Adaptive classification of electric vehicle charging locations using networked vehicle data

Abstract

The disclosure provides adaptive classification of electric vehicle charging locations using networked vehicle data. A method for providing electric vehicle charging recommendations is disclosed. The method may include obtaining information associated with a plurality of charging events of the vehicle. The information may include a plurality of vehicle geographic locations associated with a plurality of charging events. The method also includes generating a plurality of charging geo-location clusters from the plurality of vehicle geo-locations. The method may additionally include determining a charging event occurrence frequency for each charging geo-location cluster. In addition, the method may include classifying the charging geographic location cluster into a primary charging station location and a regular charging station location. Further, the method may include defining a virtual polygon connecting the primary charging station location with the regular charging station location, and transmitting the electric vehicle charging recommendation to a server based on the defined virtual polygon.

Description

Technical Field

[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 classification of EV charging locations using networked vehicle data. Background Art

[0002] Electric vehicles (EVs) operate on electrical energy, and vehicle users need to charge the vehicle battery regularly to ensure uninterrupted vehicle operation. Users can charge the vehicle battery using an EV charger located at the user's home, workplace, and / or public charging stations. When EV charging infrastructure is easily accessible, the convenience of operating an EV for a user may be significantly improved.

[0003] Understanding customer charging patterns and behaviors is important for entities that operate EV chargers and / or plan to build new charging infrastructure. However, information associated with charging patterns of different sets of customers may not be easily available or may be inaccurate. Lack of reliable information may lead to incorrect and / or delayed infrastructure-related decisions. Summary of the invention

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

[0005] The system may obtain information associated with multiple charging events within a predefined duration from the vehicle, and may determine multiple charging station locations where the vehicle may have been charged during the duration. The information may include a vehicle geographic location and a timestamp associated with each charging event. The system may determine the frequency of charging events at each charging station location, and may classify multiple charging station locations into different categories based on the frequency of charging events. For example, the system may classify charging station locations with an associated charging event frequency greater than a predefined threshold as "regular" charging station locations, and classify the charging station location with the maximum charging event frequency in the "regular" charging station location as a "primary" charging station location. The primary charging station location may be the charging station location where the vehicle may be charged the most, and the conventional charging station location may be the charging station location where the vehicle may be charged frequently. In some aspects, when the system classifies the charging station location, the system may provide a higher weight to charging events that may have occurred "recently" compared to "historical" charging events.

[0006] In another aspect, the system may define a virtual polygon on a virtual map of a geographic area connecting the primary charging station location with the regular 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 within the virtual polygon as "nearby" charging station locations. 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 location. The system may also classify one or more charging station locations located outside the virtual polygon as short-distance or long-distance charging station locations.

[0007] The system may aggregate virtual polygons and associated charging station location classifications for multiple vehicles over a predefined duration, and may determine EV charging recommendations based on the aggregated information. For example, the system may determine a recommendation for building new EV charging infrastructure at a location that may be set at a predefined distance from a short-distance or long-distance charging station location. As another example, the system may determine a recommendation for providing incentives (e.g., discounts, coupons, subscriptions, etc.) to vehicle users who can use nearby charging station locations to charge their vehicles to enhance the use of nearby charging station locations. In response to determining the recommendation, the system may transmit the recommendation to one or more servers associated with an entity that may be managing an existing EV charging infrastructure and / or planning to build a 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 multiple vehicles. Since the system provides recommendations based on data obtained directly from the vehicle, the recommendations are accurate and up-to-date. In addition, since the system provides recommendations based on real-time data collection over a period of time (e.g., 3 months, 6 months, 1 year, etc.), the recommendations provide actionable insights to entities that manage EV charging infrastructure, thereby facilitating timely and informed decision making. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Detailed description is set forth with reference to the accompanying drawings. The use of the same reference numerals may indicate similar or identical items. Various embodiments may utilize elements and / or components other than those shown in the accompanying drawings, and some elements and / or components may not be present in various embodiments. The elements and / or components in the accompanying drawings are not necessarily drawn to scale. Throughout this disclosure, singular and plural terms may be used interchangeably, depending on the context.

[0010] Figure 1 An exemplary environment is depicted in which techniques and structures for providing the systems and methods disclosed herein may be implemented.

[0011] Figure 2A block diagram of an exemplary electric vehicle (EV) charging recommendation system according to the present disclosure is depicted.

[0012] Figure 3A Depicted are exemplary virtual polygonal regions in accordance with the present disclosure.

[0013] Figure 3B Depicted are exemplary virtual circular areas according to the present disclosure.

[0014] Figure 4 A flow chart of an exemplary EV charging recommendation method according to the present disclosure is depicted. DETAILED DESCRIPTION

[0015] The present disclosure will be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments of the disclosure are shown and which are not intended to be limiting.

[0016] Figure 1 An exemplary environment 100 in which techniques and structures for providing the systems and methods disclosed herein may be implemented is depicted. 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 to 105c (or vehicle 105) may take the form of any passenger vehicle or commercial vehicle, such as, for example, an SUV, a car, a crossover, a van, a minivan, a bus, a truck, etc. In addition, the vehicle 105 may be a manually driven vehicle and / or may be configured to operate in a partially or fully autonomous mode. In addition, the vehicle 105 may include a traction battery or battery pack ("vehicle battery", not shown) that may provide energy for vehicle propulsion. The vehicle battery may be charged by an external power source (e.g., an electric vehicle (EV) charger).

[0017] A 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 to 115f). Each EV charging station 115 (or a plurality of EV charging stations 115) may include one or more EV chargers (not shown) that a vehicle user may use to charge the vehicle 105. In some aspects, the EV charging station 115 may be a public charging station that may be used by one or more vehicle users to charge their vehicles. For example, the EV charging station 115 may be a commercial EV charging station, and / or may be a charging station / charger located at a shopping mall, a parking lot, a gym, an office, etc. In other aspects, one or more EV charging stations 115 may be personal charging stations that may be located at a user's home.

[0018] The environment 100 may also include an electric vehicle charging recommendation system 120 (system 120) and one or more servers 125. The system 120, the server 125, and the plurality of vehicles 105 may be communicatively coupled to each other via one or more networks 130. The network 130 illustrates an exemplary communication infrastructure in which networked devices discussed in various embodiments of the present disclosure may communicate. The network 130 may be and / or may include the Internet, a private network, a public network, or other configurations operating using any one or more known communication protocols, such as, for example, Transmission Control Protocol / Internet Protocol (TCP / IP), Wi-Fi, UWB, and cellular technologies based on the Institute of Electrical and Electronics Engineers (IEEE) standard 802.11, 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 a few examples.

[0019] In some aspects, the server 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 provides services to the plurality of vehicles 105 and other vehicles that may be part of a vehicle fleet ( Figure 1 110). In additional aspects, the server 125 may be associated with an entity that may be operating one or more EV charging stations 115 and / or an entity that may be planning to build new EV charging infrastructure on the road network 110. For example, the server 125 may be associated with a company that may be planning to build new EV charging stations on the road network 110. In further aspects, the server 125 may be associated with an entity that may provide one or more incentives to vehicle users who may use the EV charging station 115 to charge the vehicle 105. For example, the server 125 may be associated with an entity that may provide discounts, subscriptions, coupons, etc. to vehicle users to incentivize users to use the EV charging station 115 and / or one or more other facilities (e.g., coffee shops, restaurants, etc.) located on the road network 110.

[0020] The system 120 may be configured to provide EV charging recommendations to an entity associated with the server 125 based on the charging patterns of the plurality of vehicles 105. Specifically, the system 120 may obtain data associated with vehicle charging within a predefined duration from each vehicle 105 (e.g., vehicle 105a), and may determine the charging pattern of the vehicle 105a. The predefined duration may be, for example, 1 month, 3 months, 6 months, 12 months, etc. In some aspects, the system 120 may aggregate the individual charging patterns of each vehicle 105a, 105b, 105c, and may then determine a combined charging pattern for the plurality of vehicles 105. The system 120 may provide EV charging recommendations to an entity associated with the server 125 based on the combined charging patterns for the plurality of vehicles 105.

[0021] In some aspects, the system 120 may determine the charging mode of the vehicle 105a by determining the frequency with which the user of the vehicle 105a uses the EV charging station 115 to charge the vehicle 105a. In response to determining the frequency of use, the system 120 may classify the EV charging station 115 into a "primary" charging station, a "regular" charging station, and a "nearby" charging station based on the frequency of use. For example, when the frequency of use associated with the charging station 115a, 115b, 115c exceeds a first predefined threshold (e.g., more than 10 times) within a predefined duration (e.g., 3 months), the system 120 may classify the charging station 115a, 115b, 115c as a "regular" charging station. Classifying the charging station 115a, 115b, 115c as a "regular charging station" may indicate that the user frequently charges the vehicle 105a at the charging station 115a, 115b, 115c.

[0022] In an alternative aspect, when the frequency of use associated with the charging station 115a, 115b, 115c exceeds a second predefined threshold (e.g., more than 5 times) within a "recent" predefined duration (e.g., 1 month or less than 3 months), the system 120 can classify the charging station 115a, 115b, 115c as a regular charging station. In yet another aspect, the system 120 can give a greater weight to the "recent" frequency of use (e.g., frequency within the past 1 month or 2 months) than the "historical" frequency of use of the charging station 115a, 115b, 115c (e.g., frequency within the past 3 or more months) while classifying the charging station 115a, 115b, 115c as a regular charging station.

[0023] The system 120 may further classify a charging station (e.g., charging station 115a) as a "primary" charging station among charging stations 115a, 115b, 115c where the user can charge the vehicle 105a the most. The system 120 may also identify one or more charging stations (e.g., charging station 115d) as "nearby" charging stations that may be located near a conventional charging station, however, the user may rarely use the nearby charging station. For example, the associated frequency of use of the nearby charging station may be less than a third predefined threshold (e.g., less than 2 times) within a predefined duration (e.g., 3 months) or a recent predefined duration (e.g., 1 month). In another aspect, the system 120 may classify additional charging stations (e.g., 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 conventional charging station and / or the associated frequency of use of the long-distance / short-distance charging station.

[0024] In some aspects, the system 120 can classify the EV charging stations 115 based on the big data obtained from the vehicles 105a and by using one or more supervised or unsupervised machine learning algorithms operating based on a preset rule set. Examples of machine learning algorithms include, but are not limited to, algorithms associated with linear classifiers (logistic regression, naive Bayes classifier), nearest neighbors, support vector machines, decision trees, boosted trees, random forests, hidden Markov models, and / or neural networks. As the system 120 obtains more real-time charging data from the vehicles 105a, the classification of each EV charging station 115 can evolve over time. In combination Figure 2 A detailed process of classifying the EV charging station 115 is described.

[0025] The system 120 may aggregate the determined charging patterns of the plurality of vehicles 105 (e.g., the classification of the EV charging stations 115 for each vehicle 105a, 105b, 105c), and may transmit EV charging recommendations to the server 125 based on the aggregated charging patterns. Specifically, the system 120 may use the EV charging station classification to determine the EV charging recommendations that the system 120 may transmit to the server 125. In some aspects, the EV charging recommendations may include EV charging infrastructure related recommendations. For example, the system 120 may transmit to the server 125 (or an entity associated with the server 125) a recommendation for building new EV charging infrastructure in a geographic area where the count of conventional charging stations may be less than a first predefined count threshold. The system 120 may also transmit to the server 125 (or an entity associated with the server 125) a recommendation for building new EV charging infrastructure in a geographic area where the count of long-distance or short-distance charging stations may be less than a second predefined count threshold.

[0026] In other aspects, EV charging recommendations may include EV charging incentive-related recommendations. For example, system 120 may transmit to server 125 (or an entity associated with server 125) recommendations for providing incentives (e.g., discounts, coupons, etc.) for use of "nearby" charging stations and / or facilities (e.g., coffee shops, restaurants, etc.) located near nearby charging stations to incentivize vehicle users to use nearby charging stations.

[0027] Entities associated with server 125 may use recommendations provided by system 120 to increase the frequency of use of existing EV charging stations on road network 110 (e.g., by providing incentives), and / or identify optimal locations on road network 110 for constructing new EV charging infrastructure.

[0028] Figure 2 A block diagram of an exemplary electric vehicle (EV) charging recommendation system 200 (system 200) according to the present disclosure is depicted. Figure 2 When you can refer to Figure 3A and Figure 3B .

[0029] The system 200 may be the same as the system 120. As described herein, the system 200 may be implemented in hardware, software (e.g., firmware), or a combination thereof. The system 200 may be connected to a plurality of vehicles 202 (shown as a first vehicle 202a, a second vehicle 202b, a third vehicle 202c) and one or more servers 204 via a network 206. In some aspects, the system 200 may be part of the server 204. In other aspects, the system 200 may be part of an external server (not shown), which may not be part of the server 204. The vehicle 202 may be the same as the vehicle 105, the server 204 may be the same as the server 125, and the network 206 may be the same as the network 130.

[0030] The system 200 may include a number 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 and receive information to and from the vehicle 202 and the server 204 via the network 206.

[0031] Processor 210 may be an artificial intelligence (AI) based processor and may be configured to communicate with one or more memory devices (e.g., memory 212 and / or one or more external databases ( Figure 2200 operations according to the present disclosure. The processor 210 may utilize the memory 212 to store programs in code form and / or store data to perform various system 200 operations according to the present disclosure. The memory 212 may be a non-transitory computer-readable memory that stores EV charging recommendation program code. The memory 212 may include any one or combination of volatile memory elements (e.g., dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), etc.), and may include 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.).

[0032] The memory 212 may include multiple modules and databases, including but not limited to a vehicle information database 214, a charging event determination module 216, a geographic location cluster determination module 218, a charging event frequency determination module 220, and a classification module 222. The modules 216, 218, 220, 222 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 for performing the functions of the system 200 according to the present disclosure. Specifically, the modules 216, 218, 220, 222 may store computer executable instructions associated with one or more supervised or unsupervised machine learning algorithms, and the computer executable instructions may enable the processor 210 to perform the functions of the system 200. In combination Figure 1 Describe examples of machine learning algorithms.

[0033] In operation, the transceiver 208 may receive information associated with a charging alert or action from each vehicle 202a, 202b, 202c via the network 206. The information associated with the charging action may include, for example, a timestamp and a geographic location of one or more actions associated with the vehicle 202a, 202b, 202c. Examples of charging actions include, but are not limited to, a vehicle key-on action, a vehicle key-off action, an electric vehicle charger plug-in action, an electric vehicle charger unplug action, a charging start action, a charging stop action, and the like.

[0034] The transceiver 208 may receive information associated with a charging action from a vehicle (e.g., vehicle 202a) whenever a corresponding action may be performed on the vehicle 202a. For example, when a user starts charging the vehicle 202a via an EV charging station (e.g., charging station 115a), the transceiver 208 may receive a timestamp and a vehicle geographic location associated with the charging start action. Similarly, when a user stops charging the vehicle 202a via the charging station 115a, the transceiver 208 may receive a timestamp and a vehicle geographic location associated with the charging stop action.

[0035] In response to receiving information associated with a charging action from vehicle 202a, transceiver 208 may send the received information to vehicle information database 214 for storage purposes. Processor 210 may obtain information from vehicle information database 214 (or directly from transceiver 208), and may generate one or more "charging event" data structures or records based on the information obtained. The charging event record may indicate a single instance of vehicle charging performed on vehicle 202a, and processor 210 may generate a charging event record based on the information obtained and instructions stored in charging event determination module 216. Specifically, processor 210 may associate the timestamps and vehicle geographic locations of electric vehicle charger insertion actions, charging start actions, electric vehicle charger unplugging actions, and charging stop actions to create a single charging event record. For example, if the timestamp (and vehicle geographic location) associated with the electric vehicle charger insertion action is equal to the timestamp (and vehicle geographic location) associated with the charging start action, processor 210 may determine that the action may be associated with a single charging event. Similarly, if the timestamp (and vehicle geographic location) associated with the electric vehicle charger unplug action is equal to the timestamp (and vehicle geographic location) associated with the charging stop action, the processor 210 can determine that the actions can be associated with a single charging event. In addition, when the associated vehicle geographic locations of the charging start action and the charging stop action may be the same and the difference between the associated timestamps is less than a predefined charging time threshold (which can be equal to a standard EV battery charging duration), the processor 210 can determine that the two actions can be associated with a single charging event.

[0036] In some aspects, the processor 210 may use information associated with the charging action and may "stitch" the actions together (based on timestamps and / or vehicle geolocation) to determine one or more separate charging events associated with the vehicle 202a, as described above. In response to determining separate charging events, the processor may create a record of the charging event in the vehicle information database 214 and store it as a "charging event record" associated with the vehicle 202a. The charging event record may include the charging event duration (e.g., the duration between the charging start action and the charging stop action) and the charging event geolocation. The charging event geolocation may be determined using the vehicle geolocation obtained from the vehicle 202a, and may indicate the location of the EV charger that the user may have used to charge the vehicle 202a. It will be understood by those of ordinary skill in the art from the above description that the charging event geolocation is determined by the processor 210 based on the vehicle geolocation associated with the charging action obtained from the vehicle 202a.

[0037] In a similar manner as described above, processor 210 may create (and store) a charging event record for a plurality of charging events associated with vehicle 202a over a predefined duration. For example, processor 210 may create a charging event record for vehicle 202a over a duration of 1 month, 3 months, 6 months, 12 months, etc. Each charging event record may include an associated charging event geographic location, which may indicate the location of an EV charger that may have been used to charge vehicle 202a for the charging event.

[0038] In response to generating / creating a charging event record, the processor 210 may use instructions stored in the geographic location cluster determination module 218 and generate (or determine) multiple charging geographic location clusters based on the charging event geographic locations associated with multiple charging events. In some aspects, the processor 210 may generate multiple charging geographic location clusters based on the distance between the charging event geographic locations. Specifically, the processor 210 may cluster or "combine" charging event geographic locations that may be close to each other (e.g., the distance between the geographic locations is less than 250 meters) into a single charging geographic location cluster. For example, if a user uses two EV chargers that may be located at two separate edges of a parking lot (e.g., the right parking lot edge and the left parking lot edge that may be separated by a distance of 200 meters from each other) to charge the vehicle 202a, the processor 210 may "combine" the geographic locations of the two EV chargers into a single geographic location cluster.

[0039] In some aspects, to generate charging geolocation clusters, processor 210 may determine the distance between each charging event geolocation and may cluster together in a single cluster those charging event geolocations whose distances may be less than a predefined threshold (eg, 250 meters).

[0040] An example of a charging geolocation cluster is Figure 3A and Figure 3B shown in . Specifically, Figure 3A and Figure 3B A map of a geographic area 300 (e.g., a city, suburbs, etc.) is depicted. The geographic area 300 may include a plurality of charging geographic location clusters 305a-305f, which may represent a plurality of charging station locations where a user may have charged a vehicle 202a over a period of 1 month, 3 months, 6 months, 12 months, etc. Hereinafter, the charging geographic location clusters 305a-305f are referred to as charging station locations 305a-305f.

[0041] In response to determining the charging station locations 305a-305f, the processor 210 may determine the charging event occurrence frequency for each charging station location 305a-305f using instructions stored in the charging event frequency determination module 220. The charging event occurrence frequency may indicate a count of charging events associated with the vehicle 202a that may have occurred in a particular charging station location. For example, if the user charged the vehicle 202a eight times in the charging station location 305a in the past three months, the charging event occurrence frequency for the charging station location 305a may be eight times.

[0042] In some aspects, the processor 210 may determine the frequency of occurrence of charging events at the charging station location based on a linear count of charging events that may have occurred at the charging station location within a predefined duration (e.g., 1 month, 3 months, 6 months, 12 months, etc.). In other aspects, the processor 210 may determine the frequency of occurrence of charging events at the charging station location based on a weighted count of charging events that may have occurred at the charging station location within a predefined duration. In this case, the processor 210 may give a higher weight to recent charging event occurrences (e.g., may have occurred "recently" within the past month) than to historical charging event occurrences (e.g., may have occurred in the past month). For example, if the user charged the vehicle 202a at the charging station location 305a four times in the past month and charged twice before the past month, the processor 210 may determine that the frequency of occurrence of charging events at the charging station location 305a is five times (rather than six times). In this case, the processor 210 may assign a weight of "1" to the charging event occurrence within the past month and a weight of "0.5" to the charging event occurrence before the past month. In some aspects, the weights associated with the predefined durations may be pre-stored in the memory 212. It will be appreciated by those of ordinary skill in the art that the weights described herein are exemplary in nature and should not be construed to limit the scope of the present disclosure.

[0043] In some aspects, processor 210 may determine a count of charging events based on timestamps associated with charging actions obtained from vehicle 202a and / or types of charging actions. For example, processor 210 may identify a "pair" of charging start and stop actions (having the same geographic location and with associated timestamps having a difference greater than a predefined charging threshold) as a single charging event. As another example, two charging start actions with a difference between associated timestamps greater than a predefined timestamp threshold may be identified by processor 210 as two separate charging events.

[0044] In response to determining the charging event occurrence frequency of the charging station locations 305a to 305f, the processor 210 may send the determined charging event occurrence frequency to the memory 212 for storage purposes. In addition, the processor 210 may classify the charging station locations 305a to 305f into different categories based on the determined charging event occurrence frequency, as described below.

[0045] The processor 210 may use instructions stored in the classification module 222 and classify the charging station locations 305a-305f into a plurality of categories, including, but not limited to, “regular” charging station locations, “primary” charging station locations, “nearby” charging station locations, “short-distance” charging locations, “long-distance” charging locations, etc. In an exemplary aspect, a “regular” charging station location may have an associated charging event occurrence frequency greater than a predefined regular threshold (e.g., in the range of 4 to 8 instances in the past 1 or 2 months). In this case, the predefined regular threshold may be pre-stored in the memory 212, and the processor 210 may extract the predefined regular threshold from the memory 212 to classify the charging station locations 305a-305f.

[0046] In another aspect, the processor 210 may classify the charging station location with the greatest frequency of charging events among the "regular" charging station locations as a "primary" charging station location. The "primary" charging station location may indicate the charging station location where the user may have charged the vehicle 202a the most times in history. Figure 3A and Figure 3B , a "primary" charging station location is depicted as charging station location 305a, while "regular" charging station locations are depicted as charging station locations 305b and 305c.

[0047] In response to classifying one or more charging station locations as “primary” charging station locations and “regular” charging station locations, processor 210 may define a virtual polygon 310 (or polygon vector) connecting the primary charging station locations with the regular charging station locations on a map of geographic area 300, such as Figure 3A For example, Figure 3A As shown in , the processor 210 can 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 can represent a "daily driving area" associated with the user of the vehicle 202a. In other words, the area within the first virtual triangle 310 can represent an area where the user of the vehicle 202a can frequently or most frequently drive the vehicle 202a (and therefore charge the vehicle). Defining the first virtual triangle 310 can enable the processor 210 to classify the charging station locations into "nearby", "short distance", and "long distance" charging station locations, which in turn can enable the processor 210 to provide EV charging recommendations to the server 204, as described below.

[0048] 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 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 exemplary aspect, the "nearby" charging station locations may represent charging station locations that may be within a daily driving area associated with the user of the vehicle 202a, however, the vehicle may rarely use the "nearby" charging station locations to charge the vehicle 202a.

[0049] In addition, 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 side of the first virtual triangle 310 and define a second virtual triangle 315 (or a second virtual polygon), such as Figure 3A In an exemplary aspect, the predefined virtual distance buffer may vary based on the area of ​​the first virtual triangle 310, such that the area of ​​the second virtual triangle 315 may be in the range of 1.5 times to 5 times the area of ​​the first virtual triangle 310. In some aspects, the processor 210 may calculate the predefined virtual distance buffer based on the area of ​​the first virtual triangle 310 and a preset ratio of the area of ​​the second virtual triangle 315 to the area of ​​the first virtual triangle 310 (which may be pre-stored in the memory 212).

[0050] In an exemplary 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 represent a "short-distance driving area" associated with the user of the vehicle 202a. The processor 210 may classify the charging station location located in the short-distance driving area as a short-distance charging station location. For example, the processor 210 may classify the charging station location 305f as a short-distance charging station location. In addition, the processor 210 may classify the charging station location located outside the second virtual triangle 315 as a long-distance charging station location. For example, the processor 210 may classify the charging station location 305g as a long-distance charging station location. The short-distance charging station location may indicate the charging station location where the user can charge the vehicle 202a when the user uses the vehicle 202a for a short trip (starting from the daily driving area). Similarly, the long-distance charging station location may indicate the charging station location where the user can charge the vehicle 202a when the user uses the vehicle 202a for a long trip (starting from the daily driving area).

[0051] In a similar manner, the processor 210 may define a first virtual polygon and a second virtual polygon and classify the charging station locations of a plurality of vehicles (e.g., vehicles 202a, 202b, 202c) within a predefined duration into different categories. The processor 210 may also transmit EV charging recommendations to the server 204 based on the defined first virtual polygon and the second virtual polygon. Specifically, the processor 210 may determine a daily driving area (e.g., the first virtual polygon 310) and a short-distance driving area (e.g., the second virtual polygon 315) for each of the plurality of vehicles, and may transmit EV charging recommendations to the server 204 based on the main charging station locations, regular charging station locations, nearby charging station locations, short-distance charging station locations, and long-distance charging station locations associated with the plurality of vehicles.

[0052] For example, if a charging station (e.g., charging station location 305d) is classified as a "nearby" charging station location for multiple vehicles, processor 210 may determine that although charging station location 305d may be within the daily driving area associated with the user of the multiple vehicles, the user may not frequently use charging station location 305d to charge their vehicles. In this case, processor 210 may transmit to server 204 (and therefore to an entity associated with server 204) a recommendation for providing an incentive to the user to use charging station location 305d. The incentive may be, for example, a discount coupon, a subscription, a coupon for a facility (e.g., a coffee shop, a restaurant, etc.) located near charging station location 305d, etc.

[0053] As another example, if a charging station (e.g., charging station location 305g) can be used by multiple vehicles to charge the vehicles over long distances, processor 210 can transmit to server 204 (and therefore to server 204) a recommendation to construct new EV charging infrastructure at a predefined distance from charging station location 305g to maximize the probability of use of the new EV charging infrastructure.

[0054] In additional aspects, processor 210 may transmit EV charging recommendations to server 204 based on the charging station location and the duration that users typically spend charging their vehicles at the charging station location. For example, if users typically spend more duration charging their vehicles at charging station location 305c than at charging station location 305b, processor 210 may transmit a recommendation to server 204 indicating that new EV charging infrastructure may be built near charging station location 305c (thereby alleviating the load at charging station location 305c). As another example, processor 210 may transmit a recommendation to server 204 indicating that coupons may be provided to users for facilities (e.g., coffee shops, restaurants, etc.) located near charging station location 305c.

[0055] Although the above description describes the aspect that the processor 210 defines virtual triangles (e.g., first virtual triangle 310 and second virtual triangle 315) to classify the charging station location, the present disclosure is not limited to the polygon being a triangle. In addition, the present disclosure is not limited to the processor 210 defining a polygon to classify the charging station location. Figure 3B Another aspect of the present disclosure is depicted in which the processor 210 defines circles (shown as first circle 320a, second circle 320b, and third circle 320c) with predefined radii (which may be pre-stored in the memory 212) around a "primary" charging station location and a "regular" charging station location. Charging station locations that may be located within the defined circles (e.g., charging station location 305d) may be classified as "nearby" charging station locations, while charging station locations that may be located outside of the defined circles (e.g., charging station location 305g) may be classified as "travel" charging station locations. In this aspect, the processor 210 does not classify charging station locations as short-distance or long-distance charging station locations.

[0056] Figure 4 A flow chart of an exemplary EV charging recommendation method 400 according to the present disclosure is depicted. Figure 1 , Figure 2 , Figure 3A and Figure 3B The previous figures are used to describe Figure 4 The following process is exemplary and is not limited to the steps described below. Furthermore, alternative embodiments may include more or fewer steps shown or described herein, and may include the steps in an order different from that described in the example embodiments below.

[0057] Method 400 begins at step 402. At step 404, method 400 may include obtaining, by processor 210, information associated with a plurality of charging events for vehicle 202a. As described above, processor 210 may obtain information associated with charging alerts or actions associated with vehicle 202a, and may "stitch" the actions together to identify one or more individual charging events associated with vehicle 202a. The information associated with the charging events may include charging event durations and charging event geographic locations, as described above.

[0058] At step 406, the method 400 may include generating, by the processor 210, a plurality of charging geographic location clusters 305a to 305f based on the charging event geographic locations. At step 408, the method 400 may include determining, by the processor 210, a charging event occurrence frequency for each charging geographic location cluster 305a to 305f. As described above, the processor 210 may determine the charging event occurrence frequency based on a linear or weighted count of charging events that may have occurred at each charging geographic location cluster 305a to 305f within a predefined duration.

[0059] At step 410, method 400 may include processor 210 classifying a first charging geographic location cluster (e.g., charging station location 305a) as a "primary" charging station location based on the frequency of charging events, and classifying multiple second charging geographic location clusters (e.g., charging station locations 305b and 305c) as "regular" charging station locations, as described above.

[0060] 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 with the conventional charging station location. At step 414, the method 400 may include transmitting, by the processor 210, an electric vehicle charging recommendation to the server 204 based on the defined virtual polygon. As described above, the electric vehicle charging recommendation may be associated with a charging station infrastructure creation recommendation and / or a vehicle user incentive recommendation.

[0061] At step 416 , method 400 may end.

[0062] In some aspects, the method 400 may include an additional step of defining another virtual polygon (eg, the second virtual polygon 315) by adding a predefined virtual distance buffer to each first virtual triangle 310 edge. Figure 4 The processor 210 may classify the charging station location as a short distance charging station location or a long distance charging station location based on the second virtual polygon 315, such as in combination with Figure 2 When the charging station locations are located within the first virtual triangle 310, the processor 210 may also classify one or more charging station locations as nearby charging station locations.

[0063] In the above disclosure, reference has been made to the accompanying drawings that form a part of the above disclosure, which illustrate specific embodiments in which the present disclosure can be practiced. It should be understood that other embodiments may be utilized and structural changes may be made without departing from the scope of the present disclosure. References in this specification to "one embodiment," "embodiment," "example embodiment," etc. indicate that the described embodiment may include specific features, structures, or characteristics, but each embodiment may not necessarily include the specific features, structures, or characteristics. In addition, such phrases do not necessarily refer to the same embodiment. In addition, when features, structures, or characteristics are described in conjunction with an embodiment, whether or not explicitly described, those skilled in the art will recognize such features, structures, or characteristics in conjunction with other embodiments.

[0064] In addition, where appropriate, the functions described herein may be performed in one or more of the following: hardware, software, firmware, digital components, or analog components. For example, one or more application specific integrated circuits (ASICs) may be programmed to perform one or more of the systems and programs described herein. Certain terms are used throughout the specification and claims to refer to specific system components. As will be appreciated by those skilled in the art, components may be referred to by different names. This document is not intended to distinguish between components that have different names but the same function.

[0065] It should also be understood that the word "example" as used herein is intended to be non-exclusive and non-limiting in nature. More specifically, the word "example" used herein indicates one of several examples, and it should be understood that no undue emphasis or preference is placed on the specific example described.

[0066] Computer-readable media (also referred to as processor-readable media) include any non-transitory (e.g., tangible) media that participate in providing data (e.g., instructions) that can be read by a computer (e.g., by a processor of a computer). Such media can take many forms, including but not limited to non-volatile media and volatile media. A computing device may include computer-executable instructions, where the instructions are executable by one or more computing devices (such as those listed above) and stored on a computer-readable medium.

[0067] With respect to the processes, systems, methods, heuristics, etc. described herein, it should be understood that although the steps of such processes, etc. have been described as occurring according to a certain ordered sequence, such processes may be practiced by performing the described steps in an order different from the order described herein. It should also be understood that certain steps may be performed simultaneously, other steps may be added, or certain steps described herein may be omitted. In other words, the descriptions of processes herein are provided for the purpose of illustrating various embodiments and should in no way be construed as limiting the claims.

[0068] Therefore, it should be understood that the above description is intended to be illustrative rather than restrictive. Upon reading the above description, many embodiments and applications other than the examples provided will be apparent. The scope should not be determined with reference to the above description, but should be determined with reference to the entire scope of the appended claims and equivalents to which such claims are entitled. It is anticipated and expected that the technology discussed herein will develop in the future, and the disclosed systems and methods will be incorporated into such future embodiments. In short, it should be understood that the present application is capable of modification and change.

[0069] Unless explicitly indicated to the contrary in this article, all terms used in the claims are intended to be given their ordinary meanings as understood by the skilled person described herein. Specifically, unless the claims state an explicit limitation to the contrary, the use of singular articles such as "one", "the", "said" and the like should be interpreted as describing one or more of the indicated elements. Unless otherwise specifically stated or understood in other ways within the context when used, conditional language such as, in particular, "can", "may", "can" or "may" is generally intended to express that certain embodiments may include certain features, elements and / or steps, while other embodiments may not include certain features, elements and / or steps. Therefore, such conditional language is generally not intended to imply that one or more embodiments require each feature, element and / or step in any way.

[0070] According to one embodiment, the processor classifies the main charging station location by: identifying a first regular charging station location from the regular charging station locations, wherein the first regular charging station location has a maximum charging event frequency among the regular charging event occurrence frequencies; and classifying the first regular charging station location as the main charging station location.

[0071] According to one embodiment, the processor is further configured to classify one or more third charging geographic location clusters of the plurality of charging geographic location clusters located within the virtual polygon as nearby charging station locations.

[0072] According to one embodiment, the processor is also configured to: classify one or more fourth charging geographic location clusters among the multiple charging geographic location clusters that are located at a distance less than a predefined virtual distance from the edge of the virtual polygon as short-distance charging station locations; and classify one or more fifth charging geographic location clusters among the multiple charging geographic location clusters that are located at a distance greater than the predefined virtual distance from the edge of the virtual polygon as long-distance charging station locations, wherein the processor determines the electric vehicle charging recommendation based on the short-distance charging station locations and the long-distance charging station locations.

[0073] According to one embodiment, the electric vehicle charging recommendation includes at least one of a charging station infrastructure creation recommendation and a charging station incentive recommendation.

[0074] According to the present invention, a non-transitory computer-readable storage medium is provided, on which instructions are stored, which, when executed by a processor, cause the processor to: obtain information associated with multiple charging events of a vehicle, wherein the information includes multiple vehicle geographic locations associated with the multiple charging events; generate multiple charging geographic location clusters from the multiple vehicle geographic locations; determine the frequency of occurrence of charging events for each charging geographic location cluster based on the information; classify a first charging geographic location cluster among the multiple charging geographic location clusters as a primary charging station location based on the frequency of occurrence of the charging events, and classify multiple second charging geographic location clusters among the multiple charging geographic location clusters as regular charging station locations; define a virtual polygon connecting the primary charging station location with the regular charging station location; and transmit 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 events for a vehicle, wherein the information includes a plurality of geographic locations of the vehicle associated with the plurality of charging events; generating, by the processor, a plurality of charging geographic location clusters from the plurality of vehicle geographic locations; determining, by the processor, a frequency of occurrence of charging events for each charging geographic location cluster based on the information; classifying, by the processor, a first charging geographic location cluster of the plurality of charging geographic location clusters as primary charging station locations, and classifying a plurality of second charging geographic location clusters of the plurality of charging geographic location clusters as regular charging station locations based on the charging event occurrence frequency; defining, by the processor, a virtual polygon connecting the primary charging station location with the conventional charging station location; as well as The electric vehicle charging recommendation is transmitted, by the processor, to a server based on the virtual polygon. 2 . The method of claim 1 , wherein the regular charging station location has a regular charging event occurrence frequency greater than a predefined threshold.

3. The method of claim 2, wherein classifying the primary charging station location comprises: identifying a first regular charging station location from the regular charging station locations, wherein the first regular charging station location has a maximum charging event frequency among the regular charging event occurrence frequencies; as well as The first conventional charging station is classified as the primary charging station location. The method of claim 1 , wherein the information includes a timestamp for each charging event.

5. The method of claim 4, further comprising: assigning a weight to each charging event based on the timestamp; as well as The charging event occurrence frequency is determined based on the weight. 6 . The method of claim 1 , wherein generating the plurality of charging geographic location clusters comprises generating the plurality of charging geographic location clusters based on distances of the plurality of vehicle geographic locations from one another. 7 . The method of claim 1 , wherein the plurality of charging events comprises at least one of the following: a vehicle key-on event, a vehicle key-off event, a vehicle charging start event, and a vehicle charging end event. 8 . The method of claim 7 , wherein the information further includes a duration between the vehicle charging start event and the vehicle charging end event. 9 . The method of claim 8 , further comprising determining the electric vehicle charging recommendation based on the duration.

10. The method of claim 1, wherein the electric vehicle charging recommendation comprises at least one of a charging station infrastructure creation recommendation and a charging station incentive recommendation. 11 . The method of claim 1 , further comprising classifying one or more third charging geographic location clusters of the plurality of charging geographic location clusters that are within the virtual polygon as nearby charging station locations.

12. The method of claim 11, further comprising: classifying one or more fourth charging geographic location clusters of the plurality of charging geographic location clusters located at less than a predefined virtual distance from an edge of the virtual polygon as short-distance charging station locations; as well as One or more fifth charging geographic location clusters of the plurality of charging geographic location clusters located more than the predefined virtual distance from the virtual polygon edge are classified as long-distance charging station locations.

13. The method of claim 12, further comprising determining the electric vehicle charging recommendation based on the short-distance charging station locations and the long-distance charging station locations.

14. A system for providing electric vehicle charging recommendations, the system comprising: a transceiver configured to receive information associated with a plurality of charging events for a vehicle, wherein the information includes a plurality of geographic locations of the vehicle associated with the plurality of charging events; 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 geographic location clusters from the plurality of vehicle geographic locations; determining a frequency of occurrence of charging events for each charging geographic location cluster based on the information; classifying a first charging geographic location cluster among the plurality of charging geographic location clusters as primary charging station locations based on the charging event occurrence frequency, and classifying a plurality of second charging geographic location clusters among the plurality of charging geographic location clusters as regular charging station locations; defining a virtual polygon connecting the primary charging station location with the conventional charging station location; as well as The electric vehicle charging recommendation is transmitted to a server based on the virtual polygon.

15. The system of claim 14, wherein the regular charging station location has a regular charging event occurrence frequency greater than a predefined threshold.

Images