CN117852722B - Electric vehicle charging demand prediction method, device, equipment and storage medium - Google Patents
Electric vehicle charging demand prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117852722B CN117852722B CN202410087744.5A CN202410087744A CN117852722B CN 117852722 B CN117852722 B CN 117852722B CN 202410087744 A CN202410087744 A CN 202410087744A CN 117852722 B CN117852722 B CN 117852722B
- Authority
- CN
- China
- Prior art keywords
- charging
- data
- user
- vehicle
- distance
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
本发明涉及电动车辆技术领域，公开了一种电动汽车充电需求预测方法、装置、设备及存储介质。该方法包括获取预设区域内的车辆轨迹数据；基于密度的时空聚类算法处理车辆轨迹数据，以剔除漂移点获得常驻点；根据车辆轨迹数据中的充电状态和经纬度数据确定充电位置；根据常驻点和充电位置确定用户的充电距离集合；根据预设非参数估计算法分析充电距离集合获得充电距离容忍度的概率密度分布曲线，以进行电动汽车充电需求预测。本发明充分考虑到轨迹数据漂移导致分析结果不够精准的问题，通过密度的时空聚类算法剔除漂移点得到高精度的电动汽车用户充电距离容忍度的概率密度分布曲线，作为制定电动汽车引导策略时分析充电偏好的参考依据。
The present invention relates to the technical field of electric vehicles, and discloses a method, device, equipment and storage medium for predicting charging demand of electric vehicles. The method includes obtaining vehicle trajectory data within a preset area; processing the vehicle trajectory data based on a density-based spatiotemporal clustering algorithm to remove drift points to obtain permanent points; determining the charging location according to the charging status and longitude and latitude data in the vehicle trajectory data; determining the user's charging distance set according to the permanent points and the charging location; analyzing the charging distance set according to a preset non-parametric estimation algorithm to obtain a probability density distribution curve of charging distance tolerance, so as to predict the charging demand of electric vehicles. The present invention fully considers the problem that the drift of trajectory data leads to inaccurate analysis results, and removes drift points through a density-based spatiotemporal clustering algorithm to obtain a high-precision probability density distribution curve of the charging distance tolerance of electric vehicle users, which serves as a reference for analyzing charging preferences when formulating electric vehicle guidance strategies.
Description
Technical Field
The present invention relates to the field of electric vehicle technologies, and in particular, to a method, an apparatus, a device, and a storage medium for predicting a charging demand of an electric vehicle.
Background
With the increasing market share of electric vehicles in recent years, people travel more conveniently in daily life and simultaneously generate massive electric vehicle data. In the related technology for constructing user portraits for charging users of electric vehicles and guiding the charging behaviors of the users, a method for calculating the charging distance tolerance of the users of the electric vehicles aiming at large data volume is lacking, and differentiated accurate services aiming at different types of users cannot be realized.
At present, in the method for evaluating and classifying the power customer tolerance, cluster analysis of the customer tolerance is carried out based on a customer group, group tolerance characteristics are mined, and a power customer tolerance classification result distributed according to space is obtained. The scheme can guide and optimize customer service, can implement differentiated and accurate service for customers with large data volume, improves customer satisfaction and has important application value. The behavior data image and the charging data image are generally carried out on the user of the electric automobile through the user charging behavior image processing, including a charging period, the sensitivity of the user to electric charge and the like, but the analysis result is not accurate enough due to the fact that the track data drift is not considered, and calculation of tolerance of different users to the charging distance is lacking.
Disclosure of Invention
The invention mainly aims to provide a method, a device, equipment and a storage medium for predicting the charging demand of an electric automobile, and aims to solve the problems that the tolerance evaluation analysis result of the existing electric power customer is not accurate enough and the like.
In order to achieve the above object, the present invention provides a method for predicting charging demand of an electric vehicle, including:
acquiring vehicle track data of a vehicle in a preset area;
Processing the vehicle track data based on a density space-time clustering algorithm to remove drift points and obtain the resident points of the user;
determining a charging position of the vehicle according to the charging state and longitude and latitude data in the vehicle track data;
determining a charging distance set of a user according to the constant standing point and the charging position;
analyzing the charging distance set according to a preset non-parameter estimation algorithm to obtain a probability density distribution curve of the charging distance tolerance;
and predicting the charging requirement of the electric automobile based on the probability density distribution curve.
In some embodiments, the acquiring vehicle track data of the vehicle in the preset area includes:
acquiring track data of a vehicle in a preset area;
Processing and cleaning the track data to obtain a user travel track section;
Generating vehicle track data according to the user travel track section; the vehicle track data comprise longitude and latitude data of vehicle running in the preset area and the charging state of the vehicle.
In some embodiments, the processing and cleaning the track data to obtain a user travel track segment includes:
Generating a track point set of a complete travel chain based on the track data; each position point in the track point set comprises longitude, latitude, a time stamp and a corresponding charging state;
Deleting travel track point data, wherein the travel time is smaller than preset time, the travel distance is smaller than preset distance and the travel track point data is smaller than the preset number of track data points in the travel process, in the track point set;
deleting the track point data outside the preset area range in the track point set;
And deleting the abnormal track point data with the deleted position offset in the track point set to obtain a user travel track section.
In some embodiments, the density-based spatio-temporal clustering algorithm processes the vehicle trajectory data to reject drift points, and obtains resident points of a user, including:
According to a DBSCAN clustering algorithm, the vehicle track data are clustered into a plurality of clusters according to the activity radius, so that drift points are eliminated, and a data set of each cluster is used as a new input;
Determining a resident area of a user according to the radius parameters of the DBSCAN clustering algorithm;
And solving the position of the centroid of the resident region according to iterative aggregation of the K-means algorithm, and taking the position of the centroid as a resident point of a user.
In some embodiments, the determining the set of charging distances for the user from the constant standing point and the charging location includes:
Determining the distance between the charging position and the resident point according to a Euclidean distance formula by taking the resident point as a circle center;
constructing sequence data based on the distance, and taking the sequence data as a user tolerance charging distance range;
and generating a charging distance set of the user according to the sequence data.
In some embodiments, the analyzing the set of charging distances according to a preset non-parametric estimation algorithm to obtain a probability density distribution curve of charging distance tolerance includes:
generating a plurality of independent random sample data with the same distribution according to the charging distance set;
Based on a kernel density estimation algorithm, combining the independent random sample data with the same distribution to obtain a conventional probability density function of the tolerance distance of the user to the charging station;
carrying out non-parametric kernel density estimation on the conventional probability density function based on a Gaussian kernel function to obtain a Gaussian probability density function;
the Gaussian probability density function is improved by a self-adaptive diffusion Gaussian kernel density estimation algorithm based on a diffusion equation so as to obtain a self-adaptive diffusion kernel density estimation model;
and solving the self-adaptive diffusion kernel density estimation model to obtain a probability density distribution curve of the charging distance tolerance.
In some embodiments, the solving the adaptive diffusion kernel density estimation model to obtain a probability density distribution curve of charging distance tolerance comprises:
Carrying out Taylor expansion according to an average integral square error calculation formula and omitting a high-order term to obtain a progressive integral mean square error;
solving an optimal bandwidth of the adaptive diffusion kernel density estimation model based on the progressive integral mean square error;
After the self-adaptive diffusion kernel density estimation model is solved, fitting is carried out on the charging distance tolerance probability density curve of the electric automobile user according to the measured data, so as to obtain the probability density distribution curve of the electric automobile user on the charging distance tolerance.
In addition, in order to achieve the above object, the present invention further provides an electric vehicle charging demand prediction apparatus, including:
the data acquisition module is used for acquiring vehicle track data of the vehicle in a preset area;
the data processing module is used for processing the vehicle track data based on a density space-time clustering algorithm so as to remove drift points and obtain resident points of a user;
the position determining module is used for determining the charging position of the vehicle according to the charging state and longitude and latitude data in the vehicle track data;
The set determining module is used for determining a charging distance set of the user according to the constant standing point and the charging position;
the estimation analysis module is used for analyzing the charging distance set according to a preset non-parameter estimation algorithm so as to obtain a probability density distribution curve of the charging distance tolerance;
And the demand prediction module is used for predicting the charging demand of the electric automobile based on the probability density distribution curve.
In addition, in order to achieve the above object, the present invention also proposes an electric vehicle charging demand prediction apparatus, including: the system comprises a memory, a processor and an electric vehicle charging demand prediction program stored on the memory and capable of running on the processor, wherein the electric vehicle charging demand prediction program is configured to realize the electric vehicle charging demand prediction method.
In addition, in order to achieve the above object, the present invention also proposes a storage medium storing an electric vehicle charging demand prediction program for causing a processor to implement the electric vehicle charging demand prediction method as described above when executed.
The invention provides a method for predicting charging requirements of an electric automobile, which comprises the following steps: acquiring vehicle track data of a vehicle in a preset area; processing the vehicle track data based on a density space-time clustering algorithm to remove drift points and obtain the resident points of the user; determining a charging position of the vehicle according to the charging state and longitude and latitude data in the vehicle track data; determining a charging distance set of a user according to the constant standing point and the charging position; analyzing the charging distance set according to a preset non-parameter estimation algorithm to obtain a probability density distribution curve of the charging distance tolerance; and predicting the charging requirement of the electric automobile based on the probability density distribution curve. According to the method, the problem that the analysis result is not accurate enough due to track data drift is fully considered, drift points are removed through a density space-time clustering algorithm, a probability density distribution curve of the charging distance tolerance of the electric vehicle user is obtained, the result can be used as a reference basis for analyzing the charging preference of the electric vehicle group when an electric vehicle guiding strategy is formulated, and therefore the problems that the existing electric vehicle user tolerance evaluation analysis result is not accurate enough and the like are solved.
Drawings
Fig. 1 is a schematic structural diagram of an electric vehicle charging demand prediction device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an embodiment of a method for predicting a charging demand of an electric vehicle according to the present invention;
FIG. 3 is a schematic diagram illustrating a specific operation flow of the method for predicting the charging demand of an electric vehicle according to the present invention;
fig. 4 is a block diagram illustrating an embodiment of a charging demand prediction apparatus for an electric vehicle according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that all directional indicators (such as up, down, left, right, front, and rear … …) in the embodiments of the present invention are merely used to explain the relative positional relationship, movement, etc. between the components in a particular posture (as shown in the drawings), and if the particular posture is changed, the directional indicator is changed accordingly.
Furthermore, the description of "first," "second," etc. in this disclosure is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an electric vehicle charging demand prediction apparatus in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the electric vehicle charging demand prediction apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM Memory) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the electric vehicle charging demand prediction apparatus, and may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and an electric vehicle charging demand prediction program may be included in the memory 1005 as one type of storage medium.
In the electric vehicle charging demand prediction apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electric vehicle charging demand prediction device of the present invention may be provided in the electric vehicle charging demand prediction device, where the electric vehicle charging demand prediction device invokes an electric vehicle charging demand prediction program stored in the memory 1005 through the processor 1001, and executes the electric vehicle charging demand prediction method provided by the embodiment of the present invention.
The invention provides a method, a device, equipment and a storage medium for predicting the charging demand of an electric automobile.
An embodiment of the invention provides a method for predicting charging requirements of an electric vehicle, and referring to fig. 2, fig. 2 is a flow chart of an embodiment of the method for predicting charging requirements of an electric vehicle.
As shown in fig. 2, the method for predicting the charging demand of the electric automobile includes:
step S100: acquiring vehicle track data of a vehicle in a preset area;
Step S200: processing the vehicle track data based on a density space-time clustering algorithm to remove drift points and obtain the resident points of the user;
step S300: determining a charging position of the vehicle according to the charging state and longitude and latitude data in the vehicle track data;
Step S400: determining a charging distance set of a user according to the constant standing point and the charging position;
Step S500: analyzing the charging distance set according to a preset non-parameter estimation algorithm to obtain a probability density distribution curve of the charging distance tolerance;
step S600: and predicting the charging requirement of the electric automobile based on the probability density distribution curve.
It should be noted that, the execution body in this embodiment may be an electric vehicle charging demand prediction device, and the electric vehicle charging demand prediction device may be a computer device with a data processing function, or may be other devices that may implement the same or similar functions, which is not limited in this embodiment, and in this embodiment, a computer device is taken as an example for description.
Referring to fig. 3, the embodiment provides a method for calculating the charging distance tolerance distribution of an electric automobile user in consideration of track data drift, which comprises the following steps:
A. Acquiring track data of the vehicle in a preset area, including processing and cleaning the data, and acquiring a final user travel track section: the vehicle track data comprise longitude and latitude data of vehicle running in a preset area and the charging state of the vehicle;
B. based on the vehicle track data in the step A, the drift points are effectively removed by using a density-based space-time clustering algorithm, the resident areas and the resident points of the user are obtained, and the charging position of the vehicle is judged based on the charging state of the vehicle and longitude and latitude coordinates;
C. And B, calculating the distance between the vehicle charging and the resident point based on the resident point and the charging position in the step B by taking the resident point as the center of a circle, taking the obtained sequence data as the charging distance range which can be tolerated by the user, and analyzing the tolerance of the user to the distance of the charging station by using a non-parameter estimation method.
The steps of this embodiment will be described in detail with reference to fig. 2 and 3:
In one embodiment, acquiring vehicle trajectory data of a vehicle in a preset area includes: acquiring track data of a vehicle in a preset area; processing and cleaning the track data to obtain a user travel track section; generating vehicle track data according to the user travel track section; the vehicle track data comprise longitude and latitude data of vehicle running in the preset area and the charging state of the vehicle.
The method includes the steps of obtaining track data of a vehicle in a preset area, including processing and cleaning the data, and obtaining a final user travel track section: the vehicle track data comprises longitude and latitude data of vehicle running in a preset area and the charging state of the vehicle.
In an embodiment, processing and cleaning the track data to obtain a travel track segment of the user includes: generating a track point set of a complete travel chain based on the track data; each position point in the track point set comprises longitude, latitude, a time stamp and a corresponding charging state; deleting travel track point data, wherein the travel time is smaller than preset time, the travel distance is smaller than preset distance and the travel track point data is smaller than the preset number of track data points in the travel process, in the track point set; deleting the track point data outside the preset area range in the track point set; and deleting the abnormal track point data with the deleted position offset in the track point set to obtain a user travel track section.
The processing and cleaning of the data are carried out to obtain a final user travel track section, specifically:
(1) And counting a track point set of the complete travel chain. Dividing the daily track data points into a plurality of sets according to the daily travel times, and recording the sets as a complete journey chain which is expressed as N is the length of the track, where each location point contains a longitude, latitude, timestamp and corresponding state of charge,Wherein, the method comprises the steps of, wherein,Represents a longitude of the person in question,Representing latitude,The time stamp is represented, the charge state is represented, the state 0 is not charged, and the state 1 is in charge. The daily travel times are recorded as one travel end when the GPS coordinates of the vehicle are not changed for more than thirty minutes.
(2) And deleting the travel data track point set with travel time less than one minute, travel distance less than 500 meters and less than 10 track data points in the travel process.
(3) Track point data outside the range of the investigation region (e.g. the preset region) is deleted.
(4) And deleting the abnormal track point data with the position offset. The abnormal track point data is the included angle between the travel chain track point p i and the previous track point p i-1 and the next track point p i+1 Is an acute angle, an included angleThe calculation mode of (a) is as follows:
Wherein a is the distance between the i-1 th sampling point and the i-1 th sampling point, b is the distance between the i-1 th sampling point and the i+1 th sampling point, and c is the distance between the i-1 th sampling point and the i+1 th sampling point.
In an embodiment, the processing the vehicle track data by a density-based space-time clustering algorithm to eliminate drift points and obtain resident points of a user includes: according to a DBSCAN clustering algorithm, the vehicle track data are clustered into a plurality of clusters according to the activity radius, so that drift points are eliminated, and a data set of each cluster is used as a new input; determining a resident area of a user according to the radius parameters of the DBSCAN clustering algorithm; and solving the position of the centroid of the resident region according to iterative aggregation of the K-means algorithm, and taking the position of the centroid as a resident point of a user.
By way of example, the drift points can be effectively removed by using a density-based space-time clustering algorithm, and the resident region and the clustering center point of the user are obtained, specifically:
Considering the noise of outlier drift points, the drift points are often outlier and isolated and are insufficient to form a cluster, so that the drift points can be effectively removed by adopting a density-based space-time clustering algorithm, a track dataset of a user is aggregated into a plurality of clusters according to the activity radius by using the density reachable characteristic of a DBSCAN algorithm, the dataset of each cluster is used as a new input, and the position of a centroid is obtained by using iterative aggregation of a K-means algorithm and is used as the normally standing point position of the user. The radius of activity is the radius parameter eps of the DBSCAN clustering algorithm, which is determined according to the size of the activity range of the electric automobile User, and the activity range Scope (User i) of any User i can be calculated by the following formula:
Lon imax、Lonimin is the maximum value and the minimum value of latitude coordinates in the user position data, lat imax、Latimin is the maximum value and the minimum value of longitude coordinates in the user position data, R is the earth radius, and 6371km can be taken. The radius parameter eps is determined according to the function fitted by the user track data of different movable ranges: 。
In one embodiment, the charging position of the vehicle is determined according to the charging state and longitude and latitude data in the vehicle track data: each position point in the vehicle track data comprises longitude, latitude, a time stamp and a corresponding charging state, and the charging position of the vehicle can be judged based on the charging state of the vehicle and longitude and latitude coordinates.
In an embodiment, determining the set of charging distances for the user according to the constant standing point and the charging position includes: determining the distance between the charging position and the resident point according to a Euclidean distance formula by taking the resident point as a circle center; constructing sequence data based on the distance, and taking the sequence data as a user tolerance charging distance range; and generating a charging distance set of the user according to the sequence data.
Specifically, based on the constant standing point and the charging position, the distance between the vehicle charging and the constant standing point is calculated by taking the constant standing point as the circle center, and the obtained sequence data is used as the charging distance range which can be tolerated by the user.
In an embodiment, analyzing the charging distance set according to a preset non-parameter estimation algorithm to obtain a probability density distribution curve of charging distance tolerance includes: generating a plurality of independent random sample data with the same distribution according to the charging distance set; based on a kernel density estimation algorithm, combining the independent random sample data with the same distribution to obtain a conventional probability density function of the tolerance distance of the user to the charging station; carrying out non-parametric kernel density estimation on the conventional probability density function based on a Gaussian kernel function to obtain a Gaussian probability density function; the Gaussian probability density function is improved by a self-adaptive diffusion Gaussian kernel density estimation algorithm based on a diffusion equation so as to obtain a self-adaptive diffusion kernel density estimation model; and solving the self-adaptive diffusion kernel density estimation model to obtain a probability density distribution curve of the charging distance tolerance.
The method for obtaining the probability density distribution curve of the charging distance tolerance comprises the following steps of: carrying out Taylor expansion according to an average integral square error calculation formula and omitting a high-order term to obtain a progressive integral mean square error; solving an optimal bandwidth of the adaptive diffusion kernel density estimation model based on the progressive integral mean square error; after the self-adaptive diffusion kernel density estimation model is solved, fitting is carried out on the charging distance tolerance probability density curve of the electric automobile user according to the measured data, so as to obtain the probability density distribution curve of the electric automobile user on the charging distance tolerance.
Illustratively, a non-parametric estimation method is utilized to analyze the user's tolerance to charging station distance, specifically: probability modeling of distance tolerance when an electric vehicle user selects a charging station is performed using adaptive diffusion kernel density estimation. Assuming x 1,x2,…,xn (sequence data) as n independent co-distributed random sample data of the tolerance distance of the user to the charging station, the true probability density function of the tolerance distance of the user to the charging station isProbability density function obtained by conventional kernel density estimation methodThe formula of (2) is:
Wherein x 1,x2,…,xN is the actual measurement distance of the tolerance distance of the user to the charging station, h represents the bandwidth, N represents the total sample amount, Representing a kernel function. In this embodiment, since the gaussian kernel function can well reflect the sample distribution characteristics, the gaussian kernel function is selected to perform non-parameter kernel density estimation, and then the formula of the kernel density estimation based on the gaussian kernel function is:
Because the user has uncertainty and fluctuation on the sample data of the tolerance distance of the charging station, the overall data density is uneven, the influence of the selection of the bandwidth h on the estimation result is very obvious, and the self-adaptive diffusion Gaussian kernel density estimation model based on a diffusion equation is used, the local adaptability of the self-adaptive diffusion Gaussian kernel density estimation model is improved by improving the traditional Gaussian kernel density estimation method, the optimal bandwidth is selected, and the probability density estimation and the kernel function expression thereof are as follows:
where K (X, X i, t) is a diffusion Gaussian kernel function, a (X) and p (X) are positive functions defining any second derivative in the domain, X, y represent random variables in the domain of the kernel function definition, and linear diffusion parameters can be obtained by adjusting a (X) and p (X) And adjusting.
It should be noted that, according to the kernel density estimation theory, a calculation formula of average integral square Error (MEAN INTEGRATED square Error, MISE) is generally adopted to perform taylor expansion and omit a higher order term to obtain a progressive integral mean square Error, then an optimal bandwidth of a proposed adaptive diffusion kernel density estimation model is solved, and when the progressive integral mean square Error obtains a minimum value, the corresponding optimal bandwidth is obtained:
In the method, in the process of the invention, 。
It can be understood that after the adaptive diffusion kernel density estimation model is completed, actually measured data is used for fitting the probability density curve of the charging distance tolerance of the electric automobile user, so as to obtain the probability density distribution curve of the charging distance tolerance of the electric automobile user.
It should be noted that, with reference to fig. 2 and fig. 3, a specific embodiment is used to describe the technical solution and effects of this embodiment in detail:
in the step A, track data of the vehicle in a preset area is obtained, wherein the track data comprises the steps of processing and cleaning the data, and a final user travel track section is obtained:
Specifically, in this embodiment, the preset area may be set according to actual needs, for example, the preset area may be a region or a range of a certain city, and the track data is a GPS track sampling point of an electric automobile in the area, including information such as sampling time, vehicle status, and the like, and abnormal value cleaning processing or null value filling processing is performed on the track data, so as to obtain the processed track data. Considering that the original track point data is huge in quantity and severely disordered, track data points are divided into a plurality of sets according to the travel times, when the track point longitude and latitude data are unchanged and exceed 30 minutes, the travel of the electric automobile is finished for a plurality of times, and a plurality of complete travel chains exist, the track data points are corresponding to the plurality of track data point sets, so that the sets of track points of the electric automobile which are ordered according to time points by taking the travel times as a unit can be generated. On the basis, the included angle between each track point and the track points at two adjacent moments is calculated, when the included angle is an acute angle, the position of the track point is judged to be deviated, the GPS data sampling time can be set to be 10S, the track point updating frequency is fast, and therefore the track points are directly deleted when abnormal deviation points occur, and new data points are not needed to be replaced. If the data volume is small, the average value of 6 sampling points before and after can be taken for filling.
In the step B, drift points are effectively removed by using a space-time clustering algorithm based on density, a resident area and a clustering center point of a user are obtained, and the charging position of the vehicle is judged based on the charging state of the vehicle and longitude and latitude coordinates:
Specifically, in this embodiment, firstly, according to the sizes of the active ranges of different users, a functional relationship between the active ranges Scope of different users and the cluster radius parameters eps is fitted, so that the clustering algorithm can automatically select the corresponding radius parameter sizes according to the travel habits of different users, and the situations that the radius parameters eps are too small to select, the number of clusters is too large, and the effective resident points cannot be identified due to too large selection are avoided. For example, selecting data of 10 groups of users with different movable ranges, and performing polynomial fitting on 10 groups of Scope-eps samples for three times to obtain the function:
Taking a travel track of a certain user as an example, counting travel track data of the user within 3 months, calculating travel activity range of the user, measuring distance between geographic positions by using spherical distance to obtain radius parameters of a DBSCAN algorithm, using the DBSCAN algorithm to aggregate geographic position data sets of the user into a plurality of clusters according to the activity radius, taking the data set of each cluster as a new input, using iterative aggregation of a K-means algorithm to obtain the position of a centroid, setting a K value as 1, and obtaining longitude and latitude data of a resident point of the user. And judging the charging place of the user according to the charging state, and obtaining longitude and latitude coordinate data of the charging position.
In the step C, the distance between the vehicle charging and the resident point is calculated by taking the resident point as the center of a circle, the obtained sequence data is used as the charging distance range which can be tolerated by the user, and the tolerance of the user to the distance of the charging station is analyzed by utilizing a non-parameter estimation method:
Specifically, in this embodiment, taking a certain user as an example, calculating the coordinates of the frequent standing point and the coordinate data of the charging position according to the step B, taking a series of calculation results as a set of actual measurement data of the charging distance of the user, and fitting the actual measurement data according to the kernel diffusion probability estimation method in the step C, so as to obtain the charging distance tolerance probability density curve of the electric automobile user. If the distribution condition of the charging distance tolerance of the whole user in the area is to be analyzed, the charging distance actual measurement data of all users are used as a set, and then the fitting is carried out by using a nuclear density diffusion estimation method.
The embodiment obtains the vehicle track data of the vehicle in a preset area; processing the vehicle track data based on a density space-time clustering algorithm to remove drift points and obtain the resident points of the user; determining a charging position of the vehicle according to the charging state and longitude and latitude data in the vehicle track data; determining a charging distance set of a user according to the constant standing point and the charging position; analyzing the charging distance set according to a preset non-parameter estimation algorithm to obtain a probability density distribution curve of the charging distance tolerance; and predicting the charging requirement of the electric automobile based on the probability density distribution curve. In the embodiment, the problem that the analysis result is not accurate enough due to the drift of the track data is fully considered, the drift points are removed through a density space-time clustering algorithm, a probability density distribution curve of the charging distance tolerance of the electric vehicle user is obtained, the result can be used as a reference basis for analyzing the charging preference of the electric vehicle group when an electric vehicle guiding strategy is formulated, and therefore the problems that the existing electric vehicle user tolerance evaluation analysis result is not accurate enough and the like are solved.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium stores an electric vehicle charging demand prediction program, and the electric vehicle charging demand prediction program realizes the steps of the electric vehicle charging demand prediction method when being executed by a processor.
Referring to fig. 4, fig. 4 is a block diagram illustrating an embodiment of a charging demand prediction apparatus for an electric vehicle according to the present invention.
As shown in fig. 4, the electric vehicle charging demand prediction apparatus includes:
A data acquisition module 10, configured to acquire vehicle track data of a vehicle in a preset area;
The data processing module 20 is used for processing the vehicle track data based on a density space-time clustering algorithm to remove drift points and obtain resident points of a user;
A position determining module 30, configured to determine a charging position of the vehicle according to the charging state and longitude and latitude data in the vehicle track data;
A set determining module 40, configured to determine a set of charging distances of the user according to the constant standing point and the charging position;
the estimation analysis module 50 is configured to analyze the charging distance set according to a preset non-parameter estimation algorithm, so as to obtain a probability density distribution curve of the charging distance tolerance;
The demand prediction module 60 is configured to predict a charging demand of the electric vehicle based on the probability density distribution curve.
According to the electric vehicle charging demand prediction device, in the embodiment, the problem that analysis results are not accurate enough due to track data drift is fully considered through the electric vehicle charging demand prediction device, drift points are removed through a density-based space-time clustering algorithm, a probability density distribution curve of the charging distance tolerance of electric vehicle users is obtained, the result can be used as a reference basis for analyzing charging preference of electric vehicle groups when an electric vehicle guiding strategy is formulated, and therefore the problems that the existing electric power customer tolerance evaluation analysis results are not accurate enough and the like are solved.
In addition, technical details not described in detail in the embodiment of the present electric vehicle charging demand prediction apparatus may be referred to the electric vehicle charging demand prediction method provided in any embodiment of the present invention, which is applied to the above-described electric vehicle charging demand prediction method, and will not be described herein.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (6)
1. The electric automobile charging demand prediction method is characterized by comprising the following steps of:
acquiring vehicle track data of a vehicle in a preset area;
Processing the vehicle track data based on a density space-time clustering algorithm to remove drift points and obtain the resident points of the user;
determining a charging position of the vehicle according to the charging state and longitude and latitude data in the vehicle track data;
determining a charging distance set of a user according to the constant standing point and the charging position;
analyzing the charging distance set according to a preset non-parameter estimation algorithm to obtain a probability density distribution curve of the charging distance tolerance;
Carrying out electric vehicle charging demand prediction based on the probability density distribution curve;
The density-based space-time clustering algorithm processes the vehicle track data to remove drift points, and obtains resident points of a user, and the method comprises the following steps: according to a DBSCAN clustering algorithm, the vehicle track data are clustered into a plurality of clusters according to the activity radius, so that drift points are eliminated, and a data set of each cluster is used as a new input; determining a resident area of a user according to the radius parameters of the DBSCAN clustering algorithm; according to iterative aggregation of the K-means algorithm, the position of the centroid of the resident area is obtained, and the position of the centroid is used as a resident point of a user; the radius of activity is a radius parameter eps of the DBSCAN clustering algorithm, which is determined according to the size of the range of activity of the electric automobile User, and for any User i, the range of activity Scope (User i) thereof can be calculated by the following formula:
；
Wherein Lon imax、Lonimin is the maximum value and the minimum value of latitude coordinates in the user position data, lat imax、Latimin is the maximum value and the minimum value of longitude coordinates in the user position data, R is the earth radius, 6371km is taken, and radius parameter eps is determined according to the function fitted by the user track data of different movable ranges: ；
The determining the charging distance set of the user according to the constant standing point and the charging position comprises the following steps: determining the distance between the charging position and the resident point according to a Euclidean distance formula by taking the resident point as a circle center; constructing sequence data based on the distance, and taking the sequence data as a user tolerance charging distance range; generating a charging distance set of a user according to the sequence data;
The analyzing the charging distance set according to a preset non-parameter estimation algorithm to obtain a probability density distribution curve of the charging distance tolerance comprises the following steps: generating a plurality of independent random sample data with the same distribution according to the charging distance set; based on a kernel density estimation algorithm, combining the independent random sample data with the same distribution to obtain a conventional probability density function of the tolerance distance of the user to the charging station; carrying out non-parametric kernel density estimation on the conventional probability density function based on a Gaussian kernel function to obtain a Gaussian probability density function; the Gaussian probability density function is improved by a self-adaptive diffusion Gaussian kernel density estimation algorithm based on a diffusion equation so as to obtain a self-adaptive diffusion kernel density estimation model; solving the self-adaptive diffusion kernel density estimation model to obtain a probability density distribution curve of the charging distance tolerance;
The solving the adaptive diffusion kernel density estimation model to obtain a probability density distribution curve of charging distance tolerance comprises: carrying out Taylor expansion according to an average integral square error calculation formula and omitting a high-order term to obtain a progressive integral mean square error; solving an optimal bandwidth of the adaptive diffusion kernel density estimation model based on the progressive integral mean square error; after the self-adaptive diffusion kernel density estimation model is solved, fitting is carried out on the charging distance tolerance probability density curve of the electric automobile user according to the measured data, so as to obtain the probability density distribution curve of the electric automobile user on the charging distance tolerance.
2. The method of claim 1, wherein the acquiring vehicle trajectory data for the vehicle within the predetermined area comprises:
acquiring track data of a vehicle in a preset area;
Processing and cleaning the track data to obtain a user travel track section;
Generating vehicle track data according to the user travel track section; the vehicle track data comprise longitude and latitude data of vehicle running in the preset area and the charging state of the vehicle.
3. The method of claim 2, wherein the processing and cleaning the trajectory data to obtain a user travel trajectory segment comprises:
Generating a track point set of a complete travel chain based on the track data; each position point in the track point set comprises longitude, latitude, a time stamp and a corresponding charging state;
Deleting travel track point data, wherein the travel time is smaller than preset time, the travel distance is smaller than preset distance and the travel track point data is smaller than the preset number of track data points in the travel process, in the track point set;
deleting the track point data outside the preset area range in the track point set;
And deleting the abnormal track point data with the deleted position offset in the track point set to obtain a user travel track section.
4. An electric vehicle charging demand prediction apparatus, comprising:
the data acquisition module is used for acquiring vehicle track data of the vehicle in a preset area;
the data processing module is used for processing the vehicle track data based on a density space-time clustering algorithm so as to remove drift points and obtain resident points of a user;
the position determining module is used for determining the charging position of the vehicle according to the charging state and longitude and latitude data in the vehicle track data;
The set determining module is used for determining a charging distance set of the user according to the constant standing point and the charging position;
the estimation analysis module is used for analyzing the charging distance set according to a preset non-parameter estimation algorithm so as to obtain a probability density distribution curve of the charging distance tolerance;
the demand prediction module is used for predicting the charging demand of the electric automobile based on the probability density distribution curve;
The density-based space-time clustering algorithm processes the vehicle track data to remove drift points, and obtains resident points of a user, and the method comprises the following steps: according to a DBSCAN clustering algorithm, the vehicle track data are clustered into a plurality of clusters according to the activity radius, so that drift points are eliminated, and a data set of each cluster is used as a new input; determining a resident area of a user according to the radius parameters of the DBSCAN clustering algorithm; according to iterative aggregation of the K-means algorithm, the position of the centroid of the resident area is obtained, and the position of the centroid is used as a resident point of a user; the radius of activity is a radius parameter eps of the DBSCAN clustering algorithm, which is determined according to the size of the range of activity of the electric automobile User, and for any User i, the range of activity Scope (User i) thereof can be calculated by the following formula:
；
Wherein Lon imax、Lonimin is the maximum value and the minimum value of latitude coordinates in the user position data, lat imax、Latimin is the maximum value and the minimum value of longitude coordinates in the user position data, R is the earth radius, 6371km is taken, and radius parameter eps is determined according to the function fitted by the user track data of different movable ranges: ；
The determining the charging distance set of the user according to the constant standing point and the charging position comprises the following steps: determining the distance between the charging position and the resident point according to a Euclidean distance formula by taking the resident point as a circle center; constructing sequence data based on the distance, and taking the sequence data as a user tolerance charging distance range; generating a charging distance set of a user according to the sequence data;
The analyzing the charging distance set according to a preset non-parameter estimation algorithm to obtain a probability density distribution curve of the charging distance tolerance comprises the following steps: generating a plurality of independent random sample data with the same distribution according to the charging distance set; based on a kernel density estimation algorithm, combining the independent random sample data with the same distribution to obtain a conventional probability density function of the tolerance distance of the user to the charging station; carrying out non-parametric kernel density estimation on the conventional probability density function based on a Gaussian kernel function to obtain a Gaussian probability density function; the Gaussian probability density function is improved by a self-adaptive diffusion Gaussian kernel density estimation algorithm based on a diffusion equation so as to obtain a self-adaptive diffusion kernel density estimation model; solving the self-adaptive diffusion kernel density estimation model to obtain a probability density distribution curve of the charging distance tolerance;
The solving the adaptive diffusion kernel density estimation model to obtain a probability density distribution curve of charging distance tolerance comprises: carrying out Taylor expansion according to an average integral square error calculation formula and omitting a high-order term to obtain a progressive integral mean square error; solving an optimal bandwidth of the adaptive diffusion kernel density estimation model based on the progressive integral mean square error; after the self-adaptive diffusion kernel density estimation model is solved, fitting is carried out on the charging distance tolerance probability density curve of the electric automobile user according to the measured data, so as to obtain the probability density distribution curve of the electric automobile user on the charging distance tolerance.
5. Electric automobile charging demand prediction equipment, its characterized in that, electric automobile charging demand prediction equipment includes: a memory, a processor, and an electric vehicle charging demand prediction program stored on the memory and operable on the processor, the electric vehicle charging demand prediction program configured to implement the electric vehicle charging demand prediction method of any one of claims 1 to 3.
6. A storage medium storing an electric vehicle charging demand prediction program for causing a processor to execute the electric vehicle charging demand prediction method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410087744.5A CN117852722B (en) | 2024-01-22 | 2024-01-22 | Electric vehicle charging demand prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410087744.5A CN117852722B (en) | 2024-01-22 | 2024-01-22 | Electric vehicle charging demand prediction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117852722A CN117852722A (en) | 2024-04-09 |
| CN117852722B true CN117852722B (en) | 2024-07-09 |
Family
ID=90538062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410087744.5A Active CN117852722B (en) | 2024-01-22 | 2024-01-22 | Electric vehicle charging demand prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117852722B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182446A (en) * | 2017-12-13 | 2018-06-19 | 北京中交兴路信息科技有限公司 | A kind of driver's permanent residence Forecasting Methodology and device based on clustering algorithm |
| WO2019023324A1 (en) * | 2017-07-26 | 2019-01-31 | Via Transportation, Inc. | Systems and methods for managing and routing ridesharing vehicles |
-
2024
- 2024-01-22 CN CN202410087744.5A patent/CN117852722B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019023324A1 (en) * | 2017-07-26 | 2019-01-31 | Via Transportation, Inc. | Systems and methods for managing and routing ridesharing vehicles |
| CN108182446A (en) * | 2017-12-13 | 2018-06-19 | 北京中交兴路信息科技有限公司 | A kind of driver's permanent residence Forecasting Methodology and device based on clustering algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117852722A (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101982159B1 (en) | A method of measuring floating population using information on floating population divided by category | |
| Wang et al. | Predictability and prediction of human mobility based on application-collected location data | |
| CN111460076B (en) | Driving route familiarity determination method, driving route familiarity determination device, computer device, and storage medium | |
| US20150088766A1 (en) | Automated-valuation-model training-data optimization systems and methods | |
| CN108596648A (en) | A kind of commercial circle determination method and device | |
| CN111475746B (en) | Point-of-interest mining method, device, computer equipment and storage medium | |
| CN106776925B (en) | Method, server and system for predicting gender of mobile terminal user | |
| JP2013036887A (en) | Observed value reliability assessing apparatus, observed value reliability assessing method, and observed value reliability assessing program | |
| CN109769210A (en) | Method, device and computer equipment for judging similarity of user activity area | |
| CN109948066A (en) | A kind of point of interest recommended method based on Heterogeneous Information network | |
| CN119513636B (en) | A method, system and device for clustering analysis of population based on spatiotemporal data | |
| US20230245002A1 (en) | Stationary Classifier for Geographic Route Trace Data | |
| EP3192061B1 (en) | Measuring and diagnosing noise in urban environment | |
| CN110377846B (en) | Social relationship mining method, device, storage medium and computer equipment | |
| CN115412852A (en) | Method and system for determining motion trail of mobile terminal | |
| CN117852722B (en) | Electric vehicle charging demand prediction method, device, equipment and storage medium | |
| CN111104607A (en) | Location recommendation method and device based on sign-in data | |
| CN114048391A (en) | A method for recommending interest activities based on geographic grid | |
| CN111667920B (en) | Crowd close contact investigation method based on positioning data | |
| EP3182738B1 (en) | Method and means for triggering at least one action based on geolocation and user information, places and user habits | |
| CN118525286B (en) | Optimization of the network of electric vehicle charging stations | |
| CN113282844A (en) | Method and device for determining priority | |
| CN115510317B (en) | Cloud-edge collaborative interest point recommendation method and device | |
| CN117291638A (en) | Business circle division method, device, terminal equipment and storage medium | |
| CN112800346B (en) | POI recommendation method and system integrated into spatial relationship |
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 |