtime probability, maximum are non-super
Value;Scheduler module, according to the maximum of the dispatching resource it is non-super when back single amount dispatch the dispatching resource.
A kind of electronic equipment is also provided in embodiments of the present invention, comprising: at least one processor;And with it is described
The memory of at least one processor communication connection;Wherein, the memory, which is stored with, to be held by least one described processor
Capable instruction, described instruction are executed by least one described processor to realize: being obtained conditional information and dispensed the category of resource
Property information;According to the conditional information, the attribute information of the dispatching resource and the single capability model of back, assessment is at the first time
Back single amount when the maximum of the dispatching resource is non-super in section, wherein the single capability model of the back is for characterizing the single amount of back and time-out
The corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the corresponding relationship of probability, the maximum are non-super.
A kind of electronic equipment of Order splitting is also provided in embodiments of the present invention, the electronic equipment includes: at least
One processor;And the memory being connect at least one described processor communication;Wherein, be stored with can for the memory
The instruction executed by least one described processor, described instruction are executed by least one described processor to realize: obtaining the
Back single amount when the maximum of dispatching resource is non-super in one period, wherein the single amount of back is based on conditional information, institute when maximum is non-super
It states the attribute information of dispatching resource and carries on the back single capability model and obtain, the single capability model of the back is for characterizing the single amount of back and time-out
The corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the corresponding relationship of probability, the maximum are non-super;According to described
Back single amount when the maximum of dispatching resource is non-super, progress Order splitting.
A kind of electronic equipment for dispensing scheduling of resource is also provided in embodiments of the present invention, the electronic equipment includes:
At least one processor;And the memory being connect at least one described processor communication;Wherein, the memory storage
There is the instruction that can be executed by least one described processor, described instruction is executed by least one described processor to realize: being obtained
Back single amount when taking the maximum of dispatching resource in first time period non-super, wherein the single amount of back is based on condition letter when maximum is non-super
Breath, the attribute information of the dispatching resource and the single capability model of back obtain, and the single capability model of the back is for the single amount of characterization back
With the corresponding relationship of overtime probability, the corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the maximum is non-super;Root
Back is single when non-super according to the maximum of the dispatching resource measures to dispatch the dispatching resource.
A kind of computer readable storage medium is also provided in embodiments of the present invention, is stored with computer program, institute
State the method that assessment dispatching resource capability involved in the embodiment of the present application is realized when computer program is executed by processor.
A kind of computer readable storage medium is also provided in embodiments of the present invention, is stored with computer program, it is described
The method of distribution order involved in the embodiment of the present application is realized when computer program is executed by processor.
A kind of computer readable storage medium is also provided in embodiments of the present invention, is stored with computer program, it is described
The method of scheduling dispatching resource involved in the embodiment of the present application is realized when computer program is executed by processor.
In addition, described according to the conditional information, the attribute information and the single capability model of back, assessment is at the first time
Back single amount when the maximum of the dispatching resource is non-super in section, comprising: by the conditional information and the attribute of the dispatching resource
Information input obtains overtime probability of the dispatching resource under the single amount of initial back into the single capability model of the back;If described
It dispenses overtime probability of the resource under the initial single amount of back and is less than the timeout threshold, singly amount is initial with the initial back
Value, X are that step-length is updated the back list amount of the dispatching resource;The dispatching resource is calculated under the back list amount updated every time
Overtime probability, until obtain maximum it is non-super when the single amount of back, wherein X is greater than 0.In embodiments of the present invention, with initial
The single amount of back is initial value, and the single amount of back, this method are conducive to more rapidly and accurately determine most when determining maximum non-super as step-length using X
Back single amount when big non-super.
In addition, the single capability model of the back is the first ability model or the second ability model, it is described to be believed according to the condition
Breath, the dispatching resource attribute information and carry on the back single capability model, the dispatching resource is most in first time period for assessment
When big non-super before the single amount of back, the method also includes: weather condition is determined according to the conditional information;If the weather condition
For bad weather, select the first ability model as the single capability model of the back;If the weather condition is non-severe day
Gas selects the second ability model as the single capability model of the back.In embodiments of the present invention, single capability model packet is carried on the back
Two versions are included, so that also can accurately estimate in inclement weather.
In addition, the corresponding timeout threshold of the first ability model is less than the corresponding overtime threshold of the second ability model
Value.In embodiments of the present invention, since the timeout criterion of bad weather dispatching resource inherently relaxes, threshold value is lowered into energy
The back list ability of more acurrate assessment dispatching resource.
In addition, described according to the conditional information, the attribute information and the single capability model of back, assessment is at the first time
Back single amount when the maximum of the dispatching resource is non-super in section, comprising: if the maximum of the first ability model output is non-super
When the single amount of back it is abnormal, according to back list when average maximum of the dispatching resource is non-super under the bad weather in historical data
Amount determines back single amount when the maximum of the dispatching resource in the first time period is non-super;If and/or the second ability model
When maximum of output is non-super the single amount of back is abnormal, according in historical data under the non-bad weather resource that dispenses
Back single amount when average maximum non-super determines back single amount when the maximum of the dispatching resource in the first time period is non-super.At this
In invention embodiment, abnormal conditions can be handled according to historical data, the program have stronger operability with
And application.
In addition, the single capability model logic-based regression algorithm building of the back or the single capability model of the back are based on model
Training obtain, overtime sample and it is non-super when sample between ratio be preset ratio.In embodiments of the present invention, due to time-out
Order negligible amounts itself, thus default overtime sample and it is non-super when sample ratio, be conducive to relatively accurately carry out maximum
Single amount prediction is carried on the back when non-super.
In addition, the conditional information includes that Weather information, temperature information, date information and total list are measured in information at least
It is a kind of;The attribute information of the dispatching resource includes the single amount information of current back, class information, work number of days information and maximum
Carry on the back at least one of single ability information, wherein the maximum list ability information of carrying on the back is for being characterized in history second time period
The single amount of maximum back.In embodiments of the present invention, weather, temperature, the date, total single amount, it is current carry on the back single amount, grade, the number of days that works,
It is the factor for influencing dispatching resource and carrying on the back single ability that maximum, which carries on the back single ability, and the single amount of back carries out when carrying out maximum non-super using the factor
Prediction is conducive to obtain relatively accurately prediction result.
In addition, it includes that the single ability information of personal back and team carry on the back in single ability information that maximum described in root, which carries on the back single ability information,
It is at least one, wherein individual carries on the back single ability for characterizing the dispatching the resource maximum single amount of back, group in history second time period
Single ability information is carried on the back for characterizing the affiliated team of the dispatching resource average maximum single amount of back in history second time period by team.?
In embodiment of the present invention, individual carries on the back single ability and the single ability of team's back is the factor for influencing dispatching resource and carrying on the back list ability,
Consider at least one of two factors, back single amount when being conducive to relatively accurately assess maximum non-super.
In embodiments of the present invention, using single capability model is carried on the back, by multiple factors for influencing dispatching resource and carrying on the back single ability
It calculates back single amount when the maximum of dispatching resource is non-super, it is more comprehensive to consider parameter, so that assessment data more dynamic is accurate.Into one
Step ground carries on the back single amount and carries out Order splitting or carry out dispatching scheduling of resource when non-super using the maximum, be conducive to improve dispatching efficiency.
Detailed description of the invention
Fig. 1 is the flow chart of the method for the assessment dispatching resource capability in first embodiment according to the present invention;
Fig. 2 is the flow chart of the method for the assessment dispatching resource capability in second embodiment according to the present invention;
Fig. 3 is the flow chart of the method for the assessment dispatching resource capability in third embodiment according to the present invention;
Fig. 4 is the method flow diagram of the Order splitting in the 4th embodiment according to the present invention;
Fig. 5 is the method schematic diagram of the dispatching scheduling of resource in the 5th embodiment according to the present invention;
Fig. 6 is the schematic diagram of the device of the assessment dispatching resource capability in sixth embodiment according to the present invention;
Fig. 7 is the device flow chart of the Order splitting in the 7th embodiment according to the present invention;
Fig. 8 is the schematic device of the dispatching scheduling of resource in the 8th embodiment according to the present invention;
Fig. 9 is the electronic devices structure schematic diagram in the 9th embodiment according to the present invention;
Figure 10 is the electronic devices structure schematic diagram in the tenth embodiment according to the present invention;
Figure 11 is the electronic devices structure schematic diagram in the 11st embodiment according to the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Each embodiment be explained in detail.However, it will be understood by those skilled in the art that in each embodiment party of the present invention
In formula, in order to make the reader understand this application better, many technical details are proposed.But even if without these technical details
And various changes and modifications based on the following respective embodiments, the application technical solution claimed also may be implemented.
It should be understood that the division of following each embodiment is for convenience, should not to constitute any restriction to the present invention,
Each embodiment can be combined with each other mutual reference under the premise of reconcilable.
Fig. 1 is the flow chart of the method for the assessment dispatching resource capability in first embodiment according to the present invention.This implementation
Mode can be applied in terminal side, such as applied in mobile phone, the terminal devices such as tablet computer, can also be applied the clothes in network side
It is engaged in device.Present embodiment assessment dispatching resource capability method as shown in Figure 1, this method comprises:
Step 101. obtains conditional information and dispenses the attribute information of resource.
Optionally, the dispatching resource may include: at least one of jockey, courier, robot and unmanned vehicle.
Embodiment to facilitate the understanding of the present invention, conditional information described in detail below and the attribute letter for dispensing resource
Breath.
One, conditional information
Optionally, the conditional information is used to characterize condition when order occurs.
Optionally an example, the conditional information may include Weather information, temperature information, date information and total list
Measure at least one of information.
Embodiment to facilitate the understanding of the present invention is below described in detail the information for including in the conditional information.
1, Weather information:
Optionally an example, Weather information can be used for characterizing current weather.
Weather can be divided into following two grades by optionally another example:
1) bad weather;Optionally, bad weather may include the weather such as strong wind, haze, light rain and moderate rain.Further may be used
Selection of land, bad weather can be divided into general bad weather and extreme weather.For example, light rain, moderate rain, gentle breeze are general severe
Weather;Haze, strong wind, heavy rain are extreme weather.
2) non-bad weather;Optionally, non-bad weather may include fine day, it is cloudy and part it is cloudy.
It should be understood that above bad weather and non-boisterous description are merely illustrative, specific bad weather and non-severe
How weather, which divides, flexibly to determine according to the actual situation.
Weather information can be used for characterizing which shelves is current weather be specially.
Specifically, why weather is divided into bad weather and non-bad weather, is because whether weather is bad weather
The single amount of back (carrying on the back single ability), subsequent to will do it detailed description when will affect maximum non-super.
2, temperature information:
Optionally an example, temperature information can be used for characterizing current temperature.Work as example, temperature information is used to indicate
Preceding temperature is 20 degrees Celsius.
3, date information:
Optionally an example, it is which can be used for characterizing current for which day of one week, and/or for characterizing
It whether is currently weekend or working day.Optionally, the date can be divided into two shelves of working day and nonworkdays.
4, total single amount information:
Optionally an example, total single amount information can be used for characterizing total single amount that the current website receives.
It should be understood that website refers to the place of distribution order.Specifically, order is distributed according to website, i.e. some range
Order is all dispensed by some website.
Two, the attribute information of resource is dispensed
Optionally, the attribute information of the dispatching resource is used to characterize the distribution capacity of dispatching resource.
Optionally an example, the attribute information of the dispatching resource may include the current back list amount letter for dispensing resource
Breath, the class information of dispatching resource, the work number of days information of dispatching resource and the maximum of dispatching resource are carried on the back in single ability information
At least one.
Embodiment to facilitate the understanding of the present invention is below described in detail the information for including in the attribute information.
1, the current back for dispensing resource singly measures information
Optionally an example, the current single amount information of back can be used for characterizing the current back list amount of dispatching resource.For example,
It is 5 single that current back list amount information, which can be used for characterizing dispatching resource currently to carry on the back single amount,.
2, the class information of resource is dispensed.
Optionally an example, the class information can be used for characterizing the grade of dispatching resource.Optionally, resource etc. is dispensed
Grade can be divided into 22 grades.Optionally, the class information of the dispatching resource can be the dispatching resource etc. that logistics company provides
Grade table.
3, the work number of days information of resource is dispensed.
Optionally an example, the work number of days information can be used for characterizing the work number of days of dispatching resource.For example, the work
Making number of days information can be used for characterizing the number of days that dispatching resource history generates waybill.
4, maximum to carry on the back single ability information.
Optionally an example, the maximum single ability information of back is for being characterized in history second time period maximum back list
Amount.
It should be understood that back list when maximum back list amount is non-super for the maximum in history second time period in the history second time period
Amount, in order to it is maximum non-super in subsequent first time period when the single amount of back distinguish, herein will be maximum non-in history second time period
The single amount of time-out back is denoted as in history second time period the single amount of maximum back.
The second time period can flexibly be set according to demand, for example, it may be 30 days, 28 days, 21 days, 14 days, 7 days, 5
It or 3 days etc..It is assumed that second time period is 30 days, the single amount of back can be with when the maximum of history second time period is non-super are as follows: in the past
The single amount of the average maximum back of 30 days dispatching resources.
Still optionally further, it may include that the single ability information of personal maximum back and team are maximum which, which carries on the back single ability information,
Carry on the back at least one of single ability information.Wherein, personal to carry on the back single ability for characterizing the dispatching resource in the second time of history
Single ability information is carried on the back for characterizing the affiliated team of the dispatching resource in history second time period by the maximum single amount of back, team in section
The average single amount of maximum back.Single ability information and team's maximum are carried on the back it should be understood that maximum is carried on the back list ability information and is divided into personal maximum
Single ability information is carried on the back, is because whether personal maximum carries on the back single ability or team's maximum carries on the back single ability and directly will affect dispatching
The single amount of back, hereafter will do it detailed description when the maximum of resource is non-super.
Step 102. is according to the conditional information, the attribute information and carries on the back single capability model, and assessment is at the first time
Back single amount when the maximum of dispatching resource is non-super in section.
Optionally, which can be one day.
Wherein, the input for carrying on the back single capability model may include the conditional information and the attribute information.Carry on the back single energy
The output of power model is back single amount when the maximum is non-super.The list capability model of carrying on the back is used to characterize the single amount of back and overtime probability
The corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when corresponding relationship, the maximum are non-super.
In order to make it easy to understand, being briefly described below to some concepts that embodiment of the present invention is related to:
1) back single amount when maximum non-super
Optionally an example, single amount is carried on the back when the maximum is non-super can be understood as dispatching resource maximum can carry on the back how many list.
For example, it is assumed that the single amount of back is 15 when the maximum that dispatching resource A is calculated is non-super, it can indicate that the dispatching resource A maximum can
Back 15 is single, if currently dispatching resource A has carried on the back 5 lists, at this point, can also be single to dispatching resource A distribution 10.
Optionally another example, carried on the back when the maximum is non-super single amount can be understood as currently dispensing resource maximum can also carry on the back it is more
It is few single.For example, it is assumed that the single amount of back is 10 when the maximum that dispatching resource A is calculated is non-super, can indicate that the dispatching can also be given
Resource A distributes 10 orders.For ease of description, below with " back is single when maximum non-super measures as current dispatching resource maximum also
It is illustrated for the how many lists of energy back ".It should be understood that " how many list can be carried on the back for dispatching resource maximum for the single amount of back when maximum non-super " this
Scheme may refer to the related description in embodiment of the present invention.
It should be noted that the single amount of back is all when being greater than maximum non-super it is to be understood that a critical value when maximum non-super
It carries on the back the corresponding overtime probability of the back list amount singly measured and is all larger than timeout threshold.For ease of description, it can incite somebody to action " when being greater than maximum non-super
Carry on the back the back list amount singly measured " it is denoted as " the single amount of the first back ", that is, and the corresponding overtime probability of the single amount of the first back is greater than the timeout threshold.
That is, the corresponding overtime probability of the single amount of back is less than or equal to timeout threshold, the single amount of the first back when maximum non-super
Corresponding time-out probability is greater than the timeout threshold, and it is a critical value that single amount is carried on the back when the maximum is non-super.
For example, it is assumed that timeout threshold=0.25, carrying on the back the step-length that single amount increases is 0.5, and it is general to carry on the back the corresponding time-out of single amount=9.5
Rate=0.18;Corresponding overtime probability=0.2 of the single amount=10 of back;Corresponding overtime probability=0.27 of the single amount=10.5 of back, is less than
Or the corresponding overtime probability of back list amount equal to 10 is less than timeout threshold, the corresponding overtime probability of the back list amount greater than 10 is greater than super
When threshold value, 10 be a critical value, and single amount=10 is carried on the back when the maximum is non-super.This 10.5 is the single amount of the first back above.
2) timeout threshold
Optionally, timeout threshold is it is to be understood that carry on the back the distribution feelings singly measured when the maximum of multiple dispatching resources is non-super
Condition meets the overtime probability of normal distribution.In other words, under the timeout threshold, back is single when the maximum of multiple dispatching resources is non-super
The distribution situation of amount meets normal distribution.
Specifically, between 0 to 1, a timeout threshold is determined, under the timeout threshold, determining multiple dispatching resources
Maximum it is non-super when to carry on the back single ability distribution situation be a normal distribution.
For example, it is assumed that there is 100 dispatching resources, if when overtime probability=0.25, this 100 dispatching resources correspondences 100
Single amount is carried on the back when maximum non-super, the distribution singly measured is carried on the back when 100 maximums are non-super and meets normal distribution, can determine that 0.25 is overtime
Threshold value.
Specifically, corresponding overtime probability is singly measured according to the available current back of the single capability model of back.For example, it is assumed that overtime
Threshold value is 0.25, and carrying on the back the corresponding timeout threshold of single amount n is 0.2, and the timeout threshold that all back greater than n are singly measured is all larger than 0.25,
The single amount of back, the back list capability model can export n when back list amount n is maximum non-super at this time.
That is: assuming that carrying on the back single capability model includes y=S (a, b, x), a, b are respectively conditional information and attribute information,
The two belong to the coefficient for carrying on the back single capability model, and x belongs to the variable carried on the back in single capability model, after coefficient is once input, according to y
With the size relation of timeout threshold, the value of x is determined, if the corresponding y of x is less than timeout threshold, and the corresponding y of x+i is greater than overtime threshold
Value can determine back single amount when x is maximum non-super, and the x value can be exported by carrying on the back single capability model, wherein i is that the single amount of back increases
Step-length.
Specifically, why consider at least one of above-mentioned several factors when back list amount when assessment is maximum non-super, be
Because several factors are the factor for influencing to carry on the back single amount (i.e. maximum to carry on the back list ability) when dispatching resource is maximum non-super.
By taking the single amount of back when weather influences maximum non-super as an example, when non-bad weather, the dispatching condition for dispensing resource is preferable, has
Carry out order dispatching conducive to dispatching resource high-efficiency, in the case, dispense resource maximum it is non-super when the single amount of back it is higher;Instead
It, when bad weather, dispensing the dispatching condition of resource, poor (for example, rain and snow weather, road conditions are poor, will affect riding for jockey
Speed), be unfavorable for carrying out order dispatching with dispensing resource high-efficiency, dispense resource maximum it is non-super when the single amount of back it is lower.
By taking the single amount of back when temperature influences maximum non-super as an example, when preference temperature, the dispatching condition for dispensing resource is preferable, favorably
In the carry out order dispatching of dispatching resource high-efficiency, dispense resource maximum it is non-super when the single amount of back it is higher;Conversely, high temperature or low temperature
When, dispense resource maximum it is non-super when the single amount of back it is lower.
By taking the single amount of back when influencing maximum non-super on the date as an example, noon peak and evening peak on weekdays, due to order total amount compared with
Height, the quantity on order being assigned to each dispatching resource can be higher, dispense resource maximum it is non-super when the single amount of back it is higher;Instead
It, in inoperative, dispense resource maximum it is non-super when the single amount of back it is less.In other words, working day and nonworkdays will affect
The distribution and order volume of order.
By taking always single amount influences to carry on the back single amount when maximum is non-super as an example, when total list measures more, the order for needing to dispense is more, herein
In the case of, dispatching resource needs the order that dispenses more, dispense resource maximum it is non-super when the single amount of back it is higher;Conversely, total single amount
When less, dispense resource maximum it is non-super when the single amount of back it is less (because can be distributed without so much order).
By taking back single amount when dispensing the current back list amount of resource and influencing maximum non-super as an example, it is assumed that the current back list of dispatching resource
Amount is very low, and the order that the dispatching resource can connect at this time is more, i.e. the single amount of back is higher when the maximum of the dispatching resource is non-super;Instead
It, it is assumed that the current back list amount of dispatching resource is very high, and the single amount of back is lower when the maximum of the dispatching resource is non-super.
When class information to dispense resource influences maximum non-super for the single amount of back, if the class information of dispatching resource compared with
Height illustrates that the dispatching efficiency of the dispatching resource or dispatching qualification are higher, and the ability of the dispatching resource is stronger, and the dispatching resource is most
The single amount of back is higher when big non-super;Conversely, if the class information of dispatching resource is lower, back single amount when the maximum of the dispatching resource is non-super
It is lower.
By taking the work number of days for dispensing resource as an example, if the work number of days of dispatching resource is more, illustrate the dispatching resource to warp
Test abundanter more familiar to road conditions, the ability of the dispatching resource is stronger, and the single amount of back is higher when the maximum of the dispatching resource is non-super;Instead
It, if the work number of days of dispatching resource is fewer, the single amount of back is lower when the maximum of the dispatching resource is non-super.
By it is personal maximum carry on the back single ability for, it is personal maximum to carry on the back single ability higher (i.e. the dispatching resource is in the historical data
The single amount of maximum back is higher), illustrate that the dispatching efficiency of the dispatching resource or dispatching qualification are higher, the ability of the dispatching resource is stronger,
The single amount of back is higher when the maximum of the dispatching resource is non-super;Conversely, the personal single ability of maximum back is lower, the maximum of the dispatching resource is non-
The single amount of time-out back is lower.
By taking team's maximum carries on the back single ability as an example, the single amount of maximum back is higher in the historical data for team, can be to the team point
With more order, the order of team's distribution is more, and the order for sharing single dispatching resource is more, corresponding dispatching resource
The single amount of back is higher when maximum non-super;Conversely, the single amount of maximum back is lower in the historical data for team, dispense resource maximum it is non-super when
The single amount of back is lower.
Consider above several factors when assessment is maximum non-super when back list amount based on this, be conducive to relatively accurately assess
Back single amount when maximum non-super.
In embodiments of the present invention, the corresponding different overtime probability of the single amount of different back can by presetting timeout threshold
Estimate dispatching resource maximum it is non-super when the single amount of back.Also, the Multiple factors for influencing the single ability of dispatching resource back are examined
Amount, keeps assessment result more accurate.
Fig. 2 is the flow chart of the method for the assessment dispatching resource capability in second embodiment according to the present invention.This implementation
Mode can be applied in terminal side, such as applied in mobile phone, the terminal devices such as tablet computer, can also be applied the clothes in network side
It is engaged in device.As shown in Fig. 2, this method comprises:
201. obtain the attribute information of current conditional information and dispatching resource;
202. are input to the attribute information of the conditional information and the dispatching resource in the single capability model of the back,
Obtain overtime probability of the dispatching resource under the single amount of initial back;
If overtime probability of the 203. dispatching resources under the initial single amount of back is less than the timeout threshold, with described
The initial single amount of back is initial value, X is that step-length is updated the back list amount of the dispatching resource;
204. calculate overtime probability of the dispatching resource under the single amount of back updated every time, until it is non-to obtain the maximum
The single amount of time-out back, wherein X is greater than 0.Optionally, X is equal to 1 or equal to 0.5.
Specifically, in second embodiment of the invention, to carry on the back single amount initially as initial value, X is step-length to dispatching resource
Back list amount be updated, and the lower overtime probability of the single amount of the back updated every time is calculated, until obtaining carrying on the back list when maximum is non-super
Amount.
That is, if the corresponding overtime probability of the single amount of initial back is no more than timeout threshold, on the basis of existing single amount
Often plus X back singly amount calculates primary overtime probability, timeout threshold is no more than with overtime probability and closest to the back list of timeout threshold
Back list amount when measuring non-super as the maximum for dispensing resource during order transport, that is, dispense resource and carry on the back single ability.
Optionally, which can be equal to the current back list amount of dispatching resource.Assuming that the back that dispatching resource is current
Single amount is M (M > 0), and X=0.5 calculates the corresponding overtime probability of M;
If the corresponding overtime probability of M is less than timeout threshold, the back list amount of dispatching resource is updated, M+0.5 is obtained, is counted
Calculate the corresponding overtime probability of M+0.5;
If the corresponding overtime probability of M+0.5 is less than timeout threshold, continue that the back list amount of dispatching resource is updated to obtain M
+ 0.5+0.5 calculates the corresponding overtime probability of M+0.5+0.5;
Aforesaid operations are repeated, until obtaining M+0.5*K, the corresponding overtime probability of M+0.5*K is less than or equal to timeout threshold,
It updates back singly to measure M+0.5* (K+1), and the corresponding overtime probability of M+0.5* (K+1) is greater than timeout threshold, can determine M+
Back single amount when 0.5*K is maximum non-super.
In embodiments of the present invention, being measured using the initial back list is initial value, X is back of the step-length to the dispatching resource
Single measure is updated, until obtaining carrying on the back single amount when the maximum is non-super, this method is easy to operate to be easily achieved, and is conducive to quick obtain
Single amount is carried on the back when non-super to accurate maximum.
Fig. 3 is the flow chart of the method for the assessment dispatching resource capability in third embodiment according to the present invention.This implementation
Mode can be applied in terminal side, such as applied in mobile phone, the terminal devices such as tablet computer, can also be applied the clothes in network side
It is engaged in device.As shown in figure 3, this method comprises:
301. obtain the attribute information of current conditional information and dispatching resource;
302. determine weather condition according to the conditional information;
If 303. weather conditions are bad weather, select the first ability model as the single capability model of back;If described
Weather condition is non-bad weather, selects the second ability model as the single capability model of back;
304. according to the conditional information, the dispatching resource attribute information and carry on the back single capability model, assessment is the
Back single amount when the maximum of the dispatching resource is non-super in one period.
Specifically, in embodiments of the present invention, the single capability model of the back is the first ability model or the second ability mould
Type, that is to say, that carrying on the back single capability model may include two versions.If the Weather information is used for characterizing bad weather
Back single amount when the first ability model obtains maximum non-super, if the Weather information uses the second energy for characterizing non-bad weather
Back single amount when power model obtains maximum non-super.
Optionally, the corresponding timeout threshold of the first ability model is less than the corresponding overtime threshold of the second ability model
Value.Specifically, because bad weather dispatching condition is poor (for example, road conditions are poor), the efficiency that will lead to dispatching resource is reduced,
In this case, lower timeout threshold is conducive to make dispatching resource that can complete to dispense in inclement weather on time.For example, it is assumed that
The corresponding timeout threshold of the second ability model (non-bad weather) is equal to 0.25, and the first ability model (bad weather) is corresponding super
When threshold value can be 0.2.
Optionally, if the single amount of back is abnormal when the maximum of the first ability model output is non-super, according to historical data
In back single amount when average maximum of the dispatching resource is non-super under the bad weather, determine in the first time period described in
Back single amount when the maximum of dispatching resource is non-super;And/or
If back single amount exception when maximum of the second ability model output is non-super, according in historical data described
Back single amount when the average maximum of the dispatching resource is non-super under non-bad weather determines the dispatching money in the first time period
Back single amount when the maximum in source is non-super.
Specifically, in abnormal cases, the logic of revealing all the details for carrying on the back single capability model can be non-according to the dispatching resource history maximum
Time-out back is single, to carry on the back single amount when determining bad weather and non-super non-boisterous maximum.
Optionally an example, in abnormal cases, the single amount of back is equal to the average maximum of history when can determine maximum non-super
Single amount is carried on the back when non-super.
Such as: in inclement weather, timeout threshold=0.2, according to the first ability model, assessment is matched in first time period
The single amount of back is single for 12 when sending the maximum of resource non-super, under non-bad weather, timeout threshold=0.25, according to the second ability mould
The single amount of back is 10 single when the maximum of type, assessment dispatching resource in first time period is non-super, which belongs to abnormal conditions, it is assumed that
Within past 7 days, in inclement weather, the average value that back is singly measured when dispatching resource A is maximum non-super is 9 single, can be determined the
The single amount of back is single for 9 when the maximum of dispatching resource is non-super in one period, i.e., it is single that 12 obtained assessment are singly modified to 9;In non-evil
Under bad weather, the average value that back is singly measured when dispatching resource A is maximum non-super is 11 single, i.e., 10 obtained assessment are singly modified to 11
It is single.
In order to easy to operate in all weather, the first ability model and the second energy can be used in optionally an example
Power model calculate separately corresponding maximum it is non-super when the single amount of back.
Back list ability mould for a further understanding of embodiment of the present invention, in the embodiment of the present invention described in detail below
Type.
One, the selection of single capability model is carried on the back.
Specifically, model may include a variety of, for example, may include linear regression model (LRM) and Logic Regression Models.At me
Scheme in, it would be desirable to select a kind of model, be able to carry out whether Chao Shi judgement.Wherein, linear regression model (LRM) can not
Carry out 0, the 1 judgement judgement of time-out (can not be made whether), and Logic Regression Models 0,1 judgement may be implemented (can be into
Whether time-out judges row, for example, it may be determined that 0 is to have not timed out, 1 is time-out), it is thereby possible to select Logic Regression Models conduct
Core algorithm.That is, the back list capability model logic-based regression algorithm in embodiment of the present invention constructs.
Two, the input and output of single capability model are carried on the back
Specifically, the feature on waybill can be described by carrying on the back single capability model, wherein the feature on waybill may include:
Waybill, wherein waybill may include: the date, weather, temperature, temporal information, in Air Way Bill No. at least
It is a kind of;
Dispense resource information, wherein dispatching resource information may include: to dispense the name of resource, ID, dispense resource etc.
At least one of the information of team where grade, dispatching resource history carry on the back single ability, dispatching resource, wherein where dispatching resource
The information of team may include: back single amount when the maximum of dispatching resource team is non-super.
The input for carrying on the back single capability model may include features described above, according to the Logic Regression Models carried on the back in single capability model,
Whether the available waybill is overtime, wherein 0 indicates to have not timed out, and 1 indicates time-out.The core algorithm for carrying on the back single capability model is to patrol
Volume regression model, the output of Logic Regression Models are 0 or 1, based on this 0 or 1, when to carry on the back the output of single capability model be maximum non-super
The single amount of back.
Three, the construction of single capability model training set is carried on the back
It in model training, needs trained the set pair analysis model and is trained, it is alternatively possible to ordering according to historical time section
Forms data constructs training set.It is, for example, possible to use the order datas on peak of nearest 14 day noon (10:30~12:30) as training
Collection.Further, due to overtime order compared to it is non-super when order account for it is smaller, when constructing training set, adjustable time-out
Sample and it is non-super when sample ratio.That is, overtime sample and it is non-super when sample between ratio be equal to preset value.
For example, it is assumed that preset ratio is 1:1, in the order data on 14 day noon peak (10:30~12:30), time-out is ordered
Singly have 130,000, order has 1,000,000 when non-super, in sampling process, to it is non-super when order take 13% (i.e. 130,000) as overtime sample
This, will all overtime orders as overtime sample so that overtime sample and it is non-super when sample ratio be 1:1.
Four, the construction of forecast set.
Optionally, it after model training is completed, needs prediction the set pair analysis model and is detected.It is alternatively possible to according to going through
The order data structure forecast collection of history period, it should be appreciated that the forecast set and above-mentioned training set are non-overlapping.
For example, it is assumed that preset ratio is 1:1, in the order data on 14 day noon peak (10:30~12:30), time-out is ordered
Singly have 130,000, order has 1,000,000 when non-super, choose 120,000 overtime orders and 120,000 it is non-super when order be used as training set, selection
In the overtime order of residue 10,000 and residue 880,000 10,000 it is non-super when order as forecast set.
Five, single capability model training is carried on the back
In the training process, a timeout threshold is defined, for example, 0.25 (illustrates and may refer to timeout threshold above
Associated description), using the order data in training set, calculate overtime probability and be no more than 0.25 and back list when closest to 0.25
Amount adjusts model parameter, until singly amount obtains carrying on the back single capability model the corresponding back of all order datas close to being just distributed very much.
Further, from the foregoing, it can be understood that the back list capability model in embodiment of the present invention include the first ability model and
The second ability model.Above-mentioned back list capability model related introduction, there is no consider influence of the weather to the single ability of dispatching resource back.
Therefore, can further be segmented on the basis of above-mentioned model bad weather version the first ability model and non-bad weather version
This second ability model.Wherein, the first ability model and the second ability model are close, and difference place includes the following:
1) training set range is different.
Specifically, it is assumed that the training set of the second ability model include nearest 14 days non-bad weather noons peak (10:30~
Order data 12:30), for the first ability model, since the ratio that bad weather occurs is relatively low, so will instruction
Practice collection range and extended to nearest 90 days from nearest 14 days, is i.e. the training set of the first ability model includes under nearest 90 days bad weathers
The order data on noon peak (10:30~12:30).That is, the training set range of the first ability model is greater than the second ability
The training set range of model.
2) forecast set is different
Specifically, the forecast set of the second ability model includes peak of nearest 14 days non-bad weather noons (10:30~12:30)
Order data.For the second ability model, two parts of forecast sets can be constructed, are that general bad weather is corresponding pre- respectively
It surveys and collects forecast set corresponding with extreme weather, the second ability model is predicted using two parts of forecast sets, so that the
Two capability models can accurately predict the back list ability of general bad weather and extreme weather.
3) timeout threshold is different
From the foregoing, it can be understood that since bad weather will lead to the single ability decline of back, the corresponding time-out of the first ability model
Threshold value is lower than the corresponding timeout threshold of the second ability model, and the different detailed description of timeout threshold may refer to above mutually speak on somebody's behalf
It is bright, in order to not repeat herein succinctly.
Fig. 4 is the method flow diagram of the Order splitting in the 4th embodiment according to the present invention.Present embodiment can answer
Used in terminal side, such as applies in mobile phone, the terminal devices such as tablet computer, can also apply in the server of network side.Such as
Shown in Fig. 4, this method comprises:
401. obtain dispatching resources in first time period maximum it is non-super when the single amount of back, wherein the maximum is carried on the back when non-super
Single amount is obtained based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the single capability model of the back
For characterizing the corresponding relationship of back single amount and overtime probability, the corresponding time-out probability of the single amount of back is less than or waits when maximum is non-super
In timeout threshold;
402. carry on the back single amount when non-super according to the maximum of the dispatching resource, carry out Order splitting.
Specifically, the single amount of back carries out Order splitting when can be non-super according to maximum.For example, it is assumed that according to single ability mould is carried on the back
Type determines that the single amount of back is 10 when the maximum of dispatching resource #1 is non-super, dispatching resource #1 can also carry on the back it is 10 single, therefore can will be new
Order splitting gives dispatching resource #1.In another example, it is assumed that according to single capability model is carried on the back, determines and carried on the back when the maximum of dispatching resource #2 is non-super
Single amount is 0, and new order should distribute other dispatching resources provided except dispatching resource #2.
In the application embodiment, can according to it is maximum non-super when the single amount of back, carry out Order splitting, be conducive to efficiently,
Reasonable distribution order, improves dispatching efficiency.
It should be understood that the related description that back is singly measured when the maximum in the embodiment is non-super can be public according to embodiment above
The associated description for the method opened, for sake of simplicity, not repeating herein.
Fig. 5 is the method schematic diagram of the dispatching scheduling of resource in the 5th embodiment according to the present invention.Present embodiment can
To apply in terminal side, such as applies in mobile phone, the terminal devices such as tablet computer, the server in network side can also be applied
In.As shown in figure 5, this method comprises:
501. obtain dispatching resources in first time period maximum it is non-super when the single amount of back, wherein the maximum is carried on the back when non-super
Single amount is obtained based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the single capability model of the back
For characterizing the corresponding relationship of back single amount and overtime probability, the corresponding time-out probability of the single amount of back is less than or waits when maximum is non-super
In timeout threshold;
502. according to the maximum of the dispatching resource it is non-super when back single amount dispatch the dispatching resource.
Specifically, the single amount of back, carries out dispatching scheduling of resource when can be non-super according to maximum.For example, it is assumed that dispatching resource is most
The single amount of back is larger when big non-super, can dispatch the multiple order of dispatching resource.Assuming that when dispatching resource is maximum non-super the single amount of back compared with
It is small, dispatch the dispatching resource order amount should be less than corresponding maximum of the dispatching resource it is non-super when back is single measures.
It should be understood that the related description that back is singly measured when the maximum in the embodiment is non-super can be public according to embodiment above
The associated description for the method opened, for sake of simplicity, not repeating herein.
Fig. 6 is the schematic diagram of the device of the assessment dispatching resource capability in sixth embodiment according to the present invention.
As shown in fig. 6, the device includes:
601. obtain module, for obtaining conditional information and dispensing the attribute information of resource;
602. evaluation modules, for according to the conditional information, the attribute information of the dispatching resource and the single ability of back
Back single amount when the maximum of model, assessment dispatching resource in first time period is non-super, wherein the single capability model of the back is used
The corresponding relationship of single amount and overtime probability is carried on the back in characterization, and the corresponding time-out probability of the single amount of back is less than or equal to when maximum is non-super
Timeout threshold.
It is not difficult to find that present embodiment is Installation practice corresponding with first embodiment, present embodiment can be with
First embodiment is worked in coordination implementation.The relevant technical details mentioned in first embodiment still have in the present embodiment
Effect, in order to reduce repetition, which is not described herein again.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in
In first embodiment.
Fig. 7 is the device flow chart of the Order splitting in the 7th embodiment according to the present invention.As shown in fig. 7, the device
Include:
701. obtain module, back single amount when the maximum for obtaining dispatching resource in first time period is non-super, wherein described
Back list amount based on conditional information, the attribute information for dispensing resource and carries on the back single capability model acquisition when maximum non-super, described
Carry on the back the corresponding relationship that single capability model is used to characterize back single amount and overtime probability, back list amount corresponding time-out when maximum is non-super
Probability is less than or equal to timeout threshold;
702. distribution modules, back single amount when non-super for the maximum according to the dispatching resource, carry out Order splitting.
It is not difficult to find that present embodiment is Installation practice corresponding with the 4th embodiment, present embodiment can be with
4th embodiment is worked in coordination implementation.The relevant technical details mentioned in 4th embodiment still have in the present embodiment
Effect, in order to reduce repetition, which is not described herein again.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in
In 4th embodiment.
Fig. 8 is the schematic device of the dispatching scheduling of resource in the 8th embodiment according to the present invention.As shown in figure 8, should
Device includes:
801. obtain module, back single amount when the maximum for obtaining dispatching resource in first time period is non-super, wherein described
The single amount of back is obtained based on single capability model is carried on the back when maximum non-super, and the input for carrying on the back single capability model includes current conditional information
With the attribute information of dispatching resource, the list capability model of carrying on the back is used to characterize the corresponding relationship for carrying on the back single amount with overtime probability, described
The corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when maximum non-super, and the corresponding overtime probability of the single amount of the first back is big
In the timeout threshold, the first back single amount carries on the back the back list amount singly measured when being non-super greater than the maximum;
802. scheduler modules, the single amount of back, carries out dispatching scheduling of resource when being used for non-super according to the maximum.
It is not difficult to find that present embodiment is Installation practice corresponding with the 5th embodiment, present embodiment can be with
5th embodiment is worked in coordination implementation.The relevant technical details mentioned in 5th embodiment still have in the present embodiment
Effect, in order to reduce repetition, which is not described herein again.Correspondingly, the relevant technical details mentioned in present embodiment are also applicable in
In 5th embodiment.
It is noted that each mould involved in sixth embodiment, the 7th embodiment and the 8th embodiment
Block is logic module, and in practical applications, a logic unit can be a physical unit, is also possible to a physics list
A part of member, can also be realized with the combination of multiple physical units.In addition, in order to protrude innovative part of the invention, the 6th
Not by the technical problem relationship proposed by the invention with solution in embodiment, the 7th embodiment and the 8th embodiment
Less close unit introduces, but this does not indicate and does not deposit in sixth embodiment, the 7th embodiment and the 8th embodiment
In other units.
Fig. 9 is the electronic devices structure schematic diagram in the 9th embodiment according to the present invention.As shown in figure 9, the electronics is set
It is standby to include:
At least one processor 901;And the memory 902 with the communication connection of at least one described processor 901;With
And the communication component 903 with scanning means communication connection, communication component 903 send and receive number under the control of processor 901
According to;Wherein, memory 902 is stored with the instruction that can be executed by least one processor 901, instructs by least one processor
901 execute to realize:
It obtains conditional information and dispenses the attribute information of resource;
According to the conditional information, the attribute information of the dispatching resource and the single capability model of back, assess at first
Between in section the dispatching resource maximum it is non-super when the single amount of back, wherein the single capability model of the back is for characterizing the single amount of back and surpassing
When probability corresponding relationship, the corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the maximum is non-super.
It is taken a processor as an example in Fig. 9.Processor 901, memory 902 can be connected by bus or other modes
It connects, in Fig. 9 for being connected by bus.Memory 902 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for
Store non-volatile software program, non-volatile computer executable program and module.Processor 901 is stored in by operation
Non-volatile software program, instruction and module in memory 902, thereby executing the various function application and data of equipment
The method of above-mentioned assessment dispatching resource capability is realized in processing.
The said goods can be performed the application embodiment provided by method, have the corresponding functional module of execution method and
Beneficial effect, the not technical detail of detailed description in the present embodiment, reference can be made to method provided by the application embodiment.
Figure 10 is the electronic devices structure schematic diagram in the tenth embodiment according to the present invention.This is as shown in Figure 10, the electricity
Sub- equipment includes:
At least one processor 1001;And the memory 1002 with the communication connection of at least one described processor 1001;
And with scanning means communication connection communication component 1003, communication component 1003 is received under the control of processor 1001 with
Send data;Wherein, memory 1002 is stored with the instruction that can be executed by least one processor 1001, instructs by least one
Processor 1001 is executed to realize:
Obtain dispatching resource in first time period maximum it is non-super when the single amount of back, wherein back is single when maximum is non-super measures
It is obtained based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the single capability model of the back is used for
The corresponding overtime probability of the single amount of back, which is less than or equal to, when the corresponding relationship of characterization back single amount and overtime probability, maximum are non-super surpasses
When threshold value;
Back single amount when non-super according to the maximum of the dispatching resource, carries out Order splitting.
It is taken a processor as an example in Figure 10.Processor 1001, memory 1002 can pass through bus or other modes
It connects, in Figure 10 for being connected by bus.Memory 1002 is used as a kind of non-volatile computer readable storage medium storing program for executing, can
For storing non-volatile software program, non-volatile computer executable program and module.Processor 1001 passes through operation
Non-volatile software program, instruction and the module being stored in memory 1002, thereby executing the various function application of equipment
And data processing, that is, realize the method for the above order distribution.
Figure 11 is the electronic devices structure schematic diagram in the 11st embodiment according to the present invention.This as shown in figure 11, should
Electronic equipment includes:
At least one processor 1101;And the memory 1102 with the communication connection of at least one described processor 1101;
And with scanning means communication connection communication component 1103, communication component 1103 is received under the control of processor 1101 with
Send data;Wherein, memory 1102 is stored with the instruction that can be executed by least one processor 1101, instructs by least one
Processor 1101 is executed to realize:
Obtain dispatching resource in first time period maximum it is non-super when the single amount of back, wherein back is single when maximum is non-super measures
It is obtained based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the single capability model of the back is used for
The corresponding overtime probability of the single amount of back, which is less than or equal to, when the corresponding relationship of characterization back single amount and overtime probability, maximum are non-super surpasses
When threshold value;
According to the maximum of the dispatching resource it is non-super when back single amount dispatch the dispatching resource.
In Figure 11 by taking a processor 1101 as an example.Processor 1101, memory 1102 can by bus or other
Mode connects, in Figure 11 for being connected by bus.Memory 1102 is used as a kind of non-volatile computer readable storage medium
Matter can be used for storing non-volatile software program, non-volatile computer executable program and module.Processor 1101 passes through
Non-volatile software program, instruction and the module being stored in memory 1102 are run, thereby executing the various functions of equipment
Using and data processing, that is, realize the method for above-mentioned dispatching scheduling of resource.
The said goods can be performed the application embodiment provided by method, have the corresponding functional module of execution method and
Beneficial effect, the not technical detail of detailed description in the present embodiment, reference can be made to method provided by the application embodiment.
In the electronic equipment of ninth embodiment of the invention, the tenth embodiment and the 11st embodiment, memory
It may include storing program area and storage data area, wherein storing program area can be needed for storage program area, at least one function
The application program wanted;It storage data area can the Save option list etc..In addition, memory may include high random access storage
Device, can also include nonvolatile memory, a for example, at least disk memory, flush memory device or other are non-volatile
Solid-state memory.In some embodiments, it includes the memory remotely located relative to processor that memory is optional, these
Remote memory can pass through network connection to external equipment.The example of above-mentioned network includes but is not limited to internet, in enterprise
Portion's net, local area network, mobile radio communication and combinations thereof.
Twelveth embodiment of the invention is related to a kind of computer readable storage medium, is stored with computer program.It calculates
Machine program realizes the embodiment of the method for above-mentioned assessment dispatching resource capability when being executed by processor.
Thirteenth embodiment of the invention is related to a kind of computer readable storage medium, is stored with computer program.It calculates
Machine program realizes the embodiment of the method for above-mentioned distribution order when being executed by processor.
Fourteenth embodiment of the invention is related to a kind of computer readable storage medium, is stored with computer program.It calculates
Machine program realizes the embodiment of the method for above-mentioned scheduling dispatching resource when being executed by processor.
That is, it will be understood by those skilled in the art that implement the method for the above embodiments be can be with
Relevant hardware is instructed to complete by program, which is stored in a storage medium, including some instructions are to make
It obtains an equipment (can be single-chip microcontroller, chip etc.) or processor (processor) executes side described in each embodiment of the application
The all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
It will be understood by those skilled in the art that the respective embodiments described above are to realize specific embodiments of the present invention,
And in practical applications, can to it, various changes can be made in the form and details, without departing from the spirit and scope of the present invention.
The application embodiment provides a kind of method of assessment dispatching resource capability of A1., comprising:
It obtains conditional information and dispenses the attribute information of resource;
According to the conditional information, the attribute information of the dispatching resource and the single capability model of back, assess at first
Between in section the dispatching resource maximum it is non-super when the single amount of back, wherein the single capability model of the back is for characterizing the single amount of back and surpassing
When probability corresponding relationship, the corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the maximum is non-super.
A2. method according to a1, it is described according to the conditional information, the attribute information and the single ability mould of back
Back single amount when the maximum of type, assessment dispatching resource in first time period is non-super, comprising:
The attribute information of the conditional information and the dispatching resource is input in the single capability model of the back, is obtained
Overtime probability of the dispatching resource under the single amount of initial back;
If overtime probability of the dispatching resource under the initial single amount of back is less than the timeout threshold, with described initial
The single amount of back is initial value, X is that step-length is updated the back list amount of the dispatching resource;
Calculate overtime probability of the dispatching resource under the single amount of back updated every time, until obtain the maximum it is non-super when
The single amount of back, wherein X is greater than 0.
A3. method according to a1 or a2, the single capability model of the back are the first ability model or the second ability model,
It is described according to the conditional information, the attribute information of the dispatching resource and carry on the back single capability model, assess in first time period
When the maximum of the interior dispatching resource is non-super before the single amount of back, the method also includes:
Weather condition is determined according to the conditional information;
If the weather condition is bad weather, select the first ability model as the single capability model of the back;
If the weather condition is non-bad weather, select the second ability model as the single capability model of the back.
A4. method according to a3, the corresponding timeout threshold of the first ability model are less than the second ability mould
The corresponding timeout threshold of type.
A5. method according to a3, it is described according to the conditional information, the attribute information and the single ability mould of back
Back single amount when the maximum of type, assessment dispatching resource in first time period is non-super, comprising:
If back single amount exception when maximum of the first ability model output is non-super, according in historical data described
The single amount of back, determines the dispatching resource in the first time period when the average maximum of the dispatching resource is non-super under bad weather
Maximum it is non-super when the single amount of back;And/or
If back single amount exception when maximum of the second ability model output is non-super, according in historical data described
Back single amount when the average maximum of the dispatching resource is non-super under non-bad weather determines the dispatching money in the first time period
Back single amount when the maximum in source is non-super.
A6. method according to a1 or a2, the single capability model logic-based regression algorithm building of the back, or
The single capability model of the back is obtained based on model training, overtime sample and it is non-super when sample between ratio be default
Ratio.
A7. method according to a1 or a2, the conditional information include Weather information, temperature information, date information with
And at least one of total single amount information;
The attribute information of the dispatching resource includes the single amount information of current back, class information, work number of days information and most
It is big to carry on the back at least one of single ability information, wherein the maximum single ability information of back is for being characterized in history second time period
The interior single amount of maximum back.
A8. the method according to A7, the maximum single ability information of back includes that individual carries on the back list ability information and team's back
At least one of single ability information, wherein individual carries on the back single ability for characterizing the dispatching resource in history second time period
The interior single amount of maximum back, team carry on the back single ability information and put down in history second time period for characterizing the affiliated team of the dispatching resource
The maximum single amount of back.
Embodiment further provides a kind of methods of Order splitting of B9. by the application, which comprises
Obtain dispatching resource in first time period maximum it is non-super when the single amount of back, wherein back is single when maximum is non-super measures
It is obtained based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the single capability model of the back is used for
The corresponding overtime probability of the single amount of back, which is less than or equal to, when the corresponding relationship of characterization back single amount and overtime probability, maximum are non-super surpasses
When threshold value;
Back single amount when non-super according to the maximum of the dispatching resource, carries out Order splitting.
Embodiment further provides a kind of methods for dispensing scheduling of resource of C10. by the application, which comprises
Obtain dispatching resource in first time period maximum it is non-super when the single amount of back, wherein back is single when maximum is non-super measures
It is obtained based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the single capability model of the back is used for
The corresponding overtime probability of the single amount of back, which is less than or equal to, when the corresponding relationship of characterization back single amount and overtime probability, maximum are non-super surpasses
When threshold value;
According to the maximum of the dispatching resource it is non-super when back single amount dispatch the dispatching resource.
Embodiment further provides the devices that a kind of assessment dispatching resource of D11. carries on the back single ability by the application, comprising:
Module is obtained, for obtaining conditional information and dispensing the attribute information of resource;
Evaluation module, for according to the attribute information of the conditional information, the dispatching resource and carrying on the back single capability model,
Back single amount when the maximum of assessment dispatching resource in first time period is non-super, wherein the single capability model of the back is used for table
The corresponding overtime probability of the single amount of back is less than or equal to overtime when the corresponding relationship of sign back single amount and overtime probability, maximum are non-super
Threshold value.
Embodiment further provides a kind of device of Order splitting of E12., described devices to include: by the application
Module is obtained, back single amount when the maximum for obtaining dispatching resource in first time period is non-super, wherein the maximum
It carries on the back single amount when non-super to obtain based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the back is single
Capability model is used to characterize the corresponding relationship of back single amount and overtime probability, and back is single when maximum is non-super measures corresponding time-out probability
Less than or equal to timeout threshold;
Distribution module, back single amount when non-super for the maximum according to the dispatching resource, carries out Order splitting.
The application embodiment party additionally provides a kind of device for dispensing scheduling of resource of F13., and described device includes:
Module is obtained, back single amount when the maximum for obtaining dispatching resource in first time period is non-super, wherein the maximum
It carries on the back single amount when non-super to obtain based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the back is single
Capability model is used to characterize the corresponding relationship of back single amount and overtime probability, and back is single when maximum is non-super measures corresponding time-out probability
Less than or equal to timeout threshold;
Scheduler module, according to the maximum of the dispatching resource it is non-super when back single amount dispatch the dispatching resource.
The application embodiment party also discloses G14. a kind of electronic equipment, comprising:
At least one processor;And
The memory being connect at least one described processor communication;
Wherein, the memory is stored with the instruction that can be executed by least one described processor, and described instruction is described
At least one processor is executed to realize: being obtained conditional information and is dispensed the attribute information of resource;
According to the conditional information, the attribute information of the dispatching resource and the single capability model of back, assess at first
Between in section the dispatching resource maximum it is non-super when the single amount of back, wherein the single capability model of the back is for characterizing the single amount of back and surpassing
When probability corresponding relationship, the corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the maximum is non-super.
G15. the electronic equipment according to G14, described instruction are executed by least one described processor to realize:
The attribute information of the conditional information and the dispatching resource is input in the single capability model of the back, is obtained
Overtime probability of the dispatching resource under the single amount of initial back;
If overtime probability of the dispatching resource under the initial single amount of back is less than the timeout threshold, with described initial
The single amount of back is initial value, X is that step-length is updated the back list amount of the dispatching resource;
Calculate overtime probability of the dispatching resource under the single amount of back updated every time, until obtain the maximum it is non-super when
The single amount of back, wherein X is greater than 0.
G16. the electronic equipment according to G14 or G15, the processor are also used to:
Weather condition is determined according to the conditional information;
If the weather condition is bad weather, select the first ability model as the single capability model of the back;
If the weather condition is non-bad weather, select the second ability model as the single capability model of the back.
G17. the electronic equipment according to G16, the corresponding timeout threshold of the first ability model are less than described second
The corresponding timeout threshold of capability model.
G18. the electronic equipment according to G16, described instruction are executed by least one described processor to implement:
If back single amount exception when maximum of the first ability model output is non-super, according in historical data described
The single amount of back, determines the dispatching resource in the first time period when the average maximum of the dispatching resource is non-super under bad weather
Maximum it is non-super when the single amount of back;And/or
If back single amount exception when maximum of the second ability model output is non-super, according in historical data described
Back single amount when the average maximum of the dispatching resource is non-super under non-bad weather determines the dispatching money in the first time period
Back single amount when the maximum in source is non-super.
G19. the electronic equipment according to G14 or G15, the single capability model logic-based regression algorithm building of the back,
And/or
The single capability model of the back is obtained based on model training, overtime sample and it is non-super when sample between ratio be default
Ratio.
G20. the electronic equipment according to G14 or G15, the conditional information include Weather information, temperature information, date
At least one of information and total single amount;
The attribute information of the dispatching resource includes the single amount of initial back, class information, work number of days information and maximum back
At least one of single ability information, wherein the maximum list ability information of carrying on the back is for being characterized in history second time period most
The big single amount of back.
G21. the electronic equipment according to G20, it is described it is maximum carry on the back single ability information include it is personal carry on the back single ability information and
At least one of single ability information is carried on the back by team, wherein individual carries on the back single ability for characterizing individual in history second time period
Single ability information is carried on the back for characterizing team's average maximum single amount of back in history second time period by the single amount of maximum back, team.
For the application embodiment further provides H22. a kind of electronic equipment, the electronic equipment includes: at least one processing
Device;And
The memory being connect at least one described processor communication;
Wherein, the memory is stored with the instruction that can be executed by least one described processor, and described instruction is described
At least one processor is executed to realize: back list amount when the maximum of dispatching resource is non-super in acquisition first time period, wherein described
Back list amount based on conditional information, the attribute information for dispensing resource and carries on the back single capability model acquisition when maximum non-super, described
Carry on the back the corresponding relationship that single capability model is used to characterize back single amount and overtime probability, back list amount corresponding time-out when maximum is non-super
Probability is less than or equal to timeout threshold;
Back single amount when non-super according to the maximum of the dispatching resource, carries out Order splitting.
For the application embodiment further provides I23. a kind of electronic equipment, the electronic equipment includes: at least one processing
Device;And
The memory being connect at least one described processor communication;
Wherein, the memory is stored with the instruction that can be executed by least one described processor, and described instruction is described
At least one processor is executed to realize: back list amount when the maximum of dispatching resource is non-super in acquisition first time period, wherein described
Back list amount based on conditional information, the attribute information for dispensing resource and carries on the back single capability model acquisition when maximum non-super, described
Carry on the back the corresponding relationship that single capability model is used to characterize back single amount and overtime probability, back list amount corresponding time-out when maximum is non-super
Probability is less than or equal to timeout threshold;
According to the maximum of the dispatching resource it is non-super when back single amount dispatch the dispatching resource.
The application is stored with computer program embodiment further provides a kind of computer readable storage medium of J24., institute
State method of the computer-readable program for executing the assessment dispatching resource capability as described in any one of A1 to A8 for computer.
The application is stored with computer program embodiment further provides a kind of computer readable storage medium of K25., institute
State method of the computer-readable program for executing the Order splitting as described in A9 for computer.
The application is stored with computer program embodiment further provides a kind of computer readable storage medium of L26., institute
State method of the computer-readable program for executing the dispatching scheduling of resource as described in A10 for computer.
Claims (10)
1. a kind of method of assessment dispatching resource capability characterized by comprising
It obtains conditional information and dispenses the attribute information of resource;
According to the conditional information, the attribute information of the dispatching resource and the single capability model of back, assess in first time period
Back single amount when the maximum of the interior dispatching resource is non-super, wherein the single capability model of the back is general for characterizing the single amount of back and time-out
The corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the corresponding relationship of rate, the maximum are non-super.
2. the method according to claim 1, wherein it is described according to the conditional information, the attribute information with
And single capability model is carried on the back, back single amount when the maximum of assessment dispatching resource in first time period is non-super, comprising:
The attribute information of the conditional information and the dispatching resource is input in the single capability model of the back, is obtained described
Dispense overtime probability of the resource under the single amount of initial back;
If overtime probability of the dispatching resource under the initial single amount of back is less than the timeout threshold, single with the initial back
Amount is initial value, X is that step-length is updated the back list amount of the dispatching resource;
The overtime probability for dispensing resource under the single amount of back updated every time is calculated, until obtaining carrying on the back when the maximum is non-super single
Amount, wherein X is greater than 0.
3. method according to claim 1 or 2, which is characterized in that the single capability model of the back be the first ability model or
The second ability model, it is described according to the conditional information, the attribute information of the dispatching resource and carry on the back single capability model, assessment
When the maximum of the dispatching resource is non-super in first time period before the single amount of back, the method also includes:
Weather condition is determined according to the conditional information;
If the weather condition is bad weather, select the first ability model as the single capability model of the back;
If the weather condition is non-bad weather, select the second ability model as the single capability model of the back.
4. according to the method described in claim 3, it is characterized in that, the corresponding timeout threshold of the first ability model is less than institute
State the corresponding timeout threshold of the second ability model.
5. according to the method described in claim 3, it is characterized in that, it is described according to the conditional information, the attribute information with
And single capability model is carried on the back, back single amount when the maximum of assessment dispatching resource in first time period is non-super, comprising:
If the single amount of back is abnormal when maximum of the first ability model output is non-super, according in historical data it is described badly
The single amount of back, determines that the dispatching resource is most in the first time period when the average maximum of the dispatching resource is non-super under weather
Back single amount when big non-super;And/or
If back single amount exception when maximum of the second ability model output is non-super, according in historical data in the non-evil
Back single amount when the average maximum of the dispatching resource is non-super under bad weather determines the dispatching resource in the first time period
Back single amount when maximum non-super.
6. a kind of method of Order splitting, which is characterized in that the described method includes:
Obtain dispatching resource in first time period maximum it is non-super when the single amount of back, wherein single measure of back is based on when maximum is non-super
Conditional information, the attribute information of the dispatching resource and the single capability model of back obtain, and the single capability model of the back is for characterizing
The corresponding overtime probability of the single amount of back is less than or equal to time-out threshold when the corresponding relationship of back single amount and overtime probability, maximum are non-super
Value;
Back single amount when non-super according to the maximum of the dispatching resource, carries out Order splitting.
7. a kind of method for dispensing scheduling of resource, which is characterized in that the described method includes:
Obtain dispatching resource in first time period maximum it is non-super when the single amount of back, wherein single measure of back is based on when maximum is non-super
Conditional information, the attribute information of the dispatching resource and the single capability model of back obtain, and the single capability model of the back is for characterizing
The corresponding overtime probability of the single amount of back is less than or equal to time-out threshold when the corresponding relationship of back single amount and overtime probability, maximum are non-super
Value;
According to the maximum of the dispatching resource it is non-super when back single amount dispatch the dispatching resource.
8. a kind of electronic equipment, comprising:
At least one processor;And
The memory being connect at least one described processor communication;
Wherein, the memory be stored with can by least one described processor execute instruction, described instruction by it is described at least
One processor is executed to realize: being obtained conditional information and is dispensed the attribute information of resource;
According to the conditional information, the attribute information of the dispatching resource and the single capability model of back, assess in first time period
Back single amount when the maximum of the interior dispatching resource is non-super, wherein the single capability model of the back is general for characterizing the single amount of back and time-out
The corresponding overtime probability of the single amount of back is less than or equal to timeout threshold when the corresponding relationship of rate, the maximum are non-super.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes: at least one processor;And
The memory being connect at least one described processor communication;
Wherein, the memory be stored with can by least one described processor execute instruction, described instruction by it is described at least
One processor is executed to realize: back list amount when the maximum of dispatching resource is non-super in acquisition first time period, wherein the maximum
It carries on the back single amount when non-super to obtain based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the back is single
Capability model is used to characterize the corresponding relationship of back single amount and overtime probability, and back is single when maximum is non-super measures corresponding time-out probability
Less than or equal to timeout threshold;
Back single amount when non-super according to the maximum of the dispatching resource, carries out Order splitting.
10. a kind of electronic equipment, which is characterized in that the electronic equipment includes: at least one processor;And
The memory being connect at least one described processor communication;
Wherein, the memory be stored with can by least one described processor execute instruction, described instruction by it is described at least
One processor is executed to realize: back list amount when the maximum of dispatching resource is non-super in acquisition first time period, wherein the maximum
It carries on the back single amount when non-super to obtain based on conditional information, the attribute information of the dispatching resource and the single capability model of back, the back is single
Capability model is used to characterize the corresponding relationship of back single amount and overtime probability, and back is single when maximum is non-super measures corresponding time-out probability
Less than or equal to timeout threshold;
According to the maximum of the dispatching resource it is non-super when back single amount dispatch the dispatching resource.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811443129.4A CN109636276A (en) | 2018-11-29 | 2018-11-29 | Assessment dispatching resource capability, Order splitting, dispatching resource regulating method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811443129.4A CN109636276A (en) | 2018-11-29 | 2018-11-29 | Assessment dispatching resource capability, Order splitting, dispatching resource regulating method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109636276A true CN109636276A (en) | 2019-04-16 |
Family
ID=66069770
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811443129.4A Pending CN109636276A (en) | 2018-11-29 | 2018-11-29 | Assessment dispatching resource capability, Order splitting, dispatching resource regulating method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109636276A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325503A (en) * | 2020-02-10 | 2020-06-23 | 拉扎斯网络科技(上海)有限公司 | Order processing method, device, server and nonvolatile storage medium |
CN112036695A (en) * | 2020-07-28 | 2020-12-04 | 拉扎斯网络科技(上海)有限公司 | Weather information prediction method and device, readable 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 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107403296A (en) * | 2017-06-29 | 2017-11-28 | 北京小度信息科技有限公司 | Conveyance equilibrium method and device |
CN108564269A (en) * | 2018-04-09 | 2018-09-21 | 北京小度信息科技有限公司 | Dispense method for allocating tasks, device, electronic equipment and computer storage media |
-
2018
- 2018-11-29 CN CN201811443129.4A patent/CN109636276A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107403296A (en) * | 2017-06-29 | 2017-11-28 | 北京小度信息科技有限公司 | Conveyance equilibrium method and device |
CN108564269A (en) * | 2018-04-09 | 2018-09-21 | 北京小度信息科技有限公司 | Dispense method for allocating tasks, device, electronic equipment and computer storage media |
Non-Patent Citations (1)
Title |
---|
陈宁: "干货 | 机器学***衡***中的应用", 《腾讯云 HTTPS://CLOUD.TENCENT.COM/DEVELOPER/ARTICLE/1063420》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325503A (en) * | 2020-02-10 | 2020-06-23 | 拉扎斯网络科技(上海)有限公司 | Order processing method, device, server and nonvolatile storage medium |
CN111325503B (en) * | 2020-02-10 | 2023-09-26 | 拉扎斯网络科技(上海)有限公司 | Order processing method, device, server and nonvolatile 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 |
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 |
CN112036695A (en) * | 2020-07-28 | 2020-12-04 | 拉扎斯网络科技(上海)有限公司 | Weather information prediction method and device, readable storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Doubleday et al. | Benchmark probabilistic solar forecasts: Characteristics and recommendations | |
CN109636276A (en) | Assessment dispatching resource capability, Order splitting, dispatching resource regulating method and device | |
CN102855525B (en) | A kind of resident's load prediction analytic system and method | |
CN104504619B (en) | Two kinds consider that the monthly system of temperature and economic growth factor calls power predicating method | |
Millet et al. | Extensive analysis of photovoltaic battery self-consumption: Evaluation through an innovative district case-study | |
CN104881003A (en) | Effectiveness evaluation method for metering production facilities | |
CN112446534A (en) | Construction period prediction method and device for power transmission and transformation project | |
CN116632838B (en) | Method and device for analyzing electric energy supply of power generation enterprise | |
CN106384256A (en) | Power supplying service satisfaction dynamic testing system based on index system dynamic change | |
Weniger et al. | Emerging performance issues of photovoltaic battery systems | |
CN111950794A (en) | Park energy consumption prediction method, system, equipment and storage medium | |
CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
CN115859099A (en) | Sample generation method and device, electronic equipment and storage medium | |
US9141100B2 (en) | System and method for estimating performance metrics of conservation voltage reduction (CVR) systems and VOLT/VAR optimization systems | |
Bernards et al. | Statistical modelling of load profiles incorporating correlations using copula | |
CN102468997A (en) | Method for assessing stability of safety index system of multidimension network | |
Fışkın et al. | Forecasting domestic shipping demand of cement: comparison of SARIMAX, ANN and hybrid SARIMAX-ANN | |
CN116992216A (en) | Short-term load prediction method based on power user data | |
Bracale et al. | A Bayesian-based approach for the short-term forecasting of electrical loads in smart grids.: Part I: theoretical aspects | |
CN116186950A (en) | Processing method, system, device and storage medium for gas pipe network simulation | |
Maalej et al. | Sensor data augmentation strategy for load forecasting in smart grid context | |
CN106355515A (en) | Power load sorting method and system | |
Suryanarayana et al. | EV charging site day-ahead load prediction in a synthetic environment for RL based grid-informed charging | |
Bagchi | Power system adequacy and cost/worth assessment incorporating virtual power plants | |
Swide et al. | Energy Demand Prediction Based on Deep Learning Techniques |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |