CN110163453A - A kind of resources recharge allocation strategy prediction technique, device, system and storage medium - Google Patents
A kind of resources recharge allocation strategy prediction technique, device, system and storage medium Download PDFInfo
- Publication number
- CN110163453A CN110163453A CN201910538612.9A CN201910538612A CN110163453A CN 110163453 A CN110163453 A CN 110163453A CN 201910538612 A CN201910538612 A CN 201910538612A CN 110163453 A CN110163453 A CN 110163453A
- Authority
- CN
- China
- Prior art keywords
- supply
- type
- sportsman
- competition
- supplies
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of resources recharge allocation strategy prediction technique, device, system and storage mediums, this method comprises: weather data, racing track type, supply point information and at least one supplies type when obtaining all history competition data, this match of the sportsman of this competition;Weather data and racing track type when data, this match that all history are taken in competition are input in pre-established result prediction model as input parameter, predict sportsman's regularity of distribution of each supply point;Weather data, racing track type, the first supplies type, supply point information, sportsman's regularity of distribution and the games results of each sportsman are input in the first supply prediction model, predicts that the first supplies type is corresponding and feeds consumption per capita;According to sportsman's regularity of distribution of each supply point and each supplies type in the supply consumption per capita of each supply point, final resources recharge allocation strategy is predicted.
Description
Technical field
The present embodiments relate to field of computer technology, and in particular to a kind of resources recharge allocation strategy prediction technique,
Device, system and storage medium.
Background technique
With gradually increasing for people's health consciousness, the international sports events such as marathon increasingly obtain public welcome.Referring to
The people of race is more and more, and the service for race staff is then a huge challenge.It needs to be arranged on the way in match
Different race supply points, it is corresponding that each race supply point needs to be equipped with staff, relevant device, supplies and setting
Feed duration.
Due to different sections of highway, contestant's number of process is different, cannot be flat in different stages simply with average system
Identical equipment, personnel and increment are distributed, identical supply duration is set.Although in the prior art, also there is a kind of benefit
To the supply method for setting arrangement of point, the flow of the people of the point is exactly estimated according to artificial experience by situation, according to stream of people peak
Value determines personnel, number of devices, determines supply point operating time according to stream of people's duration.
But due to based entirely on artificial experience it is assumed that error is larger to have that resource allocation is unreasonable.It causes
But there is resource excess in the shortage of many supply point personnel, supplies etc., some places.
So, how just can guarantee and more accurate prediction is carried out for the resource of different supply points, make full use of all
Resources recharge avoids the wasting of resources from becoming the application technical problem urgently to be resolved.
Summary of the invention
It is situated between for this purpose, the embodiment of the present invention provides a kind of resources recharge allocation strategy prediction technique, device, system and storage
Matter, to solve not accurate enough for the prediction of resources recharge in the prior art, the technology for causing supply point resource allocation unreasonable
Problem.
To achieve the goals above, the embodiment of the present invention provides the following technical solutions:
According to a first aspect of the embodiments of the present invention, a kind of resources recharge allocation strategy prediction technique, this method are provided
Include:
Obtain this competition sportsman all history competition data, this match when weather data, racing track type,
Supply point information and at least one supplies type;
Weather data and racing track class when data, this match that all history of the sportsman of this competition are taken in competition
Type is input in pre-established result prediction model as input parameter, predicts the movement of each supply point of this competition
Member's regularity of distribution;
Weather data, racing track type, the first supplies type, supply point information when by this match and the sheet of prediction
Sportsman's regularity of distribution of secondary competition and the games results of each sportsman are input to corresponding with the first supplies type
In first supply prediction model of prebuild, predict in each supply point, it is corresponding with the first supplies type to feed per capita
Consumption, wherein the first supplies type is any type at least one supplies type;
According to sportsman's regularity of distribution of each supply point of prediction and each supplies type in each benefit
To the supply consumption per capita of point, final resources recharge allocation strategy is predicted.
Further, all history competition data of the sportsman of this competition are specific to wrap:
The corresponding historical weather data of every bout, history racing track type, history supply point letter when history is taken in competition
Breath, history supplies type, the consumption of each history supplies, the final Historical Results of sportsman, each timing point
Historical Results data and competition completion rate.
Further, by this competition sportsman all history take in competition data, this match when weather data, with
And racing track type is input in pre-established result prediction model as input parameter, predicts each supply of this competition
Sportsman's regularity of distribution of point, specifically includes:
Weather data and racing track class when data, this match that all history of the sportsman of this competition are taken in competition
Type utilizes stream of people's distribution situation of pre-established result prediction model prediction racing track as input parameter;
According to stream of people's distribution situation of racing track, sportsman's regularity of distribution of each supply point is statisticallyd analyze.
Further, the first supply prediction model is pre- including the first supply surplus prediction model, the first supply consumption
It surveys model and the first supply total flow prediction model, the supplies of each type is all corresponding with a kind of supply total flow
Prediction model, at least one surplus prediction model, and at least one supply consumption prediction model.
Further, when the first supply surplus prediction model includes that at least two, and first supply consumption predicts mould
Weather data, racing track type, the first supplies type, the first supply point letter when type includes at least two, when by this match
Sportsman's regularity of distribution of this of breath and prediction competition and the games results of each sportsman are input to and mend with first
To in the first supply prediction model of the corresponding prebuild of category type, predict in the first supply point, with the first supplies type pair
The supply consumption per capita answered, specifically includes:
Weather data, racing track type, the first supplies type, supply point information and prediction when respectively by this match
Sportsman's regularity of distribution of this competition and the games results of each sportsman to be input to each first supply remaining
It measures in prediction model, obtains the supply surplus of at least two predictions;
Seek the first average value of the supply surplus of at least two predictions;
Weather data, racing track type, the first supplies type, supply point information and prediction when respectively by this match
This competition sportsman's regularity of distribution and each sportsman games results be input to each supply consumption it is pre-
It surveys in model, obtains the supply consumption of at least two predictions;
Seek the second average value of the supply consumption of at least two predictions;
Weather data, racing track type, the first supplies type, supply point information when by this match and the sheet of prediction
Sportsman's regularity of distribution of secondary competition and the games results of each sportsman are input to the first supply total flow prediction mould
Type predicts the supply total flow of the first supply point;
According to the supply total flow of the first average value, the second average value and the first supply point, the first supply point is predicted
Practical supply consumption determine the corresponding supply consumption per capita of the first supplies type to feed consumption according to practical
Amount, wherein the first supply point is any of this match supply point.
Further, final resources recharge allocation strategy, includes at least:
Crew numbers, number of devices, the sendout per capita of each supplies of each supply point, each benefit
To the total score dosage and service duration of each supplies of point.
According to a second aspect of the embodiments of the present invention, a kind of resources recharge allocation strategy prediction meanss, the device are provided
Include:
Acquiring unit, obtain this competition sportsman all history competition data, this match when weather data,
Racing track type, supply point information and at least one supplies type;
Predicting unit, by this competition sportsman all history take in competition data, this match when weather data, with
And racing track type is input in pre-established result prediction model as input parameter, predicts each supply of this competition
Sportsman's regularity of distribution of point;
Weather data, racing track type, the first supplies type, supply point information when by this match and the sheet of prediction
Sportsman's regularity of distribution of secondary competition and the games results of each sportsman are input to corresponding with the first supplies type
In first supply prediction model of prebuild, predict in each supply point, it is corresponding with the first supplies type to feed per capita
Consumption, wherein the first supplies type is any type at least one supplies type;
Processing unit, for according to sportsman's regularity of distribution of each supply point of prediction and each supply category
Type predicts final resources recharge allocation strategy in the supply consumption per capita of each supply point.
Further, final resources recharge allocation strategy, includes at least:
Crew numbers, number of devices, the sendout per capita of each supplies of each supply point, each benefit
To the total score dosage and service duration of each supplies of point.
According to a third aspect of the embodiments of the present invention, a kind of resources recharge allocation strategy forecasting system, the system are provided
It include: processor and memory;
Memory is for storing one or more program instructions;
Processor, it is pre- to execute a kind of resources recharge allocation strategy as above for running one or more program instructions
Method step either in survey method.
According to a fourth aspect of the embodiments of the present invention, a kind of computer storage medium is provided, the computer storage medium
In comprising one or more program instructions, one or more program instructions are used for by a kind of resources recharge allocation strategy forecasting system
Either execute in a kind of as above resources recharge allocation strategy prediction technique method step.
The embodiment of the present invention has the advantages that all history competition data for obtaining the sportsman of this competition;Then
By history competition data and this match some parameters, such as weather data, racing track type, etc. all be used as input data, it is defeated
Enter the sportsman that each supply point of this competition is obtained to the result prediction model for advancing with historical parameter data building
Rule respectively.It further include supplies type, supply point information and prediction in addition, will handle except above-mentioned described parameter again
This competition sportsman's regularity of distribution and the games results of each sportsman be input to and each supplies type
First supply prediction model of corresponding prebuild, is predicted in each supply point, the supply per capita of all supplies disappears
Consumption.By this kind of mode, staff's number that prediction different time sections difference supply point that can be more accurate should be equipped with
The resources recharges point such as supplies type, supplies quantity and the staff's service duration of the number of devices, outfit that measure, are equipped with
With strategy.Resources recharge is rationally utilized as a result, avoids to meet as far as possible all competing athletes' while the wasting of resources
Demand.
Detailed description of the invention
It, below will be to embodiment party in order to illustrate more clearly of embodiments of the present invention or technical solution in the prior art
Formula or attached drawing needed to be used in the description of the prior art are briefly described.It should be evident that the accompanying drawings in the following description is only
It is merely exemplary, it for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer, which is extended, obtains other implementation attached drawings.
Structure depicted in this specification, ratio, size etc., only to cooperate the revealed content of specification, for
Those skilled in the art understands and reads, and is not intended to limit the invention enforceable qualifications, therefore does not have technical
Essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the function of the invention that can be generated
Under effect and the purpose that can reach, should all still it fall in the range of disclosed technology contents obtain and can cover.
Fig. 1 is a kind of resources recharge allocation strategy prediction technique flow diagram that the embodiment of the present invention 1 provides;
Fig. 2 is bout provided by the invention in stream of people's distribution situation that timing point is at 10 kilometers;
Fig. 3 is bout provided by the invention in stream of people's distribution situation that timing point is at 15 kilometers;
Fig. 4 is bout provided by the invention in stream of people's distribution situation that timing point is at 20 kilometers;
Fig. 5 is bout provided by the invention in the practical water that timing point is at 10 kilometers, 15 kilometers and 20 kilometers
The contrast schematic diagram of supply and prediction water supply;
Fig. 6 is a kind of resources recharge allocation strategy prediction meanss structural schematic diagram that the embodiment of the present invention 2 provides;
Fig. 7 is a kind of resources recharge allocation strategy forecasting system structural schematic diagram that the embodiment of the present invention 3 provides.
Specific embodiment
Embodiments of the present invention are illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book is understood other advantages and efficacy of the present invention easily, it is clear that described embodiment is the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
The embodiment of the present invention 1 provides a kind of resources recharge allocation strategy prediction technique, specifically as shown in Figure 1, this method
Steps are as follows:
Step 110, obtain this competition sportsman all history competition data, this match when weather data,
Racing track type, supply point information and at least one supplies type.
Specifically, history competition data can include but is not limited to following parameter: history every bout difference when taking in competition
Corresponding historical weather data, history racing track type, history supply point information, history supplies type, the supply of each history
The consumption of product, the final Historical Results of sportsman, the Historical Results data of each timing point and competition completion rate.Competition
Completion rate is mainly the ratio of the quantity of registering before register quantity and the athlete's of the sportsman after the completion of competing.History is mended
Mainly include how many a supply points to information, each supply point be where, such as have one every 5 kms
Supply point, then the position of supply point is exactly the roadside location apart from 5 km of runway starting point, 10 kms, 15 kms etc..Weather
Data may include the weather data of gas epidemic disaster, wind speed, fine day, cloudy day or rainy day etc..Racing track type may include as
Several situations:
It is divided according to height above sea level:
A) down type: racing track start, end altitude difference is more than 1 meter every kilometer, and starting point is higher than terminal.
B) ascending-type: racing track start, end altitude difference is more than 1 meter every kilometer, and starting point is lower than terminal.
C) high order smooth pattern: racing track start, end altitude difference is no more than 1 meter every kilometer, and the accumulation of all sections of climbing rises
The height of the accumulation decline of height or all descending brancies is no more than 80 meters every kilometer.
D) fluctuating type: racing track start, end altitude difference is no more than 1 meter every kilometer, and the accumulation of all sections of climbing rises
The height of the accumulation decline of height or all descending brancies is more than 80 meters every kilometer.
It is divided according to ground: and including types such as highway, mountainous region and plastic cement.
It is selected and is divided according to player: including choice of drawing lots at random, the modes such as registration of selecting or form a team according to Historical Results.
Step 120, by this competition sportsman all history take in competition data, this match when weather data, with
And racing track type is input in pre-established result prediction model as input parameter, predicts each supply of this competition
Sportsman's regularity of distribution of point.
Specifically, fixture, match number when history competition data can also include every bout, history competition
Player's identity information (such as the information such as number, name, identification card number), when taking part in game player's age etc. in relation to the number competed
According to.
Such as step 110, racing track type may include a variety of, then, pre-established result prediction model prediction sportsman
Stream of people's distribution situation principle on racing track are as follows:
Take in competition data firstly the need of according to history, count all history contestants on each type racing track it is average at
Achievement.Then, first kind transformation ratio is calculated according to history contestant average achievement between different type racing track.According to history ratio
It matches the age of each history contestant in data, and Historical Results when competition, calculates the second class transformation ratio.
Since in history match, match timing point set-up mode is different, even if being joined when the same person's same age
The position of two matches added, the record point of games results will not be completely the same.Therefore, it is necessary to the competition of first kind history
In the history match that player participates on the basis of the timing point set-up mode of the first match, except the first kind competes it in history match
Adjust timing point according to predetermined manner in outer other classes match, predetermined manner includes one of following or a variety of: it is newly-increased or
Person deletes;And when increasing timing point newly in other classes match in history is competed in addition to first kind match, calculated according to interpolation
Method is filled the achievement of newly-increased timing point.
That is to say, for example, the first kind racing track participated in of history contestant on first kind racing track match when it is every
It is primary every 5 kilometers of timing, and when the match of Second Type racing track, it is primary every 10 kilometers of timing, if that with the first kind
The match of type racing track is taken in competition on the basis of timing point set-up mode, just to lack the first history in the match of Second Type racing track
Player reaches timing at 5 kilometers, needs newly-increased timing point.Alternatively, if with the timing point in the match of Second Type racing track
On the basis of set-up mode, then more data of 5 kilometers of timing in the match of first kind racing track, then need to carry out timing point
It deletes.
If it is newly-increased timing point, then can be filled according to achievement of the interpolation algorithm to newly-increased timing point.Certainly, then
It executes in the above process, each in the match to the other types racing track in addition to the match of first kind racing track is needed to take in competition
Player is adjusted correspondingly according to the achievement of oneself respectively.For example, newly-increased timing point.
And when calculating Second Type transformation ratio, it can specifically include: according to the age by each history contestant
It is divided to an age group, and according to the updated history games results of each history contestant, determines each age
The average achievement of all history contestants in group;
According to the average achievement of all history contestants between different two age groups, the second class transformation ratio is calculated.
Optionally, no matter before calculating first kind transformation ratio or Second Type transformation ratio, it is also necessary to execute
Certain pretreatment.For example, removing first in history match on the basis of the match timing point set-up mode of first kind racing track
In other types lane race other than type racing track, timing point is adjusted according to predetermined manner, predetermined manner includes in following
It is one or more: to increase newly or delete;
And it is counted when being increased newly in the match of the other types racing track in history is competed in addition to the match of first kind racing track
It when time point, is filled according to achievement of the interpolation algorithm to newly-increased timing point, so as to subsequent according to updated achievement, determines every
The average achievement of all history contestants on one type racing track;
And/or the timing point set-up mode that the first kind is competed in the history match participated in first kind history contestant
On the basis of, timing point is adjusted according to predetermined manner in other classes match in history match in addition to first kind match, is preset
Mode includes one of following or a variety of: increasing newly or deletes;
And when increasing timing point newly in other classes match in history is competed in addition to first kind match, according to interpolation
Algorithm is filled the achievement of newly-increased timing point.
It that is to say, it is described in step 110, when obtaining sportsman and participating in all matches, on the basis of bout, obtain
The Historical Results data of each timing point in other matches.
From history competition data, the year for participating in history contestant identical with this match racing track type is extracted
The Historical Results of age and each history contestant, and be grouped according to the age, obtain h age group.
In i-th of age group, according to the Historical Results of each history contestant, it is divided into n rank, calculates the
History contestant number accounts in i-th of age group in the probability value of history contestant number and j-th of rank in j rank
The average achievement of history contestant.
For example, all history contestants of each age group grade can be carried out according to Historical Results to draw
Point, such as race fast, general and the slow three grades run.
Historical Results are in the first range, and for the fast of race, Historical Results are in the second range, for the general of race
, Historical Results are third range, for the slow of race.Then the fast number for counting race accounts for the ratio of age group total number of persons,
As the fast probability that age group people runs, same reason calculates the general probability of race and the slow probability of race.Also want
Average achievement in the fast people of race, the average achievement in the general people of race are calculated, and average achievement in the slow people run.
The player for never participating in match is extracted in this time player of match from participating in, and is grouped according to the age,
Obtain h age group.
According to probability value and each rank corresponding to each rank in i-th of age group for participating in history match
Corresponding average achievement, by participate in this time match i-th of age group in player be randomly assigned, obtain each from
That did not participated in the player of match estimates achievement.
From the player for extracting in this time player of match and participating in history and competing is participated in, match was participated according to each
Player Historical Results, first kind transformation ratio and/or the second class transformation ratio determine and participate in estimating into for this time match
Achievement.
In other words, for not participating in the people of match, their achievement can be with there is no any historical data
As judging basis.It is possible to reference to these do not participated in match people's same age section, and with this match racing track
The achievement of the identical history contestant of type is estimated.
In estimating again, purpose and not lie in achievement that these people can run out of mostly accurate on earth, but to predict how much
People can run faster, and how many people run general, and how many people can run slow.So, so that it may join according to the history of same age bracket
The fast probability run when match player's competition, multiplied by the same age bracket total number of persons for participating in this match, as the year in this match
The total number of persons that age section may run a good foot extracts the fast of possible race from the people for not participating in match in age bracket remittance at random
Total number of persons player, and set the average achievement that runs a good foot for them.It is similar on earth, calculate may race it is general total
Number, it is then random to be assigned on corresponding people, and the general average achievement of race is set for them, after randomly selecting, remain
Under people be exactly the slow people run, the slow average achievement of race is set for them.
Certainly, the achievement set here is not to participate in the true achievement of this time player of match, but estimate achievement, in advance
Estimate achievement to be merely possible to when subsequent stream of people's distribution to racing track is predicted as reference frame.Whom therefore, set as
Surely fast, whose setting race slow can't be affected for player run.
Finally, achievement is estimated according to each player for participating in this match, simulates all players in this match
Travelling route on racing track predicts racing track stream of people distribution situation.Wherein, h, i and n are the positive integer more than or equal to 1, and
I is the positive integer less than or equal to h.
By this kind of mode, racing track stream of people's distribution situation can be not only predicted, can also be distributed feelings according to the racing track stream of people
Condition, analysis count sportsman's regularity of distribution of each supply point of this competition.
For example, which some supply point carved from will welcome first sportsman, which welcomes last movement at the moment
Member.It is which etc. that sportsman's number most period is welcome during this period.
Weather data, racing track type, the first supplies type, supply point information when step 130, by this match and
The sportsman's regularity of distribution of this competition and the games results of each sportsman of prediction are input to and the first supply category
In first supply prediction model of the corresponding prebuild of type, predict in each supply point, it is corresponding with the first supplies type
Consumption is fed per capita.
Optionally, the first supply prediction model includes the first supply surplus prediction model, the first supply consumption prediction
Model and the first supply total flow prediction model, it is pre- that the supplies of each type are all corresponding with a kind of supply total flow
Survey model, at least one surplus prediction model, and at least one supply consumption prediction model.
Be also says, supply prediction model may include it is a variety of, one is prediction feed surplus prediction model, one is
The prediction model of prediction supply consumption, another kind are supply total flow prediction models.It can use these three prediction models
It is predicted respectively for the resources recharge of each supply point, for more clearly supply of the explanation for the first supply point
Resource is predicted, so being positioned as the first supply surplus prediction model, the first supply consumption respectively in application documents
Prediction model and the first supply total flow prediction model.But it is to say just for the first supply point that first here, which is not,
But these prediction models can be used for each supply point respectively.
It goes due to predicting that inherently there is a certain error, in order to enable final prediction can be more accurate, Ke Yishe
Fixed first supply surplus prediction model and the first supply consumption prediction model are respectively at least two.For example, the first supply
Surplus prediction model is set as 3, and the first supply consumption prediction model is set as 5.
By constructing multiple prediction models, using each prediction model respectively to the input parameter referring to this match into
Row prediction, weather data, racing track type, the first supplies type, the first supply point information when including this match and pre-
Sportsman's regularity of distribution and the games results of each sportsman of this competition surveyed etc. are input to phase as input parameter
In the prediction model answered, prediction result is obtained.
That is, respectively by this match when weather data, racing track type, the first supplies type, supply point information and
The sportsman's regularity of distribution of this competition and the games results of each sportsman of prediction are input to each first supply
In surplus prediction model, the supply surplus of at least two predictions is obtained;
Seek the first average value of the supply surplus of at least two predictions;
Weather data, racing track type, the first supplies type, supply point information and prediction when respectively by this match
This competition sportsman's regularity of distribution and each sportsman games results be input to each supply consumption it is pre-
It surveys in model, obtains the supply consumption of at least two predictions;
Seek the second average value of the supply consumption of at least two predictions;
Weather data, racing track type, the first supplies type, supply point information when by this match and the sheet of prediction
Sportsman's regularity of distribution of secondary competition and the games results of each sportsman are input to the first supply total flow prediction mould
Type predicts the supply total flow of the first supply point;
According to the supply total flow of the first average value, the second average value and the first supply point, the first supply point is predicted
Practical supply consumption.
And according to the supply total flow of the first average value, the second average value and the first supply point, the first supply of prediction
The practical supply consumption of point determines that the corresponding supply per capita of the first supplies type disappears to feed consumption according to practical
Consumption can be embodied using following formula:
H=x- (z-x-y)/2 (formula 1)
Wherein, H is practical supply consumption, and x is the second average value, and y is the first average value, and z is the benefit of the first supply point
To total flow.
It should be noted that training first supply surplus prediction model, first supply consumption prediction model and
When the first supply total flow prediction model, the parameter of input is slightly different.
For example, to be directed to the supplies of each type respectively, respectively in training the first supply surplus prediction model
Training the first supply surplus prediction model, mainly according to weather data as introduced above, the runway in history competition data
The history surplus of the type supplies of categorical data, the historical relevance achievement data of sportsman and each supply point
As input data, tune ginseng is carried out to the first supply surplus prediction model, obtains corresponding with the supplies of the type first
Feed surplus prediction model.
In training the first supply consumption prediction model, the same supplies for being directed to each type are respectively trained the
One supply consumption prediction model.The parameter of input is unlike training the first supply surplus prediction model, the ginseng of input
It does not include the history surplus of the type supplies of each supply point in number, but the type including each supply point
The history consumption of supplies.
In training the first supply total flow prediction model, primarily directed to the consumption of all types supplies, institute
One is only included with the first supply total flow prediction model.In training, the parameter and training the first supply surplus of input
It does not include the history surplus of the type supplies of each supply point in the parameter of input unlike prediction model, and
Be include each supply point all types supplies history total flow.
Specific training method is the prior art, does not do excessive explanation here.Training pattern can use neural network
The regressive prediction models such as training pattern or decision-tree model.
After getting practical supply consumption, consumption is fed according to practical, determines that the first supplies type is corresponding
Consumption is fed per capita, wherein the first supply point is that any of this match supply point, the first supplies type are at least one
Any type in kind supplies type.
Step 140, existed according to sportsman's regularity of distribution of each supply point of prediction and each supplies type
The supply consumption per capita of each supply point predicts final resources recharge allocation strategy.
Specifically, when the sportsman's regularity of distribution and each supplies type that each supply point has been determined are each
After the consumption of supply per capita of a supply point, so that it may determine the crew numbers for needing to be equipped with, number of devices, each benefit
When to the sendout per capita of each supplies of point, the total score dosage of each supplies of each supply point and service
It is long etc..It that is to say and predict final resources recharge allocation strategy.
In a specific example, Fig. 2 to Fig. 4 shows stream of people's distribution situation of different timing points respectively.Also, it can
To find out in figure, stream of people's peak value is 200 people at 10 kilometers, therefore staff's configuration of the supply point should meet every point
Clock services 200 people, and service time is 78 minutes started between latter 30th minute to 108 minutes of competing.
Similarly, should meet 160 people of service per minute at 15 kilometers, service time be compete start after arriving within the 44th minute
112 minutes between 156 minutes;
125 people of service per minute should be met at 20 kilometers, service time is the 58th minute to 198 minutes after match starts
Between 140 minutes.
This of Fig. 5 competes, and actually dispensing feeds goods and materials quantity per capita for 10,15,20 kilometers of positions, per capita practical supply consumption
The consumption forecast result of supply per capita that amount and system provide.
A kind of resources recharge allocation strategy prediction technique provided in an embodiment of the present invention obtains the sportsman's of this competition
All history competition data;Then by some parameters of history competition data and this match, such as weather data, racing track class
Type, etc. all be used as input data, be input to advance with historical parameter data building result prediction model, obtain this competition
Each supply point sportsman respectively rule.It further include supply category in addition, will handle except above-mentioned described parameter again
Sportsman's regularity of distribution of this competition of type, supply point information and prediction and the games results input of each sportsman
First to prebuild corresponding with each supplies type feeds prediction model, predicts in each supply point, institute
There is the supply consumption per capita of supplies.By this kind of mode, prediction different time sections difference supply point that can be more accurate
The number of devices of the crew numbers, outfit that should be equipped with, the supplies type of outfit, supplies quantity and staff
The resources recharges allocation strategy such as service duration.Resources recharge is rationally utilized as a result, it can also be as far as possible while avoiding the wasting of resources
Meets the needs of all competing athletes.
Corresponding with above-described embodiment 1, the embodiment of the present invention 2 additionally provides a kind of resources recharge allocation strategy prediction dress
It sets, specifically as shown in fig. 6, the device includes: acquiring unit 601, predicting unit 602 and processing unit 603.
Acquiring unit 601 obtains day destiny when all history competition data, this match of the sportsman of this competition
According to, racing track type, supply point information and at least one supplies type;
Predicting unit 602, by this competition sportsman all history take in competition data, this match when day destiny
According to and racing track type as input parameter, be input in pre-established result prediction model, predict this competition each
Sportsman's regularity of distribution of supply point;
Weather data, racing track type, the first supplies type, supply point information when by this match and the sheet of prediction
Sportsman's regularity of distribution of secondary competition and the games results of each sportsman are input to corresponding with the first supplies type
In first supply prediction model of prebuild, predict in each supply point, it is corresponding with the first supplies type to feed per capita
Consumption, wherein the first supplies type is any type at least one supplies type;
Processing unit 603, for according to sportsman's regularity of distribution of each supply point of prediction and each supply
Category type predicts final resources recharge allocation strategy in the supply consumption per capita of each supply point.
Optionally, all history competition data of the sportsman of this competition are specific to wrap:
The corresponding historical weather data of every bout, history racing track type, history supply point letter when history is taken in competition
Breath, history supplies type, the consumption of each history supplies, the final Historical Results of sportsman, each timing point
Historical Results data and competition completion rate.
Optionally, predicting unit 602 is specifically used for, by this competition sportsman all history competition data, this
Weather data and racing track type when match utilize pre-established result prediction model prediction racing track as input parameter
Stream of people's distribution situation;
According to stream of people's distribution situation of racing track, sportsman's regularity of distribution of each supply point is statisticallyd analyze.
Optionally, the first supply prediction model includes the first supply surplus prediction model, the first supply consumption prediction
Model and the first supply total flow prediction model, it is pre- that the supplies of each type are all corresponding with a kind of supply total flow
Survey model, at least one surplus prediction model, and at least one supply consumption prediction model.
Optionally, when the first supply surplus prediction model includes at least two, and first supply consumption prediction model
When including at least two, predicting unit 602 is specifically used for, respectively by this match when weather data, racing track type, first mend
To category type, supply point information and prediction this take in competition sportsman's regularity of distribution and each sportsman match at
Achievement is input in each first supply surplus prediction model, obtains the supply surplus of at least two predictions;
Seek the first average value of the supply surplus of at least two predictions;
Weather data, racing track type, the first supplies type, supply point information and prediction when respectively by this match
This competition sportsman's regularity of distribution and each sportsman games results be input to each supply consumption it is pre-
It surveys in model, obtains the supply consumption of at least two predictions;
Seek the second average value of the supply consumption of at least two predictions;
Weather data, racing track type, the first supplies type, supply point information when by this match and the sheet of prediction
Sportsman's regularity of distribution of secondary competition and the games results of each sportsman are input to the first supply total flow prediction mould
Type predicts the supply total flow of the first supply point;
According to the supply total flow of the first average value, the second average value and the first supply point, the first supply point is predicted
Practical supply consumption determine the corresponding supply consumption per capita of the first supplies type to feed consumption according to practical
Amount, wherein the first supply point is any of this match supply point.
Optionally, final resources recharge allocation strategy, includes at least:
Crew numbers, number of devices, the sendout per capita of each supplies of each supply point, each benefit
To the total score dosage and service duration of each supplies of point.
Function performed by each component is equal in a kind of resources recharge allocation strategy prediction meanss provided in an embodiment of the present invention
It is discussed in detail in above-described embodiment 1, therefore does not do excessively repeat here.
A kind of resources recharge allocation strategy prediction meanss provided in an embodiment of the present invention obtain the sportsman's of this competition
All history competition data;Then by some parameters of history competition data and this match, such as weather data, racing track class
Type, etc. all be used as input data, be input to advance with historical parameter data building result prediction model, obtain this competition
Each supply point sportsman respectively rule.It further include supply category in addition, will handle except above-mentioned described parameter again
Sportsman's regularity of distribution of this competition of type, supply point information and prediction and the games results input of each sportsman
First to prebuild corresponding with each supplies type feeds prediction model, predicts in each supply point, institute
There is the supply consumption per capita of supplies.By this kind of mode, prediction different time sections difference supply point that can be more accurate
The number of devices of the crew numbers, outfit that should be equipped with, the supplies type of outfit, supplies quantity and staff
The resources recharges allocation strategy such as service duration.Resources recharge is rationally utilized as a result, it can also be as far as possible while avoiding the wasting of resources
Meets the needs of all competing athletes.
Corresponding with above-described embodiment, the embodiment of the present invention 3 additionally provides a kind of resources recharge allocation strategy prediction system
System, specifically as shown in fig. 7, the system includes: processor 701 and memory 702;
Memory 702 is for storing one or more program instructions;
Processor 701, for running one or more program instructions, a kind of benefit for being introduced to execute embodiment as above
To method step either in resource allocation policy prediction technique.
A kind of resources recharge allocation strategy forecasting system provided in an embodiment of the present invention obtains the sportsman's of this competition
All history competition data;Then by some parameters of history competition data and this match, such as weather data, racing track class
Type, etc. all be used as input data, be input to advance with historical parameter data building result prediction model, obtain this competition
Each supply point sportsman respectively rule.It further include supply category in addition, will handle except above-mentioned described parameter again
Sportsman's regularity of distribution of this competition of type, supply point information and prediction and the games results input of each sportsman
First to prebuild corresponding with each supplies type feeds prediction model, predicts in each supply point, institute
There is the supply consumption per capita of supplies.By this kind of mode, prediction different time sections difference supply point that can be more accurate
The number of devices of the crew numbers, outfit that should be equipped with, the supplies type of outfit, supplies quantity and staff
The resources recharges allocation strategy such as service duration.Resources recharge is rationally utilized as a result, it can also be as far as possible while avoiding the wasting of resources
Meets the needs of all competing athletes.
Corresponding with above-described embodiment, the embodiment of the invention also provides a kind of computer storage medium, the computers
Include one or more program instructions in storage medium.Wherein, one or more program instructions are used for by a kind of resources recharge point
A kind of resources recharge allocation strategy prediction technique as described above is executed with tactful forecasting system.
Although above having used general explanation and specific embodiment, the present invention is described in detail, at this
On the basis of invention, it can be made some modifications or improvements, this will be apparent to those skilled in the art.Therefore,
These modifications or improvements without departing from theon the basis of the spirit of the present invention are fallen within the scope of the claimed invention.
Claims (10)
1. a kind of resources recharge allocation strategy prediction technique, which is characterized in that the described method includes:
Obtain this competition sportsman all history competition data, this match when weather data, racing track type, supply
Point information and at least one supplies type;
Weather data and racing track type when data, this match that all history of the sportsman of this competition are taken in competition are made
To input parameter, it is input in pre-established result prediction model, predicts the sportsman point of each supply point of this competition
Cloth rule;
This of weather data, racing track type, the first supplies type, supply point information when by this match and prediction ginseng
Sportsman's regularity of distribution of match and the games results of each sportsman are input to corresponding with the first supplies type
In first supply prediction model of prebuild, predict in each supply point, it is corresponding per capita with the first supplies type
Feed consumption, wherein the first supplies type is any type at least one supplies type;
According to sportsman's regularity of distribution of each supply point of the prediction and each supplies type in each benefit
To the supply consumption per capita of point, final resources recharge allocation strategy is predicted.
2. the number the method according to claim 1, wherein all history of the sportsman of this competition are taken in competition
According to specific to wrap:
Every bout corresponding historical weather data when history is taken in competition, history supply point information, is gone through history racing track type
The history of history supplies type, the consumption of each history supplies, the final Historical Results of sportsman, each timing point
Achievement data and competition completion rate.
3. according to the method described in claim 2, it is characterized in that, all history of the sportsman by this competition are taken in competition
Weather data and racing track type when data, this match are input to pre-established result prediction model as input parameter
In, it predicts sportsman's regularity of distribution of each supply point of this competition, specifically includes:
Weather data and racing track type when data, this match that all history of the sportsman of this competition are taken in competition are made
To input parameter, stream of people's distribution situation of pre-established result prediction model prediction racing track is utilized;
According to stream of people's distribution situation of the racing track, sportsman's regularity of distribution of each supply point is statisticallyd analyze.
4. according to the method described in claim 2, it is characterized in that, the first supply prediction model includes that the first supply surplus is pre-
Survey model, the first supply consumption prediction model and the first supply total flow prediction model, the supplies of each type
All it is corresponding with a kind of supply total flow prediction model, at least one surplus prediction model, and at least one supply consumption
Measure prediction model.
5. according to the method described in claim 4, it is characterized in that, when the first supply surplus prediction model includes at least
Two, and it is described first supply consumption prediction model include at least two when, weather data, racing track class when by this match
Type, the first supplies type, the first supply point information and prediction this competition sportsman's regularity of distribution and each
The games results of sportsman are input in the first supply prediction model of prebuild corresponding with the first supplies type, in advance
It surveys in the first supply point, it is corresponding with the first supplies type to feed consumption per capita, it specifically includes:
Weather data, racing track type, the first supplies type, supply point information when respectively by this match and the sheet of prediction
It is pre- that sportsman's regularity of distribution of secondary competition and the games results of each sportsman are input to each first supply surplus
It surveys in model, obtains the supply surplus of at least two predictions;
Seek the first average value of the supply surplus of at least two predictions;
Weather data, racing track type, the first supplies type, supply point information when respectively by this match and the sheet of prediction
Sportsman's regularity of distribution of secondary competition and the games results of each sportsman are input to each supply consumption prediction mould
In type, the supply consumption of at least two predictions is obtained;
Seek the second average value of the supply consumption of at least two predictions;
This of weather data, racing track type, the first supplies type, supply point information when by this match and prediction ginseng
Sportsman's regularity of distribution of match and the games results of each sportsman are input to the first supply total flow prediction mould
Type predicts the supply total flow of first supply point;
According to the supply total flow of first average value, second average value and first supply point, institute is predicted
The practical supply consumption of the first supply point is stated, to determine the first supply category according to the practical supply consumption
Type is corresponding to feed consumption per capita, wherein first supply point is any of this match supply point.
6. method according to claim 1-5, which is characterized in that the final resources recharge allocation strategy,
It includes at least:
Crew numbers, number of devices, the sendout per capita of each supplies of each supply point, each supply point
Each supplies total score dosage and service duration.
7. a kind of resources recharge allocation strategy prediction meanss, which is characterized in that described device includes:
Acquiring unit, obtain this competition sportsman all history competition data, this match when weather data, racing track
Type, supply point information and at least one supplies type;
Predicting unit, by this competition sportsman all history take in competition data, this match when weather data, Yi Jisai
Road type is input in pre-established result prediction model as input parameter, predicts each supply point of this competition
Sportsman's regularity of distribution;
This of weather data, racing track type, the first supplies type, supply point information when by this match and prediction ginseng
Sportsman's regularity of distribution of match and the games results of each sportsman are input to corresponding with the first supplies type
In first supply prediction model of prebuild, predict in each supply point, it is corresponding per capita with the first supplies type
Feed consumption, wherein the first supplies type is any type at least one supplies type;
Processing unit, for according to sportsman's regularity of distribution of each supply point of the prediction and each supply category
Type predicts final resources recharge allocation strategy in the supply consumption per capita of each supply point.
8. device according to claim 7, which is characterized in that the final resources recharge allocation strategy includes at least:
Crew numbers, number of devices, the sendout per capita of each supplies of each supply point, each supply point
Each supplies total score dosage and service duration.
9. a kind of resources recharge allocation strategy forecasting system, which is characterized in that the system comprises: processor and memory;
The memory is for storing one or more program instructions;
The processor, for running one or more program instructions, to execute side as claimed in any one of claims 1 to 6
Method.
10. a kind of computer storage medium, which is characterized in that refer in the computer storage medium comprising one or more programs
It enables, one or more of program instructions are used to execute such as claim 1-6 by a kind of resources recharge allocation strategy forecasting system
Described in any item methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910538612.9A CN110163453B (en) | 2019-06-20 | 2019-06-20 | Method, device and system for predicting replenishment resource allocation strategy and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910538612.9A CN110163453B (en) | 2019-06-20 | 2019-06-20 | Method, device and system for predicting replenishment resource allocation strategy and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110163453A true CN110163453A (en) | 2019-08-23 |
CN110163453B CN110163453B (en) | 2021-08-13 |
Family
ID=67626417
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910538612.9A Active CN110163453B (en) | 2019-06-20 | 2019-06-20 | Method, device and system for predicting replenishment resource allocation strategy and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110163453B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113673800A (en) * | 2020-05-15 | 2021-11-19 | 阿里巴巴集团控股有限公司 | Data processing method and device and terminal equipment |
CN113743337A (en) * | 2021-09-09 | 2021-12-03 | 江阴市浩华新型复合材料有限公司 | Image signal capturing platform using depth of field analysis |
CN113947753A (en) * | 2021-10-15 | 2022-01-18 | 泰州市华达机电设备有限公司 | Cloud-operated field article putting platform |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110191263A1 (en) * | 2007-10-12 | 2011-08-04 | Advisor Software, Inc. | Stochastic Control System and Method for Multi-Period Consumption |
CN108256685A (en) * | 2018-01-22 | 2018-07-06 | 浙江工业大学 | A kind of Hospital Logistic shipping time Forecasting Methodology based on multiple linear regression model |
-
2019
- 2019-06-20 CN CN201910538612.9A patent/CN110163453B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110191263A1 (en) * | 2007-10-12 | 2011-08-04 | Advisor Software, Inc. | Stochastic Control System and Method for Multi-Period Consumption |
CN108256685A (en) * | 2018-01-22 | 2018-07-06 | 浙江工业大学 | A kind of Hospital Logistic shipping time Forecasting Methodology based on multiple linear regression model |
Non-Patent Citations (3)
Title |
---|
姚红霞: "美国陆军旅战斗队的后勤预测和估算", 《现代军事》 * |
秦大建等: "基于神经网络的时间序列组合预测模型研究及应用", 《计算机应用》 * |
黄必佳 等: "航母编队油料伴随补给规划模型及算法研究", 《兵工自动化》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113673800A (en) * | 2020-05-15 | 2021-11-19 | 阿里巴巴集团控股有限公司 | Data processing method and device and terminal equipment |
CN113743337A (en) * | 2021-09-09 | 2021-12-03 | 江阴市浩华新型复合材料有限公司 | Image signal capturing platform using depth of field analysis |
CN113947753A (en) * | 2021-10-15 | 2022-01-18 | 泰州市华达机电设备有限公司 | Cloud-operated field article putting platform |
Also Published As
Publication number | Publication date |
---|---|
CN110163453B (en) | 2021-08-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110163453A (en) | A kind of resources recharge allocation strategy prediction technique, device, system and storage medium | |
JP7494254B2 (en) | A system for providing individual performance goals for multiple sports activities | |
Shaw et al. | Travel cost models of the demand for rock climbing | |
Constantinou et al. | pi-football: A Bayesian network model for forecasting Association Football match outcomes | |
US11093513B2 (en) | System and method for personal and peer performance ranking of outdoor activities | |
RU2607953C2 (en) | Capturing of optical data on exercises in addition to calculation of assessment of health | |
CN103647671B (en) | A kind of intelligent perception network management and its system based on Gur Game | |
Morey et al. | Estimating the benefits and costs to mountain bikers of changes in trail characteristics, access fees, and site closures: choice experiments and benefits transfer | |
CN107392512A (en) | Grouped task method and apparatus | |
Fister et al. | Data mining in sporting activities created by sports trackers | |
CN109034566A (en) | A kind of intelligent dispatching method and device based on passenger flow above and below bus station | |
CN108151756A (en) | The travel time computation method and device of a kind of urban public tranlport system | |
CN101964085A (en) | Method for distributing passenger flows based on Logit model and Bayesian decision | |
CN106504535B (en) | A kind of trip distribution modeling method of combination Gravity Models and Fratar models | |
Drakoulis et al. | A gamified flexible transportation service for on-demand public transport | |
CN107392389A (en) | Taxi dispatching processing method based on ARIMA models | |
CN112950251A (en) | Reputation-based vehicle crowd sensing node reverse combination auction excitation optimization method | |
Khoshkangini et al. | Generating personalized challenges to enhance the persuasive power of gamification | |
CN107392446B (en) | A kind of step power station scheduling scheme evaluation method based on sensitivity analysis | |
CN106935044A (en) | A kind of site location optimization method for preferentially coordinating control based on bus signals | |
CN109697637A (en) | Object type determines method, apparatus, electronic equipment and computer storage medium | |
Pullman et al. | Strategies for integrating capacity with demand in service networks | |
CN109993371A (en) | Predict method, apparatus, system and the storage medium of racing track stream of people distribution situation | |
CN104933593A (en) | Integration excitation system based on Elo hierarchy model and integration excitation method based on Elo hierarchy model | |
CN104318053B (en) | Telephone traffic prediction method for calculating weighted moving average weight on the basis of univariate regression |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |