CN113344277A - Prediction model training method, state updating method, device, equipment and medium - Google Patents
Prediction model training method, state updating method, device, equipment and medium Download PDFInfo
- Publication number
- CN113344277A CN113344277A CN202110672041.5A CN202110672041A CN113344277A CN 113344277 A CN113344277 A CN 113344277A CN 202110672041 A CN202110672041 A CN 202110672041A CN 113344277 A CN113344277 A CN 113344277A
- Authority
- CN
- China
- Prior art keywords
- charging station
- data
- track
- electric quantity
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000012549 training Methods 0.000 title claims abstract description 48
- 238000005065 mining Methods 0.000 claims abstract description 24
- 238000005070 sampling Methods 0.000 claims description 56
- 238000004590 computer program Methods 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 8
- 230000003203 everyday effect Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 17
- 238000012545 processing Methods 0.000 abstract description 17
- 238000013135 deep learning Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 8
- 239000013598 vector Substances 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 5
- 230000005611 electricity Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000003924 mental process Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 230000000007 visual 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G06Q50/40—
Abstract
The present disclosure provides a state prediction model training method, a state updating method, an apparatus, a device, a medium, and a program product for a charging station, which relate to the field of data processing, and in particular, to intelligent transportation, big data, and deep learning technologies. The specific implementation scheme is as follows: acquiring track data and electric quantity data from historical data of a vehicle; mining sample characteristics according to road network data, attribute data of the charging station and the track data and electric quantity data, and constructing sample data according to the sample characteristics, wherein the sample characteristics are used for describing factors related to whether the charging station is available or not; training a state prediction model by using the sample data, wherein the state prediction model is used for predicting the state of whether the charging station is available. The method and the device can effectively utilize the state prediction model to improve the automatic updating efficiency and accuracy of the state information of the charging station in the map.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to intelligent transportation, big data, and deep learning technologies, and in particular, to a prediction model training method, a state updating method, apparatus, device, medium, and program product.
Background
With the increasing of the quantity of new energy vehicles in China, the charging pile industry is rapidly developed as an important infrastructure for supporting the development of new energy vehicles.
In the map APP, each charging station is a POI (point of interest), and each charging station POI includes dynamic and static data such as a name, a location, a state, a charging pile number, power, an idle number, and the like. The state of the charging station describes the open and closed states of the charging station, and if the state information is not updated in time, the use efficiency of the charging station and the charging experience of a user are greatly influenced.
Disclosure of Invention
The present disclosure provides a state prediction model training method, a state updating method, an apparatus, a device, a medium, and a program product for a charging station to improve the automatic updating efficiency and accuracy of charging station information.
According to an aspect of the present disclosure, there is provided a state prediction model training method for a charging station, including:
acquiring track data and electric quantity data from historical data of a vehicle;
mining sample characteristics according to road network data, attribute data of the charging station and the track data and electric quantity data, and constructing sample data according to the sample characteristics, wherein the sample characteristics are used for describing factors related to whether the charging station is available or not;
training a state prediction model by using the sample data, wherein the state prediction model is used for predicting the state of whether the charging station is available.
According to another aspect of the present disclosure, there is provided a status updating method for a charging station, including:
acquiring track data and electric quantity data of a vehicle in a set time period;
performing feature mining according to the road network data, the attribute data of the charging station, the track data and the electric quantity data to obtain the characteristics of the charging station;
predicting the state of the charging station according to the charging station characteristics by using a state prediction model trained by the method according to any embodiment of the disclosure;
and updating the state of the charging station according to the prediction result.
According to another aspect of the present disclosure, there is provided a state prediction model training apparatus for a charging station, including:
the historical data acquisition module is used for acquiring track data and electric quantity data from the historical data of the vehicle;
the sample data construction module is used for mining sample characteristics according to road network data, attribute data of the charging station, the track data and the electric quantity data and constructing sample data according to the sample characteristics, wherein the sample characteristics are used for describing factors related to whether the charging station is available or not;
and the model training module is used for training a state prediction model by using the sample data, wherein the state prediction model is used for predicting the state of whether the charging station is available.
According to another aspect of the present disclosure, there is provided a status updating apparatus for a charging station, including:
the data acquisition module is used for acquiring track data and electric quantity data of the vehicle within a set time period;
the characteristic mining module is used for mining characteristics according to the road network data, the attribute data of the charging station, the track data and the electric quantity data to obtain the characteristics of the charging station;
a state prediction module configured to predict a state of a charging station according to the charging station characteristics using a state prediction model trained by the apparatus according to any embodiment of the present disclosure;
and the state updating module is used for updating the state of the charging station according to the prediction result.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a state prediction model training method for a charging station according to any embodiment of the disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a state prediction model training method for a charging station according to any embodiment of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the state prediction model training method for a charging station according to any of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a status updating method for a charging station according to any embodiment of the disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the status updating method for a charging station according to any embodiment of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the status updating method for a charging station according to any of the embodiments of the present disclosure.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram of a state prediction model training method for a charging station, according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a state prediction model training method for a charging station, according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a status update method for a charging station according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a state prediction model training apparatus for a charging station according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a status updating apparatus for a charging station according to an embodiment of the present disclosure;
FIG. 6 is a block diagram of an electronic device for implementing a state prediction model training method for a charging station of an embodiment of the present disclosure;
fig. 7 is a schematic diagram of a trajectory of a vehicle heading to a charging station for charging, according to an embodiment of the disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic flow chart of a state prediction model training method for a charging station according to an embodiment of the present disclosure, which is applicable to a situation of updating a state of a charging station on a map, and relates to the field of data processing, in particular to intelligent transportation, big data and deep learning technologies. The method may be performed by a state prediction model training apparatus for a charging station, which is implemented in software and/or hardware, and is preferably configured in an electronic device, such as a computer device or a server. As shown in fig. 1, the method specifically includes the following steps:
s101, obtaining track data and electric quantity data from historical data of the vehicle.
Specifically, since the charging stations are usually installed on the sides of roads, in underground parking lots or in residential areas, the user driving to the charging stations appears on the track as a pattern of driving off the road, entering the charging stations, charging, leaving the charging stations, and driving on the road. Fig. 7 is a schematic diagram of a track of a vehicle going to a charging station for charging according to an embodiment of the disclosure. Fig. 7 depicts a charging trajectory for a vehicle traveling to a charging station (station), where the vehicle travels to a charging station beside route a- > G for charging, travels from point B to the road to station, enters station from point D via point C, exits station from point E, and travels to the road to continue traveling from point F. The whole track comprises the steps of driving away from the road, entering a charging station to stop and charge, leaving the charging station after charging is finished, and driving into the road again to continue the journey.
Generally, when a user goes to a charging station for charging, the user can leave the charging station when finding that the charging station is unavailable, and the electric quantity of the vehicle machine cannot be increased; when the charging station is available, the user can select charging, the electric quantity of the vehicle is increased after charging, and if more vehicles waiting for charging are available, the vehicle needs to wait for charging in a queue; of course, the user may also choose to leave without charging when the charging station is found to be available, while the amount of power still does not increase. Therefore, if the electric quantity before the vehicle enters the charging station is less than the electric quantity when the vehicle leaves the charging station, indicating that the user performs charging action at the charging station, the charging station can be considered to be available; if the amount of electricity before the vehicle enters the charging station is greater than or equal to the amount of electricity when the vehicle leaves the charging station, it indicates that the user is not charging at the charging station, which may be because the charging station is not available, or because the user leaves the charging station by himself due to other reasons, such as long queuing time, other charging stations nearby, etc.
In summary, whether a charging station is available or not can be determined at least by analyzing the trajectory of the vehicle and the change in the vehicle's charge, and therefore, the trajectory data and the charge data are closely related to whether a charging station is available or not.
S102, mining sample characteristics according to road network data, attribute data of the charging station, the track data and the electric quantity data, and constructing sample data according to the sample characteristics, wherein the sample characteristics are used for describing factors related to whether the charging station is available or not.
S103, training a state prediction model by using the sample data, wherein the state prediction model is used for predicting the state of whether the charging station is available.
The state prediction model may be, for example, a binary model, and the state prediction model is used to predict the state of the charging station and provide a state prediction result indicating whether the charging station is available or unavailable. Therefore, the sample data used for training the model includes a positive sample and a negative sample, wherein the positive sample represents that the charging station is available, and the negative sample represents that the charging station is not available, and both have sample labeling information that the corresponding charging station is available or unavailable. During training, the model is trained by taking sample data with sample labeling information as input of the model, and a prediction result obtained in the training process is continuously close to a true value of labeling. Sample characteristics in the sample data are used to describe factors relating to whether a charging station is available, and need to be obtained through data mining.
Specifically, as described above, the trajectory data and the electric quantity data are closely related to whether the charging station is available. Accordingly, if the track of the vehicle going to a certain charging station needs to be determined, the vehicle needs to be associated with the road network, and the pure track data may also contain noise, so that the track information associated with the road network is more accurate. In addition, the attribute information of the charging station itself, such as the number of charging piles or the location and cost of the charging station, can be used to analyze the service capability of the charging station, including whether queuing is often required or the charging efficiency, the willingness of the user to charge at the charging station, and the like, which are related to the reason why the vehicle is not charged at the charging station. Therefore, the road network data and the attributes of the charging stations are also closely related to whether the charging stations are available. Therefore, the embodiment of the disclosure excavates sample characteristics according to road network data, attribute data of a charging station, trajectory data and electric quantity data, and constructs sample data according to the sample characteristics.
The sample characteristics are not unique in type, so that the purpose of describing whether the charging station is available or not from multiple angles is achieved. These factors may include, for example, a high capacity of the charging station, a low number of other charging stations in the area of the charging station, too many vehicles that need to be charged around the charging station during a certain period of time, a low value of the vehicle's electrical charge when leaving the charging station, a low value of the vehicle's electrical charge when arriving at the charging station, a dwell time of the vehicle at the charging station, and a user's heat of search for the charging station. The abundant sample characteristics can improve the training effect of the model, enable the model to fully learn the characteristics related to whether the charging station is available, and then improve the accuracy of model prediction. It should be noted that, the embodiment of the present disclosure does not limit the specific content of the sample feature at all, and features that can be used to describe factors related to whether a charging station is available or not can be used in the embodiment of the present disclosure.
In an implementation mode, sample data can be represented in a sample vector mode, different states of the charging station at different moments can be used as one sample, meanwhile, a certain charging station can also correspond to a plurality of samples in a current certain state, each sample is formed by a feature vector and a sample label and is used as a sample vector of the sample, and the training effect of the model can be improved due to abundant training data. If the status of a certain charging station at a certain time is available, the sample of this sample may be labeled with a "1", meaning that a positive sample is labeled, and if the status is not available, may be labeled with a "0", meaning that a negative sample is labeled. Each sample vector comprises data of a plurality of dimensions, the sample label can be used as one dimension, and different types of sample characteristics are used as other dimensions in the sample vector. The plurality of different sample vectors may differ in characteristics of a dimension or a plurality of dimensions. In practice, each sample vector may be normalized, and the processed data may be used as an input of the model to train the model.
The state prediction model can adopt a Wide + Deep + Recurrent classic structure, wherein the input of a Wide module is normalized continuous characteristics and discrete characteristics after coding, and the module is used for learning the direct linear relation between the input characteristics and the target variable and has stronger memory capacity; the input of the Deep module is low-dimensional dense vector representation of normalized continuous features and discrete features after embedding, and the Deep module is used for learning the abstract relation behind data and has strong generalization capability; the input to the Recurrent module is a sequence feature that captures the relationship of time series data to target variables. In addition, for time-dependent sequence features, weight attenuation needs to be performed according to time, and the feature weight that is farther away is lower, and the feature weight of the time-series sequence that is closer is higher. Of course, the present disclosure does not set any limit to the model structure of the state prediction model.
According to the technical scheme, the sample characteristics are mined from road network data, attribute data of the charging station, track data and electric quantity data, sample data is constructed, a state prediction model capable of predicting the state of the charging station is trained by using the sample data, so that the automatic updating efficiency and accuracy of the state information of the charging station in the map are effectively improved by using the model, the influences of three-party cooperation data quality, low user feedback coverage and the like are avoided, the state updating efficiency of the charging station is improved, and the service experience of the map user related to the charging station is improved.
Fig. 2 is a schematic flow chart of a state prediction model training method for a charging station according to an embodiment of the present disclosure, which is further optimized based on the above embodiment. As shown in fig. 2, the method specifically includes the following steps:
s201, obtaining track data and electric quantity data from historical data of the vehicle.
S202, mapping each track point in the track data to a road network to obtain track matching road network data.
Because a vehicle runs on a road, GPS points are influenced by precision and surrounding buildings and may drift, all track points in a track are mapped to a road network through a road network matching algorithm (MapMatch), track matching road network data can be obtained, attributes of the road where the track is located can be conveniently fused, and then the whole navigation process can be described from a global or local angle, for example, the number of passing traffic lights, the length of the road, the average number of passing roads and other characteristics can be obtained through subsequent data analysis and characteristic mining.
And S203, assigning the electric quantity value of each sampling point in the electric quantity data to each track point in the track matching road network data to obtain electric quantity matching track data.
The electric quantity matching track assigns the electric quantity value to each track point through the sampling timestamp, and characteristic information such as electric quantity change characteristics of the vehicle at different positions on the track can be conveniently acquired.
Specifically, in an embodiment, assigning the electric quantity value of each sampling point in the electric quantity data to each track point in the track matching road network data may include: determining the track sampling frequency of the track matching road network data and the electric quantity sampling frequency of the electric quantity data; if the electric quantity sampling frequency is the same as the track sampling frequency, the electric quantity value of each sampling point in the electric quantity data can be directly assigned to each track point in the track matching road network data; and if the electric quantity sampling frequency is different from the track sampling frequency, the electric quantity sampling frequency is the same through down-sampling, and then the electric quantity value of each sampling point in the adjusted electric quantity data is assigned to each track point in the track matching road network data. Through the process, the accuracy of the electric quantity matching track can be improved.
In addition, in another embodiment, if the electric quantity sampling frequency is lower than the track sampling frequency, the electric quantity value of each sampling point in the electric quantity data can be assigned to each track point in the track matching road network data, and then the electric quantity data of the un-assigned track points is subjected to smoothing processing according to the assigned electric quantity of the track points around the track points; if the electric quantity sampling frequency is higher than the track sampling frequency, the electric quantity data can be directly subjected to down-sampling, so that the electric quantity sampling frequency is the same as the track sampling frequency, and then the electric quantity value of each sampling point in the down-sampled electric quantity data is assigned to each track point in the track matching road network data.
And S204, mining sample characteristics according to the road network data, the attribute data of the charging station and the electric quantity matching track data.
Wherein the sample characteristics include at least a charging station attribute, charging station history information, adjacent road information, and area information around a charging station. Each type of sample feature is described in detail below.
1. The charging station attributes include at least one of: number of charging piles, power or cost.
Specifically, the more the charging piles are, the higher the service capacity of the charging station is, the lower the possibility that the user is queued up, the lower the probability that the user leaves because the user cannot tolerate queuing up, and the higher the probability that the user is unavailable when leaving the charging station without increasing the amount of electricity compared with entering the charging station. Similarly, the higher the power of the charging pile is, the faster the charging is, and the higher the traffic flow is possibly. The lower the cost of the charging station, the stronger the willingness of the user to go to the charging station for charging may be. Thus, by analyzing the attributes of the charging station, the reason why the vehicle is charged or not charged at the charging station can be directly or indirectly determined, which in turn serves as a factor in describing whether the state of the charging station is available.
2. The charging station history information includes at least one of the following information within a set period of time before occurrence of a vehicle trajectory passing through the current charging station: the track quantity of each day, and the electric quantity change data before and after the vehicle passes through the current charging station of each day.
Further, the charging station history information may further include: and searching the heat of the current charging station every day in a set time period before the vehicle track of the current charging station occurs.
Specifically, the vehicles passing through the charging stations of the positive sample and the negative sample can be determined according to the determined positive sample and the determined negative sample, and then the track quantity of each day and the electric quantity change data before and after the vehicles pass through the current charging stations in the set time period before the track occurs are determined. The set time period may be, for example, the past week, which is not limited in any way by the present disclosure.
In the charging station history information, the change in the amount of electricity leaving the charging station compared to entering the charging station can reflect to some extent whether the vehicle is charged or not. The higher the amount of track entering and leaving the charging station, the more samples of the charging station, and the stronger the difference in electric quantity between leaving and entering the vehicle passing through the charging station, the less available the vehicle is directed to the charging station. In addition, the higher the search heat of the charging station, the more vehicles may be traveling to the charging station for charging, and the more feedback may be. It can be seen that by analyzing the charging station history information, the reason why the vehicle is charged or not charged at the charging station can also be determined directly or indirectly, and then be a factor describing whether the state of the charging station is available.
3. The adjacent road information includes at least one of: the current charging station is used for charging the electric vehicles in the charging period, and the current charging station is used for charging the electric vehicles in the charging period.
Specifically, the approaching road refers to a road entering or leaving a charging station, and the larger the electric vehicle flow on the approaching road is, the more the vehicle amount to be charged in the charging station may be; the lower the electric quantity of the vehicle reaching the adjacent road is, the stronger the charging appeal of the user is; the higher the grade of the adjacent road, the more the charging stations are at the service area beside the national road and the provincial road than at the charging stations beside the roads of the towns.
4. The region information includes at least one of: the charging station charging method comprises the steps of setting the general traffic flow, the electric vehicle flow, the number of other charging stations within a set range near the current charging station, or the minimum distance between the other charging stations and the current charging station.
In addition, the region information may further include: the regional heat within the set range near the current charging station.
Specifically, the set range near the charging station may be, for example, a range of 5km, 10km, or 15km around the charging station, and the size of the area is not limited in any way by the present disclosure. In the regional information, the greater the number of charging stations near the charging station, the more likely the charging demand is shunted; the closer the nearest charging station is, the lower the willingness of the user to queue at the charging station may be, and thus the less charging behavior may be. Similarly, the heat and traffic flow of the area can reflect the charging possibility of the area (such as a mall and a park) where the charging station is located.
In summary, the sample characteristics are divided into four categories of charging station attributes, charging station historical information, adjacent road information and area information around the charging station, after specific characteristic contents of each category of characteristics are set, data processing and data mining are carried out according to road network data, attribute data of the charging station and electric quantity matching track data, and specific characteristic contents of each sample under each category of characteristics are determined. However, the specific feature contents of each type of features listed above are merely examples, and in practice, any feature content or combination of any feature contents of each type of features may be selected. In addition, the embodiments of the present disclosure do not limit the specific features of different categories, and the features that can be used to describe the factors related to whether the charging station is available or not without departing from the technical idea of the present disclosure belong to the scope of protection of the present disclosure.
It should be noted that, although there are many reasons why the vehicle is not charged at the charging station, the mining of the sample characteristics allows the model to sufficiently learn the factors related to the unavailability of the charging station in the negative sample, so that in the prediction, whether the charging is not performed due to the unavailability of the charging station is discriminated from the behavior of the uncharged vehicle, thereby more accurately predicting the state of the charging station.
S205, training a state prediction model by using the sample data, wherein the state prediction model is used for predicting the state of whether the charging station is available.
According to the technical scheme, the sample characteristics are mined according to the road network data, the attribute data of the charging station, the track data and the electric quantity data, and the sample data is constructed according to the sample characteristics, so that a state prediction model capable of accurately predicting the state of the charging station is trained, the automatic updating efficiency and accuracy of the state information of the charging station in the map are effectively improved by utilizing the model, the influences of three-party cooperation data quality, low user feedback coverage and the like are avoided, the state updating efficiency of the charging station is improved, and the service experience of the map user related to the charging station is improved.
Fig. 3 is a schematic flow chart diagram of a state updating method for a charging station according to an embodiment of the present disclosure, where the embodiment is applicable to a situation of updating a state of a charging station on a map, and relates to the field of data processing, in particular to intelligent transportation, big data, and deep learning technologies. The method can be performed by a status updating device for a charging station, which is implemented in software and/or hardware, preferably configured in an electronic device, such as a computer device or a server. As shown in fig. 3, the method specifically includes the following steps:
s301, obtaining track data and electric quantity data of the vehicle in a set time period.
And S302, carrying out feature mining according to the road network data, the attribute data of the charging station and the track data and the electric quantity data to obtain the charging station features.
S303, predicting the state of the charging station according to the charging station characteristics by using a state prediction model trained by the state prediction model training method for the charging station according to any embodiment of the disclosure;
and S304, updating the state of the charging station according to the prediction result.
The charging station characteristics at least include charging station attributes, charging station history information, adjacent road information, and area information around the charging station. More specifically, the charging station features are the same as the specific contents in the sample features described in any embodiment of the present disclosure, and are not described herein again.
According to the technical scheme, the automatic updating efficiency and accuracy of the charging station state information in the map are effectively improved by the aid of the model, influences of three-party cooperation data quality, low user feedback coverage and the like are avoided, available state information of the charging station is captured from track and electric quantity data in time, the charging station state updating efficiency is improved, and related charging station service experience of map users is improved.
Fig. 4 is a schematic structural diagram of a state prediction model training device for a charging station according to an embodiment of the present disclosure, which is applicable to a situation of updating a state of a charging station on a map, and relates to the field of data processing, in particular to intelligent transportation, big data and deep learning technologies. The device can realize the state prediction model training method for the charging station according to any embodiment of the disclosure. As shown in fig. 4, the apparatus 400 specifically includes:
a historical data obtaining module 401, configured to obtain track data and electric quantity data from historical data of a vehicle;
a sample data construction module 402, configured to mine sample characteristics according to road network data, attribute data of the charging station, and the trajectory data and the electric quantity data, and construct sample data according to the sample characteristics, where the sample characteristics are used to describe factors related to whether the charging station is available;
a model training module 403, configured to train a state prediction model using the sample data, where the state prediction model is used to predict a state of whether the charging station is available.
Optionally, the sample data constructing module 402 includes:
the track matching unit is used for mapping each track point in the track data to a road network to obtain track matching road network data;
the electric quantity assignment unit is used for assigning the electric quantity value of each sampling point in the electric quantity data to each track point in the track matching road network data to obtain electric quantity matching track data;
and the sample characteristic mining unit is used for mining sample characteristics according to the road network data, the attribute data of the charging station and the electric quantity matching track data.
Optionally, the electric quantity assignment unit is specifically configured to:
determining the track sampling frequency of the track matching road network data and the electric quantity sampling frequency of the electric quantity data;
if the electric quantity sampling frequency is the same as the track sampling frequency, the electric quantity value of each sampling point in the electric quantity data is assigned to each track point in the track matching road network data;
and if the electric quantity sampling frequency is different from the track sampling frequency, the electric quantity sampling frequency is the same through down-sampling, and then the electric quantity value of each sampling point in the adjusted electric quantity data is assigned to each track point in the track matching road network data.
Optionally, the sample characteristics include at least a charging station attribute, charging station history information, adjacent road information, and area information around the charging station.
Optionally, the charging station attribute includes at least one of: number of charging piles, power or cost;
the charging station history information includes at least one of the following information within a set period of time before occurrence of a vehicle trajectory passing a current charging station: the track quantity of each day and the electric quantity change data before and after the vehicle passes through the current charging station each day;
the adjacent road information includes at least one of: the method comprises the steps that the grade of a road adjacent to a current charging station, the time interval electric vehicle flow, the electric vehicle flow of a vehicle passing through the current charging station every day in a set time period before the vehicle track occurs, or the average value of electric quantity of the vehicle when the time interval reaches the current charging station;
the region information includes at least one of: the charging station charging method comprises the steps of setting the general traffic flow, the electric vehicle flow, the number of other charging stations within a set range near the current charging station, or the minimum distance between the other charging stations and the current charging station.
Optionally, the charging station history information further includes: searching the heat of the current charging station every day in a set time period before the vehicle track of the current charging station occurs;
the region information further includes: the regional heat within the set range near the current charging station.
Optionally, the state prediction model is a binary model.
The product can execute the state prediction model training method for the charging station provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects of the execution method.
Fig. 5 is a schematic structural diagram of a state updating apparatus for a charging station according to an embodiment of the present disclosure, where the embodiment is applicable to a situation of updating a state of a charging station on a map, and relates to the field of data processing, in particular to intelligent transportation, big data, and deep learning technologies. The device can realize the state updating method for the charging station according to any embodiment of the disclosure. As shown in fig. 5, the apparatus 500 specifically includes:
the data acquisition module 501 is used for acquiring track data and electric quantity data of a vehicle in a set time period;
the characteristic mining module 502 is used for performing characteristic mining according to road network data, attribute data of the charging station, the track data and the electric quantity data to obtain charging station characteristics;
a state prediction module 503, configured to predict a state of the charging station according to the charging station characteristics by using a state prediction model trained by the state prediction model training apparatus for a charging station according to any embodiment of the present disclosure;
and a state updating module 504, configured to update the state of the charging station according to the prediction result.
The product can execute the state updating method for the charging station provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects of the executing method.
In the technical scheme of the present disclosure, the acquisition, storage, application, and the like of the personal information of the user, such as the related track, are all in accordance with the regulations of the relevant laws and regulations, and do not violate the customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the apparatus 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 601 performs the respective methods and processes described above, such as the state prediction model training method for the charging station. For example, in some embodiments, the state prediction model training method for a charging station may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the state prediction model training method for a charging station described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured by any other suitable means (e.g., by means of firmware) to perform a state prediction model training method for a charging station.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome. The server may also be a server of a distributed system, or a server incorporating a blockchain.
Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge map technology and the like.
Cloud computing (cloud computing) refers to a technology system that accesses a flexibly extensible shared physical or virtual resource pool through a network, where resources may include servers, operating systems, networks, software, applications, storage devices, and the like, and may be deployed and managed in a self-service manner as needed. Through the cloud computing technology, high-efficiency and strong data processing capacity can be provided for technical application and model training of artificial intelligence, block chains and the like.
Furthermore, according to an embodiment of the present application, there is provided another electronic device, another readable storage medium, and another computer program product for executing one or more steps of the status updating method for a charging station according to any embodiment of the present application. The specific structure and program code thereof can be referred to the content description of the embodiment shown in fig. 6, and are not described herein again.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in this disclosure may be performed in parallel or sequentially or in a different order, as long as the desired results of the technical solutions provided by this disclosure can be achieved, and are not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (22)
1. A state prediction model training method for a charging station, comprising:
acquiring track data and electric quantity data from historical data of a vehicle;
mining sample characteristics according to road network data, attribute data of the charging station and the track data and electric quantity data, and constructing sample data according to the sample characteristics, wherein the sample characteristics are used for describing factors related to whether the charging station is available or not;
training a state prediction model by using the sample data, wherein the state prediction model is used for predicting the state of whether the charging station is available.
2. The method of claim 1, wherein said mining sample features from road network data, charging station attribute data, and said trajectory data and electrical quantity data comprises:
mapping each track point in the track data to a road network to obtain track matching road network data;
assigning the electric quantity value of each sampling point in the electric quantity data to each track point in the track matching road network data to obtain electric quantity matching track data;
and mining sample characteristics according to road network data, attribute data of the charging station and the electric quantity matching track data.
3. The method according to claim 2, wherein the assigning of the electric quantity value of each sampling point in the electric quantity data to each track point in the track matching road network data comprises:
determining the track sampling frequency of the track matching road network data and the electric quantity sampling frequency of the electric quantity data;
if the electric quantity sampling frequency is the same as the track sampling frequency, the electric quantity value of each sampling point in the electric quantity data is assigned to each track point in the track matching road network data;
and if the electric quantity sampling frequency is different from the track sampling frequency, the electric quantity sampling frequency is the same through down-sampling, and then the electric quantity value of each sampling point in the adjusted electric quantity data is assigned to each track point in the track matching road network data.
4. The method of claim 1, wherein the sample characteristics include at least charging station attributes, charging station history information, adjacent road information, and area information around charging stations.
5. The method of claim 4, wherein,
the charging station attributes include at least one of: number of charging piles, power or cost;
the charging station history information includes at least one of the following information within a set period of time before occurrence of a vehicle trajectory passing a current charging station: the track quantity of each day and the electric quantity change data before and after the vehicle passes through the current charging station each day;
the adjacent road information includes at least one of: the method comprises the steps that the grade of a road adjacent to a current charging station, the time interval electric vehicle flow, the electric vehicle flow of a vehicle passing through the current charging station every day in a set time period before the vehicle track occurs, or the average value of electric quantity of the vehicle when the time interval reaches the current charging station;
the region information includes at least one of: the charging station charging method comprises the steps of setting the general traffic flow, the electric vehicle flow, the number of other charging stations within a set range near the current charging station, or the minimum distance between the other charging stations and the current charging station.
6. The method of claim 5, wherein,
the charging station history information further includes: searching the heat of the current charging station every day in a set time period before the vehicle track of the current charging station occurs;
the region information further includes: the regional heat within the set range near the current charging station.
7. The method of claim 1, wherein the state prediction model is a binary model.
8. A status updating method for a charging station, comprising:
acquiring track data and electric quantity data of a vehicle in a set time period;
performing feature mining according to the road network data, the attribute data of the charging station, the track data and the electric quantity data to obtain the characteristics of the charging station;
predicting a state of a charging station from the charging station characteristics using a state prediction model trained using the method of any of claims 1-7;
and updating the state of the charging station according to the prediction result.
9. A state prediction model training apparatus for a charging station, comprising:
the historical data acquisition module is used for acquiring track data and electric quantity data from the historical data of the vehicle;
the sample data construction module is used for mining sample characteristics according to road network data, attribute data of the charging station, the track data and the electric quantity data and constructing sample data according to the sample characteristics, wherein the sample characteristics are used for describing factors related to whether the charging station is available or not;
and the model training module is used for training a state prediction model by using the sample data, wherein the state prediction model is used for predicting the state of whether the charging station is available.
10. The apparatus of claim 9, wherein the sample data construction module comprises:
the track matching unit is used for mapping each track point in the track data to a road network to obtain track matching road network data;
the electric quantity assignment unit is used for assigning the electric quantity value of each sampling point in the electric quantity data to each track point in the track matching road network data to obtain electric quantity matching track data;
and the sample characteristic mining unit is used for mining sample characteristics according to the road network data, the attribute data of the charging station and the electric quantity matching track data.
11. The device according to claim 10, wherein the electric quantity assigning unit is specifically configured to:
determining the track sampling frequency of the track matching road network data and the electric quantity sampling frequency of the electric quantity data;
if the electric quantity sampling frequency is the same as the track sampling frequency, the electric quantity value of each sampling point in the electric quantity data is assigned to each track point in the track matching road network data;
and if the electric quantity sampling frequency is different from the track sampling frequency, the electric quantity sampling frequency is the same through down-sampling, and then the electric quantity value of each sampling point in the adjusted electric quantity data is assigned to each track point in the track matching road network data.
12. The apparatus of claim 9, wherein the sample characteristics include at least charging station attributes, charging station history information, adjacent road information, and area information around a charging station.
13. The apparatus of claim 12, wherein,
the charging station attributes include at least one of: number of charging piles, power or cost;
the charging station history information includes at least one of the following information within a set period of time before occurrence of a vehicle trajectory passing a current charging station: the track quantity of each day and the electric quantity change data before and after the vehicle passes through the current charging station each day;
the adjacent road information includes at least one of: the method comprises the steps that the grade of a road adjacent to a current charging station, the time interval electric vehicle flow, the electric vehicle flow of a vehicle passing through the current charging station every day in a set time period before the vehicle track occurs, or the average value of electric quantity of the vehicle when the time interval reaches the current charging station;
the region information includes at least one of: the charging station charging method comprises the steps of setting the general traffic flow, the electric vehicle flow, the number of other charging stations within a set range near the current charging station, or the minimum distance between the other charging stations and the current charging station.
14. The apparatus of claim 13, wherein,
the charging station history information further includes: searching the heat of the current charging station every day in a set time period before the vehicle track of the current charging station occurs;
the region information further includes: the regional heat within the set range near the current charging station.
15. The apparatus of claim 9, wherein the state prediction model is a binary model.
16. A status updating apparatus for a charging station, comprising:
the data acquisition module is used for acquiring track data and electric quantity data of the vehicle within a set time period;
the characteristic mining module is used for mining characteristics according to the road network data, the attribute data of the charging station, the track data and the electric quantity data to obtain the characteristics of the charging station;
a state prediction module for predicting a state of a charging station from the charging station characteristics using a state prediction model trained by the apparatus of any one of claims 9-15;
and the state updating module is used for updating the state of the charging station according to the prediction result.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the state prediction model training method for a charging station of any of claims 1-7.
18. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the state prediction model training method for a charging station according to any one of claims 1 to 7.
19. A computer program product comprising a computer program which, when executed by a processor, implements a state prediction model training method for a charging station according to any of claims 1-7.
20. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the status updating method for a charging station of claim 8.
21. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the status updating method for a charging station according to claim 8.
22. A computer program product comprising a computer program which, when executed by a processor, implements the status updating method for a charging station according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110672041.5A CN113344277B (en) | 2021-06-17 | 2021-06-17 | Predictive model training method, state updating method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110672041.5A CN113344277B (en) | 2021-06-17 | 2021-06-17 | Predictive model training method, state updating method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113344277A true CN113344277A (en) | 2021-09-03 |
| CN113344277B CN113344277B (en) | 2024-03-12 |
Family
ID=77475970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110672041.5A Active CN113344277B (en) | 2021-06-17 | 2021-06-17 | Predictive model training method, state updating method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113344277B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102022115793A1 (en) | 2022-06-24 | 2024-01-04 | Lade Gmbh | System for providing electrical energy for electric vehicles, charging device for electric vehicles and method for operating the same |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011156776A2 (en) * | 2010-06-10 | 2011-12-15 | The Regents Of The University Of California | Smart electric vehicle (ev) charging and grid integration apparatus and methods |
| CN104281129A (en) * | 2014-09-19 | 2015-01-14 | 安徽旗翔科技发展有限公司 | Intelligent charge-discharge Internet-of-Things cloud comprehensive integration system of electric automobile |
| CN104778263A (en) * | 2015-04-23 | 2015-07-15 | 储盈新能源科技（上海）有限公司 | Simulating data mining method for electric vehicle charging station system |
| US20180373268A1 (en) * | 2017-06-27 | 2018-12-27 | Veniam, Inc. | Systems and methods for managing fleets of autonomous vehicles to optimize electric budget |
| US20200218270A1 (en) * | 2019-01-07 | 2020-07-09 | Wing Aviation Llc | Using machine learning techniques to estimate available energy for vehicles |
| CN112193112A (en) * | 2020-10-16 | 2021-01-08 | 安徽继远软件有限公司 | Intelligent management method and device for charging piles of electric automobile charging station |
| CN112433122A (en) * | 2020-11-23 | 2021-03-02 | 广州橙行智动汽车科技有限公司 | Charging pile available state detection method, device, equipment and storage medium |
| CN112862183A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Prediction method of charging difficulty, training method of model, training device of model and equipment |
-
2021
- 2021-06-17 CN CN202110672041.5A patent/CN113344277B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011156776A2 (en) * | 2010-06-10 | 2011-12-15 | The Regents Of The University Of California | Smart electric vehicle (ev) charging and grid integration apparatus and methods |
| CN104281129A (en) * | 2014-09-19 | 2015-01-14 | 安徽旗翔科技发展有限公司 | Intelligent charge-discharge Internet-of-Things cloud comprehensive integration system of electric automobile |
| CN104778263A (en) * | 2015-04-23 | 2015-07-15 | 储盈新能源科技（上海）有限公司 | Simulating data mining method for electric vehicle charging station system |
| US20180373268A1 (en) * | 2017-06-27 | 2018-12-27 | Veniam, Inc. | Systems and methods for managing fleets of autonomous vehicles to optimize electric budget |
| US20200218270A1 (en) * | 2019-01-07 | 2020-07-09 | Wing Aviation Llc | Using machine learning techniques to estimate available energy for vehicles |
| CN112193112A (en) * | 2020-10-16 | 2021-01-08 | 安徽继远软件有限公司 | Intelligent management method and device for charging piles of electric automobile charging station |
| CN112433122A (en) * | 2020-11-23 | 2021-03-02 | 广州橙行智动汽车科技有限公司 | Charging pile available state detection method, device, equipment and storage medium |
| CN112862183A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Prediction method of charging difficulty, training method of model, training device of model and equipment |
Non-Patent Citations (2)
| Title |
|---|
| 郑强;赵丽平;周林;: "电动汽车充电站综合监控系统设计", 电气自动化, no. 04 * |
| 龚钢军;安晓楠;陈志敏;张帅;文亚凤;吴秋新;苏畅;: "基于SAE-ELM的电动汽车充电站负荷预测模型", 现代电力, no. 06 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102022115793A1 (en) | 2022-06-24 | 2024-01-04 | Lade Gmbh | System for providing electrical energy for electric vehicles, charging device for electric vehicles and method for operating the same |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113344277B (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11305780B2 (en) | Road condition status prediction method, device, and server, and storage medium | |
| CN114428828A (en) | Method and device for digging new road based on driving track and electronic equipment | |
| CN113899381B (en) | Method, apparatus, device, medium, and product for generating route information | |
| CN112069635A (en) | Battery replacement cabinet deployment method, device, medium and electronic equipment | |
| CN113344277B (en) | Predictive model training method, state updating method, device, equipment and medium | |
| CN114596709A (en) | Data processing method, device, equipment and storage medium | |
| CN114543829A (en) | Model training method, navigation track recommendation method and device and vehicle | |
| CN113008253A (en) | Hybrid vehicle running method, device and storage medium | |
| CN114625744A (en) | Updating method and device of electronic map | |
| CN112862183A (en) | Prediction method of charging difficulty, training method of model, training device of model and equipment | |
| CN112883236A (en) | Map updating method, map updating device, electronic equipment and storage medium | |
| CN113837455B (en) | Taxi taking method, taxi taking device, electronic equipment and readable storage medium | |
| CN115060249A (en) | Electronic map construction method, device, equipment and medium | |
| CN113344278A (en) | Electric quantity prediction method, apparatus, device, storage medium and program product | |
| CN111060122B (en) | Navigation information sharing method and device | |
| CN114218504A (en) | Blocked road segment identification method and device, electronic equipment and storage medium | |
| Fanani et al. | Bus Arrival Prediction-to Ensure Users not to Miss the Bus | |
| CN114419896B (en) | Traffic signal lamp control method, device, equipment and medium based on digital twins | |
| CN112541021B (en) | Route evaluation method, scenic spot tour estimated time length calculation method and device | |
| CN114719878B (en) | Vehicle navigation method, device, system, electronic equipment and computer medium | |
| CN114970949B (en) | Method and device for predicting running speed, electronic device, and storage medium | |
| CN117270913B (en) | Map updating method, device, electronic equipment and storage medium | |
| CN114659534A (en) | Navigation path passing time processing method, device, equipment, medium and product | |
| CN117037484A (en) | Vehicle position determining method, training method and device of vehicle position determining model | |
| CN114781714A (en) | Route pushing method, route pushing device, model training method, model training device, electronic equipment and storage medium |
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 |