WO2023087108A1 - Systems, methods, and devices for determining optimal electric car charging stations - Google Patents

Systems, methods, and devices for determining optimal electric car charging stations Download PDF

Info

Publication number
WO2023087108A1
WO2023087108A1 PCT/CA2022/051699 CA2022051699W WO2023087108A1 WO 2023087108 A1 WO2023087108 A1 WO 2023087108A1 CA 2022051699 W CA2022051699 W CA 2022051699W WO 2023087108 A1 WO2023087108 A1 WO 2023087108A1
Authority
WO
WIPO (PCT)
Prior art keywords
charging station
computer
charging
factor
weighted mean
Prior art date
Application number
PCT/CA2022/051699
Other languages
French (fr)
Inventor
JR. Jerry GUNTER
Andrew Ryu
Maxime MARTINEAU
Hezekiah BACOVCIN
Original Assignee
Datametrex Electric Vehicle Solutions Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Datametrex Electric Vehicle Solutions Inc. filed Critical Datametrex Electric Vehicle Solutions Inc.
Publication of WO2023087108A1 publication Critical patent/WO2023087108A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
    • B60K35/00—Arrangement of adaptations of instruments
    • B60K35/28—
    • B60K35/65—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q50/40—
    • B60K2360/169—
    • B60K2360/731—

Definitions

  • the specification generally relates to computer systems for electric car charging and, in particular, to artificial intelligence systems relating to electric car charging stations.
  • a computer-implemented method for determining at least one recommendation for a vehicle charging station including: assigning a numerical representation on the same numerical scale to at least one charging station factor for each charging station; generating a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; generating a weighted mean for each charging station based on each weight of the charging station; generating a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and communicating the at least one recommendation at an output device based on the weighted mean ranking.
  • each charging station factor comprises distance to charging station, charging rate, charging cost, quality of destination, or proximity to amenities.
  • each charging station factor is selected based on user input. [0006] In some embodiments, each charging station factor is selected based on at least one automatically determined factor.
  • each automatically determined factor comprises present vehicle power or distance to destination.
  • the output device is a computer display.
  • the output device is a speaker.
  • the at least one recommendation comprises an optimal ranked list of charging stations.
  • the at least one recommendation comprises an alternative ranked list of charging stations.
  • the at least one recommendation comprises a charging station having a highest weighted mean.
  • a computer-implemented system for determining at least one recommendation for a vehicle charging station including: an input processor 110 configured to assign a numerical representation on the same numerical scale to at least one charging station factor for each charging station; an artificial intelligence unit 120 configured to generate a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; the artificial intelligence unit 120 further configured to generate a weighted mean for each charging station based on each weight of the charging station; the artificial intelligence unit 120 further configured to generate a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and a recommendation unit 130 configured to communicate the at least one recommendation at an output device based on the weighted mean ranking.
  • each charging station factor comprises distance to charging station, charging rate, charging cost, quality of destination, or proximity to amenities.
  • each charging station factor is selected based on user input.
  • each charging station factor is selected based on at least one automatically determined factor.
  • each automatically determined factor comprises present vehicle power or distance to destination.
  • the output device is a computer display.
  • the at least one recommendation comprises an optimal ranked list of charging stations.
  • the at least one recommendation includes an alternative ranked list of charging stations.
  • the at least one recommendation includes a charging station having a highest weighted mean.
  • a non-transitory computer-readable medium storing a set of machine-interpretable instructions, which, when executed, cause a processor to perform a method for determining at least one recommendation for a vehicle charging station, the method including: assigning a numerical representation on the same numerical scale to at least one charging station factor for each charging station; generating a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; generating a weighted mean for each charging station based on each weight of the charging station; generating a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and communicating the at least one recommendation at an output device based on the weighted mean ranking.
  • a computer-implemented system and method for determining optimal electric car charging station locations includes retrieving a list of available charging stations, indexing the list of available stations, sorting the results based on user location or criteria selected by the user by Artificial Intelligence converting the unsorted list of stations into a ranked list, and displaying the results to the user in ranked list format.
  • the ranking criteria options include time, charging cost, length of travel involved, charging speed, destination, if known, additional provided amenities at the charging station, and entertainment located nearby the charging station.
  • the method further comprises advising the user on the best course of action based on the available data.
  • FIG. 1 is a schematic diagram of a computer program for determining a ranked list, according to some embodiments.
  • FIG. 2 is a schematic diagram of a charging recommendation system, according to some embodiments.
  • the unsorted list of available charging stations can be sorted into a ranked list to allow a user to know the location of close charging stations.
  • a person can select criteria to weigh the results of the sorted list including cost, distance travelled, or charge time.
  • the ability to view a ranked list helps a person in planning an optimal route with nearby charging stations.
  • an application is configured to match a driver of an electric vehicle or hybrid vehicle with the optimal charging solution for their vehicle, such as while the user is driving, either locally or on a longer trip.
  • the application is configured to base the matching and/or selection based on a combination of predictive analytics and artificial intelligence.
  • the application includes functionality for obtaining a ranked list of available charging stations for electric and hybrid vehicles.
  • the application is configured to display the results based on available data criteria including time, charging cost, charging rate/speed, destination, additional provided amenities, entertainment options nearby, and extra travel required to arrive at the charging station.
  • a charging recommendation system 100 includes a processor configured to execute instructions in non-transitory memory to configure a storage device, including an input processor 110, an artificial intelligence unit 120, and a recommendation unit 130.
  • Input processor 110 is configured to determine a list of charging stations by first converting factors (assigning a numerical representation), such as the 1) charging rate/speed, 2) charging cost, 3) quality of destination (e.g., crime rate), 4) available amenities, 5) nearby entertainment options, and/or 6) other criteria into numerical representations on the same scale.
  • factors such as the 1) charging rate/speed, 2) charging cost, 3) quality of destination (e.g., crime rate), 4) available amenities, 5) nearby entertainment options, and/or 6) other criteria into numerical representations on the same scale.
  • a charging rate that is equal to the average charging rate globally is assigned a value of five, while the fastest rate would be assigned a value of ten.
  • artificial intelligence unit 120 is configured to use Weighted Mean Ranking to rank each charging station.
  • the weights for the Weighted Mean Ranking are generated by artificial intelligence unit 120 from a combination of user preferences (e.g., would prefer faster charging even if more expensive) and artificial intelligence determined situational weights (e.g., make short distance a priority if the car is about to run completely out of charge).
  • a weighted mean ranking is generated for each charging station (or each selected charging stations) and a recommendation is generated based on the weighted mean rankings by ranking the weighted mean rankings. For example, a charging station having a higher scoring weighted mean can be ranked higher and be assigned a higher weighted mean ranking relative to other charging stations.
  • User preference data is received by the charging system at input processor 110, such as via an interactive display unit and interface (e.g., computer or mobile screen, mouse, microphone, etc.). For example, a weight for a factor is increased by artificial intelligence unit 120 relative to another factor where user preference data defines that the user prioritizes that factor over the other factor. Conversely, a weight for a factor is decreased by artificial intelligence unit 120 relative to another factor where user preference data defines that the user places a lower priority to that factor over the other factor, according to some embodiments. Similarly, a weight for a factor is increased by artificial intelligence unit 120 relative to another factor where determined situational weights defines that factor should have a greater priority relative to the other factor, according to some embodiments. In some embodiments, artificial intelligence unit 120 is configured to generate determined situational weights based on machine learning. Determined situational weights can be adjusted over time by artificial intelligence unit 120 to improve the accuracy of the priority assigned to different factors, for example.
  • an interactive display unit and interface e.g., computer or mobile screen, mouse, microphone, etc
  • Recommendation unit 130 is configured to communicate at least one recommendation at an output device based on the weighted mean ranking.
  • recommendation unit 130 is configured to generate an audio output and/or a user interface component at a display device, representing advice to the user of a course of action that is optimal or recommended based on the data available.
  • Recommendation unit 130 is further configured to generate output advising the user of viable alternatives, if they exist, and allow the user to decide whether to accept or reject the recommended course of action.
  • This user feedback can be received by artificial intelligence unit 120 and used to adjust the artificial intelligence determined situational weights and improve future accuracy of such weights, according to some embodiments.
  • a user may also request advice from the charging recommendation system 100 via providing user input at input processor 110 in response to which the charging recommendation system 100 is configured to display viable options based on any user selected criteria, including options based solely on time or distance and charging speed, according to some embodiments.
  • An example of this recommendation functionality is when a user is driving and in risk of running out of power, the application will advise them to stop at a charging station close to their location (e.g., at a house one kilometre away). In the alternative, if the application determines the user will be able to make it to their home before running out of power, the application will advise the user to recharge upon arriving home.
  • the application When a user is on a long trip and requests charging advice from the application, the application will advise the user on the most optimal charging location on the user’s current route, which may or may not be the closest or cheapest available option.
  • the recommendation can be based on a variety of factors including one or more of the foregoing.
  • the user can alter the selection criteria by selecting preference(s) for one or more of a variety of factors such as cost, distance travelled, charging time, etc.
  • the user can select a destination and plan the trip according to the best charging options available.
  • a car includes any vehicle.
  • the user can request that the application provide a recommendation as to the most viable charging option based on a combination of factors selected.
  • the application can be instructed to provide the best charging station based solely on the time and charging speed criteria.
  • the application further includes functionality to accept user input to alter how the charging stations are ranked. This includes accepting input from a user to provide results based only on time and charging speed criteria. Without user input, the application will determine the optimum location for a user to charge their vehicle without human intervention.
  • the application includes functionality to display information for commercially and privately controlled car charging stations.
  • Commercially operated charging stations will be monitored by the application to obtain information on their availability, charging rates, and costs.
  • Individuals in control of privately owned charging stations will be able to sign up as a provider for electric car charging services, setting their own availability, charging rates, costs, and any other conditions they see fit for use of their station.
  • These charging stations can be included in a set of those that can be selected by the application based on the method described herein.
  • charging recommendation system 100 is implemented as a computer application or accessible via a web browser.
  • the computer application can be accessible via a computer, such as a desktop computer or a mobile computing device, for example.
  • charging recommendation system 100 is configured for communication over a network, such as the Internet, and can receive and transmit data to and from a remote server, such as for updates and/or receiving or requesting other data.
  • Various units or components of charging recommendation system 100 can be implemented in a distributed system.
  • a processor as referred to herein can include more than one processor.

Abstract

Embodiments described herein provide a computer-implemented method and system for determining at least one recommendation for a vehicle charging station, including: assigning a numerical representation on the same numerical scale to at least one charging station factor for each charging station; generating a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; generating a weighted mean for each charging station based on each weight of the charging station; generating a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and communicating the at least one recommendation at an output device based on the weighted mean ranking.

Description

SYSTEMS, METHODS, AND DEVICES FOR DETERMINING OPTIMAL ELECTRIC CAR CHARGING STATIONS
FIELD
[0001] The specification generally relates to computer systems for electric car charging and, in particular, to artificial intelligence systems relating to electric car charging stations.
BACKGROUND
[0002] Driving an electric or hybrid car is beneficial to the environment, but they require access to charging stations when away from your home charging unit. When planning a long trip, a person may not be aware of convenient charging stations on their desired route. This may mean that a person will have to travel out of their way to have access to a charging station, risking depleting their battery before arriving at a charging station.
SUMMARY
[0003] In accordance with an aspect, there is provided a computer-implemented method for determining at least one recommendation for a vehicle charging station, the method including: assigning a numerical representation on the same numerical scale to at least one charging station factor for each charging station; generating a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; generating a weighted mean for each charging station based on each weight of the charging station; generating a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and communicating the at least one recommendation at an output device based on the weighted mean ranking.
[0004] In some embodiments, each charging station factor comprises distance to charging station, charging rate, charging cost, quality of destination, or proximity to amenities.
[0005] In some embodiments, each charging station factor is selected based on user input. [0006] In some embodiments, each charging station factor is selected based on at least one automatically determined factor.
[0007] In some embodiments, each automatically determined factor comprises present vehicle power or distance to destination.
[0008] In some embodiments, the output device is a computer display.
[0009] In some embodiments, the output device is a speaker.
[0010] In some embodiments, the at least one recommendation comprises an optimal ranked list of charging stations.
[0011] In some embodiments, the at least one recommendation comprises an alternative ranked list of charging stations.
[0012] In some embodiments, the at least one recommendation comprises a charging station having a highest weighted mean.
[0013] In accordance with an aspect, there is provided a computer-implemented system for determining at least one recommendation for a vehicle charging station, the system including: an input processor 110 configured to assign a numerical representation on the same numerical scale to at least one charging station factor for each charging station; an artificial intelligence unit 120 configured to generate a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; the artificial intelligence unit 120 further configured to generate a weighted mean for each charging station based on each weight of the charging station; the artificial intelligence unit 120 further configured to generate a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and a recommendation unit 130 configured to communicate the at least one recommendation at an output device based on the weighted mean ranking. [0014] In some embodiments, each charging station factor comprises distance to charging station, charging rate, charging cost, quality of destination, or proximity to amenities.
[0015] In some embodiments, each charging station factor is selected based on user input.
[0016] In some embodiments, each charging station factor is selected based on at least one automatically determined factor.
[0017] In some embodiments, each automatically determined factor comprises present vehicle power or distance to destination.
[0018] In some embodiments, the output device is a computer display.
[0019] In some embodiments, the at least one recommendation comprises an optimal ranked list of charging stations.
[0020] In some embodiments, the at least one recommendation includes an alternative ranked list of charging stations.
[0021] In some embodiments, the at least one recommendation includes a charging station having a highest weighted mean.
[0022] In accordance with an aspect, there is provided a non-transitory computer-readable medium storing a set of machine-interpretable instructions, which, when executed, cause a processor to perform a method for determining at least one recommendation for a vehicle charging station, the method including: assigning a numerical representation on the same numerical scale to at least one charging station factor for each charging station; generating a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; generating a weighted mean for each charging station based on each weight of the charging station; generating a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and communicating the at least one recommendation at an output device based on the weighted mean ranking. [0023] In some embodiments, there is provided a computer-implemented system and method for determining optimal electric car charging station locations. The method includes retrieving a list of available charging stations, indexing the list of available stations, sorting the results based on user location or criteria selected by the user by Artificial Intelligence converting the unsorted list of stations into a ranked list, and displaying the results to the user in ranked list format. The ranking criteria options include time, charging cost, length of travel involved, charging speed, destination, if known, additional provided amenities at the charging station, and entertainment located nearby the charging station. The method further comprises advising the user on the best course of action based on the available data.
[0024] Other aspects and features and combinations thereof concerning embodiments described herein will become apparent to those ordinarily skilled in the art upon review of the instant disclosure of embodiments in conjunction with the accompanying figures.
BRIEF DESCRIPTION OF THE DRAWINGS
[0001] The principles may better be understood with reference to the accompanying figures provided by way of illustration of an exemplary embodiment, or embodiments, and in which:
[0002] FIG. 1 is a schematic diagram of a computer program for determining a ranked list, according to some embodiments; and
[0003] FIG. 2 is a schematic diagram of a charging recommendation system, according to some embodiments.
DETAILED DESCRIPTION
[0025] The description that follows, and the embodiments described therein, are provided by way of illustration of an example, or examples, of particular embodiments. These examples are provided for the purposes of explanation, and not of limitation, of those principles. [0026] Technology passively displays to a person currently available charging stations close to their current location and provides information about each option. A user is required to manually sort through potentially hundreds of results to find the best charging station location to meet their needs.
[0027] By having an application that utilizes artificial intelligence, the unsorted list of available charging stations can be sorted into a ranked list to allow a user to know the location of close charging stations. A person can select criteria to weigh the results of the sorted list including cost, distance travelled, or charge time. The ability to view a ranked list helps a person in planning an optimal route with nearby charging stations.
[0028] According to an embodiment, an application is configured to match a driver of an electric vehicle or hybrid vehicle with the optimal charging solution for their vehicle, such as while the user is driving, either locally or on a longer trip. The application is configured to base the matching and/or selection based on a combination of predictive analytics and artificial intelligence.
[0029] According to an embodiment, the application includes functionality for obtaining a ranked list of available charging stations for electric and hybrid vehicles. The application is configured to display the results based on available data criteria including time, charging cost, charging rate/speed, destination, additional provided amenities, entertainment options nearby, and extra travel required to arrive at the charging station. For example, in some embodiments, a charging recommendation system 100 includes a processor configured to execute instructions in non-transitory memory to configure a storage device, including an input processor 110, an artificial intelligence unit 120, and a recommendation unit 130.
[0030] Input processor 110 is configured to determine a list of charging stations by first converting factors (assigning a numerical representation), such as the 1) charging rate/speed, 2) charging cost, 3) quality of destination (e.g., crime rate), 4) available amenities, 5) nearby entertainment options, and/or 6) other criteria into numerical representations on the same scale. In an example embodiment, a charging rate that is equal to the average charging rate globally is assigned a value of five, while the fastest rate would be assigned a value of ten. After converting each type of information into a similarly scaled numerical value, artificial intelligence unit 120 is configured to use Weighted Mean Ranking to rank each charging station. The weights for the Weighted Mean Ranking are generated by artificial intelligence unit 120 from a combination of user preferences (e.g., would prefer faster charging even if more expensive) and artificial intelligence determined situational weights (e.g., make short distance a priority if the car is about to run completely out of charge). In some embodiments, a weighted mean ranking is generated for each charging station (or each selected charging stations) and a recommendation is generated based on the weighted mean rankings by ranking the weighted mean rankings. For example, a charging station having a higher scoring weighted mean can be ranked higher and be assigned a higher weighted mean ranking relative to other charging stations.
[0031] User preference data is received by the charging system at input processor 110, such as via an interactive display unit and interface (e.g., computer or mobile screen, mouse, microphone, etc.). For example, a weight for a factor is increased by artificial intelligence unit 120 relative to another factor where user preference data defines that the user prioritizes that factor over the other factor. Conversely, a weight for a factor is decreased by artificial intelligence unit 120 relative to another factor where user preference data defines that the user places a lower priority to that factor over the other factor, according to some embodiments. Similarly, a weight for a factor is increased by artificial intelligence unit 120 relative to another factor where determined situational weights defines that factor should have a greater priority relative to the other factor, according to some embodiments. In some embodiments, artificial intelligence unit 120 is configured to generate determined situational weights based on machine learning. Determined situational weights can be adjusted over time by artificial intelligence unit 120 to improve the accuracy of the priority assigned to different factors, for example.
[0032] Recommendation unit 130 is configured to communicate at least one recommendation at an output device based on the weighted mean ranking. For example, in some embodiments, recommendation unit 130 is configured to generate an audio output and/or a user interface component at a display device, representing advice to the user of a course of action that is optimal or recommended based on the data available. Recommendation unit 130 is further configured to generate output advising the user of viable alternatives, if they exist, and allow the user to decide whether to accept or reject the recommended course of action. This user feedback can be received by artificial intelligence unit 120 and used to adjust the artificial intelligence determined situational weights and improve future accuracy of such weights, according to some embodiments. A user may also request advice from the charging recommendation system 100 via providing user input at input processor 110 in response to which the charging recommendation system 100 is configured to display viable options based on any user selected criteria, including options based solely on time or distance and charging speed, according to some embodiments. An example of this recommendation functionality is when a user is driving and in risk of running out of power, the application will advise them to stop at a charging station close to their location (e.g., at a house one kilometre away). In the alternative, if the application determines the user will be able to make it to their home before running out of power, the application will advise the user to recharge upon arriving home. When a user is on a long trip and requests charging advice from the application, the application will advise the user on the most optimal charging location on the user’s current route, which may or may not be the closest or cheapest available option. The recommendation can be based on a variety of factors including one or more of the foregoing. The user can alter the selection criteria by selecting preference(s) for one or more of a variety of factors such as cost, distance travelled, charging time, etc. The user can select a destination and plan the trip according to the best charging options available.
[0033] As used herein, a car includes any vehicle.
[0034] According to an embodiment, the user can request that the application provide a recommendation as to the most viable charging option based on a combination of factors selected. For example, the application can be instructed to provide the best charging station based solely on the time and charging speed criteria.
[0035] According to an embodiment, the application further includes functionality to accept user input to alter how the charging stations are ranked. This includes accepting input from a user to provide results based only on time and charging speed criteria. Without user input, the application will determine the optimum location for a user to charge their vehicle without human intervention.
[0036] According to an embodiment, the application includes functionality to display information for commercially and privately controlled car charging stations. Commercially operated charging stations will be monitored by the application to obtain information on their availability, charging rates, and costs. Individuals in control of privately owned charging stations will be able to sign up as a provider for electric car charging services, setting their own availability, charging rates, costs, and any other conditions they see fit for use of their station. These charging stations can be included in a set of those that can be selected by the application based on the method described herein.
[0037] In some embodiments, charging recommendation system 100 is implemented as a computer application or accessible via a web browser. The computer application can be accessible via a computer, such as a desktop computer or a mobile computing device, for example. In some embodiments, charging recommendation system 100 is configured for communication over a network, such as the Internet, and can receive and transmit data to and from a remote server, such as for updates and/or receiving or requesting other data. Various units or components of charging recommendation system 100 can be implemented in a distributed system. A processor as referred to herein can include more than one processor.
[0038] Various embodiments have been described in detail. Changes in and/or additions to the present description may be made.

Claims

CLAIMS What is claimed is:
1. A computer-implemented method for determining at least one recommendation for a vehicle charging station, comprising: assigning a numerical representation on the same numerical scale to at least one charging station factor for each charging station; generating a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; generating a weighted mean for each charging station based on each weight of the charging station; generating a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and communicating the at least one recommendation at an output device based on the weighted mean ranking.
2. The computer-implemented method of claim 1, wherein each charging station factor comprises distance to charging station, charging rate, charging cost, quality of destination, or proximity to amenities.
3. The computer-implemented method of claim 1 or 2, wherein each charging station factor is selected based on user input.
4. The computer-implemented method of any one of claims 1 to 3, wherein each charging station factor is selected based on at least one automatically determined factor.
5. The computer-implemented method of claim 4, wherein each automatically determined factor comprises present vehicle power or distance to destination.
6. The computer-implemented method of any one of claims 1 to 5, wherein the output device is a computer display.
7. The computer-implemented method of any one of claims 1 to 6, wherein the output device is a speaker.
8. The computer-implemented method of any one of claims 1 to 7, wherein the at least one recommendation comprises an optimal ranked list of charging stations.
9 The computer-implemented method of any one of claims 1 to 8, wherein the at least one recommendation comprises an alternative ranked list of charging stations. The computer-implemented method of any one of claims 1 to 9, wherein the at least one recommendation comprises a charging station having a highest weighted mean. A computer-implemented system for determining at least one recommendation for a vehicle charging station, comprising: an input processor configured to assign a numerical representation on the same numerical scale to at least one charging station factor for each charging station; an artificial intelligence unit configured to generate a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; the artificial intelligence unit further configured to generate a weighted mean for each charging station based on each weight of the charging station; the artificial intelligence unit further configured to generate a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and a recommendation unit configured to communicate the at least one recommendation at an output device based on the weighted mean ranking. The computer-implemented system of claim 11, wherein each charging station factor comprises distance to charging station, charging rate, charging cost, quality of destination, or proximity to amenities. The computer-implemented system of claim 11 or 12, wherein each charging station factor is selected based on user input. The computer-implemented system of any one of claims 11 to 13, wherein each charging station factor is selected based on at least one automatically determined factor. The computer-implemented system of claim 14, wherein each automatically determined factor comprises present vehicle power or distance to destination. The computer-implemented method of any one of claims 11 to 15, wherein the output device is a computer display. The computer-implemented system of any one of claims 11 to 16, wherein the at least one recommendation comprises an optimal ranked list of charging stations. The computer-implemented system of any one of claims 11 to 17, wherein the at least one recommendation comprises an alternative ranked list of charging stations. The computer-implemented system of any one of claims 11 to 18, wherein the at least one recommendation comprises a charging station having a highest weighted mean. A non-transitory computer-readable medium storing a set of machine-interpretable instructions, which, when executed, cause a processor to perform a method for determining at least one recommendation for a vehicle charging station, the method comprising: assigning a numerical representation on the same numerical scale to at least one charging station factor for each charging station; generating a weight for each charging station factor based on user preference data and artificial intelligence determined situational weights; generating a weighted mean for each charging station based on each weight of the charging station; generating a weighted mean ranking of the charging stations based on the weighted mean for each charging station; and communicating the at least one recommendation at an output device based on the weighted mean ranking.
11
PCT/CA2022/051699 2021-11-17 2022-11-17 Systems, methods, and devices for determining optimal electric car charging stations WO2023087108A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202163280255P 2021-11-17 2021-11-17
US63/280,255 2021-11-17

Publications (1)

Publication Number Publication Date
WO2023087108A1 true WO2023087108A1 (en) 2023-05-25

Family

ID=86396056

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CA2022/051699 WO2023087108A1 (en) 2021-11-17 2022-11-17 Systems, methods, and devices for determining optimal electric car charging stations

Country Status (1)

Country Link
WO (1) WO2023087108A1 (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140316939A1 (en) * 2013-04-19 2014-10-23 Honda Motor Co., Ltd. System and method for selecting an electric vehicle charging station
US20170276503A1 (en) * 2016-03-23 2017-09-28 I-On Communications Co., Ltd. System and method for recommending charging station for electric vehicle
CN110888908A (en) * 2019-11-01 2020-03-17 广州大学 Charging station/pile recommendation system and method capable of achieving deep learning continuously
CN111159533A (en) * 2019-11-29 2020-05-15 国网电动汽车服务有限公司 Intelligent charging service recommendation method and system based on user image
CN111291920A (en) * 2020-01-10 2020-06-16 国网重庆市电力公司电力科学研究院 Electric vehicle charging station recommendation method considering multiple factors and multiple scenes
CN112036943A (en) * 2020-08-27 2020-12-04 全球能源互联网研究院有限公司 Charging facility site selection method and system
CN112418524A (en) * 2020-11-23 2021-02-26 广州橙行智动汽车科技有限公司 Method, device, equipment and storage medium for predicting available state of charging station
CN112632380A (en) * 2020-12-24 2021-04-09 北京百度网讯科技有限公司 Training method of interest point recommendation model and interest point recommendation method
CN112819576A (en) * 2021-01-27 2021-05-18 北京百度网讯科技有限公司 Training method and device for charging station recommendation model and recommendation method for charging station
CN112819215A (en) * 2021-01-26 2021-05-18 北京百度网讯科技有限公司 Recommendation strategy training method and device, electronic equipment and readable storage medium
CN113313276A (en) * 2021-05-31 2021-08-27 广东电网有限责任公司 Automobile charging reservation method and device, electronic equipment and storage medium

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140316939A1 (en) * 2013-04-19 2014-10-23 Honda Motor Co., Ltd. System and method for selecting an electric vehicle charging station
US20170276503A1 (en) * 2016-03-23 2017-09-28 I-On Communications Co., Ltd. System and method for recommending charging station for electric vehicle
CN110888908A (en) * 2019-11-01 2020-03-17 广州大学 Charging station/pile recommendation system and method capable of achieving deep learning continuously
CN111159533A (en) * 2019-11-29 2020-05-15 国网电动汽车服务有限公司 Intelligent charging service recommendation method and system based on user image
CN111291920A (en) * 2020-01-10 2020-06-16 国网重庆市电力公司电力科学研究院 Electric vehicle charging station recommendation method considering multiple factors and multiple scenes
CN112036943A (en) * 2020-08-27 2020-12-04 全球能源互联网研究院有限公司 Charging facility site selection method and system
CN112418524A (en) * 2020-11-23 2021-02-26 广州橙行智动汽车科技有限公司 Method, device, equipment and storage medium for predicting available state of charging station
CN112632380A (en) * 2020-12-24 2021-04-09 北京百度网讯科技有限公司 Training method of interest point recommendation model and interest point recommendation method
CN112819215A (en) * 2021-01-26 2021-05-18 北京百度网讯科技有限公司 Recommendation strategy training method and device, electronic equipment and readable storage medium
CN112819576A (en) * 2021-01-27 2021-05-18 北京百度网讯科技有限公司 Training method and device for charging station recommendation model and recommendation method for charging station
CN113313276A (en) * 2021-05-31 2021-08-27 广东电网有限责任公司 Automobile charging reservation method and device, electronic equipment and storage medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
MOSCHELLA, M. ET AL.: "Decentralized Assignment of Electric Vehicles at Charging Stations Based on Personalized Cost Functions and Distributed Ledger Technologies", IEEE INTERNET OF THINGS JOURNAL, vol. 8, no. 14, 15 July 2021 (2021-07-15), pages 11112 - 11122, XP011864913, DOI: 10.1109/JIOT.2021.3052045 *
WANG, W. ET AL.: "Optimal user oriented multi-level experience planning strategy for electric automobile charging path", PROCEEDINGS OF E3S WEB OF CONF., INTERNATIONAL SYMPOSIUM ON ENERGY, ENVIRONMENTAL SCIENCE AND ENGINEERING, SECTION NEW ENERGY DEVELOPMENT AND ENERGY SUSTAINABLE DEVELOPMENT OPTIMIZATION, vol. 218, no. 02028, 11 December 2020 (2020-12-11), pages 5, XP093069446 *
YAQUB RAZIQ, HEIDARY KAVEH: "Automatic discovery and selection of most qualified electric vehicle charging station", INTERNATIONAL JOURNAL OF ELECTRIC AND HYBRID VEHICLES, INDERSCIENCE, vol. 12, no. 4, 28 January 2021 (2021-01-28), pages 279 - 303, XP009546723, ISSN: 1751-4088, DOI: 10.1504/IJEHV.2020.113081 *

Similar Documents

Publication Publication Date Title
TWI683272B (en) Information acquisition method, providing method, device, system, and storage medium
US10262535B2 (en) Vehicle management system
US11694130B2 (en) System and method for assigning an agent to execute and fulfill a task request
JP2019140908A (en) Information output method, information presentation device and information output system
EP2369299A1 (en) Navigation device and method for predicting the destination of a trip
US11687850B2 (en) System and method for processing a task request to be executed and fulfilled
CN108306851B (en) Information acquisition method, information providing method, information acquisition device, information providing device and information acquisition system
KR101206577B1 (en) Expert system based on social network service
US10248393B2 (en) System and method for generating a user interface by auctioning space on the user interface to self-determining, content-providing modules
CN111242733B (en) Vehicle function control method, device, equipment and storage medium
CN113516332B (en) Information processing apparatus, non-transitory storage medium, and evaluation method
WO2023087108A1 (en) Systems, methods, and devices for determining optimal electric car charging stations
CN111612286B (en) Order distribution method and device, electronic equipment and storage medium
CN108770014B (en) Calculation evaluation method, system and device of network server and readable storage medium
CN115795165A (en) Air-rail joint whole-process personalized travel scheme recommendation method and device
CN116155981A (en) Service recommendation method, system, device and computer program product
CN111831686A (en) Optimization method, device and system of sequencing model, electronic equipment and storage medium
US20220292414A1 (en) Dynamic invitation transmission and presentation mode determination for a network-based service
CN115711629A (en) On-the-way charging strategy planning method and related equipment
CN115330556A (en) Training method and device for information adjustment model of charging station and product
US11620575B2 (en) Interactive and dynamic mapping engine (iDME)
CN113761396A (en) Recommendation technology for electric vehicle charging scheme
EP4009251B1 (en) Information output device and information output method
CN114440918B (en) Charging pile navigation method and device, electronic equipment and automatic driving vehicle
CN112050822B (en) Method, system and device for generating driving route

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22894053

Country of ref document: EP

Kind code of ref document: A1