CN115169922A - Charging pile site selection method based on big data machine learning - Google Patents
Charging pile site selection method based on big data machine learning Download PDFInfo
- Publication number
- CN115169922A CN115169922A CN202210847114.4A CN202210847114A CN115169922A CN 115169922 A CN115169922 A CN 115169922A CN 202210847114 A CN202210847114 A CN 202210847114A CN 115169922 A CN115169922 A CN 115169922A
- Authority
- CN
- China
- Prior art keywords
- data
- charging pile
- building
- regional
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010187 selection method Methods 0.000 title claims abstract description 19
- 238000010801 machine learning Methods 0.000 title claims abstract description 18
- 238000003062 neural network model Methods 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000012216 screening Methods 0.000 claims abstract description 12
- 210000002569 neuron Anatomy 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010219 correlation analysis Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000003631 expected effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000002759 z-score normalization Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Water Supply & Treatment (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Software Systems (AREA)
- Biodiversity & Conservation Biology (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a charging pile address selection method based on big data machine learning, which comprises the following steps: s1: acquiring regional data and charging pile data; s2: analyzing the regional data and the charging pile data in an associated manner, screening the charging pile data meeting the conditions based on a charging pile data threshold value, and updating the regional data; s3: establishing a neural network model based on the updated regional data, and training the neural network model; s4: and (4) taking the area data of the area to be addressed as the input of the neural network model to obtain the building distance, thereby obtaining the position of the charging pile. The invention has the beneficial effects that: the charging pile site selection can be carried out according to the charging pile comprehensive data and the to-be-selected site area attributes, and the effectiveness of the charging pile site selection is guaranteed.
Description
Technical Field
The invention relates to the technical field of charging pile site selection, in particular to a charging pile site selection method based on big data machine learning.
Background
At present, with the development of technology and the requirement of environmental protection, the development of electric vehicles is leapfrog, the technical development of electric vehicles is mature gradually, the driving experience is perfect, but still problems such as limited cruising ability and fixed charging position exist. Therefore, how to rationally plan the public position of charging pile, the promptness and the stability of vehicle charging are guaranteed, and the method has great significance for developing the electric vehicle industry.
In the prior art, charging piles are usually arranged in a parking lot according to attribute information of the parking lot, positions of the charging piles are usually arranged in places such as a residential quarter or an office area according to the number of people living in the residential quarter or the office area, and the problem that site selection of the charging piles cannot be carried out according to comprehensive data of the charging piles and attributes of an area to be selected exists.
For example, a "charging pile site selection method and device" disclosed in chinese patent literature has a publication number: CN109800940B, filing date: in 03.12.2018, a map of a charging pile area to be arranged is divided into a plurality of grids, parking lots corresponding to the grids are counted, traffic demand of the grids is counted according to a pre-collected vehicle position data set, corresponding parking lots are selected from the parking lots according to attribute information of the parking lots, the traffic demand of the grids and the total number of charging piles to be arranged, the corresponding number of parking lots are used as addresses for arranging the charging piles, and the arrangement addresses of the charging piles are finally determined by considering potential charging demands and attribute information of the parking lots.
Disclosure of Invention
Aiming at the defect that the charging pile address selection can not be carried out according to the charging pile comprehensive data and the to-be-addressed area attribute in the prior art, the invention provides the charging pile address selection method based on big data machine learning, the charging pile address selection can be carried out according to the charging pile comprehensive data and the to-be-addressed area attribute, and the charging pile address selection effectiveness is ensured.
The technical scheme is that the charging pile site selection method based on big data machine learning comprises the following steps:
s1: acquiring regional data and charging pile data;
s2: the regional data and the charging pile data are subjected to correlation analysis, the charging pile data meeting the conditions are screened based on the charging pile data threshold value, and the regional data are updated;
s3: establishing a neural network model based on the updated regional data, and training the neural network model;
s4: and (4) taking the area data of the area to be addressed as the input of the neural network model to obtain the building distance, thereby obtaining the position of the charging pile.
According to the technical scheme, regional data and charging pile data are obtained, the regional data and the charging pile data are analyzed in an associated mode, the charging pile data meeting conditions are screened based on a charging pile data threshold value, the regional data are updated, data cleaning is carried out according to the charging pile threshold value, the validity of experimental data is guaranteed, a neural network model is established based on the updated regional data, the neural network model is trained, after model training is guaranteed, the regional data of a region to be selected are used as input of the neural network model, the building distance is obtained, the charging pile position is obtained, the scheme of selecting the charging pile site based on the charging pile comprehensive data threshold value is achieved, and the validity of the charging pile site selection is guaranteed.
Preferably, the regional data includes regional area, regional resident number, regional traffic flow, regional pedestrian flow, regional vehicle holding rate and building data, the building data includes building position, building pedestrian flow, building area, building density, building number and building distance, and the charging pile data includes position, duration of use, number of use and accumulated duration.
Preferably, the region comprehensive data expression is established based on the region data:
wherein S is the area of the area, A is the number of residents in the area, p is the area holding rate, r p Is the regional flow of people, r c Is regional traffic flow, q is building data, a k For the kth building Integrated evaluation, b k Is the building distance of the kth building, r k For the kth building traffic, s k Is the kth building area and σ is the building density.
Preferably, a charging pile comprehensive data expression is established based on charging pile data:
in the formula, n is the number of charging piles, t i Charging pile for the ith to use the total time length, wherein m is the total use times of the ith charging pile and t j The j charging time length of the ith charging pile is obtained.
Preferably, if the comprehensive charging pile data are larger than the threshold value, the data are effective charging pile data, invalid charging pile data are deleted, and the building distance is updated.
In the scheme, charging pile data are used as constraint conditions, and charging pile data with charging pile data larger than a threshold value in a screening area are used as effective data. And screening the charging pile data meeting the conditions based on the charging pile data threshold, deleting the charging pile data which do not meet the charging pile data threshold from the original data, and updating the building distance in the regional data. The effectiveness of the charging pile data is guaranteed through threshold value screening, so that the training of the model also meets the charging pile data threshold value, the scheme of site selection of the charging pile based on the charging pile comprehensive data threshold value is realized, and the effectiveness of site selection of the charging pile is guaranteed.
Preferably, the proportion of the training set and the test set in the neural network model is 4:1, and the data of the training set and the test set are normalized.
In the scheme, updated region data is used as a neural network model data set, a training set and a test set are separated according to the proportion of 4:1, and two data iterators are initialized and used for the training set and the test set respectively. Since there may be sample vectors in the region data that are particularly large or small relative to other input samples, which may cause an increase in training time, and may fail to converge, the region data is normalized by the methods of max-min normalization, Z-score normalization, and function transformation.
Preferably, the expression of the number of hidden layer neurons of the neural network model is as follows:
o∈{1,2,3,4,5}
in the formula, n is the number of neurons in an input layer, m is the number of neurons in an output layer, and o is a compensation constant.
In the scheme, the network calculated amount is increased and the overfitting problem is easy to generate due to the fact that the number of the hidden layer neurons is too large, the network performance is influenced due to the fact that the number of the neurons is too small, the expected effect cannot be achieved, at present, a determined corresponding relation of the number of the hidden layer neurons does not exist, experimental results show that when the number expression of the hidden layer neurons is met, the overfitting problem cannot be generated by a model, the network performance is not influenced, and the effectiveness of model training is guaranteed
Preferably, the training times of the neural network model are set to be 200 times, and the neural network model completes training when the mean square error is less than 0.001.
In the scheme, the training frequency of the neural network model is set to be 200 times, the neural network model completes training when the mean square error is less than 0.001, actually, when the training frequency of the model reaches 120 times, the mean square error is gradually less than 0.001, when the training frequency of the model reaches 150 times, the mean square error is less than 0.001 and the model tends to be stable, and in order to guarantee the training effect, the training frequency of the model is not less than 150 times.
Preferably, the input data of the neural network model comprises area, area resident number, area vehicle holding rate, area passenger flow, area vehicle flow, building passenger flow, building position, building density, building area and building number, the neural network model outputs building distance, and the position of the charging pile is determined according to the building position and the building distance.
According to the technical scheme, the input data of the neural network model comprise the area, the number of residents in the area, the area vehicle holding rate, the area pedestrian flow, the area vehicle flow, the building pedestrian flow, the building position, the building area and the building number, the data are derived from the area data of the area to be planned, the site selection planning of the charging pile is carried out according to specific area data, the training result of the model also meets the comprehensive data threshold value of the charging pile due to the fact that the trained area data are screened through the comprehensive data threshold value of the charging pile, the site selection of the charging pile is carried out based on the comprehensive data threshold value of the charging pile, after the neural network model outputs the building distance, the position relation between the charging pile and the building can be known by combining the building position, the position of each building in the area corresponds to the building distance, and the position of the charging pile can be obtained through mathematical operation or graphic solution.
Preferably, the building location is expressed in terms of longitude and latitude, with the east longitude and north latitude being positive and the west longitude and south latitude being negative.
In the scheme, the building position is represented by longitude and latitude, the longitude and latitude are the combined name of the longitude and the latitude to form a coordinate system, any position on the earth can be marked, the uniqueness of the building position is ensured, the east longitude and the north latitude are positive, and the west longitude and the south latitude are negative, so that mathematical operation is facilitated.
The beneficial effects of the invention are: the charging pile site selection can be carried out according to the charging pile comprehensive data and the to-be-selected site area attributes, and the effectiveness of the charging pile site selection is guaranteed.
Drawings
FIG. 1 is a flow chart of a charging pile address selection method based on big data machine learning.
Detailed Description
The technical scheme of the invention is further specifically described by the following embodiments and the accompanying drawings.
The embodiment is as follows: as shown in fig. 1, a charging pile site selection method based on big data machine learning includes the following steps:
s1: and acquiring regional data and charging pile data.
S2: and performing correlation analysis on the regional data and the charging pile data, screening the charging pile data meeting the conditions based on the charging pile data threshold value, and updating the regional data.
S3: and establishing a neural network model based on the updated region data, and training the neural network model.
S4: and (4) taking the area data of the area to be addressed as the input of the neural network model to obtain the building distance, thereby obtaining the position of the charging pile.
S1: and acquiring regional data and charging pile data.
Specifically, regional data can be obtained from a third party based on big data, wherein the regional data can be obtained according to cities, counties, districts or streets, and regional data within a range of a plurality of kilometers of a specified target point can also be obtained, the regional data comprises regional area, regional resident quantity, regional vehicle flow, regional pedestrian flow, building data and regional vehicle holding rate, the building data comprises building position, building pedestrian flow, building area, building density, building quantity and building distance, the building distance represents the distance between a building and a charging pile, the building position and the target point coordinate are represented by longitude and latitude, east longitude and north latitude are positive, west longitude and south latitude are negative, the building position is represented by longitude and latitude, the longitude and latitude are a coordinate system formed by combining the longitude and the latitude, any position on the earth can be marked, the uniqueness of the building position is ensured, east longitude and north latitude are positive, west longitude and south latitude are negative, and mathematical operation is convenient.
The charging pile data comprise positions, use time, use times and accumulated time.
S2: and performing correlation analysis on the regional data and the charging pile data, screening the charging pile data meeting the conditions based on a threshold value, and updating the regional data.
Specifically, a regional comprehensive data expression is established according to the regional area, the regional number of residents, the regional vehicle holding rate, the regional passenger flow, the regional vehicle flow and the building data, and the regional comprehensive data expression is as follows:
wherein S is the area of the area, A is the number of residents in the area, p is the area holding rate, r p Is the regional flow of people, r c Is regional traffic flow, q is building data, a k For the kth building Integrated evaluation, b k Is the building distance of the kth building, r k For the kth building traffic, s k Is the kth building area and σ is the building density.
According to fill electric pile quantity, fill electric pile total number of times of use, fill electric pile single use time length and fill electric pile total length of use and establish and fill electric pile comprehensive data expression, fill the expression of electric pile comprehensive data as follows:
in the formula, n is the number of charging piles, t i Charging pile for the ith to use the total time length, wherein m is the total use times of the ith charging pile and t j The j charging time length of the ith charging pile is obtained.
And taking the charging pile data as a constraint condition, and screening the charging pile data with the charging pile data larger than a threshold value in the area as effective data.
P≥P 0
And screening the charging pile data meeting the conditions based on the charging pile data threshold value, deleting the charging pile data which do not meet the charging pile data threshold value from the original data, and updating the building distance in the regional data. And taking the charging pile data as constraint conditions, and screening the charging pile data with the charging pile data larger than a threshold value in the area as effective data. And screening the charging pile data meeting the conditions based on the charging pile data threshold, deleting the charging pile data which do not meet the charging pile data threshold from the original data, and updating the building distance in the regional data. The effectiveness of the charging pile data is guaranteed through threshold value screening, so that the training of the model also meets the charging pile data threshold value, the scheme of site selection of the charging pile based on the charging pile comprehensive data threshold value is realized, and the effectiveness of site selection of the charging pile is guaranteed.
S3: and establishing a neural network model based on the updated regional data, and training the neural network model.
Specifically, the updated region data is used as a neural network model data set, a training set and a test set are separated according to the proportion of 4:1, and two data iterators are initialized and used for the training set and the test set respectively.
Since there may be sample vectors in the region data that are particularly large or small relative to other input samples, which may cause an increase in training time, and may fail to converge, the region data is normalized by the methods of max-min normalization, Z-score normalization, and function transformation.
The neural network model is constructed, the training times are set to be 200 times, the calculated amount of the network is increased and the overfitting problem is easy to generate due to the fact that the number of neurons in the hidden layer is too large, the performance of the network is affected due to the fact that the number of the neurons is too small, the expected effect cannot be achieved, and the number of the neurons in the hidden layer is planned by adopting the following expression:
o∈{1,2,3,4,5}
in the formula, n is the number of neurons in an input layer, m is the number of neurons in an output layer, and o is a compensation constant.
At present, a determined corresponding relation of the number of hidden layer neurons does not exist, and experimental results show that when the expression of the number of hidden layer neurons is met, the model cannot generate an overfitting problem, network performance is not affected, and effectiveness of model training is guaranteed.
The training precision of the neural network model is judged by the mean square error, and when the mean square error is less than 0.001, the model meets the precision requirement. The training frequency of the neural network model is set to be 200 times, the neural network model completes training when the mean square error is smaller than 0.001, actually, the mean square error is gradually smaller than 0.001 when the training frequency of the model reaches 120 times, the mean square error is smaller than 0.001 and the model tends to be stable when the training frequency of the model reaches 150 times, and the training frequency of the model is not smaller than 150 times in order to guarantee the training effect.
S4: and (4) inputting the area data of the area to be addressed as the neural network model to obtain the building distance, so as to obtain the position of the charging pile.
Specifically, after training of the neural network model is completed and accuracy requirements are met, inputting area data of an area to be located into the neural network model as input data, wherein the input data of the neural network model comprises area, area resident quantity, area vehicle holding rate, area pedestrian flow, area vehicle flow, building pedestrian flow, building positions, building density, building area and building quantity, the data are derived from the area data of the area to be planned, location planning of the charging pile is carried out according to specific area data, the training result of the model also meets the comprehensive data threshold of the charging pile due to the fact that the trained area data are screened through the comprehensive data threshold of the charging pile, location selection based on the comprehensive data threshold of the charging pile is achieved, building distances are output after the neural network model is processed, the obtained data are denormalized to obtain predicted data, after the building distances are output by the neural network model, the position relation between the charging pile and the building positions can be known by combining the building positions, and the positions of the charging piles can be solved through mathematical operation or graphics.
Claims (10)
1. A charging pile site selection method based on big data machine learning is characterized by comprising the following steps:
s1: acquiring regional data and charging pile data;
s2: analyzing the regional data and the charging pile data in an associated manner, screening the charging pile data meeting the conditions based on a charging pile data threshold value, and updating the regional data;
s3: establishing a neural network model based on the updated regional data, and training the neural network model;
s4: and (4) taking the area data of the area to be addressed as the input of the neural network model to obtain the building distance, thereby obtaining the position of the charging pile.
2. The charging pile site selection method based on big data machine learning as claimed in claim 1, wherein the regional data comprises regional area, regional resident number, regional traffic flow, regional pedestrian flow, regional vehicle holding rate and building data, the building data comprises building position, building pedestrian flow, building area, building density, building number and building distance, and the charging pile data comprises position, duration of use, number of use and accumulated duration.
3. The big data machine learning-based charging pile address selection method according to claim 1, wherein a regional comprehensive data expression is established based on regional data:
wherein S is the area of the area, A is the number of residents in the area, p is the area holding rate, r p Is the regional flow of people, r c Is regional traffic flow, q is building data, a k For the kth building Integrated evaluation, b k Is the building distance of the kth building, r k For the kth building traffic, s k Is the kth building area and σ is the building density.
4. The big data machine learning-based charging pile site selection method according to claim 1, wherein a charging pile comprehensive data expression is constructed based on charging pile data:
in the formula, n is the number of charging piles, t i Charging pile for the ith is long in total use time, m is the total use times of the ith charging pile, and t j The charging time of the jth charging pile is the jth charging time.
5. The charging pile site selection method based on big data machine learning, as claimed in claim 4, is characterized in that if the charging pile comprehensive data is larger than a threshold value, the charging pile comprehensive data is effective charging pile data, invalid charging pile data is deleted, and the building distance is updated.
6. The big data machine learning-based charging pile site selection method as claimed in claim 1, wherein the ratio of the training set to the test set in the neural network model is 4:1, and the data of the training set and the test set are normalized.
7. The big data machine learning-based charging pile address selection method according to claim 1, wherein the neural network model hidden layer neuron number expression is as follows:
o∈{1,2,3,4,5}
in the formula, n is the number of neurons in an input layer, m is the number of neurons in an output layer, and o is a compensation constant.
8. The charging pile site selection method based on big data machine learning of claim 1, wherein training times of the neural network model are set to 200 times, and the neural network model completes training when a mean square error is less than 0.001.
9. The big data machine learning-based charging pile site selection method according to claim 1, wherein input data of the neural network model comprise regional area, regional number of residents, regional vehicle holding rate, regional pedestrian flow, regional vehicle flow, building pedestrian flow, building position, building density, building area and building number, the neural network model outputs building distance, and the position of the charging pile is determined according to the building position and the building distance.
10. The big data machine learning-based charging pile site selection method according to claim 9, wherein the building location is expressed in longitude and latitude, east longitude and north latitude are positive, and west longitude and south latitude are negative.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210847114.4A CN115169922A (en) | 2022-07-07 | 2022-07-07 | Charging pile site selection method based on big data machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210847114.4A CN115169922A (en) | 2022-07-07 | 2022-07-07 | Charging pile site selection method based on big data machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115169922A true CN115169922A (en) | 2022-10-11 |
Family
ID=83495109
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210847114.4A Pending CN115169922A (en) | 2022-07-07 | 2022-07-07 | Charging pile site selection method based on big data machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115169922A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829633A (en) * | 2023-02-16 | 2023-03-21 | 中测智联(深圳)科技有限公司 | Charging pile design system based on big data city new energy carrier distribution |
-
2022
- 2022-07-07 CN CN202210847114.4A patent/CN115169922A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829633A (en) * | 2023-02-16 | 2023-03-21 | 中测智联(深圳)科技有限公司 | Charging pile design system based on big data city new energy carrier distribution |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107016851B (en) | The method that a kind of quantitative analysis city built environment influences road journey time | |
| CN108446470B (en) | Medical facility accessibility analysis method based on vehicle trajectory data and population distribution | |
| Boeing | Off the grid… and back again? The recent evolution of American street network planning and design | |
| CN111814596B (en) | Automatic city function partitioning method for fusing remote sensing image and taxi track | |
| CN110399445B (en) | Method, device and equipment for processing interest points | |
| Zhang et al. | Using street view images to identify road noise barriers with ensemble classification model and geospatial analysis | |
| CN115169922A (en) | Charging pile site selection method based on big data machine learning | |
| Kazak et al. | Land use change in suburban zone: European context of urban sprawl | |
| Chung et al. | Investigating the effects of POI-based land use on traffic accidents in Suzhou Industrial Park, China | |
| CN118014297A (en) | Intelligent evaluation method and system for supply and demand responsiveness of outdoor fitness facility | |
| CN104318319A (en) | Multi-agent urban expansion simulation method based on land acquisition process competition result | |
| CN117993707A (en) | Urban road collapse disaster risk assessment method and system based on artificial intelligence | |
| CN113672788A (en) | Urban building function classification method based on multi-source data and weight coefficient method | |
| CN117436653A (en) | Prediction model construction method and prediction method for travel demands of network about vehicles | |
| Mohammadi et al. | Probabilistic prediction of trip travel time and its variability using hierarchical Bayesian learning | |
| Huo et al. | Exploring the influencing factors on demand-responsive customized bus ridership using multi-source data | |
| CN109508749A (en) | A kind of cluster analysis system and method based on deep knowledge expression | |
| CN110515961A (en) | A kind of Fundamental Geographic Information System based on space-time big data is upgraded demand evaluation method | |
| CN114863272A (en) | Method and system for determining influence strength of urban vegetation on urban comprehensive vitality | |
| CN108874993A (en) | The display methods and device of a kind of urban planning in map | |
| CN113343781B (en) | City functional area identification method using remote sensing data and taxi track data | |
| Vanichrujee et al. | Taxi demand prediction using ensemble model and taxi GPS data analysis | |
| EP4343576A1 (en) | Method, apparatus, and computer program product for map data conflation | |
| CN111832527B (en) | Residential area extraction and type identification method based on remote sensing and social sensing data | |
| Hazarika et al. | Road Network Analysis of Major Destinations in Guwahati City Using GIS |
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 |