CN113850350A - Urban building land intelligent planning system and method - Google Patents
Urban building land intelligent planning system and method Download PDFInfo
- Publication number
- CN113850350A CN113850350A CN202111438533.4A CN202111438533A CN113850350A CN 113850350 A CN113850350 A CN 113850350A CN 202111438533 A CN202111438533 A CN 202111438533A CN 113850350 A CN113850350 A CN 113850350A
- Authority
- CN
- China
- Prior art keywords
- expert
- data
- land
- group
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000013135 deep learning Methods 0.000 claims abstract description 32
- 238000011161 development Methods 0.000 claims abstract description 25
- 238000011835 investigation Methods 0.000 claims abstract description 24
- 238000012937 correction Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims description 31
- 238000010276 construction Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 12
- 239000000126 substance Substances 0.000 claims description 12
- 238000007726 management method Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000013278 delphi method Methods 0.000 claims description 6
- 238000013136 deep learning model Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 206010039203 Road traffic accident Diseases 0.000 claims description 3
- 239000003643 water by type Substances 0.000 claims description 2
- 230000009471 action Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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"
-
- 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
- G06Q50/08—Construction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Primary Health Care (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent planning system and method for urban building land, and belongs to the technical field of intelligent planning of urban building land. The system comprises a regional data acquisition module, a deep learning module, a correction module, a prediction investigation module and an intelligent building land planning module; the output end of the regional data acquisition module is connected with the input end of the deep learning module; the output end of the deep learning module is connected with the input end of the correction module; the output end of the correction module is connected with the input end of the prediction investigation module; the output end of the prediction investigation module is connected with the input end of the intelligent building land planning module. According to the invention, the virtual expert group can continuously weaken the individual subjective consciousness of the real expert group judgment, and continuously enhance the accuracy of the system, so that the judgment of urban building land planning becomes intelligent, a certain rule is met, the working efficiency is improved, and the urban development requirement is met.
Description
Technical Field
The invention relates to the technical field of intelligent planning of urban building land, in particular to an intelligent planning system and method of urban building land.
Background
The planning management of the construction land is an important component of the urban planning management, and the strict planning control of the construction land is the basic guarantee of the urban planning implementation and is the continuation of the planning management of the site selection of the construction project. The intelligent planning of the urban building land is in line with the current technical development concept and is an important step in smart city construction, and the urban building land planning can control all constructions to reasonably use the land in the urban planning area and ensure the implementation of the urban planning; the construction land is saved, and the coordinated development of urban construction and agriculture is promoted; comprehensively coordinating the comprehensive benefits of the requirements of the relevant contradiction and relevant aspects of the construction land; the urban planning is continuously perfected and deepened.
However, in the current technical means, no effective means for realizing the intelligent planning of the urban building land exists, and the artificial planning is usually performed by means of urban planning experts, because the manpower capacity is limited, a large amount of urban data cannot be considered completely, meanwhile, the artificial planning is difficult to be close to the civilian life, the regularity of final planning cannot be guaranteed, and meanwhile, the artificial planning has certain purposiveness and subjective awareness and is inevitable to cause errors, so that a great amount of blanks exist in the technical field of the intelligent planning of the urban building land at present.
Disclosure of Invention
The invention aims to provide an intelligent planning system and method for urban building land, which aim to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
an intelligent planning system for urban building land comprises a regional data acquisition module, a deep learning module, a correction module, a prediction investigation module and an intelligent planning module for building land;
the regional data acquisition module is used for acquiring four kinds of data in a region, wherein the four kinds of data comprise geographic information data, traffic information data, resident information data and consumption information data, and analyzing and sorting the four kinds of data; the deep learning module establishes a virtual expert group through analysis of a real expert group based on a deep learning mechanism and establishes a regional development prediction model; the correction module continuously fits a deep learning model based on the condition of similarity, so that the accuracy of the system is ensured as much as possible; the prediction investigation module is used for establishing a prediction questionnaire and performing prediction investigation through a Delphi method; the building land intelligent planning module is used for carrying out intelligent planning on the urban building land according to the output final urban building land planning scheme group;
the output end of the regional data acquisition module is connected with the input end of the deep learning module; the output end of the deep learning module is connected with the input end of the correction module; the output end of the correction module is connected with the input end of the prediction investigation module; the output end of the prediction investigation module is connected with the input end of the intelligent building land planning module.
According to the technical scheme, the regional data acquisition module comprises a regional data acquisition unit and a time period establishment unit;
the regional data acquisition unit is used for acquiring geographic information data, traffic information data, resident information data and consumption information data in a region; the time period establishing unit is used for establishing a time period and sorting the four data according to the time period;
the output end of the regional data acquisition unit is connected with the input end of the time period establishing unit; and the output end of the time period establishing unit is connected with the input end of the deep learning module.
According to the technical scheme, the deep learning module comprises a feature extraction unit and a training unit;
the characteristic extraction unit is used for extracting expert characteristics of the real expert group and establishing expert characteristics of the virtual expert group; the training unit is used for constructing the judgment standard of the virtual expert group through the continuously increased training data;
the output end of the feature extraction unit is connected with the input end of the training unit; and the output end of the training unit is connected with the input end of the correction module.
According to the technical scheme, the correction module comprises a similarity judgment unit and a fitting unit;
the similarity judging unit is used for judging the similarity between the real expert group and the virtual expert group; the fitting unit is used for fitting the model continuously to ensure the accuracy of the system;
the output end of the similarity judging unit is connected with the input end of the fitting unit; and the output end of the fitting unit is connected with the input end of the prediction investigation module.
According to the technical scheme, the prediction investigation module comprises a questionnaire establishing unit and an output unit;
the questionnaire establishing unit is used for establishing a questionnaire and inputting data for the system; the output unit is used for outputting the urban building land planning scheme group and outputting the final urban building land planning scheme group based on the time period;
the output end of the questionnaire establishing unit is connected with the input end of the output unit; and the output end of the output unit is connected with the input end of the intelligent building land planning module.
According to an intelligent planning system for urban building land, an intelligent planning method for urban building land suitable for the system is provided;
an intelligent planning method for urban building land comprises the following steps:
s1, constructing an area, recording the area as an area A, acquiring four data in the area A, establishing a time period, and performing segmented arrangement on the four data according to the time period, namely TiCorresponding to a data group MiData set MiIncluding region A in the time periodPeriod TiFour data in, wherein TiIs any one time period;
s2, constructing a virtual expert group based on deep learning, designing a prediction questionnaire, constructing a region A development prediction model, and establishing an initial urban building land planning scheme group;
s3, constructing N groups of data sets based on the time period T, and inputting a first new group of data sets M1Analyzing with the initial city building land planning scheme group by the virtual expert group, and outputting a city building land planning scheme group I1；
S4, inputting new data M of S-th group based on time period TsPlan set I for urban building lands-1After being analyzed by the virtual expert group, the urban building land planning scheme group I is outputsUntil s = N, and outputting the planning plan group I of the city building land at the timeNIs shown byNAs a final output;
and S5, acquiring a median according to the final output, constructing a data weight proportion, and calculating and outputting a final urban building land intelligent planning scheme.
According to the technical scheme, in the steps S1-S2, the geographic information data comprise mountains, scenic areas and water areas in the area A; the traffic information data comprises the duration time of a traffic peak and the number of times of traffic accidents; the resident information data comprises resident population distribution and resident age data; the consumption information data comprises average consumption level and large consumption data ratio;
the development prediction model comprises land property region distribution of urban building land, wherein the land property comprises residential land, public management and public service facility land, commercial service facility land, industrial land, road and transportation facility land;
the city building land planning scheme group comprises all development prediction model combinations proposed in the virtual expert group.
The Delphi method can absorb the participation of experts in prediction and fully utilize the experience and the learning of the experts; by adopting an anonymous or back-to-back mode, each expert can independently and freely make own judgment; several rounds of feedback are given to the prediction process, so that the opinions of the experts gradually converge.
The prediction by using the Delphi method has certain scientificity and practicability, can avoid the defects of fear of authority and random harmony, or permanent harmony, or unwilling conflict with opinions of other people due to worry, and the like during discussion, avoids subjective consciousness as much as possible, and has certain comprehensive opinion objectivity. Through the thought of the Delphi method, the virtual expert group is used for replacing the real expert group, the intelligent necessity is realized, the subjective consciousness is further weakened, and meanwhile, the system precision is improved through continuous fitting.
According to the above technical solution, in step S2, the establishing of the virtual expert group includes:
s8-1, constructing a real expert group, providing training data of any region to the real expert group, analyzing by each expert in the real expert group, and outputting respective development prediction models, wherein the real expert group is an analysis group consisting of city building planning expert persons;
s8-2, extracting expert characteristics of any expert B, wherein the expert characteristics comprise work seniority, achievement and style;
s8-3, acquiring a development prediction model of the expert B, and constructing the relation between four groups of data of the expert B and land use property region allocation based on the expert characteristics of the expert B;
s8-3-1, expert B includes distributing area x to residential land during land property area distribution operation1Public management and public service facility land use distribution area x2Region x for distributing commercial service facility land3Industrial distribution area x4Distribution area x for road and traffic facilities5Recording the normalized data of the four groups of data at the moment, including the geographic information data y1Traffic information data y2And resident information data y3Consumption information data y4(ii) a And the record stack is y1，y2，y3，y4K, U, where K is a set of scaling functions assigned to the terrain property region, i.e., K ═ a {1，a2，a3，a4，a5}，a1、a2、a3、a4、a5Are respectively x1、x2、x3、x4、x5Area fraction of (a); u is an expert characteristic set of expert B;
s8-3-2, each time a new training data set is input, a stack is obtained and is imported into the database, and a counter is set for counting the number of stacks;
s8-3-3, judging whether the stack number reaches C, wherein C is the upper limit of the recording stack, if so, entering the step S8-3-4, and if not, returning to the step S8-3-2;
s8-3-4, entering deep learning to generate a virtual expert of the real expert B, wherein the virtual expert comprises:
obtaining the difference value between the data of the set K in a group of stacks and the average data 0.2, and marking as a new set K1={a11，a22，a33，a44，a55-there is a negative value in the set, i.e. the data in K minus 0.2 in the set; establishing K1The functional relationship between the medium data and four groups of data on the basis of the expert B, namely the virtual expert evaluation standard:
wherein the content of the first and second substances,
is a set K1Any one of the above-mentioned data items,
are each y1，y2，y3，y4The average influence coefficient of (a);
s8-3-5, establishing a judgment similarity formula of the virtual expert and the real expert:
wherein the content of the first and second substances,
in order to evaluate the similarity difference value,
is the judgment value of the real expert,
is the evaluation value of the virtual expert, and j is the number of participating items;
continuously adding a training group to fit a virtual expert evaluation standard, namely:
wherein h is a fitting value and changes along with the times of the training set;
until the similarity difference values of the continuous G groups are all at the threshold value
MINTherein, wherein
MINIs the lowest similarity threshold;
outputting the judgment standard of the virtual expert at the moment as the virtual expert of the expert B, establishing a corresponding virtual expert for each real expert, and further establishing a virtual expert group.
According to the above technical solution, in steps S2-S5, the creating of the prediction questionnaire further includes:
s9-1, constructing an initial questionnaire, wherein the initial questionnaire at least comprises four kinds of data of an area A;
s9-2, the virtual expert group outputs an initial city building land planning scheme group through analysis according to the initial questionnaire;
s9-3, sorting the time period T, and establishing a prediction questionnaire in batches according to a sorting mode from the past to the present, wherein the prediction questionnaire at least comprises four data of the area A in the current time period T and all the outputted urban building land planning scheme groups;
and S9-4, ending the input until the time period T reaches the current time, and recording the final output as the final urban building land planning scheme group.
According to the above technical solution, in step S5, the weight proportion establishment further includes the intention of the residents, a statistical table is established, the land occupation properties are counted according to the intention of the residents, and a statistical proportion is generated and is recorded as a set R = { R =1，r2，r3，r4，r5}; and using the weight proportion as a weight proportion to finally generate an urban building land planning scheme L as follows:
wherein the content of the first and second substances,
and respectively planning the median of the scheme groups for the final urban construction land.
The representative value of the whole unit mark value determined by the median can not be influenced by the maximum or minimum value of the distribution number sequence, thereby improving the representativeness of the median to the distribution number sequence to a certain extent and meeting the application of the invention.
Compared with the prior art, the invention has the following beneficial effects:
the invention can analyze and arrange four data through time period based on four data in the area, namely geographic information data, traffic information data, resident information data and consumption information data; meanwhile, a deep learning mechanism is established, and a virtual expert group is established through analysis of the real expert group, so that a regional development prediction model is established; moreover, a deep learning model can be continuously fitted based on the condition of similarity, and the system accuracy is ensured; according to the invention, the virtual expert group can continuously weaken the individual subjective consciousness of the real expert group judgment, and continuously enhance the accuracy of the system, so that the judgment of urban building land planning becomes intelligent, a certain rule is met, the working efficiency is improved, and the urban development requirement is met.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of an intelligent planning system and method for urban building sites according to the present invention;
fig. 2 is a schematic step diagram of an intelligent planning method for urban building sites according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides the following technical solutions:
an intelligent planning system for urban building land comprises a regional data acquisition module, a deep learning module, a correction module, a prediction investigation module and an intelligent planning module for building land;
the regional data acquisition module is used for acquiring four kinds of data in a region, wherein the four kinds of data comprise geographic information data, traffic information data, resident information data and consumption information data, and analyzing and sorting the four kinds of data; the deep learning module establishes a virtual expert group through analysis of a real expert group based on a deep learning mechanism and establishes a regional development prediction model; the correction module continuously fits a deep learning model based on the condition of similarity, so that the accuracy of the system is ensured as much as possible; the prediction investigation module is used for establishing a prediction questionnaire and performing prediction investigation through a Delphi method; the building land intelligent planning module is used for carrying out intelligent planning on the urban building land according to the output final urban building land planning scheme group;
the output end of the regional data acquisition module is connected with the input end of the deep learning module; the output end of the deep learning module is connected with the input end of the correction module; the output end of the correction module is connected with the input end of the prediction investigation module; the output end of the prediction investigation module is connected with the input end of the intelligent building land planning module.
The regional data acquisition module comprises a regional data acquisition unit and a time period establishment unit;
the regional data acquisition unit is used for acquiring geographic information data, traffic information data, resident information data and consumption information data in a region; the time period establishing unit is used for establishing a time period and sorting the four data according to the time period;
the output end of the regional data acquisition unit is connected with the input end of the time period establishing unit; and the output end of the time period establishing unit is connected with the input end of the deep learning module.
The deep learning module comprises a feature extraction unit and a training unit;
the characteristic extraction unit is used for extracting expert characteristics of the real expert group and establishing expert characteristics of the virtual expert group; the training unit is used for constructing the judgment standard of the virtual expert group through the continuously increased training data;
the output end of the feature extraction unit is connected with the input end of the training unit; and the output end of the training unit is connected with the input end of the correction module.
The correction module comprises a similarity judgment unit and a fitting unit;
the similarity judging unit is used for judging the similarity between the real expert group and the virtual expert group; the fitting unit is used for fitting the model continuously to ensure the accuracy of the system;
the output end of the similarity judging unit is connected with the input end of the fitting unit; and the output end of the fitting unit is connected with the input end of the prediction investigation module.
The prediction investigation module comprises a questionnaire establishing unit and an output unit;
the questionnaire establishing unit is used for establishing a questionnaire and inputting data for the system; the output unit is used for outputting the urban building land planning scheme group and outputting the final urban building land planning scheme group based on the time period;
the output end of the questionnaire establishing unit is connected with the input end of the output unit; and the output end of the output unit is connected with the input end of the intelligent building land planning module.
An intelligent planning method for urban building land comprises the following steps:
s1, constructing an area, recording the area as an area A, acquiring four data in the area A, establishing a time period, and performing segmented arrangement on the four data according to the time period, namely TiCorresponding to a data group MiData set MiIncluding the region A during the time period TiFour data in, wherein TiIs any one time period;
s2, constructing a virtual expert group based on deep learning, designing a prediction questionnaire, constructing a region A development prediction model, and establishing an initial urban building land planning scheme group;
s3, constructing N groups of data sets based on the time period T, and inputting a first new group of data sets M1Analyzing with the initial city building land planning scheme group by the virtual expert group, and outputting a city building land planning scheme group I1；
S4, inputting new data M of S-th group based on time period TsPlan set I for urban building lands-1After being analyzed by the virtual expert group, the urban building land planning scheme group I is outputsUntil s = N, and outputting the planning plan group I of the city building land at the timeNIs shown byNAs a final output;
and S5, acquiring a median according to the final output, constructing a data weight proportion, and calculating and outputting a final urban building land intelligent planning scheme.
In steps S1-S2, the geographic information data includes mountains, scenic areas, waters in the area a; the traffic information data comprises the duration time of a traffic peak and the number of times of traffic accidents; the resident information data comprises resident population distribution and resident age data; the consumption information data comprises average consumption level and large consumption data ratio;
the development prediction model comprises land property region distribution of urban building land, wherein the land property comprises residential land, public management and public service facility land, commercial service facility land, industrial land, road and transportation facility land;
the city building land planning scheme group comprises all development prediction model combinations proposed in the virtual expert group.
In step S2, the establishing of the virtual expert group includes:
s8-1, constructing a real expert group, providing training data of any region to the real expert group, analyzing by each expert in the real expert group, and outputting respective development prediction models, wherein the real expert group is an analysis group consisting of city building planning expert persons;
s8-2, extracting expert characteristics of any expert B, wherein the expert characteristics comprise work seniority, achievement and style;
s8-3, acquiring a development prediction model of the expert B, and constructing the relation between four groups of data of the expert B and land use property region allocation based on the expert characteristics of the expert B;
s8-3-1, expert B includes distributing area x to residential land during land property area distribution operation1Public management and public service facility land use distribution area x2Region x for distributing commercial service facility land3Industrial distribution area x4Distribution area x for road and traffic facilities5Recording the grouping of four groups of data at this timeNormalized data, including geographic information data y1Traffic information data y2And resident information data y3Consumption information data y4(ii) a And the record stack is y1，y2，y3，y4K, U, where K is a set of scaling functions assigned to the terrain property region, i.e., K ═ a {1，a2，a3，a4，a5}，a1、a2、a3、a4、a5Are respectively x1、x2、x3、x4、x5Area fraction of (a); u is an expert characteristic set of expert B;
s8-3-2, each time a new training data set is input, a stack is obtained and is imported into the database, and a counter is set for counting the number of stacks;
s8-3-3, judging whether the stack number reaches C, wherein C is the upper limit of the recording stack, if so, entering the step S8-3-4, and if not, returning to the step S8-3-2;
s8-3-4, entering deep learning to generate a virtual expert of the real expert B, wherein the virtual expert comprises:
obtaining the difference value between the data of the set K in a group of stacks and the average data 0.2, and marking as a new set K1={a11，a22，a33，a44，a55}, establishing K1The functional relationship between the medium data and four groups of data on the basis of the expert B, namely the virtual expert evaluation standard:
wherein the content of the first and second substances,
is a set K1Any one of the above-mentioned data items,
are each y1，y2，y3，y4The average influence coefficient of (a);
s8-3-5, establishing a judgment similarity formula of the virtual expert and the real expert:
wherein the content of the first and second substances,
in order to evaluate the similarity difference value,
is the judgment value of the real expert,
is the evaluation value of the virtual expert, and j is the number of participating items;
continuously adding a training group to fit a virtual expert evaluation standard, namely:
wherein h is a fitting value and changes along with the times of the training set;
until the similarity difference values of the continuous G groups are all at the threshold value
MINTherein, wherein
MINIs the lowest similarity threshold;
outputting the judgment standard of the virtual expert at the moment as the virtual expert of the expert B, establishing a corresponding virtual expert for each real expert, and further establishing a virtual expert group.
In steps S2-S5, the creating of the prediction questionnaire further comprises:
s9-1, constructing an initial questionnaire, wherein the initial questionnaire at least comprises four kinds of data of an area A;
s9-2, the virtual expert group outputs an initial city building land planning scheme group through analysis according to the initial questionnaire;
s9-3, sorting the time period T, and establishing a prediction questionnaire in batches according to a sorting mode from the past to the present, wherein the prediction questionnaire at least comprises four data of the area A in the current time period T and all the outputted urban building land planning scheme groups;
and S9-4, ending the input until the time period T reaches the current time, and recording the final output as the final urban building land planning scheme group.
In step S5, the weight proportion is established with the intention of the residents, a statistical table is established, the land occupation properties are counted according to the intention of the residents, and a statistical proportion is generated and recorded as a set R = { R =1，r2，r3，r4，r5}; and using the weight proportion as a weight proportion to finally generate an urban building land planning scheme L as follows:
wherein the content of the first and second substances,
and respectively planning the median of the scheme groups for the final urban construction land.
In this embodiment:
constructing a virtual expert group:
constructing a real expert group, providing training data of any region to the real expert group, analyzing by each expert in the real expert group, and outputting respective development prediction models, wherein the real expert group is an analysis group consisting of urban building planning expert persons;
extracting expert characteristics of any expert B, wherein the expert characteristics comprise work seniority, achievement and style;
acquiring a development prediction model of expert B, and establishing the relation between four groups of data of expert B and land property region allocation based on the expert characteristics of expert B;
expert B, in the land property region allocation operation, includes allocating a region x to the residential land1Public management and public service facility land use distribution area x2Region x for distributing commercial service facility land3Industrial distribution area x4Distribution area x for road and traffic facilities5Recording the normalized data of the four groups of data at the moment, including the geographic information data y1Traffic information data y2And resident information data y3Consumption information data y4(ii) a And the record stack is y1，y2，y3，y4K, U, where K is a set of scaling functions assigned to the terrain property region, i.e., K ═ a {1，a2，a3，a4，a5}，a1、a2、a3、a4、a5Are respectively x1、x2、x3、x4、x5Area fraction of (a); u is an expert characteristic set of expert B;
when a new training data set is input, a stack is obtained and is imported into the database, and a counter is arranged for counting the number of the stacks;
judging whether the stack number reaches C, wherein C is the upper limit of the recording stack, if so, entering deep learning to generate a virtual expert of a real expert B, and the method comprises the following steps:
wherein the stack data set is as follows:
{0.3，0.25，0.4，0.6，K，U}
corresponding to K is:
K＝{0.1，0.2，0.3，0.2，0.2}
obtaining the difference value between the data of the set K in a group of stacks and the average data 0.2, and marking as a new set K1K is established by { -0.1, 0, 0.1, 0, 0}1The functional relationship between the medium data and four groups of data on the basis of the expert B, namely the virtual expert evaluation standard:
wherein the content of the first and second substances,
is a set K1Any one of the above-mentioned data items,
are each y1，y2，y3，y4The average influence coefficient of (a);
obtaining the average influence coefficient
Thereby establishing a virtual expert judgment standard;
establishing a judgment similarity formula of the virtual expert and the real expert:
wherein the content of the first and second substances,
in order to evaluate the similarity difference value,
is the judgment value of the real expert,
is the evaluation value of the virtual expert, and j is the number of participating items;
continuously adding a training group to fit a virtual expert evaluation standard, namely:
wherein h is a fitting value and changes along with the times of the training set;
until the similarity difference values of the continuous G groups are all at the threshold value
MINTherein, wherein
MINIs the lowest similarity threshold;
outputting the judgment standard of the virtual expert at the moment as the virtual expert of the expert B, establishing a corresponding virtual expert for each real expert, and further establishing a virtual expert group.
Constructing an initial questionnaire, wherein the initial questionnaire at least comprises four kinds of data of an area A;
the virtual expert group outputs an initial city building land planning scheme group through analysis according to the initial questionnaire;
sorting the time period T, and establishing a prediction questionnaire in batches according to a sorting mode from the past to the present, wherein the prediction questionnaire at least comprises four data of the area A in the current time period T and all the outputted urban building land planning scheme groups;
and ending the input until the time period T reaches the current time, and recording the final output as a final urban building land planning scheme group.
Selecting the final urban building land planning scheme group, and selecting the most representative data in the virtual expert group as the final urban building land planning scheme by taking the median as the reference;
the establishment of the weight proportion further comprises the steps of establishing a statistical table according to the intention of residents, carrying out statistics on land use properties according to the intention of residents, generating a statistical proportion, and recording the statistical proportion as a set R = { R =1，r2，r3，r4，r5}; and using the weight proportion as a weight proportion to finally generate an urban building land planning scheme L as follows:
wherein the content of the first and second substances,
and respectively planning the median of the scheme groups for the final urban construction land.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The utility model provides an intelligent planning system of urban building land which characterized in that: the system comprises a regional data acquisition module, a deep learning module, a correction module, a prediction investigation module and an intelligent building land planning module;
the regional data acquisition module is used for acquiring four kinds of data in a region, wherein the four kinds of data comprise geographic information data, traffic information data, resident information data and consumption information data, and analyzing and sorting the four kinds of data; the deep learning module establishes a virtual expert group through analysis of a real expert group based on a deep learning mechanism and establishes a regional development prediction model; the correction module continuously fits a deep learning model based on the condition of similarity, so that the accuracy of the system is ensured as much as possible; the prediction investigation module is used for establishing a prediction questionnaire and performing prediction investigation through a Delphi method; the building land intelligent planning module is used for carrying out intelligent planning on the urban building land according to the output final urban building land planning scheme group;
the output end of the regional data acquisition module is connected with the input end of the deep learning module; the output end of the deep learning module is connected with the input end of the correction module; the output end of the correction module is connected with the input end of the prediction investigation module; the output end of the prediction investigation module is connected with the input end of the intelligent building land planning module.
2. The intelligent planning system for urban construction land according to claim 1, characterized in that: the regional data acquisition module comprises a regional data acquisition unit and a time period establishment unit;
the regional data acquisition unit is used for acquiring geographic information data, traffic information data, resident information data and consumption information data in a region; the time period establishing unit is used for establishing a time period and sorting the four data according to the time period;
the output end of the regional data acquisition unit is connected with the input end of the time period establishing unit; and the output end of the time period establishing unit is connected with the input end of the deep learning module.
3. The intelligent planning system for urban construction land according to claim 1, characterized in that: the deep learning module comprises a feature extraction unit and a training unit;
the characteristic extraction unit is used for extracting expert characteristics of the real expert group and establishing expert characteristics of the virtual expert group; the training unit is used for constructing the judgment standard of the virtual expert group through the continuously increased training data;
the output end of the feature extraction unit is connected with the input end of the training unit; and the output end of the training unit is connected with the input end of the correction module.
4. The intelligent planning system for urban construction land according to claim 1, characterized in that: the correction module comprises a similarity judgment unit and a fitting unit;
the similarity judging unit is used for judging the similarity between the real expert group and the virtual expert group; the fitting unit is used for fitting the model continuously to ensure the accuracy of the system;
the output end of the similarity judging unit is connected with the input end of the fitting unit; and the output end of the fitting unit is connected with the input end of the prediction investigation module.
5. The intelligent planning system for urban construction land according to claim 1, characterized in that: the prediction investigation module comprises a questionnaire establishing unit and an output unit;
the questionnaire establishing unit is used for establishing a questionnaire and inputting data for the system; the output unit is used for outputting the urban building land planning scheme group and outputting the final urban building land planning scheme group based on the time period;
the output end of the questionnaire establishing unit is connected with the input end of the output unit; and the output end of the output unit is connected with the input end of the intelligent building land planning module.
6. An intelligent planning method for urban building land is characterized by comprising the following steps: the method comprises the following steps:
s1, constructing an area, recording the area as an area A, acquiring four data in the area A, establishing a time period, and performing segmented arrangement on the four data according to the time period, namely TiCorresponding to a data group MiData set MiIncluding the region A during the time period TiFour data in, wherein TiIs any one time period;
s2, constructing a virtual expert group based on deep learning, designing a prediction questionnaire, constructing a region A development prediction model, and establishing an initial urban building land planning scheme group;
s3, constructing N groups of data sets based on the time period T, and inputting a first new group of data sets M1Analyzing with the initial city building land planning scheme group by the virtual expert group, and outputting a city building land planning scheme group I1；
S4, inputting new data M of S-th group based on time period TsPlan set I for urban building lands-1After being analyzed by the virtual expert group, the urban building land planning scheme group I is outputsUntil s = N, and outputting the planning plan group I of the city building land at the timeNIs shown byNAs a final output;
and S5, acquiring a median according to the final output, constructing a data weight proportion, and calculating and outputting a final urban building land intelligent planning scheme.
7. The intelligent planning method for urban building land according to claim 6, wherein the method comprises the following steps: in steps S1-S2, the geographic information data includes mountains, scenic areas, waters in the area a; the traffic information data comprises the duration time of a traffic peak and the number of times of traffic accidents; the resident information data comprises resident population distribution and resident age data; the consumption information data comprises average consumption level and large consumption data ratio;
the development prediction model comprises land property region distribution of urban building land, wherein the land property comprises residential land, public management and public service facility land, commercial service facility land, industrial land, road and transportation facility land;
the city building land planning scheme group comprises all development prediction model combinations proposed in the virtual expert group.
8. The intelligent planning method for urban building land according to claim 7, characterized in that: in step S2, the establishing of the virtual expert group includes:
s8-1, constructing a real expert group, providing training data of any region to the real expert group, analyzing by each expert in the real expert group, and outputting respective development prediction models, wherein the real expert group is an analysis group consisting of city building planning expert persons;
s8-2, extracting expert characteristics of any expert B, wherein the expert characteristics comprise work seniority, achievement and style;
s8-3, acquiring a development prediction model of the expert B, and constructing the relation between four groups of data of the expert B and land use property region allocation based on the expert characteristics of the expert B;
s8-3-1, expert B includes distributing area x to residential land during land property area distribution operation1Public management and public service facility land use distribution area x2Region x for distributing commercial service facility land3Industrial distribution area x4Distribution area x for road and traffic facilities5Recording the normalized data of the four groups of data at the moment, including the geographic information data y1Traffic information data y2And resident information data y3Consumption information data y4(ii) a And the record stack is y1，y2，y3，y4K, U, where K is a set of scaling functions assigned to the terrain property region, i.e., K ═ a {1，a2，a3，a4，a5}，a1、a2、a3、a4、a5Are respectively x1、x2、x3、x4、x5Area fraction of (a); u is an expert characteristic set of expert B;
s8-3-2, each time a new training data set is input, a stack is obtained and is imported into the database, and a counter is set for counting the number of stacks;
s8-3-3, judging whether the stack number reaches C, wherein C is the upper limit of the recording stack, if so, entering the step S8-3-4, and if not, returning to the step S8-3-2;
s8-3-4, entering deep learning to generate a virtual expert of the real expert B, wherein the virtual expert comprises:
obtaining the difference value between the data of the set K in a group of stacks and the average data 0.2, and marking as a new set K1={a11，a22，a33，a44，a55}, establishing K1The functional relationship between the medium data and four groups of data on the basis of the expert B, namely the virtual expert evaluation standard:
wherein the content of the first and second substances,
is a set K1Any one of the above-mentioned data items,
are each y1，y2，y3，y4The average influence coefficient of (a);
s8-3-5, establishing a judgment similarity formula of the virtual expert and the real expert:
wherein the content of the first and second substances,
in order to evaluate the similarity difference value,
is the judgment value of the real expert,
is the evaluation value of the virtual expert, and j is the number of participating items;
continuously adding a training group to fit a virtual expert evaluation standard, namely:
wherein h is a fitting value and changes along with the times of the training set;
until the similarity difference values of the continuous G groups are all at the threshold value
MINTherein, wherein
MINIs the lowest similarity threshold;
outputting the judgment standard of the virtual expert at the moment as the virtual expert of the expert B, establishing a corresponding virtual expert for each real expert, and further establishing a virtual expert group.
9. The intelligent planning method for urban building land according to claim 6, wherein the method comprises the following steps: in steps S2-S5, the creating of the prediction questionnaire further comprises:
s9-1, constructing an initial questionnaire, wherein the initial questionnaire at least comprises four kinds of data of an area A;
s9-2, the virtual expert group outputs an initial city building land planning scheme group through analysis according to the initial questionnaire;
s9-3, sorting the time period T, and establishing a prediction questionnaire in batches according to a sorting mode from the past to the present, wherein the prediction questionnaire at least comprises four data of the area A in the current time period T and all the outputted urban building land planning scheme groups;
and S9-4, ending the input until the time period T reaches the current time, and recording the final output as the final urban building land planning scheme group.
10. According toThe intelligent planning method for urban building land as claimed in claim 9, wherein: in step S5, the weight proportion is established with the intention of the residents, a statistical table is established, the land occupation properties are counted according to the intention of the residents, and a statistical proportion is generated and recorded as a set R = { R =1，r2，r3，r4，r5}; and using the weight proportion as a weight proportion to finally generate an urban building land planning scheme L as follows:
wherein the content of the first and second substances,
and respectively planning the median of the scheme groups for the final urban construction land.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111438533.4A CN113850350B (en) | 2021-11-30 | 2021-11-30 | Urban building land intelligent planning system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111438533.4A CN113850350B (en) | 2021-11-30 | 2021-11-30 | Urban building land intelligent planning system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113850350A true CN113850350A (en) | 2021-12-28 |
| CN113850350B CN113850350B (en) | 2022-04-22 |
Family
ID=78982318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111438533.4A Active CN113850350B (en) | 2021-11-30 | 2021-11-30 | Urban building land intelligent planning system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113850350B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116805175A (en) * | 2023-06-02 | 2023-09-26 | 中哲国际工程设计有限公司 | Medical care building operation and maintenance management system based on CIM technology |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102456158A (en) * | 2010-10-26 | 2012-05-16 | 中国民航大学 | Security assessment method for air traffic management (ATM) information system based on ANNBP (Artificial Neural Network Blood Pressure) model |
| CN106844934A (en) * | 2017-01-17 | 2017-06-13 | 武汉邮电科学研究院 | Smart city planning and designing expert system and smart city planning and designing method |
| CN108304969A (en) * | 2018-01-30 | 2018-07-20 | 东南大学 | A kind of development zone planned land use scale forecast method based on space efficiency |
| CN110008260A (en) * | 2019-03-13 | 2019-07-12 | 武汉零点视觉数字科技有限公司 | A kind of wisdom National land space planning numbers show system |
| CN111079941A (en) * | 2019-12-03 | 2020-04-28 | 武汉纺织大学 | Credit information system combining expert experience model and supervised machine learning algorithm |
| CN113065688A (en) * | 2021-03-18 | 2021-07-02 | 博雅达勘测规划设计集团有限公司 | Territorial function-based territorial space division simulation system, method and terminal |
| CN113505978A (en) * | 2021-06-30 | 2021-10-15 | 煤炭科学研究总院 | Disaster prevention function evaluation method and device for different forms of urban communities |
| CN113592220A (en) * | 2021-06-17 | 2021-11-02 | 国网河北省电力有限公司行唐县供电分公司 | Power grid line loss fine management method based on data mining |
-
2021
- 2021-11-30 CN CN202111438533.4A patent/CN113850350B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102456158A (en) * | 2010-10-26 | 2012-05-16 | 中国民航大学 | Security assessment method for air traffic management (ATM) information system based on ANNBP (Artificial Neural Network Blood Pressure) model |
| CN106844934A (en) * | 2017-01-17 | 2017-06-13 | 武汉邮电科学研究院 | Smart city planning and designing expert system and smart city planning and designing method |
| CN108304969A (en) * | 2018-01-30 | 2018-07-20 | 东南大学 | A kind of development zone planned land use scale forecast method based on space efficiency |
| CN110008260A (en) * | 2019-03-13 | 2019-07-12 | 武汉零点视觉数字科技有限公司 | A kind of wisdom National land space planning numbers show system |
| CN111079941A (en) * | 2019-12-03 | 2020-04-28 | 武汉纺织大学 | Credit information system combining expert experience model and supervised machine learning algorithm |
| CN113065688A (en) * | 2021-03-18 | 2021-07-02 | 博雅达勘测规划设计集团有限公司 | Territorial function-based territorial space division simulation system, method and terminal |
| CN113592220A (en) * | 2021-06-17 | 2021-11-02 | 国网河北省电力有限公司行唐县供电分公司 | Power grid line loss fine management method based on data mining |
| CN113505978A (en) * | 2021-06-30 | 2021-10-15 | 煤炭科学研究总院 | Disaster prevention function evaluation method and device for different forms of urban communities |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116805175A (en) * | 2023-06-02 | 2023-09-26 | 中哲国际工程设计有限公司 | Medical care building operation and maintenance management system based on CIM technology |
| CN116805175B (en) * | 2023-06-02 | 2023-12-26 | 中哲国际工程设计有限公司 | Medical care building operation and maintenance management system based on CIM technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113850350B (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Understanding commuting patterns using transit smart card data | |
| Oribe-Garcia et al. | Identification of influencing municipal characteristics regarding household waste generation and their forecasting ability in Biscay | |
| Jin et al. | Comparison of contingent valuation and choice experiment in solid waste management programs in Macao | |
| Tzeng et al. | Multicriteria analysis of environmental quality in Taipei: public preferences and improvement strategies | |
| CN109299438B (en) | Public transport facility supply level evaluation method based on network appointment data | |
| CN110134865B (en) | Commuting passenger social contact recommendation method and platform based on urban public transport trip big data | |
| Ghodousi et al. | Analyzing public participant data to evaluate citizen satisfaction and to prioritize their needs via K-means, FCM and ICA | |
| CN112348404A (en) | Village planning implementation evaluation system | |
| CN110647692A (en) | Multidimensional travel data monitoring and presenting method based on big data | |
| Jahanshahi et al. | Evaluation and relocating bicycle sharing stations in mashhad city using multi-criteria analysis | |
| CN113850350B (en) | Urban building land intelligent planning system and method | |
| CN107506872A (en) | A kind of residential block part throttle characteristics and the Categorical research method of model prediction | |
| CN115829124A (en) | Charging pile address selection method, device, equipment and storage medium | |
| Shin | The quality of municipal service: Concept, measure and results | |
| CN110633401A (en) | Prediction model of store data and establishment method thereof | |
| Yagi et al. | Joint models of home-based tour mode and destination choices: applications to a developing country | |
| Oses et al. | Monitoring and benchmarking the performance of a destination's hotel industry: the case study of Bilbao in 2014 | |
| CN108133296B (en) | Event attendance prediction method combining environmental data under social network based on events | |
| CN116662860A (en) | User portrait and classification method based on energy big data | |
| CN106127419A (en) | A kind of construction project decision system based on group decision and decision method | |
| CN112508425B (en) | Urban travel user portrait system construction method for elastic public transport system | |
| CN112465396B (en) | Bus scheduling method and system based on station events along line | |
| Hill et al. | Forests' role in tourism: Phase 2 | |
| CN113744525A (en) | Traffic distribution prediction method based on feature extraction and deep learning | |
| Karaman Aksentijević et al. | Tendencies of development inequalities of Croatian counties |
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 |