CN108596657A - Trees Value Prediction Methods, device, electronic equipment and storage medium - Google Patents
Trees Value Prediction Methods, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN108596657A CN108596657A CN201810320887.0A CN201810320887A CN108596657A CN 108596657 A CN108596657 A CN 108596657A CN 201810320887 A CN201810320887 A CN 201810320887A CN 108596657 A CN108596657 A CN 108596657A
- Authority
- CN
- China
- Prior art keywords
- trees
- predicted
- data
- value
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0278—Product appraisal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present disclosure discloses a kind of trees Value Prediction Methods, device, electronic equipment and storage medium.The method includes:Obtain the predictive factor of trees to be predicted;The predictive factor includes that the trees to be predicted foster data;The value of the trees to be predicted is predicted according to the predictive factor and prediction model;The prediction model is the model pre-established according to sample data.Pass through the embodiment of the present disclosure, trees, which are not necessarily to become a useful person completely, can be carried out price evaluation and then completes the corresponding economic behaviours such as transaction, mortgage, and the price evaluation in these economic behaviours accurately incorporates the influence factor fostered to final lumber quality so that the prediction of trees value is more accurate.
Description
Technical field
This disclosure relates to forest industry technical field, and in particular to a kind of trees Value Prediction Methods, device, electronic equipment
And storage medium.
Background technology
In forest industry, due to the limitation of trees nature growth cycle, the final Economic Benifits of trees are often sent out
Life is after trees are planted 5 to 20 years.This makes trees, and as the value assessment, transaction, mortgage of industrial crops, there are larger barriers
Hinder and uncertain.One side producer is since the pressure in fund period so that long-term investment can not be carried out, particularly with small-sized
Forest farm master is due to this uncertain so that it can not carry out effective investment decision.Another aspect artificial forest fosters to final wood
The price of material product is larger, the implementation of various Tending methods, for example, prune foster can determine the circle of final timber directly spend with
And the situation that scabs, these factors all determine that final timber becomes current evaluation price.
In current system for forestry, fostering for artificial forest is completed by manual operation, this to foster the data of record without
Method carries out accurate recording and tracking, therefore can not be to fostering process to carry out fining tracking and pipe to the influence that timber is grown
Reason.
Invention content
A kind of trees Value Prediction Methods of embodiment of the present disclosure offer, device, electronic equipment and storage medium.
In a first aspect, providing a kind of trees Value Prediction Methods in the embodiment of the present disclosure.
Obtain the predictive factor of trees to be predicted;The predictive factor includes that the trees to be predicted foster data;
The value of the trees to be predicted is predicted according to the predictive factor and prediction model;The prediction mould
Type is the model pre-established according to sample data.
Optionally, in the developmental process for fostering data to be included in the trees to be predicted to the trees to be predicted into
The historical data and current data that row records when fostering.
It is optionally, described that foster data include at least one of:
Strategy is fostered to what the trees to be predicted executed;
The trees to be predicted are executed and foster data after fostering strategy;
The standing forest data of environment where the trees to be predicted.
Optionally, the predictive factor of trees to be predicted is obtained, including:
Number is fostered by fostering the trees of strategy to foster automatically described in device acquisition the automatic execution of the trees to be predicted
According to;And/or
It is obtained by sensing device and fosters data described in the trees to be predicted.
Optionally, the value of the trees to be predicted is predicted according to the predictive factor and prediction model, is wrapped
It includes:
The type of the trees to be predicted is determined according to the predictive factor of the trees to be predicted;
The corresponding prediction model is obtained according to the type of the trees to be predicted;Wherein, different types of trees pair
The prediction model answered is different;
The predictive factor is input to the prediction model, prediction obtains the value of the trees to be predicted.
Optionally, the value of the trees to be predicted is predicted according to the predictive factor and prediction model, is wrapped
It includes:
After including currently fostering data and history that the predictive factor of data is fostered to be input to the prediction model, in advance
Measure the value in the trees future to be predicted.
Optionally, the prediction model is the machine learning regression model or machine trained in advance by training sample
Learning classification model;The training sample includes the predictive factor and labeled data of sample trees;The labeled data includes
Market value of the sample trees at least one period;Alternatively,
The prediction model is the non-machine learning regression model established by sample data;The sample data includes sample
The predictive factor and labeled data of this trees;The labeled data includes market of the sample trees at least one period
Value.
Optionally, the value of the prediction trees includes at least one of:
The value interval of the trees to be predicted;
The quality and grade of the trees to be predicted.
Optionally, the predictive factor further includes at least one of:The growth region of the trees to be predicted;It is described to wait for
The natural calamity that prediction trees live through;The fire that the trees to be predicted live through;The people that the trees to be predicted live through
To cut down behavior;The disease and insect information of the trees to be predicted.
Optionally, the trees to be predicted are single plant trees or more plants of trees.
Second aspect, the embodiment of the present disclosure propose a kind of trees value forecasting device, including:
Acquisition module is configured as obtaining the predictive factor of trees to be predicted;The predictive factor includes described to be predicted
Trees foster data;
Prediction module, be configured as according to the predictive factor and prediction model to the values of the trees to be predicted into
Row prediction;The prediction model is the model pre-established according to sample data.
Optionally, in the developmental process for fostering data to be included in the trees to be predicted to the trees to be predicted into
The historical data and current data that row records when fostering.
It is optionally, described that foster data include at least one of:
Strategy is fostered to what the trees to be predicted executed;
The trees to be predicted are executed and foster data after fostering strategy;
The standing forest data of environment where the trees to be predicted.
Optionally, the acquisition module, including:
First acquisition submodule is configured as fostering the trees of strategy automatic by executing the trees to be predicted automatically
It fosters and fosters data described in device acquisition;And/or
Second acquisition submodule is configured as obtaining by sensing device and fosters data described in the trees to be predicted.
Optionally, the prediction module, including:
Determination sub-module is configured as determining the kind of the trees to be predicted according to the predictive factor of the trees to be predicted
Class;
Third acquisition submodule is configured as obtaining the corresponding prediction mould according to the type of the trees to be predicted
Type;Wherein, the corresponding prediction model of different types of trees is different;
First prediction submodule is configured as the predictive factor being input to the prediction model, and prediction obtains described
The value of trees to be predicted.
Optionally, the prediction module, including:
Second prediction submodule is configured as including the predictive factor for currently fostering data and history to foster data
After being input to the prediction model, the value in the trees future to be predicted is predicted.
Optionally, the prediction model is the machine learning regression model or machine trained in advance by training sample
Learning classification model;The training sample includes the predictive factor and labeled data of sample trees;The labeled data includes
Market value of the sample trees at least one period;Alternatively,
The prediction model is the non-machine learning regression model established by sample data;The sample data includes sample
The predictive factor and labeled data of this trees;The labeled data includes market of the sample trees at least one period
Value.
Optionally, the value of the prediction trees includes at least one of:
The value interval of the trees to be predicted;
The quality and grade of the trees to be predicted.
Optionally, the predictive factor further includes at least one of:The growth region of the trees to be predicted;It is described to wait for
The natural calamity that prediction trees live through;The fire that the trees to be predicted live through;The people that the trees to be predicted live through
To cut down behavior;The disease and insect information of the trees to be predicted.
Optionally, the trees to be predicted are single plant trees or more plants of trees.
The function can also execute corresponding software realization by hardware realization by hardware.The hardware or
Software includes one or more modules corresponding with above-mentioned function.
In a possible design, the structure of trees value forecasting device includes memory and processor, described to deposit
Reservoir supports trees value forecasting device to execute trees Value Prediction Methods in above-mentioned first aspect for storing one or more
Computer instruction, the processor is configurable for executing the computer instruction stored in the memory.The trees
Value forecasting device can also include communication interface, for trees value forecasting device and other equipment or communication.
The third aspect, the embodiment of the present disclosure provide a kind of electronic equipment, including memory and processor;Wherein, described
Memory is for storing one or more computer instruction, wherein one or more computer instruction is by the processor
It executes to realize the method and step described in first aspect.
Fourth aspect, the embodiment of the present disclosure provide a kind of computer readable storage medium, pre- for storing trees value
The computer instruction used in device is surveyed, it includes by executing in above-mentioned first aspect based on involved by trees Value Prediction Methods
Calculation machine instructs.
The technical solution that the embodiment of the present disclosure provides can include the following benefits:
The embodiment of the present disclosure is by attribute information to trees and data is fostered to be monitored and track, and establishes rational
Prediction model, and using the attribute information of prediction model and trees to be predicted and foster data to be worth it to predict.It is logical
The embodiment of the present disclosure is crossed, trees, which are not necessarily to become a useful person completely, can be carried out price evaluation and then complete the corresponding economy such as merchandise, mortgage
Behavior, and the price evaluation in these economic behaviours accurately incorporates the influence factor fostered to final lumber quality, makes
The prediction for obtaining trees value is more accurate.
It should be understood that above general description and following detailed description is only exemplary and explanatory, not
The disclosure can be limited.
Description of the drawings
In conjunction with attached drawing, by the detailed description of following non-limiting embodiment, the other feature of the disclosure, purpose and excellent
Point will be apparent.In the accompanying drawings:
Fig. 1 shows the flow chart of the trees Value Prediction Methods according to one embodiment of the disclosure;
Fig. 2 shows the flow charts of the step S102 of embodiment according to Fig. 1;
Fig. 3 shows the structure diagram of the trees value forecasting device according to one embodiment of the disclosure;
Fig. 4 is adapted for the knot of the electronic equipment for realizing the trees Value Prediction Methods according to one embodiment of the disclosure
Structure schematic diagram.
Specific implementation mode
Hereinafter, the illustrative embodiments of the disclosure will be described in detail with reference to the attached drawings, so that those skilled in the art can
Easily realize them.In addition, for the sake of clarity, the portion unrelated with description illustrative embodiments is omitted in the accompanying drawings
Point.
In the disclosure, it should be appreciated that the term of " comprising " or " having " etc. is intended to refer to disclosed in this specification
Feature, number, step, behavior, the presence of component, part or combinations thereof, and be not intended to exclude other one or more features,
Number, step, behavior, component, part or combinations thereof there is a possibility that or be added.
It also should be noted that in the absence of conflict, the feature in embodiment and embodiment in the disclosure
It can be combined with each other.The disclosure is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the flow chart of the trees Value Prediction Methods according to one embodiment of the disclosure.As shown in Figure 1, described
Trees Value Prediction Methods include the following steps S101-S102:
In step S101, the predictive factor of trees to be predicted is obtained;The predictive factor includes the trees to be predicted
Foster data;
In step s 102, the value of the trees to be predicted is carried out according to the predictive factor and prediction model pre-
It surveys;The prediction model is the model pre-established according to sample data.
In the present embodiment, trees to be predicted can be trees in artificial forest or other pass through the trees of constructed floating bed.
Predictive factor may include fostering data, and the data of fostering of trees to be predicted include relevant fostering number with trees to be predicted value
According to, such as foster relevant data, intermediate cutting that relevant data etc., pruning is fostered to foster phase the pruning that trees to be predicted were implemented
The data of pass may include the branch parameter of trimming, Mowing frequency, stay a parameter, notch image data etc. after trimming.It is to be predicted
The predictive factor of trees can also include the standing forests data such as the density of crop, site quality.
In one embodiment, predict that the predictive factor of trees can also include the attribute information of trees to be predicted.It is to be predicted
The attribute information of trees includes being worth relevant self attributes, such as the straight degree of seeds, the age of tree, circle, trees ruler with trees to be predicted
Very little, outer shape feature, defects in timber, pest and disease damage situation etc., seeds can be any seeds, and the age of tree can be based on predictive value
The place time determines that the straight degree of circle is also an important factor for influencing trees value;Trees size may include the diameter of a cross-section of a tree trunk 1.3 meters above the ground, tree it is high, outside
Portion's shape feature may include taperingness, curvature etc., and defects in timber may include that knot (includes in trunk or major branch timber
Branch part) and the factors such as microorganism, moth influence and a large amount of defective woods etc. for generating, pest and disease damage situation can influence to set
Important one of the factor of wood later growing state and value forecasting.
The data of fostering of trees to be predicted can foster device to adopt automatically automatically by trees during constructed floating bed
Collection obtains, can also be treat foster trees execute foster strategy after record.Other predictive factors of trees to be predicted
Such as attribute information, stand facters etc. can also foster device to be collected during fostering automatically by trees.
It can include mobile device, control device, sensing device and foster executive device that trees foster device automatically
Machine automatization equipment can acquire the sensing data of trees by sensing device, and further by control device to sensing data
Strategy is fostered in planning after being handled, and then controls mobile device and executive device is fostered to execute corresponding trees and foster strategy.
In one embodiment, prediction model can be the model pre-established according to sample data, and such as regression model divides
Class model etc..Regression model can be machine learning regression model, can also be non-machine learning regression model.For example, prediction
Model can be neural network, k nearest neighbour methods, perceptron, naive Bayesian method, decision tree, logistical regression model, SVM,
The machine learning regression model such as adaBoost, Bayesian network can also be such as polynomial regression, Stepwise
Regression successive Regressions, Ridge Regression ridge regressions, the recurrence of Lasso Regression lasso tricks, ElasticNet
The non-machine learning regression models such as recurrence.The specifically used type of prediction model can be selected according to actual conditions, herein not
It is limited.
In one embodiment, sample data may include the predictive factor of sample trees and the value of sample trees, i.e.,
Predictive factor only includes when fostering data, and sample data includes that sample trees foster data and value, and predictive factor is in addition to comforting
Also include other data in addition to fostering data in sample data when to educate data further include other data.Prediction model is then foundation
The sample data of multiple sample trees constantly updates the finally obtained model of its parameter.
In one embodiment, different types of since the value assessment mode of different types of trees is different
Trees can correspond to different prediction models.
There are many ways to assessing trees value in prior art, such as utilize the Volume table of the diameter of a cross-section of a tree trunk 1.3 meters above the ground and the high data organization of tree
The binary nonlinear regression model that (timber assortment table) is established.However, the trees that the volume of timber is equal, due to Stem quality (such as knot, point
Degree of cutting, curvature, form) difference, the corresponding volume of timber of the timber variety that can be provided (such as sawn timber, veneer) has prodigious
Difference causes its economic value also to differ.And the positive correlation of the diameter of a cross-section of a tree trunk 1.3 meters above the ground and its volume recovery also has special circumstances:Tree breast-height diameter
Mean that the age of tree is bigger more greatly, tree body can contain a large amount of defective woods, and to reduce its volume recovery, and trees foster, and can monitor
The defect of tree body.Knot is the branch part for including in trunk or major branch timber, is that a kind of of generally existing in timber lacks naturally
It falls into, can determine the quality of timber, and the knot or branch defect of trees can then be dispelled by fostering to prune, and then improve the circle of trees
Straight degree.Therefore, foster data that can more accurately assess timber value using complete.
In an optional realization method of the present embodiment, the growth for fostering data to be included in the trees to be predicted
The historical data and current data recorded when being fostered in the process to the trees to be predicted.
The current value of trees to be predicted and the value of future N foster strategy with what it was carried out in growth course
Closely, this is because different pruning strategies may leave different traces on trees, such as tree may be left after pruning
Section, and this has a certain impact to the value of trees.Therefore it can consider that trees currently foster simultaneously when predicting trees value
Data and history foster data, and the value of trees can be more accurately predicted out in this way.
In an optional realization method of the present embodiment, described to foster data include at least one of:
Strategy is fostered to what the trees to be predicted executed;
The trees to be predicted are executed and foster data after fostering strategy;
The standing forest data of environment where the trees to be predicted.
In the optional realization method, it includes that pruning is fostered, intermediate cutting is fostered to foster strategy;Economic value prediction can be with
In conjunction with strategy is fostered, due to fostering data according to fostering strategy to foster to obtain, it is the sensing number by trees to foster strategy
It is obtained according to planning.Foster data may include include image data, such as the height of trees, the diameter of a cross-section of a tree trunk 1.3 meters above the ground, tree crown and leaf form,
The form of branch and leaf, trunk circle directly spend, arboreal growth situation, shoot growth situation, the image feature informations such as age of tree.Into
One step, the image data of pruning port can include the potential burl feature of trees.The image data can be used and calculated
Machine vision is identified with the method that machine vision is combined.Computer vision, the analysis mainly confronted, such as classification are known
Not, it for accuracy requirement, in general wants lower, is suitble to use machine learning.And machine vision, mainly stress to amount
It analyzes, for example removes the diameter of one part of measurement by vision, it is in general, very high to accuracy requirement, be not suitable for using machine
Device learns.Therefore, by computer vision, matter can be obtained from image data fosters data.It, can be with and by machine vision
Data are fostered from the image data amount of obtaining.Standing forest data can foster the collected sensing data of device to obtain automatically by trees
It arrives, such as the density of crop, site quality etc..
In an optional realization method of the present embodiment, the step S101, that is, obtain the predictions of trees to be predicted because
The step of son, further comprises the steps:
Number is fostered by fostering the trees of strategy to foster automatically described in device acquisition the automatic execution of the trees to be predicted
According to;And/or
It is obtained by sensing device and fosters data described in the trees to be predicted.
In the optional realization method, foster data device can be fostered to obtain automatically by trees, trees comfort automatically
The sensing data of trees can be acquired during fostering automatically by educating device, including image data, on the spot environmental data etc., trees from
It is dynamic foster device can also be recorded in foster during taken foster strategy etc..Certainly, in other embodiments, can also
It is obtained by individual sensing device, such as imaging sensor, is made a reservation for by being arranged around unmanned plane or trees to be fostered
Imaging sensor at position obtains the image information of trees to be predicted, and is extracted from image information and foster data accordingly.
Can certainly foster that device acquires and record automatically in conjunction with trees foster data, foster strategy etc. as prediction because
Son.
In an optional realization method of the present embodiment, as shown in Fig. 2, the step S102, i.e., according to the prediction
The step of factor and prediction model predict the value of the trees to be predicted, further comprises the steps S201-
S203:
In step s 201, the type of the trees to be predicted is determined according to the predictive factor of the trees to be predicted;
In step S202, the corresponding prediction model is obtained according to the type of the trees to be predicted;Wherein, different
The corresponding prediction model of trees of type is different;
In step S203, the predictive factor is input to the prediction model, prediction obtains the trees to be predicted
Value.
In the optional realization method, during prediction, current trees to be predicted can be determined according to predictive factor
Type, different types of trees can correspond to different prediction models;After determining tree families, selected according to tree families
Corresponding prediction model, and predictive factor is input to prediction model and then predicts to be worth accordingly.
In an optional realization method of the present embodiment, the step S102, i.e., according to the predictive factor and in advance
The step of model predicts the value of the trees to be predicted is surveyed, is further comprised the steps:
After including currently fostering data and history that the predictive factor of data is fostered to be input to the prediction model, in advance
Measure the value in the trees future to be predicted.
In the optional realization method, prediction model can both predict the current economic value of trees to be predicted, may be used also
To predict the economic value of future N.For example, prediction model, which inputs the 1st year, fosters data, the 1st year can be predicted to N
Economic value;Input fosters data in first 2 years, can predict the 2nd year economic value to N;…;I before input
Data are fostered, can predict 1 year economic value to N, wherein N is the time limit of trees maturation felling.Preceding i's comforts
The form input that matrix may be used in data is educated, such as { First Year fosters data;Second year fosters data;……;(i-1)-th
Year fosters data;1 year foster data }.
In an optional realization method of the present embodiment, the prediction model is to be trained in advance by training sample
Machine learning regression model or machine learning classification model;The training sample includes the predictive factor and mark of sample trees
Note data;The labeled data includes market value of the sample trees at least one period;Alternatively,
The prediction model is the non-machine learning regression model established by sample data;The sample data includes sample
The market value of the predictive factor of this trees and corresponding trees sample.
In the optional realization method, machine learning regression model, such as neural network etc. passes through the training of training sample
It afterwards, can be according to the economic value for predicting trees to be predicted with the same type of predictive factor of data in training sample.Instruction
Practice the predictive factor and labeled data that sample may include sample trees, labeled data may include sample trees at least one
Market value in period;Data type included by the predictive factor of training sample and the trees to be predicted during prediction
Predictive factor included by data type it is identical.Prediction model can also be classification regression model,
Below by taking neural network as an example, illustrate training and the prediction process of lower prediction model:
It is trained the mark of sample first.The training sample of mark is:History and currently accumulate include foster data
Predictive factor, mark the timber current year to N market evaluation be worth, composition labeled data.Then a nerve net is trained
Network.After largely training, the economic value of the neural network forecast timber is used.
Training method
Labeled data collection input neural network is trained, for neural network, inputs and fosters number for timber
According to adjusting the weight of neural network, you can the corresponding economic value of output timber.
In this embodiment, the method that neural network makes regression forecasting is to change the activation primitive and cost letter of output layer
Number, linear regression model (LRM) is made by output layer.It is linear relationship, front since linear regression requires dependent variable and independent variable
Hidden layer can regard the expression of space for primitive character being mapped to one and dependent variable linear correlation as.
Prediction for forest economic value, in addition to using the prediction model returned, the prediction mould of classification can also be used
Type.In one embodiment, forest economic value is subjected to section classification.The mark sample of training data is:To history and
The timber currently accumulated fosters data, and the market evaluation value interval for marking timber current year to N is classified.In this way after training
Forest economic value can be predicted as different classifications section by disaggregated model, such as { nanmu, the 5th year economic value, economic value area
Between 3, { jujube wood, the 8th year economic value, economic value section 2 }, { sandalwood, the 3rd year economic value, economic value section 4 }.
Prediction model can also be the non-machine learning regression model established by sample data, such as pass through foundation side
Journey, and using the predictive factor in labeled data as independent variable, using the market value of sample trees as dependent variable, by continuous
Adjust the weight parameter of independent variable in equation, the value and sample of the final dependent variable that the equation is obtained based on predictive factor
The market value of this trees reaches unanimity.
In an optional realization method of the present embodiment, the value of the prediction trees includes at least one of:
The value interval of the trees to be predicted;
The quality and grade of the trees to be predicted.
In the optional realization method, the trees value that prediction model is predicted can be value interval, such as predict
Go out the maximum value, intermediate value and minimum value of trees to be predicted.Final conclusion of the business economic value is fallen between a minimum value and a maximum value, average
Value is intermediate value.The influence that economic policy wave zone comes can be resisted in this way.
Prediction model can also predict the quality and grade of trees to be predicted.The quality index of trees can be by the outside of trees
Characteristic quantification, to evaluate the grade of trees.The tree features of quantization may include:Tree crown rank, trunk curvature, branch number
Amount, branching, rotten and scar.And trees to be predicted can be divided into multiple grades by the tree features of above-mentioned quantization, such as
Excellent, medium, low 3 grades.
In an optional realization method of the present embodiment, the predictive factor further includes at least one of:It is described to wait for
Predict the growth region of trees;The natural calamity that the trees to be predicted live through;The fire that the trees to be predicted live through;
The artificial felling behavior that the trees to be predicted live through.
In the optional realization method, there is certain influence in the growth region of trees to be predicted to the economic value of trees, because
Growth and value to plant same timber in different geographical may have bigger difference.And trees to be predicted are subjected to from
Right disaster, fire or artificial unreasonable felling etc. can also generate its economic value certain influence.Therefore it is waited in prediction pre-
When the economic value of assize wood, it may be considered that above-mentioned factor.Predictive factor may include a variety of data, and different data is for economy
The influence of value is different, can be that each predictive factor assigns different weighted values by empirical value or historical data, so as to
The economic value of trees can more reasonably be predicted.
In an optional realization method of the present embodiment, the trees to be predicted are single plant trees or more plants of trees.
During prediction, prediction model can predict the economic value of an individual trees, can also be in full wafer forest
Multiple trees predicted.Economic value prediction for single plant trees, the input of prediction model can be the single plant trees
Foster data.And for more plants so the economic value of group strain trees prediction, the input of prediction model can also include standing forest
The factor fosters data.Stand facters may include the density of crop, site quality etc., such as trees composition, woods layer, crown diameter (hat
Width), tree height, standing forest strain number, lower wood canopy density and standing tree position.More economic valences of plant, group strain trees are predicted using stand facters
The method and embodiment of value and the method and embodiment class for fostering data prediction single plant forest economic value of single plant trees
Seemingly.
Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.
Fig. 3 shows that the structure diagram of the trees value forecasting device according to one embodiment of the disclosure, the device can lead to
Cross being implemented in combination with as some or all of of electronic equipment of software, hardware or both.As shown in figure 3, the trees valence
Value prediction meanss include acquisition module 301 and prediction module 302:
Acquisition module 301 is configured as obtaining the predictive factor of trees to be predicted;The predictive factor waits for pre- including described in
Assize wood fosters data;
Prediction module 302 is configured as the valence to the trees to be predicted according to the predictive factor and prediction model
Value is predicted;The prediction model is the model pre-established according to sample data.
In an optional realization method of the present embodiment, the growth for fostering data to be included in the trees to be predicted
The historical data and current data recorded when being fostered in the process to the trees to be predicted.
In an optional realization method of the present embodiment, described to foster data include at least one of:
Strategy is fostered to what the trees to be predicted executed;
The trees to be predicted are executed and foster data after fostering strategy;
The standing forest data of environment where the trees to be predicted.
In an optional realization method of the present embodiment, the acquisition module, including:
First acquisition submodule is configured as fostering the trees of strategy automatic by executing the trees to be predicted automatically
It fosters and fosters data described in device acquisition;And/or
Second acquisition submodule is configured as obtaining by sensing device and fosters data described in the trees to be predicted.
In an optional realization method of the present embodiment, the prediction module, including:
Determination sub-module is configured as determining the kind of the trees to be predicted according to the predictive factor of the trees to be predicted
Class;
Third acquisition submodule is configured as obtaining the corresponding prediction mould according to the type of the trees to be predicted
Type;Wherein, the corresponding prediction model of different types of trees is different;
First prediction submodule is configured as the predictive factor being input to the prediction model, and prediction obtains described
The value of trees to be predicted.
In an optional realization method of the present embodiment, the prediction module, including:
Second prediction submodule is configured as including the predictive factor for currently fostering data and history to foster data
After being input to the prediction model, the value in the trees future to be predicted is predicted.
In an optional realization method of the present embodiment, the prediction model is to be trained in advance by training sample
Machine learning regression model or machine learning classification model;The training sample includes the predictive factor and mark of sample trees
Note data;The labeled data includes market value of the sample trees at least one period;Alternatively,
The prediction model is the non-machine learning regression model established by sample data;The sample data includes sample
The predictive factor and labeled data of this trees;The labeled data includes market of the sample trees at least one period
Value.
In an optional realization method of the present embodiment, the value of the prediction trees includes at least one of:
The value interval of the trees to be predicted;
The quality and grade of the trees to be predicted.
In an optional realization method of the present embodiment, the predictive factor further includes at least one of:It is described to wait for
Predict the growth region of trees;The natural calamity that the trees to be predicted live through;The fire that the trees to be predicted live through;
The artificial felling behavior that the trees to be predicted live through;The disease and insect information of the trees to be predicted.
In an optional realization method of the present embodiment, the trees to be predicted are single plant trees or more plants of trees.
The trees proposed in trees value forecasting device and embodiment illustrated in fig. 1 and related embodiment in above-described embodiment
Value Prediction Methods correspond to unanimously, and detail can be found in the above-mentioned description in embodiment illustrated in fig. 1 and related embodiment,
This is repeated no more.
Fig. 4 is adapted for the structure of the electronic equipment for realizing the trees Value Prediction Methods according to disclosure embodiment
Schematic diagram.
As shown in figure 4, electronic equipment 400 includes central processing unit (CPU) 401, it can be according to being stored in read-only deposit
Program in reservoir (ROM) 402 is held from the program that storage section 408 is loaded into random access storage device (RAM) 403
Various processing in the above-mentioned embodiment shown in FIG. 1 of row.In RAM403, be also stored with electronic equipment 400 operate it is required
Various programs and data.CPU401, ROM402 and RAM403 are connected with each other by bus 404.Input/output (I/O) interface
405 are also connected to bus 404.
It is connected to I/O interfaces 405 with lower component:Importation 406 including keyboard, mouse etc.;It is penetrated including such as cathode
The output par, c 407 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.;Storage section 408 including hard disk etc.;
And the communications portion 409 of the network interface card including LAN card, modem etc..Communications portion 409 via such as because
The network of spy's net executes communication process.Driver 410 is also according to needing to be connected to I/O interfaces 405.Detachable media 411, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 410, as needed in order to be read from thereon
Computer program be mounted into storage section 408 as needed.
Particularly, according to embodiment of the present disclosure, it is soft to may be implemented as computer above with reference to Fig. 1 methods described
Part program.For example, embodiment of the present disclosure includes a kind of computer program product comprising be tangibly embodied in and its readable
Computer program on medium, the computer program include the program code of the method for executing Fig. 1.In such implementation
In mode, which can be downloaded and installed by communications portion 409 from network, and/or from detachable media
411 are mounted.
Flow chart in attached drawing and block diagram, it is illustrated that according to the system, method and computer of the various embodiments of the disclosure
The architecture, function and operation in the cards of program product.In this regard, each box in course diagram or block diagram can be with
A part for a module, section or code is represented, a part for the module, section or code includes one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it wants
It is noted that the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, Ke Yiyong
The dedicated hardware based system of defined functions or operations is executed to realize, or can be referred to specialized hardware and computer
The combination of order is realized.
Being described in unit or module involved in disclosure embodiment can be realized by way of software, also may be used
It is realized in a manner of by hardware.Described unit or module can also be arranged in the processor, these units or module
Title do not constitute the restriction to the unit or module itself under certain conditions.
As on the other hand, the disclosure additionally provides a kind of computer readable storage medium, the computer-readable storage medium
Matter can be computer readable storage medium included in device described in the above embodiment;Can also be individualism,
Without the computer readable storage medium in supplying equipment.There are one computer-readable recording medium storages or more than one journey
Sequence, described program is used for executing by one or more than one processor is described in disclosed method.
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from the inventive concept, it is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed in the disclosure
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (10)
1. a kind of trees Value Prediction Methods, which is characterized in that including:
Obtain the predictive factor of trees to be predicted;The predictive factor includes that the trees to be predicted foster data;
The value of the trees to be predicted is predicted according to the predictive factor and prediction model;The prediction model is
The model pre-established according to sample data.
2. trees Value Prediction Methods according to claim 1, which is characterized in that described that data is fostered to be included in described wait for
Predict the historical data and current data that are recorded when being fostered to the trees to be predicted in the developmental process of trees.
3. trees Value Prediction Methods according to claim 1, which is characterized in that it is described foster data include it is following at least
One of:
Strategy is fostered to what the trees to be predicted executed;
The trees to be predicted are executed and foster data after fostering strategy;
The standing forest data of environment where the trees to be predicted.
4. according to claim 1-3 any one of them trees Value Prediction Methods, which is characterized in that obtain trees to be predicted
Predictive factor, including:
Data are fostered by fostering the trees of strategy to foster automatically described in device acquisition the automatic execution of the trees to be predicted;
And/or
It is obtained by sensing device and fosters data described in the trees to be predicted.
5. according to claim 1-3 any one of them trees Value Prediction Methods, which is characterized in that according to the predictive factor
And prediction model predicts the value of the trees to be predicted, including:
The type of the trees to be predicted is determined according to the predictive factor of the trees to be predicted;
The corresponding prediction model is obtained according to the type of the trees to be predicted;Wherein, different types of trees are corresponding
Prediction model is different;
The predictive factor is input to the prediction model, prediction obtains the value of the trees to be predicted.
6. according to claim 1-3 any one of them trees Value Prediction Methods, which is characterized in that according to the predictive factor
And prediction model predicts the value of the trees to be predicted, including:
After including currently fostering data and history that the predictive factor of data is fostered to be input to the prediction model, predict
The value in the trees future to be predicted.
7. according to claim 1-3 any one of them trees Value Prediction Methods, which is characterized in that the prediction model is logical
Cross the machine learning regression model or machine learning classification model that training sample was trained in advance;The training sample includes sample
The predictive factor and labeled data of this trees;The labeled data includes market of the sample trees at least one period
Value;Alternatively,
The prediction model is the non-machine learning regression model established by sample data;The sample data includes sample tree
The predictive factor and labeled data of wood;The labeled data includes market price of the sample trees at least one period
Value.
8. a kind of trees value forecasting device, which is characterized in that including:
Acquisition module is configured as obtaining the predictive factor of trees to be predicted;The predictive factor includes the trees to be predicted
Foster data;
Prediction module is configured as carrying out the value of the trees to be predicted according to the predictive factor and prediction model pre-
It surveys;The prediction model is the model pre-established according to sample data.
9. a kind of electronic equipment, which is characterized in that including memory and processor;Wherein,
The memory is for storing one or more computer instruction, wherein one or more computer instruction is by institute
Processor is stated to execute to realize claim 1-7 any one of them method and steps.
10. a kind of computer readable storage medium, is stored thereon with computer instruction, which is characterized in that the computer instruction quilt
Claim 1-7 any one of them method and steps are realized when processor executes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810320887.0A CN108596657A (en) | 2018-04-11 | 2018-04-11 | Trees Value Prediction Methods, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810320887.0A CN108596657A (en) | 2018-04-11 | 2018-04-11 | Trees Value Prediction Methods, device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108596657A true CN108596657A (en) | 2018-09-28 |
Family
ID=63621710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810320887.0A Pending CN108596657A (en) | 2018-04-11 | 2018-04-11 | Trees Value Prediction Methods, device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108596657A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109249300A (en) * | 2018-10-25 | 2019-01-22 | 北京木业邦科技有限公司 | Timber processing control method, device, electronic equipment and storage medium |
CN109447836A (en) * | 2018-11-13 | 2019-03-08 | 何沙沙 | A kind of ecological garden management method and system based on Internet of Things |
CN109829372A (en) * | 2018-12-26 | 2019-05-31 | 北京木业邦科技有限公司 | Trees intermediate cutting method, apparatus, electronic equipment and computer readable storage medium |
CN110059561A (en) * | 2019-03-18 | 2019-07-26 | 北京木业邦科技有限公司 | A kind of method and device of Forest Growth modeling and prediction based on machine learning |
CN111982905A (en) * | 2020-08-26 | 2020-11-24 | 杭州宣迅电子科技有限公司 | Wood quality intelligent detection system based on industrial big data image analysis |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102265287A (en) * | 2008-12-24 | 2011-11-30 | 韦尔豪泽Nr公司 | Method and apparatus for monitoring tree growth |
CN102667816A (en) * | 2009-12-22 | 2012-09-12 | 韦尔豪泽Nr公司 | Method and apparatus for predicting information about trees in images |
CN104166748A (en) * | 2014-05-04 | 2014-11-26 | 中南林业科技大学 | Forest stand growth modeling method based on relation model |
CN105808963A (en) * | 2016-03-24 | 2016-07-27 | 北京林业大学 | Method for determining wood ages by adopting model method |
CN105894178A (en) * | 2016-03-24 | 2016-08-24 | 北京林业大学 | Afforestation operation method for optimal rotation of timber plantation |
CN106294990A (en) * | 2016-08-08 | 2017-01-04 | 青岛智能产业技术研究院 | Tree breast-height diameter Forecasting Methodology |
CN106407880A (en) * | 2015-07-31 | 2017-02-15 | 埃森哲环球服务有限公司 | Inventory, growth, and risk prediction using image processing |
CN106408132A (en) * | 2016-09-30 | 2017-02-15 | 深圳前海弘稼科技有限公司 | Method and device of crop yield prediction based on plantation device |
CN106442382A (en) * | 2016-07-15 | 2017-02-22 | 中国林业科学研究院热带林业研究所 | Method for rapid prediction of Eucapyptus urophylla * E. tereticornis wood basic density |
CN106645563A (en) * | 2016-09-30 | 2017-05-10 | 深圳前海弘稼科技有限公司 | Disease and pest predicting method and device based on planting equipment |
US20180032883A1 (en) * | 2016-07-27 | 2018-02-01 | Facebook, Inc. | Socioeconomic group classification based on user features |
-
2018
- 2018-04-11 CN CN201810320887.0A patent/CN108596657A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102265287A (en) * | 2008-12-24 | 2011-11-30 | 韦尔豪泽Nr公司 | Method and apparatus for monitoring tree growth |
CN102667816A (en) * | 2009-12-22 | 2012-09-12 | 韦尔豪泽Nr公司 | Method and apparatus for predicting information about trees in images |
CN104166748A (en) * | 2014-05-04 | 2014-11-26 | 中南林业科技大学 | Forest stand growth modeling method based on relation model |
CN106407880A (en) * | 2015-07-31 | 2017-02-15 | 埃森哲环球服务有限公司 | Inventory, growth, and risk prediction using image processing |
CN105808963A (en) * | 2016-03-24 | 2016-07-27 | 北京林业大学 | Method for determining wood ages by adopting model method |
CN105894178A (en) * | 2016-03-24 | 2016-08-24 | 北京林业大学 | Afforestation operation method for optimal rotation of timber plantation |
CN106442382A (en) * | 2016-07-15 | 2017-02-22 | 中国林业科学研究院热带林业研究所 | Method for rapid prediction of Eucapyptus urophylla * E. tereticornis wood basic density |
US20180032883A1 (en) * | 2016-07-27 | 2018-02-01 | Facebook, Inc. | Socioeconomic group classification based on user features |
CN106294990A (en) * | 2016-08-08 | 2017-01-04 | 青岛智能产业技术研究院 | Tree breast-height diameter Forecasting Methodology |
CN106408132A (en) * | 2016-09-30 | 2017-02-15 | 深圳前海弘稼科技有限公司 | Method and device of crop yield prediction based on plantation device |
CN106645563A (en) * | 2016-09-30 | 2017-05-10 | 深圳前海弘稼科技有限公司 | Disease and pest predicting method and device based on planting equipment |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109249300A (en) * | 2018-10-25 | 2019-01-22 | 北京木业邦科技有限公司 | Timber processing control method, device, electronic equipment and storage medium |
CN109447836A (en) * | 2018-11-13 | 2019-03-08 | 何沙沙 | A kind of ecological garden management method and system based on Internet of Things |
CN109447836B (en) * | 2018-11-13 | 2021-01-29 | 广东城基生态科技股份有限公司 | Ecological garden management method and system based on Internet of things |
CN109829372A (en) * | 2018-12-26 | 2019-05-31 | 北京木业邦科技有限公司 | Trees intermediate cutting method, apparatus, electronic equipment and computer readable storage medium |
CN110059561A (en) * | 2019-03-18 | 2019-07-26 | 北京木业邦科技有限公司 | A kind of method and device of Forest Growth modeling and prediction based on machine learning |
CN111982905A (en) * | 2020-08-26 | 2020-11-24 | 杭州宣迅电子科技有限公司 | Wood quality intelligent detection system based on industrial big data image analysis |
CN111982905B (en) * | 2020-08-26 | 2021-02-19 | 北新国际木业有限公司 | Wood quality intelligent detection system based on industrial big data image analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108596657A (en) | Trees Value Prediction Methods, device, electronic equipment and storage medium | |
Reilly et al. | Irreversibility, uncertainty, and learning: portraits of adaptation to long-term climate change | |
Blanco et al. | The effect of forest owner decision-making, climatic change and societal demands on land-use change and ecosystem service provision in Sweden | |
Díaz-Yáñez et al. | Multifunctional comparison of different management strategies in boreal forests | |
Babatunde et al. | Impact of climatic change on agricultural product yield using k-means and multiple linear regressions | |
Edenius et al. | Utility of habitat suitability models as biodiversity assessment tools in forest management | |
Pukkala | Instructions for optimal any-aged forestry | |
JP2021125238A (en) | Future transaction information display program | |
Farnham et al. | National forest timber management over the past decade: A change in emphasis for the forest service? | |
Pukkala | Improved guidelines for any-aged forestry | |
Bahr et al. | Missing links in predicting berry sunburn in future vineyards | |
Zhang et al. | Agricultural cybernetics | |
Torres-Garcia et al. | Integral projection models and sustainable forest management of Agave inaequidens in Western Mexico | |
CN116361562A (en) | Knowledge recommendation method and system for agricultural industry Internet | |
Henry et al. | Governing taste: data, temporality and everyday kiwifruit dry matter performances | |
Anindya et al. | IoT Based Climate Prediction System Using Long Short-Term Memory (LSTM) Algorithm as Part of Smart Farming 4.0 | |
Susilo et al. | Decision Tree-Based Bok Choy Growth Prediction Model for Smart Farm | |
Manivasagam et al. | An efficient crop yield prediction using machine learning | |
Sigler et al. | Alaska regional action plan for the Southeastern Bering Sea: NOAA Fisheries Climate Science Strategy | |
Albayrak et al. | Development of Information System for Effcient Use of Nectar Resources and Increase Honey Yield per Colony. | |
Blattert et al. | Evaluation of growth simulators for forest management in terms of functionality and software structure using AHP | |
Rovira-Más | Agricultural Robotics | |
Coulon-Leroy et al. | The vine functioning pathway, a new conceptual representation | |
Hummel et al. | Ecological and financial assessment of late-successional reserve management | |
Mitsuda et al. | Comparison of growth responses to climatic conditions of Sugi (Cryptomeria japonica) and Hinoki (Chamaecyparis obtusa) using a carbon balance-based growth model |
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: 20180928 |