CN115660296A - Method for automatically issuing non-compliance project suggestion scheme based on machine learning - Google Patents
Method for automatically issuing non-compliance project suggestion scheme based on machine learning Download PDFInfo
- Publication number
- CN115660296A CN115660296A CN202211681618.XA CN202211681618A CN115660296A CN 115660296 A CN115660296 A CN 115660296A CN 202211681618 A CN202211681618 A CN 202211681618A CN 115660296 A CN115660296 A CN 115660296A
- Authority
- CN
- China
- Prior art keywords
- compliance
- project
- examination
- opinions
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention is suitable for the field of project compliance review, and provides a method for automatically issuing an out-of-compliance project proposal scheme based on machine learning, which comprises the following steps: establishing a multi-rule-in-one data base and a learning result base; importing automatic review of project information; processing the checked compliance item and non-compliance item; automatically issuing examination opinions aiming at non-compliant projects by adopting an improved KNN algorithm; matching a compliance examination rule, a training result, a land mutual exclusion and a land mutual adaptation rule from the obtained non-compliance examination opinions to obtain a final proposal set; calculating project values of the schemes in the suggested scheme set by adopting an entropy method; outputting an non-compliance project review report. The method and the system realize automatic examination of the compliance of the city construction projects, can provide examination reports of the compliance projects and examination reports of the non-compliance projects containing a plurality of suggested schemes with top ranks in a short time, and improve the efficiency of examination of the compliance of the projects and determination of new schemes.
Description
Technical Field
The invention belongs to the field of project compliance review, and particularly relates to an automatic issuing method of an out-of-compliance project proposal scheme based on machine learning.
Background
The project compliance examination is a legal procedure which is required to be carried out before all city construction projects obtain the land pre-examination and site selection opinions, the project which does not pass the compliance examination needs to be subjected to the compliance examination after the project range is adjusted, and otherwise, the project can not be continuously promoted. Due to the fact that the same project is not in compliance, multiple times of range adjustment and multiple times of compliance examination are needed, the project process is delayed, administrative cost is wasted, and adverse effects are caused to the operator environment and the social economy.
The existing compliance analysis needs to go through the following steps: (1) the construction unit provides a project compliance review application; (2) the management department's related departments check the conformity of project address selection and the plan of the department supervisor respectively through man-machine interaction, and issue examination opinions; (3) the relevant departments shall review and comprehensively review the opinions (without a project non-compliance space position diagram); (4) feeding the opinions back to the construction unit; (5) adjusting projects by a construction unit; (6) the method can be used for secondary examination of the project site, and has the advantages of secondary examination of the project site, 8230, urgent regulation of the project site, urgent reduction of the project site, and the like.
Machine learning is a multi-disciplinary cross specialty, covers probability theory knowledge, statistical knowledge, approximate theoretical knowledge and complex algorithm knowledge, uses a computer as a tool and is dedicated to a real-time simulation human learning mode, and knowledge structure division is carried out on the existing content to effectively improve learning efficiency. How to utilize machine learning to improve project compliance review efficiency, save administrative cost for natural resource management, optimize operator environment, become the key work at present stage.
Disclosure of Invention
In view of the above problems, the present invention provides an automatic issuing method for non-compliant item suggestion scheme based on machine learning, and aims to solve the above technical problems.
The invention adopts the following technical scheme:
an automatic issuing method of non-compliant project suggestion scheme based on machine learning comprises
S1, establishing an all-in-one data base, and training historical compliance analysis opinions to obtain a learning result base;
s2, importing project information, automatically selecting space management and control plans and elements, selecting referential plans and elements, and automatically reviewing according to compliance review rules;
s3, automatically issuing compliance examination opinions for the examined compliance projects, analyzing results of the examined non-compliance projects, and automatically issuing non-compliance examination opinions by adopting an improved KNN algorithm;
s4, matching the compliance examination rules and the training results in the learning result base from the obtained non-compliance examination opinions, and matching the land mutual exclusion rules and the land mutual adaptation rules to obtain a final proposal set;
s5, calculating item values of the schemes in the suggested scheme set by adopting an entropy method;
and S6, outputting non-compliance project review reports of a plurality of suggested schemes with top-ranked project values.
The invention has the beneficial effects that: firstly, the method can automatically examine the compliance of the city construction project, and can provide an examination report of the compliance project and an examination report of the non-compliance project containing a plurality of suggested schemes with top ranking in a short time for the non-compliance project according to examination opinions and machine learning, so that the operation is very simple, and the efficiency of examining the compliance of the project and determining a new scheme is greatly improved; in addition, when the method is concretely implemented, a uniform compliance data base is formed, an improved KNN algorithm is adopted, examination opinions of historical compliance projects are grouped, all original traversal samples of non-compliance projects are changed into the mode that only samples of the corresponding group need to be traversed, the adaptive K value and the adaptive T value are found, the corresponding category can be obtained, the examination opinions can be automatically generated, and examination time is greatly saved; in addition, a ground exclusive and mutual adaptation rule is formulated to provide support for providing a project proposal, the weight of the influence factor of the proposal is objectively and scientifically determined by adopting an entropy method, and the comprehensive scores of all the proposals in the proposal set are determined, so that the subjectivity caused by manually determining the weight is avoided, and the ranking of the proposal is more scientific.
Drawings
FIG. 1 is a flow chart of a method for automatically issuing a proposal for an out-of-compliance project based on machine learning according to an embodiment of the invention;
fig. 2 is a flowchart of step S4 provided in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
As shown in fig. 1, the method for automatically issuing the non-compliance item suggestion scheme based on machine learning provided by the embodiment includes the following steps:
s1, establishing a multi-rule-in-one data base, and training historical compliance analysis opinions to obtain a learning result base.
The specific process of the step is as follows:
s11, collecting space management and control type plans and elements and referential plans and elements, and standardizing according to a unified data standard to form a multi-rule-in-one data base.
The space management and control class planning comprises the following steps: three control lines (permanent basic farmland, ecological protection red line, town development boundary), land utilization overall planning, city overall planning, increase and decrease hook implementation planning and controllability detailed planning.
The space management and control type elements comprise: basic farmland protection areas, primary forest lands, natural protection areas, primary drinking water source protection areas, river management areas, scenic spot areas, secondary drinking water source protection areas and quasi water source protection areas, rivers and their dikes (inland rivers), reservoirs and their engineering areas, raw water pipe canals, water conservancy main engineering and its production areas, flood storage areas, forest lands, forest parks, wetland parks, geological disaster high-risk areas, infrastructure isolation belts, city-around green belts, country parks, ecological tourism vacation areas.
The referential planning includes: and (5) special planning.
The reference elements include: airport control height, city updating, and rail traffic control area.
Standardizing the data according to the unified data standard of metadata information such as unified data names, data types and data structures, and finally forming the all-in-one data base.
And S12, collecting historical compliance analysis opinions, and performing text preprocessing on the compliance analysis opinions to obtain a text corpus.
And collecting historical project compliance analysis opinions, and performing text preprocessing on the historical compliance analysis opinions by using technologies such as word segmentation, noise reduction, optimal matching and the like. If not, the following steps are carried out: permanently occupying the pressure of the basic farmland, occupying the pressure of the ecological protection red line; the distance between the refuse landfill and the residential area is at least 500 meters, and the like.
And S13, constructing a training model, and selecting polar words from the text corpus to perform model training.
Polar words are words that are used for positive sentences or only for negative sentences. And the accuracy of the training result is continuously improved through the polar word model training.
And S14, judging and classifying the regularity analysis opinions by adopting a KNN algorithm, and storing a classified learning result library.
The method collects three control lines, a land utilization overall plan, a city overall plan, an increase and decrease hook implementation plan, a special plan, a management and control element and a referential element. Various data are difficult to utilize due to the fact that a coordinate system, a data standard, a data specification and a data format are not uniform. Therefore, a unified coordinate system and a unified data standard are needed, all data are subjected to quality inspection according to a unified quality inspection rule, and the qualified data are brought into an all-in-one planning data pool for project compliance analysis.
And S2, importing project information, automatically selecting space management and control plans and elements, selecting referential plans and elements, and automatically examining according to compliance examination rules.
The specific process of the step is as follows:
and S21, importing item information of the basic information and the accessory material information.
The basic information includes a project name, a land attribute, a project attribute, and a land area. Basic information and accessory material information are imported, and a user-drawn item range can also be imported. The imported project block data formats include CAD, SHP formats, and TXT format of the natural resource homeland government edition.
And S22, selecting the necessary selected space management and control type plans and elements, and selecting the referential plans and elements according to requirements.
Firstly, the system automatically selects the necessary space management and control type plans and elements, and the user selects the referential plans and elements according to the requirements and then analyzes the plans and elements. The space management and control type plans and elements belong to necessary options, the system is automatically selected and cannot be manually changed, and the accuracy of the examination result is ensured. The referential planning and elements belong to unnecessary options, and can be selectively superposed and analyzed according to the actual conditions of the land parcel.
And S23, the project information is overlapped with the selected plans and elements, and project compliance is analyzed in a space overlapping mode, so that automatic review of the compliance is realized.
And (4) superposing the imported project information and the selected plans and elements, and carrying out superposition analysis on project compliance by adopting a spatial superposition analysis method of a geographic information system to obtain an analysis chart and analysis data.
Selecting space management and control plans and elements, referring plans and elements, combing the conformity of various land attributes and map layers and elements according to the requirements of related legal and legal documents, and formulating examination rules. Such as: the educational facilities are overlapped with the three control lines, and can not be built in the range of permanent basic farmland, can be built in the range of ecological protection red lines and can be built in the range of town development boundaries; superposed with the land utilization overall plan, can be constructed according with the map spots of the land class at the end of the term, can be constructed in the range of allowed construction areas, can not be constructed in the range of conditional construction areas, can not be constructed in the range of restricted areas, can not be constructed in the range of forbidden construction areas, and can be constructed in the range of town/village and town construction land; superposed with the city overall plan, can be constructed in a suitable construction area, can not be constructed in a restricted construction area, can not be constructed in a forbidden construction area, can not be constructed in a purple line range of a city, can not be constructed in a yellow line range of the city, can not be constructed in a green line range of the city, and can not be constructed in a blue line range of the city; the method is superposed with the increase and decrease hook implementation plan, and cannot be constructed in the range of an old demolished area and the range of a new construction area; the method is superposed with space management and control elements, and cannot be built if conflicts exist; and the land range and the land property are both in accordance with the construction requirement by overlapping with referential planning (special planning of educational facilities).
And S3, automatically issuing compliance examination opinions for the examined compliance projects, analyzing results of the examined non-compliance projects, and automatically issuing non-compliance examination opinions by adopting an improved KNN algorithm.
The specific process of the step is as follows:
and S31, constructing a compliance project and non-compliance project examination report template, wherein the compliance project examination report template comprises an analysis detail part and an analysis conclusion part, and the non-compliance project examination report template comprises an analysis detail part, an analysis conclusion part and a proposal part.
The analysis details comprise project plot occupied pressure space management and control plans, element and referential plans, the areas and types of the elements, analysis results of various plans of occupied pressure/unoccupied pressure and the elements are listed in a mode of combining figures, and the analysis conclusion automatically judges whether the conditions are in compliance according to occupied pressure conditions and compliance examination rules.
And S32, setting the link between the examination result and the corresponding module in the examination report template.
If the result of the pressure occupation analysis of the project superposition permanent basic farmland is positioned in the first row, the result of the pressure occupation analysis of the project superposition ecological protection red line is positioned in the second row, and so on.
S33, selecting different review report templates according to the automatic review result, and selecting a compliance project review report template if the compliance is met; if not, the non-compliance project audit report template is selected.
And S34, automatically matching a learning result library by adopting an improved KNN algorithm according to the plan of the non-compliant project, the number and the category of the elements, and automatically issuing an examination opinion.
And (4) superposing the project and space management and control plans, elements and referential plans and elements, and determining the plans, the element quantities and the categories of the project occupation pressure according to the formulated examination rule. By automatically analyzing the plans, the number of elements and the types of the non-compliant projects, an improved KNN algorithm is adopted to automatically match a learning result library, and the examination opinions are automatically issued.
KNN (K-nearest neighbor), called K-nearest neighbor, is a basic classification and logistic regression algorithm in machine learning. The working mechanism is relatively simple: a sample set, also called a sample training set, is given and the correspondence of the data in the sample set to the class to which it belongs is known. After inputting a new data without classification, the computer extracts the features of the data and compares the features with the features in the data set to find out K data similar to the features, and the classification with the highest frequency among the K data is used as the classification of the new data. The algorithm does not have any model parameters, and model parameter training is not needed. It has two major disadvantages: (1) The time complexity of the calculation process is high, and the efficiency is low. Because the number of training samples of the manual historical review opinions is large, all training sample sets must be traversed when classification calculation is carried out on any new sample to be measured, and the calculation process is long in time, high in complexity and low in efficiency; (2) the accuracy is not high. The value of K is not verified to be the most appropriate K value, and the K is too small, so that the classification result is easily influenced by noise points; if K is too large, too many other types of points may be contained in the neighborhood, which may result in inaccurate results.
The present embodiment improves this by the following two points: (1) And grouping the historical sample sets again according to the number of the elements which do not accord with the image layers, and only traversing all the samples in the corresponding groups. (2) And solving the optimal solution of the K value by adopting an MAPE evaluation method and a prediction algorithm. The specific implementation process is as follows:
341. and grouping the historical compliance analysis opinions in the learning result library according to the number of the layers of the project non-compliance map.
And respectively training the historical examination opinions processed by the natural language according to the grouping of the number of the layers which are not met by the items. According to the compliance analysis rule, the project needs to be overlapped and analyzed with 45 layers and elements at most, so that the historical review opinions are divided into: the first group does not conform to 1 layer and element; the second group does not conform to the 2 layers and elements; and setting the 45 th group which does not conform to the 45 layers and elements in sequence. The possible situation of non-conforming layers and elements in each type of data set is
C represents a combination mathematically, n represents the total number of layers and elements, and m represents the number of layers of the map which are not in accordance with the items in each group; m is more than or equal to 1 and less than or equal to n, and n =45.
342. And determining a corresponding group according to the number of the unconventional layers and the elements of the sample to be detected.
After the grouping, the grouping of the samples to be tested can be determined.
343. And traversing all samples in the current group, establishing a searching mechanism by using the state vector, the distance measurement mode and the neighbor number K, and searching.
The state vector is a standard for comparing the current examination result with the historical examination opinions, and the most relevant factors to the sample to be tested are generally selected to balance the requirements of prediction precision and traversal time. By observing the classification of the inspection opinions in the historical inspection opinion database.
The distance measure being for degreeMeasuring the approximation degree of each historical sample in the historical database correlation group and the current sample to be measured, and adopting Euclidean distance as a measurement index:
。
the distance between the historical sample vector and the sample vector to be measured is calculated;
there are u non-conforming layers/elements for the sample to be tested,
the group of the u non-conforming layers contains s possible situations; t has a value range of [1,45 ]]。
344. And calculating a prediction result by using K adjacent data in the searched current group as a test data set and other data as a training data set and using a K adjacent prediction algorithm.
345. And adopting the prediction precision and the difference value of the MAPE evaluation model, when the MAPE obtains the minimum value, the corresponding group and the K pieces of adjacent data are the optimal values of the sample to be tested, and the optimal values are the review opinions corresponding to the category to which the current non-compliant item belongs.
For more intuitive prediction accuracy and difference of the reaction model, MAPE (mean absolute percentage error) is adopted, and smaller MAPE indicates higher accuracy, i.e. closer approach.
The search prediction is a review result of how to predict the non-compliance of the sample to be tested by using the searched K adjacent data:
in the formula:
predict values for non-compliance data;
the non-compliance examination result corresponding to the ith neighbor searched in the historical examination opinion database;
is the distance of the current vector from the ith point of proximity.
Then, determining an adaptive K value and an adaptive T value: 1. matching the classification of the sample to be tested and the historical sample data, wherein the sample to be tested is matched into the Nth class, and setting N =
(ii) a 2. Sample to be tested
Determining the value of the state vector T; 3. let T =
，
(ii) a Is provided with
，
(ii) a 4. Selecting K neighbor data in the Nth group of a History review opinion dataset
As test data sets, others of the group
Each as a training data set; 5. computing
And
test data set of
Percent mean absolute error:
(ii) a 6. Computing
And
mean absolute error percentage for all test data sets:
。
when MAPE takes the minimum value, the corresponding is predicted
And
the optimal value of the sample to be measured in the scene is obtained. The optimal value is the review opinion corresponding to the category to which the non-compliant item belongs.
The classification category of the sample to be tested, namely the examination opinions of the non-compliant items, is finally obtained, and the examination opinions are automatically filled in the corresponding positions according to the set links, so that the purpose of automatically issuing the examination opinions is achieved. Through the improved KNN model, the group needing to traverse the samples can be selected according to the non-compliant layers and the number of elements, the time for traversing all the samples of the original KNN model is greatly reduced, and the examination efficiency is greatly improved.
And S35, automatically inputting examination opinions of compliance and non-compliance according to the set link.
According to the link established in the step, the automatic input of the examination opinions is realized, if the item occupies a permanent basic farmland, the examination opinions are as follows: the method is not in compliance, the permanent basic farmland square meter is occupied by pressure, and a graph in the occupation space range and a square meter with the occupation area A are automatically input into a specified position; if the ecological protection red line is occupied and the permanent basic farmland is not occupied, the examination and opinion is as follows: the method is characterized in that the method is not in compliance, the pressure-occupying ecological protection red line B square meter is adopted, the graph of the pressure-occupying ecological protection red line and the pressure-occupying area B square meter are automatically input, and the superposition graph of the project range and the permanent basic farmland and the pressure-occupying area 0 square meter are automatically input. The examination report of the compliance project is automatically filled according to the set link, and the preview and the export examination report can be clicked to generate; the review opinions are automatically output by the non-compliance items.
And S4, matching the compliance examination rule in the obtained non-compliance examination opinions, matching the training results in the learning result base, and matching the land mutual exclusion rule and the land mutual adaptation rule to obtain a final proposal set.
As shown in fig. 2, the specific process of this step is as follows:
and S41, logging the right mutual exclusion rule and the right mutual adaptation rule.
The right-of-land selection rule comprises a right-of-land mutual exclusion rule and a right-of-land mutual adaptation rule. Based on the related standard specification and the requirements of various land for the surrounding environment, the land mutual exclusion and land mutual adaptation rules are obtained. For example, the site for education facilities is matched with the site for addresses, the sites can be closely adjacent when a proposal is issued, are not related to the administrative and office sites, are mutually exclusive with the site for medical and health, and are far away when the proposal is issued.
And S42, automatically matching the obtained non-compliance examination opinions with compliance examination rules, and removing the plans occupying pressure in the examination opinions and the space range of elements according to a space superposition analysis method to obtain a first pre-suggestion scheme set.
S43, matching the first pre-proposed scheme set with training results in a learning result library, such as at least 500 meters of distance between the landfill site and the residential area, and excluding all proposed schemes of which the distance between the landfill site and the residential area is less than 500 meters to obtain a second pre-proposed scheme set.
And S44, matching the second pre-proposed scheme set with the land mutual exclusion rule and the land mutual adaptation rule to obtain a final proposed scheme set.
And S5, calculating item values of the schemes in the suggested scheme set by adopting an entropy value method.
The specific process of the step is as follows:
and S51, scoring the influence factors of each scheme in the suggested scheme set according to a traffic reachability analysis mode, a distance analysis mode, a right-of-land mutual exclusion rule and a right-of-land mutual exclusion rule.
For example, a traffic accessibility analysis mode is adopted, the accessibility degree of road traffic around each proposal in the proposal set is calculated, and the traffic accessibility influence factors in each proposal are scored according to the set scoring rule; if the reaching degree is more than or equal to 90 percent, the score is 10; the content is more than or equal to 70 percent and can reach less than 90 percent, and the score is 8; the content is more than or equal to 50 percent and can reach less than 70 percent, and the score is 5; the content is more than or equal to 30 percent and can reach the degree less than 50 percent, and the score is 3; less than 30 percent and is scored into 0.
The scores of other impact factors are also set with reference to this rule. And by analogy, the score of each scheme under each influence factor is calculated respectively.
And S52, determining the weight of each influence factor by adopting an entropy method.
And determining the weights of traffic accessibility, distance analysis, land mutual exclusivity, land mutual adaptability and the like in the comprehensive scoring of the proposed scheme by adopting an entropy method, performing comprehensive scoring on all schemes in the proposed scheme set, and sequencing the schemes from high to low according to the scores, wherein the higher the score is, the better the comprehensive condition of the scheme is.
And S53, calculating the comprehensive scores of all the schemes in the suggested scheme set according to the scores and the weights, namely calculating the item values, and sequencing according to the size of the item values.
And S6, outputting non-compliance project review reports of a plurality of suggested schemes with the top project values.
And outputting a scheme with comprehensive scores and ranking the first three, setting the same ranking for a plurality of schemes with the same scores, and reserving the schemes with the same scores in the schemes with the first three.
The invention realizes the automatic examination of the compliance of the city construction projects, and can provide a plurality of compliance suggestion schemes in a short time for the non-compliance projects according to manual examination opinions and machine learning. Taking a certain refuse landfill as an example, 5 different department examinees are respectively spent on the traditional compliance examination, each individual needs about 10 minutes, 1 person needs to be invested for about 0.5 day when the project scheme is adjusted for 1 time, and if the project is not compliant after adjustment, the time spent on the project needs to be accumulated according to the time spent on the project; the method and the system improve the efficiency of issuing the proposal of compliance review and compliance to 1 minute and finish the proposal, greatly improve the efficiency of project compliance review and new scheme determination, reduce repeated adjustment and review caused by non-compliance of the project, greatly improve review efficiency and save administrative cost.
In conclusion, the data standards of all space plans, elements, referential plans and elements are unified, a unified compliance review data base is formed, and a construction unit does not need to butt up a supervisor department of related plans one by one to check whether the project is in compliance, so that the time cost is greatly saved, and the operator environment is optimized; in addition, the improved KNN algorithm is adopted to group the manual review opinions of the historical compliance analysis project, all samples of the non-compliance project are changed from the original traversal through, only the samples of the affiliated group are traversed, the self-adaptive K value and the self-adaptive T value are found, the affiliated category can be obtained, the review opinions are further automatically generated, the review time is greatly saved, and the review efficiency is improved; thirdly, compliance review rules of all planning layers and elements which need to be superposed in compliance analysis are creatively formulated, and space management and control planning/element automatic selection reduces interference caused by human factors; for referential planning and element examiners, the results can be automatically analyzed and output only by selecting the examiners according to needs; fourthly, the invention sets out a ground exclusive and mutual adaptation rule and provides support for issuing a project proposal; fifthly, the method objectively and scientifically determines the weight of the evaluation index of the proposal scheme by adopting an entropy method, and determines the comprehensive score of all proposal schemes in the proposal scheme set by combining with the scoring rule, thereby avoiding the subjectivity caused by manually determining the weight and ensuring that the ranking of the proposal scheme is more scientific.
The above description is intended to be illustrative of the preferred embodiment of the present invention and should not be taken as limiting the invention, but rather, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (7)
1. A method for automatically issuing an out-of-compliance item proposal based on machine learning, the method comprising the steps of:
s1, establishing an all-in-one data base, and training historical compliance analysis opinions to obtain a learning result base;
s2, importing project information, automatically selecting space management and control plans and elements, selecting referential plans and elements, and automatically reviewing according to compliance review rules;
s3, automatically issuing compliance examination opinions for the examined compliance projects, analyzing results of the examined non-compliance projects, and automatically issuing non-compliance examination opinions by adopting an improved KNN algorithm;
s4, matching the compliance examination rules and the training results in the learning result base from the obtained non-compliance examination opinions, and matching the land mutual exclusion rules and the land mutual adaptation rules to obtain a final proposal set;
s5, calculating item values of the schemes in the suggested scheme set by adopting an entropy method;
and S6, outputting non-compliance project review reports of a plurality of suggested schemes with the top project values.
2. The method for automatically issuing the non-compliant item proposal scheme based on machine learning as claimed in claim 1, wherein the specific process of the step S1 is as follows:
s11, collecting space management and control type plans and elements and referential plans and elements, and standardizing according to a unified data standard to form a multi-rule-in-one data base;
s12, collecting historical compliance analysis opinions, and performing text preprocessing on the compliance analysis opinions to obtain a text corpus;
s13, constructing a training model, and selecting polar words from the text corpus to perform model training;
and S14, judging and classifying the regularity analysis opinions by adopting a KNN algorithm, and storing a classified learning result library.
3. The method for automatically issuing the non-compliance item proposal scheme based on machine learning as claimed in claim 2, wherein the specific process of the step S2 is as follows:
s21, importing item information of basic information and accessory material information;
s22, selecting a necessary space management and control type plan and elements, and selecting a referential plan and elements according to requirements;
and S23, the project information is overlapped with the selected plans and elements, and the project compliance is subjected to overlapping analysis in a space overlapping mode, so that automatic review of the compliance is realized.
4. The method for automatically issuing the out-of-compliance item recommendation scheme based on machine learning as claimed in claim 3, wherein the specific process of the step S3 is as follows:
s31, constructing a compliance project and non-compliance project examination report template, wherein the compliance project examination report template comprises an analysis detail part and an analysis conclusion part, and the non-compliance project examination report template comprises an analysis detail part, an analysis conclusion part and a proposal part;
s32, setting the link between the examination result and the corresponding module in the examination report template;
s33, selecting different review report templates according to the automatic review result, and selecting a compliance project review report template if compliance is met; if not, selecting a non-compliant project review report template;
s34, automatically matching a learning result library by adopting an improved KNN algorithm according to the plan of the non-compliant project, the number and the category of the elements, and automatically issuing an examination opinion;
and S35, automatically inputting examination opinions of compliance and non-compliance according to the set link.
5. The method for automatically issuing the non-compliance item proposal scheme based on machine learning as claimed in claim 4, wherein the step S34 is implemented as follows:
341. grouping historical compliance analysis opinions in the learning outcome library according to the number of the layers of the project non-compliance graphs;
342. determining a corresponding group according to the number of non-compliant layers and elements of the sample to be detected;
343. traversing all samples in the current group, establishing a searching mechanism by using a state vector, a distance measurement mode and the neighbor number K, and searching;
344. calculating a prediction result by using K neighbor prediction algorithm by using K neighbor data in the searched current group as a test data set and other data as a training data set;
345. and adopting the prediction precision and the difference value of the MAPE evaluation model, when the MAPE obtains the minimum value, the corresponding group and the K pieces of adjacent data are the optimal values of the sample to be tested, and the optimal values are the review opinions corresponding to the category to which the current non-compliant item belongs.
6. The method for automatically issuing the non-compliance item proposal scheme based on machine learning according to claim 5, characterized in that the specific process of the step S4 is as follows:
s41, inputting a land mutual exclusion rule and a land mutual adaptation rule;
s42, automatically matching the obtained non-compliance inspection opinions with compliance inspection rules, and removing the space range of the occupied plan and elements in the inspection opinions according to a space superposition analysis method to obtain a first pre-suggestion scheme set;
s43, matching the first pre-proposed scheme set with training results in a learning result library to obtain a second pre-proposed scheme set:
and S44, matching the second pre-proposed scheme set with the land mutual exclusion rule and the land mutual adaptation rule to obtain a final proposed scheme set.
7. The method for automatically issuing the non-compliant item proposal scheme based on machine learning as claimed in claim 6, wherein the step S5 is implemented as follows:
s51, scoring the influence factors of each scheme in the suggested scheme set according to a traffic reachability analysis mode, a distance analysis mode, a land mutual exclusion rule and a land mutual adaptability rule;
s52, determining the weight of each influence factor by adopting an entropy method;
and S53, calculating the comprehensive scores of all the schemes in the suggested scheme set according to the scores and the weights, namely calculating the item values, and sequencing according to the size of the item values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211681618.XA CN115660296B (en) | 2022-12-27 | 2022-12-27 | Automatic issuing method of non-compliance project proposal scheme based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211681618.XA CN115660296B (en) | 2022-12-27 | 2022-12-27 | Automatic issuing method of non-compliance project proposal scheme based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115660296A true CN115660296A (en) | 2023-01-31 |
| CN115660296B CN115660296B (en) | 2023-07-04 |
Family
ID=85023380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211681618.XA Active CN115660296B (en) | 2022-12-27 | 2022-12-27 | Automatic issuing method of non-compliance project proposal scheme based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660296B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116090705A (en) * | 2023-03-06 | 2023-05-09 | 广东新视野信息科技股份有限公司 | Data processing method and system based on intelligent building site and cloud platform |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040117337A1 (en) * | 2002-12-11 | 2004-06-17 | Beck Walter R. | Export compliance system and method |
| CN104063458A (en) * | 2014-06-26 | 2014-09-24 | 北京奇虎科技有限公司 | Method and device for providing corresponding solution for terminal fault problem |
| CN107516191A (en) * | 2017-08-10 | 2017-12-26 | 广州市城市规划勘测设计研究院 | " more rule unifications " " figure " Project cooperation approval system, method and instrument |
| CN107798357A (en) * | 2017-11-28 | 2018-03-13 | 南京大学 | A kind of village land used reclamation planning analogy method based on KNN |
| CN108446885A (en) * | 2018-01-31 | 2018-08-24 | 国网山东省电力公司经济技术研究院 | A kind of automatic collecting method of review comment |
| CN111950976A (en) * | 2020-07-23 | 2020-11-17 | 深圳供电局有限公司 | Engineering project review system and method |
| CN113094459A (en) * | 2021-04-21 | 2021-07-09 | 自然资源部地图技术审查中心 | Map checking method and device |
| CN114443709A (en) * | 2021-12-28 | 2022-05-06 | 厦门市美亚柏科信息股份有限公司 | Method, system, device and storage medium for checking data compliance |
| CN114936835A (en) * | 2022-04-26 | 2022-08-23 | 东南大学 | BIM-based compliance automatic review method and system |
| CN115239211A (en) * | 2022-09-22 | 2022-10-25 | 国家电投集团科学技术研究院有限公司 | Method, device and system for researching and examining photovoltaic power generation project and electronic equipment |
-
2022
- 2022-12-27 CN CN202211681618.XA patent/CN115660296B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040117337A1 (en) * | 2002-12-11 | 2004-06-17 | Beck Walter R. | Export compliance system and method |
| CN104063458A (en) * | 2014-06-26 | 2014-09-24 | 北京奇虎科技有限公司 | Method and device for providing corresponding solution for terminal fault problem |
| CN107516191A (en) * | 2017-08-10 | 2017-12-26 | 广州市城市规划勘测设计研究院 | " more rule unifications " " figure " Project cooperation approval system, method and instrument |
| CN107798357A (en) * | 2017-11-28 | 2018-03-13 | 南京大学 | A kind of village land used reclamation planning analogy method based on KNN |
| CN108446885A (en) * | 2018-01-31 | 2018-08-24 | 国网山东省电力公司经济技术研究院 | A kind of automatic collecting method of review comment |
| CN111950976A (en) * | 2020-07-23 | 2020-11-17 | 深圳供电局有限公司 | Engineering project review system and method |
| CN113094459A (en) * | 2021-04-21 | 2021-07-09 | 自然资源部地图技术审查中心 | Map checking method and device |
| CN114443709A (en) * | 2021-12-28 | 2022-05-06 | 厦门市美亚柏科信息股份有限公司 | Method, system, device and storage medium for checking data compliance |
| CN114936835A (en) * | 2022-04-26 | 2022-08-23 | 东南大学 | BIM-based compliance automatic review method and system |
| CN115239211A (en) * | 2022-09-22 | 2022-10-25 | 国家电投集团科学技术研究院有限公司 | Method, device and system for researching and examining photovoltaic power generation project and electronic equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116090705A (en) * | 2023-03-06 | 2023-05-09 | 广东新视野信息科技股份有限公司 | Data processing method and system based on intelligent building site and cloud platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115660296B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yu et al. | Tracing knowledge diffusion of TOPSIS: A historical perspective from citation network | |
| CN111222661B (en) | Urban planning implementation effect analysis and evaluation method | |
| JP2022518887A (en) | Profit evaluation method for implementing technical standardization for large and medium-sized companies | |
| Jones et al. | A multi-attribute value model for the study of UK energy policy | |
| CN107784394A (en) | Consider that the highway route plan of prospect theory does not know more attribute method for optimizing | |
| Franklin et al. | Co-citation bibliometric modeling as a tool for S&T policy and R&D management: Issues, applications, and developments | |
| CN108256022A (en) | Talent evaluation model building method and personnel evaluation methods and system | |
| CN112860769B (en) | Energy planning data management system | |
| Brendel et al. | Information systems in the context of sustainable mobility services: A literature review and directions for future research | |
| CN115660296A (en) | Method for automatically issuing non-compliance project suggestion scheme based on machine learning | |
| Centobelli et al. | The future of sustainable supply chains: a novel tertiary-systematic methodology | |
| CN116502755A (en) | System and method for industrial development prediction by constructing industrial map by adopting big data | |
| CN112508336B (en) | Space and environmental efficiency correlation measurement method based on structural equation model | |
| CN113421037A (en) | Multi-source collaborative construction planning compilation method and device | |
| CN106447144A (en) | Target object evaluation method and target object evaluation device | |
| Alshehadeh et al. | The impact of business intelligence tools on sustaining financial report quality in Jordanian commercial banks | |
| CN103559585A (en) | Method and system for achieving library comprehensive performance evaluation | |
| Sari et al. | Application of the Promethee II method for determining road improvement priorities | |
| Eskandary et al. | Identification and prioritization of public-private partnership indicators in Iran’s water and wastewater industry via data mining algorithms | |
| CN112506930B (en) | Data insight system based on machine learning technology | |
| KR100700376B1 (en) | Real-time quality measurement method of bibliographic database | |
| Li et al. | Big-Data Measurement-Model Research about Judges’ Actual Workload in China | |
| CN114546994B (en) | Data analysis method and system for improving functions of old factory floor based on data container | |
| Wang et al. | Research on economic development trend of reform and opening up: based on big data modeling analysis method | |
| CN116308158B (en) | National asset supervision and management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |