Artificial intelligence-based apparatus and method for charging electric vehicle

Abstract

The present invention relates to an artificial intelligence-based apparatus and method for charging an electric vehicle capable of providing various services through customer information analysis and target marketing, in which a processor may: upon arrival of an electric vehicle, instruct a communication unit to establish a communication connection with the electric vehicle; when basic information including passenger information, driving information, and charging information is received from the electric vehicle with which the communication connection is established, inputs the basic information into a pre-trained neural network model to predict a charging capacity and charging time of the electric vehicle and sets a charging schedule; and, when a charging request for the electric vehicle is received, charges the electric vehicle with a charging type corresponding to the set charging schedule.

Description

Artificial intelligence-based electric vehicle charging device and method

[0001] The present disclosure relates to an artificial intelligence-based electric vehicle charging device and method capable of providing various services through customer information analysis and targeted marketing.

[0002] Recently, electric vehicles (EVs), unlike conventional internal combustion engine vehicles, operate by driving a motor with power stored in a battery; as they can minimize carbon dioxide emissions and significantly reduce air pollution, they are becoming an important alternative for preventing global warming.

[0003] Consequently, as the government provides subsidies to expand the adoption of electric vehicles, sales of electric vehicles are increasing rapidly.

[0004] Since electric vehicles require regular charging because the battery discharges during operation, one can move to a location equipped with a charging device to recharge the battery.

[0005] These charging devices take a long time to charge electric vehicles on average, although the charging time varies depending on whether the method is fast charging or slow charging.

[0006] Accordingly, electric vehicle drivers and passengers spend time shopping at supermarkets or department stores or performing personal tasks while the electric vehicle is being charged.

[0007] As such, existing charging devices had a problem in that they performed only basic charging functions and could not provide necessary services to customers during long charging times.

[0008] Therefore, in the future, it is necessary to develop electric vehicle charging devices capable of analyzing customer information and conducting targeted marketing during charging times to provide various services to customers.

[0009] The present disclosure aims to solve the aforementioned problems and other problems.

[0010] The present disclosure aims to provide an electric vehicle charging device and method that can improve passenger satisfaction and convenience by predicting the charging capacity and charging time of an electric vehicle through a pre-trained neural network model to set a passenger-customized charging schedule, and charging the electric vehicle with a charging type corresponding to the passenger-customized charging schedule, thereby performing targeted marketing to the passenger and providing various discount services during the time the electric vehicle is being charged.

[0011] An electric vehicle charging device according to one embodiment of the present disclosure includes a communication unit that communicates with an electric vehicle and an external server, and a processor that sets a charging schedule based on information obtained from the electric vehicle. The processor controls the communication unit to communicate with the electric vehicle when the electric vehicle enters the vehicle, and when basic information including passenger information, driving information, and charging information is received from the electric vehicle connected via communication, the basic information is input into a pre-trained neural network model to predict the charging capacity and charging time of the electric vehicle and set a charging schedule. When a charging request for the electric vehicle is received, the electric vehicle can be charged with a charging type corresponding to the set charging schedule.

[0012] An electric vehicle charging method according to one embodiment of the present disclosure is an electric vehicle charging method of an electric vehicle charging device that is connected to an electric vehicle in communication with the electric vehicle, and may include the steps of: connecting to a connected electric vehicle in communication when the electric vehicle enters the vehicle; receiving basic information including passenger information, driving information, and charging information from the connected electric vehicle; inputting the received basic information into a pre-trained neural network model to predict the charging capacity and charging time of the electric vehicle and setting a charging schedule; receiving a charging request for the electric vehicle; and charging the electric vehicle with a charging type corresponding to the set charging schedule.

[0013] According to one embodiment of the present disclosure, an electric vehicle charging device can improve passenger satisfaction and convenience by predicting the charging capacity and charging time of an electric vehicle through a pre-trained neural network model to set a passenger-customized charging schedule and charging the electric vehicle with a charging type corresponding to the passenger-customized charging schedule, thereby performing targeted marketing to the passenger and providing various discount services during the time the electric vehicle is being charged.

[0014] In addition, the present disclosure can increase the sales of a store and encourage electric vehicle passengers, including drivers and co-passengers, to frequently use the electric vehicle chargers installed in the store by predicting products preferred by passengers and providing advertisements for the predicted preferred products tailored to the passengers, thereby offering discount benefits on electric vehicle charging costs.

[0015] In addition, the present disclosure utilizes passenger-specific charging pattern information received from an electric vehicle to change the electric charging method to a high-speed, medium-speed, or low-speed charging method, thereby completing the charging at the time the passenger returns from performing personal activities such as shopping, thus eliminating the passenger's waiting time and improving satisfaction and convenience.

[0016] In addition, the present disclosure can identify passenger information of an electric vehicle and driving habits for each passenger to automatically calculate charging time and charging amount and provide individually customized recommended charging information on a display screen.

[0017] In addition, the present disclosure can provide economic benefits to mart operators and charger manufacturers by providing a charging fee discount benefit to passengers who purchase products at a mart where a charger is installed, thereby encouraging passengers to purchase products and charge electric vehicles at the same time at the mart.

[0018] FIGS. 1 and FIGS. 2 are drawings for explaining an electric vehicle charging device according to one embodiment of the present disclosure.

[0019] FIG. 3 is a drawing for explaining the configuration of an electric vehicle charging device according to one embodiment of the present disclosure.

[0020] FIGS. 4 and FIGS. 5 are drawings for explaining the process of analyzing the gaze position of an occupant of an electric vehicle charging device according to one embodiment of the present disclosure.

[0021] FIG. 6 is a diagram illustrating the process of obtaining purchase information for each passenger of an electric vehicle charging device according to one embodiment of the present disclosure.

[0022] FIG. 7 is a diagram illustrating the process of obtaining charging and driving information for each passenger of an electric vehicle charging device according to one embodiment of the present disclosure.

[0023] FIGS. 8 to 13 are drawings for explaining the operation process of an on-device charging model of an electric vehicle charging device according to one embodiment of the present disclosure.

[0024] FIGS. 14 to 16 are drawings for explaining the process of providing a service of an electric vehicle charging device according to one embodiment of the present disclosure.

[0025] FIG. 17 is a drawing for explaining a charging method of an electric vehicle charging device according to one embodiment of the present disclosure.

[0026] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Identical or similar components, regardless of drawing symbols, are assigned the same reference number, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not inherently possess distinct meanings or roles. Furthermore, in describing embodiments disclosed in this specification, if it is determined that a detailed description of related prior art could obscure the essence of the embodiments disclosed in this specification, such detailed description will be omitted. Additionally, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification; the technical concept disclosed in this specification is not limited by the attached drawings, and it should be understood that they include all modifications, equivalents, and substitutions that fall within the concept and technical scope of this disclosure.

[0027] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another.

[0028] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0029] The neural networks, artificial neural networks, and network functions of the present disclosure can often be used interchangeably.

[0030] Additionally, in this disclosure, the terms neural network, neural network, and network function may be used interchangeably. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as “nodes.” These “nodes” may also be referred to as “neurons.” A neural network is composed of at least two nodes. The nodes (or neurons) constituting the neural networks may be interconnected by one or more “links.”

[0031] Artificial Intelligence (AI)

[0032] Artificial intelligence refers to the field of researching artificial intelligence or the methodologies capable of creating it, while machine learning refers to the field of researching methodologies to define and solve various problems addressed within the field of artificial intelligence. Machine learning is also defined as an algorithm that improves performance on a task through continuous experience.

[0033] An Artificial Neural Network (ANN) is a model used in machine learning that can refer to any model capable of problem-solving, composed of artificial neurons (nodes) that form a network through the connection of synapses. An artificial neural network can be defined by connection patterns between neurons in different layers, a learning process that updates model parameters, and an activation function that generates output values.

[0034] An artificial neural network may include an input layer, an output layer, and optionally one or more hidden layers. Each layer may include one or more neurons, and the artificial neural network may include synapses connecting the neurons. In an artificial neural network, each neuron may output a function value of an activation function for input signals, weights, and biases input through the synapses.

[0035] Model parameters refer to parameters determined through learning, including synaptic connection weights and neuron biases. Hyperparameters, on the other hand, refer to parameters that must be set before training in a machine learning algorithm, including the learning rate, number of iterations, mini-batch size, and initialization function.

[0036] The objective of training an artificial neural network can be viewed as determining model parameters that minimize the loss function. The loss function can be used as an indicator to determine optimal model parameters during the training process of an artificial neural network.

[0037] Machine learning can be classified into supervised learning, unsupervised learning, and reinforcement learning depending on the learning method.

[0038] Supervised learning refers to a method of training an artificial neural network with labels provided for the training data; a label can refer to the correct answer (or result) that the neural network must infer when training data is input. Unsupervised learning refers to a method of training an artificial neural network without labels provided for the training data. Reinforcement learning refers to a learning method in which an agent defined within an environment is trained to select an action or sequence of actions that maximizes the cumulative reward in each state.

[0039] Among artificial neural networks, machine learning implemented by a deep neural network (DNN) containing multiple hidden layers is also called deep learning, and deep learning is a part of machine learning. Hereinafter, machine learning is used in a sense that includes deep learning.

[0040] FIGS. 1 and FIGS. 2 are drawings for explaining an electric vehicle charging device according to one embodiment of the present disclosure.

[0041] As illustrated in FIGS. 1 and 2, the electric vehicle charging device (100) of the present disclosure is connected to an electric vehicle (10) and an external server (30) via communication, and can set a charging schedule tailored to the individual electric vehicle occupant (20) based on information obtained from the electric vehicle (10) and the external server (30).

[0042] The electric vehicle charging device (100) establishes a communication connection with the electric vehicle (10) when the electric vehicle (10) enters, and when basic information including passenger information, driving information, and charging information is received from the electric vehicle (10) connected to the communication, the basic information is input into a pre-trained neural network model to predict the charging capacity and charging time of the electric vehicle (10) and set a charging schedule, and when a charging request for the electric vehicle (10) is received from the passenger (20), the electric vehicle (10) can be charged with a charging type corresponding to the set charging schedule.

[0043] Here, when the electric vehicle charging device (100) checks the entry of the electric vehicle (10), it receives the identifier and entry time of the electric vehicle (10) currently entering from a server managing vehicle entry and exit among the external servers (30), and checks the entry of the electric vehicle (10) based on the identifier and entry time of the electric vehicle (10), and can establish a communication connection with the electric vehicle (10) based on the identifier of the electric vehicle (10).

[0044] And, when setting a charging schedule, the electric vehicle charging device (100) extracts a first element including the gender, age, and preference of the driver and passenger from the passenger information among the basic information, extracts a second element including the driving route, driving speed, and destination from the driving information, extracts a third element including the remaining battery amount, the amount of charge in progress, the past charging method, and the charging speed from the charging information, predicts the charging capacity and charging time of the electric vehicle (10) based on the first, second, and third elements, and can set a charging schedule customized for the passenger based on the predicted charging capacity and charging time.

[0045] Next, when the electric vehicle charging device (100) receives a charging request for the electric vehicle (10) when charging the electric vehicle (10), it selects a charging type that is optimal for the set charging schedule, and if the selected charging type is a slow charging type, it can slow charge the electric vehicle (10), or if the selected charging type is a fast charging type, it can fast charge the electric vehicle (10).

[0046] Next, the electric vehicle charging device (100) can obtain credit card information from the passenger's credit card when the passenger's credit card of the electric vehicle (10) is inserted, obtain the passenger's purchase information from a server managing the credit card among the external servers (30) based on the obtained credit card information, extract the passenger's (20) past charging information from the purchase information, and create a recommended charging menu popup based on the passenger's (20) past charging information and display it on the display screen.

[0047] Here, the electric vehicle charging device (100) can reset the charging schedule based on the recommended charging menu when it receives an approval input from the passenger (20) from the recommended charging menu popup.

[0048] Additionally, the electric vehicle charging device (100) can extract product information that the passenger (20) purchased during the past charging time from the purchase information, obtain advertising and discount coupon information corresponding to the passenger (20)'s past purchased products from a server managing product sales among the external servers (30) based on the passenger (20)'s past purchased product information, and generate an advertising text for charging discount based on the advertising and discount coupon information and display it on the display screen.

[0049] Here, the electric vehicle charging device (100) receives a charging discount request input from a passenger (20) from an advertisement for a charging discount, provides information of the passenger (20) requesting the charging discount to a server managing product sales, and when it receives the subsequent purchase history of the passenger (20) requesting the charging discount from the server managing product sales, it checks whether there is a purchase of a target product related to the advertisement and discount coupon from the subsequent purchase history, and if there is a purchase of a target product related to the advertisement and discount coupon, it can readjust the charging fee of the electric vehicle (10) based on the discount fee corresponding to the target product.

[0050] And, when the electric vehicle charging device (100) receives purchase activity information of a passenger (20), including purchase record information or discount coupon usage history information from an external server (30), while charging the electric vehicle (10), it can reset the charging schedule by adjusting the charging completion time based on the purchase activity information of the passenger (20), and can change or maintain the charging type in accordance with the reset charging schedule.

[0051] Additionally, the electric vehicle charging device (100) may obtain past driving information and past charging information of the electric vehicle (10) from a cloud server among external servers (30), and based on the obtained past driving information and past charging information, generate a message inquiring whether to select a charging method according to the existing menu, including the existing charging capacity, existing charging cost, and existing charging method, and display it on a display screen.

[0052] Additionally, the electric vehicle charging device (100) can obtain passenger information and individual driving information of the passenger (20) from the electric vehicle (10), analyze and store the individual driving pattern of the passenger (20) based on the individual driving information of the passenger (20), control the camera unit (190) to capture a face image of the passenger (20) looking at the display screen of the display unit (150), identify the passenger (20) based on the face image of the passenger (20), extract the individual driving pattern of the identified passenger (20), and generate a recommended charging menu corresponding to the individual driving pattern and display it on the display screen.

[0053] Here, the electric vehicle charging device (100) obtains driving path information from the electric vehicle (10), calculates the minimum charging amount and recharging time required to reach a destination after the current charging based on the driving path information, and can generate map information including the calculated minimum charging amount and recharging time and the location of a recommended charging station for recharging and display it on a display screen.

[0054] Next, the electric vehicle charging device (100) acquires past charging pattern information of the electric vehicle (10), generates recommended charging information and purchase proposal product and service menu information for charging fee discounts based on the past charging pattern information and displays it on the display screen of the display unit (150), and when a passenger (20) selects a specific product and service menu from the displayed purchase proposal product and service menu information, it can generate a message including a corresponding discount rate and a charging discount fee according to the discount rate and display it on the display screen.

[0055] Next, the electric vehicle charging device (100) checks for the presence of a passenger (20) waiting inside the electric vehicle (10), and if there is a waiting passenger (20), receives information about the passenger (20) from the electric vehicle (10), provides the information about the passenger (20) to a server managing product sales among external servers (30), obtains advertising and discount coupon information corresponding to the passenger's preferred product from the server managing product sales, matches the advertising and discount coupon information according to the passenger seat position inside the electric vehicle (10), and transmits the matched advertising and discount coupon information to the electric vehicle (10) so that it is displayed on a display unit according to the passenger seat position.

[0056] And, the electric vehicle charging device (100) can identify the passenger (20) looking at the display screen based on the passenger information received from the electric vehicle (10) and the face image obtained from the camera unit (190) when it obtains a face image of the passenger (20) looking at the display screen from the camera unit (190), predict the preferred product of the identified passenger (20) and obtain advertising and discount coupon information corresponding to the preferred product, analyze the pupil position and gaze position in the face image of the passenger (20) obtained from the camera unit (190) to identify a gaze matching screen area (152) that matches the gaze position of the passenger (20) on the display screen, and display advertising and discount coupon information corresponding to the preferred product on the gaze matching screen area (152).

[0057] Here, the electric vehicle charging device (100) can analyze the pupil position and gaze position in the face image of the passenger (20) obtained from the camera unit (190) and, by confirming the gaze matching screen area (152) that matches the gaze position of the passenger (20) on the display screen, predict the necessary products required for electric vehicle operation and display advertisements and discount coupon information corresponding to the necessary products on the gaze matching screen area (152).

[0058] Next, the electric vehicle charging device (100) can acquire charging information of the new electric vehicle when the new electric vehicle starts charging through another charging device while the electric vehicle (10) is being charged with a charging type corresponding to a set charging schedule, calculate the total power consumption based on the charging information of the new electric vehicle, and reset the charging schedule based on the total power consumption.

[0059] Additionally, when setting a charging schedule, the electric vehicle charging device (100) checks whether there are other electric vehicles being charged at the same time, and if there are other electric vehicles, obtains charging information from the other electric vehicles, calculates the total power usage based on the obtained charging information, and sets a charging schedule based on the total power usage.

[0060] Additionally, when setting a charging schedule, the electric vehicle charging device (100) can set a charging schedule such that if N electric vehicle charging devices exist in the same location, the electric vehicle is charged with a power amount lower than the maximum power consumption available at that location during the same time period.

[0061] Here, when setting a charging schedule, the electric vehicle charging device (100) receives information on the purchase activity of the passenger (20) while the electric vehicle (10) is charging, calculates the return time for the passenger (10) to return to the electric vehicle based on the purchase activity information, and can set a charging schedule as fast charging or slow charging based on the calculated return time and maximum power consumption.

[0062] In this way, the present disclosure can improve passenger satisfaction and convenience by predicting the charging capacity and charging time of an electric vehicle through a pre-trained neural network model to set a passenger-customized charging schedule and charging the electric vehicle with a charging type corresponding to the passenger-customized charging schedule, thereby performing targeted marketing to the passenger and providing various discount services during the time the electric vehicle is being charged.

[0063] In addition, the present disclosure can increase the sales of a store and encourage electric vehicle passengers, including drivers and co-passengers, to frequently use the electric vehicle chargers installed in the store by predicting products preferred by passengers and providing advertisements for the predicted preferred products tailored to the passengers, thereby offering discount benefits on electric vehicle charging costs.

[0064] In addition, the present disclosure utilizes passenger-specific charging pattern information received from an electric vehicle to change the electric charging method to a high-speed, medium-speed, or low-speed charging method, thereby completing the charging at the time the passenger returns from performing personal activities such as shopping, thus eliminating the passenger's waiting time and improving satisfaction and convenience.

[0065] In addition, the present disclosure can identify passenger information of an electric vehicle and driving habits for each passenger to automatically calculate charging time and charging amount and provide individually customized recommended charging information on a display screen.

[0066] In addition, the present disclosure can provide economic benefits to mart operators and charger manufacturers by providing a charging fee discount benefit to passengers who purchase products at a mart where a charger is installed, thereby encouraging passengers to purchase products and charge electric vehicles at the same time at the mart.

[0067] FIG. 3 is a drawing for explaining the configuration of an electric vehicle charging device according to one embodiment of the present disclosure.

[0068] As illustrated in FIG. 3, the electric vehicle charging device (100) of the present disclosure may include a communication unit (110), an input unit (120), a learning processor (130), a sensing unit (140), an output unit (150), a memory (170), and a processor (180), etc.

[0069] The communication unit (110) can transmit and receive data with external devices, such as electric vehicles and external servers, using wired and wireless communication technology. For example, the communication unit (110) can transmit and receive sensor information, user input, learning models, control signals, etc., with external devices.

[0070] At this time, the communication technologies used by the communication unit (110) include GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), LTE (Long Term Evolution), 5G, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Bluetooth (Bluetooth), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), ZigBee, NFC (Near Field Communication), etc.

[0071] The input unit (120) can acquire various types of data.

[0072] At this time, the input unit (120) may include a camera for inputting a video signal, a microphone for receiving an audio signal, a user input unit for receiving information from a user, etc. Here, the camera or microphone may be treated as a sensor, and the signal obtained from the camera or microphone may be referred to as sensing data or sensor information.

[0073] The input unit (120) can obtain training data for model training and input data to be used when obtaining an output using the training model. The input unit (120) may also obtain unprocessed input data, in which case the processor (180) or the learning processor (130) can extract input feature points as a preprocessing step for the input data.

[0074] The learning processor (130) can train a model composed of an artificial neural network using training data. Here, the trained artificial neural network may be referred to as a learning model. The learning model can be used to infer a result value for new input data other than the training data, and the inferred value can be used as a basis for judgment to perform an action.

[0075] At this time, the learning processor (130) may perform AI processing together with the learning processor of an external server.

[0076] At this time, the learning processor (130) may include memory integrated or implemented in the electric vehicle charging device (100). Alternatively, the learning processor (130) may be implemented using memory (170), external memory directly coupled to the electric vehicle charging device (100), or memory maintained in an external device.

[0077] The sensing unit (140) can obtain at least one of internal information of the electric vehicle charging device (100), surrounding environment information of the electric vehicle charging device (100), and user information using various sensors.

[0078] At this time, the sensors included in the sensing unit (140) include a proximity sensor, an illuminance sensor, an accelerometer, a magnetic sensor, a gyroscope, an inertial sensor, an RGB sensor, an IR sensor, a fingerprint recognition sensor, an ultrasonic sensor, a light sensor, a microphone, a lidar, a radar, etc.

[0079] The output unit (150) can generate output related to sight, hearing, or touch.

[0080] At this time, the output unit (150) may include a display unit that outputs visual information, a speaker that outputs auditory information, a haptic module that outputs tactile information, etc.

[0081] The memory (170) can store data that supports various functions of the electric vehicle charging device (100). For example, the memory (170) can store input data, learning data, learning models, learning history, etc. obtained from the input unit (120).

[0082] The processor (180) can determine at least one executable operation of the electric vehicle charging device (100) based on information determined or generated using a data analysis algorithm or a machine learning algorithm. The processor (180) can perform the determined operation by controlling the components of the electric vehicle charging device (100).

[0083] To this end, the processor (180) can request, search, receive, or utilize data from the learning processor (130) or memory (170), and can control the components of the electric vehicle charging device (100) to execute a predicted operation or a preferred operation among at least one executable operation.

[0084] At this time, the processor (180) can generate a control signal to control the external device when the connection of the external device is required to perform a determined operation, and transmit the generated control signal to the external device.

[0085] The processor (180) can obtain intention information regarding user input and determine the user's requirements based on the obtained intention information.

[0086] At this time, the processor (180) can obtain intent information corresponding to the user input by using at least one of a Speech To Text (STT) engine for converting voice input into a string or a Natural Language Processing (NLP) engine for obtaining intent information of natural language.

[0087] At this time, at least one of the STT engine or NLP engine may be composed of an artificial neural network in which at least a portion is learned according to a machine learning algorithm. Also, at least one of the STT engine or NLP engine may be learned by a learning processor (130), learned by a learning processor (240) of an electric vehicle charging device (200), or learned by distributed processing thereof.

[0088] The processor (180) can collect history information, including the operation details of the electric vehicle charging device (100) or user feedback regarding the operation, and store it in memory (170) or a learning processor (130), or transmit it to an external device such as an external server. The collected history information can be used to update a learning model.

[0089] The processor (180) can control at least some of the components of the electric vehicle charging device (100) to run an application stored in memory (170). Furthermore, the processor (180) can operate two or more of the components included in the electric vehicle charging device (100) in combination with each other to run the application.

[0090] The processor (180) controls the communication unit (110) to establish a communication connection with the electric vehicle when the electric vehicle enters the vehicle, and when basic information including passenger information, driving information, and charging information is received from the electric vehicle connected to the communication, the basic information is input into a pre-trained neural network model to predict the charging capacity and charging time of the electric vehicle and set a charging schedule, and when a charging request for the electric vehicle is received, the electric vehicle can be charged with a charging type corresponding to the set charging schedule.

[0091] Here, when the processor (180) checks the entry of an electric vehicle, if it receives the identifier and entry time of the electric vehicle currently entering from a server managing vehicle entry and exit among external servers, it can check the entry of the electric vehicle based on the identifier and entry time of the electric vehicle and control the communication unit (110) to perform a communication connection with the electric vehicle based on the identifier of the electric vehicle.

[0092] And, when the processor (180) receives basic information, if it is connected to the electric vehicle, it can request the basic information pre-set in the electric vehicle connected to the communication, and receive the requested basic information from the electric vehicle.

[0093] Here, when the processor (180) requests basic information, it checks whether the basic information is set, and if the basic information is set, it can request basic information including passenger information, driving information, and charging information of the electric vehicle from the electric vehicle connected via communication.

[0094] For example, passenger information of an electric vehicle may include the gender, age, and preferences of the driver and passenger, driving information of an electric vehicle may include the driving route, driving speed, and destination, and charging information of an electric vehicle may include the remaining battery capacity, the amount charged in progress, the past charging method, and the charging speed, but this is merely one embodiment and is not limited thereto.

[0095] Additionally, when the processor (180) checks whether basic information is set, if the basic information is not set, it may receive all basic information that is set by the electric vehicle itself.

[0096] In some cases, when the processor (180) receives basic information, if it is connected to the electric vehicle, it may automatically receive basic information set by itself from the electric vehicle connected to the communication.

[0097] Next, when setting a charging schedule, the processor (180) extracts a first element including the gender, age, and preference of the driver and passenger from the passenger information among the basic information, extracts a second element including the driving route, driving speed, and destination from the driving information, extracts a third element including the remaining battery amount, the amount of charge in progress, the past charging method, and the charging speed from the charging information, predicts the charging capacity and charging time of the electric vehicle based on the first, second, and third elements, and can set a charging schedule customized for the passenger based on the predicted charging capacity and charging time.

[0098] And, when the processor (180) receives a charging request for the electric vehicle when charging the electric vehicle, it selects a charging type that is optimal for the set charging schedule, and if the selected charging type is a slow charging type, it can slow charge the electric vehicle, or if the selected charging type is a fast charging type, it can fast charge the electric vehicle.

[0099] Next, the processor (180) can control the display unit (150) to obtain credit card information from the passenger's credit card when the passenger's credit card of the electric vehicle is inserted, obtain the passenger's purchase information from a server managing the credit card among external servers based on the obtained credit card information, extract the passenger's past charging information from the purchase information, and generate a recommended charging menu popup based on the passenger's past charging information and display it on the display screen.

[0100] Here, the processor (180) can reset the charging schedule based on the recommended charging menu when it receives an approval input from the passenger from the recommended charging menu popup.

[0101] Additionally, the processor (180) can control the display unit (150) to extract product information that the passenger purchased during the past charging time from the purchase information, obtain advertising and discount coupon information corresponding to the passenger's past purchased products from a server managing product sales among external servers based on the passenger's past purchased product information, and generate an advertising phrase for charging discount based on the advertising and discount coupon information and display it on the display screen.

[0102] Here, the processor (180) receives a request for a charging discount from a passenger in the form of an advertisement for a charging discount, provides information of the passenger requesting the charging discount to a server managing product sales, and when it receives the passenger's subsequent purchase history from the server managing product sales, checks whether there is a purchase of a target product related to the advertisement and discount coupon from the subsequent purchase history, and if there is a purchase of a target product related to the advertisement and discount coupon, it can readjust the charging fee of the electric vehicle based on the discount rate corresponding to the target product.

[0103] Additionally, when the processor (180) receives information on a passenger's purchase activity, including purchase history information or discount coupon usage history information from an external server while charging the electric vehicle, it can reset the charging schedule by adjusting the charging completion time based on the passenger's purchase activity information, and can vary or maintain the charging type in accordance with the reset charging schedule.

[0104] Next, the processor (180) can control the display unit (150) to obtain past driving information and past charging information of the electric vehicle from a cloud server among external servers, and to generate a message inquiring whether to select a charging method according to the existing menu, including the existing charging capacity, existing charging cost, and existing charging method based on the obtained past driving information and past charging information, and to display it on the display screen.

[0105] Furthermore, the present disclosure may further include a camera unit for photographing a passenger looking at the display screen of a display unit (150). A processor (180) may obtain passenger information and individual driving information of the passenger from an electric vehicle, analyze and store the individual driving pattern of the passenger based on the individual driving information of the passenger, control the camera unit to photograph a face image of the passenger looking at the display screen, identify the passenger based on the face image of the passenger, extract the individual driving pattern of the identified passenger, and control the display unit (150) to generate a recommended charging menu corresponding to the individual driving pattern and display it on the display screen.

[0106] Here, the processor (180) can control the display unit (150) to obtain driving path information from the electric vehicle, calculate the minimum charging amount and recharging time required to reach a destination after the current charging based on the driving path information, and generate map information including the calculated minimum charging amount and recharging time and the location of a recommended charging station for recharging, and display it on the display screen.

[0107] For example, the processor (180) can control the display unit (150) to generate information about affiliated stores around recommended charging stations for recharging and discount information about recommended charging stations and display it on the display screen.

[0108] Additionally, the processor (180) can control the communication unit (110) to transmit passenger information, driving information, and charging information of the electric vehicle currently being charged to the charger of the recommended charging station for recharging when generating map information.

[0109] Here, the processor (180) can control the communication unit (110) to display map information including the locations of recommended charging stations for recharging, and when a passenger selects one of the recommended charging stations for recharging from the displayed map information, the passenger information, driving information, and charging information of the electric vehicle currently being charged are transmitted to the charger of the recommended charging station selected by the passenger.

[0110] And, the processor (180) can control the display unit (150) to obtain past charging pattern information of the electric vehicle, generate recommended charging information and purchase proposal product and service menu information for charging fee discounts based on the past charging pattern information and display it on the display screen, and when a passenger selects a specific product and service menu from the displayed purchase proposal product and service menu information, the processor can control the display unit (150) to generate a message including a corresponding discount rate and a charging discount fee according to the discount rate and display it on the display screen.

[0111] Next, the processor (180) checks for the presence of a passenger waiting inside the electric vehicle, and if a passenger is waiting, receives passenger information from the electric vehicle, provides passenger information to a server managing product sales among external servers, obtains advertising and discount coupon information corresponding to the passenger's preferred product from the server managing product sales, matches the advertising and discount coupon information according to the passenger seat position inside the electric vehicle, and transmits the matched advertising and discount coupon information to the electric vehicle so that it is displayed on a display unit according to the passenger seat position.

[0112] Here, the processor (180) can transmit the selected advertisement and discount coupon information to a server managing product sales when the advertisement and discount coupon information is selected from the electric vehicle, receive a charging discount coupon based on the passenger's future purchase history from the server managing product sales based on the selected advertisement and discount coupon information, apply the charging discount coupon to discount the charging fee of the electric vehicle, and generate a charging fee discount history of the electric vehicle and transmit it to the electric vehicle to display it on the display unit (150) for each passenger seat location.

[0113] Next, the processor (180) can identify the passenger looking at the display screen based on the passenger information received from the electric vehicle and the face image obtained from the camera unit when it obtains a face image of the passenger looking at the display screen from the camera unit, predict the preferred product of the identified passenger and obtain advertising and discount coupon information corresponding to the preferred product, analyze the pupil position and gaze position in the passenger's face image obtained from the camera unit to identify a gaze matching screen area that matches the passenger's gaze position on the display screen, and control the display unit (150) to display advertising and discount coupon information corresponding to the preferred product on the gaze matching screen area.

[0114] Here, the processor (180) can control the display unit (150) to display advertisements and discount coupon information corresponding to the necessary products on the eye-matching screen area by analyzing the pupil position and gaze position in the passenger's face image obtained from the camera unit and identifying the gaze matching screen area that matches the passenger's gaze position on the display screen, thereby predicting the necessary products required for electric vehicle operation.

[0115] At this time, the processor (180) can control the display unit (150) to generate a message including a discount rate for purchasing the required product and a charging discount fee based on the discount rate, and display it on the eye-matching screen area when advertising and discount coupon information corresponding to the required product is displayed on the eye-matching screen area.

[0116] And, the processor (180) can obtain charging information of the new electric vehicle when the new electric vehicle starts charging through another charging device while the electric vehicle is being charged with a charging type corresponding to the set charging schedule, calculate the total power usage based on the charging information of the new electric vehicle, and reset the charging schedule based on the total power usage.

[0117] Next, when setting a charging schedule, the processor (180) checks whether there are other electric vehicles charging at the same time, and if there are other electric vehicles, obtains charging information from the other electric vehicles, calculates the total power usage based on the obtained charging information, and sets a charging schedule based on the total power usage.

[0118] Next, the processor (180) can set the charging schedule so that when N electric vehicle charging devices exist in the same location, the electric vehicle is charged with a power amount lower than the maximum power usage available at that location during the same time period.

[0119] Here, when setting a charging schedule, the processor (180) receives information on the passenger's purchasing activity while the electric vehicle is charging, calculates the return time for the passenger to return to the electric vehicle based on the purchasing activity information, and can set the charging schedule as fast charging or slow charging based on the calculated return time and maximum power consumption.

[0120] For example, when the processor (180) sets the charging schedule for fast charging, it can set the charging schedule for fast charging through the following mathematical formula 1.

[0121]

[0122] Here, is the passenger's return time, and is the maximum power consumption, and is the amount of fast charging power for the nth charging device during each t time slit t=1 ~ T=1.

[0123] As another example, when the processor (180) sets the charging schedule for slow charging, it can set the charging schedule for slow charging through the following mathematical formula 2.

[0124]

[0125] Here, is the passenger's return time, and is the maximum power consumption, and is the amount of slow charging power for the nth charging device during each t time slit t=1 ~ T=1.

[0126] As another example, when the processor (180) sets a charging schedule that varies between fast charging and slow charging, it can set a charging schedule that varies between fast charging and slow charging through the following mathematical formulas 3 and 4.

[0127]

[0128] Here, is the maximum power consumption in time slot t, and is the amount of rapid charging power that the n-th charging device charges at time slit t, and is the amount of slow charging power that the n-th charging device charges at time t.

[0129]

[0130] Here, is the maximum power consumption, and is the sum of the power usage of fast charging and slow charging for each t time slit t=1 ~ T=1 of the nth charging device.

[0131] FIGS. 4 and FIGS. 5 are drawings for explaining the process of analyzing the gaze position of an occupant of an electric vehicle charging device according to one embodiment of the present disclosure.

[0132] As illustrated in FIGS. 4 and 5, the present disclosure analyzes the position of the pupil (24) and the position of the gaze in the face image (22) of the passenger obtained from the camera unit to identify a gaze matching screen area that matches the position of the passenger's gaze in the display screen, and can display advertisements and discount coupon information corresponding to the passenger's preferred product on the gaze matching screen area.

[0133] As shown in FIG. 4, the present disclosure can extract a face image (22) from a full body image of a passenger captured by a camera unit, and extract coordinates of an area presumed to be an eye from the face image (22).

[0134] And, the present disclosure can extract the coordinates of the pupil (24) from the square area (23) of the eye.

[0135] Furthermore, the present disclosure checks for a change in the position of the pupil (24), and when the coordinates of the pupil (24) change, the passenger checks the coordinates touched through the touchscreen and can check the service menu of the corresponding coordinates.

[0136] Next, the present disclosure may convert and store data including the initial coordinates of the pupil, the changing coordinates of the pupil, the height, the angle of the upper body bending, the touch coordinates, the touched menu name, etc., into vectors to find the coordinate area of ​​the screen where the passenger's gaze falls, taking into account the position of the pupil (24), the passenger's height, and the angle of the upper body bending.

[0137] In addition, the present disclosure can search for similar vectors that have a high degree of similarity to the corresponding vector.

[0138] That is, the present disclosure can search for, as a similar vector, the initial coordinates of the similar pupil, the changing coordinates of the similar pupil, the similar key, the similar upper body bending angle, the similar touch coordinates, and the similar touched menu name.

[0139] Furthermore, the present disclosure can digitize the searched similar vector as follows.

[0140] That is, the present disclosure can convert each element of a similar vector into a decimal point less than 1, and then concatenate each decimal element into a single number.

[0141] The process of converting a vector into a number involves limiting the length of each element of the vector to M decimal places to ensure a fixed length, and then deleting the digits after M decimal places from the converted elements.

[0142] Accordingly, the present disclosure can extract only the numeric part from an element in which digits M or fewer decimal places have been deleted.

[0143] For example, in the present disclosure, if the first element is 0.123456, the second element is 0.246801357, the third element is 0.2692581, and M is 3, the numbers with three or fewer decimal places can be deleted.

[0144] That is, since the first element 0.123456 has three decimal places removed and becomes 0.12, the present disclosure can extract only the number 12 from the first element.

[0145] In addition, since the second element 0.246801357 has three decimal places or less removed and becomes 0.24, the present disclosure can extract only the number 24 for the second element.

[0146] In addition, since the third element 0.2692581 has three decimal places removed and becomes 0.34, the present disclosure can extract only the number 34 for the third element.

[0147] Finally, the present disclosure can create the number 01.122434 based on the embedded first element + second element + third element by concatenating each number as 0.12 + 24 + 34.

[0148] That is, the present disclosure can create a single combined numeric element by converting into a numeric first element, a numeric second element, and a numeric third element, and then connecting the numeric first element + the numeric second element + the numeric third element.

[0149] As another embodiment, the present disclosure may convert the initial coordinates of the pseudo pupil, the pseudo key, the pseudo upper body bending angle, the pseudo touch coordinates, and the pseudo touched menu name into a pseudo vector as follows.

[0150] If the initial coordinates of the pseudo-pupil are 0.110567890, 0.210456789, and 0.310369874, the present disclosure may convert the numbers to 0.112131 by deleting the numbers with three or fewer decimal places and concatenating the numbers.

[0151] In addition, the present disclosure can be digitized as 0.18 when the height is 180cm, and as 0.03 when the upper body bending angle is 30 degrees; when the touch coordinates are 0.42369, 0.521357, and 0.62159, the numbers can be digitized as 0.425262 by deleting the numbers after three decimal places and concatenating the numbers; and when the touched menu name is brown rice and tokenized as brown rice + rice, the numbers can be digitized as 0.53689 and 0.3458768 by deleting the numbers after three decimal places and concatenating the numbers.

[0152] Furthermore, the present disclosure can generate a single numerical element 0.112131180342520625334 by concatenating the initial coordinates of the pseudo pupil + the pseudo key + the pseudo upper body bending angle + the pseudo touch coordinates + the pseudo touched menu name.

[0153] In addition, the present disclosure can calculate the similarity of N elements constituting a vector as follows in order to perform similarity analysis.

[0154] A is the initial coordinates of the pseudo pupil, 0.110567890, 0.210456789, 0.310369874, B is the pseudo key and upper body bending angle, 0.18, 0.03, C is the pseudo touch coordinates, 0.42369, 0.521357, 0.62159, and D is the pseudo touched menu name, 0.53689, 0.3458768.

[0155] Similarity S can be calculated as shown in Equation 5 below.

[0156]

[0157] Here, is, (A, B) = (0.110567890, 0.210456789, 0.310369874, 0.18, 0.03), and is, (C,D) = (0.42369, 0.521357, 0.62159, 0.53689, 0.3458768).

[0158] The present disclosure can determine that vectors have high similarity if the similarity S value is greater than or equal to a specific value (e.g., 0.9).

[0159] In addition, the present disclosure allows for the selection of similar words such as brown rice, brown rice porridge, and brown rice crackers that have high similarity to the keyword brown rice when a passenger touches a brown rice menu displayed on a display screen while gazing at it with their finger, and displays a discount coupon menu corresponding to brown rice, brown rice porridge, and brown rice crackers on a display area adjacent to the coordinates where the passenger's gaze is directed and touched with their finger on the display screen.

[0160] As shown in FIG. 5, the present disclosure can calculate the three-dimensional coordinates (24b) of the similar pupil point and the three-dimensional coordinates (154b) of the similar touch point based on the angle of the line connecting the three-dimensional coordinates (154a) of the first touch point of the display panel (154) and the three-dimensional coordinates (24a) of the first pupil point when no similar pupil coordinates exist after receiving the first pupil coordinates.

[0161] FIG. 6 is a diagram illustrating the process of obtaining purchase information for each passenger of an electric vehicle charging device according to one embodiment of the present disclosure.

[0162] As illustrated in FIG. 6, the present disclosure can predict the product purchasing propensity of a passenger through a passenger purchasing model that is pre-trained based on data including passenger name, phone number, name of the purchased product, quantity, date of purchase, card number (card number used for product purchase), coupon discount price, coupon discount rate, coupon validity period, and battery charge amount (amount charged on the day).

[0163] The present disclosure can select multiple products that are highly correlated with item A of the battery charge amount in FIG. 6 for the learning of a passenger purchase model, and calculate the correlation between items B, C, and D, which are paid for with anonymized card numbers, and item A of the battery charge amount.

[0164] For example, in item A of battery charge, if the charge percentage increases and the purchase quantity of item B of gum product increases, the correlation can be calculated using the formula A = k1 · B.

[0165] As another example, in item A of battery charge amount, if the charge amount % increases and the purchase quantity of item C of 1.5L bottled water increases, the correlation can be calculated using the formula A = k2 · C.

[0166] As another example, if the percentage of battery charge A increases and the purchase quantity of bread product D increases, the correlation can be calculated using the formula A = k3 · D.

[0167] In addition, the present disclosure can determine which passenger items B through D were purchased for by checking the data of the first passenger and the second passenger, and then reflect the determination result in the learning of the passenger purchase model.

[0168] In addition, the present disclosure can analyze the correlation regarding which product purchase a credit card holder is influenced by which item (coupon discount amount, coupon discount rate, coupon expiration date, etc.) when purchasing items of items B through D using a credit card number and discount items of items E through H.

[0169] The present disclosure allows determining, through the following mathematical formula 6, how much the purchase amount of product S (bread, gum, bottled water) is affected by each discount factor (coupon discount rate, discount amount, expiration date, etc.).

[0170]

[0171] The present disclosure predicts discount coupon information for products the passenger can purchase and products likely to be purchased when the passenger revisits with the same credit card, transmits this information to a store server, and requests store location and map information.

[0172] In addition, the present disclosure can display discount coupon information and map information on a display screen and transmit the information to a passenger's terminal when receiving such information from a store server.

[0173] FIG. 7 is a diagram illustrating the process of obtaining charging and driving information for each passenger of an electric vehicle charging device according to one embodiment of the present disclosure.

[0174] As illustrated in FIG. 7, the present disclosure can collect charging data and vehicle driving data from an electric vehicle to predict battery consumption, and display an estimated charging amount and charging fee on a display screen based on the predicted battery consumption.

[0175] The present disclosure can collect data of items A to I from an electric vehicle as shown in FIG. 7, train a battery consumption model with the collected data, predict battery consumption based on the pre-trained battery consumption model, and calculate an estimated charging amount and charging fee based on the predicted battery consumption.

[0176] For example, the present disclosure can read ECU data of an electric vehicle (vehicle unique ID, current battery charge amount, charging start capacity, charging completion capacity, driving path, motor power amount, brake pad pressure record, etc.) when connected to a communication network with an electric vehicle, and then combine data such as the driving path, average RPM of the motor, motor RPM record, brake pad pressure record, etc. to calculate a first amount of power consumed by the electric vehicle motor for each driving section.

[0177] In addition, the present disclosure can calculate the pressure applied to the brake pad, calculate the second amount of power consumed by the pressure, and then predict the battery consumption by adding the first amount of power and the second amount of power.

[0178] FIGS. 8 to 13 are drawings for explaining the operation process of an on-device charging model of an electric vehicle charging device according to one embodiment of the present disclosure.

[0179] FIGS. 8 to 10 are flowcharts illustrating the process of predicting passenger interest products and providing services according to the present disclosure.

[0180] As illustrated in FIGS. 8 to 10, the charging model agent of the present disclosure receives credit card information from a passenger of an electric vehicle, transmits the passenger's name and credit card number to an embedding unit (S101), and can receive card approval details from the embedding unit.

[0181] Next, the charging model agent can decompose the card approval history sentence morphemes and transmit the token list to the embedding unit (S103).

[0182] And, the embedding unit can convert the list of tokens into a vector and transmit the word and vector to the vector store unit (S104).

[0183] Next, the vector store can store words and vectors, and search for similar vectors based on the vectors to find similar words and similar vectors (S105).

[0184] Additionally, the charging model agent transmits image data including the passenger's pupils and gaze obtained through the camera to the embedding unit (S107), and the embedding unit converts the image data into an image vector and transmits the image data and image vector to the vector store unit (S109).

[0185] Next, the vector store unit stores image data and image vector, generates a first similar image vector similar to the image vector, obtains first similar image data from the first similar image vector, and can transmit the first similar image data (S111).

[0186] And, the embedding unit can convert the first similar image data into a second similar image vector and transmit the first similar image data and the second similar image vector to the vector store unit (S113).

[0187] Next, the vector store unit stores the first similar image data and the second similar image vector, generates a third similar image vector similar to the second similar image vector, obtains the third similar image data from the third similar image vector (S115), identifies similar words and the passenger's gaze position based on this, and then transmits the similar words and the passenger's gaze coordinates to the charging model agent (S117).

[0188] Next, the charging model agent can analyze similar words of interest to the passenger based on similar words and the passenger's gaze coordinates (S119).

[0189] And, when the store server receives a list of products and services of interest to the passenger from the charging model agent, it checks whether it has stock corresponding to the list of products and services of interest to the passenger (S121), and can issue discount promotions and discount coupons for the products of interest to the passenger and provide a list of discount coupons to the charging model agent (S123).

[0190] Next, the charging model agent can display a list of discount coupons on the display screen when at least one of the passenger's screen touch, voice, gaze and mobile phone number is entered (S125).

[0191] FIG. 11 is a flowchart illustrating the charging model retraining process of the present disclosure.

[0192] As illustrated in FIG. 11, the on-device charging model of the present disclosure can acquire driving information of an electric vehicle, transmit driving information such as a driving route by day of the week, vehicle ID, and battery discharge to a cloud server, and request a charging model (S131).

[0193] Next, the cloud server can train a charging model based on driving information and transmit the trained charging model to an on-device charging model (S133).

[0194] Next, the on-device charging model updates the inferor by applying the received charging model (S135), presents the inferred electric charging amount to the passenger by considering the remaining battery power amount when charging the electric vehicle (S136), and when the passenger selects the electric charging amount, the passenger information, vehicle ID, actual charging amount, inferred charging amount, card number, card payment amount, etc. can be transmitted to the cloud server (S137).

[0195] And, the cloud server can retrain the charging model by reflecting passenger information, vehicle ID, actual charging amount and card payment amount, and transmit the retrained charging model to the on-device charging model (S138).

[0196] Next, the on-device charging model can be updated by applying the newly retrained charging model to the inference unit (S139).

[0197] FIGS. 12 and FIGS. 13 are flowcharts for explaining the process of applying the battery consumption model of the present disclosure.

[0198] As illustrated in FIGS. 12 and 13, the on-device charging model of the present disclosure can generate a status check request message for an electric motor control ECU (Electronic Control Unit) for an electric vehicle and transmit power line communication and Ethernet frames for the status check request of the electric motor control ECU to a heterogeneous gateway for the vehicle (S141).

[0199] Next, the vehicle heterogeneous gateway can convert power line communication and Ethernet frames in response to a status check request from the electric motor control ECU into CAN messages and transmit them to the electric motor control ECU (S143).

[0200] Next, the electric motor control ECU obtains information on the average power consumption and average RPM of the electric motor (S145), generates a CAN message for motor control information including the average power consumption and average RPM of the electric motor, and can transmit it to a heterogeneous gateway for the vehicle (S146).

[0201] And, the vehicle heterogeneous gateway can convert a CAN message for motor control information into a power line communication and Ethernet frame, and transmit the power line communication and Ethernet frame for motor control information to an on-device charging model (S147).

[0202] Next, the on-device charging model can generate an Ethernet frame containing the average power consumption of the electric motor, average RPM information, and battery consumption based on the motor control information and transmit it to a cloud server (S148).

[0203] Next, the on-device charging model can generate a status information request message for the brake pad pressure control ECU of the electric vehicle and transmit power line communication and Ethernet frames for the status information request of the brake pad pressure control ECU to a heterogeneous gateway for the vehicle (S151).

[0204] Next, the vehicle heterogeneous gateway can convert power line communication and Ethernet frames in response to the status information request of the brake pad pressure control ECU into CAN messages and transmit them to the brake pad pressure control ECU (S153).

[0205] Next, the brake pad pressure control ECU can acquire brake pad pressure control record data, generate a CAN message for the brake pad pressure control record data, and transmit it to a vehicle heterogeneous gateway (S154).

[0206] And, the vehicle heterogeneous gateway can convert CAN messages into power line communication and Ethernet frames, and transmit power line communication and Ethernet frames for brake pad pressure control record data to an on-device charging model (S155).

[0207] Next, the on-device charging model can generate an Ethernet frame based on brake pad pressure control record data and transmit it to a cloud server (S157).

[0208] Next, the cloud server can train a battery consumption model based on the electric motor average power consumption, average RPM information, battery consumption, and brake pad pressure control record data, and transmit the trained battery consumption model to an on-device charging model (S158).

[0209] And, the on-device charging model can be updated by applying the learned battery consumption model to the inferer (S159).

[0210] FIGS. 14 to 16 are drawings for explaining the process of providing a service of an electric vehicle charging device according to one embodiment of the present disclosure.

[0211] First, as illustrated in FIG. 14, the parking lot gate management server measures the identifier and entry time of the entering electric vehicle and can transmit the electric vehicle identifier and entry time information to the electric vehicle charger (S161).

[0212] And, the electric vehicle can acquire the electric vehicle identifier, passenger information, driving information, charging information and passenger interests, etc., and transmit the acquired information to the electric vehicle charger (S163).

[0213] Next, the electric vehicle charger of the present disclosure can verify the identity of the passenger through a camera (S165) and obtain the passenger's credit card information (S166).

[0214] Next, the electric vehicle charger requests the passenger card payment details from the card company server, and the card company server obtains the passenger card payment details in accordance with the request from the electric vehicle charger and transmits the passenger card payment details to the electric vehicle charger (S167).

[0215] In addition, the electric vehicle charger can extract products and services of interest to the passenger based on the passenger's card payment history and send a request to the store server to issue a discount coupon for the products and services of interest to the passenger (S168).

[0216] Next, as illustrated in FIG. 15, the store server can determine a discount amount within the available event costs, issue a coupon, and transmit advertisements for products and services, coupons, and discount amounts to the electric vehicle charger (S171).

[0217] Next, when the electric vehicle charger receives information including advertisements for products and services, coupons, and discount amounts (S173), it can calculate the charging capacity, charging method, and discount amount of the electric vehicle based on the received information (S175).

[0218] In addition, the electric vehicle charger can display advertisements and coupons in a matching screen area where the passenger's gaze is matched, and additionally display the electric vehicle charging capacity and discount amount (S176).

[0219] Next, when the electric vehicle charger receives a passenger input selecting information displayed in the matching screen area, it can transmit information including the product and service selected by the passenger, discount amount, coupon number, passenger identifier, and electric vehicle identifier to the store server (S177).

[0220] Next, the store server can verify whether products and services are purchased at the store using the passenger identifier and electric vehicle identifier based on the received information, and then transmit the passenger identifier, electric vehicle identifier and information regarding whether products and services are purchased to the electric vehicle charger (S178).

[0221] And, as shown in FIG. 16, the electric vehicle charger starts charging the electric vehicle by applying a predetermined charging method and charging speed (S181), and when charging the electric vehicle is completed, it can charge a discounted amount for the charging fee (S183).

[0222] Next, the parking lot gate management server can record electric vehicle investment information and transmit the recorded electric vehicle exit information and charging fee payment information to the electric vehicle charger (S185).

[0223] Next, the electric vehicle charger can predict the passenger's stay time and passenger tendency by considering the electric vehicle's exit time and entry time, and transmit information about the passenger identifier, electric vehicle identifier, entry time, exit time, passenger's stay time and passenger tendency to a cloud server (S187).

[0224] And, the cloud server can store information about the passenger identifier, electric vehicle identifier, entry time, exit time, passenger's stay time and passenger tendency received from the electric vehicle charger in a database (S189).

[0225] FIG. 17 is a drawing for explaining a charging method of an electric vehicle charging device according to one embodiment of the present disclosure.

[0226] As illustrated in FIG. 17, the present disclosure allows for a communication connection to be established with the electric vehicle when the electric vehicle enters the vehicle (S10).

[0227] Herein, the present disclosure can confirm the entry of an electric vehicle based on the identifier and entry time of the electric vehicle when receiving the identifier and entry time of the electric vehicle from a server managing vehicle entry and exit among external servers, and can establish a communication connection with the electric vehicle based on the identifier of the electric vehicle.

[0228] And, the present disclosure can receive basic information including passenger information, driving information, and charging information from a communication-connected electric vehicle (S20).

[0229] Herein, the present disclosure can request basic information pre-set in the electric vehicle connected to the communication when a communication connection is established with the electric vehicle, and receive the requested basic information from the electric vehicle.

[0230] Next, the present disclosure can set a charging schedule by inputting received basic information into a pre-trained neural network model to predict the charging capacity and charging time of the electric vehicle (S30).

[0231] Herein, the present disclosure extracts a first element including the gender, age, and preference of the driver and passenger from passenger information among basic information, extracts a second element including a driving route, driving speed, and destination from driving information, extracts a third element including a remaining battery amount, a process charge amount, a past charging method, and a charging speed from charging information, predicts the charging capacity and charging time of the electric vehicle based on the first, second, and third elements, and can set a customized charging schedule for the passenger based on the predicted charging capacity and charging time.

[0232] Next, the present disclosure can receive a charging request for an electric vehicle (S40).

[0233] In addition, the present disclosure can charge an electric vehicle with a charging type corresponding to a set charging schedule (S50).

[0234] Herein, the present disclosure allows for selecting a charging type that is optimal for a set charging schedule when a charging request for an electric vehicle is received, and if the selected charging type is a slow charging type, the electric vehicle can be slow-charged, or if the selected charging type is a fast charging type, the electric vehicle can be fast-charged.

[0235] In addition, the present disclosure can obtain credit card information from the passenger's credit card when the passenger's credit card of the electric vehicle is inserted, obtain the passenger's purchase information from a server managing the credit card among external servers based on the obtained credit card information, extract the passenger's past charging information from the purchase information, and generate and display a recommended charging menu popup based on the passenger's past charging information on a display screen.

[0236] Herein, the present disclosure can reset the charging schedule based on the recommended charging menu when a passenger's approval input is received from the recommended charging menu popup.

[0237] In addition, the present disclosure extracts product information purchased by a passenger during a past charging time from purchase information, obtains advertising and discount coupon information corresponding to the passenger's past purchased products from a server managing product sales among external servers based on the passenger's past purchased product information, and generates advertising text for charging discounts based on the advertising and discount coupon information and displays it on a display screen.

[0238] In this disclosure, when a request for a charging discount is received from a passenger via an advertisement for a charging discount, information of the passenger requesting the charging discount is provided to a server managing product sales; when subsequent purchase history of the passenger requesting the charging discount is received from the server managing product sales, it is checked whether there is a purchase of a target product related to the advertisement and discount coupon from the subsequent purchase history; and if there is a purchase of a target product related to the advertisement and discount coupon, the charging fee of the electric vehicle can be readjusted based on a discount rate corresponding to the target product.

[0239] In addition, the present disclosure may, when receiving purchase activity information of a passenger including purchase record information or discount coupon usage history information from an external server while charging an electric vehicle, adjust the charging completion time based on the passenger's purchase activity information to reset the charging schedule, and may vary or maintain the charging type in accordance with the reset charging schedule.

[0240] In addition, the present disclosure can acquire passenger information and individual driving information of the passenger from an electric vehicle, analyze and store the individual driving pattern of the passenger based on the individual driving information of the passenger, capture a face image of the passenger looking at a display screen, identify the passenger based on the face image of the passenger, extract the individual driving pattern of the identified passenger, generate a recommended charging menu corresponding to the individual driving pattern, and display it on the display screen.

[0241] In addition, the present disclosure can acquire past charging pattern information of an electric vehicle, generate recommended charging information and purchase proposal product and service menu information for charging fee discounts based on the past charging pattern information and display them on a display screen, and when a passenger selects a specific product and service menu from the displayed purchase proposal product and service menu information, generate and display a message including a corresponding discount rate and a charging discount fee based on the discount rate on the display screen.

[0242] In addition, the present disclosure can confirm the presence of a passenger waiting inside the interior of an electric vehicle, receive passenger information from the electric vehicle if a waiting passenger is present, provide passenger information to a server managing product sales among external servers, obtain advertising and discount coupon information corresponding to a preferred product for each passenger from the server managing product sales, match the advertising and discount coupon information according to the passenger seat position inside the electric vehicle, and transmit the matched advertising and discount coupon information to the electric vehicle so as to display it on a display unit corresponding to the passenger seat position.

[0243] Herein, the present disclosure can transmit the selected advertisement and discount coupon information to a server managing product sales when advertisement and discount coupon information is selected from an electric vehicle, receive a charging discount coupon based on the passenger's future purchase history from the server managing product sales based on the selected advertisement and discount coupon information, apply the charging discount coupon to discount the charging fee of the electric vehicle, and generate a charging fee discount history for the electric vehicle and transmit it to the electric vehicle to display it on a display for each passenger seat location.

[0244] In addition, the present disclosure can acquire charging information of a new electric vehicle when the new electric vehicle starts charging through another charging device while the electric vehicle is being charged with a charging type corresponding to a set charging schedule, calculate total power consumption based on the charging information of the new electric vehicle, and reset the charging schedule based on total power consumption.

[0245] In addition, the present disclosure can determine whether there are other electric vehicles being charged at the same time, and if there are other electric vehicles, obtain charging information from the other electric vehicles, calculate total power consumption based on the obtained charging information, and set a charging schedule based on total power consumption.

[0246] In addition, the present disclosure receives information on a passenger's purchasing activity while the electric vehicle is charging, calculates the return time for the passenger to return to the electric vehicle based on the purchasing activity information, and can set a charging schedule for fast charging or slow charging based on the calculated return time and maximum power consumption.

[0247] In addition, the present disclosure can reset the charging schedule based on the time interval information from the time of receiving past purchase record information or discount coupon usage history information for the occupant of the electric vehicle to the time of departure of the electric vehicle.

[0248] For example, if a passenger's grocery shopping record is received while charging an electric vehicle, and the past average time from the time the passenger's past grocery shopping record is received until the time the electric vehicle leaves the vehicle is about 20 minutes, the charging schedule can be adjusted so that charging ends 20 minutes after the time the current shopping record is received based on the past average time of 20 minutes, or the charging can be changed to a fast charging mode after the shopping record is received.

[0249] In addition, the present disclosure may also reset the charging schedule by obtaining the estimated stay time from the passenger's purchase record details.

[0250] For example, the estimated time of stay can be set to the movie running time + 20 minutes from the movie theater's A movie reservation details among the passenger's purchase history details.

[0251] As another example, if a passenger's cafe / restaurant purchase record is received while charging an electric vehicle, the passenger's purchase record details can be used to determine whether the meal is for one person or multiple people, and the estimated time of stay can be set accordingly.

[0252] In this way, the present disclosure can improve passenger satisfaction and convenience by predicting the charging capacity and charging time of an electric vehicle through a pre-trained neural network model to set a passenger-customized charging schedule and charging the electric vehicle with a charging type corresponding to the passenger-customized charging schedule, thereby performing targeted marketing to the passenger and providing various discount services during the time the electric vehicle is being charged.

[0253] In addition, the present disclosure can increase the sales of a store and encourage electric vehicle passengers, including drivers and co-passengers, to frequently use the electric vehicle chargers installed in the store by predicting products preferred by passengers and providing advertisements for the predicted preferred products tailored to the passengers, thereby offering discount benefits on electric vehicle charging costs.

[0254] In addition, the present disclosure utilizes passenger-specific charging pattern information received from an electric vehicle to change the electric charging method to a high-speed, medium-speed, or low-speed charging method, thereby completing the charging at the time the passenger returns from performing personal activities such as shopping, thus eliminating the passenger's waiting time and improving satisfaction and convenience.

[0255] In addition, the present disclosure can identify passenger information of an electric vehicle and driving habits for each passenger to automatically calculate charging time and charging amount and provide individually customized recommended charging information on a display screen.

[0256] In addition, the present disclosure can provide economic benefits to mart operators and charger manufacturers by providing a charging fee discount benefit to passengers who purchase products at a mart where a charger is installed, thereby encouraging passengers to purchase products and charge electric vehicles at the same time at the mart.

[0257] The above-described disclosure can be implemented as computer-readable code on a medium on which a program is recorded. A computer-readable medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable media include HDD (Hard Disk Drive), SSD (Solid State Disk), SSD (Silicon Disk Drive), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. Additionally, the computer may include a processor (180) of an artificial intelligence device.

[0258] According to the artificial intelligence-based electric vehicle charging device of the present disclosure, since it is possible to perform targeted marketing to passengers and provide various discount services while the electric vehicle is being charged, thereby improving passenger satisfaction and convenience, its industrial applicability is significant.

Claims

1. A communication unit connected to an electric vehicle and an external server; and, It includes a processor that sets a charging schedule based on information obtained from the electric vehicle, and The above processor is, An electric vehicle charging device characterized by controlling a communication unit to establish a communication connection with the electric vehicle when the electric vehicle enters, inputting the basic information including passenger information, driving information, and charging information into a pre-trained neural network model when basic information is received from the electric vehicle connected to the communication, predicting the charging capacity and charging time of the electric vehicle to set the charging schedule, and when a charging request for the electric vehicle is received, charging the electric vehicle with a charging type corresponding to the set charging schedule.

2. In Paragraph 1, The above processor is, An electric vehicle charging device characterized by, when setting the above charging schedule, extracting a first element including the gender, age, and preference of the driver and passenger from the passenger information among the basic information, extracting a second element including the driving route, driving speed, and destination from the driving information, extracting a third element including the remaining battery amount, process charging amount, past charging method, and charging speed from the charging information, predicting the charging capacity and charging time of the electric vehicle based on the first, second, and third elements, and setting a passenger-customized charging schedule based on the predicted charging capacity and charging time.

3. In Paragraph 1, The above processor is, An electric vehicle charging device characterized by, when charging the electric vehicle, when a charging request for the electric vehicle is received, selecting a charging type that is optimal for the set charging schedule, and if the selected charging type is a slow charging type, slow charging the electric vehicle, or if the selected charging type is a fast charging type, fast charging the electric vehicle.

4. In Paragraph 1, It further includes a display unit that displays charging menu items of the electric vehicle, and The above processor is, An electric vehicle charging device characterized by controlling a display unit to obtain credit card information from the passenger's credit card when the passenger's credit card of the electric vehicle is inserted, obtain the passenger's purchase information from a server managing the credit card among the external servers based on the obtained credit card information, extract the passenger's past charging information from the purchase information, and generate a recommended charging menu popup based on the passenger's past charging information and display it on a display screen.

5. In Paragraph 4, The above processor is, An electric vehicle charging device characterized by resetting the charging schedule based on the recommended charging menu when approval input from a passenger is received from the recommended charging menu popup.

6. In Paragraph 4, The above processor is, An electric vehicle charging device characterized by extracting product information purchased by the passenger during a past charging time from the purchase information, obtaining advertising and discount coupon information corresponding to the passenger's past purchased products from a server managing product sales among the external servers based on the passenger's past purchased product information, and controlling the display unit to generate an advertising phrase for charging discounts based on the advertising and discount coupon information and display it on a display screen.

7. In Paragraph 6, The above processor is, An electric vehicle charging device characterized by, when a request for a charging discount from a passenger is received from the above-mentioned advertising text for charging discount, providing information of the passenger requesting the charging discount to a server managing product sales, and when subsequent purchase history of the passenger requesting the charging discount is received from the server managing product sales, checking whether there is a purchase of a target product related to the above-mentioned advertisement and discount coupon from the subsequent purchase history, and if there is a purchase of a target product related to the above-mentioned advertisement and discount coupon, readjusting the charging fee of the electric vehicle based on a discount rate corresponding to the target product.

8. In Paragraph 4, The above processor is, An electric vehicle charging device characterized by receiving passenger purchase activity information, including purchase record information or discount coupon usage history information, from an external server while charging the electric vehicle, adjusting the charging completion time based on the passenger purchase activity information to reset the charging schedule, and varying or maintaining the charging type in accordance with the reset charging schedule.

9. In Paragraph 1, A display unit that displays charging menu items; and, It further includes a camera unit that photographs a passenger looking at the display screen of the above-mentioned display unit, and The above processor is, An electric vehicle charging device characterized by acquiring passenger information and individual driving information of the passenger from the electric vehicle, analyzing and storing the individual driving pattern of the passenger based on the individual driving information of the passenger, controlling the camera unit to capture a face image of the passenger looking at the display screen, identifying the passenger based on the face image of the passenger, and controlling the display unit to extract the individual driving pattern of the identified passenger and generate a recommended charging menu corresponding to the individual driving pattern and display it on the display screen.

10. In Paragraph 1, A display unit that displays charging menu items; and, It further includes a camera unit that photographs a passenger looking at the display screen of the above-mentioned display unit, and The above processor is, An electric vehicle charging device characterized by acquiring a face image of a passenger gazing at the display screen from the camera unit, identifying the passenger gazing at the display screen based on passenger information received from the electric vehicle and the face image acquired from the camera unit, predicting the preferred product of the identified passenger to acquire advertising and discount coupon information corresponding to the preferred product, analyzing the pupil position and gaze position in the passenger's face image acquired from the camera unit to identify a gaze matching screen area that matches the passenger's gaze position on the display screen, and controlling the display unit to display advertising and discount coupon information corresponding to the preferred product on the gaze matching screen area.

11. In Paragraph 1, The above processor is, An electric vehicle charging device characterized by acquiring charging information of a new electric vehicle when the electric vehicle starts charging through another charging device while the electric vehicle is being charged with a charging type corresponding to the charging schedule set above, calculating total power consumption based on the charging information of the new electric vehicle, and resetting the charging schedule based on the total power consumption.

12. In Paragraph 1, The above processor is, An electric vehicle charging device characterized by, when setting the charging schedule, checking whether there are other electric vehicles charging at the same time, and if there are other electric vehicles, obtaining charging information from the other electric vehicles, calculating the total power consumption based on the obtained charging information, and setting the charging schedule based on the total power consumption.

13. In Paragraph 1, The above processor is, An electric vehicle charging device characterized by setting the charging schedule such that, when N electric vehicle charging devices exist in the same location, the charging schedule is set so that the electric vehicle is charged with a power amount lower than the maximum power consumption available at that location during the same time period.

14. In Paragraph 13, The above processor is, An electric vehicle charging device characterized by receiving information on the passenger's purchasing activity while the electric vehicle is charging when setting the charging schedule, calculating the return time for the passenger to return to the electric vehicle based on the purchasing activity information, and setting the charging schedule as fast charging or slow charging based on the calculated return time and the maximum power consumption.

15. In a method for charging an electric vehicle using an electric vehicle charging device that communicates with an electric vehicle, A step of establishing a communication connection to the entered electric vehicle when the electric vehicle enters; A step of receiving basic information including passenger information, driving information, and charging information from the electric vehicle connected via communication above; A step of inputting the received basic information into a pre-trained neural network model to predict the charging capacity and charging time of the electric vehicle and setting the charging schedule; A step of receiving a charging request for the electric vehicle; and An electric vehicle charging method characterized by including the step of charging the electric vehicle with a charging type corresponding to the charging schedule set above.

16. In Paragraph 15, The step of setting the above charging schedule is, A step of extracting a first element including the gender, age, and preference of the driver and passenger from the passenger information among the basic information above, extracting a second element including the driving route, driving speed, and destination from the driving information, and extracting a third element including the remaining battery amount, process charge amount, past charging method, and charging speed from the charging information; A step of predicting the charging capacity and charging time of the electric vehicle based on the first, second, and third elements; and, An electric vehicle charging method characterized by including the step of setting a passenger-customized charging schedule based on the predicted charging capacity and charging time.

17. In Paragraph 15, A step of obtaining credit card information from the passenger's credit card when the passenger's credit card of the electric vehicle is inserted; A step of obtaining the passenger's purchase information from a server managing credit cards among external servers based on the credit card information obtained above; A step of extracting the passenger's past charging information from the above purchase information; and, An electric vehicle charging method characterized by further including the step of generating and displaying a recommended charging menu popup based on the past charging information of the aforementioned passenger.

18. In Paragraph 17, A step of resetting the charging schedule by adjusting the charging completion time based on the passenger's purchasing activity information when receiving passenger's purchasing activity information, including purchase record information or discount coupon usage history information, from the external server while charging the electric vehicle; and, An electric vehicle charging method characterized by further including the step of varying or maintaining the charging type in accordance with the above-mentioned reset charging schedule.

19. In Paragraph 15, A step of obtaining passenger information and individual driving information of the passenger from the electric vehicle; A step of analyzing and storing the individual driving pattern of the passenger based on the individual driving information of the passenger; A step of acquiring a face image of the above-mentioned passenger; A step of identifying the occupant based on the face image of the occupant; An electric vehicle charging method characterized by further including the step of extracting the individual driving pattern of the identified passenger and generating and displaying a recommended charging menu corresponding to the individual driving pattern.

20. A computer program stored on a computer-readable storage medium, wherein, when executed on one or more processors, the computer program performs the following operations for charging an electric vehicle, said operations being: An operation to establish a communication connection to the entered electric vehicle when the electric vehicle enters; The operation of receiving basic information including passenger information, driving information, and charging information from the above-mentioned communication-connected electric vehicle; The operation of inputting the received basic information into a pre-trained neural network model to predict the charging capacity and charging time of the electric vehicle and setting the charging schedule; The operation of receiving a charging request for the above electric vehicle; and A computer program stored in a computer-readable storage medium, characterized by including an operation to charge the electric vehicle with a charging type corresponding to the charging schedule set above.

Images