Vehicle Charging Intention Prediction Using Travel and Battery Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining a vehicle's charging intention fail to accurately consider drivers' habits, leading to inefficiencies in charging preparation and management.
Innovation Solution
A method and device that acquire travel information to determine a confidence level of charging intention by analyzing preset dimensions such as charging position, time, and battery state, using historical data to predict and confirm travel plans, thereby improving the accuracy of charging intention determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If charging intention is determined only by surrounding environment and basic travel parameters, then the determination process is simple, but the accuracy of charging intention prediction is insufficient
Solution Approach 1:
The charging intention determination is segmented into multiple independent dimensions: travel information dimension, battery state dimension, charging station dimension, and user habit dimension. Each dimension is evaluated separately to calculate a charging probability, which are then aggregated to determine the overall charging intention. This segmentation allows the system to comprehensively analyze multiple factors without creating an overly complex monolithic determination process.
Solution Approach 2:
The patent introduces a new dimension of user charging habits and historical behavior patterns to the traditional determination process. By adding the user habit dimension with multiple sub-dimensions (charging time preferences, charging location preferences, battery level thresholds), the system transitions from a two-dimensional assessment (environment + basic travel info) to a multi-dimensional assessment, significantly improving prediction accuracy.
2Measurement precision
If multiple dimensions are used to determine charging probability, then the charging intention determination becomes more accurate, but the computational complexity increases
Solution Approach 1:
The complex multi-dimensional determination process is segmented into four independent probability calculations, each focusing on a specific dimension (travel information, battery state, charging station, user habits). This segmentation reduces the analytical complexity by breaking down the overall task into manageable sub-tasks that can be processed independently and then aggregated.
Solution Approach 2:
The system calculates charging probability for each dimension separately and then aggregates them, performing a complete analysis across all dimensions. This approach ensures that no relevant factor is overlooked while maintaining a systematic and organized computation process that avoids unnecessary redundancy.
3Measurement precision
If user charging habits and historical data are analyzed, then the charging intention prediction becomes more accurate, but the data processing time increases
Solution Approach 1:
The system pre-processes and stores user charging habits and historical behavior data in advance, organizing them into structured dimensions (charging time preferences, location preferences, battery level thresholds). This preliminary organization of data allows for rapid retrieval and analysis during the charging intention determination process, reducing the time required for real-time data processing.
Solution Approach 2:
The historical data analysis is segmented into specific dimensional assessments (user habit dimension with multiple sub-dimensions) that can be independently evaluated. This segmentation allows the system to efficiently query and process only the relevant historical data needed for each dimension, rather than analyzing the entire historical dataset, thereby reducing processing time.
Data Source
AI summary
A method for determining a vehicle charging intention includes: acquiring travel information of a target travel as target travel information; determining a confidence level of a charging intention in the target travel according to the target travel information, in which the confidence level of the charging intention is determined by a charging probability of at least one preset dimension, in which the preset dimension includes a charging position dimension, a charging time dimension and a battery state dimension; and determining whether the charging intention exists in the target travel according to the confidence level of the charging intention.