CN111815488A - Photovoltaic power generation learning assisting method based on decision tree - Google Patents
Photovoltaic power generation learning assisting method based on decision tree Download PDFInfo
- Publication number
- CN111815488A CN111815488A CN202010618881.9A CN202010618881A CN111815488A CN 111815488 A CN111815488 A CN 111815488A CN 202010618881 A CN202010618881 A CN 202010618881A CN 111815488 A CN111815488 A CN 111815488A
- Authority
- CN
- China
- Prior art keywords
- attribute
- decision tree
- characteristic
- power generation
- attributes
- 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
- 238000003066 decision tree Methods 0.000 title claims abstract description 37
- 238000010248 power generation Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000005611 electricity Effects 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a photovoltaic power generation learning assisting method based on a decision tree, which specifically comprises the following steps: s1, taking the characteristic attribute and the assistance grade of the historical assistance object as sample data in a training sample set S, and constructing a decision tree based on the sample data; s2, judging the assistance grade of the assistance object based on the decision tree; and S3, determining the power utilization auxiliary amount of each auxiliary grade based on the total daily power generation amount of the photovoltaic. The student characteristic attribute information is classified by using the decision tree, students with difficult life and excellent performance are accurately screened out, the economic benefit generated by photovoltaic power generation grid connection is directly transferred to the electricity utilization account of the corresponding student according to the campus power dispatching platform, the campus photovoltaic platform is used for generating electricity to bear partial or all electricity utilization of a dormitory, and a new learning-assisting mode is developed.
Description
Technical Field
The invention belongs to the technical field of self-learning, and particularly relates to a photovoltaic power generation learning assisting method based on a decision tree.
Background
With the continuous improvement of the support of the cultural education cause of China. As an important component of cultural construction, colleges and universities also develop rapidly, the number of recruits is increased year by year, and more people can enter colleges and universities for study. However, still some students are in poverty, so that the nation establishes various forms of college and university family economic difficulty student subsidy policies such as national awards, national study aids, national study loan aids, work and study fee reduction and avoidance in the advanced education stage.
The method is characterized in that the auxiliary study subsidy condition is artificially established, and the auxiliary study subsidy grade is determined in a voting mode or subjective judgment mode among students meeting the auxiliary study subsidy condition, wherein the assessment mode of the subsidy grade is relatively strong in subjectivity, and the problem of inaccurate assessment of the subsidy grade is easy to occur.
Disclosure of Invention
The invention provides a photovoltaic power generation learning assisting method based on a decision tree, which is used for determining the assistance grade of an assistance object based on the decision tree and improving the objectivity and accuracy of assessment of the assistance grade.
The invention discloses a photovoltaic power generation learning-assisting method based on a decision tree, which comprises the following steps:
s1, taking the characteristic attribute and the subsidy grade of the historical subsidy object as sample data in a training sample set S, and constructing a decision tree based on the sample data;
s2, judging the assistance grade of the assistance object based on the decision tree;
and S3, determining the power utilization auxiliary amount of each auxiliary grade based on the total daily power generation amount of the photovoltaic.
Further, the method for constructing the decision tree specifically comprises the following steps:
s11, calculating the category information entropy of the subsidy level according to the training sample set S;
s12, dividing each characteristic attribute into a plurality of sub-attributes, calculating the conditional entropy of the classification mode,
s13, taking the difference value between the category information entropy of the subsidy level and the conditional entropy of each classification mode as the attribute information gain under the corresponding classification mode;
s14, calculating attribute segmentation information quantity of the characteristic attribute;
s15, calculating the information gain rate of each characteristic attribute based on the attribute segmentation information quantity and the attribute information gain, taking the characteristic attribute with the highest information gain rate as a root node of the decision tree, if a specific sub-attribute under the characteristic attribute corresponds to a subsidy level, taking the sub-attribute under the characteristic attribute as a leaf node, and if not, taking the sub-attribute as a branch to continue splitting;
s16, removing the characteristic attributes of the root node and the bifurcation node;
s17, executing steps S11 to S16, taking the feature attributes with the highest information gain rate as next-level bifurcation nodes until all the feature attributes are used, and finally forming a decision tree;
further, the category information entropy calculation formula of the subsidy level is specifically as follows:
wherein, | Sj| is the number of samples for each level of assistance, | S | is the total number of samples, βNM represents the number of subsidy classes as the sum of the weights of the feature attributes.
Further, the conditional entropy calculation formula of the classification mode is specifically as follows:
feature attribute AxIs divided into1、A2、…、APMapping the samples in the training sample set S to the sample subsets corresponding to the sub-attributes, wherein AiIs a characteristic attribute AxP is a characteristic attribute AxNumber of sub-attributes, | AiI is a characteristic attribute AxIth sub-attribute AiCorresponding to the number of samples in the subset of samples, | S | is the total number of samples, βxIs a characteristic attribute AxCorresponding weight parameter, βNIs the sum of the weights of the feature attributes, | AijI denotes the sample subset AiTo obtain the number of samples, beta, of the jth subsidy levelxiIs characterized by the attribute AxIth sub-attribute AiThe weight parameter of (A), Info (A)i) And representing the information entropy of the corresponding subset of the ith sub-attribute Ai of the characteristic attribute Ax.
Further, the attribute segmentation information amount calculation formula of the feature attribute is specifically as follows:
wherein, | AiI is a characteristic attribute AxIth sub-attribute AiCorresponding to the number of samples in the subset of samples, | S | is the total number of samples, βxIs a characteristic attribute AxCorresponding weight parameter, βNIs the sum of the weights of the characteristic attributes.
Further, the calculation formula of the information gain ratio is specifically as follows:
wherein, Gain (A)x) For the attribute information gain in the classification mode, SplitInfo (A)x) The information amount is divided for the attributes of the feature attributes.
Further, the characteristic attributes include: poverty degree, public welfare activity record, illegal electricity utilization record, campus consumption record and score level.
The student characteristic attribute information is classified by using the decision tree, students with difficult life and excellent performance are accurately screened out, the economic benefit generated by photovoltaic power generation grid connection is directly transferred to the electricity utilization account of the corresponding student according to the campus power dispatching platform, the campus photovoltaic platform is used for generating electricity to bear part or all of electricity in the dormitory, and a new learning-assisting mode is developed.
Drawings
FIG. 1 is a flow chart of a decision tree-based learning-aiding method for photovoltaic power generation provided by an embodiment of the invention;
fig. 2 is a schematic diagram of a simplified decision tree with feature attributes according to an embodiment of the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be given with reference to the accompanying drawings for a more complete, accurate and thorough understanding of the inventive concept and technical solutions of the present invention by those skilled in the art.
Fig. 1 is a flowchart of a decision tree-based photovoltaic power generation learning assistance method provided in an embodiment of the present invention, and the method specifically includes the following steps:
s0, taking the characteristic attributes and the subsidy grades of the historical subsidy objects as sample data in a training sample set S, wherein the characteristic attributes comprise: poverty degree, public welfare activity record, illegal electricity utilization record, campus consumption record and score level.
S1, calculating the category information entropy of the subsidy level according to the training sample set S, wherein the calculation formula is as follows:
wherein, | Sj| is the number of samples for each level of assistance, | S | is the total number of samples, βNM represents the number of subsidy classes as the sum of the weights of the feature attributes.
In the embodiment of the invention, the category information entropy represents the sum of uncertainties of various auxiliary level categories in all samples, the larger the information entropy value is, the larger the uncertainty is, and when the information entropy value is 0, only one auxiliary level category is represented. Because the influence factors of various characteristic attributes of students on the judgment result of the subsidy level are different, if the achievement of the students has larger influence than the achievement of participating in public welfare activities and the excellent achievement of the students has larger influence, a weight parameter beta is given to each characteristic attribute and the sub-attribute under each characteristic attribute on the basis of the decision tree.
S2, dividing each characteristic attribute into a plurality of sub-attributes, and calculating the conditional entropy of the classification mode, wherein the calculation formula is as follows:
feature attribute AxIs divided into1、A2、…、APMapping the total sample data to a sample subset corresponding to each sub-attribute, wherein AiIs a characteristic attribute AxP is a feature attribute AxNumber of sub-attributes, | AiI is a characteristic attribute AxIth sub-attribute AiCorresponding to the number of samples in the subset of samples, | S | is the total number of samples, βxIs a characteristic attribute AxCorresponding weight parameter, βNIs the sum of the weights of the characteristic attributes, | AijI denotes the sample subset AiTo obtain the number of samples, beta, of the jth subsidy levelxiIs a characteristic attribute AxIth sub-attribute AiThe weight parameter of (A), Info (A)i) Representing a characteristic attribute AxIth sub-attribute AiThe information entropy of the corresponding subset.
The conditional entropy of each classification mode represents the sum of the uncertainty of the occurrence of various sub-attribute classes in the classification mode, and the larger the conditional entropy is, the more disorderly the sample classes owned by the attribute are.
S3, taking the difference value between the category information entropy of the subsidy level and the conditional entropy of each classification mode as the attribute information gain under the corresponding classification mode, wherein the calculation formula is as follows:
Gain(Ax)＝Info(S)-Info(Ax)
the attribute information gain represents the degree of information uncertainty reduction. The larger the information gain is, the more uncertainty of the divided samples can be better reduced by the attribute, and the attribute is selected as the next-level splitting node, so that the classification target can be better completed.
S4, calculating attribute segmentation information quantity of the characteristic attribute, wherein the calculation formula is as follows:
the attribute segmentation information quantity is used for considering the quantity information and the size information of branches when a certain attribute is split, and is beneficial to improving the accuracy of qualification judgment.
S5, calculating the information gain rate of each characteristic attribute based on the attribute segmentation information quantity and the attribute information gain, taking the characteristic attribute with the highest information gain rate as a root node of the decision tree, if a specific sub-attribute under the characteristic attribute corresponds to a subsidy level, taking the sub-attribute under the characteristic attribute as a leaf node, and if not, taking the sub-attribute as a branch to continue splitting, wherein the calculation formula of the information gain rate is as follows:
s6, removing the characteristic attributes of the root node and the bifurcation node;
s7, executing steps S1 to S6, taking the feature attributes with the highest information gain rate as next-level bifurcation nodes until all the feature attributes are used, and finally forming a decision tree; FIG. 2 is a schematic diagram of a decision tree with simplified feature attributes.
S8, judging the assistance grade of the assistance object based on the decision tree;
and S9, determining the power utilization auxiliary amount of each auxiliary grade based on the total daily power generation amount of the photovoltaic.
In the embodiment of the invention, the method for acquiring the daily electricity supply auxiliary amount of each auxiliary level specifically comprises the following steps:
the number of the assistant grade numbers m is divided into i types, and the number of the assistant objects corresponding to each assistant grade is N1、N2、.....、Ni，Qi....:Q2:Q1For the power utilization auxiliary proportion corresponding to each auxiliary grade, the total photovoltaic power generation amount before one day is Q, and the following requirements are met:
because the number of students is large, all people can not enjoy the benefits brought by photovoltaic learning assistance even if the students are classified according to the assistance levels, the priority coefficient corresponding to each assistance level is generated, the power utilization assistance is issued based on the sequence of the priority coefficients from large to small, and the calculation formula of the priority coefficient corresponding to each assistance level is as follows:
if the subsidy object cannot obtain the power utilization subsidy in the application, updating the priority coefficient corresponding to the subsidy grade based on the following formula, wherein the calculation formula is as follows:
wherein, the first application without power assistance is taken as the first application, RDeThe difference between the application times of the current application and the first application.
The student characteristic attribute information is classified by using the decision tree, students with difficult life and excellent performance are accurately screened out, the economic benefit generated by photovoltaic power generation grid connection is directly transferred to the electricity utilization account of the corresponding student according to the campus power dispatching platform, the campus photovoltaic platform is used for generating electricity to bear part or all of electricity in the dormitory, and a new learning-assisting mode is developed.
The present invention has been described in connection with the accompanying drawings, and it is to be understood that the invention is not limited to the precise construction and instrumentalities shown, but is intended to cover various modifications, no matter how practical the invention may be embodied, and may be embodied in other forms without departing from the spirit or essential characteristics thereof.
Claims (7)
1. A photovoltaic power generation learning assisting method based on a decision tree is characterized by comprising the following steps:
s1, taking the characteristic attribute and the assistance grade of the historical assistance object as sample data in a training sample set S, and constructing a decision tree based on the sample data;
s2, judging the assistance grade of the assistance object based on the decision tree;
and S3, determining the power utilization auxiliary amount of each auxiliary grade based on the total daily power generation amount of the photovoltaic.
2. The decision tree-based photovoltaic power generation learning-assisting method according to claim 1, wherein the decision tree construction method specifically comprises the following steps:
s11, calculating the category information entropy of the subsidy level according to the training sample set S;
s12, dividing each characteristic attribute into a plurality of sub-attributes, calculating the conditional entropy of the classification mode,
s13, taking the difference value between the category information entropy of the subsidy level and the conditional entropy of each classification mode as the attribute information gain under the corresponding classification mode;
s14, calculating attribute segmentation information quantity of the characteristic attribute;
s15, calculating the information gain rate of each characteristic attribute based on the attribute segmentation information quantity and the attribute information gain, taking the characteristic attribute with the highest information gain rate as a root node of the decision tree, if a specific sub-attribute under the characteristic attribute corresponds to a subsidy level, taking the sub-attribute under the characteristic attribute as a leaf node, otherwise, taking the sub-attribute as a branch to continue splitting;
s16, removing the characteristic attributes of the root node and the bifurcation node;
and S17, executing the steps S11 to S16, taking the feature attributes with the highest information gain rate as the next-level bifurcation nodes until all the feature attributes are used, and finally forming a decision tree.
3. The decision tree-based photovoltaic power generation learning-assisting method according to claim 2, wherein the category information entropy calculation formula of the assistance level is specifically as follows:
wherein, | Sj| is the number of samples for each level of assistance, | S | is the total number of samples, βNM represents the number of subsidy classes as the sum of the weights of the feature attributes.
4. The decision tree-based photovoltaic power generation learning-assisting method according to claim 2, wherein the conditional entropy calculation formula of the classification manner is as follows:
feature attribute AxIs divided into1、A2、...、APMapping the samples in the training sample set S to the sample subsets corresponding to the sub-attributes, wherein AiIs a characteristic attribute AxP is a feature attribute AxNumber of sub-attributes, | AiI is a characteristic attribute AxIth sub-attribute AiCorresponding to the number of samples in the subset of samples, | S | is the total number of samples, βxIs a characteristic attribute AxCorresponding weight parameter, βNIs the sum of the weights of the characteristic attributes, | AijI denotes the sample subset AiTo obtainNumber of samples, β, of the jth subsidy levelxiIs a characteristic attribute AxIth sub-attribute AiThe weight parameter of (A), Info (A)i) Representing a characteristic attribute AxIth sub-attribute AiThe information entropy of the corresponding subset.
5. The decision tree-based photovoltaic power generation learning-assisting method according to claim 2, wherein the attribute segmentation information amount calculation formula of the feature attribute is specifically as follows:
wherein, | AiI is a characteristic attribute AxIth sub-attribute AiCorresponding to the number of samples in the subset of samples, | S | is the total number of samples, βxIs a characteristic attribute AxCorresponding weight parameter, βNIs the sum of the weights of the characteristic attributes.
6. The decision tree-based photovoltaic power generation learning-aiding method according to claim 2, wherein the calculation formula of the information gain rate is as follows:
wherein, Gain (A)x) For the attribute information gain in the classification mode, SplitInfo (A)x) The information amount is divided for the attributes of the feature attributes.
7. The decision tree-based photovoltaic power generation learning-aiding method according to claim 1, wherein the characteristic attributes comprise: poverty degree, public welfare activity record, illegal electricity utilization record, campus consumption record and score level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010618881.9A CN111815488A (en) | 2020-06-30 | 2020-06-30 | Photovoltaic power generation learning assisting method based on decision tree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010618881.9A CN111815488A (en) | 2020-06-30 | 2020-06-30 | Photovoltaic power generation learning assisting method based on decision tree |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111815488A true CN111815488A (en) | 2020-10-23 |
Family
ID=72855692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010618881.9A Pending CN111815488A (en) | 2020-06-30 | 2020-06-30 | Photovoltaic power generation learning assisting method based on decision tree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111815488A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112861692A (en) * | 2021-02-01 | 2021-05-28 | 电子科技大学中山学院 | Room classification model construction method and device and room classification method and device |
-
2020
- 2020-06-30 CN CN202010618881.9A patent/CN111815488A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112861692A (en) * | 2021-02-01 | 2021-05-28 | 电子科技大学中山学院 | Room classification model construction method and device and room classification method and device |
| CN112861692B (en) * | 2021-02-01 | 2024-03-15 | 电子科技大学中山学院 | Method and device for constructing room classification model, and method and device for classifying rooms |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256102A (en) | A kind of Independent College Studentss based on cluster comment religion data analysing method | |
| CN110309300A (en) | A method of identification natural sciences knowledge-ID | |
| CN102591929B (en) | Library data processing system and data processing method thereof | |
| CN111143539A (en) | Knowledge graph-based question-answering method in teaching field | |
| CN106355347A (en) | Faculty member evaluation method and faculty member evaluation system | |
| CN111339285B (en) | BP neural network-based enterprise resume screening method and system | |
| CN112396252A (en) | Method for acquiring construction success evaluation values of double-creation park of power internet of things | |
| Pedersen | A ‘heart of goal’and the will to succeed: Goal commitment and task performance among teachers in public schools | |
| CN114186983B (en) | Video interview multidimensional scoring method, system, computer equipment and storage medium | |
| Yang | Decision tree algorithm based university graduate employment trend prediction | |
| Feng et al. | Dialect diversity and foreign direct investment in China | |
| CN111815488A (en) | Photovoltaic power generation learning assisting method based on decision tree | |
| CN108961453B (en) | Classroom roll call assistant decision-making system | |
| CN110188958A (en) | A kind of method that college entrance will intelligently makes a report on prediction recommendation | |
| Fotheringham et al. | Multiscale geographically weighted regression: Theory and practice | |
| CN110738565A (en) | Real estate finance artificial intelligence composite wind control model based on data set | |
| CN112700356B (en) | Method and system for managing information of training personnel for real-time online education and training | |
| Siraj et al. | Pre-selection of recruitment candidates using case based reasoning | |
| Ma et al. | Optimal evaluation index system and benefit evaluation model for agricultural informatization in Beijing | |
| Zaidi et al. | Employment transitions and earnings dynamics in the SAGE model | |
| CN113064962B (en) | Environment complaint reporting event similarity analysis method | |
| Liu et al. | Mobile Landscape: An Analysis of Chinese Foreign-Educated Young Scientists | |
| CN117196899B (en) | Internet information intelligent online management system and method based on vocational education | |
| CN112686057B (en) | College student psychological consultation appointment recommendation method and system | |
| Shkolnykova et al. | Systems of Innovation in Central and Eastern European countries: Path of Economic Transition and Differences in Institutions |
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 |
Application publication date: 20201023 |
|
| RJ01 | Rejection of invention patent application after publication |