Personalized service station recommendations

Abstract

A system includes a monitoring module configured to determine at least one of a location and a route of a vehicle, and a recommendation module configured to identify a plurality of service stations based on the at least one of the location and the route of the vehicle. The monitoring module is configured to compare a preference of a first user of the vehicle to preference data relating to a second user of another vehicle, predict a preferred service station of the plurality of service stations based on the comparison, and present a recommendation to the first user, the recommendation indicating the preferred service station.

Description

Technical Field

[0001] This subject matter disclosure relates to energy or power transfer, and more specifically to systems and methods for controlling power transfer between energy storage systems with different parameters. Background Technology

[0002] Vehicles, including gasoline and diesel-powered vehicles, as well as electric and hybrid vehicles, are characterized by battery storage for purposes such as powering electric motors, electronic equipment, and other vehicle subsystems. The battery packs can be charged using dedicated charging stations and other power sources such as residences and buildings connected to the power grid. Multiple charging stations may be available while the vehicle is in motion. It is desirable to provide a device or system that can determine the optimal or best charging station for the vehicle. Summary of the Invention

[0003] In one exemplary embodiment, a system includes a monitoring module configured to determine at least one of a vehicle's location and route, and a recommendation module configured to identify a plurality of service stations based on at least one of the vehicle's location and route. The monitoring module is configured to compare the preferences of a first user of the vehicle with preference data associated with a second user of another vehicle, predict a preferred service station among the plurality of service stations based on the comparison, and present a recommendation to the first user indicating the preferred service station.

[0004] In addition to one or more of the features described herein, the vehicle is an electric vehicle, and the multiple service stations are multiple charging stations.

[0005] In addition to one or more features described herein, the first user and the second user are part of a group of users, and the second user is selected from the group of users based on the similarity between the second user and the first user.

[0006] In addition to one or more features described in this paper, similarity is determined by comparing the attributes of the first user with the attributes of each of the multiple users.

[0007] In addition to one or more features described herein, the prediction of preferred service stations includes assigning prediction scores to at least one of a plurality of service stations.

[0008] In addition to one or more features described in this paper, predicted scores are determined based on a score matrix of multiple users, including a first user and a second user. The score matrix includes scores for each combination of users and identified service stations.

[0009] In addition to one or more features described in this paper, similarity is determined based on a first set of latent factors for each of multiple users and a second set of latent factors for multiple service stations, which are estimated based on machine learning algorithms.

[0010] In addition to one or more features described herein, predicting the preferred service station includes training a machine learning algorithm to generate a user latent factor vector for each of a plurality of users, generating a service station latent factor vector for each of a plurality of service stations, and combining the user latent factor vector and the service station latent factor vector.

[0011] In addition to one or more features described herein, the predictive optimization service station includes selecting a second user based on a combination, and assigning a predicted score to a first user based on the second user's score.

[0012] In another exemplary embodiment, a method includes determining at least one of a vehicle's location and route, identifying a plurality of service stations based on at least one of the vehicle's location and route, comparing the preferences of a first user of the vehicle with preference data associated with a second user of another vehicle, predicting a preferred service station among the plurality of service stations based on the comparison, and presenting a recommendation to the first user that indicates the preferred service station.

[0013] In addition to one or more of the features described herein, the vehicle is an electric vehicle, and the multiple service stations are multiple charging stations.

[0014] In addition to one or more features described herein, the first user and the second user are part of a group of users, and the second user is selected from the group of users based on the similarity between the second user and the first user.

[0015] In addition to one or more features described herein, the prediction of preferred service stations includes assigning prediction scores to at least one of a plurality of service stations.

[0016] In addition to one or more features described in this paper, similarity is determined based on a score matrix of multiple users, including a first user and multiple second users. The score matrix includes the scores of each combination of user and identified service station.

[0017] In addition to one or more features described in this paper, similarity is determined based on a first set of latent factors for each of multiple users and a second set of latent factors for multiple service stations, which are estimated based on machine learning algorithms.

[0018] In addition to one or more features described herein, predicting the preferred service station includes training a machine learning algorithm to generate a user latent factor vector for each of a plurality of users, generating a service station latent factor vector for each of a plurality of service stations, and combining the user latent factor vector and the service station latent factor vector.

[0019] In addition to one or more features described herein, the prediction optimization service station includes selecting a second user based on a combination and assigning a prediction score to the first user based on the score of the selected second user.

[0020] In yet another exemplary embodiment, the vehicle system includes a memory having computer-readable instructions and a processing means for executing the computer-readable instructions, which control the processing means to perform a method. The method includes determining at least one of the vehicle's location and route; identifying a plurality of service stations based on the vehicle's location and route; comparing the preferences of a first user of the vehicle with preference data associated with a second user of another vehicle, wherein the first user and the second user are part of a plurality of users. The method further includes predicting a preferred service station among the plurality of service stations based on the comparison; and presenting a recommendation to the first user, the recommendation indicating the preferred service station.

[0021] In addition to one or more features described in this paper, a second user is selected from multiple users based on the similarity between the second user and the first user.

[0022] In addition to one or more features described in this paper, similarity is determined based on a score matrix of multiple users, which includes scores for each combination of users and identified service stations, and similarity is also determined based on a first set of latent factors for each of the multiple users and a second set of latent factors for the multiple service stations, which are estimated based on machine learning algorithms.

[0023] The above-described features and advantages, as well as other features and advantages, of this disclosure will become apparent when taken in conjunction with the accompanying drawings and the following detailed description. Attached Figure Description

[0024] Other features, advantages, and details appear by way of example only in the following detailed description, which is described in detail with reference to the accompanying drawings, wherein:

[0025] Figure 1 This is a top view schematic diagram of a motor vehicle including a battery system according to an exemplary embodiment;

[0026] Figure 2 Multiple vehicle users and charging stations according to exemplary embodiments are schematically depicted, and aspects of a method for predicting user preferences and presenting service station recommendations are shown.

[0027] Figure 3 This is a flowchart depicting various aspects of a method for recommending service stations to vehicle users according to an exemplary embodiment;

[0028] Figure 4 The aspects of determining service station recommendations based on a score matrix and collaborative filtering technique, according to an exemplary embodiment, are described;

[0029] Figure 5 An aspect of determining service station recommendations based on latent factors learned via a machine learning model, according to an exemplary embodiment, is described;

[0030] Figure 6 An aspect of determining service station recommendations based on latent factors learned via a machine learning model, according to an exemplary embodiment, is described;

[0031] Figure 7 An example of a fraction matrix according to an exemplary embodiment is depicted;

[0032] Figure 8 An example of a custom filter according to an exemplary embodiment is depicted;

[0033] Figure 9 An example of a multidimensional embedding, according to an exemplary embodiment, including clusters associated with users having similar preferences; and

[0034] Figure 10 A computer system according to an exemplary embodiment is described. Detailed Implementation

[0035] The following description is exemplary in nature only and is not intended to limit this disclosure, its application, or use. It should be understood that throughout the drawings, corresponding reference numerals denote the same or corresponding parts and features.

[0036] According to one or more exemplary embodiments, methods, apparatus, and systems are provided for presenting recommendations to a user regarding available charging stations or other service stations (e.g., gasoline and / or diesel refueling stations for combustion and hybrid vehicles, hydrogen refueling stations for fuel cell vehicles, etc.). Embodiments of the recommendation system are configured to provide personalized recommendations to a vehicle user based on user preferences, vehicle type, and behavior. Recommendations may be based on a score assigned to each charging / refueling station for the user.

[0037] In this embodiment, a score for a charging station assigned to a user (also referred to as the "first user") is estimated based on determining the preferences and other information of several other users (also referred to as "second users") and determining the similarity between the first user and each of the several second users. Similarity can be determined using collaborative filtering techniques, which employ matrix factorization to identify latent factors associated with each user and charging station. These latent factors and / or other information associated with other users are compared to identify another user or users with the highest similarity. Based on existing scores assigned to one or more charging stations by similar users, scores are assigned to one or more charging stations (e.g., charging stations that do not yet have assigned scores). The scores associated with each charging station can then be used to recommend the best or desired charging station to the user.

[0038] The embodiments described herein present numerous advantages and technical effects. For example, the embodiments provide improvements in navigation, user experience, charging, and vehicle performance by offering personalized recommendations that will help users find the most beneficial charging stations. The embodiments offer benefits such as reduced or minimized travel and / or charging time, and increased user satisfaction. The embodiments allow users to choose charging stations that best suit their behavior, routes, and preferences, thereby saving time and ensuring the use of the most suitable charging stations.

[0039] Existing recommendation systems suggest public charging locations along driving routes; however, recommendations from such systems are based solely on distance from the route. The embodiments described herein tailor recommendations to specific users based on their preferences and behaviors, optimizing user satisfaction and the public charging experience. Furthermore, user preferences and scores for a given charging station can be inferred without directly asking the user.

[0040] The implementation is not limited to use with any particular vehicle, device, or system that utilizes battery components and is applicable to a wide range of contexts. For example, the embodiments can be used with automobiles, trucks, aircraft, construction equipment, farm equipment, automated factory equipment, and / or any other equipment or system that can utilize charging stations.

[0041] Figure 1 An embodiment of a motor vehicle 10 is shown, which includes a body 12 that at least partially defines an occupant compartment 14. The body 12 also supports various vehicle subsystems, including a propulsion system 16 and other subsystems, to support the functions of the propulsion system 16 and other vehicle components, such as a braking subsystem, a suspension system, a steering subsystem, a fuel injection subsystem, an exhaust subsystem, etc.

[0042] Vehicle 10 can be an internal combustion engine vehicle, an electric vehicle (EV), or a hybrid electric vehicle (HEV). In the example, vehicle 10 is a hybrid vehicle that includes an internal combustion engine 18 and an electric motor 20.

[0043] Vehicle 10 includes a battery system 22, which may be electrically connected to motor 20 and / or other components, such as vehicle electronics. In an embodiment, battery system 22 includes battery assemblies, such as a high-voltage battery pack 24 having multiple battery modules 26. Each of the battery modules 26 includes multiple individual battery cells (not shown). Battery system 22 may also include a monitoring unit 28 configured to receive measurements from sensors 30. Each sensor 30 may be an assembly or system having one or more sensors for measuring various battery and environmental parameters, such as temperature, current, and voltage. Monitoring unit 28 includes various components, such as processors, memory, interfaces, buses, and / or other suitable components.

[0044] The battery system 22 includes various conversion devices for controlling the power supply from the battery pack 24 to the motor 20 and / or electronic components. The conversion devices include a direct current (DC) to DC converter module 32, which includes a DC-DC converter 34. The conversion devices also include an inverter module 36, which includes an inverter 38 that receives DC power from the DC-DC converter 34 and converts the DC power into alternating current (AC) power to be supplied to the motor 20.

[0045] The vehicle 10 also includes a charging system that can be used to charge the battery system 22 and / or supply power from the battery system 22 to charge another energy storage system (e.g., vehicle-to-vehicle (V2V) and / or vehicle-to-everything (V2X) charging). The vehicle charging system includes a charging control device 40, such as an on-board charging module (OBCM) connected to the charging port 42.

[0046] The charging control device 40 can be configured to perform other functions, such as monitoring battery parameters (e.g., temperature, voltage, current, and impedance) during the charging process, controlling various aspects of the charging process, and / or providing charging station recommendations as described herein.

[0047] Vehicle 10 includes at least one processor or processing device, referred to as processor 44, for controlling various aspects of identifying and recommending charging stations. Processor 44 may be a separate device as shown, or it may be part of the vehicle's monitoring and / or navigation system. Note that embodiments are not limited to any particular controller or processing device and may encompass multiple processors or controllers.

[0048] Vehicle 10 also includes a computer system 48, which includes one or more processing units 50 and a user interface 52. The computer system 48 can communicate with a controller or vehicle system, for example, to provide commands to it in response to user input. Various processing devices, modules, and units can communicate with each other via communication devices or systems such as Controller Area Network (CAN) or Transmission Control Protocol (TCP) buses.

[0049] Processor 44, computer system 48, and / or other processing units in vehicle 10 may be configured to communicate with various remote devices and systems, such as charging stations and other vehicles. This communication may be achieved, for example, via network 54 (e.g., cellular network, cloud, etc.) and / or via wireless communication. For example, vehicle 10 may communicate with various charging stations 56, remote entities 58 (e.g., workstations, fleet management systems, computers, servers, mapping systems, etc.), and / or database 60. Database 60 may store information about charging station locations and parameters (e.g., conventional or DC fast charging) as well as user information. Database 60 may store a fractional matrix, as further described herein.

[0050] Examples include one or more methods for identifying and recommending one or more charging stations to a user. Typically, the method includes identifying potential charging stations that the user can use based on the user's route and / or location. The method also includes providing recommendations to the user based on the scores or preferences of one or more other users who are sufficiently similar to the user.

[0051] Figure 2 Multiple vehicle users and charging stations are schematically depicted, and aspects of an example of the recommendation method described herein are illustrated. In this example, a first user 70 is driving an electric vehicle and determines that vehicle 10 should access a charging station. Based on the vehicle's location and / or route, four charging stations 72a, 72b, 72c, and 72d are considered available (e.g., within a selected distance from vehicle 10 and / or along the route).

[0052] The recommended approach includes identifying one or more similar users. A “similar” user is another user of another vehicle, where the other user and / or another vehicle share at least one attribute (or are sufficiently similar in at least one attribute). In this example, user information such as vehicle type and demographics is used to identify a similar user, referred to as Second User 74.

[0053] The processing device accesses charging station and user data (e.g., in database 60), which includes information about a first user 70 and a second user 74 (and potentially one or more additional users / drivers). The charging station and user data also includes information about available charging stations.

[0054] The second user 74 is associated with a score or ranking for each of the charging stations 72a, 72b, 72c, and 72d. Note that the score or ranking is specific to a given user and a specific charging station.

[0055] For example, the charging station score for the second user 74 includes a score R2a associated with charging station 72a, a score R2b associated with charging station 72b, a score R2c associated with charging station 72c, and a score R2d associated with charging station 72d. Each score in this example is indicated by a "thumbs up" symbol representing a positive score (or a relatively high score) or a "thumbs down" symbol representing a negative score (or a relatively low score).

[0056] The first user 70 is associated with the scores of each of charging stations 72a, 72b, and 72c, but not with the score of charging station 72d. For example, the charging station scores of the first user 70 include the score R1a associated with charging station 72a, the score R1b associated with charging station 72b, and the score R1c associated with charging station 72c.

[0057] The method includes predicting a score to be assigned by the first user 70 based on the preferences of the second user 74. The method then includes assigning a first user score (thumbs up) to charging station 72d, which is the same as the score (thumbs up) of the charging station 72d associated with the second user 74. Now that all charging stations have scores associated with user 70, recommendations can be presented to user 70.

[0058] Figure 3 An embodiment of a method 80 for recommending charging stations or other service stations or locations to a user is depicted. Method 80 includes multiple steps or stages represented by boxes 81-88. Method 80 is not limited to the number or order of the steps, as some steps represented by boxes 81-88 may be performed in a different order than described below, or fewer than all steps may be performed.

[0059] For illustrative purposes, method 80 is described in conjunction with vehicle 10 and processor 44. It should be understood that method 80 can be performed using any type of vehicle and any suitable processing equipment or combination of processing equipment.

[0060] Although the embodiments have been described in conjunction with electric vehicles and charging stations, the embodiments are not limited thereto. For example, the embodiments can be applied to internal combustion engine vehicles and hybrid vehicles, as well as other types of service stations (e.g., gas stations, mechanics, dealerships, etc.).

[0061] At box 81, processor 44 determines that vehicle 10 is expected to access a public charging station. Processor 44 may make this determination based on a user request or a signal indicating that the battery system has low charge. The driver or user of vehicle 10 is referred to herein as the “first user”.

[0062] At box 82, processor 44 collects or accesses information describing the characteristics of the first user and vehicle 10. This information may include user preferences (e.g., charging stations should be near restaurants or other places of interest), user demographics (e.g., age), any limitations imposed on the first user (e.g., mobility issues that may affect the type of charging station the first user can comfortably use), and any other information related to determining the similarity between the first user and other users. This information may also include vehicle type and charging capacity.

[0063] At box 83, processor 44 identifies available charging stations within a selected distance of vehicle 10 and / or conveniently accessible from the planned route.

[0064] In box 84, processor 44 accesses user data of one or more other users (second users) who have already used available charging stations and / or have provided sorting or other preference information about available charging stations. The user data of other users may include scores or preferences associated with each other user's charging stations, as well as demographic information.

[0065] At box 85, user data and information related to the first user are compared, and processor 44 determines the level of similarity between the first user and each of the other users. The level of similarity can be determined at least in part by finding matching or similar characteristics between users. Examples of such characteristics include age (and / or other demographic features), preferences, vehicle type, charging capability, etc.

[0066] In this embodiment, the level of similarity is determined at least in part by estimating latent factors for each user (the first user and other users). “Late factors” are any characteristics or attributes of a user determined through machine learning, as discussed further herein. Latent factors can be discovered without asking or prompting the users of vehicle 10, thus allowing similarity determination without requiring input from the users.

[0067] At box 86, processor 44 identifies which other user or user group has the greatest similarity (“similar user” or “similar group”) and assigns a predicted score to each available charging station of the first user (or each available charging station that does not have a predefined score of the first user). The predicted score is based on the scores or preferences of one or more similar users.

[0068] If a score is predefined or has already been assigned to one or more charging stations (for the first user), the scores of one or more similar users are used to predict the score, and the predicted score is assigned to each of the remaining charging stations. If multiple similar users have already assigned different scores to charging stations, the predicted score can be based on the average of the scores or on other values ​​of the scores.

[0069] At box 87, processor 44 identifies which charging station has the highest score (predicted or predetermined score), or which group of charging stations has the highest score, and presents a recommendation regarding which charging station is the most preferred for the first user. The recommendation can be presented as a single charging station or multiple charging stations that meet the first user's preferences. For example, the list of charging stations, along with their corresponding rankings or scores (e.g., numerical rankings, colors, thumbs-up / thumb symbols, or other symbols), can be presented via any suitable modality (e.g., graphically via a touchscreen or head-up display, audibly, etc.).

[0070] The predicted scores and recommendations for charging stations can consider additional factors beyond those used to determine similarity. For example, machine learning models can also consider predicted availability of a given planned route, distance from the planned route, reliability issues, and other charging-related aspects. This can be achieved through a weighted scoring formula.

[0071] At box 88, various actions can be performed based on recommendations. For example, directions to a recommended charging station can be provided, or if vehicle 10 has autonomous control capabilities, it can autonomously control itself to go to the recommended charging station. In another example, vehicle 10 can communicate with a network and / or the recommended charging station.

[0072] Figure 4 schematically depicted Figure 3 An embodiment of method 80, wherein similarity determination is based on factorization of a user score matrix. Collaborative filtering is used to determine similarity, where matrix factorization is used to learn latent factors. These latent factors are used to identify which other users are similar to the first user. Scores can then be predicted using scores assigned to charging stations of similar users, and the predicted scores are assigned to the first user's charging stations.

[0073] refer to Figure 4 Charging station data 90 and user data 92 are accessed and used to construct or update a user-station matrix 94 containing user ratings or scores for multiple users (including the first user of vehicle 10) and charging stations. Matrix 94 is referred to as the "score matrix".

[0074] Charging station data 90 includes various types of information for each of the multiple charging stations. Examples include each charging station's identifier (e.g., a numeric ID) and location (e.g., from GPS communications). Charging station data 90 may also include other characteristics of each charging station, such as charging level (e.g., DC fast charging (DCFC)), automatic charging capability, plug type, etc.

[0075] User data 92 includes various types of information for each of multiple users, which can be used to determine the similarity between users and their preferences. Examples include each user's identifier (e.g., a numeric identifier) ​​and demographic information.

[0076] User data 92 may also include information about user experiences and ratings of various charging stations. Such information may include actual user ratings, the number of visits to a given charging station with successful charging sessions, the number of visits with unsuccessful attempts, charging speed, etc.

[0077] User and charging station data are used to construct a score matrix 94. For each user, a score is calculated for each charging station (if sufficient information is available for calculation).

[0078] exist Figure 4 In the matrix, score matrix 94 includes data for m users (U1…U…). i …U m The sum of rows for n charging stations (CS1…CS) j …CS n The score matrix consists of columns. For a given preference or ranking, one or more entries are filled with scores (e.g., 1-5). Scores can be derived directly from known rankings or inferred from other information. For example, scores could be based on the number of successful charging attempts a user made at a given charging station, the kilowatt-hours charged at a session, and / or the charging speed. Multiple entries can be empty, where the charging station's preference or ranking relative to a given user is unknown.

[0079] Processor 44 uses a collaborative filtering technique (represented by element 96), which may include initially finding similar characteristics between users and vehicles (represented by element 98), as well as similarities between charging stations. These relationships can be used to identify one or more users most similar to the first user, and to identify similar charging stations.

[0080] Processor 44 collects data from multiple users and charging stations from score matrix 94. Collection can be performed on all users and charging stations or a subset based on similarity characteristics. For example, if prediction and recommendation are being performed for User1, data from a set of other users with a sufficient level of similarity is collected.

[0081] In this embodiment, collaborative filtering 96 includes learning latent factors (element 100) of the collected users and charging stations. These latent factors are learned using machine learning techniques as discussed further herein. Semantic relationships and / or the latent factors are then used to predict the score of U1 (represented by element 102).

[0082] Figure 5 and Figure 6 Various aspects of embodiments of method 80 are schematically depicted. In these embodiments, a neural network or other machine learning model is trained to detect potential factors of the user and the charging station, which are used to determine similarity and predict scores.

[0083] In this embodiment, user and charging station rating data 110 from the score matrix 94 (e.g., a list of user and charging station identifiers, ratings, or combinations thereof) is input into a latent feature space or embedding space (embedding). For example, the user and charging station data 110 includes a user identifier (UID) column and a charging station identifier (CSID) column. The score (S) column includes a numerical score for each combination of user and charging station.

[0084] In this embodiment, user data describing the characteristics of each user is input into the embedding layer 112. The embedding layer 112 is trained to generate clusters 114 of similar users. The clustering provides a set of User Latent Vectors (ULVs) 116 for each user identifier.

[0085] Similarly, charging station data describing the characteristics of each available charging station is input into an embedding layer 120, which is trained to generate clusters 122 of similar charging stations. The clustering provides a set of latent vectors (SCLV) 124 for each charging station identifier.

[0086] In one implementation scheme, such as Figure 5 As shown, latent vector 116 is combined into a dense layer 118, and latent vector 124 is combined into a dense layer 126. Dense layers 118 and 126 are combined by calculating the cross product of the dense layers (represented by element 119). The result is a set of predicted scores 128 for each combination of user and charging station. The loss (the difference between the predicted score and the actual score) can be returned to refine the score predictions.

[0087] Figure 6 express Figure 5 An alternative to the embodiment is described above. In this embodiment, matrix information and latent vectors are applied to another machine learning model 130, which learns dot products via a deep neural network.

[0088] The training process used to predict scores can be repeated as needed. For example, training can be repeated at predetermined time intervals (e.g., daily, weekly, etc.).

[0089] Figure 7 An example of a score matrix 94 is depicted, along with examples of pre-existing or predefined scores. In this example, the score matrix represents four users (U1 to U4) and four charging stations (CS1 to CS4). Missing scores (indicated by "?") exist in this example and can be predicted based on the similarity between users. By applying this data to a machine learning model including embedding layers 112 and 120, missing scores can be added based on scores of similar drivers. For example, if U1 is determined to be similar to U3 (i.e., they have similar preferences), a score "2" can be assigned to the combination of U1 and CS4.

[0090] In an embodiment, a custom filter can be added to method 80 to take into account specific requirements or characteristics, or to further analyze the similarity between users and charging stations. A custom filtering procedure can be executed to provide additional filtering. This process includes selecting or creating categories, such as plug type or charging mode such as automatic charging, to determine if they are available.

[0091] The customized filtering process involves creating concatenated vector representations as two types of vectors. The first vector is the learned embedding, denoted as "e". The norm of these vectors is significantly lower than one (||e||=ε<<1).

[0092] The second vector (scalar) represents the desired category "c", which is used as an indicator function and has a value of 1 or 0.

[0093] The cascaded vector is denoted by x. For a given user with embedding x1 and a given charging station with embedding x2, the cascaded vector is represented by the following equation:

[0094]

[0095] When x1 and x2 share the same category, the concatenated vector is represented as:

[0096]

[0097] When x1 and x2 do not share the same category, the concatenated vector is represented as:

[0098]

[0099] Adding an indicator function results in vectors of the same category having significantly higher dot products.

[0100] Figure 8An example of user score information 132 for user U1 is described, which includes a predicted score S assigned to each of a set of charging stations, and also includes an indicator function for each of two categories. The first category (represented by UA) is whether the user's vehicle has automatic charging capability. If the user's vehicle has automatic charging capability, an indicator function value of 1 is provided, and if the user's vehicle does not have this capability, an indicator function value of 0 is provided. The second category (represented by CSA) is whether the charging station has automatic charging capability. If the charging station has automatic charging capability, an indicator function value of 1 is provided, and if the charging station does not have this capability, an indicator function value of 0 is provided.

[0101] Figure 8 The category values ​​for user U1 and each charging station are also shown. As illustrated, using the indicator function results in a higher dot product and a correspondingly higher score. For example, the scores associated with the user and charging stations in the same category have significantly higher scores (4.8 and 4.5) than the scores (2, 2.3, and 1.5) for charging stations in different categories from the user.

[0102] It should be noted that the embedding layer can be two-dimensional, three-dimensional, or have any number of dimensions. Figure 9 An example of a 15-dimensional user embedding layer 140 is shown, representing multiple users. The embedding layer includes various clusters, such as cluster 142, which represent users predicted to have similar preferences (i.e., similar users).

[0103] Figure 10 Various aspects of an embodiment of a computer system 240 capable of performing various aspects of the embodiments described herein are illustrated. The computer system 240 includes at least one processing means 242, which typically includes one or more processors for performing various aspects of the image acquisition and analysis methods described herein.

[0104] The components of computer system 240 include processing device 242 (such as one or more processors or processing units), memory 244, and bus 246, which couples various system components, including system memory 244, to processing device 242. System memory 244 may be a non-transitory computer-readable medium and may contain a variety of computer-readable media. Such media may be any available medium accessible by processing device 242, and includes volatile and non-volatile media as well as removable and non-removable media.

[0105] For example, system memory 244 includes non-volatile memory 248 such as a hard disk drive, and may also include volatile memory 250 such as random access memory (RAM) and / or cache memory. Computer system 240 may also include other removable / non-removable, volatile / non-volatile computer system storage media.

[0106] System memory 244 may include at least one program product having a set (i.e., at least one) of program modules configured to perform the functions of the embodiments described herein. For example, system memory 244 stores various program modules that typically perform the functions and / or methods of the embodiments described herein. Module 252 may be included to perform functions related to performing impedance measurements, and module 254 may be included to perform functions related to controlling the charging process. System 240 is not limited thereto, as other modules may be included. As used herein, the term "module" refers to processing circuitry that may include application-specific integrated circuits (ASICs), electronic circuitry, processor (shared, dedicated, or group) and memory executing one or more software or firmware programs, combinational logic circuitry, and / or other suitable components that provide the described functions.

[0107] The processing device 242 can also communicate with one or more external devices 256, such as a keyboard, a pointing device, and / or any device that enables the processing device 242 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Communication with various devices can occur via input / output (I / O) interfaces 264 and 265.

[0108] Processing device 242 can also communicate via network adapter 268 with one or more networks 266, such as a local area network (LAN), a general wide area network (WAN), a bus network, and / or a public network (e.g., the Internet). It should be understood that, although not shown, other hardware and / or software components may be used in conjunction with computer system 40. Examples include, but are not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, and data archiving storage systems.

[0109] The terms “a” and “an” do not indicate a limitation of quantity, but rather that at least one of the referenced items is present. Unless the context clearly indicates otherwise, the term “or” means “and / or”. Throughout the specification, reference to “aspect” means that a particular element described in connection with that aspect (e.g., a feature, structure, step, or characteristic) is included in at least one aspect described herein and may or may not be present in other aspects. Furthermore, it should be understood that the described elements may be combined in any suitable manner in the aspects.

[0110] When an element, such as a layer, film, region, or substrate, is referred to as being “on” another element, it can be directly on the other element, or there may be intermediate elements present. Conversely, when an element is referred to as being “directly” on another element, there are no intermediate elements present.

[0111] Unless otherwise stated herein, all test standards are the most recent standards effective up to the filing date of this application, or, if priority is claimed, the most recent standards effective up to the filing date of the earliest priority application in which the test standards appear.

[0112] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0113] While the foregoing disclosure has been described with reference to exemplary embodiments, those skilled in the art will understand that various changes can be made and elements can be substituted with equivalents without departing from its scope. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of this disclosure without departing from the basic scope of this disclosure. Therefore, it is intended that this disclosure be limited to the specific embodiments disclosed, but will include all embodiments falling within its scope.

Claims

1. A system comprising: A monitoring module, configured to determine at least one of the vehicle's location and route; and The recommendation module is configured to execute: Multiple service stations are identified based on at least one of the vehicle's location and the route; Compare the preferences of the first user of the vehicle with the preference data related to the second user of another vehicle; Based on the comparison, a preferred service station is predicted among the plurality of service stations; and A recommendation is presented to the first user, and the recommendation indicates the preferred service station.

2. The system according to claim 1, wherein, The vehicle is an electric vehicle, and the multiple service stations are multiple charging stations.

3. The system according to claim 1, wherein, The first user and the second user are part of a plurality of users, and the second user was selected from the plurality of users based on the similarity between the second user and the first user.

4. The system according to claim 3, wherein, The similarity is determined by comparing the attributes of the first user with the attributes of each of the plurality of users.

5. The system of claim 1, wherein predicting the preferred service station includes assigning a prediction score to at least one of the plurality of service stations.

6. The system according to claim 5, wherein, The predicted score is determined based on a score matrix of multiple users, including the first user and the second user, and the score matrix includes the score for each combination of user and identified service station.

7. The system according to claim 6, wherein, The similarity is determined based on a first set of latent factors for each of the plurality of users and a second set of latent factors for the plurality of service stations, the first set of latent factors and the second set of latent factors being estimated based on a machine learning algorithm.

8. The system according to claim 7, wherein, Predicting the preferred service station includes training the machine learning algorithm to generate a user latent factor vector for each of the plurality of users, generating a service station latent factor vector for each of the plurality of service stations, combining the user latent factor vectors and the service station latent factor vectors, selecting the second user based on the combination, and assigning a predicted score to the first user based on the score of the second user.

9. A method comprising: Determine at least one of the vehicle's location and route; Multiple service stations are identified based on at least one of the vehicle's location and the route; Compare the preferences of the first user of the vehicle with the preference data related to the second user of another vehicle; Based on the comparison, a preferred service station is predicted among the plurality of service stations; and A recommendation is presented to the first user, and the recommendation indicates the preferred service station.

10. The method according to claim 9, wherein, The first user and the second user are part of a plurality of users. The second user is selected from the plurality of users based on the similarity between the second user and the first user, and the similarity is determined based on a score matrix of the plurality of users, which includes the first user and the plurality of second users. The score matrix includes the score of each combination of user and identified service station.

Images