Artificial intelligence-based electric vehicle battery remaining value certification system and method

Abstract

The present invention relates to a battery remaining value certification system, which may comprise: a real-time data collection unit for collecting real-time operation data of a vehicle; a database in which the collected real-time operation data is stored; a data analysis unit for analyzing the stored real-time operation data in a batch form whenever the real-time operation data stored in the database reaches a predetermined level; a training data generation unit for generating training data to be applied to an artificial intelligence model from the data analyzed in the batch form; a driving habit analysis unit for deriving driving habits of a driver of the vehicle by applying the training data to the artificial intelligence model; and a prediction unit for predicting the remaining value of the battery by analyzing the driving habits.

Description

AI-based electric vehicle battery residual value authentication system and method

[0001] The present invention relates to an artificial intelligence-based electric vehicle battery residual value certification system and an evaluation method using the same.

[0002] The following explanations are intended to assist in understanding the technical significance of the invention and do not presuppose prior public disclosure. Therefore, even if they are included in the background technology of the invention, they should not be considered publicly known technology in and of themselves.

[0003] Electric vehicle batteries are a core component of electric vehicles, and their condition significantly impacts the overall value of the vehicle. Existing battery assessment systems rely solely on simple statistical analysis, manually collecting driving data and battery usage information to assess battery condition. This increases uncertainty surrounding the residual value of batteries, potentially leading to a lack of trust between transaction parties and inefficiencies. Therefore, the need for a system that objectively and standardically scores battery condition and issues a certificate based on this score is emerging. Such a certificate would provide clear and consistent information about battery condition, facilitating more transparent and smooth transactions for used electric vehicles. Building trust between transaction parties through an accredited certificate and laying the foundation for stimulating the growth of the used electric vehicle market is emerging as a critical challenge.

[0004] The purpose of the present invention is to provide an artificial intelligence-based electric vehicle battery residual value authentication system and method.

[0005] In addition, the present invention aims to issue a certificate after applying data on each factor influencing the residual value of an electric vehicle battery.

[0006] However, the technical task that this embodiment seeks to achieve is not limited to the technical task described above, and other technical tasks may exist.

[0007] In order to achieve the above-described purpose, a battery residual value authentication system according to one embodiment of the present invention may include a real-time data collection unit that collects real-time driving data based on the driving habits of a vehicle driver, a database that stores the collected real-time driving data, a data analysis unit that analyzes the stored real-time driving data in batch form whenever the real-time driving data stored in the database reaches a certain level, a learning data generation unit that generates learning data for application to an artificial intelligence model from the data analyzed in batch form, an artificial intelligence analysis unit that analyzes the learning data using an artificial intelligence model, an analysis result provision unit that provides an analysis result of the artificial intelligence analysis unit, and a battery residual value certificate issuance unit that issues a certificate of the battery residual value based on the analysis result.

[0008] According to one embodiment, real-time driving data based on the driving habits of the vehicle driver may include data related to voltage difference between battery cells during driving, temperature difference between battery modules during driving, number of cells below or above a reference voltage, number of rapid decelerations or rapid accelerations, and battery charge and discharge rates.

[0009] According to one embodiment, the artificial intelligence analysis unit can receive battery value assessment data and determine the remaining value of the battery based on the data.

[0010] According to one embodiment, the prediction unit can predict the stability of the battery by analyzing driving habits.

[0011] According to one embodiment, the artificial intelligence model may use at least one of an STM and a Transformer model.

[0012] According to one embodiment, the analysis result provider can grade the battery residual value and provide the main evaluation basis.

[0013] According to one embodiment, the battery residual value certificate issuing unit can receive battery value assessment data provided by the artificial intelligence analysis unit and determine the current residual value of the battery based on the data.

[0014] According to one embodiment, the residual value of a battery can be evaluated based on the battery's state of charge (SOC), remaining useful life, charge / discharge efficiency, and performance degradation due to temperature changes.

[0015] According to one embodiment, a certificate of battery residual value includes evaluation criteria, an evaluation number, an evaluation formula, and an evaluation result, and the evaluation criteria are composed of a major category, a minor category, and a mid-category, and the major category includes items consisting of remaining life, stability, and usability, and the remaining life is evaluated based on an estimated SOH and a driving range factor, and the stability is evaluated based on a cell voltage difference during operation, a module temperature difference during operation, a cell voltage difference during charging, under voltage, and over voltage, and the usability can be evaluated based on the number of sudden deceleration accelerations, battery management temperature, and C-rate. Each evaluation result based on the estimated SOH, the driving range factor, the cell voltage difference during operation, the module temperature difference during operation, the cell voltage difference during charging, under voltage, over voltage, the number of sudden deceleration accelerations, battery management temperature, and C-rate is scored, and the final evaluation result can be expressed as a final score and a grade.

[0016] According to one embodiment, the certificate of battery residual value may indicate an evaluation result score and grade by scoring the remaining life, stability, and usability according to the vehicle.

[0017] A battery residual value authentication method according to another embodiment of the present invention may include a step of collecting real-time driving data based on a driving habit of a vehicle driver, a step of storing the collected real-time driving data in a database, a step of analyzing the stored real-time driving data in a batch form whenever the real-time driving data stored in the database reaches a certain level, a step of generating learning data for application to an artificial intelligence model from the data analyzed in the batch form, a step of analyzing the learning data using an artificial intelligence model, a step of providing an artificial intelligence analysis result, and a step of issuing a certificate of the battery residual value based on the analysis result.

[0018] According to the present invention, an artificial intelligence-based electric vehicle battery residual value authentication system and method can be provided.

[0019] In addition, the present invention can issue a certificate for the residual value of an electric vehicle battery after applying data on each influencing factor for the residual value of an electric vehicle battery.

[0020] FIG. 1 is a schematic diagram illustrating a battery remaining value authentication system according to one embodiment of the present invention.

[0021] Figure 2 is an example drawing showing a battery residual value certification report.

[0022] Figure 3 is a diagram showing another example of a battery residual value certificate.

[0023] FIG. 4 is a flowchart illustrating a battery residual value authentication method performed by a battery residual value authentication system according to one embodiment of the present invention.

[0024] FIG. 5 is a conceptual diagram illustrating a computing device that performs a battery remaining value authentication method according to one embodiment of the present invention.

[0025] Below, with reference to the attached drawings, embodiments of the present invention are described in detail so that those skilled in the art can easily implement them. The present invention is susceptible to various modifications and embodiments, and specific embodiments are illustrated in the drawings and specifically described in the detailed description. However, this is not intended to limit the present invention to specific embodiments, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and scope of the present invention.

[0026] To clearly explain the present invention, parts irrelevant to the description have been omitted from the drawings, and similar parts have been designated with similar drawing reference numerals throughout the specification. In addition, when describing with reference to the drawings, even if components are indicated by the same name, the drawing numbers may vary depending on the drawing. The drawing numbers are described merely for the convenience of explanation, and the concept, feature, function, or effect of each component is not limited by the drawing numbers.

[0027] In describing each drawing, similar reference numerals are used to refer to similar components. Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by these terms. These terms are used only to distinguish one component from another. For example, without departing from the scope of the present invention, a first component could be referred to as a second component, and similarly, a second component could also be referred to as a first component. The term "and / or" includes any combination of multiple related items described or any item among multiple related items described.

[0028] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

[0029] Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense unless expressly defined in this application.

[0030] Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected" but also the case where it is "electrically connected" with another element in between. Furthermore, when a part is said to "include" a component, this should be understood to mean that it may include other components rather than excluding other components unless specifically stated to the contrary, and does not preclude the presence or possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0031] Hereinafter, a battery residual value authentication system and method according to the present invention will be described with reference to the attached drawings.

[0032] FIG. 1 is a schematic diagram illustrating a battery residual value authentication system according to the present invention.

[0033] Referring to FIG. 1, a battery remaining value authentication system (100) according to the present invention includes a vehicle (110) and a computing device (120). The vehicle (110) may include a real-time data collection unit (111), a database (112), a battery (113), and a battery control device (114), and the computing device (120) may include a data analysis unit (121), a learning data generation unit (122), an artificial intelligence analysis unit (123), an analysis result provision unit (124), and an improvement plan provision unit (125).

[0034] The real-time data collection unit (111) can collect various driving data in real time through the OBD-2 module attached to the vehicle (110) based on the driver's driving habits. The collected data can provide essential information for comprehensively analyzing the vehicle's performance and battery status.

[0035] For example, speed data collected through the OBD-2 module can precisely track changes in speed while driving, and this data can be used to analyze a driver's driving patterns. The frequency of rapid acceleration or braking in specific sections reflects a driver's driving habits, which can be closely correlated with battery drain. Driving styles that frequently involve rapid acceleration can accelerate battery energy consumption, and these habits have a significant impact on assessing the battery's remaining value.

[0036] Furthermore, engine condition data is essential for understanding the relationship between driving habits and battery efficiency. Information such as engine temperature, engine load, and fuel consumption provide insight into how the driver operates the vehicle, which can directly impact the battery's charging and discharging efficiency. High engine load and fuel consumption can cause additional energy consumption from the battery, which can lead to reduced battery performance in the long term.

[0037] Battery state of charge (SOC) is another important data point in driving behavior analysis. The battery state of charge, monitored in real time via the OBD-2 module, can vary depending on the driver's driving patterns. For example, sustained high-speed driving or frequent rapid acceleration can rapidly deplete the battery's SOC, which is a key variable in assessing the battery's remaining value.

[0038] Mileage data plays a crucial role in understanding driving habits. Mileage includes not only accumulated mileage but also the distance traveled during specific driving sessions, which directly correlates with battery usage patterns. The frequency of long and short trips can have different effects on the battery, and this data is useful for assessing battery usage history.

[0039] Furthermore, the frequency of rapid acceleration and braking directly reflects a driver's driving habits, making it crucial for analyzing their relationship with battery performance degradation. Drivers who frequently accelerate and brake rapidly typically experience faster battery performance degradation, which can negatively impact battery life and residual value. This behavioral data plays a crucial role in establishing optimal charge and discharge strategies in battery management systems.

[0040] Additionally, other sensor data can be used to collect information such as outside temperature, battery temperature, and driving mode. Outside temperature and battery temperature significantly impact battery performance, and driving in extreme temperatures can reduce battery efficiency. Furthermore, driving modes (e.g., Eco mode, Sport mode) are linked to the driver's driving style, and this data can provide valuable insights into battery consumption and performance degradation.

[0041] Data collected through the real-time data collection unit (111) can be organized by various items, such as driving time, driving distance, battery charge / discharge cycles, engine status, speed, and the frequency of sudden acceleration and sudden braking, and stored in a database (112). For example, driving time data can record the start and end times of each driving session. Driving distance data can be used to track battery usage history and evaluate driving conditions related to battery consumption by recording not only the cumulative driving distance but also the driving distance during a specific driving session. Battery charge / discharge cycle data can be used to predict the remaining battery life and provide information for deriving efficient charging / discharging patterns by recording the number of battery charges and discharges, changes in the state of charge (SOC), and charging speed. Engine status data can be used to evaluate various factors affecting battery performance, including engine temperature, engine load, and fuel consumption. Speed ​​data can be used to record changes in speed during driving in real time, allowing for analysis of the correlation between driving patterns and battery consumption rates. Rapid acceleration and sudden braking frequency data can be used to evaluate a driver's driving habits.

[0042] The database (112) can be designed using a high-performance storage device and an optimized database management system (DBMS). For example, a non-volatile storage device such as flash memory can be used to store the vehicle's (110) operating data. The data stored in the database (112) is also linked to the battery (113) and battery control unit (114), enabling continuous updating and recording of data on the battery's status and performance.

[0043] Data collected within a vehicle (110) may be transmitted to a computing device (120) within or outside the vehicle (110) via a network (130). The network (130) may be implemented in a wired or wireless communication manner, and may generally be connected to the inside or outside via a communication module within the vehicle. The network (130) provides a data transmission path between the database (112) within the vehicle and the computing device (120), and a protocol may be used to safely and quickly transmit data during this process.

[0044] Data transmitted to the computing device (120) is first processed by the data analysis unit (121). The data analysis unit (121) can receive real-time operation data stored in the database (112) and analyze it in batch form. Batch analysis enables efficient analysis of large amounts of data by collecting data at regular time intervals and processing them in batches. Whenever a certain level of data is accumulated in the database (112), the data analysis unit (121) can process the data in batches to perform in-depth analysis.

[0045] The data analysis unit (121) can also perform tasks to remove data noise and errors. It filters sensor errors or data input errors that may occur during real-time data collection and generates refined data, thereby improving analysis accuracy.

[0046] The learning data generation unit (123) can generate learning data necessary for artificial intelligence model learning based on data analyzed in batch form by the data analysis unit (121). The learning data generation unit (123) refines the raw data analyzed in batch form, extracts necessary features, and ultimately constructs a data set optimized for artificial intelligence model learning.

[0047] The data collected by the real-time data collection unit (111) is extremely extensive and diverse in format. This includes various driving data such as vehicle speed, engine status, battery charge status, driving distance, frequency of sudden acceleration and sudden braking, external temperature, battery temperature, and driving mode. While this data can provide useful information on its own, it requires purification and processing for the artificial intelligence model to learn effectively. The learning data generation unit (123) converts this raw data into structured learning data.

[0048] First, the learning data generation unit (123) performs a cleaning process for the collected raw data. The data cleaning process includes procedures such as handling missing data, removing outliers, and reducing noise. For example, if some driving data is corrupted or incompletely collected, the learning data generation unit (123) supplements or removes this data, thereby minimizing any potential interference with the AI ​​model's learning.

[0049] Next, the learning data generation unit (123) extracts features important for learning the AI ​​model. Feature extraction is a crucial step that helps the model learn data more effectively. It extracts meaningful information from raw data and converts it into input variables necessary for learning. For example, to analyze the relationship between driving speed and battery consumption rate, the learning data generation unit (123) can extract driving speed fluctuation patterns as features and include them as part of the learning data. During this process, other related variables, such as driving distance, engine load, and battery temperature, can also be analyzed and selected as key features. Additionally, the learning data generation unit (123) structures the learning data based on the extracted features. This process includes converting each feature into an appropriate format and creating an environment in which the AI ​​model can learn stably through data normalization or standardization. For example, if the values ​​of each feature have different ranges, they can be adjusted to a uniform scale to increase the efficiency of model learning. The training data generated through this data preprocessing process is optimized for the AI ​​model to learn the relationship between specific driving habits and battery performance.

[0050] Additionally, the learning data generation unit (122) can perform the task of labeling the learning data. This is an essential step in supervised learning models, and is the process of assigning a correct answer for each data point (e.g., the impact of a specific driving pattern on battery life). The labeled learning data allows the AI ​​model to learn how to predict the corresponding output from the input data during learning. This process clearly defines the relationship between the driver's driving habits and the resulting changes in battery performance, and by organizing the learning data based on this, supports the model's ability to demonstrate predictive power in actual driving situations.

[0051] Finally, the learning data generation unit (122) can continuously monitor the quality of the learning data and provide functions to update or generate additional data as needed. For example, changes in the vehicle's operating environment or driver habits may necessitate new learning data. In this case, the learning data generation unit (122) can collect new data and support the continuous learning of the artificial intelligence model through the previously described purification, feature extraction, and preprocessing processes.

[0052] The artificial intelligence analysis unit (123) analyzes the remaining battery value based on the vehicle's driving habits based on data generated by the learning data generation unit (122), and predicts safety accordingly. The artificial intelligence analysis unit (123) utilizes advanced artificial intelligence algorithms to precisely model the complex interactions between driving habits and battery performance, thereby providing a function for predicting battery status and vehicle operational safety.

[0053] First, the AI ​​analysis unit (123) receives structured learning data provided by the learning data generation unit (122) as input. This learning data includes various driving data, such as the driver's driving habits, the vehicle's operating conditions, and the battery's state of charge and consumption patterns. This data can provide essential information for assessing the battery's residual value. The AI ​​analysis unit (123) uses this data to learn complex patterns, thereby enabling a precise analysis of the impact of the driver's driving habits on battery performance.

[0054] The artificial intelligence analysis unit (123) can model the relationship between driving habits and battery residual value by utilizing various machine learning and deep learning algorithms. For example, the artificial intelligence analysis unit (123) can process time-series data using a recurrent neural network (RNN)-based model, such as a Long Short-Term Memory (LSTM) network. The LSTM model can analyze a driver's driving patterns, such as the frequency of rapid acceleration, rapid braking, and changes in driving speed, and evaluate the long-term impact of these patterns on battery performance. In this process, the LSTM model can handle long-term data dependencies and identify the cumulative impact of each driving habit on the battery residual value.

[0055] Additionally, the artificial intelligence analysis unit (123) can analyze the complex correlation between driving habits and battery performance by utilizing advanced deep learning algorithms, such as the Transformer model. The Transformer model precisely analyzes the interactions between driving data using a self-attention mechanism, enabling it to clearly model the correlation between the battery's state of charge (SOC) and driving habits. The Transformer model efficiently analyzes large amounts of data through parallel processing, enabling it to predict changes in the battery's residual value in real time under various driving scenarios.

[0056] The AI ​​analysis unit (123) can also provide a function to evaluate battery safety based on data related to driving habits. Battery safety assessments can predict potential risks, such as battery overheating, excessive discharge, and unbalanced charging. The AI ​​analysis unit (123) can analyze the potential for battery damage that may occur if the driver continues to drive in a specific manner and, based on these analysis results, provide real-time warnings or suggest maintenance measures. For example, if a specific driving habit is likely to cause battery overheating, the AI ​​analysis unit (123) can detect this in advance, provide a warning to the driver, and, if necessary, send appropriate control signals to vehicle systems.

[0057] Additionally, the AI ​​analysis unit (123) can simulate various scenarios to predict the expected battery life and residual value. This contributes to optimizing battery management strategies by simulating changes in battery performance due to changes in the driver's driving habits.

[0058] The AI ​​analysis unit (123) can be linked to various interfaces that can intuitively convey battery residual value and safety prediction results to drivers or vehicle managers. For example, analysis results can be provided in real time via an in-vehicle display or mobile application, allowing drivers to check critical battery condition information at any time. Such features optimize vehicle maintenance plans and maximize battery performance.

[0059] The analysis results provider (124) converts the complex data generated by the AI ​​analysis provider (123) into a format that is easily understandable for the user. For example, it can provide a visual graph or table showing changes in the battery's remaining value, intuitively displaying the battery's current status, predicted lifespan, charging status, energy consumption rate, and other information. These visual tools help drivers understand the vehicle's condition at a glance and facilitate decision-making regarding vehicle maintenance.

[0060] Furthermore, the analysis result provider (124) can immediately update analysis results through a real-time data stream and provide real-time warnings of significant changes or abnormalities occurring during driving. If the battery temperature reaches a dangerous level or the battery's state of charge decreases, potentially threatening driving safety, an immediate warning is sent, allowing the driver to take appropriate action. The analysis result provider (124) can also be integrated with various platforms, such as in-vehicle displays, mobile applications, and remote management systems, and can provide analysis results through a user interface (UI) customized for each platform. The in-vehicle display provides simple and intuitive information to avoid visual distraction while driving, while the mobile application allows for more detailed analysis data.

[0061] The battery residual value certificate issuing unit (125) first receives battery residual value assessment data provided by the artificial intelligence analysis unit (123) and comprehensively reviews the current condition of the battery based on this data. This review process considers various battery performance indicators, including the battery's state of charge (SOC), remaining useful life, charge / discharge efficiency, and performance degradation due to temperature changes. These indicators are then combined to create a final assessment of the battery's residual value, which is then reflected in the certificate.

[0062] During the certificate issuance process, the battery residual value certificate issuing unit (125) applies standardized evaluation criteria to generate consistent and objective certificates. For example, if a battery's remaining capacity remains above a certain percentage of its manufacturing date, it may be given an "Excellent" rating, while a battery with a certain number of charge / discharge cycles or fewer may be given a "Good" rating. This rating system clearly indicates the condition of a vehicle's battery and provides reliable information to buyers when reselling the vehicle.

[0063] Additionally, the battery residual value certificate issuing unit (125) can include not only the battery condition at the time of certificate issuance, but also predictive information regarding expected future battery performance changes. For example, based on data provided by the artificial intelligence analysis unit (123), the expected residual value changes over a specific period can be visualized in a graph or table and attached to the certificate. This predictive information can provide vehicle buyers, insurance companies, and vehicle managers with valuable data for evaluating the long-term performance of the battery.

[0064] The battery residual value certificate issuing unit (125) can provide issued certificates in various formats. For example, in addition to traditional paper certificates, the certificates can be issued in digital form, enabling online verification. Digital certificates can incorporate features that facilitate verification of the certificate's authenticity through blockchain technology, thereby preventing forgery and enhancing its reliability.

[0065] Additionally, the battery residual value certificate issuing unit (125) may provide a function to continuously monitor and renew the validity of the issued certificate. Since the battery condition may change over time, regular evaluation and certificate renewal may be necessary. In this case, the battery residual value certificate issuing unit (125) can issue a new certificate or renew an existing certificate based on the latest data, thereby maintaining the certificate with the most up-to-date information. The items of the battery residual value certificate will be described in detail in FIG. 2, which will be described later.

[0066] Figure 2 is an example drawing showing a battery residual value certification report, and Figure 3 is a drawing showing another example of a battery residual value certificate.

[0067] Referring to Figure 2, the battery evaluation report comprehensively evaluates the remaining life, stability, and usability of an electric vehicle battery, indicating the battery's current condition and residual value. Battery ratings can be broadly categorized into three categories: remaining life evaluation, battery cell stability evaluation, and usability evaluation based on vehicle driving history.

[0068] First, in the remaining life assessment, the estimated SOH (State Of Health) evaluation (R1_01) is calculated by calculating the change in the SOC (State of Charge) during the battery charge / discharge and the Ampere-hour (Ah) during the corresponding time and comparing it with the initial capacity. The current health of the battery can be evaluated through the ratio of the current capacity to the initial capacity. For example, if a battery with an initial capacity of 100Ah currently has a capacity of 80Ah, the SOH will be 80%. The driving range coefficient (R1_02) can be used to evaluate the driving range efficiency of the battery based on the vehicle's cumulative driving distance and the SOH reduction amount. The driving range efficiency is calculated by dividing the total cumulative driving distance (ODO meter) by the SOH reduction amount and the number of packs. For example, if the vehicle's cumulative mileage is 102273 km, the SOH reduction is 8.93%, and the number of packs is 3, the mileage coefficient is 102273 / (8.93 * 3) = 3818.

[0069] The stability evaluation items can be analyzed to evaluate the stability of the battery by analyzing the voltage difference between cells during operation (R2_01), temperature difference between modules (R2_02), number of cell voltage drops during charging (R2_03), number of undervoltage cells (R2_04), and number of overvoltage cells (R2_05). The cell voltage difference during operation can be evaluated based on the ratio of the abnormal section of the cell voltage difference during operation to the total operating time. The warning standard is a cell voltage difference of 0.13 V or more but less than 0.26 V, and the fault standard is a cell voltage difference of 0.26 V or more. Since the temperature difference between battery modules can adversely affect the battery performance and lifespan if the temperature difference is large, the temperature difference can be continuously monitored and evaluated by measuring the duration of the section with a large temperature difference. The number of cell voltage drops during charging monitors the phenomenon of a sudden drop in cell voltage during charging and measures how often such an event occurs. The number of undervoltage cells can be assessed by monitoring the number of cells with abnormally low voltage when the SOC is low, and the number of overvoltage cells can be assessed by monitoring the number of cells with abnormally high voltage when the SOC is high.

[0070] Usability evaluation items can be analyzed to evaluate battery usage patterns, such as the number of rapid acceleration, rapid deceleration, rapid starts, and rapid stops (R3_01), battery management temperature (R3_05 and R3_06), and charge / discharge C-rate (R3_07 and R3_08). The number of rapid acceleration, rapid deceleration, rapid starts, and rapid stops can be calculated as the frequency per driving distance according to the standards of the Korea Transportation Safety Authority to evaluate excessive stress on battery use. Battery management temperature can be used to evaluate the thermal management status of the battery by measuring how long the battery has been operated in a section outside the appropriate temperature range. Charge / discharge C-rate can be used to monitor the section with high C-rate during battery charging and discharging to evaluate the impact of these high-load conditions on battery performance.

[0071] The final grade can be calculated by comprehensively assessing the remaining life, stability, and usability of the battery through the evaluation criteria described above.

[0072] Figure 3 shows a sample battery residual value certificate, showing the evaluation results for four vehicles (Vehicle 1, Vehicle 2, Vehicle 3, and Vehicle 4). Each vehicle is provided with a Life Score, Safety Score, Usability Score, total score, evaluation result (percentage), and grade. These results allow for a comprehensive comparison of the battery performance of each vehicle.

[0073] The evaluation results represent the final evaluation, which is calculated by converting the scores for each item shown in Figure 2 into a percentage, and the vehicle's battery performance is classified into grades based on this percentage. For example, the total evaluation result for "Vehicle-1" is 79%, corresponding to Grade 3, and the evaluation result for "Vehicle-4" is 93%, corresponding to Grade 1. Grades range from Grade 1 to Grade 4, with Grade 1 indicating the best battery performance, and Grade 4 indicating relatively poor performance.

[0074] FIG. 4 is a flowchart illustrating a battery residual value authentication method performed by a battery residual value authentication system according to one embodiment of the present invention.

[0075] Referring to Figure 4, real-time vehicle operation data can be collected through the real-time data collection unit (S410). Real-time vehicle operation data can be collected in real time through the OBD-2 module attached to the vehicle.

[0076] Next, the collected real-time driving data can be stored in a database (S420). The database can be designed using high-performance storage devices and an optimized database management system (DBMS). The data stored in the database is also linked to the battery and battery control unit, allowing for continuous updating and recording of data on the battery's condition and performance.

[0077] Next, real-time operating data stored in the database can be analyzed in batches whenever it reaches a certain level (S430). Batch analysis allows for in-depth analysis by processing the data in batches whenever a certain level of data accumulates in the database.

[0078] Next, training data for application to the AI ​​model can be generated from the data analyzed in batch form (S440). The training data generation unit can generate the battery's charge / discharge pattern. This charge / discharge pattern can include the battery's state of charge (SOC), charge rate, and discharge rate for each charging cycle. This charge / discharge pattern reflects the battery's actual usage conditions and is essential for accurately predicting battery performance and remaining lifespan. Furthermore, the system can record battery temperature changes during each driving session and generate data on battery performance changes under various temperature conditions. For example, in high-temperature environments, the battery's chemical reaction rate can accelerate, accelerating performance degradation. In low-temperature environments, the battery's internal resistance can increase, degrading performance. By including this temperature change data as training data, the AI ​​model can accurately predict battery performance under various temperature conditions. Furthermore, various driving conditions, such as city driving, highway driving, and mountainous terrain driving, can be considered. By analyzing battery consumption patterns in each driving environment, the AI ​​model can generate data to predict battery performance under specific driving conditions. In addition, the learning data generation unit can increase the accuracy of the learning data by removing noise and errors from the data transmitted in the data analysis stage.

[0079] Next, the residual battery value can be predicted based on the driver's driving habits (S450). Here, the AI ​​analysis unit can model the relationship between driving habits and battery residual value by utilizing various machine learning and deep learning algorithms. For example, the AI ​​analysis unit can process time-series data using recurrent neural network (RNN)-based models, such as Long Short-Term Memory (LSTM) networks. The LSTM model can analyze the driver's driving patterns, such as the frequency of rapid acceleration, rapid braking, and changes in driving speed, and evaluate the long-term impact of these patterns on battery performance. In this process, the LSTM model can handle long-term data dependencies and identify the cumulative impact of each driving habit on the battery residual value.

[0080] Furthermore, the AI ​​analysis unit utilizes advanced deep learning algorithms, such as the Transformer model, to analyze the complex correlations between driving habits and battery performance. The Transformer model precisely analyzes the interactions between driving data using a self-attention mechanism, enabling it to clearly model the correlation between battery state of charge (SOC) and driving habits. The Transformer model efficiently analyzes massive amounts of data through parallel processing, enabling it to predict changes in battery residual value in real time across various driving scenarios.

[0081] Next, the battery residual value certificate issuance unit can issue a battery certificate based on the battery's residual value (S460). The battery residual value certificate issuance unit first receives battery residual value assessment data provided by the AI ​​analysis unit and comprehensively reviews the current condition of the battery based on this data. This review process considers various battery performance indicators, such as the battery's state of charge (SOC), remaining useful life, charge / discharge efficiency, and performance degradation due to temperature changes. These indicators are then combined to create a final assessment of the battery's residual value, which is then reflected in the certificate.

[0082] During the certification issuance process, the battery residual value certificate issuing department applies standardized evaluation criteria to produce consistent and objective certificates. For example, a battery may be given an "Excellent" rating if its remaining capacity exceeds a certain percentage of its original capacity, while a battery that has undergone fewer than a certain number of charge / discharge cycles may be given a "Good" rating. This rating system clearly indicates the condition of a vehicle's battery and provides reliable information to buyers when reselling the vehicle.

[0083] FIG. 5 is a conceptual diagram illustrating a computing device that performs a battery remaining value authentication method according to one embodiment of the present invention.

[0084] An exemplary computing device (500) for performing the above-described methods and / or embodiments, etc. is described. According to one embodiment, the computing device (500) may be implemented using hardware and / or software configured to interact with a user. Here, the computing device (500) may include, but is not limited to, a laptop, a desktop, a workstation, a personal digital assistant, a server, a blade server, a main frame, etc. The components of the computing device described above, their connection relationships, and their functions are intended to be exemplary and are not intended to limit the implementations of the present invention described and / or claimed herein. The computing device (500) includes a processor (510), a memory (520), a storage device (530), a communication device (540), a high-speed interface (550) connected to the memory (520) and a high-speed expansion port, and a low-speed interface (560) connected to a low-speed bus and the storage device. Each of the components (510, 520, 530, 540, 550, and 560) may be interconnected using various buses and may be mounted on the same main board or may be mounted and connected in another suitable manner. The processor (510) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. For example, the processor (510) may process instructions stored in a memory (520), a storage device (530), etc., and / or instructions executed within the computing device (500), and display graphic information on an external input / output device (570), such as a display device coupled to a high-speed interface (550).The communication device (540) may provide a configuration or function for the input / output device (570) and the computing device (500) to communicate with each other through a network, and may provide a configuration or function for supporting the input / output device (570) and / or the computing device (500) to communicate with other external devices, etc. For example, a request or data generated by a processor of an external device according to any program code may be transmitted to the computing device (500) through a network under the control of the communication device (540). Conversely, a control signal or command provided under the control of the processor (510) of the computing device (500) may be transmitted to another external device through the communication device (540) and a network. Although the computing device (500) is illustrated as including one processor (510), one memory (520), etc., it is not limited thereto, and the computing device (500) may be implemented using multiple memories, multiple processors, and / or multiple buses, etc. In addition, although it has been described above that there is one computing device (500) in the city, this is not limited thereto, and multiple computing devices may interact and perform operations necessary to execute the above-described method. The memory (520) may store information within the computing device (500). According to one embodiment, the memory (520) may be configured as a volatile memory unit or as multiple memory units. Additionally or alternatively, the memory (520) may be configured as a non-volatile memory unit or as multiple memory units. In addition, the memory (520) may be configured as another form of computer-readable media, such as a magnetic disk or an optical disk. In addition, the memory (520) may store an operating system and at least one program code and / or instruction. The storage device (530) may be one or more mass storage devices for storing data for the computing device (500).For example, the storage device (530) may be a computer-readable medium including, or configured to include, a magnetic disc such as a hard disk, a removable disk, an optical disc, a semiconductor memory device such as an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable PROM (EEPROM), a flash memory device, a CD-ROM, a DVD-ROM disk, etc. In addition, a computer program may be tangibly implemented in such a computer-readable medium. The high-speed interface (550) and the low-speed interface (560) may be a means for interacting with an input / output device (570). For example, the input device may include a device such as a camera, a keyboard, a microphone, a mouse, etc., including an audio sensor and / or an image sensor, and the output device may include a device such as a display, a speaker, a haptic feedback device, etc. In another example, the high-speed interface (550) and the low-speed interface (560) may be means for interfacing with a device that has a configuration or function integrated for performing input and output, such as a touchscreen. In one embodiment, the high-speed interface (550) may manage bandwidth-intensive operations for the computing device (500), while the low-speed interface (560) may manage less bandwidth-intensive operations than the high-speed interface (550), but this functional assignment is merely exemplary. In one embodiment, the high-speed interface (550) may be coupled to high-speed expansion ports that can accommodate memory (520), input / output devices (570), and various expansion cards (not shown). Additionally, the low-speed interface (560) may be coupled to a storage device (530) and a low-speed expansion port.Additionally, a low-speed expansion port, which may include various communication ports (e.g., USB, Bluetooth, Ethernet, wireless Ethernet), may be coupled to one or more input / output devices (570), such as a keyboard, pointing device, scanner, or networking devices, such as a router, switch, or the like, via a network adapter. The computing device (500) may be implemented in a number of different forms. For example, the computing device (500) may be implemented as a standard server, or may be implemented as a group of such standard servers. Additionally or alternatively, the computing device (500) may be implemented as part of a rack server system, or may be implemented as a personal computer, such as a laptop computer. In this case, components from the computing device (500) may be coupled with other components within any mobile device (not shown). The computing device (500) may include one or more other computing devices, or may be configured to communicate with one or more other computing devices. Although the input / output device (570) is depicted in the drawing as not being included in the computing device (500), it is not limited thereto, and may be configured as a single device with the computing device (500). In addition, although the high-speed interface (550) and / or the low-speed interface (560) are depicted as elements configured separately from the processor (510), it is not limited thereto, and the high-speed interface (550) and / or the low-speed interface (560) may be configured to be included in the processor (510). In the present invention, various embodiments may be implemented in a computing device that includes a back-end component (e.g., a data server), a middleware component (e.g., an application server), and / or a front-end component. In this case, the components may be interconnected by any form or medium of digital data communication, such as a communication network.According to one embodiment, the communication network may be comprised of a wired network such as Ethernet, a wired home network (Power Line Communication), a telephone line communication device, and RS-serial communication, a mobile communication network, a wireless network such as WLAN (Wireless LAN), Wi-Fi, Bluetooth, and ZigBee, or a combination thereof. For example, the communication network may include a Local Area Network (LAN), a Wide Area Network (WAN), and the like.

[0085] A computing device based on the exemplary embodiments described herein may be implemented using hardware and / or software configured to interact with a user, including a user device, a user interface (UI) device, a user terminal, or a client device. For example, the computing device may include a portable computing device, such as a laptop computer. Additionally or alternatively, the computing device may include, but is not limited to, Personal Digital Assistants (PDAs), tablet PCs, game consoles, wearable devices, Internet of Things (IoT) devices, virtual reality (VR) devices, augmented reality (AR) devices, and the like. The computing device may further include other types of devices configured to interact with a user. Furthermore, the computing device may include a portable communication device (e.g., a mobile phone, a smart phone, a cordless cellular phone, etc.) suitable for wireless communication over a network, such as a mobile communication network. The computing device may be configured to communicate wirelessly with a network server using wireless communication technologies and / or protocols, such as Radio Frequency (RF), Microwave Frequency (MWF), and / or Infrared Ray Frequency (IRF).

[0086] The various embodiments of the present invention, including specific structural and functional details, are exemplary. Therefore, the embodiments of the present invention are not limited to those described above and may be implemented in various other forms. Furthermore, the terminology used herein is intended to describe certain embodiments and is not intended to limit the embodiments. For example, singular terms and the above may be interpreted to include plural forms, unless the context clearly dictates otherwise.

[0087] In the present invention, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which they pertain. Furthermore, commonly used terms, such as terms defined in dictionaries, should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology.

[0088] While the present invention has been described in connection with certain embodiments herein, it should be understood that various modifications and variations can be made without departing from the scope of the invention as understood by those skilled in the art. Furthermore, such modifications and variations should be considered to fall within the scope of the claims appended to this specification.

[0089] [Explanation of symbols]

[0090] 100: Battery residual value certification system 110: Vehicle

[0091] 111: Real-time data collection unit 112: Database

[0092] 113: Battery 114: Battery control unit

[0093] 120, 500: Computing device 121: Data analysis unit

[0094] 122: Driving Habit Analysis Department 123: Learning Data Generation Department

[0095] 124: Prediction Department 125: Analysis Results Provider Department

[0096] 126: Improvement proposal provider 130: Network

[0097] 510: Processor 520: Memory

[0098] 530: Storage device 540: Communication device

[0099] 550: High-speed interface 560: Low-speed interface

[0100] 570: Input / output device

Claims

1. Real-time data collection unit that collects real-time driving data based on the driving habits of vehicle drivers; A database in which the collected real-time driving data is stored; A data analysis unit that analyzes the stored real-time driving data in batch form whenever the real-time driving data stored in the database reaches a certain level; A learning data generation unit that generates learning data for application to an artificial intelligence model from data analyzed in the above batch format; An artificial intelligence analysis unit that analyzes the learning data using the artificial intelligence model; An analysis result provision unit that provides the analysis results of the artificial intelligence analysis unit; and A battery residual value certificate issuing department that issues a certificate of battery residual value based on the above analysis results; Battery residual value certification system including.

2. In paragraph 1, A battery residual value certification system that uses real-time driving data based on the driving habits of the above vehicle driver, which is data related to the vehicle's speed, engine status, battery charge status, driving distance, and frequency of sudden acceleration and sudden braking.

3. In paragraph 1, A battery residual value certification system that uses real-time driving data based on the driving habits of the driver of the above vehicle, including data related to the voltage difference between battery cells during driving, the temperature difference between battery modules during driving, the number of cells below or above the reference voltage, the number of times rapid deceleration or rapid acceleration occurs, and the battery charge and discharge rate.

4. In paragraph 1 The above artificial intelligence analysis unit is a battery residual value certification system that receives battery value assessment data and determines the residual value of the battery based on the data.

5. In paragraph 1, A battery residual value authentication system, wherein the above artificial intelligence model is at least one of the STM and Transformer models.

6. In paragraph 4, The above analysis result provision unit is a battery residual value certification system that grades the above battery residual value and provides the main evaluation basis.

7. In paragraph 1, The above battery residual value certificate issuing unit is a battery residual value certification system that receives battery value assessment data provided by the above artificial intelligence analysis unit and determines the current residual value of the battery based on the data.

8. In paragraph 7, A battery residual value certification system in which the residual value of the above battery is evaluated based on the battery's state of charge (SOC, State of Charge), remaining useful life, charge / discharge efficiency, and performance degradation due to temperature changes.

9. In paragraph 1, The certificate of the above battery residual value includes evaluation criteria, evaluation number, evaluation formula, and evaluation result, and the evaluation criteria are composed of major categories, minor categories, and intermediate categories, and the major categories include items consisting of residual life, stability, and usability, and the residual life is evaluated based on the estimated SOH and driving distance coefficient, and the stability is evaluated based on the cell voltage difference during operation, the module temperature difference during operation, the cell voltage difference during charging, under voltage, and over voltage, and the usability is evaluated based on the number of sudden accelerations, battery management temperature, and C-rage. A battery residual value certification system that scores each evaluation result based on the above-mentioned estimated SOH, driving distance coefficient, cell voltage difference during operation, module temperature difference during operation, cell voltage difference during charging, under voltage, over voltage, number of sudden accelerations, battery management temperature, and C-rage, and then derives the final evaluation result, which is expressed as a final score and grade.

10. In paragraph 1, The above battery residual value certificate is a battery residual value certification system that evaluates the remaining life, stability, and usability of each vehicle and indicates the evaluation result score and grade.

11. Step of collecting real-time driving data based on the driving habits of the vehicle driver; A step of storing the collected real-time driving data in a database; A step of analyzing the stored real-time operation data in batch form whenever the real-time operation data stored in the database reaches a certain level; A step of generating learning data for application to an artificial intelligence model from data analyzed in the above batch format; A step of analyzing the learning data using the artificial intelligence model; A step of providing the above artificial intelligence analysis results; and A step of issuing a certificate of battery residual value based on the above analysis results; A method for authenticating the residual value of a battery, including:

12. In paragraph 11, A method for authenticating a battery residual value, wherein the collected data includes data related to the vehicle's speed, engine status, battery charge status, driving distance, and frequency of sudden acceleration and sudden braking, in a step of collecting real-time driving data based on the driving habits of the vehicle driver.

13. In paragraph 11, A method for authenticating a battery residual value, wherein the collected data includes data related to the voltage difference between battery cells during driving, the temperature difference between battery modules during driving, the number of cells below or above a reference voltage, the number of rapid decelerations or rapid accelerations, and the battery charge and discharge rates.

14. In paragraph 11, A battery residual value authentication method, wherein, in the step of analyzing learning data using the above artificial intelligence model, battery value assessment data is input and the residual value of the battery is determined based on the data.

15. In paragraph 14, A method for verifying the remaining battery value, which predicts the stability of the battery by analyzing driving habits in the step of analyzing learning data using the above artificial intelligence model.

16. In paragraph 11, The above artificial intelligence model is a battery residual value authentication method using at least one of the STM and Transformer models.

17. In paragraph 14, A method for certifying the residual value of a battery, wherein the residual value of the battery is graded and the main basis for evaluation is provided in the step of providing the above analysis results.

18. In paragraph 11, A battery residual value certification method, wherein, in the step of issuing the above battery residual value certificate, battery value assessment data provided by the artificial intelligence analysis unit is input and the current residual value of the battery is determined based on the above data.

19. In paragraph 18, A method for authenticating a battery residual value, wherein, in the step of evaluating the residual value of the above battery, the residual value of the battery is evaluated based on the battery's state of charge (SOC, State of Charge), remaining useful life, charge / discharge efficiency, and performance degradation due to temperature changes.

20. In paragraph 11, A method for certifying a battery residual value, wherein the step of issuing the above battery residual value certificate includes evaluation criteria, an evaluation number, an evaluation formula, and an evaluation result, wherein the evaluation criteria are composed of major categories, minor categories, and intermediate categories, and the major categories include items consisting of residual life, stability, and usability, wherein the residual life is evaluated based on an estimated SOH and a driving distance coefficient, and the stability is evaluated based on a cell voltage difference during operation, a module temperature difference during operation, a cell voltage difference during charging, under voltage, and over voltage, and the usability is evaluated based on the number of sudden accelerations, battery management temperature, and C-rate, and wherein each evaluation result is scored to derive a final evaluation result, which is then expressed as a final score and grade.

21. In paragraph 11, A battery residual value certification method that, in the step of issuing the above battery residual value certificate, evaluates the remaining life, stability, and usability of each vehicle and indicates the evaluation result score and grade.

Images