System and method for selecting charging station for a vehicle

Abstract

The present invention describes a system (200) for selecting charging stations for a vehicle. The system (200) comprises a receiving unit (202) configured to receive source information and destination

Description

[002] The present invention generally relates to the field of selecting charging station for an electric vehicle. BACKGROUND

[003] The following description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.

[004] Traditionally, selecting a charging station for electric vehicles (EVs) has been based on the principle of contextual proximity. This method generally involves displaying a list of charging stations that are within the vicinity of the vehicle’s current location, along the vehicle's planned route, or near the destination. These stations are typically identified using GPS data, and the user can select from the available options. In the conventional systems, once a list of charging stations is presented, the user is required to manually select the most suitable option. While proximity to the vehicle current position or destination may be a useful criterion, it does not guarantee that the selected station will meet the user actual needs.

[005] The problem of manually selecting the most optimal charging station is addressed in prior art such as U.S. Patent No. 8,738,277 Bl. This patent introduces a method where the system determines a preferred charging station based on a derived factor, such as brand preference factor, a price sensitivity factor, a time sensitivity factor, and a third party rating sensitivity factor, which is based on the user historical charging data. The system then compare this derived factor with the available charging stations to recommend a preferred option. Additionally, if the user chooses a non-preferred charging station, the system updates the derived factor to adjust future recommendations.

[006] However, the above patent application fails to integrate personalized and contextual preferences that a driver may have while navigating. SUMMARY

[007] The present disclosure overcomes one or more shortcomings of the prior art and provides additional advantages discussed throughout the present disclosure. Additional features and advantages are realized through the techniques of the present disclosure. Other embodiments and aspects of the disclosure are described in detail herein and are considered a part of the claimed disclosure.

[008] In an aspect, the present disclosure recites a system for selecting charging stations for a vehicle. The system comprises a receiving unit configured to receive source information and destination information to determine navigation route of the vehicle and receive a signal to perform automatic selection of at least one charging station from a plurality of charging stations associated with one of the navigation route and the destination information. The system further comprises a processing unit configured to select at least one charging station from the plurality of charging stations based on the received signal and a user preference profile, wherein the user preference profile is associated with user past history of selecting charging stations over a predefined time period based on at least one charging station profile parameter and at least one charging station navigation parameter and provide the selected at least one charging station.

[009] In an aspect, the present disclosure recites a system for training a plurality of models for selecting charging stations for a vehicle. The system comprises a receiving unit configured to receive a plurality of navigation patterns over a predefined time period during a navigation of the vehicle. The plurality of navigation patterns corresponds to selection of charging stations by a user and navigation of the vehicle towards the selected charging stations. The system further include a training unit configured to generate a plurality of meta features for each of the plurality of navigation patterns by training a first set of model of the plurality of models on the received plurality of navigation patterns. The plurality of meta features correspond to prediction of the selection of charging stations. Further, the training unit is configured to train a second set of model of the plurality of models based on the generated meta features and the received plurality of navigation patterns to predict selection of the charging stations. In an aspect, the system uses a stacked meta-leaming model to identify meta features for selecting charging stations for a vehicle.

[0010] In an aspect, the present disclosure recites a method of selecting charging stations for a vehicle. The method includes receiving source information and destination information to determine navigation route of the vehicle and receiving a signal to perform automatic selection of at least one charging station from a plurality of charging stations associated with one of the navigation route and the destination information, after receiving the information, the method include selecting at least one charging station from the plurality of charging stations based on the received signal and a user preference profile. The user preference profile is associated with user past history of selecting charging stations over a predefined time period based on at least one charging station profile parameter and at least one charging station navigation parameter. Finally, the method include providing the selected at least one charging station.

[0011] In an aspect, the present disclosure recites a method of training a plurality of models for selecting charging stations for a vehicle. The method includes receiving a plurality of navigation patterns over a predefined time period during a navigation of the vehicle. After receiving, the method include generating a plurality of meta features for each of the plurality of navigation patterns by training a first set of model of the plurality of models on the received plurality of navigation patterns. The plurality of meta features correspond to prediction of the selection of charging stations. Finally, the method include training a second set of model of the plurality of models based on the generated meta features and the received plurality of navigation patterns to predict selection of the charging stations.

[0012] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0013] The embodiments of the disclosure itself, as well as a preferred mode of use, further objectives and advantages thereof, will best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying drawings. One or more embodiments are now described, by way of example only, with reference to the accompanying drawings in which:

[0014] FIG. 1 illustrates an environment architecture 100 of a system for selecting charging stations for a vehicle, in accordance with an embodiment of the present disclosure.

[0015] FIG. 2 illustrates a system 200 (same as the system 104 of Fig. 1) for selecting charging stations for a vehicle, in accordance with an embodiment of the present disclosure.

[0016] FIG.3 illustrates a system 300 for facilitating training of the ML model 112, in accordance with an embodiment of the present disclosure.

[0017] FIG. 4 depicts a flow diagram of a method 400 of selecting charging stations for a vehicle, in accordance with an embodiment of the present disclosure.

[0018] FIG. 5 depicts a flow diagram of a method 500 of training a plurality of models for selecting charging stations for a vehicle, in accordance with an embodiment of the present disclosure.

[0019] The figures depict embodiments of the disclosure for purposes of illustration only. One skilled in the art will readily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein. DETAILED DESCRIPTION

[0020] The foregoing has broadly outlined the features and technical advantages of the present disclosure in order that the detailed description of the disclosure that follows may be better understood. It should be appreciated by those skilled in the art that the conception and specific embodiment disclosed may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes of the present disclosure.

[0021] Various embodiments of the present invention will now be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. Indeed, the invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements.

[0022] The term “or” is used herein in both the alternative and conjunctive sense, unless otherwise indicated.

[0023] The terms “illustrative,” “example,” and “exemplary” are used to be examples with no indication of quality level. Like numbers refer to like elements throughout.

[0024] The phrases “in an embodiment,” “in one embodiment,” “according to one embodiment,” and the like generally mean that the particular feature, structure, or characteristic following the phrase may be included in at least one embodiment of the present disclosure and may be included in more than one embodiment of the present disclosure (importantly, such phrases do not necessarily refer to the same embodiment).

[0025] The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any implementation described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other implementations.

[0026] If the specification states a component or feature “can,” “may,” “could,” “should,” “would,” “preferably,” “possibly,” “typically,” “optionally,” “for example,” “often,” or “might” (or other such language) be included or have a characteristic, that particular component or feature is not required to be included or to have the characteristic. Such component or feature may be optionally included in some embodiments, or it may be excluded.

[0027] The phrase “vehicle” or “electric vehicle” are used interchangeably throughout the disclosure. The electric vehicle refers to Battery Electric Vehicles (BEVs). These vehicles are powered entirely by batteries that store electricity, which is used to power the electric motor that drives the wheels. The electric vehicle may not have a gasoline engine and may not use any fossil fuels. The electric vehicle may be charged by plugging the electric vehicle into an electrical outlet or charging station. The electric vehicle may be a car, truck, semi-truck, motorcycle, plane, train, moped, scooter, or other type of transportation. Further, the electric vehicle may use many types of powertrains. For example, the electric vehicle may be a plugin electric vehicle, a plug-in hybrid electric vehicle, a hybrid electric vehicle, or a fuel cell vehicle.

[0028] The phrase “artificial intelligence” refers to the field of studying artificial intelligence or methodology for making artificial intelligence. The phrase “machine learning” is used throughout the disclosure. The machine learning broadly describes a function of systems that learn from data. A machine learning system, engine, or module can include a machine learning algorithm that can be trained to learn functional relationships between inputs and outputs that are currently unknown. In one or more embodiments, machine learning functionality can be implemented using an artificial neural network (ANN) having the capability to be trained to perform a currently unknown function. In machine learning and cognitive science, ANNs are a family of statistical learning models inspired by the biological neural networks of animals, and in particular the brain. ANNs can be used to estimate or approximate systems and functions that depend on a large number of inputs.

[0029] Machine learning may be classified into supervised learning, unsupervised learning, and reinforcement learning according to a learning method. The supervised learning may refer to a method of learning an artificial neural network in a state in which a label for learning data is given, and the label may mean the correct answer (or result value) that the artificial neural network must infer when the learning data is input to the artificial neural network. Unsupervised learning may refer to a method of learning an artificial neural network in a state in which a label for learning data is not given. The reinforcement learning may refer to a learning method in which an agent defined in a certain environment learns to select a behavior or a behavior sequence that maximizes cumulative compensation in each state.

[0030] Turning now to the drawings, the detailed description set forth below in connection with the appended drawings is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of various concepts with like numerals denote like components throughout the several views. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details.

[0031] FIG. 1 illustrates an environment architecture 100 of a system for selecting charging stations for a vehicle, in accordance with an embodiment of the present disclosure. The environment architecture 100 may be constituted a vehicle 102 and a system 104. All the elements of the environment architecture 100 illustrated in FIG. 1 are essential elements, however the environment architecture 100 may be implemented by more elements than the elements illustrated in FIG. 1. However, the same are not explained for the sake of brevity.

[0032] In an embodiment, the vehicle 102 may include a Human Machine Interface (HMI) unit 108. The HMI unit 108 may be a user interface or dashboard that connects a user to a machine, system, or device in the vehicle 102. In an embodiment, the HMI unit 108 may be an integral part of the vehicle 102. In an embodiment, the HMI unit 108 may include, not limited to, a display unit. In an embodiment, the display unit may be used for receiving user input and displaying the navigation route to a charging station selected by the user based on the user input.

[0033] In an embodiment, the system 104 may constitute a receiving unit 108 and a processing unit 110. In an embodiment, the processing unit 110 may comprises an ML model 112. It may be noted, all the elements included in the system 104 illustrated in FIG. 1 are essential elements, however the system 104 may comprise more elements than the elements illustrated in FIG. 1 and the same are not explained for the sake of brevity. Further, all the elements of the system 104 may communicate with each other via wireless / wired communication network. The detailed functioning of the system 104 is further explained in Fig. 2 in forthcoming paragraphs of the present disclosure.

[0034] In an embodiment, the system 104 may be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a server, a network server, a cloud-based server and the like.

[0035] In an alternative embodiment, the system 104 may be a part of the integral part of the vehicle 102.

[0036] Moving towards FIG. 2 that illustrates a system 200 (same as the system 104 of Fig. 1) for selecting charging stations for a vehicle, in accordance with an embodiment of the present disclosure.

[0037] According to an embodiment of the present disclosure, the system 200 (same as the system 104 of Fig. 1) may be constituted by a receiving unit 202 (same as the receiving unit 108 of Fig. 1), a processing unit 204 (same as the processing unit 110 of Fig. 1). All the elements of the system 200 illustrated in FIG. 2 are essential elements, and the system 200 may be implemented by more elements than the elements illustrated in FIG. 2, however the same are not explained for the sake of brevity. All the elements of the system 200 may communicate with each other via wireless connection, electric connection, or combination of both.

[0038] In an embodiment, the receiving unit 202 may be an interface that allows the system 200 to receive and transmit information related to user input. In an exemplary embodiment, the HMI unit 106 may be configured to receive user input based on user operation on the user HMI unit 106 and the HMI unit 106 may provide the received user input to the receiving unit 202.

[0039] In an embodiment, the system 200 may be configured to perform training of a ML model 206 (same as the ML model 112 of Fig. 1) for a predefined time period to understand user behaviour regarding selection of the charging station.

[0040] After training the ML model 206, the system 200 may be configured to generate a default preference option and provide the default preference option to the HMI unit 106 in order to display the default preference option along with a manual selection option. Training of the ML model to understand the user behaviour regarding selection of the charging station is further explained in Fig. 3.

[0041] Fig. 2 illustrates the selection of the charging station after training of the ML model 206 for the predefined time period. In one embodiment, the user may input the destination information (i.e., destination location) into the HMI unit 106. This destination information may be provided in various formats, such as by selecting a location from a digital map displayed on the HMI unit 106, entering an address manually, or using voice commands that the HMI unit 106 may interpret and process. Once the destination information is received, the HMI unit 106 may utilize the destination information in conjunction with vehicle current location (i.e., source information), determined through an onboard GPS or similar location-tracking system of the vehicle 102 (not shown in figs.), to generate a navigation route. The HMI unit 106 may provide the navigation route along with the source information and destination information to the processing unit 204 via the receiving unit 202.

[0042] In an alternative embodiment, the receiving unit 202 may be configured to receive the destination information by communication with the HMI unit 106. Further, the receiving unit 202 may be configured to receive source information (i.e., current location of the vehicle 102) by communicating with the onboard GPS or similar location-tracking system (not shown in figs) of the vehicle 102. After receiving the source information and the destination information, the receiving unit 202 may provide the source information and the destination information to the processing unit 204. The processing unit 204 may be configured to determine navigation route of the vehicle based on the source information and the destination information.

[0043] In an embodiment, the user is presented with an interface for selecting a charging station. The HMI unit 106 may offer two modes for selecting a charging station: a default mode and a manual mode. In the default mode, the system 200 may be configured to automatically identify and select the most suitable charging station. In contrast, in the manual mode, the system 200 may be configured to allow the user to choose a charging station of their preference by manually selecting from a list of available charging stations. During selection of the default option:

[0044] In an embodiment, if the user has selected the default option (i.e., automatic selection of the charging station) for selection of the charging station, the processing unit 204 may select at least one charging station based on the user past history of selecting charging stations over a predefined time period. In an embodiment, the processing unit 204 may use the ML-model 206 (trained using the user past history of selecting charging stations over a predefined time period) to select the charging station.

[0045] In particular, when the user select the default option for the selection of the charging station by using the HMI unit 106, the HMI unit 106 may provide a signal to the receiving unit 202 related to automatic selection of the charging station. The receiving unit 202 may provide the signal to the processing unit 204. The processing unit 204 may be configured to determine a plurality of charging stations by using the generated navigation route, the source information, and the destination information. Specifically, the processing unit 204 may be configured to identify the plurality of charging stations located in the vicinity of the user, near the destination, or along the route to the destination. After determining the plurality of charging stations, the processing unit 204 may be configured to identify at least one charging station profile parameter corresponding to the charging station characteristics and charging station contextual proximity of the plurality of charging stations. The charging station characteristics corresponds to at least one of surrounding facilities associated with charging station, vendor information associated with the charging station, a type of charging station, payment option associated with the charging station, and parking charges policies associated with the charging station.

[0046] In an embodiment, the surrounding facilities associated with the charging station may refer to amenities and services available in proximity to the charging station that may be relevant to the user. For example, the charging station may be located near a shopping area, a restaurant, and so on.

[0047] In an embodiment, the vendor information associated with the charging station may refer to the service provider responsible for operating or maintaining the charging station. For example, the charging station may be managed by well-known providers such as HP, Indane, Shell, or Reliance.

[0048] In an embodiment, the type of charging station may be defined by its charging capability, such as standard, fast, or ultra-fast charging, and its compatibility with various EV models.

[0049] In an embodiment, the payment options associated with the charging station may refer to the available methods by which users may complete a transaction. For example, the charging station may accept Radio-Frequency Identification (RFID)-based payments, support mobile wallet transactions, or provide other payment options.

[0050] In an embodiment, the parking charge policies associated with the charging station may refer to the fees applicable for parking while utilizing the charging station. For example, the charging station may be located within a paid parking lot that charges an hourly rate for parking in addition to the charging cost, or it may be located in an area without parking fees.

[0051] In an embodiment, charging station contextual proximity of the plurality of charging stations corresponds to location of each of the plurality of charging stations with respect to the navigation route, the source information, and the destination information. In an embodiment, the charging station contextual proximity may refer to a relative location / position of the charging station in relation to a specific route that a vehicle is intended to take. The charging station contextual proximity may be further classified into the following types, based on how the charging stations relate to the route and destination:

[0052] In the Vicinity: This type may refer to charging stations that are located nearby the vehicle current location / source location. Near Destination: This type may refer to charging stations located closer to the destination information / location. Along the Route: This type may refer to charging stations location directly along the planned navigation route.

[0053] In a non-limiting example of the present disclosure, if a user selects Silkboard as a destination, the processing unit 204 may be configured to identify three charging stations: Station 1, Station 2, and Station 3. Upon evaluation, the processing unit 204 may be configured to identify (as shown in Table-1 below) that the Station 1 is located in the vicinity of the vehicle current location, near a shopping mall, and is operated by HP. The Station 2, on the other hand, is on the way to the navigated route, located near a coffee shop, with Reliance as the service provider. Finally, The Station 3 is located near the destination at Silkboard, positioned near a restaurant, with Shell as the service provider. Charging Station Destination Contextual Proximity Facilities Nearby Vendor Station 1 Silkboard In the vicinity Shopping mall HP Station 2 Silkboard On the way Coffee shop Reliance Station 3 Silkboard Near the destination restaurant Shell Table-1

[0054] After identifying charging station profile parameters and the charging station contextual proximity, the processing unit 204 may be configured to identify charging station navigation parameter corresponding to travel adjustments required during navigation to each of the plurality of charging stations. In particular, the processing unit 204 may be configured to identify travel adjustments, including the extra kilometres needed to reach the charging station from the navigated route, as well as various routing options that may be necessary during navigation. These routing options may include diversions, U-turns, or no changes to the route (i.e., no diversion or U-turn).

[0055] In a non-limiting example of the present disclosure, after identifying the charging station profile parameters and the contextual proximity of the charging stations, the processing unit 204 may be configured to determine the travel adjustments required to reach the charging station from the navigated route (as shown in Table-2 below). For the Station 1, an additional 2 km and a diversion are required; for the Station 2, an extra 1.5 km and a U-tum are required; and for the Station 3, no routing changes or diversions are needed. Charging Station Destination Extra KM Routing Option Station 1 Silkboard 2KM Diversion Station 2 Silkboard 1.5KM U-Turn Station 3 Silkboard 0KM No Routing Table-2

[0056] After identifying the charging station profile parameters, the charging station contextual proximity, and the charging station navigation parameter, the processing unit 204 may use the ML model 206 to select the charging station from the plurality of charging stations. In particular, the ML model 206 may be configured to analyze the identified at least one charging station profile parameter and the charging station navigation parameter based on user past history of selecting charging stations over the predefined time period. After analyzing the information, the ML model 206 may be configured to select the at least one charging station.

[0057] In particular, the ML model 206 may be configured to process identified at least one charging station profile parameter and the charging station navigation parameter in combination with the user past history of selecting charging stations. This historical data may include previous instances where the user select a charging station based on profile preferences, the convenience of the station location. Over the predefined time period, the ML model 206 learns from these historical choices and identifies patterns or preferences in the user behaviour. Using this information, the ML model 206 may be configured to predict whether the user would prefer to navigate to a particular charging station. The ML model 206 may be configured to analyse the probability that the user will choose a specific station based on their past selections and preferences. Finally, The ML model 206 may be configured to select the at least one charging station based on this analysis. Chargin g Station Destinatio n Contextua 1 Proximity Facilities Nearby Vendor Extra KM Routing Option Navigate d Station 1 Silkboard In the vicinity Shopping mall HP 2KM Diversio n Yes Station 2 Silkboard On the way Coffee shop Relianc e 1.5K M U-Turn No Station 3 Silkboard Near the destinatio n Restaura nt Shell 0KM No Routing No Table-3

[0058] In a non-limiting example of the present disclosure, if the ML model 206 identifies that the user prefers to select a charging station near a shopping mall and only chooses HP vendor charging stations, the ML model may select the Charging Station-1 as the recommended charging station based on the user's preferences, as shown in Table 3 above, towards which the user may be navigated.

[0059] After selecting the at least one charging station, the processing unit 204 may be configured to provide the relevant charging station information to the HMI unit 106. The HMI unit 106 may be configured to display this information, showing the selected charging station as a recommended option, along with a navigation path that guides the user to the selected charging station. During selection of the Manual option:

[0060] In an embodiment, if the user is not satisfied with the charging station selected through the default selection process, the user may move towards manually selection of a charging station. In an alternative embodiment, the user may choose to manually select a charging station directly, without relying on the default selection process.

[0061] In an embodiment, if the user wants to move towards manual option (i.e., manual selection of the charging station) for selection of the charging station, the HMI unit 106 may display the contextual proximity option of the EV charging station. The user selects one of the contextual proximity option. After selecting one of the contextual proximity option, the HMI unit 106 may display charging station profile parameters. The charging station profile parameters corresponds to at least one of surrounding facilities associated with charging station, a type of charging station, payment option associated with the charging station, and parking charges policies associated with the charging station. The user may select one of the charging station profile parameter by performing operation on the HMI unit 106. The HMI unit 106 may provide the selection of the contextual proximity option and the selection of the charging station profile parameter to the receiving unit 202.

[0062] In a non-limiting example of the present disclosure, if the user prefers to manually select the charging station, the HMI unit 106 may display contextual proximity options, such as “In the Vicinity,” “Near Destination,” or “Along the Route.” For example, after the selection of the contextual proximity option, the HMI unit 106 may present the charging station profile parameters, including surrounding facilities, the type of charging station, payment options, and parking charge policies. The user may choose one of these parameters by interacting with the HMI unit 106, and the selection of both the proximity option and the charging station profile parameter is sent to processing unit 206 for further processing.

[0063] After receiving the user selection of the contextual proximity option and the charging station profile parameter, the processing unit 204 may be configured to identify list of charging stations based on the user preferred charging station profile and preferred contextual proximity. These identified list of charging stations are then provided to the HMI unit 106, which is responsible for displaying the relevant charging station information. The HMI unit 106 presents the list of charging stations, recommended based on the selected criteria, along with the navigation path to the chosen charging station. The user may then select one charging station from the displayed list. Upon this selection, the HMI unit 106 generates and updates the navigation path, incorporating the selected charging station to guide the user to the designated location.

[0064] Additionally, the training unit of the processing unit 204, as shown in Fig. 3, may be configured to update the trained ML model 206 based on the user interaction with the vehicle 102 during the selection of the charging station. If the user chooses to switch to the manual option after the initial training of the ML model 206, the training unit may be capable of updating the ML model 206 accordingly.

[0065] Now moving towards Fig. 3 that illustrates a system 300 for facilitating training of the ML model 112, in accordance with an embodiment of the present disclosure. The system 300 (same as the system 200 of Fig. 2) may constitute of a receiving unit 302 (same as the receiving unit 202 of Fig. 2), a training unit 304, a plurality of ML models 306 including a first set of ML model 308 and a second set of ML model 308. All the elements of the system 300 illustrated in FIG. 3 are essential elements, and the system 300 may be implemented by more elements than the constituent elements illustrated in FIG. 3, however the same are not explained for the sake of brevity. All the elements of the system 300 may communicate with each other via wireless connection, electric connection, or combination of both. In an embodiment, the training unit 304 may be a part of the processing unit 204 of the Fig. 2. In an embodiment, in order to perform training of the plurality of ML model 306 and to provide the default option for the selection of the charging station based on the training of the plurality of ML model 306, the system 300 may collect data related to the manual selection of charging station over the predefined time period. The predefined time period may be, not limited to, at least one month or year. In particular, when the user wants to select the charging station, before training of the ML model 308, the HMI unit 106 may display the contextual proximity option of the charging station. The user may select one of the contextual proximity option. After selecting one of the contextual proximity option, the HMI unit 106 may display charging station profile parameters. The charging station profile parameters corresponds to at least one of surrounding facilities associated with charging station, a type of charging station, payment option associated with the charging station, and parking charges policies associated with the charging station. The user may select one of the charging station profile parameter by performing operation on the HMI unit 106. The HMI unit 106 may provide the selection of the contextual proximity option and the selection of the charging station profile parameter to the receiving unit 108. The system 300 may collect and store the data related to manual selection of the charging station performed the till predefined time period. The data may be a navigation pattern including selection of a charging station and the navigation choices (e.g., routes, detours, or specific paths taken) associated with reaching those charging station.

[0066] In an embodiment, after collecting the data related to the manual selection of the charging station performed the till predefined time period, the training unit 304 may be configured to extract data from the memory (not shown in figs.) of the vehicle regarding the selection of the charging station. Further, training unit 304 may be configured to divide the data into two parts i.e., training data and test data. After dividing the data into the two parts, the training unit 304 may be configured to perform the training of the ML model based on the training data.

[0067] In an embodiment, the navigation pattern may include various factors influencing a user decision-making process and behaviors while selecting and navigating towards a charging station. The navigation pattern may include the vendor of the selected charging station, routing options, contextual proximity of the charging station facilities nearby the charging stations.

[0068] In an embodiment, the training unit 304 may provide the training data to the first set of the ML model 308. The first set of the ML model 308 may be, not limited to, a Random Forest, a Support Vector Machine (SVM), a Decision Tree, and a XGBoost. In an embodiment, the first set of the ML model 308 may include at least two ML model or more than two ML models. Each of the ML model of the first set of the ML model may be different. In an embodiment, after receiving the training data from the training unit 304, the first set of ML model 308 may be trained on the training data. During the training of the first set of ML model 308, each ML model 308 may learn significant patterns and relationships that help predict user choices based on the training data. After learning, each ML model 308 may generate predictions on the training data. These prediction are referred as meta-features.

[0069] After generating the meta-features, each of the ML model 308 may provide the generated meta-features to the second set of the ML model 310. The second set of the ML model 310 may be, not limited to, logistic regression model or any stacked model. In an embodiment, the second set of the ML model 310 may include only one ML model.

[0070] After generating meta-features from the predictions of multiple base models, these meta-features, together with the training data, are provided to the second set of the ML model 310 for training. During the training process of the second set of the ML model 310, the meta-features received from each ML model 308 are first aggregated. Following the aggregation, regression analysis may be performed on the aggregated meta-features to identify patterns and correlations with the navigation data in the training data. Based on this correlation, the ML model 310 may be configured to identify relationship between user preferences and the likelihood of selecting certain charging stations.

[0071] After performing training of the training data, the test data may be provided to the first set of ML model 308. The test data may be used for evaluating the plurality of ML models 306 predictive capabilities after training. After providing the test data to the first set of the ML model 308, the first set of the ML model 308 may generate meta-features (i.e., the predicted output). Once these meta-features are generated, these meta-feature may be provided to the second set of ML model 310. The second set of ML model 310 may use the meta-features as input to produce the final output predictions for the test data. Further, Evaluation of the second set of ML model 310 performance may be done by comparing its predictions with the final output of the test data.

[0072] Moving towards Fig. 4 showing steps of a method 400 of selecting charging stations for a vehicle, in accordance with an embodiment of the present disclosure. The method starts at step 402, at step 402 the method 400 may include receiving source information and destination information to determine navigation route of the vehicle. In an exemplary aspect, a receiving unit 202 of Fig. 2 of the system 200 may be configured to carry out the process steps disclosed in step 402.

[0073] At step 404, the method 400 may include receiving a signal to perform automatic selection of at least one charging station from a plurality of charging stations associated with one of the navigation route and the destination information. In an exemplary aspect, a processing unit 204 of Fig. 2 of the system 200 may be configured to carry out the process steps disclosed in step 404.

[0074] At step 406, the method 400 may include selecting at least one charging station from the plurality of charging stations based on the received signal and a user preference profile. The user preference profile is associated with user past history of selecting charging stations over a predefined time period based on at least one charging station profile parameter and at least one charging station navigation parameter. In order to select the at least one charging station, the method 400 include determining the plurality of charging stations based on the navigation route, the source information, and the destination information, identifying at least one charging station profile parameter corresponding to charging station characteristics of the plurality of charging stations and charging station contextual proximity of the plurality of charging stations, identifying charging station navigation parameter corresponding to travel adjustments required during navigation to each of the plurality of charging stations, analyzing the identified at least one charging station profile parameter and the charging station navigation parameter based on the user preference profile, and selecting the at least one charging station based on the analysis. In an exemplary aspect, a processing unit 204 of Fig. 2 of the system 200 may be configured to carry out the process steps disclosed in step 406.

[0075] At step 408, the method 400 may include providing the selected at least one charging station. The test template include a sequence of operations to be performed on the one or more devices. In an exemplary aspect, the processing unit 204 may be configured to carry out the process steps disclosed in step 408.

[0076] In an embodiment, the method 400 include receiving a signal to perform manual selection of the at least one charging station from the plurality of charging stations, receiving preferred charging station contextual proximity with respect to the navigation route and the destination information and preferred charging station profile parameter for the selection of the at least one charging station, identifying at least one charging station from the plurality of charging stations based on the preferred charging station profile parameter and preferred contextual proximity, and updating the user preference profile based on the identified at least one charging station. In an exemplary aspect, the processing unit 204 along with the receiving unit 202 may be configured to carry out the process steps disclosed above.

[0077] Moving towards Fig. 5 showing steps of a method 500 of training a plurality of models for selecting charging stations for a vehicle, in accordance with an embodiment of the present disclosure. The method starts at step 502, at step 502 the method 500 may include receiving a plurality of navigation patterns over a predefined time period during a navigation of the vehicle. The plurality of navigation patterns corresponds to selection of charging stations by a user and navigation of the vehicle towards the selected charging stations. In an exemplary aspect, a receiving unit 302 of Fig. 3 of the system 300 may be configured to carry out the process steps disclosed in step 502.

[0078] At step 504, the method 500 may include generating a plurality of meta features for each of the plurality of navigation patterns by training a first set of model of the plurality of models on the received plurality of navigation patterns. The plurality of meta features correspond to prediction of the selection of charging stations. In an exemplary aspect, a training unit 304 of Fig. 3 of the system 300 may be configured to carry out the process steps disclosed in step 504.

[0079] At step 506, the method 500 may include training a second set of model of the plurality of models based on the generated meta features and the received plurality of navigation patterns to predict selection of the charging stations. In order to train the second set of model, the method 500 include aggregating the plurality of meta features corresponding to a respective navigation pattern of the plurality of patterns and performing regression analysis on the aggregated plurality of meta features with respect to the respective navigation pattern to predict the selection of the charging stations. In an exemplary aspect, a training unit 304 of Fig. 3 of the system 300 may be configured to carry out the process steps disclosed in step 506.

[0080] The technical effects associated with the present disclosure as shown below:

[0081] An embodiment of the present disclosure integrates a first set of machine learning (ML) models, each trained to predict specific factors influencing user choice of charging stations. By combining the predictions from these models, a second set of ML models provides a more accurate and robust recommendation.

[0082] An embodiment of the present disclosure automatically generates recommendations based on historical data related to the user previous charging choices and preferences, such as proximity to restaurants, shopping areas, RFID compatibility, and fastcharging availability. This reduces the need for manual intervention and improves the selection process by automatically presenting personalized options.

[0083] An embodiment of the present disclosure improves upon U.S. Patent No. 8,738,277 Bl, which focuses solely on historical data and static preferences, by dynamically integrating a broader range of user-specific criteria. These criteria include preferences related to location type (e.g., proximity to restaurants or shopping areas), charging features (such as fast charging and RFID support), and additional station attributes (such as no parking charges). This approach results in a more tailored, context-aware recommendation that better aligns with the user’s personal requirements.

[0084] The foregoing method descriptions and the process flow diagrams are provided merely as illustrative examples and are not intended to require or imply that the steps of the various embodiments must be performed in the order presented. As will be appreciated by one of skill in the art the order of steps in the foregoing embodiments may be performed in any order. Words such as “thereafter,” “then,” “next,” etc. are not intended to limit the order of the steps; these words are simply used to guide the reader through the description of the methods. Further, any reference to claim elements in the singular, for example, using the articles “a,” “an” or “the” is not to be construed as limiting the element to the singular.

[0085] As used herein, the term unit may be implemented in hardware and / or in software. If the unit is implemented in hardware, the unit may be configured as a device, e.g., as a computer or as a processor or as a part of a system, e.g., a computer system. If the unit is implemented in software, the unit may be configured as a computer program product, as a function, as a routine, or as a program code.

[0086] The hardware used to implement the various illustrative logics, logical blocks, modules, and circuits described in connection with the aspects disclosed herein may include a general purpose processor, a digital signal processor (DSP), a special-purpose processor such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA), a programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but, in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Alternatively or additionally, some steps or methods may be performed by circuitry that is specific to a given function.

[0087] Many modifications and other embodiments of the inventions set forth herein will come to mind to one skilled in the art to which these inventions pertain having the benefit of teachings presented in the foregoing descriptions and the associated drawings. Although the figures only show certain components of the apparatus and systems described herein, it is understood that various other components may be used in conjunction with the system. Therefore, it is to be understood that the inventions are not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Moreover, the steps in the method described above may not necessarily occur in the order depicted in the accompanying diagrams, and in some cases one or more of the steps depicted may occur substantially simultaneously, or additional steps may be involved. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

[0088] Claims:

Claims

1. A method (400) of selecting charging stations for a vehicle, the method comprising:receiving (402) source information and destination information to determine navigation route of the vehicle;receiving (404) a signal to perform automatic selection of at least one charging station from a plurality of charging stations associated with one of the navigation route and the destination information;selecting (406) at least one charging station from the plurality of charging stations based on the received signal and a user preference profile, wherein the user preference profile is associated with user past history of selecting charging stations over a predefined time period based on at least one charging station profile parameter and at least one charging station navigation parameter; andproviding (408) the selected at least one charging station.

2. The method (400) as claimed in claim 1, to select the at least one charging station, further comprising:determining the plurality of charging stations based on the navigation route, the source information, and the destination information;identifying at least one charging station profile parameter corresponding to charging station characteristics of the plurality of charging stations and charging station contextual proximity of the plurality of charging stations,wherein the charging station characteristics corresponds to at least one of surrounding facilities associated with charging station, vendor information associated with the charging station, a type of charging station, payment option associated with the charging station, and parking charges policies associated with the charging station, andwherein the charging station contextual proximity of the plurality of charging stations corresponds to location of each of the plurality of charging stations with respect to the navigation route, the source information, and the destination information;identifying charging station navigation parameter corresponding to travel adjustments required during navigation to each of the plurality of charging stations;analyzing the identified at least one charging station profile parameter and the charging station navigation parameter based on the user preference profile; andselecting the at least one charging station based on the analysis.

3. The method (400) as claimed in claim 1, further comprising:receiving a signal to perform manual selection of the at least one charging station from the plurality of charging stations;receiving preferred charging station contextual proximity with respect to the navigation route and the destination information and preferred at least one charging station profile parameter for the selection of the at least one charging station;identifying at least one charging station from the plurality of charging stations based on the preferred charging station profile parameter and preferred contextual proximity; andupdating the user preference profile based on the identified at least one charging station.

4. A system (200) for selecting charging stations for a vehicle, the system comprising:a receiving unit (204) configured to:receive source information and destination information to determine navigation route of the vehicle;receive a signal to perform automatic selection of at least one charging station from a plurality of charging stations associated with one of the navigation route and the destination information; anda processing unit (204) communicably coupled with the receiving unit, wherein the processing unit is configured to apply a pre-trained machine learning (ML) model in order to: select at least one charging station from the plurality of charging stations based on the received signal and a user preference profile, wherein the user preference profile is associated with user past history of selecting charging stations over a predefined time period based on at least one charging station profile parameter and at least one charging station navigation parameter; andprovide the selected at least one charging station.

5. The system (200) as claimed in claim 4, wherein, to select the at least one charging station, processing unit (204) is further configured to:determine the plurality of charging stations based on the navigation route, the source information, and the destination information;identify at least one charging station profile parameter corresponding to charging station characteristics of the plurality of charging stations and charging station contextual proximity of the plurality of charging stations,wherein the charging station characteristics corresponds to at least one of surrounding facilities associated with charging station, vendor information associated with the charging station, a type of charging station, payment option associated with the charging station, and parking charges policies associated with the charging station, andwherein the charging station contextual proximity of the plurality of charging stations corresponds to location of each of the plurality of charging stations with respect to the navigation route, the source information, and the destination information;identify charging station navigation parameter corresponding to travel adjustments required during navigation to each of the plurality of charging stations;analyze the identified at least one charging station profile parameter and the charging station navigation parameter based on the user preference profile; andselect the at least one charging station based on the analysis.

6. The system (200) as claimed in claim 4, wherein the processing unit (204) is further configured to:receive a signal to perform manual selection of the at least one charging station from the plurality of charging stations;receive preferred charging station contextual proximity with respect to the navigation route and the destination information and preferred at least one charging station profile parameter for the selection of the at least one charging station;identify at least one charging station from the plurality of charging stations based on the preferred charging station profile parameter and preferred contextual proximity; andupdate the user preference profile based on the identified at least one charging station.

7. A method (500) of training a plurality of models for selecting charging stations for a vehicle, the method comprising:receiving (502) a plurality of navigation patterns over a predefined time period during a navigation of the vehicle, wherein the plurality of navigation patterns corresponds to selection of charging stations by a user and navigation of the vehicle towards the selected charging stations;generating (504) a plurality of meta features for each of the plurality of navigation patterns by training a first set of model of the plurality of models on the received plurality of navigation patterns, wherein the plurality of meta features correspond to prediction of the selection of charging stations; andtraining (506) a second set of model of the plurality of models based on the generated meta features and the received plurality of navigation patterns to predict selection of the charging stations.

8. The method (500) as claimed in claim 7, wherein training the second set of model, further comprises:aggregating the plurality of meta features corresponding to a respective navigation pattern of the plurality of patterns; andperforming regression analysis on the aggregated plurality of meta features with respect to the respective navigation pattern to predict the selection of the charging stations.

9. A system (300) for training a plurality of models for selecting charging stations for a vehicle, the system comprising:a receiving unit (302) configured to receive a plurality of navigation patterns over a predefined time period during a navigation of the vehicle, wherein the plurality of navigation patterns corresponds to selection of charging stations by a user and navigation of the vehicle towards the selected charging stations; anda training unit (304) configured to:generate a plurality of meta features for each of the plurality of navigation patterns by training a first set of model of the plurality of models on the received plurality of navigation patterns, wherein the plurality of meta features correspond to prediction of the selection of charging stations; andtrain a second set of model of the plurality of models based on the generated meta features and the received plurality of navigation patterns to predict selection of the charging stations.

10. The system (300) as claimed in claim 9, wherein, to the train the meta-model, the training unit is configured to:aggregate the plurality of meta features corresponding to a respective navigation pattern of the plurality of patterns; andperform regression analysis on the aggregated plurality of meta features with respect to the respective navigation pattern to predict the selection of the charging stations.IntellectualPropertyOfficeApplication GB2418994.6Search report under Section 17 of the Patents Act 1977Date search completed: 27 June 2025Claims searched:International classificationSubclass and subgroup Valid from G01C21 / 34Field of searchWorldwide search of patent documents classified in the following areas of the IPC:G01CDatabases used in the preparation of this search report:SEARCH-PATENTDocuments considered to be relevantPatent literatureCategory Relevant claims Document of relevance X 1-10 WO 2023 / 163930 A1 (GELL MICHAEL N), See paragraphs [0014]-[0015] and Claim 7. X 1,4 &7-10 US 2020 / 217679 A1 (IBM), See paragraphs [0022] &[0041].Intellectual Property Office is an operating name of the Patent Office www.gov.uk / ipoX 1,4 &7-10 CN 112665600 A (STATE GRID BEIJING ELECTRIC POWER CO), See the EPODOC abstract X 1-6 US 8738277 B1 (HONDA MOTOR CO LTD), See Figures 4 &6. X 1 &4 US 2018 / 143035 A1 (NEXTEV USA INC), See paragraphs [0159] &[0169]-[0170]. X 1 &4 US 2020 / 225281 A1 (FORD GLOBAL TECH LLC), See Paragraphs [0056]-[0058].Non-patent literatureCategory Relevant claims Document of relevanceCategories Letter or symbol Description X Document indicating lack of novelty or inventive step. Y Document indicating lack of inventive step, if combined with another document of the same category. & Member of the same patent family. A Document indicating technological background. P Document published on or after the priority date but before the fling date of the present application. E Earlier application published on or after the filing date of the present application.

Images