CN106384205B - Modeling method and device for collecting operation input duration - Google Patents
Modeling method and device for collecting operation input duration Download PDFInfo
- Publication number
- CN106384205B CN106384205B CN201610876791.3A CN201610876791A CN106384205B CN 106384205 B CN106384205 B CN 106384205B CN 201610876791 A CN201610876791 A CN 201610876791A CN 106384205 B CN106384205 B CN 106384205B
- Authority
- CN
- China
- Prior art keywords
- duration
- determining
- mapping relation
- parameter
- weather
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000013507 mapping Methods 0.000 claims abstract description 84
- 238000005315 distribution function Methods 0.000 claims description 14
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000012417 linear regression Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 13
- 238000003860 storage Methods 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011002 quantification Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000001134 F-test Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Images
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
- G06Q10/06—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a modeling method and a device for collecting operation input duration, wherein the modeling method for collecting the operation input duration comprises the steps of determining parameter values of parameters related to the collection of the operation input duration; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; and modeling the input duration of the acquisition operation according to the mapping relation. The invention can make reference for the arrangement of the collection operation plan, improve the effective utilization rate of resources and make reasonable reference for evaluating the operation duration of the collection operation personnel.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a modeling method and a modeling device for collecting operation input duration.
Background
The collection operation of the map data provides field support for the generation and production of the electronic map. The map data acquisition mode is that the vehicle on which the acquisition equipment is erected is used for acquiring information such as roads, ground object identifications and the like, and because the acquisition is carried out outdoors, the input duration of the acquisition operation is influenced by factors such as weather conditions, temperature, sunshine duration and the like derived from different regions, the input duration of the acquisition operation in different regions (the physical boundary is considered to be different region-level cities) is different, and the acquisition efficiency and the electronic map making progress are directly influenced by the input time of the acquisition operation.
In the related art, there is no quantitative evaluation and reference for the time length of the acquisition operation that different regions should be invested in within a certain period (e.g., month), and the utilization rate of the region resources in the acquisition operation process is low.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, an object of the present invention is to provide a modeling method for collecting operation input duration, which can make a reference for collecting operation plan arrangement, improve effective utilization rate of resources, and make a rationality reference for evaluating operation duration of collection operators.
Another object of the present invention is to provide a modeling apparatus for collecting the operation input duration.
A further object of the invention is to propose a modelling device for collecting the duration of a work input.
It is yet another object of the invention to provide a non-transitory computer readable storage medium.
It is a further object of the invention to propose a computer program product.
In order to achieve the above object, a modeling method for collecting a work input duration according to an embodiment of a first aspect of the present invention includes: determining a parameter value of a parameter associated with the acquisition operation input duration; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; and modeling the acquisition operation investment duration according to the mapping relation.
The modeling method for collecting the operation input duration provided by the embodiment of the first aspect of the invention comprises the steps of determining the parameter value of a parameter associated with the collection of the operation input duration; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; the acquisition operation investment duration is modeled according to the mapping relation, reference can be made for the arrangement of the acquisition operation plan, the effective utilization rate of resources is improved, and rationality reference can be made for the evaluation of the operation duration of the acquisition operation personnel.
In order to achieve the above object, a modeling apparatus for collecting a work input duration according to an embodiment of a second aspect of the present invention includes: the first determination module is used for determining the parameter value of the parameter associated with the acquisition operation input duration; the second determination module is used for determining the mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; and the modeling module is used for modeling the acquisition operation investment duration according to the mapping relation.
The modeling device for collecting the operation input duration provided by the embodiment of the second aspect of the invention determines the parameter value of the parameter associated with the collection of the operation input duration; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; the acquisition operation investment duration is modeled according to the mapping relation, reference can be made for the arrangement of the acquisition operation plan, the effective utilization rate of resources is improved, and rationality reference can be made for the evaluation of the operation duration of the acquisition operation personnel.
In order to achieve the above object, a modeling apparatus for collecting a work input duration according to an embodiment of a third aspect of the present invention includes: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: determining a parameter value of a parameter associated with the acquisition operation input duration; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; and modeling the acquisition operation investment duration according to the mapping relation.
The modeling device for collecting the operation input duration provided by the embodiment of the third aspect of the invention determines the parameter value of the parameter associated with the collection of the operation input duration; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; the acquisition operation investment duration is modeled according to the mapping relation, reference can be made for the arrangement of the acquisition operation plan, the effective utilization rate of resources is improved, and rationality reference can be made for the evaluation of the operation duration of the acquisition operation personnel.
To achieve the above object, a non-transitory computer-readable storage medium according to a fourth aspect of the present invention is a non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of a mobile terminal, the instructions enabling the mobile terminal to execute a modeling method for collecting a job-investment duration, the method including:
determining a parameter value of a parameter associated with the acquisition operation input duration;
determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters;
and modeling the acquisition operation investment duration according to the mapping relation.
In a non-transitory computer-readable storage medium according to a fourth aspect of the present invention, a parameter value of a parameter associated with a collection operation input duration is determined; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; the acquisition operation investment duration is modeled according to the mapping relation, reference can be made for the arrangement of the acquisition operation plan, the effective utilization rate of resources is improved, and rationality reference can be made for the evaluation of the operation duration of the acquisition operation personnel.
To achieve the above object, a computer program product according to a fifth aspect of the present invention is provided, wherein when being executed by an instruction processor, performs a modeling method for collecting a job-break duration, and the method includes:
determining a parameter value of a parameter associated with the acquisition operation input duration;
determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters;
and modeling the acquisition operation investment duration according to the mapping relation.
The computer program product provided by the embodiment of the fifth aspect of the invention is obtained by determining the parameter value of the parameter associated with the acquisition operation input duration; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; the acquisition operation investment duration is modeled according to the mapping relation, reference can be made for the arrangement of the acquisition operation plan, the effective utilization rate of resources is improved, and rationality reference can be made for the evaluation of the operation duration of the acquisition operation personnel.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flow chart of a modeling method for collecting a work input duration according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram of a modeling method for collecting work input duration according to another embodiment of the present invention;
FIG. 3a is a sample data diagram of a historical invested duration in an embodiment of the invention;
FIG. 3b is a diagram showing the relationship between the throw-in duration and the day length parameter in the embodiment of the present invention;
FIG. 4 is a schematic flow chart diagram of a modeling method for collecting work input duration according to another embodiment of the present invention;
FIG. 5 is a schematic flow chart diagram of a modeling method for collecting work input duration according to another embodiment of the present invention;
FIG. 6 is a schematic flow chart diagram of a modeling method for collecting work input duration according to another embodiment of the present invention;
FIG. 7 is a schematic diagram of a back propagation neural network model in an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a modeling apparatus for collecting a work input duration according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a modeling apparatus for collecting a work input duration according to another embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. On the contrary, the embodiments of the invention include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.
Fig. 1 is a schematic flowchart of a modeling method for collecting a job input duration according to an embodiment of the present invention. The present embodiment is exemplified in the modeling apparatus in which the modeling method for collecting a job-put duration is configured to collect a job-put duration. The modeling method for collecting the operation input duration can be applied to the map data collection operation process.
Referring to fig. 1, the modeling method for collecting the operation investment duration includes:
s11: and determining the parameter value of the parameter associated with the acquisition operation input duration.
In the embodiment of the invention, the parameter value of the parameter associated with the acquisition operation input duration is determined, the acquisition operation input duration is calculated according to the parameter value of the associated parameter, the acquisition operation plan arrangement can be referred, the effective utilization rate of resources is improved, and the reasonability reference can be made for evaluating the operation duration of the acquisition operators.
In the embodiment of the invention, the acquisition of the parameters related to the operation input duration comprises the following steps: the method for determining the parameter value of the parameter relevant to the acquisition operation input duration in a plurality of regions for executing the acquisition operation comprises the following steps: determining parameter values of the day length parameter of each region and each month in a year to obtain a plurality of day length values corresponding to each region.
It can be understood that the investment duration of the collecting operation is generally caused by region factors, and the investment durations of different regions are different. For different regions, if the physical range is too small, the separation of the investment durations is not obvious, the quantization is incorrect due to too large physical range, and meanwhile, the size unit of the region can be defined as a grade city by combining a fixed point mode of field collection and the city range limit of the country.
It should be noted that, because the day length of each region is different due to the influence of the geographical location, the day length of each month is relatively fixed for a specific region, and the day length value is only related to the latitude of the region and the latitude of the direct sun point at that time, so that the parameter value of the day length parameter of each month in a year can be determined by the following formula:
Daylength＝24·arc cos(tanα·tanβ)/π； (1)
wherein α is the average value of the latitude of the sun direct-emitting point in the current month of a certain region, β is the latitude and longitude coordinate value of the region, and Daylength is the parameter value of the day length parameter in the current month of the region.
The day length value of each region in each month in one year can be calculated by formula (1).
In an embodiment of the present invention, the acquiring parameters associated with the operation input duration further includes: and performing weather type enumeration and weather attribute enumeration of weather of each region in a plurality of regions for executing the collection operation.
Due to requirements of acquisition instruments, acquisition quality and the like, factors of weather conditions (sunny, cloudy, rainy, foggy and the like) influence the acquisition investment duration to a great extent. For example, in rainy and snowy days, the collecting operation cannot be performed due to the limitation of instruments, and the collecting operation investment time is obviously shortened in cloudy days or in some weather which affects visibility. The occurrence of weather in different regions is regularly circulated in general, because the types of weather are very many, and the description of weather is written in language, for example, table 1 shows the weather description of a city in 2015 and 6 months (the weather condition description of other cities or months is similar).
TABLE 1
| 2015/6/1 | Middle rain-yin |
| 2015/6/2 | Light rain |
| 2015/6/3 | Gust rain-intermediate rain |
| 2015/6/4 | All-weather |
| 2015/6/5 | All the clear to yin |
| 2015/6/6 | Yin (kidney) |
| … | … |
| 2015/6/23 | Heavy rain to light rain |
| 2015/6/24 | Heavy to heavy rain |
| 2015/6/25 | Little rain to cloudy |
| 2015/6/26 | Rain in the shade |
| 2015/6/27 | Rain in shade |
| 2015/6/28 | Small to large rain |
| 2015/6/29 | Rainstorm to light rain |
| 2015/6/30 | Cloudy-cloudy |
Alternatively, keywords in table 1 that cannot be used for the collection job may be defined: rain, fog, haze, snow, and so, each weather type in the weather type enumeration may be labeled as xj(j ═ 1,2, …, a), and at the same time, the attribute words in table 1 can be defined: small, medium, large, storm, thunder, battle, and thus, each weather attribute in the weather attribute enumeration may be labeled as xk(k＝1，2，…,b)。
In an embodiment of the present invention, the acquiring parameters associated with the operation input duration further includes: temperature extremes for each of a plurality of zones in which the collection operation is performed.
It will be appreciated that there is also a requirement for operating temperature due to operational limitations of the hardware of the collection task device. At more extreme temperatures, equipment and vehicles are affected by the temperature, and the time of investment in acquisition operation is reduced. Each can be marked separately by statistical analysis of historical temperature conditionsA region of extremely low temperature per month during the year of
The extreme high temperature is v.
Optionally, the parameter value of the parameter associated with the acquisition operation input duration is determined, the acquisition operation input duration is calculated according to the parameter value of the associated parameter, reference can be made for the acquisition operation plan arrangement, the effective utilization rate of resources is improved, and reasonable reference can be made for evaluating the operation duration of the acquisition operation personnel.
S12: and determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters.
In an embodiment of the present invention, when a parameter associated with an input duration of an acquisition operation is a day length parameter of each of a plurality of regions where the acquisition operation is performed, determining a mapping relationship between the input duration and the associated parameter according to a parameter value of the associated parameter includes: acquiring sample data of the investment duration; and determining a first mapping relation between the input duration of each region and the day length parameter according to the sample data and the corresponding multiple day length values.
In some embodiments, referring to fig. 2, step S12 includes:
s21: and acquiring sample data of the input time.
It should be noted that, because of the influence of the actual situation of the collecting operation, the parameter value of the day length parameter is not equal to the input duration, and the input duration and the day length value are greatly different from each other in the historical collecting situation. For example, when the weather is fine and there are no various incidental factors (e.g., instrument damage, etc.) affecting the collection operation, the larger the day length value is, the longer the input duration should be. In addition to the acquisition operation time, there are other reasonable time losses, for example, time loss on the way to the acquisition area, time loss of instrument preparation, and the like, and the distribution of such reasonable time losses is regularly recyclable from the relatively long-term data, and therefore, the day length parameter and the input time length have a certain numerical relationship.
In the embodiment of the invention, sample data of historical investment duration can be collected, and a first mapping relation between the investment duration and the day length parameter of each region is determined according to the sample data and a plurality of day length values corresponding to each region.
Optionally, the investment time is marked as engage time, vehicle days normally collected from historical vehicle days can be selected, the day length value Daylength of the current day of the selected vehicle day is calculated, and then data with the investment time less than one third of the day length value is removed by screening abnormal data, namely data with the investment time being more than or equal to 1/3Daylength is selected as sample data of the investment time.
As an example, referring to fig. 3a, fig. 3a is a schematic diagram of sample data of a historical investment duration in an embodiment of the present invention.
S22: and determining a first mapping relation between the input duration of each region and the day length parameter according to the sample data and the corresponding multiple day length values.
Alternatively, the day length value may be divided into intervals (for example, 0.1 hour), the central value of the input duration in each interval is selected, regression modeling is performed on the day length value and the input duration, and simultaneously, an F-test (a homogeneity test, i.e., by comparing the variances of two sets of data to determine whether there is a significant difference in the precision of the two sets of data) is performed, the p value is less than 0.05, if the model check shows that the input duration is linearly related to the day length parameter, for example, when the input duration is linearly related to the day length parameter, the relationship between the two can be expressed by the following formula:
Engagedtime＝c+d*Daylength； (2)
wherein c and d are parameter values calculated by regression modeling.
As an example, referring to fig. 3b, fig. 3b is a schematic diagram of the relationship between the throw-in duration and the day length parameter in the embodiment of the present invention.
In the embodiment, sample data of the investment duration is obtained; and determining a first mapping relation between the input duration and the day length parameter of each region according to the sample data and the corresponding multiple day length values, determining the size of the input duration based on the day length values, and making a rationalization quantification basis for calculating the input duration of the acquisition operation.
In the embodiment of the present invention, when the parameter associated with the invested time of the collection operation is the weather type enumeration and the weather attribute enumeration of each region weather in a plurality of regions where the collection operation is executed, determining the mapping relationship between the invested time and the associated parameter according to the parameter value of the associated parameter, includes: combining each weather type in the weather type enumeration and each weather attribute in the weather attribute enumeration to obtain a plurality of combinations; determining a weight corresponding to each combination of the plurality of combinations according to the plurality of combinations and the sample data; and determining a second mapping relation between the investment duration and the weather of each region according to the weight corresponding to each combination.
In some embodiments, referring to fig. 4, step S12 further includes:
s41: and combining each weather type in the weather type enumeration and each weather attribute in the weather attribute enumeration to obtain a plurality of combinations.
Optionally, each weather type in the weather type enumeration is labeled xj(j ═ 1,2, …, a), label each weather attribute in the weather attribute enumeration as xk(k is 1,2, …, b), converting x intojAnd xkAre combined to obtain xjk(a + b combinations).
S42: a weight corresponding to each of the plurality of combinations is determined from the plurality of combinations and the sample data.
Since the distribution range of the day length is wide, it is necessary to independently exclude the influence of weather on the duration of the investment. Therefore, when the influence of weather on the investment duration is analyzed, the day length value can be analyzed in different sections, and the influence of different weather on the investment duration is analyzed in each section.
Alternatively, the day length enumeration value may be divided into small parts to reduce the influence of the day length parameter on the thrown-in time period (for example, a minimum day length value to a maximum day length value, which are analyzed in 0.5 hour step progression), and the day length enumeration value is marked as xiFinally, reference values y and x for collecting historical investment duration of operation can be obtainedi、xjAnd xkThe relationship of (1) is:
y＝β0+β1x1+…+βpxp+ε； (3)
wherein, β0，β1，…，βpIs p +1 weights, ε is an unmeasurable random error, and ε -N (0, σ) is generally assumed2)。
Formula (3) is a multiple linear regression equation, y is a dependent variable, and xi(i-1, 2, …, p) is an argument. The following formula (4) is a rational regression equation:
E(y)＝β0+β1x1+…+βpxp； (4)
to determine the weights β0，β1，…，βpTaking the reference value of the collected operation historical input duration as the sample data (x) of n groups of input durationsi1,xi2,…,xip；yi) 1,2, …, n, which satisfy equation (3), i.e.:
wherein epsilon1,ε2,…,εnIndependent of each other and all obey N (0, sigma)2)。
Weights β in a multiple linear regression equation0，β1，…，βpCan be estimated by least squares method, choose β ═ (β)0,β1,…,βp)TThe sum of squared errors Q (β) is minimized, where Q (β) can be obtained by the following equation (6):
since Q (β) is about β0，β1，…，βpAnd thus Q (β) must have a minimum, the coefficient value of each enumerated variable, i.e., the weight of each enumerated variable, can be calculated using the extremum method of calculus.
It should be noted that the weight can be inferred only by weakening the day length enumeration value, and when the combination of the weather type and the weather attribute is "heavy rain", the weight of "heavy rain" can be obtained as 1.3 (an example value), and when the combination of the weather type and the weather attribute is "light rain", the weight of "light rain" can be obtained as 0.7 (an example value), and other weather is similar.
S43: and determining a second mapping relation between the investment duration and the weather of each region according to the weight corresponding to each combination.
Optionally, the second mapping relationship between the invested time and each regional weather may be determined according to the weight corresponding to each combination in S32, that is, each combination of the weather type in the weather type enumeration and each weather attribute in the weather attribute enumeration may correspond to an actual fitted collection job invested time in a statistical sense.
In this embodiment, a plurality of combinations are obtained by combining each weather type in the weather type enumeration and each weather attribute in the weather attribute enumeration; determining a weight corresponding to each combination of the plurality of combinations according to the plurality of combinations and the sample data; and determining a second mapping relation between the investment duration and the weather of each region according to the weight corresponding to each combination, determining the size of the investment duration based on the weather of each region, and making a rationalized and quantized basis for calculating the acquisition operation investment duration.
In the embodiment of the present invention, when the parameter associated with the collection operation input duration is a temperature extreme value of each region in a plurality of regions where the collection operation is performed, determining a mapping relationship between the input duration and the associated parameter according to the parameter value of the associated parameter includes: determining a distribution function between the input duration and the temperature of each region according to the sample data of the input duration; and determining a third mapping relation between the input duration and the temperature extreme value according to the distribution function.
In some embodiments, referring to fig. 5, step S12 further includes:
s51: and determining a distribution function between the input time and the temperature of each region according to the sample data of the input time.
Alternatively, a distribution function between the investment duration and the temperature of each region, such as a gaussian distribution, may be obtained by performing statistical analysis on the sample data of the historical investment duration.
S52: and determining a third mapping relation between the input duration and the temperature extreme value according to the distribution function.
Alternatively, a third mapping between the duration of the plunge and the temperature extremes may be determined according to a distribution function, e.g., at extremely low temperatures
And the method corresponds to a reference input time length, and corresponds to a reference input time length when the extreme high temperature is v.
In the embodiment, the distribution function between the investment duration and the temperature of each region is determined according to the sample data of the investment duration, the third mapping relation between the investment duration and the temperature extreme value is determined according to the distribution function, the size of the investment duration can be determined based on the temperature extreme value of each region, and a rationalization quantification basis is made for the calculation of the acquisition operation investment duration.
S13: and modeling the input duration of the acquisition operation according to the mapping relation.
In the embodiment of the invention, a multiple linear regression model can be established according to the first mapping relation, the second mapping relation and the third mapping relation so as to model the input duration of the acquisition operation.
In some embodiments, referring to fig. 6, the modeling method for collecting the job investment duration further includes:
s61: and acquiring real-time data of the acquisition operation input time.
Because the model parameters cannot be very accurate due to the quantity or quality of sample data of the acquisition operation input duration, the real-time data of the acquisition operation input duration needs to be acquired, and the mapping relation between the input duration and the associated parameters is updated according to the real-time data so as to ensure the accuracy of the model.
S62: and updating the mapping relation between the input duration and the associated parameters according to the real-time data.
In an embodiment of the present invention, a back propagation neural network model may be used for iterative updating to ensure the accuracy of the model. The iteration principle is as follows:
the back propagation inputs, which correspond to the attributes of the sample data metrics for each newly added acquisition job break-in duration, are simultaneously provided to a layer of units, called the input layer, whose weighted outputs are sequentially and simultaneously provided to a second layer of "neuron-like" called the hidden layer, whose weighted outputs can be input to another hidden layer, and so on, the number of hidden layers can be arbitrary (although in practice only one layer is usually used), with the weighted output of the last hidden layer being the input to the units that make up the output layer that publishes the network prediction value for a given sample.
For example, referring to fig. 7, fig. 7 is a schematic diagram of a back propagation neural network model in an embodiment of the present invention, where X ═ { X ═ X1，x2，…，xiAre training samples fed into the input layers, with weighted connections between each layer, wijRepresenting the weight from cell j of a certain layer to cell i of the previous layer.
And comparing the network predicted value of each sample data with the real-time data by the back propagation neural network to learn. For each training sample, the weights are modified such that the mean square error between the network prediction values and the real-time data is minimized. This modification is done "backwards". I.e. from the output layer, via each hidden layer, to the first hidden layer (hence the name back-propagation). Eventually, the weights will converge and the learning process stops. The flow of each step is as follows:
the samples are training samples of investment duration, l is learning rate, and the network is a multilayer feedforward network.
And (4) each time the weight is converged, using the latest model parameter, namely updating the mapping relation between the input duration and the associated parameter according to real-time data.
In the embodiment, the model can be updated according to the real-time data of the acquired operation input duration by acquiring the real-time data of the acquired operation input duration and updating the mapping relation between the input duration and the associated parameters according to the real-time data, so that the accuracy of the method is effectively improved.
In the embodiment, the parameter value of the parameter associated with the acquisition operation input duration is determined; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; the acquisition operation investment duration is modeled according to the mapping relation, reference can be made for the arrangement of the acquisition operation plan, the effective utilization rate of resources is improved, and rationality reference can be made for the evaluation of the operation duration of the acquisition operation personnel.
Fig. 8 is a schematic structural diagram of a modeling apparatus for collecting a work input duration according to an embodiment of the present invention. The modeling means 80 for collecting the operation investment time may be implemented by software, hardware, or a combination of both.
Referring to fig. 8, the modeling apparatus 80 for collecting the operation investment time includes: a first determination module 801, a second determination module 802, and a modeling module 803. Wherein,
the first determining module 801 is configured to determine a parameter value of a parameter associated with the collection operation input duration.
A second determining module 802, configured to determine a mapping relationship between the investment duration and the associated parameter according to the parameter value of the associated parameter.
And the modeling module 803 is used for modeling the input duration of the acquisition operation according to the mapping relation.
In some embodiments, referring to fig. 9, the modeling device 80 for collecting the job investment duration further includes:
optionally, the associated parameters include: in a plurality of regions where the collection operation is performed, the first determining module 801 is specifically configured to:
determining parameter values of the day length parameter of each region and each month in a year to obtain a plurality of day length values corresponding to each region.
Optionally, the second determining module 802 is specifically configured to:
acquiring sample data of the investment duration;
and determining a first mapping relation between the input duration of each region and the day length parameter according to the sample data and the corresponding multiple day length values.
Optionally, the associating parameters further include: in a plurality of regions where the collection job is executed, the weather type enumeration and the weather attribute enumeration of weather of each region, the second determining module 802 is further configured to:
combining each weather type in the weather type enumeration and each weather attribute in the weather attribute enumeration to obtain a plurality of combinations;
determining a weight corresponding to each combination of the plurality of combinations according to the plurality of combinations and the sample data;
and determining a second mapping relation between the investment duration and the weather of each region according to the weight corresponding to each combination.
Optionally, the parameters further include: the second determining module 802 is further configured to, for each of the plurality of zones where the collecting operation is performed, determine a temperature extremum of each zone:
determining a distribution function between the input duration and the temperature of each region according to the sample data of the input duration;
and determining a third mapping relation between the input duration and the temperature extreme value according to the distribution function.
Optionally, the modeling module 803 is specifically configured to:
and establishing a multiple linear regression model according to the first mapping relation, the second mapping relation and the third mapping relation so as to model the input duration of the acquisition operation.
An obtaining module 804, which obtains real-time data of the acquisition operation input duration;
and an updating module 805, configured to update a mapping relationship between the investment duration and the associated parameter according to the real-time data.
It should be noted that the explanation of the modeling method embodiment for acquiring the operation duration input in the foregoing fig. 1-6 embodiments also applies to the modeling apparatus 80 for acquiring the operation duration input in this embodiment, and the implementation principle is similar, and is not described here again.
In the embodiment, the parameter value of the parameter associated with the acquisition operation input duration is determined; determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters; the acquisition operation investment duration is modeled according to the mapping relation, reference can be made for the arrangement of the acquisition operation plan, the effective utilization rate of resources is improved, and rationality reference can be made for the evaluation of the operation duration of the acquisition operation personnel.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (8)
1. A modeling method for collecting operation input duration is characterized by comprising the following steps of:
determining a parameter value of a parameter associated with the acquisition operation input duration;
determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters;
modeling the acquisition operation investment duration according to the mapping relation;
further comprising:
acquiring real-time data of the acquisition operation input duration;
updating a mapping relation between the investment duration and the associated parameters according to the real-time data, wherein a back propagation neural network model is adopted to iteratively update the mapping relation, the back propagation neural network model comprises training samples, an input layer, a hidden layer and an output layer, each layer is in weighted connection with a weight, a network predicted value of each sample data is compared with the real-time data by adopting the back propagation neural network model for learning, and the weight is modified for each sample data, so that the mean square error between the network predicted value and the real-time data is minimum;
the associated parameters include: the determining of the parameter value of the parameter associated with the acquisition operation investment duration in the multiple regions for executing the acquisition operation, the parameter value being a day length parameter of each region, includes:
determining the parameter value of the day length parameter of each region and each month in one year to obtain a plurality of day length values corresponding to each region;
determining a mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters, wherein the mapping relation comprises the following steps:
acquiring sample data of the invested time;
and determining a first mapping relation between the input duration of each region and the day length parameter according to the sample data and the corresponding day length values.
2. A modeling method for collecting job break-in duration as defined in claim 1 wherein said correlation parameters further include: in a plurality of regions where the collection operation is executed, determining a mapping relationship between the invested time and the associated parameters according to the parameter values of the associated parameters includes:
combining each weather type in the weather type enumeration and each weather attribute in the weather attribute enumeration to obtain a plurality of combinations;
determining a weight corresponding to each combination of the plurality of combinations from the plurality of combinations and the sample data;
and determining a second mapping relation between the investment duration and the weather of each region according to the weight corresponding to each combination.
3. A modeling method for collecting job break-in duration as defined in claim 2 wherein said correlation parameter further comprises: the determining of the mapping relationship between the invested time and the associated parameters according to the parameter values of the associated parameters comprises:
determining a distribution function between the invested time and the temperature of each region according to the sample data of the invested time;
and determining a third mapping relation between the input duration and the temperature extreme value according to the distribution function.
4. A modeling method for collecting job break-in duration according to claim 3, characterized in that said modeling the collection job break-in duration according to the mapping includes:
and establishing a multiple linear regression model according to the first mapping relation, the second mapping relation and the third mapping relation so as to model the input duration of the acquisition operation.
5. A modeling device for collecting operation investment duration is characterized by being applied to the collection operation process of map data and comprising the following steps:
the first determination module is used for determining the parameter value of the parameter associated with the acquisition operation input duration;
the second determination module is used for determining the mapping relation between the input duration and the associated parameters according to the parameter values of the associated parameters;
the modeling module is used for modeling the acquisition operation investment duration according to the mapping relation;
further comprising:
the acquisition module is used for acquiring real-time data of the acquisition operation input duration;
the updating module is used for updating the mapping relation between the investment duration and the associated parameters according to the real-time data, wherein a back propagation neural network model is adopted for carrying out iterative updating on the mapping relation, the back propagation neural network model comprises training samples, a feed-in input layer, a hidden layer and an output layer, each layer is in weighted connection with each other through weights, the back propagation neural network model is adopted for comparing the network predicted value of each sample data with the real-time data for learning, and the weights are modified for each sample data so that the mean square error between the network predicted value and the real-time data is minimum;
the associated parameters include: the first determining module is specifically configured to:
determining the parameter value of the day length parameter of each region and each month in one year to obtain a plurality of day length values corresponding to each region;
the second determining module is specifically configured to:
acquiring sample data of the invested time;
and determining a first mapping relation between the input duration of each region and the day length parameter according to the sample data and the corresponding day length values.
6. Modeling apparatus for collecting a length of work input according to claim 5, characterized in that said correlation parameters further include: in a plurality of regions where the collection job is executed, a weather type enumeration and a weather attribute enumeration of weather of each region, the second determining module is further configured to:
combining each weather type in the weather type enumeration and each weather attribute in the weather attribute enumeration to obtain a plurality of combinations;
determining a weight corresponding to each combination of the plurality of combinations from the plurality of combinations and the sample data;
and determining a second mapping relation between the investment duration and the weather of each region according to the weight corresponding to each combination.
7. Modeling apparatus for collecting a length of work input according to claim 6, characterized in that said correlation parameters further include: a temperature extremum for each of a plurality of zones in which the collection is performed, the second determining module further configured to:
determining a distribution function between the invested time and the temperature of each region according to the sample data of the invested time;
and determining a third mapping relation between the input duration and the temperature extreme value according to the distribution function.
8. The modeling apparatus for collecting work-on duration as recited in claim 7, wherein the modeling module is specifically configured to:
and establishing a multiple linear regression model according to the first mapping relation, the second mapping relation and the third mapping relation so as to model the input duration of the acquisition operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610876791.3A CN106384205B (en) | 2016-09-30 | 2016-09-30 | Modeling method and device for collecting operation input duration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610876791.3A CN106384205B (en) | 2016-09-30 | 2016-09-30 | Modeling method and device for collecting operation input duration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106384205A CN106384205A (en) | 2017-02-08 |
| CN106384205B true CN106384205B (en) | 2020-03-03 |
Family
ID=57937166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610876791.3A Active CN106384205B (en) | 2016-09-30 | 2016-09-30 | Modeling method and device for collecting operation input duration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106384205B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107153891B (en) * | 2017-05-10 | 2022-02-18 | 百度在线网络技术（北京）有限公司 | Region transfer scheduling method, device, equipment and storage medium |
| CN113723755A (en) * | 2021-07-28 | 2021-11-30 | 叶红 | Natural resource is built storehouse and is used field exploration management system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8341195B1 (en) * | 2007-10-04 | 2012-12-25 | Corbis Corporation | Platform for managing media assets for multi-model licensing over multi-level pricing and asset grouping |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8399827B1 (en) * | 2007-09-10 | 2013-03-19 | Cedars-Sinai Medical Center | Mass spectrometry systems |
| CN101482941A (en) * | 2008-01-09 | 2009-07-15 | 新奥(廊坊)燃气技术研究发展有限公司 | Urban gas daily load prediction method |
| CN105488317B (en) * | 2014-09-17 | 2018-11-16 | 日本电气株式会社 | System and method for predicting air quality |
| CN105608333B (en) * | 2016-01-26 | 2018-04-03 | 广东电网有限责任公司电力科学研究院 | A kind of meteorological sensitive electricity method for digging for considering multizone difference |
-
2016
- 2016-09-30 CN CN201610876791.3A patent/CN106384205B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8341195B1 (en) * | 2007-10-04 | 2012-12-25 | Corbis Corporation | Platform for managing media assets for multi-model licensing over multi-level pricing and asset grouping |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106384205A (en) | 2017-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110363327B (en) | ConvLSTM and 3D-CNN-based short rainfall prediction method | |
| Tariq et al. | Land change modeler and CA-Markov chain analysis for land use land cover change using satellite data of Peshawar, Pakistan | |
| CN111665575B (en) | Medium-and-long-term rainfall grading coupling forecasting method and system based on statistical power | |
| Aburas et al. | Monitoring and assessment of urban growth patterns using spatio-temporal built-up area analysis | |
| Veenhuis | Spread calibration of ensemble MOS forecasts | |
| CN110276477B (en) | Flood forecasting method based on hierarchical Bayesian network and incremental learning | |
| CN112285807A (en) | Meteorological information prediction method and device | |
| CN107563554A (en) | A kind of screening technique for counting the NO emissions reduction model prediction factor | |
| CN110968929A (en) | Prediction method, device and electronic equipment for wind speed of wind farm | |
| CN115129802B (en) | A population spatialization method based on multi-source data and ensemble learning | |
| CN116451514A (en) | Bridge structure state evaluation method and device and electronic equipment | |
| Chen et al. | Combining stochastic weather generation and ensemble weather forecasts for short-term streamflow prediction | |
| CN106384205B (en) | Modeling method and device for collecting operation input duration | |
| Martín et al. | Analysis of wind power productions by means of an analog model | |
| Mangaraj et al. | A Markov chain analysis of daily rainfall occurrence at western Orissa of India | |
| Le et al. | Evaluating the utility of IPCC AR4 GCMs for hydrological application in South Korea | |
| CN113742929A (en) | Data quality evaluation method for grid weather live | |
| de Lima et al. | An operational dynamical neuro-forecasting model for hydrological disasters | |
| CN115391746B (en) | Interpolation method, interpolation device, electronic device and medium for meteorological element data | |
| CN117274813A (en) | Prediction model for constructing urban forest temperature based on point cloud technology | |
| CN116822366A (en) | Construction of runoff pollution load calculation model and runoff pollution load calculation method | |
| CN116665046A (en) | A method, system, equipment and medium for evaluating vegetation phenological change trends | |
| Jeong et al. | A hybrid approach to improvement of watershed water quality modeling by coupling process–based and deep learning models | |
| Lohani | Rainfall-Runoff Analysis and Modelling | |
| Ansa Thasneem et al. | Quantification of uncertainties in streamflow extremes in the Chaliyar river basin, India under climate change |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200619 Address after: 100085 Beijing, Haidian District, No. ten on the ground floor, No. 10 Baidu building, layer three Co-patentee after: Beijing long Fang Wanfang Technology Co.,Ltd. Patentee after: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. Address before: 100085 Beijing, Haidian District, No. ten on the ground floor, No. 10 Baidu building, layer three Patentee before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing Patentee after: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. Patentee after: Beijing Baidu Zhitu Technology Co.,Ltd. Address before: 100085 Baidu Building, 10 Shangdi Tenth Street, Haidian District, Beijing Patentee before: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. Patentee before: Beijing long Fang Wanfang Technology Co.,Ltd. |