CN108205515A - A kind of mobile platform crowdsourcing task pricing method and system - Google Patents
A kind of mobile platform crowdsourcing task pricing method and system Download PDFInfo
- Publication number
- CN108205515A CN108205515A CN201711405763.4A CN201711405763A CN108205515A CN 108205515 A CN108205515 A CN 108205515A CN 201711405763 A CN201711405763 A CN 201711405763A CN 108205515 A CN108205515 A CN 108205515A
- Authority
- CN
- China
- Prior art keywords
- task
- price
- crowdsourcing
- mission
- mission requirements
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Business, Economics & Management (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Development Economics (AREA)
- Algebra (AREA)
- Accounting & Taxation (AREA)
- Operations Research (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of mobile platform crowdsourcing task pricing method and system, includes the following steps:Data acquire:The crowdsourcing mission bit stream of labor service crowdsourcing platform is acquired, crowdsourcing mission bit stream is visualized and pre-processed;The crowdsourcing mission bit stream includes:Crowdsourcing mission number, crowdsourcing task price, the executive condition of the longitude and latitude of crowdsourcing task and crowdsourcing task;Analysis task price influence factor:The influence factor of screening task price;Establish task pricing model:By determining feature, multivariate nonlinear regression analysis model is established;Price task is treated using multivariate nonlinear regression analysis model to fix a price.The present invention carries out data acquisition, data analysis, data processing and feature extraction to the data of crowdsourcing task performance;Analysis task is fixed a price possible influence factor, establishes multivariate nonlinear regression analysis model, the influence degree that comprehensive analysis direct factor and objective factor fix a price to task, determines the task pricing method of the self-service labor service crowdsourcing platform of mobile Internet.
Description
Technical field
The invention belongs to the technical field of data analysis more particularly to a kind of mobile platform crowdsourcing task pricing method and it is
System.
Background technology
Today's society, mobile Internet already become the highly important terminal of acquisition of information, will be numerous and jumbled with crowdsourcing model
Investigation business perform chain and be transformed on mobile platform and implement, numerous APP mission requirements persons is made directly to connect on a mobile platform
It to task, execution and feeds back, only enterprise does not provide various business inspections and information search service, and is effectively guaranteed tune
Data validity is looked into, shortens the period of investigation, reduces the cost of implementation of investigation business.Problem of the existing technology is:Largely
Mission requirements person task publication peak period task is connect into robbing, easily bring pressure to mobile platform server, if
There is no rational means to take over business behavior to robbing and guide, then large-scale rob takes over business behavior mobile platform will be taken
The be engaged in operation of device generates unusual detrimental effect, if moreover, price is unreasonable will not be able to A clear guidance mission requirements person and rob
Business is taken over, partial task is caused to overstock nobody for a long time and rob and is connect, wastes the memory space of mobile platform server, but also ensure not
The timely updating of mobile platform server data;Due to robbing the private meaning taken over business behavior and be subordinated to mission requirements person completely
It is willing to, conventional scheduling means are not suitable for crowdsourcing task.
At present, the pricing method of variety classes task mainly takes fat pricing strategy and penetration pricing.Fat is taken to fix a price
Strategy is that, using the psychology of seeking new of consumer, initial stage formulation higher price occur in commodity;Penetration pricing is, by task
Prices it is very low, the phase is made to seek long term growth with quality-high and inexpensive image.These traditional task pricing methods are according to the heart
Theoretical a kind of qualitatively pricing method of science, is not the feasible solution for crowdsourcing task, and they often only relate to
And enterprise or the one-sided interests of demander, do not account for how mobile platform server stress is alleviated, do not account for more how
Allow the equal income of business and consumer both sides.
Invention content
To solve the above-mentioned problems, the present invention provides a kind of mobile platform crowdsourcing task pricing method and system, the present invention
Data acquisition, data analysis, data processing and feature extraction are carried out to the data of crowdsourcing task performance;Analysis task is overstock
The influence factor of pressure is generated to server, establishes multivariate nonlinear regression analysis model, comprehensive analysis direct factor and objective factor
To task price influence degree, solves the problems, such as fix a price it is unreasonable caused by server stress.
To achieve these goals, the present invention adopts the following technical scheme that:
A kind of mobile platform crowdsourcing task pricing method, includes the following steps:
Step (1):Data acquire:The crowdsourcing mission bit stream of labor service crowdsourcing platform is acquired, it can to the progress of crowdsourcing mission bit stream
Depending on changing and pre-processing;The crowdsourcing mission bit stream includes:Crowdsourcing mission number, crowdsourcing task are fixed a price, the longitude and latitude of crowdsourcing task
With the executive condition of crowdsourcing task;
Step (2):Analysis task price influence factor:Analytical procedure (1) as a result, screening task price influence because
Element;
Step (3):Establish task pricing model:The feature determined by step (2), establishes Multiple Non Linear Regression mould
Type;
Step (4):Price task is treated using the multivariate nonlinear regression analysis model of step (3) to fix a price.
The method further includes:
Step (5):Test and appraisal task pricing model:The multivariate nonlinear regression analysis model that evaluation steps (3) are formulated.
The step of step (1) is:
Step (1-1):According to the crowdsourcing mission bit stream of acquisition, extraction task price draws histogram according to different prices,
Visualization processing is carried out, obtains task price distribution map;
Step (1-2):Coarse localization is carried out according to the longitude and latitude of crowdsourcing task, the city position of crowdsourcing task is visual
Change;
Step (1-3):Finely positioning is carried out according to the longitude and latitude of crowdsourcing task, the counties and districts position of crowdsourcing task is visual
Change;
Step (1-4):Pretreatment:It determines whether there is data and there is exception, and abnormal task pricing data is rejected.
The abnormal data, such as repeated data, such as longitude and latitude missing data, such as price is beyond the number of setting range
According to.
In the step (2), the constraints of task price is identical to give tacit consent to each task difficulty rank, each task
Radiation radius is identical.
In the step (2), analysis task price influence factor the step of be:
Step (2-1):The task price distribution map obtained according to step (1), the radiation radius of initial setting task, in institute
State setting task restriction condition in radiation radius;The task restriction condition refers to that the difficulty level for giving tacit consent to each task is identical,
Do not consider bad weather, the radiation radius of each task is identical;
Step (2-2):According to the task radiation radius of step (1), between calculating task position and mission requirements person position
Air line distance;
Step (2-3):Air line distance between the task location obtained according to step (2-2) and mission requirements person position,
The mission requirements person in radiation radius is selected, statistics obtains mission requirements person's number in radiation radius;
Step (2-4):Air line distance between the task location obtained according to step (2-2) and mission requirements person position and
Mission requirements person's number in each task radiation radius that step (2-3) obtains finds out task location and mission requirements person position
Most short actual range between putting calculates the average distance that mission requirements person arrives task.
Step (2-5):The variance of distance, standard deviation, maximum value, crowd between calculating task demander position and task location
Number and mode number accounting;
Step (2-6):To the feature that step (2-5) obtains, feature selecting is carried out using variance back-and-forth method, sets threshold
Value selects variance to be more than the feature of given threshold, it is alternatively that the feature gone out, by the feature selected, the letter of mission requirements person
Reputation degree and mission requirements person preplanned mission limit three are provided commonly for establishing pricing model.
In the step (2-2), the step of air line distance d between calculating task position and mission requirements person position
For:
Dy=(BWD-GLAT) × ec × π/180.0; (2)
Dx=(BJD-GLON) × ed × π/180.0; (3)
Ec=Eb+ (Ea-Eb) × (90-GLAT)/90; (4)
Wherein, GLAT represents the latitude of task position, and GLON represents the longitude of task position,
BWD represents the latitude of mission requirements person position, and BJD represents the longitude of mission requirements person position,
Dy represents the vertical distance between task location and mission requirements person position, and dx represents task location and mission requirements
Lateral distance between person position;
Ed is the parallel of latitude radius where GLAT, and ec is for amendment because of the continually changing earth radius length of latitude;
Ea represents equatorial radius, and Eb represents polar radius.
In the step (2-3), the step of obtaining mission requirements person's number in each task scope is counted:
Step (2-3-1):Determine analyst coverage:The point centered on each task location, take set the circle of radiation radius as
Analyst coverage;
Step (2-3-2):The mission requirements person in each task distance range d is selected, statistics obtains each task scope
Interior mission requirements person's number M.
The preplanned mission limit refers to that mission requirements person receives the upper limit value of the number of task.
In the step (2-4):Calculating task demander is to the average distance of taskCalculation formula is:
In step (3), the step of establishing multivariate nonlinear regression analysis model:
Step (3-1):Establish model:
If y is dependent variable, x1,x2,...,xkFor independent variable, multivariate nonlinear regression analysis model is:
Wherein, b0,b1,b2,…bkIt is the parameter of unknown quantity for regression coefficient, e is stochastic error;
Step (3-2):Parameter Estimation:It enablesFormula (1) is converted into the linear of standard
Regression model:
Y=b0+b1z1+b2z2+…+bkzk+e (2)
Step (3-3):Using the method for parameter estimation of multiple linear regression model, error sum of squares is being sought as minimum feelings
Under condition, regression coefficient b is solved with least square method0,b1,b2,…,bk。
The step (4), including:
Step (4-1):R is carried out to the multivariate nonlinear regression analysis model that step (3) is established2It examines, test model validity;
Step (4-2):According to the model validation of acquisition, the price task to fail individually is found, analyzes and fixes a price to task
The other factors of influence, to advanced optimize model.
In the step (4-2), the price task to fail individually, the influence packet that analysis other factors fix a price to task are found
It includes:
Step (4-2-1):The influence of task price:The average price of task is largely completed in the data of acquisition higher than not
The average price of completion illustrates that demander is more likely to the high task of completion task price, and low-cost task is then easily lost
It loses;
Step (4-2-2):The influence that GDP fixes a price for task;
Step (4-2-3):The influence of traffic factor:Analyze traffic route, transport hub, rivers and lakes, mountain area area, hair
Existing traffic factor and gully, lake, mountain peak in nature fix a price on task and send out influence.
A kind of mobile platform crowdsourcing task pricing system, including:Memory, processor and storage on a memory and
The computer program run on processor when the computer program is run by processor, completes such as any of the above-described the method
The step of.
A kind of computer readable storage medium, runs computer program thereon, and the computer program is run by processor
When, it completes such as the step of any of the above-described the method.
Beneficial effects of the present invention:
The present invention carries out data acquisition, data analysis, data processing and feature to the data of crowdsourcing task performance and carries
It takes;Analysis task is fixed a price possible influence factor, establishes multivariate nonlinear regression analysis model, comprehensive analysis direct factor and it is objective because
The influence degree that element fixes a price to task determines the task pricing method of the self-service labor service crowdsourcing platform of mobile Internet.The present invention
The fabulous utilization of the pricing method of realization and the correlated characteristic for being extracted task price have high-accuracy and execution efficiency, full
The demand of sufficient mobile platform task performance.
Description of the drawings
The accompanying drawings which form a part of this application are used for providing further understanding of the present application, and the application's shows
Meaning property embodiment and its explanation do not form the improper restriction to the application for explaining the application.
Fig. 1 is the flow chart of overall process of the present invention;
Fig. 2 is the task price distribution map of the present invention;
Fig. 3 is the task location distribution map of the present invention;
Fig. 4 is multivariate regression models schematic diagram;
Fig. 5 is Shenzhen's task performance distribution map;
Fig. 6 is task longitude and task price relational graph.
Specific embodiment
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the application.It is unless another
It indicates, all technical and scientific terms used herein has usual with the application person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative
It is also intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or combination thereof.
Embodiment 1:
As shown in Figure 1, the present invention provides a kind of mobile Internet platform crowdsourcing task pricing methods.One of the present invention
Embodiment is for the task price in " money-making of taking pictures " APP." money-making of taking pictures " is a kind of mobile interchange self-service clothes off the net
Business pattern.Mission requirements person downloads APP, is registered as the mission requirements person of APP, and times for needing to take pictures then is got from APP
Business (for example upper supermarket goes to check the restocking situation of certain commodity), the reward that earning APP demarcates task.
(1) data acquire:The self-service labor service crowdsourcing data of previous mobile Internet are acquired, to data visualization and pre- place
Reason;
The APP task pricing datas are acquired, the collected data of this implementation are the items that ended task of " money-making of taking pictures " APP
Mesh number evidence and mission requirements person's information data, the position that the project data that ended task contains each task (use longitude and latitude
Represent), price and performance (" 1 " represent complete, " 0 " represent do not complete) (such as table 1);Mission requirements person's information data includes
The position of mission requirements person (such as table 2), credit value start the ticket reserving time with reference to the task that its prestige provides and subscribe limit,
Mission requirements person's prestige is higher in principle, more preferentially starts to select task, quota is also bigger (to be actually during task distribution
It is allotted according to limit proportion is subscribed).
Table 1 ended task project data part signal
Illustrate 2 mission requirements person's information data part of table
(1-1) extracts task price therein, Nogata is drawn according to different prices according to the crowdsourcing mission bit stream of acquisition
Figure carries out visualization processing, obtains the distribution map of task price, such as Fig. 2.Figure it is seen that task price is concentrated mainly on
Between 65.0-75.0, occurring interruption between 75.0-85.0, thus analysis can obtain, and the task quantity of low price is relatively more, and
The task negligible amounts of high price.
(1-2) extraction has terminated the task latitude and longitude coordinates in project data, and each task is obtained using Baidu map API
Actual geographic position distribution, such as Fig. 3.Fig. 3 can be seen that the distribution task of task is mainly distributed on five cities in Guangdong Province:
Shenzhen, Dongguan City, Guangzhou, Foshan City, Qingyuan City.
(1-3) is accurately positioned crowdsourcing task data latitude and longitude coordinates, and the city that data visualization is obtained carries out
Counties and districts divide, and obtaining Qingyuan City, only there are one task coordinates, it is abnormal thus to judge that this data exists, therefore appointing Qingyuan City
Data of being engaged in are rejected.Middle task price distribution figure according to fig. 2 finds that the task number that price is 80.0 and 85.0 is less, therefore temporarily
When be priced at the two prices task data reject, in addition analyzed.
(2) analysis task price influence factor:Analytical procedure (1) collected data information determines the shadow of task price
The factor of sound;
The visualization datagram that (2-1) fixes a price according to the task that step (1) obtains, the point centered on each task location,
The circle that its radius is taken to be 6 kms is analyst coverage, the changing rule of analysis task price, and provide task restriction within this range
Condition be give tacit consent to each task difficulty level it is identical, do not consider bad weather, take pictures and the influences such as refused, and each task spoke
It is identical to penetrate radius.
The data that (2-2) is obtained according to step (1), this example calculate the actual range between 2 points by longitude and latitude span,
The latitude and longitude coordinates for converting crowdsourcing task location and demander position are actual geographic position, determine task location and demander position
Air line distance between putting, is calculated using equation below:
Dy=(BWD-GLAT) × ec × π/180.0
Dx=(BJD-GLON) × ed × π/180.0
Wherein, GLAT represents the latitude of task position, and GLON represents the longitude of task position, and BWD represents to appoint
The latitude of demander of being engaged in position, BJD represent the longitude of mission requirements person position, and dy represents that task location and task need
Vertical distance between the person of asking position, dx represent the lateral distance between task location and mission requirements person position, and ed is GLAT
The parallel of latitude radius at place, for correcting because of the continually changing radius of a ball length of latitude, calculation formula is ec:
Ec=Eb+ (Ea-Eb) × (90-GLAT)/90
Wherein, Ea represents equatorial radius, and Eb represents polar radius.
(2-3) is according to lateral distance dx of each mission requirements person that (2-2) is obtained with each task location and longitudinal direction
Distance dy.Utilize range formulaCalculate the distance d that each mission requirements person arrives task locationi(i=1,
2 ... n), each 6 kilometer range of task distance is selected, statistics obtains mission requirements person's number M in each task scope.
Demander number M in each analysis range that distance and (2-3) that (2-4) basis (2-2) obtains obtain, utilizes
Mission requirements person in the range of each analysis arrives the distance d of task locationi(i=1,2 ... n), find out the shortest distance therein
dmin, the average distance of calculating task demander to taskCalculation formula is:
(2-5) in above-mentioned (2-2), (2-3), (2-4) mission requirements person position, the features such as task location expand
Exhibition;Feature extension includes:The variance of distance, standard deviation, maximum value, crowd between calculating task demander position and task location
Number, mode number accounting etc..
The feature that (2-6) obtains (2-5) carries out feature selecting, given threshold 10, selection using variance back-and-forth method
Variance is more than the feature of threshold value, as the feature that final choice goes out, for pricing model.
Embodiment 2:
(3) pricing model is established:The task price influence factor determined by step (2), establishes Multiple Non Linear Regression
Model.Multiple Non-linear Regression Analysis refers to include the nonlinear regression model (NLRM) of more than two variables, multiple regression, such as Fig. 4 institutes
Show, be the quantity of a kind of phenomenon of reflection or things according to a variety of linear or quantity variations and correspondingly Fluctuation, establish multiple
The linearly or nonlinearly statistical method of mathematical model quantitative relation formula between variable.
If y is dependent variable, x1,x2,...,xkFor independent variable, multivariate nonlinear regression analysis model is:
Wherein,For the parameter of unknown quantity, i.e. regression coefficient, e is stochastic error.It enablesFormula (1) can be converted into the linear regression model (LRM) of standard:
Y=b0+b1z1+b2z2+…+bkzk+e (2)
Using the method for parameter estimation of multiple linear regression model, that is, seeking error sum of squares ∑ e2For minimum situation
Under, it is solved with least square method.By taking bilinear regression model as an example, the normal equation group for solving regression parameter is:
Solving this equation group can be in the hope of b0,b1,b2Numerical value.
It is analyzed according to the data to ended task project data and mission requirements person's information data, it is assumed that task position
Longitude and latitude where putting, the non-linear phase between influence factors and task price such as inverse of number of mission requirements person in analyst coverage
It closes, establishes regression equation, according to principle of least square method, the price rule that can obtain task is:
By formula (4) it is found that longitude and latitude where task price and task is positively correlated, and be better than latitude with longitude positive correlation
Degree, cube with mission requirements person's number inverse in the range of each task analysis, square and inverse be negatively correlated, and
Power is higher for several times, and negative correlation is stronger.
(4) test and appraisal task pricing scheme:According to the task pricing model of the Multiple Non Linear Regression of formulation, test and appraisal task is determined
The validity and convenience of valency model.
(4-1) carries out R to the multivariate regression models of foundation2It examines, obtains R2It is 0.76, fitting effect is good.
(4-2) makees Fig. 6 according to task longitude and task pricing information in the project data that ended task, it can be seen that appoints
Very strong positive correlation is presented in business price and the longitude of its position.
(4-3) detailed analysis model validation, finds the price task to fail individually, and analysis other factors fix a price to task
Influence, to advanced optimize model.
Embodiment 3:
Data are handled, sort out each city crowdsourcing task performance, each city task in Guangdong Province is completed
Situation is as shown in table 3:
Each city task performance table in 3 Guangdong Province of table
It can be seen that the average price that task is largely completed in the data of (1) acquisition is higher than unfinished average price,
Illustrate that demander is more likely to the high task of completion task price, and low-cost task then easily fails;(2) Dongguan City
GDP is less than other cities, and task completeness is 100%, and the city task completeness of other GDP high is then relatively low, it may be said that bright
It also has a certain impact whether GDP completes task.
Embodiment 4:
According to the task coordinate information provided, each task is positioned in Baidu map and is marked and whether is completed,
Shenzhen's task performance is as shown in Figure 5.The areas such as traffic route, transport hub, rivers and lakes, mountain area are analyzed, find to hand over
There is certain influence in gully, lake, mountain peak in the factors such as access condition and nature etc. to task price.
In this example, the present invention has terminated project task data using Feature Engineering the data obtained training pattern, selection
In 435 group task data as training data, using the feature corresponding to this 435 group task as independent variable, by this 435 groups
Performance corresponding to task data is learnt as dependent variable and learning object;The test model stage will terminate item
Mesh task data 400 group task data of residue are tested as test data, calculate its performance.
The foregoing is merely the preferred embodiments of the application, are not limited to the application, for the skill of this field
For art personnel, the application can have various modifications and variations.It is all within spirit herein and principle, made any repair
Change, equivalent replacement, improvement etc., should be included within the protection domain of the application.
Claims (10)
1. a kind of mobile platform crowdsourcing task pricing method, it is characterized in that, include the following steps:
Step (1):Data acquire:The crowdsourcing mission bit stream of labor service crowdsourcing platform is acquired, crowdsourcing mission bit stream is visualized
And pretreatment;The crowdsourcing mission bit stream includes:Crowdsourcing mission number, crowdsourcing task price, the longitude and latitude of crowdsourcing task and crowd
The executive condition of packet task;
Step (2):Analysis task price influence factor:Analytical procedure (1) as a result, screening task price influence factor;
Step (3):Establish task pricing model:The feature determined by step (2), establishes multivariate nonlinear regression analysis model;
Step (4):Price task is treated using the multivariate nonlinear regression analysis model of step (3) to fix a price.
2. a kind of mobile platform crowdsourcing task pricing method as described in claim 1, it is characterized in that, the method further includes:
Step (5):Test and appraisal task pricing model:The multivariate nonlinear regression analysis model that evaluation steps (3) are formulated.
3. a kind of mobile platform crowdsourcing task pricing method as described in claim 1, it is characterized in that, the step of the step (1)
Suddenly it is:
Step (1-1):According to the crowdsourcing mission bit stream of acquisition, extraction task price is drawn histogram according to different prices, is carried out
Visualization processing obtains task price distribution map;
Step (1-2):Coarse localization is carried out according to the longitude and latitude of crowdsourcing task, the city position of crowdsourcing task is visualized;
Step (1-3):Finely positioning is carried out according to the longitude and latitude of crowdsourcing task, by counties and districts' position visualization of crowdsourcing task;
Step (1-4):Pretreatment:It determines whether there is data and there is exception, and abnormal task pricing data is rejected.
4. a kind of mobile platform crowdsourcing task pricing method as described in claim 1, it is characterized in that, in the step (2), appoint
The constraints of business price is identical to give tacit consent to each task difficulty rank, and the radiation radius of each task is identical.
5. a kind of mobile platform crowdsourcing task pricing method as described in claim 1, it is characterized in that, in the step (2), point
Analysis task fix a price influence factor the step of be:
Step (2-1):The task price distribution map obtained according to step (1), the radiation radius of initial setting task, in the spoke
Penetrate setting task restriction condition in radius;The task restriction condition refers to that the difficulty level for giving tacit consent to each task is identical, does not examine
Consider bad weather, the radiation radius of each task is identical;
Step (2-2):It is straight between calculating task position and mission requirements person position according to the task radiation radius of step (1)
Linear distance;
Step (2-3):Air line distance between the task location obtained according to step (2-2) and mission requirements person position, is selected
Mission requirements person in radiation radius, statistics obtain mission requirements person's number in radiation radius;
Step (2-4):Air line distance and step between the task location obtained according to step (2-2) and mission requirements person position
Mission requirements person's number in each task radiation radius that (2-3) is obtained, find out task location and mission requirements person position it
Between most short actual range, calculate mission requirements person arrive task average distance;
Step (2-5):The variance of distance between calculating task demander position and task location, standard deviation, maximum value, mode and
Mode number accounting;
Step (2-6):To the feature that step (2-5) obtains, feature selecting, given threshold, choosing are carried out using variance back-and-forth method
Select variance be more than given threshold feature, it is alternatively that the feature gone out, by the feature selected, the credit worthiness of mission requirements person and
Mission requirements person preplanned mission limit three is provided commonly for establishing pricing model.
6. a kind of mobile platform crowdsourcing task pricing method as described in claim 1, it is characterized in that, in the step (2-3),
The step of statistics obtains mission requirements person's number in each task scope:
Step (2-3-1):Determine analyst coverage:The point centered on each task location takes the circle for setting radiation radius as analysis
Range;
Step (2-3-2):The mission requirements person in each task distance range d is selected, statistics is obtained in each task scope
Mission requirements person's number M.
7. a kind of mobile platform crowdsourcing task pricing method as described in claim 1, it is characterized in that, the step (4), packet
It includes:
Step (4-1):R is carried out to the multivariate nonlinear regression analysis model that step (3) is established2It examines, test model validity;
Step (4-2):According to the model validation of acquisition, the price task to fail individually is found, analyzing to fix a price on task influences
Other factors, to advanced optimize model.
8. a kind of mobile platform crowdsourcing task pricing method as described in claim 1, it is characterized in that, in the step (4-2),
The price task to fail individually is found, the influence that analysis other factors fix a price to task includes:
Step (4-2-1):The influence of task price:The average price of task is largely completed in the data of acquisition higher than unfinished
Average price, illustrate that demander is more likely to completion task and fixes a price high task, and low-cost task then easily fails;
Step (4-2-2):The influence that GDP fixes a price for task;
Step (4-2-3):The influence of traffic factor:Traffic route, transport hub, rivers and lakes, mountain area area are analyzed, finds to hand over
Gully, lake, mountain peak in access condition factor and nature are fixed a price on task for sending out and be influenced.
9. a kind of mobile platform crowdsourcing task pricing system, it is characterized in that, including:Memory, processor and it is stored in storage
The computer program run on device and on a processor when the computer program is run by processor, is completed as any of the above-described
The step of the method.
10. a kind of computer readable storage medium, it is characterized in that, computer program is run thereon, and the computer program is located
When managing device operation, complete such as the step of any of the above-described the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711405763.4A CN108205515A (en) | 2017-12-22 | 2017-12-22 | A kind of mobile platform crowdsourcing task pricing method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711405763.4A CN108205515A (en) | 2017-12-22 | 2017-12-22 | A kind of mobile platform crowdsourcing task pricing method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108205515A true CN108205515A (en) | 2018-06-26 |
Family
ID=62605058
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711405763.4A Pending CN108205515A (en) | 2017-12-22 | 2017-12-22 | A kind of mobile platform crowdsourcing task pricing method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108205515A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110264272A (en) * | 2019-06-21 | 2019-09-20 | 山东师范大学 | A kind of mobile Internet labor service crowdsourcing platform task optimal pricing prediction technique, apparatus and system |
CN111260161A (en) * | 2018-11-30 | 2020-06-09 | 中移(杭州)信息技术有限公司 | Method and device for issuing crowdsourcing tasks |
CN112380489A (en) * | 2020-11-03 | 2021-02-19 | 武汉光庭信息技术股份有限公司 | Data processing time calculation method, data processing platform evaluation method and system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140279780A1 (en) * | 2013-03-12 | 2014-09-18 | Xerox Corporation | Method and system for recommending crowdsourcing platforms |
CN106327090A (en) * | 2016-08-29 | 2017-01-11 | 安徽慧达通信网络科技股份有限公司 | Real task allocation method applied to preference crowd-sourcing system |
-
2017
- 2017-12-22 CN CN201711405763.4A patent/CN108205515A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140279780A1 (en) * | 2013-03-12 | 2014-09-18 | Xerox Corporation | Method and system for recommending crowdsourcing platforms |
CN106327090A (en) * | 2016-08-29 | 2017-01-11 | 安徽慧达通信网络科技股份有限公司 | Real task allocation method applied to preference crowd-sourcing system |
Non-Patent Citations (1)
Title |
---|
王姮冰等: "基于多元线性回归的拍照任务定价模型", 《现代经济信息》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111260161A (en) * | 2018-11-30 | 2020-06-09 | 中移(杭州)信息技术有限公司 | Method and device for issuing crowdsourcing tasks |
CN111260161B (en) * | 2018-11-30 | 2023-11-14 | 中移(杭州)信息技术有限公司 | Method and equipment for issuing crowdsourcing task |
CN110264272A (en) * | 2019-06-21 | 2019-09-20 | 山东师范大学 | A kind of mobile Internet labor service crowdsourcing platform task optimal pricing prediction technique, apparatus and system |
CN112380489A (en) * | 2020-11-03 | 2021-02-19 | 武汉光庭信息技术股份有限公司 | Data processing time calculation method, data processing platform evaluation method and system |
CN112380489B (en) * | 2020-11-03 | 2024-04-16 | 武汉光庭信息技术股份有限公司 | Data processing time calculation method, data processing platform evaluation method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Nelson et al. | Comparison of a random search algorithm and mixed integer programming for solving area-based forest plans | |
Athanasopoulos et al. | The tourism forecasting competition | |
Armsworth et al. | Management costs for small protected areas and economies of scale in habitat conservation | |
Lan et al. | A crowdsourcing quality prediction model based on random forests | |
Podvezko et al. | Dependence of multi‐criteria evaluation result on choice of preference functions and their parameters | |
Jeong et al. | Integrating buildings into a rural landscape using a multi-criteria spatial decision analysis in GIS-enabled web environment | |
CN109711424B (en) | Behavior rule acquisition method, device and equipment based on decision tree | |
CN108205515A (en) | A kind of mobile platform crowdsourcing task pricing method and system | |
CN109636474A (en) | Source of houses sequence methods of exhibiting, device, equipment and storage medium | |
CN106295351B (en) | A kind of Risk Identification Method and device | |
Hill et al. | Economic values of agritourism to visitors: a multi-destination hurdle travel cost model of demand | |
CN111784084B (en) | Travel generation prediction method, system and device based on gradient lifting decision tree | |
CN107609771A (en) | A kind of supplier's value assessment method | |
CN102096633A (en) | Application field oriented software quality standard evaluating method | |
CN115456695A (en) | Method, device, system and medium for analyzing shop address selection | |
CN109325657A (en) | A kind of measures and procedures for the examination and approval of credit operation, storage medium and server | |
CN107992979A (en) | A kind of mobile platform crowdsourcing task price optimization method and system | |
CN117172633B (en) | Manufacturing service subgraph simulation method and system for industrial Internet platform | |
Puška et al. | An assessment of improving the sustainable agro-touristic offer in an emerging country using the integrative approach based on fuzzy logic | |
Jafari et al. | A systematic approach for knowledge auditing | |
Leon-Gonzalez et al. | Improving multi-site benefit functions via Bayesian model averaging: A new approach to benefit transfer | |
CN110233864B (en) | Crowdsourcing-based information acquisition method, device, equipment and storage medium | |
Skulimowski | Forward-looking activities supporting technological planning of AI-based learning platforms | |
CN116166880A (en) | Charging station recommendation method and device, electronic equipment and readable storage medium | |
CN115829209A (en) | Environment-friendly intelligent warehouse environment-friendly quality analysis method and device based on carbon path |
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: 20180626 |