Adaptive classification of an electric vehicle charging location using networked vehicle data

Abstract

A method for providing an electric vehicle charging recommendation is disclosed. The method may involve obtaining information associated with a multitude of charging events for a vehicle. This information may include a multitude of vehicle geolocations associated with these numerous charging events. The method may further involve generating a multitude of charging geolocation clusters from these vehicle geolocations. The method may also include determining the frequency of charging events for each charging geolocation cluster. Finally, the method may include classifying the charging geolocation clusters into primary charging station locations and routine charging station locations.Furthermore, the procedure can include defining a virtual polygon that connects the primary charging station location and the routine charging station locations, and transmitting the electric vehicle charging recommendation to a server based on the defined virtual polygon.

Description

FIELD OF TECHNOLOGY

[0001] The present disclosure relates to adaptive classification of electric vehicle (EV) charging locations, and more particularly to systems and methods for providing EV charging recommendations based on a classification of EV charging locations using connected vehicle data. GENERAL STATE OF THE ART

[0002] An electric vehicle (EV) is powered by electrical energy, and the vehicle user must regularly charge the vehicle battery to ensure uninterrupted vehicle operation. The user can charge the vehicle battery using EV chargers located at the user's home, workplace, and / or public charging stations. The user's convenience when operating an EV can be significantly increased if the EV charging infrastructure is easily accessible.

[0003] Knowledge of customer charging patterns and behavior is important for companies operating EV chargers and / or planning to build new charging infrastructure. However, information associated with charging patterns for a diverse set of customers may not be readily available or may be inaccurate. The lack of reliable information can lead to incorrect and / or delayed infrastructure-related decisions. SUMMARY

[0004] The present disclosure describes an electric vehicle (EV) charging recommendation system that can provide charging recommendations to companies that may operate a plurality of EV charging stations and / or plan to build new EV charging infrastructure. The recommendations may be associated with optimal locations on a road network where the new EV charging infrastructure can be built and / or one or more incentives that can be provided to vehicle users to improve the use of existing EV charging stations.

[0005] The system may obtain information associated with a plurality of charging sessions from a vehicle over a predefined period of time and may determine a plurality of charging station locations where the vehicle may have been charged during the period of time. The information may include vehicle locations and timestamps associated with each charging session. The system may determine the frequency of charging sessions at each charging station location and may classify the plurality of charging station locations into different categories based on the frequency of charging sessions.For example, the system may classify charging station locations with an associated charging frequency greater than a predefined threshold as "routine" charging station locations and a charging station location with a maximum charging frequency among the "routine" charging station locations as a "primary" charging station location. The primary charging station location may be a charging station location where the vehicle may be charged the most, and the routine charging station locations may be charging station locations where the vehicle may be charged frequently. In some aspects, the system may provide higher weights to charging events that may have occurred "recently" compared to "historical" charging events when classifying the charging station locations.

[0006] In further aspects, the system may define a virtual polygon on a virtual map of a geographic area connecting the primary charging station location and the routine charging station locations. The virtual polygon may indicate a "daily driving area" associated with the vehicle. The system may classify one or more charging station locations located within the virtual polygon as "nearby" charging station locations. The nearby charging station locations may indicate charging station locations that may be within the daily driving area associated with the vehicle; however, the vehicle may not frequently charge at the nearby charging station locations. The system may further classify one or more charging station locations located outside the virtual polygon as short- or long-distance charging stations.

[0007] The system can aggregate virtual polygons and associated charging station location classifications for a plurality of vehicles over the predefined time period and can determine EV charging recommendations based on the aggregated information. For example, the system can determine a recommendation to build new EV charging infrastructure at locations that may be located within a predefined distance from the short- or long-range charging station locations. As another example, the system can determine a recommendation to provide incentives (e.g., discounts, vouchers, subscriptions, etc.) to vehicle users who can use the nearby charging station locations to charge their vehicles, in order to improve the utilization of nearby charging station locations.In response to determining the recommendations, the system may transmit the recommendations to one or more servers associated with the companies that may manage existing EV charging infrastructure and / or plan to build new EV charging infrastructure.

[0008] The present disclosure discloses an electric vehicle charging recommendation system that provides EV charging infrastructure and / or incentive recommendations based on big data obtained from a variety of vehicles. Because the system provides the recommendations based on data obtained directly from the vehicles, the recommendations are accurate and timely. Furthermore, because the system provides recommendations based on real-time data collected over a period of time (e.g., 3 months, 6 months, 1 year, etc.), the recommendations provide actionable insights for those companies managing the EV charging infrastructure, facilitating timely and informed decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The detailed description is presented with reference to the accompanying drawings. The use of the same reference numerals may indicate similar or identical elements. Different elements and / or components than those illustrated in the drawings may be used for different embodiments, and some elements and / or components may not be present in different embodiments. The elements and / or components in the figures are not necessarily drawn to scale. Throughout the disclosure, the singular and plural terms may be used interchangeably, depending on the context. Fig. 1 illustrates an exemplary environment in which techniques and structures for providing the systems and methods disclosed in this document may be implemented. Fig. 2 illustrates a block diagram of an exemplary electric vehicle (EV) charging recommendation system according to the present disclosure. Fig. 3A illustrates an exemplary virtual polygonal surface according to the present disclosure. Fig. 3B illustrates an exemplary virtual circular area according to the present disclosure. Fig. 4 illustrates a flowchart of an exemplary EV charging recommendation method according to the present disclosure. DETAILED DESCRIPTION

[0010] The disclosure is described in more detail below in this specification with reference to the accompanying drawings, in which exemplary embodiments of the disclosure are shown and are not intended to be limiting.

[0011] Fig. 1 illustrates an example environment 100 in which techniques and structures for providing the systems and methods disclosed herein may be implemented. The environment 100 may include a plurality of vehicles (shown as a first vehicle 105a, a second vehicle 105b, and a third vehicle 105c), which may be battery electric vehicles (BEVs) or plug-in hybrid electric vehicles (PHEVs). Each vehicle 105a-c (or vehicle 105) may take the form of any passenger or commercial vehicle, such as an SUV, a car, a crossover vehicle, a van, a minivan, a taxi, a bus, etc. Further, the vehicle 105 may be a manually driven vehicle and / or configured to operate in a semi-autonomous or fully autonomous mode.Additionally, vehicle 105 may include a traction battery or battery pack ("vehicle battery," not shown) that may provide power for vehicle propulsion. The vehicle battery may be charged by an external power source, such as an electric vehicle (EV) charger.

[0012] The plurality of vehicles 105 may travel on a road network 110, which may include a plurality of EV charging stations (shown as EV charging stations 115a-f). Each EV charging station 115 (or each EV charging station 115) may include one or more EV chargers (not shown) with which a vehicle user may charge the vehicle 105. In some aspects, the EV charging stations 115 may be public charging stations that may be used by one or more vehicle users to charge their vehicles.

[0013] For example, the EV charging stations 115 may be commercial EV charging stations and / or charging stations in shopping malls, parking lots, gyms, offices, etc. In other cases, one or more EV charging stations 115 may be personal charging stations, which may be located at users' homes.

[0014] The environment 100 may further include an electric vehicle charging recommendation system 120 (system 120) and one or more servers 125. The system 120, the server(s) 125, and the plurality of vehicles 105 may be communicatively coupled to one another via one or more networks 130. The network(s) 130 illustrate(s) an example communication infrastructure in which the connected devices discussed in various embodiments of this disclosure may communicate. The network(s) 130 may be and / or include the Internet, a private network, a public network, or another configuration operating using one or more known communication protocols, such as, for example, Transmission Control Protocol / Internet Protocol (TCP / IP), Bluetooth ® , BLE ®, Wi-Fi based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, UWB and cellular technologies such as Time Division Multiple Access (TDMA), Code Division Multiple Access (CDMA), High Speed ​​Packet Access (HSPDA), Long-Term Evolution (LTE), Global System for Mobile Communications (GSM) and Fifth Generation (5G), to name just a few examples.

[0015] In some aspects, the server(s) 125 may be part of a cloud-based computing infrastructure and may be associated with and / or include a telematics service delivery network (SDN) that may be provided to the plurality of vehicles 105 and other vehicles (in Fig. 1 not shown) that may be part of a vehicle fleet. In additional aspects, the server(s) 125 may be associated with companies that may operate one or more EV charging stations 115 and / or companies that plan to build new EV charging infrastructure on the road network 110. For example, the server(s) 125 may be associated with companies that may plan to build new EV charging stations on the road network 110. In further aspects, the server(s) 125 may be associated with companies that may provide one or more incentives to vehicle users that may use the EV charging stations 115 to charge the vehicles 105. For example, the server(s) 125 may be associated with companies that may provide discounts, subscriptions, vouchers, etc. to vehicle users to incentivize users to use the EV charging stations 115 and / or one or more other facilities (e.g.,B , cafes, restaurants, etc.) located on the road network 110.

[0016] The system 120 may be configured to provide EV charging recommendations to the companies associated with the server(s) 125 based on charging patterns of the plurality of vehicles 105. In particular, the system 120 may obtain data associated with vehicle charging from each vehicle 105 (e.g., vehicle 105a) over a predefined period of time and may determine charging patterns for the vehicle 105a. The predefined period of time may be, for example, 1 month, 3 months, 6 months, 12 months, and / or the like. In some aspects, the system 120 may aggregate individual charging patterns for each vehicle 105a, 105b, 105c and then determine a consolidated charging pattern for the plurality of vehicles 105. The system 120 may provide EV charging recommendations to the companies associated with the server(s) 125 based on the consolidated charging pattern of the plurality of vehicles 105.

[0017] In some aspects, the system 120 may determine charging patterns for the vehicle 105a by determining the frequency of use of the EV charging stations 115 by the user of the vehicle 105a to charge the vehicle 105a. In response to determining the frequency of use, the system 120 may classify the EV charging stations 115 into a "primary" charging station, "routine" charging stations, and "nearby" charging stations based on the frequency of use. For example, the system 120 may classify the charging stations 115a, 115b, 115c as "routine" charging stations if the frequency of use associated with the charging stations 115a, 115b, 115c exceeds a first predefined threshold (e.g., more than 10 times) over a predefined period of time (e.g., 3 months). The classification of the charging stations 115a, 115b, 115c as “routine charging stations” may indicate that the user frequently charges the vehicle 105a at the charging stations 115a, 115b, 115c.

[0018] In an alternative aspect, the system 120 may classify the charging stations 115a, 115b, 115c as routine charging stations if the usage frequency assigned to the charging stations 115a, 115b, 115c over a "recent" predefined period of time (e.g., 1 month or less than 3 months) exceeds a second predefined threshold (e.g., more than 5 times). In yet another aspect, the system 120 may assign more weight to the "recent" usage frequency (e.g., frequency in the last 1 month or the last 2 months) than to the "historical" usage frequency (e.g., frequency in the last 3 or more months) of the charging stations 115a, 115b, 115c when classifying the charging stations 115a, 115b, 115c as routine charging stations.

[0019] The system 120 may additionally classify a charging station (e.g., charging station 115a) as the "primary" charging station from the charging stations 115a, 115b, 115c where the user may charge the vehicle 105a the most. The system 120 may further identify one or more charging stations (e.g., charging station 115d) as "nearby" charging stations, which may be located near the routine charging stations, but the user may rarely use the nearby charging station. For example, the associated usage frequency of the nearby charging stations may be less than a third predefined threshold (e.g., less than 2 times) over the predefined time period (e.g., 3 months) or the most recent predefined time period (e.g., 1 month). In further aspects, the system 120 mayclassify the charging stations (115e, 115f) as “long-distance” or “short-distance” charging stations based on the distance of the long-distance / short-distance charging station from the routine charging stations and / or the associated frequency of use of the long-distance / short-distance charging station.

[0020] In some aspects, the system 120 may classify the EV charging stations 115 based on big data acquired from the vehicle 105a and using one or more supervised or unsupervised machine learning algorithms operating based on a predefined set of rules. Examples of machine learning algorithms include, but are not limited to, algorithms associated with linear classifiers (logistic regression, Naive Bayes classifier), nearest neighbor, support vector machines, decision trees, boosted trees, random forest, hidden Markov model, and / or neural networks. The classification of each EV charging station 115 may evolve over time as the system 120 acquires more real-time charging data from the vehicle 105a. A detailed process for classifying the EV charging stations 115 is described in connection with Fig. 2 described.

[0021] The system 120 may aggregate the determined charging patterns (e.g., the classification of the EV charging stations 115 for each vehicle 105a, 105b, 105c) for the plurality of vehicles 105 and transmit EV charging recommendations to the server(s) 125 based on the aggregated charging patterns. In particular, the system 120 may use classifications of EV charging stations to determine EV charging recommendations, which the system 120 may transmit to the server(s) 125. In some aspects, the EV charging recommendations may include recommendations regarding EV charging infrastructure. For example, the system 120 may transmit a recommendation to the server(s) 125 (or companies associated with the server(s) 125) to construct new EV charging infrastructure in a geographic area where a number of routine charging stations may be less than a first predefined number threshold.The system 120 may further transmit a recommendation to the server(s) 125 (or companies associated with the server(s) 125) to construct new EV charging infrastructure in a geographic area where a number of long-range or short-range charging stations may be less than a second predefined number threshold.

[0022] In other aspects, the EV charging recommendations may include recommendations regarding EV charging incentives. For example, the system 120 may transmit a recommendation to the server(s) 125 (or companies associated with the server(s) 125) to provide incentives, e.g., discounts, coupons, etc., for the use of "nearby" charging stations and / or establishments (e.g., cafes, restaurants, etc.) located near the nearby charging stations to encourage vehicle users to use the nearby charging stations.

[0023] The companies associated with the server(s) 125 may use the recommendations provided by the system 120 to improve the frequency of use of existing EV charging stations on the road network 110 (e.g., by providing incentives) and / or to identify optimal locations on the road network 110 for the construction of new EV charging infrastructure.

[0024] Fig. 2 illustrates a block diagram of an exemplary electric vehicle (EV) charging recommendation system 200 (System 200) according to the present disclosure. During the description of Fig. 2 can be Fig. 3A and Fig. 3B reference may be made.

[0025] System 200 may be the same as system 120. System 200 described herein may be implemented in hardware, software (e.g., firmware), or a combination thereof. System 200 may be connected to a plurality of vehicles 202 (shown as a first vehicle 202a, a second vehicle 202b, and a third vehicle 202c) and one or more servers 204 via a network 206. In some aspects, system 200 may be part of server(s) 204. In other aspects, system 200 may be part of an external server (not shown) that may not be part of server(s) 204. Vehicles 202 may be the same as vehicles 105, server(s) 204 may be the same as server(s) 125, and network 206 may be the same as network 130.

[0026] The system 200 may include a variety of units, including, but not limited to, a transceiver 208, a processor 210, and a memory 212. The transceiver 208 may be configured to transmit information to and receive information from the vehicles 202 and the server(s) 204 via the network 206.

[0027] The processor 210 may be an artificial intelligence (AI) based processor and may be in communication with one or more storage devices, e.g., the memory 212 and / or one or more external databases (in Fig. 2 not shown). The processor 210 may utilize the memory 212 to store programs in code and / or to store data for performing various operations of the system 200 according to the present disclosure. The memory 212 may be non-transitory computer-readable memory for storing EV charging recommendation program code. The memory 212 may include any one or a combination of volatile memory elements (e.g., dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), etc.) and any one or more non-volatile memory elements (e.g., erasable programmable read-only memory (EPROM), flash memory, electronically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), etc.).

[0028] The memory 212 may include a variety of modules and databases, including, among others, a vehicle information database 214, a charging session determination module 216, a geolocation cluster determination module 218, a charging session frequency determination module 220, and a classification module 222. The modules 216, 218, 220, 222, as described herein, may be stored in the form of computer-executable instructions, and the processor 210 may be configured and / or programmed to execute the stored computer-executable instructions to perform functions of the system 200 according to the present disclosure. In particular, the modules 216, 218, 220, 222 may store computer-executable instructions associated with one or more supervised or unsupervised machine learning algorithms that may enable the processor 210 to perform functions of the system 200.Examples of machine learning algorithms are related to . Fig. 1 described.

[0029] In operation, transceiver 208 may receive information associated with charging alerts or actions from each vehicle 202a, 202b, 202c via network 206. The information associated with charging actions may include, for example, timestamps and geolocations for one or more actions associated with vehicles 202a, 202b, 202c. Examples of a charging action include, but are not limited to, a vehicle turn-on action, a vehicle turn-off action, an action to plug the charger into the electric vehicle, an action to unplug the charger from the electric vehicle, a charging start action, a charging stop action, and / or the like.

[0030] The transceiver 208 may receive the information associated with a charging action from a vehicle (e.g., the vehicle 202a) when the corresponding action can be performed on the vehicle 202a. For example, the transceiver 208 may receive a timestamp and geolocation of the vehicle associated with a charging start action when a user begins charging the vehicle 202a via an EV charging station (e.g., the charging station 115a). Similarly, the transceiver 208 may receive a timestamp and geolocation of the vehicle associated with a charging stop action when the user stops charging the vehicle 202a via the charging station 115a.

[0031] In response to receiving the information associated with the charging events from the vehicle 202a, the transceiver 208 may send the received information to the vehicle information database 214 for storage. The processor 210 may obtain the information from the vehicle information database 214 (or directly from the transceiver 208) and may generate one or more "charging event" data structures or records based on the obtained information. A charging event record may indicate a single instance of a vehicle charging performed on the vehicle 202a, and the processor 210 may generate the charging event record based on the obtained information and the instructions stored in the charging event determination module 216.In particular, the processor 210 may correlate timestamps and vehicle geolocations of an electric vehicle charger plug-in action, a charging start action, an electric vehicle charger unplug-out action, and a charging stop action to create a single charging event record. For example, if a timestamp (and vehicle geolocation) associated with the electric vehicle charger plug-in action is equivalent to a timestamp (and vehicle geolocation) associated with the charging start action, the processor 210 may determine that the actions can be associated with a single charging event.Similarly, if a timestamp (and vehicle geolocation) associated with the electric vehicle charger unplugging action is equivalent to a timestamp (and vehicle geolocation) associated with the charging stop action, processor 210 may determine that the actions can be associated with a single charging event. Furthermore, processor 210 may determine that the charging start action and the charging stop action can be associated with a single charging event if the associated vehicle geolocations for the two actions are the same and the difference between the associated timestamps is less than a predefined charging time threshold (which may correspond to a standard charging time duration of an EV battery).

[0032] In some aspects, the processor 210 may use the information associated with the charging actions and may "stitch" the actions (based on timestamps and / or vehicle geolocations) to determine one or more separate charging events associated with the vehicle 202a, as described above. In response to determining the separate charging events, the processor may create and store records for the charging events as "charging event records" associated with the vehicle 202a in the vehicle information database 214. A charging event record may include a charging event duration (e.g., a duration between the charging start action and the charging stop action) and a charging event geolocation.The geolocation of the charging session may be determined using the vehicle geolocation obtained from the vehicle 202a and may indicate a location of an EV charger that the user may have used to charge the vehicle 202a. Those of ordinary skill in the art will appreciate from the foregoing description that the geolocation of the charging session is determined by the processor 210 based on the vehicle geolocations associated with the charging actions obtained from the vehicle 202a.

[0033] In a similar manner as described above, the processor 210 may create (and store) charging session records for a plurality of charging sessions associated with the vehicle 202a over a predefined period of time. For example, the processor 210 may create charging session records for the vehicle 202a over a period of 1 month, 3 months, 6 months, 12 months, and / or the like. Each charging session record may include an associated charging session geolocation, which may indicate a location of an EV charger that may have been used to charge the vehicle 202a for the charging session.

[0034] In response to generating / creating the charging session records, the processor 210 may use the instructions stored in the geolocation cluster determination module 218 and generate (or determine) a plurality of charging geolocation clusters based on the charging session geolocations associated with the plurality of charging sessions. In some aspects, the processor 210 may generate the plurality of charging geolocation clusters based on distances between the charging session geolocations. In particular, the processor 210 may cluster or "combine" charging session geolocations that may be close to each other (e.g., having a distance of less than 250 meters between the geolocations) as a single charging geolocation cluster. For example, if the user uses two EV chargers that may be located at two separate edges of a parking lot (e.g.,a right parking space edge and a left parking space edge, which may be separated by a distance of 200 meters) to charge the vehicle 202a, the processor 210 may "combine" geolocations of the two EV chargers into a single geolocation cluster.

[0035] In some aspects, to generate the charging geolocation clusters, the processor 210 may determine distances between each charging geolocation and may group these charging geolocations together into a single cluster that may have distances therebetween that are less than a predefined threshold (e.g., 250 meters).

[0036] Examples of charging geolocation clusters are in Fig. 3A and Fig. 3B. In particular, Fig. 3A and Fig. 3B illustrates a map of a geographic area 300, e.g., a city, a suburb, etc. The geographic area 300 may include a plurality of charging geolocation clusters 305a-f, which may indicate a plurality of charging station locations where the user may have charged the vehicle 202a over a period of 1 month, 3 months, 6 months, 12 months, and / or the like. Hereinafter, the charging geolocation clusters 305a-f are referred to as charging station locations 305a-f.

[0037] In response to determining the charging station locations 305a-f, the processor 210 may use the instructions stored in the charging frequency determination module 220 to determine a charging frequency for each charging station location 305a-f. The charging frequency may indicate a number of charging events associated with the vehicle 202a that may have occurred at a particular charging station location. For example, if the user has charged the vehicle 202a eight times at the charging station location 305a in the last three months, the charging frequency for the charging station location 305a may be eight.

[0038] In some aspects, processor 210 may determine the frequency of charge occurrence for a charging station location based on a linear count of charge occurrences that have occurred at the charging station location over a predefined period of time (e.g., 1 month, 3 months, 6 months, 12 months, and / or the like). In other aspects, processor 210 may determine the frequency of charge occurrence for a charging station location based on a weighted count of charge occurrences that have occurred at the charging station location over a predefined period of time. In this case, processor 210 may assign a higher weight to the most recent occurrence of charge occurrences (e.g., which may have occurred "recently" in the last 1 month) compared to the occurrence of historical charge occurrences (e.g., which occurred before the last 1 month).For example, if the user charged the vehicle 202a four times at the charging station 305a in the last 1 month and twice before the last 1 month, the processor 210 may determine the frequency of charging occurrences at the charging station 305a as five (rather than six). In this case, the processor 210 may assign a weight of "1" to the occurrence of charging occurrences in the last 1 month and a weight of "0.5" to the occurrence of charging occurrences before the last 1 month. In some aspects, the weights associated with the predefined time periods may be pre-stored in the memory 212. One of ordinary skill in the art will understand that the weights described herein are exemplary in nature and should not be construed as limiting the scope of the present disclosure.

[0039] In some aspects, processor 210 may determine the number of charging events based on the timestamps associated with the charging events acquired from vehicle 202a and / or types of charging events. For example, processor 210 may identify a "pair" of a charging start and stop event (which have the same geolocation and a difference in associated timestamps greater than a predefined charging threshold) as a single charging event. As another example, two charging start events that have a difference between associated timestamps greater than a predefined timestamp threshold may be identified by processor 210 as two separate charging events.

[0040] In response to determining the frequency of charging occurrence for the charging station locations 305a-f, the processor 210 may send the determined frequency of charging occurrence to the memory 212 for storage purposes. Further, the processor 210 may classify the charging station locations 305a-f into various classifications based on the determined frequency of charging occurrence, as described below.

[0041] The processor 210 may use the instructions stored in the classification module 222 and classify the charging station locations 305a-f into a variety of classifications, including, but not limited to, "routine" charging station locations, a "primary" charging station location, "nearby" charging station locations, "short-range" charging locations, "long-range" charging locations, etc. In one example aspect, the "routine" charging station locations may have an associated frequency of charging occurrence that is greater than a predefined routine threshold (e.g., in a range of 4-8 instances in the last 1 or 2 months). In this case, the predefined routine threshold may be pre-stored in the memory 212, and the processor 210 may retrieve the predefined routine threshold from the memory 212 to classify the charging station locations 305a-f.

[0042] In further aspects, the processor 210 may classify a charging station location from the "routine" charging station locations with a maximum frequency of charging occurrence as the "primary" charging station location. The "primary" charging station location may indicate a charging station location where the user may have charged the vehicle 202a most frequently in the past. Fig. 3A and Fig. 3B, the “primary” charging station location is depicted as charging station location 305a and the “routine” charging station locations are depicted as charging station locations 305b and 305c.

[0043] In response to classifying one or more charging station locations as “primary” and “routine,” the processor 210 may define a virtual polygon 310 (or a polygonal vector) connecting the primary and routine charging station locations on the map of the geographic area 300, as shown in Fig. 3A. For example, as shown in Fig. 3A, the processor 210 may define a first virtual triangle 310 (or triangle vector) connecting the charging station locations 305a, 305b, and 305c. The area within the first virtual triangle 310 may denote a "daily driving area" associated with the user of the vehicle 202a. In other words, the area within the first virtual triangle 310 may denote an area in which the user of the vehicle 202a may frequently or primarily drive (and thus charge) the vehicle 202a. Defining the first virtual triangle 310 may enable the processor 210 to classify the charging station locations as "nearby," "short-haul," and "long-haul" charging station locations, which in turn may enable the processor 210 to provide EV charging recommendations to the server(s) 204, as described below.

[0044] In response to defining the first virtual triangle 310 on the map of the geographic area 300, the processor 210 may classify the charging station locations located within the first virtual triangle 310 as "nearby" charging station locations. For example, the processor 210 may classify the charging station locations 305d and 305e as "nearby" charging station locations. In an example case, a "nearby" charging station location may refer to a charging station location that is within the daily driving area of ​​the user of the vehicle 202a, but that the user infrequently uses to charge the vehicle 202a.

[0045] Additionally, in response to defining the first virtual triangle 310 on the map of the geographic area 300, the processor 210 may add a predefined virtual distance buffer to each edge of the first virtual triangle 310 and define a second virtual triangle 315 (or a second virtual polygon), as shown in Fig. 3A. In one example aspect, the predefined virtual distance buffer may vary based on an area of ​​a first virtual triangle 310, such that an area of ​​a second virtual triangle 315 may be in a range of 1.5 to 5 times the area of ​​the first virtual triangle 310. In some cases, the processor 210 may calculate the predefined virtual distance buffer based on the area of ​​the first virtual triangle 310 and a preset ratio (which may be stored in the memory 212) between the area of ​​the second virtual triangle 315 and the area of ​​the first virtual triangle 310.

[0046] In one example aspect, the area within the second virtual triangle 315 and outside the first virtual triangle 310 on the map of the geographic area 300 may designate a "short-range driving area" associated with the user of the vehicle 202a. The processor 210 may classify the charging station locations located within the short-range driving area as short-range charging station locations. For example, the processor 210 may classify the charging station location 305f as a short-range charging station location. Furthermore, the processor 210 may classify the charging stations located outside the second virtual triangle 315 as long-range charging station locations. For example, the processor 210 may classify the charging station location 305g as a long-range charging station location.A short-distance charging station location may indicate a charging station location where the user can charge the vehicle 202a when the user takes a short trip (outside the daily driving area) using the vehicle 202a. Similarly, a long-distance charging station location may indicate a charging station location where the user can charge the vehicle 202a when the user takes a long trip (outside the daily driving area) using the vehicle 202a.

[0047] Similarly, the processor 210 may define first and second virtual polygons for a plurality of vehicles (e.g., vehicles 202a, 202b, 202c) over a predefined period of time and classify charging station locations into different classifications. The processor 210 may further transmit EV charging recommendations to the server(s) 204 based on the defined first and second virtual polygons. In particular, the processor 210 may determine daily driving areas (e.g., the first virtual polygon 310) and short-distance driving areas (e.g., the second virtual polygon 315) for each of the plurality of vehicles and transmit EV charging recommendations to the server(s) 204 based on the primary charging station locations, routine charging station locations, nearby charging station locations, short-distance charging station locations, and long-distance charging station locations associated with the plurality of vehicles.

[0048] For example, if a charging station (e.g., charging station location 305d) is classified as a "nearby" charging station location for the plurality of vehicles, the processor 210 may determine that, although the charging station location 305d may be located within the daily driving areas associated with users of the plurality of vehicles, the users may not frequently use the charging station location 305d to charge their vehicles. In this case, the processor 210 may transmit a recommendation to the server(s) 204 (and thus to the businesses associated with the server(s) 204) to provide incentives for the users to use the charging station location 305d. The incentives may include, for example, discount vouchers, subscriptions, vouchers for establishments (e.g., cafes, restaurants, etc.) located near the charging station location 305d, and / or the like.

[0049] As another example, if a charging station (e.g., charging station location 305g) can be used by a plurality of vehicles on long trips to charge the vehicles, the processor 210 can transmit a recommendation to the server(s) 204 (and thus to the companies associated with the server(s) 204) to build a new EV charging infrastructure within a predefined distance from the charging station location 305g to maximize the likelihood of using a new EV charging infrastructure.

[0050] In additional aspects, processor 210 may transmit an EV charging recommendation to server(s) 204 based on the charging station locations and the amount of time users typically spend charging their vehicles at the charging station locations. For example, if users typically spend more time charging their vehicles at charging station location 305c than at charging station location 305b, processor 210 may transmit a recommendation to server(s) 204 indicating that new EV charging infrastructure could be built near charging station location 305c (thereby reducing the load at charging station location 305c). As another example, processor 210 may transmit a recommendation to server(s) 204 indicating that vouchers for establishments (e.g., cafes, restaurants, etc.) located near charging station location 305c may be provided to users.

[0051] Although the above description describes an aspect in which the processor 210 defines virtual triangles (e.g., the first virtual triangle 310 and the second virtual triangle 315) to classify the charging station locations, the present disclosure is not limited to the polygon being a triangle. Furthermore, the present disclosure is not limited to the processor 210 defining a polygon to classify the charging station locations. Fig. 3B illustrates another aspect of the present disclosure, wherein the processor 210 defines circles (shown as a first circle 320a, a second circle 320b, and a third circle 320c) with a predefined radius (which may be pre-stored in the memory 212) to capture the "primary" and "routine" charging station locations. A charging station location (e.g., charging station location 305d) located within the defined circles may be classified as a "nearby" charging station location, and a charging station location (e.g., charging station location 305g) located outside the defined circles may be classified as a "remote" charging station location. In this case, the processor 210 may not classify the charging station locations as short-range or long-range charging stations.

[0052] Fig. 4 illustrates a flowchart of an exemplary EV charging recommendation method 400 according to the present disclosure. Fig. 4 can be further understood by reference to the previous figures, including the Fig. 1, Fig. 2, Fig. 3A and Fig. 3B. The following process is exemplary and not limited to the steps described below. Moreover, alternative embodiments may include more or fewer steps shown or described in this specification and may include these steps in a different order than the order described in the following exemplary embodiments.

[0053] The method 400 begins at step 402. At step 404, the method 400 may include obtaining, by the processor 210, information associated with a plurality of charging events for the vehicle 202a. As described above, the processor 210 may obtain information about charging alerts or actions associated with the vehicle 202a and "stitch" the actions together to identify one or more separate charging events associated with the vehicle 202a. The information associated with the charging events may include charging event durations and charging event geolocations, as described above.

[0054] At step 406, the method 400 may include generating, by the processor 210, a plurality of charging geolocation clusters 305a-f based on the charging geolocations. At step 408, the method 400 may include determining, by the processor 210, a frequency of charging occurrences for each charging geolocation cluster 305a-f. As described above, the processor 210 may determine the frequency of charging occurrences based on a linear or weighted count of the charging occurrences that may have occurred at each geolocation cluster 305a-f over a predefined period of time.

[0055] At step 410, the method 400 may include the processor 210 classifying a first geolocation cluster (e.g., the charging station location 305a) as a “primary” charging station location and a plurality of second geolocation clusters (the charging station locations 305b and 305c) as “routine” charging station locations based on the frequency of charging occurrence, as described above.

[0056] At step 412, the method 400 may include defining, by the processor 210, a virtual polygon (e.g., the first virtual triangle 310) connecting the primary charging station location and the routine charging station locations. At step 414, the method 400 may include transmitting, by the processor 210, an electric vehicle charging recommendation to the server(s) 204 based on the defined virtual polygon. As described above, the electric vehicle charging recommendation may be associated with a recommendation to deploy charging station infrastructure and / or a recommendation to provide incentives for vehicle users.

[0057] At step 416, the method 400 may be terminated.

[0058] In some aspects, the method may include 400 additional steps (in Fig. 4 not shown) for defining another virtual polygon (e.g., the second virtual polygon 315) by adding a predefined virtual distance buffer to each first edge of the virtual triangle 310, as described above. The processor 210 may classify the charging station locations as short-range or long-range charging station locations based on the second virtual polygon 315, as described in connection with Fig. 2. The processor 210 may further classify one or more charging station locations as nearby charging station locations if the charging station locations are located within the first virtual triangle 310.

[0059] In the foregoing disclosure, reference has been made to the accompanying drawings, which form a part hereof, and illustrate specific implementations in which the present disclosure may be practiced. It is understood that other implementations may be utilized and structural changes may be made without departing from the scope of the present disclosure. References in the specification to "one embodiment," "an embodiment," etc., indicate that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Further, such phrases are not necessarily all referring to the same embodiment.Furthermore, if a feature, structure, or characteristic is described in connection with one embodiment, those skilled in the art will recognize such a feature, structure, or characteristic in connection with other embodiments, whether or not explicitly described.

[0060] Furthermore, the functions described in this document may be performed in one or more of hardware, software, firmware, digital components, or analog components, as appropriate. For example, one or more application-specific integrated circuits (ASICs) may be programmed to perform one or more of the systems and procedures described in this document. Certain terms used throughout the specification and claims refer to specific system components. It will be apparent to one skilled in the art that the components may be referred to by other names. This document does not intend to distinguish between components that differ in name but not in function.

[0061] It is also understood that the word "example," as used in this document, is intended to be non-exclusive and non-limiting. More specifically, the word "example," as used in this document, indicates one of several examples, and it is understood that no undue emphasis or preference is placed on the specific example described.

[0062] A computer-readable medium (also referred to as a processor-readable medium) includes any non-transitory (e.g., physical) medium that participates in providing data (e.g., instructions) that can be read by a computer (e.g., by a processor of a computer). Such a medium may take many forms, including, without limitation, non-transitory media and volatile media. Computing devices may include computer-executable instructions, where the instructions may be executable by one or more computing devices, such as those listed above, and may be stored on a computer-readable medium.

[0063] With respect to the processes, systems, methods, heuristics, etc., described in this specification, it is understood that although the steps of such processes, etc., have been described as occurring according to a certain ordered sequence, such processes could be practiced wherein the described steps are performed in an order different from the order described in this specification. Further, it is understood that certain steps could be performed concurrently, other steps could be added, or certain steps described in this specification could be omitted. In other words, the descriptions of processes in this specification are for the purpose of illustrating various embodiments and should in no way be construed to limit the claims.

[0064] Accordingly, it is to be understood that the foregoing description is intended to be illustrative and not restrictive. Many other embodiments and applications than the examples listed will become apparent from a reading of the foregoing description. The scope should be determined not by reference to the foregoing description, but instead by reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. It is anticipated and intended that there will be future developments in the art discussed herein, and that the disclosed systems and methods will be incorporated into such future embodiments. Overall, it is understood that the application is susceptible of modification and variation.

[0065] All terms used in the claims are intended to have their general meaning as known to one of ordinary skill in the art to which the technologies described in this specification apply, unless expressly stated otherwise herein. In particular, the use of the singular articles, such as "a," "an," "the," "the," "the," etc., is intended to refer to one or more of the specified elements, unless a claim expressly limits otherwise.Conditional language, such as "may," "could," "may," or "may possibly," is generally intended to convey that certain embodiments may include certain features, elements, and / or steps, while other embodiments may not include them, unless specifically stated otherwise or clear from the particular context used. Thus, such conditional language is generally not intended to imply that features, elements, and / or steps are in any way required for one or more embodiments.

[0066] According to one embodiment, the processor classifies the primary charging station location by: identifying a first routine charging station location from the routine charging station locations, the first routine charging station location having a maximum charging frequency from the frequency of occurrence of routine charging events; and classifying the first routine charging station location as the primary charging station location.

[0067] According to one embodiment, the processor is further configured to classify one or more third charging geolocation clusters from the plurality of charging geolocation clusters located within the virtual polygon as nearby charging station locations.

[0068] According to one embodiment, the processor is further configured to: classify one or more fourth charging geolocation clusters from the plurality of charging geolocation clusters located less than a predefined virtual distance from a virtual polygon edge as short-range charging station locations; and classify one or more fifth charging geolocation clusters from the plurality of charging geolocation clusters located more than the predefined virtual distance from the virtual polygon edge as long-range charging station locations, wherein the processor determines the electric vehicle charging recommendation based on the short-range charging station locations and the long-range charging station locations.

[0069] According to one embodiment, the electric vehicle charging recommendation comprises at least one of a recommendation to develop a charging station infrastructure and a recommendation to create charging station incentives.

[0070] According to the present invention, a non-transitory computer-readable storage medium is provided having stored thereon instructions that, when executed by a processor, cause the processor to: obtain information associated with a plurality of charging events for a vehicle, the information comprising a plurality of vehicle locations associated with the plurality of charging events; generate a plurality of charging geolocation clusters from the plurality of vehicle geolocations; determine a frequency of occurrence of charging events for each charging geolocation cluster based on the information;Classifying a first charging geolocation cluster from the plurality of charging geolocation clusters as a primary charging station location and a plurality of second charging geolocation clusters from the plurality of charging geolocation clusters as routine charging station locations based on the frequency of charging occurrences; Defining a virtual polygon connecting the primary charging station location and the routine charging station locations; and transmitting an electric vehicle charging recommendation to a server based on the virtual polygon.

Claims

[1] A method for providing an electric vehicle charging recommendation, the method comprising: Obtaining, by a processor, information associated with a plurality of charging sessions for a vehicle, the information comprising a plurality of vehicle geolocations associated with the plurality of charging sessions; generating, by the processor, a plurality of charging geolocation clusters from the plurality of vehicle geolocations; determining, by the processor, a frequency of occurrence of charging operations for each charging geolocation cluster based on the information; Classifying, by the processor, a first charging geolocation cluster from the plurality of charging geolocation clusters as a primary charging station location and a plurality of second charging geolocation clusters from the plurality of charging geolocation clusters as routine charging station locations based on the frequency of occurrence of charging events; Defining, by the processor, a virtual polygon connecting the primary charging station location and the routine charging station locations; and The processor transmits an electric vehicle charging recommendation to a server based on the defined virtual polygon. [2] The method of claim 1, wherein the routine charging station locations have a frequency of occurrence of routine charging operations that is above a predefined threshold. [3] The method of claim 2, wherein classifying the primary charging station location comprises: Identifying a first routine charging station location from the routine charging station locations, wherein the first routine charging station has a maximum charging frequency from the frequency of occurrence of routine charging processes; and Classify the first routine charging station as the primary charging station location. [4] The method of claim 1, wherein the information includes timestamps for each loading operation. [5] The method of claim 4, further comprising: Assigning a weight to each loading process based on the timestamps; and Determine the frequency of loading occurrences based on the weights. [6] The method of claim 1, wherein generating the plurality of charging geolocation clusters comprises generating the plurality of charging geolocation clusters based on distances of the plurality of vehicle geolocations from each other. [7] The method of claim 1, wherein the plurality of charging operations comprises at least one of: an operation for turning on the vehicle, an operation for turning off the vehicle, a charging start operation of the vehicle, a charging stop operation of the vehicle. [8] The method of claim 7, wherein the information further comprises a time period between the vehicle's charging start operation and the vehicle's charging stop operation. [9] The method of claim 8, further comprising determining the electric vehicle charging recommendation based on the time duration. [10] The method of claim 1, wherein the electric vehicle charging recommendation comprises at least one of a recommendation to develop a charging station infrastructure and a recommendation to create charging station incentives. [11] The method of claim 1, further comprising classifying one or more third charging geolocation clusters from the plurality of charging geolocation clusters located within the virtual polygon as nearby charging station locations. [12] The method of claim 11, further comprising: Classifying one or more fourth charging geolocation clusters from the plurality of charging geolocation clusters located less than a predefined virtual distance from a virtual polygon edge as short-range charging station locations, and Classifying one or more fifth charging geolocation clusters from the plurality of charging geolocation clusters located more than the predefined virtual distance from the virtual polygon edge as long-range charging station locations. [13] The method of claim 12, further comprising determining the electric vehicle charging recommendation based on the short-range charging station locations and the long-range charging station locations. [14] A system for providing an electric vehicle charging recommendation, the system comprising: a transceiver configured to receive information associated with a plurality of charging sessions for a vehicle, the information comprising a plurality of vehicle geolocations associated with the plurality of charging sessions; a processor communicatively coupled to the transceiver; and a memory for storing executable instructions, wherein the processor is configured to execute the instructions to: Obtaining the information from the transceiver; Generating a plurality of charging geolocation clusters from the plurality of vehicle geolocations; Determining a frequency of occurrence of charging events for each charging geolocation cluster based on the information; Classifying a first charging geolocation cluster from the plurality of charging geolocation clusters as a primary charging station location and a plurality of second charging geolocation clusters from the plurality of charging geolocation clusters as routine charging station locations based on the frequency of charging occurrence; Defining a virtual polygon connecting the primary charging station location and the routine charging station locations; and Transmitting an electric vehicle charging recommendation to a server based on the defined virtual polygon. [15] The system of claim 14, wherein the routine charging station locations have a frequency of occurrence of routine charging events that is above a predefined threshold.

Images