Charging pile intelligent control method and system based on face recognition

Abstract

The invention discloses a charging pile intelligent control method and system based on face recognition, and relates to the technical field of information security, and the method comprises the steps: collecting a user face image through a camera when a user gets close to a charging pile, and extracting a user face feature vector through a lightweight algorithm; matching the user face feature vector with a user face feature vector pre-stored in a local database, and verifying user identity information; based on the user identity information passing verification, the charging authority bound with the user identity information is distributed, meanwhile, the relation between the user and the vehicle is verified, and a charging scheme is dynamically generated in combination with user historical charging preference information and charging initial data; charging is started according to the charging scheme, and charging parameters are dynamically adjusted by monitoring real-time charging data in the charging process in real time; the face recognition technology, personalized charging scheme generation and real-time charging parameter dynamic adjustment are introduced, and the intelligent level and user experience of the charging pile system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of information security technology, and in particular to a charging pile intelligent control method and system based on face recognition. Background Art

[0002] With the rapid popularization of new energy vehicles, charging piles, as core supporting facilities, have become an important part of promoting the development of the new energy vehicle industry. In recent years, charging pile technology has gradually developed from traditional manual operation to intelligent and automated directions. By integrating the Internet, Internet of Things and big data technologies, some charging piles have realized remote monitoring, automatic settlement and intelligent adjustment of charging status. However, the existing charging pile system still has significant deficiencies in user identity authentication, charging plan formulation and privacy protection. For example, identity authentication mainly relies on traditional methods such as card insertion, code scanning or password input. These methods are not only cumbersome to operate, but also vulnerable to security risks such as card loss or password leakage. In addition, existing charging solutions mostly adopt fixed strategies and lack the ability to dynamically adjust to users' historical charging preferences, vehicle characteristics and real-time data, making it difficult to meet diverse personalized needs, resulting in low charging efficiency and poor user experience.

[0003] Further analysis found that the deficiencies of existing technologies are mainly reflected in the following three aspects: First, the identity authentication method lacks security and convenience. Traditional methods are difficult to effectively prevent unauthorized use. Even if some charging piles introduce cloud-based identity recognition functions, they are easily affected by network delays or interruptions and cannot completely eliminate the risk of impersonation. Second, the formulation of charging plans lacks the ability to comprehensively analyze multi-dimensional data and cannot dynamically generate charging strategies based on vehicle model, battery status and user preferences. At the same time, the real-time monitoring and parameter adjustment capabilities during the charging process are insufficient, which may lead to inefficiency or increased battery loss. Third, fee settlement and data storage mostly rely on cloud processing, which poses a risk of user privacy leakage and affects the normal operation of the system when the network is unstable. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent control method for charging piles based on face recognition to solve the problem that the formulation of charging plans lacks the ability to comprehensively analyze multi-dimensional data and cannot dynamically generate charging strategies according to vehicle model, battery status and user preferences.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a charging pile intelligent control method based on face recognition, which comprises:

[0008] When a user approaches a charging station, the camera collects the user's facial image, uses a lightweight algorithm to extract the user's facial feature vector, and matches it with the user's facial feature vector pre-stored in the local database to verify the user's identity information;

[0009] Based on the verified user identity information, the charging permission bound to the user is assigned, and the relationship between the user and the vehicle is verified. The charging plan is dynamically generated by combining the user's historical charging preference information and initial charging data;

[0010] Start charging according to the charging plan, and dynamically adjust the charging parameters by monitoring the real-time charging data during the charging process;

[0011] Based on the monitoring results, it determines whether charging is completed and automatically calculates the charging fee, and stores the charging record in the user account.

[0012] As a preferred solution of the charging pile intelligent control method based on face recognition of the present invention, when a user approaches the charging pile, the user's facial image is collected by a camera, a lightweight algorithm is used to extract the user's facial feature vector, and the facial feature vector is matched with the user's facial feature vector pre-stored in a local database to verify the user's identity information. The specific steps are as follows:

[0013] The charging pile is equipped with a high-resolution camera. When the user approaches the charging pile, the charging pile camera automatically starts and captures the user's facial image;

[0014] The collected color image is converted into a grayscale image through grayscale processing, and the face area is detected using the MTCNN algorithm to obtain the bounding box and crop the face image;

[0015] Using the key points of the face, affine transformation is performed to adjust the face to a standardized posture, and pixel normalization is performed on the aligned face image;

[0016] Adjust the normalized face image size to a fixed size to obtain the standardized face image matrix X, which is expressed as:

[0017]

[0018] Among them, Resize represents the image size adjustment function, represents the normalized face image matrix, represents the size of the target image, represents the height of the image, and ω represents the width of the image;

[0019] A lightweight algorithm is used to extract facial feature vectors from the standardized face image matrix X, and the expression is:

[0020]

[0021] Among them, F is the extracted facial feature vector of the current user, Represents the parameter matrix connecting two layers of the neural network, X is the standardized face image matrix, Δ is the convolution kernel matrix, B is the bias vector, ReLU is the activation function, and σ is the normalization function;

[0022] Based on the cosine similarity formula, the extracted current user facial feature vector F is matched one by one with the set of user facial feature vectors pre-stored in the local database. The expression is:

[0023] D={F1,F2,…,Fn};

[0024]

[0025] Among them, S represents the similarity score between feature vectors, F i represents the eigenvalue of the i-th dimension of the current user's facial feature vector F, D i represents the eigenvalue of the i-th dimension of a certain user facial feature vector D pre-stored in the local database, k is the dimension of the feature vector, and n represents the number of user facial feature vectors pre-stored in the set D;

[0026] Set the matching threshold to θ;

[0027] When S≥θ, it is determined that the user identity authentication is successful and proceed to the next step;

[0028] When S<θ, it is determined that the user identity authentication fails, and the account and password are entered for verification.

[0029] As a preferred solution of the charging pile intelligent control method based on face recognition of the present invention, the charging authority bound to the user is allocated based on the verified user identity information, and the relationship between the user and the vehicle is verified at the same time. The charging plan is dynamically generated in combination with the user's historical charging preference information and the initial charging data. The specific steps are as follows:

[0030] When the user identity authentication is passed, the user's binding information is queried from the local database;

[0031] The binding information is user account information, user-bound vehicle information, and user charging authority;

[0032] Allocate charging permissions based on binding information;

[0033] According to the vehicle information bound by the user, match and verify with the current vehicle information. If the user binds multiple vehicles, match the current vehicle through license plate recognition;

[0034] After confirming the binding relationship between the user and the vehicle, the connection status between the vehicle and the charging pile is verified through the ISO 15118 standard, the communication protocol between the vehicle and the charging pile;

[0035] Extracting historical charging preference information of the user, wherein the historical charging preference information of the user is charging time period, charging power and charging duration;

[0036] The user's historical charging preference feature vector H is obtained through weighted analysis, and the expression is:

[0037] H=[T w ,P w ,Z w ];

[0038] Among them, T w The weight of the user's charging period, P w is the user's weight on charging power, Z w The weight of the user's charging time;

[0039] Collecting initial charging data, wherein the initial charging data includes battery data, charging pile data, ambient temperature data and time data;

[0040] According to the charging energy required to reach the target power from the current power and the current charging power, the remaining charging time is calculated as follows:

[0041]

[0042] Among them, T rem Indicates the remaining charging time, P chg Indicates the current charging power, SOC tgt Indicates the target battery power percentage, SOC init Indicates the current battery power percentage, C bat Indicates the battery capacity;

[0043] Through the historical charging preference feature vector H and the initial charging data, the user's personalized needs are dynamically adjusted, the charging plan is generated, and the optimal charging plan is selected. The expression is:

[0044]

[0045] Among them, C opt represents the optimal solution, P max Indicates the maximum output power of the charging pile, T env represents the ambient temperature, f(T env ) represents the ambient temperature correction function, T max Indicates the maximum charging time acceptable to the user.

[0046] As a preferred solution of the intelligent control method of charging pile based on face recognition of the present invention, wherein: charging is started according to the charging scheme, and the charging parameters are dynamically adjusted by real-time monitoring of the real-time charging data during the charging process, and the specific steps are:

[0047] After starting charging, real-time monitoring of the current charging process's real-time power data, real-time battery temperature data, and real-time ambient temperature data;

[0048] According to the real-time charging data monitored, a dynamic power optimization adjustment formula is constructed, and the expression is:

[0049]

[0050] Among them, P adj Indicates the charging power after real-time adjustment, P real represents the real-time output power of the charging pile, α represents the attenuation factor when the power is close to the target, β represents the sensitivity coefficient of the power difference, SOC real represents the real-time battery power percentage, γ represents the ambient temperature factor, T real Indicates the real-time ambient temperature value, T opt Indicates the optimal operating temperature of the battery design;

[0051] When P min ≤P adj ≤P max When the charging power is adjusted in real time, the charging continues;

[0052] When P adj ≤P min When the battery is charged, it stops charging and prompts the user to check.

[0053] As a preferred solution of the charging pile intelligent control method based on face recognition of the present invention, the specific steps are as follows: judging whether charging is completed and automatically calculating the charging fee according to the monitoring results, and storing the charging record in the user account.

[0054] According to the charging data monitored in real time during the charging process, the allowable power error value is set to ∈;

[0055] When SOC tgt -SOC real >∈, it is considered that the current battery power percentage of the vehicle has not reached the target battery power percentage, and charging is determined to be incomplete, so charging continues until SOC tgt -SOC real When ≤∈, the charging fee is automatically calculated;

[0056] When SOC tgt -SOC realWhen ≤∈, the vehicle is considered to have reached the target battery percentage, charging is considered complete, and the charging fee is automatically calculated;

[0057] After the fee calculation is completed, a detailed charging record report is provided and stored in the user account.

[0058] In a second aspect, the present invention provides a charging pile intelligent control system based on face recognition, including an identity recognition module, a binding verification module, a charging scheme module, a dynamic adjustment module and a settlement storage module:

[0059] The identity recognition module is used to verify the user's identity through face recognition, ensure that legitimate users use the charging pile, and use a lightweight algorithm to extract the user's facial feature vector to determine the legitimacy of the user's identity;

[0060] The binding verification module is used to verify the relationship between the user and the bound vehicle, ensuring that the charging permission is only open to the bound vehicle, preventing the use of other people's vehicles for charging, and ensuring charging safety;

[0061] The charging solution module dynamically generates the optimal charging solution based on the user's historical charging preferences and initial charging data to meet the user's personalized needs and improve charging efficiency;

[0062] The dynamic adjustment module is used to monitor charging data in real time and dynamically adjust charging parameters to ensure the safety and efficiency of the charging process;

[0063] The settlement storage module is used to determine the charging completion status, automatically calculate the charging fee, and store the charging record in the user account for subsequent query and management.

[0064] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the charging pile intelligent control method based on face recognition as described in the first aspect of the present invention is implemented.

[0065] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the charging pile intelligent control method based on face recognition as described in the first aspect of the present invention is implemented.

[0066] The beneficial effects of the present invention are as follows: the present invention significantly improves the intelligence level and user experience of the charging pile system by introducing face recognition technology, generating personalized charging plans and dynamically adjusting real-time charging parameters. In terms of identity authentication, a lightweight algorithm is combined with a local database to achieve efficient and secure user identity recognition, avoiding the cumbersome operations and safety hazards of traditional verification methods; in charging plan formulation, a personalized plan is dynamically generated in combination with the user's historical charging preferences and real-time battery data to meet the diverse needs of users, while optimizing charging efficiency and reducing battery loss; in the charging process, the charging safety and adaptability are improved by real-time monitoring of the charging status and dynamic adjustment of charging parameters; in the cost settlement and record storage links, automated calculation and local storage methods not only improve the convenience of operation, but also effectively protect user privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0068] Figure 1 This is a flow chart of the intelligent control method of a charging pile based on face recognition in Example 1.

[0069] Figure 2 This is a schematic diagram of the charging pile intelligent control system based on face recognition in Example 1. DETAILED DESCRIPTION

[0070] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0071] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0072] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0073] Example 1, reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides a charging pile intelligent control method based on face recognition, comprising the following steps:

[0074] When the S1 user approaches the charging pile, the user's facial image is collected through the camera, and the user's facial feature vector is extracted using a lightweight algorithm. It is then matched with the user's facial feature vector pre-stored in the local database to verify the user's identity information;

[0075] The charging pile is equipped with a high-resolution camera. When the user approaches the charging pile, the charging pile camera automatically starts and captures the user's facial image;

[0076] The collected color image is converted into a grayscale image through grayscale processing, and the face area is detected using the MTCNN algorithm to obtain the bounding box and crop the face image;

[0077] Using the key points of the face (eyes, nose tip, corners of the mouth), perform affine transformation, adjust the face to a standardized posture, and perform pixel normalization on the aligned face image;

[0078] Adjust the normalized face image size to a fixed size to obtain the standardized face image matrix X, which is expressed as:

[0079]

[0080] Among them, Resize represents the image size adjustment function, represents the normalized face image matrix, represents the size of the target image, represents the height of the image, and ω represents the width of the image;

[0081] Image preprocessing is an important step to ensure the reliability of recognition. Through the steps of grayscale conversion, MTCNN algorithm detection and normalization, the accuracy of subsequent feature extraction and matching can be significantly improved, and the influence of interference factors such as ambient lighting and angle can be reduced;

[0082] A lightweight algorithm is used to extract facial feature vectors from the standardized face image matrix X, and the expression is:

[0083]

[0084] Among them, F is the extracted facial feature vector of the current user, Represents the parameter matrix connecting two layers of the neural network, X is the normalized face image matrix, Δ is the convolution kernel matrix, extracts local features, B is the bias vector, ReLU is the activation function, and σ is the normalization function;

[0085] The value range of F is [0,1], which represents the normalized range of facial feature values;

[0086] The lightweight model was chosen to achieve efficient operation in embedded devices. It has lower computational and storage requirements than traditional large models and is suitable for resource-constrained environments.

[0087] Based on the cosine similarity formula, the extracted current user facial feature vector F is matched one by one with the set of user facial feature vectors pre-stored in the local database. The expression is:

[0088] D={F1,F2,…,Fn};

[0089]

[0090] Among them, S represents the similarity score between feature vectors, F i represents the eigenvalue of the i-th dimension of the current user's facial feature vector F, D i represents the eigenvalue of the i-th dimension of a certain user facial feature vector D pre-stored in the local database, k is the dimension of the feature vector, and n represents the number of user facial feature vectors pre-stored in the set D;

[0091] Cosine similarity is a commonly used high-dimensional feature matching method. It is simple to calculate and can effectively measure the similarity between features after the feature vector is normalized, avoiding matching deviations caused by differences in vector lengths.

[0092] Local storage of user feature data reduces the risk of information leakage, reduces the degree of dependence on the network, and enhances data security;

[0093] The matching threshold is set to θ, and the threshold of the present invention is set to 0.8;

[0094] When S≥θ, it is determined that the user identity authentication is successful and proceed to the next step;

[0095] When S<θ, it is determined that the user identity authentication fails, and the account and password are entered for verification.

[0096] Through accurate facial recognition technology, it ensures that only authorized users can use the charging pile, avoiding illegal use or theft, shortening the authentication time, eliminating the trouble of entering passwords, and users can quickly complete identity authentication.

[0097] S2 assigns charging permissions to the user based on the verified user identity information, verifies the relationship between the user and the vehicle, and dynamically generates a charging plan based on the user's historical charging preference information and initial charging data;

[0098] When the user identity authentication is passed, the user's binding information is queried from the local database;

[0099] The binding information is the user account information (unique identity), the vehicle information bound to the user (vehicle identification code), and the user's charging permissions (allowed charging power range and whether fast charging is allowed);

[0100] Assign charging permissions based on binding information (if the user has special charging limits, permissions are updated based on predefined rules);

[0101] According to the vehicle information bound by the user, match and verify with the current vehicle information (to ensure that the vehicle belongs to the current user, to avoid misusing other people's vehicles or impersonating charging permissions). If the user binds multiple vehicles, the current vehicle is matched through license plate recognition;

[0102] After confirming the binding relationship between the user and the vehicle, the connection status between the vehicle and the charging pile is verified through the ISO 15118 standard, the communication protocol between the vehicle and the charging pile;

[0103] Verify the binding relationship between users and vehicles, prevent illegal vehicle access, protect charging rights, and ensure the connection between vehicles and charging piles is safe and compatible with a variety of models through standardized communication of ISO 15118 protocol;

[0104] Automatically match the current vehicle when binding multiple vehicles, reducing the trouble of manual selection for users, supporting the multi-vehicle binding needs of home users and public scenarios, improving the flexibility of the system, preventing others from stealing user accounts to bind vehicles for charging, and further optimizing the user charging experience;

[0105] Extract the user's historical charging preference information, which includes charging time (e.g., charging frequency is higher at night), charging power (ratio of fast charging or slow charging), and charging time (e.g., some users prefer to fully charge, while some users prefer to charge to 80%). Use user data to extract preference feature vectors and accurately analyze user charging habits.

[0106] The user's historical charging preference feature vector H is obtained through weighted analysis, and the expression is:

[0107] H=[T w ,P w ,Z w ];

[0108] Among them, T w The weight of the user's charging period, P w is the user's weight on charging power, Z w The weight of the user's charging time;

[0109] T w Based on the frequency distribution calculation of user charging time, P w According to the time proportion of fast charging and slow charging mode, Z wThe average SOC percentage at the end of each charge is calculated based on the user's charging completion goal (such as 80% or full) to adjust the weight;

[0110] Collect initial charging data, which includes battery data (current power, target power, total battery capacity), charging pile data (current charging power, maximum charging power and minimum charging power of the charging pile), ambient temperature data and time data (maximum charging time acceptable to users);

[0111] According to the charging energy required to reach the target power from the current power and the current charging power, the remaining charging time is calculated as follows:

[0112]

[0113] Among them, T rem Indicates the remaining charging time (the time required to charge from the current power to the target power), P chg Indicates the current charging power, SOC tgt Indicates the target battery power percentage (the user sets the target power to be charged), SOC init Indicates the current battery power percentage (the ratio of the vehicle's current remaining battery power to the total battery capacity), C bat Indicates the battery capacity;

[0114] Through the historical charging preference feature vector H and the initial charging data, the user's personalized needs are dynamically adjusted, the charging plan is generated, and the optimal charging plan is selected. The expression is:

[0115]

[0116] Among them, C opt represents the optimal solution, P max Indicates the maximum output power of the charging pile, T env represents the ambient temperature, f(T env ) represents the ambient temperature correction function, T max Indicates the maximum charging time acceptable to the user;

[0117] This formula is composed of three weight terms (T w ,P w ,Z w ), combining power demand, charging efficiency, ambient temperature and charging time, dynamically calculates the score of the charging plan, and selects the optimal charging plan C that best meets user needs by maximizing the formula score opt ;

[0118] Through comprehensive analysis of historical preferences and real-time data, the dynamically generated charging plan fully considers the user's charging habits (fast charging / slow charging, target power, charging time, etc.), making the charging process more in line with user needs;

[0119] Optimize the charging plan based on the target power and current battery status to avoid overcharging or long charging time, thus improving user time utilization;

[0120] Combined with the maximum power and ambient temperature data of the charging pile, it ensures the balanced utilization of charging pile resources, alleviates the pressure of peak electricity consumption, avoids battery loss caused by excessively high / low temperatures, extends battery life, reduces resource waste, reduces charging electricity costs, and promotes the green and sustainable development of charging piles.

[0121] S3 starts charging according to the charging plan and dynamically adjusts the charging parameters by monitoring the real-time charging data during the charging process;

[0122] After starting charging, real-time monitoring of the current charging process's real-time power data, real-time battery temperature data, and real-time ambient temperature data;

[0123] According to the real-time charging data monitored, a dynamic power optimization adjustment formula is constructed, and the expression is:

[0124]

[0125] Among them, P adj Indicates the charging power after real-time adjustment, P real represents the real-time output power of the charging pile, α represents the attenuation factor when the power is close to the target, β represents the sensitivity coefficient of the power difference, SOC real represents the real-time battery power percentage, γ represents the ambient temperature factor, T real Indicates the real-time ambient temperature value, T opt Indicates the optimal operating temperature of the battery design (determined based on the battery manufacturer's recommendations and safe operating range);

[0126] When P min ≤P adj ≤P max When the charging power is adjusted in real time, the charging continues;

[0127] When P adj ≤P min When the battery is low, charging stops and the user is prompted to check.

[0128] Monitor the battery status in real time and dynamically adjust the charging power to effectively avoid battery safety issues caused by overcharging or excessive temperature. By gradually reducing the power to approach the target power, the pressure on the battery when it is fully charged due to high current is reduced, extending the battery life. Dynamic power adjustment ensures that the charging process is always in the best state and reduces unnecessary energy waste.

[0129] S4 determines whether charging is completed and automatically calculates the charging fee based on the monitoring results, and stores the charging record in the user account.

[0130] According to the charging data monitored in real time during the charging process, the allowable power error value is set to ∈, and the allowable power error value of the present invention is set to 0.01;

[0131] When SOC tgt -SOC real >∈, it is considered that the current battery power percentage of the vehicle has not reached the target battery power percentage, and charging is determined to be incomplete, so charging continues until SOC tgt -SOC real When ≤∈, the charging fee is automatically calculated;

[0132] When SOC tgt -SOC real When ≤∈, the vehicle is considered to have reached the target battery percentage, charging is considered complete, and the charging fee is automatically calculated;

[0133] After the fee calculation is completed, a detailed charging record report is provided and stored in the user account;

[0134] Automatically complete charging completion judgment and fee calculation without manual intervention by the user, reducing operation time and improving convenience;

[0135] Provide detailed charging reports to avoid users' concerns about charging costs and increase user trust. Historical charging records are stored for easy user query and provide data support for subsequent charging preference analysis.

[0136] This embodiment also provides a charging pile intelligent control system based on face recognition, including: an identity recognition module, a binding verification module, a charging scheme module, a dynamic adjustment module and a settlement storage module:

[0137] The identity recognition module is used to verify the user's identity through face recognition to ensure that legitimate users use the charging pile. It uses a lightweight algorithm to extract the user's facial feature vector and determine the legitimacy of the user's identity.

[0138] The binding verification module is used to verify the relationship between the user and the bound vehicle, ensuring that charging permissions are only open to bound vehicles, preventing the use of other people's vehicles for charging, and ensuring charging safety;

[0139] The charging plan module combines the user's historical charging preferences and initial charging data to dynamically generate the optimal charging plan to meet the user's personalized needs and improve charging efficiency;

[0140] Dynamic adjustment module, used to monitor charging data in real time and dynamically adjust charging parameters to ensure the safety and efficiency of the charging process;

[0141] The settlement storage module is used to determine the charging completion status, automatically calculate the charging fee, and store the charging record in the user account for subsequent query and management.

[0142] This embodiment also provides a computer device, which is suitable for the case of an intelligent control method for a charging pile based on face recognition, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent control method for a charging pile based on face recognition as proposed in the above embodiment.

[0143] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0144] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by the processor, the intelligent control method of the charging pile based on face recognition proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0145] In summary, the present invention significantly improves the intelligence level and user experience of the charging pile system by: introducing face recognition technology, generating personalized charging plans, and dynamically adjusting real-time charging parameters. In terms of identity authentication, a lightweight algorithm is combined with a local database to achieve efficient and secure user identity recognition, avoiding the cumbersome operations and safety hazards of traditional verification methods; in charging plan formulation, a personalized plan is dynamically generated in combination with the user's historical charging preferences and real-time battery data to meet the diverse needs of users, while optimizing charging efficiency and reducing battery loss; in the charging process, the charging safety and adaptability are improved by real-time monitoring of the charging status and dynamic adjustment of charging parameters; in the cost settlement and record storage links, automated calculation and local storage methods not only improve the convenience of operation, but also effectively protect user privacy.

[0146] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A charging pile intelligent control method based on face recognition, characterized in that: include, When a user approaches a charging station, the camera collects the user's facial image, uses a lightweight algorithm to extract the user's facial feature vector, and matches it with the user's facial feature vector pre-stored in the local database to verify the user's identity information; Based on the verified user identity information, the charging permission bound to the user is assigned, and the relationship between the user and the vehicle is verified. The charging plan is dynamically generated by combining the user's historical charging preference information and initial charging data; Start charging according to the charging plan, and dynamically adjust the charging parameters by monitoring the real-time charging data during the charging process; Based on the monitoring results, it determines whether charging is completed and automatically calculates the charging fee, and stores the charging record in the user account.

2. The charging pile intelligent control method based on face recognition according to claim 1, characterized in that: When the user approaches the charging pile, the camera collects the user's facial image. The specific steps are as follows: The charging pile is equipped with a high-resolution camera. When the user approaches the charging pile, the charging pile camera automatically starts and captures the user's facial image; The collected color image is converted into a grayscale image through grayscale processing, and the face area is detected using the MTCNN algorithm to obtain the bounding box and crop the face image; Using the key points of the face, affine transformation is performed to adjust the face to a standardized posture, and pixel normalization is performed on the aligned face image; Adjust the normalized face image size to a fixed size to obtain the standardized face image matrix X, which is expressed as: Among them, Resize represents the image size adjustment function, represents the normalized face image matrix, represents the size of the target image, represents the height of the image, and ω represents the width of the image.

3. The charging pile intelligent control method based on face recognition as claimed in claim 2, characterized in that: The method uses a lightweight algorithm to extract the user's facial feature vector, and matches it with the user's facial feature vector pre-stored in the local database to verify the user's identity information. The specific steps are: A lightweight algorithm is used to extract facial feature vectors from the standardized face image matrix X, and the expression is: Among them, F is the extracted facial feature vector of the current user, Represents the parameter matrix connecting two layers of the neural network, X is the standardized face image matrix, Δ is the convolution kernel matrix, B is the bias vector, ReLU is the activation function, and σ is the normalization function; Based on the cosine similarity formula, the extracted current user facial feature vector F is matched one by one with the set of user facial feature vectors pre-stored in the local database. The expression is: D={F1,F2,…,Fn}; Among them, S represents the similarity score between feature vectors, F i represents the eigenvalue of the i-th dimension of the current user's facial feature vector F, D i represents the eigenvalue of the i-th dimension of a certain user facial feature vector D pre-stored in the local database, k is the dimension of the feature vector, and n represents the number of user facial feature vectors pre-stored in the set D; Set the matching threshold to θ; When S≥θ, it is determined that the user identity authentication is successful and proceed to the next step; When S<θ, it is determined that the user identity authentication fails, and the account and password are entered for verification.

4. The charging pile intelligent control method based on face recognition as claimed in claim 3, characterized in that: Based on the verified user identity information, the charging authority bound to the user is allocated, and the relationship between the user and the vehicle is verified. The specific steps are: When the user identity authentication is passed, the user's binding information is queried from the local database; The binding information is user account information, user-bound vehicle information, and user charging authority; Allocate charging permissions based on binding information; According to the vehicle information bound by the user, match and verify with the current vehicle information. If the user binds multiple vehicles, match the current vehicle through license plate recognition; After confirming the binding relationship between the user and the vehicle, the connection status between the vehicle and the charging pile is verified through the ISO 15118 standard, the communication protocol between the vehicle and the charging pile.

5. The charging pile intelligent control method based on face recognition as claimed in claim 4, characterized in that: The specific steps of dynamically generating a charging plan by combining the user's historical charging preference information and the initial charging data are as follows: Extracting historical charging preference information of the user, wherein the historical charging preference information of the user is charging time period, charging power and charging duration; The user's historical charging preference feature vector H is obtained through weighted analysis, and the expression is: H=[T w ,P w ,Z w ]; Among them, T w The weight of the user's charging period, P w is the user's weight on charging power, Z w The weight of the user's charging time; Collecting initial charging data, wherein the initial charging data includes battery data, charging pile data, ambient temperature data and time data; According to the charging energy required to reach the target power from the current power and the current charging power, the remaining charging time is calculated as follows: Among them, T rem Indicates the remaining charging time, P chg Indicates the current charging power, SOC tgt Indicates the target battery power percentage, SOC init Indicates the current battery power percentage, C bat Indicates battery capacity; Through the historical charging preference feature vector H and the initial charging data, the user's personalized needs are dynamically adjusted, the charging plan is generated, and the optimal charging plan is selected. The expression is: Among them, C opt represents the optimal solution, P max Indicates the maximum output power of the charging pile, T env represents the ambient temperature, f(T env ) represents the ambient temperature correction function, T max Indicates the maximum charging time acceptable to the user.

6. The charging pile intelligent control method based on face recognition as claimed in claim 5, characterized in that: The charging is started according to the charging scheme, and the charging parameters are dynamically adjusted by real-time monitoring of the real-time charging data during the charging process. The specific steps are as follows: After starting charging, real-time monitoring of the current charging process's real-time power data, real-time battery temperature data, and real-time ambient temperature data; According to the real-time charging data monitored, a dynamic power optimization adjustment formula is constructed, and the expression is: Among them, P adj Indicates the charging power after real-time adjustment, P real represents the real-time output power of the charging pile, α represents the attenuation factor when the power is close to the target, β represents the sensitivity coefficient of the power difference, SOC real represents the real-time battery power percentage, γ represents the ambient temperature factor, T real Indicates the real-time ambient temperature value, T opt Indicates the optimal operating temperature of the battery design; When P min ≤P adj ≤P max When the charging power is adjusted in real time, the charging continues; When P adj ≤P min When the battery is charged, it stops charging and prompts the user to check.

7. The charging pile intelligent control method based on face recognition according to claim 6, characterized in that: The specific steps of judging whether charging is completed and automatically calculating charging fees based on the monitoring results and storing the charging records in the user account are as follows: According to the charging data monitored in real time during the charging process, the allowable power error value is set to ∈; When SOC tgt -SOC real >∈, it is considered that the current battery power percentage of the vehicle has not reached the target battery power percentage, and charging is determined to be incomplete, so charging continues until SOC tgt -SOC real When ≤∈, the charging fee is automatically calculated; When SOC tgt -SOC real When ≤∈, the vehicle is considered to have reached the target battery percentage, charging is considered complete, and the charging fee is automatically calculated; After the fee calculation is completed, a detailed charging record report is provided and stored in the user account.

8. A charging pile intelligent control system based on face recognition, based on the charging pile intelligent control method based on face recognition according to any one of claims 1 to 7, characterized in that: Including identity recognition module, binding verification module, charging plan module, dynamic adjustment module and settlement storage module: The identity recognition module is used to verify the user's identity through face recognition, ensure that legitimate users use the charging pile, and use a lightweight algorithm to extract the user's facial feature vector to determine the legitimacy of the user's identity; The binding verification module is used to verify the relationship between the user and the bound vehicle, ensuring that the charging permission is only open to the bound vehicle, preventing the use of other people's vehicles for charging, and ensuring charging safety; The charging solution module dynamically generates the optimal charging solution based on the user's historical charging preferences and initial charging data to meet the user's personalized needs and improve charging efficiency; The dynamic adjustment module is used to monitor charging data in real time and dynamically adjust charging parameters to ensure the safety and efficiency of the charging process; The settlement storage module is used to determine the charging completion status, automatically calculate the charging fee, and store the charging record in the user account for subsequent query and management.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the charging pile intelligent control method based on face recognition described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the charging pile intelligent control method based on face recognition described in any one of claims 1 to 7 are implemented.

Images