Intelligent elevator card swiping management method based on fusion algorithm

Abstract

The invention belongs to the technical field of automation control. According to the intelligent elevator card swiping management method, dynamic permission allocation is achieved based on a chaos genetic hybrid algorithm, and safety protection is enhanced in combination with quantum encryption and behavior feature recognition; the elevator dispatching efficiency is improved through an improved particle swarm optimization algorithm, and personalized services are provided through multi-dimensional user portraits; fault early warning is realized by means of space-time sequence prediction, and data management and sharing are optimized by adopting a block chain technology. All the modules operate cooperatively, the safety, convenience and management efficiency of elevator use are remarkably improved, the operation cost is reduced, and the requirement of modern buildings for elevator intelligent management is met.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent elevator control, and in particular to an intelligent elevator card swiping management method integrating multiple innovative algorithms. Background Art

[0002] Existing elevator card management systems are plagued by rigid permissions management, significant security risks, and inefficient dispatching. Traditional systems employ a fixed permission allocation model, making it impossible to dynamically adjust permissions based on user needs or time constraints. Furthermore, cards are susceptible to duplication, and data transmission lacks effective encryption protection. Furthermore, dispatching processes struggle to rationally plan elevator routes, leading to long passenger wait times during peak hours and high elevator idle rates. These issues severely hinder the development of intelligent elevator management, making it difficult to meet the demands of modern buildings for efficient and safe elevator operation. Summary of the Invention

[0003] Purpose of the Invention

[0004] The present invention aims to provide an intelligent elevator card swiping management method to solve many problems existing in the existing elevator card swiping management system, realize dynamic and flexible allocation of permissions, strengthen security protection, optimize elevator scheduling, and improve user experience and the intelligent level of elevator management.

[0005] The method includes:

[0006] A dynamic permission allocation module based on a chaos-genetic hybrid algorithm: This algorithm combines chaos theory with a genetic algorithm to create a chaos-genetic hybrid algorithm. This algorithm uses user identity information, time information, and building area information as input parameters. The initial population generated by the chaotic system exhibits good ergodicity. Through the genetic algorithm's selection, crossover, and mutation operations, it searches for the optimal permission allocation scheme within the solution space. For example, for temporary visitors, this algorithm rapidly generates corresponding temporary permissions based on their appointment time, access area, and other information. The validity period of these permissions is accurate to the minute level and can be dynamically adjusted based on actual conditions.

[0007] Quantum encryption and behavioral signature recognition dual-security module: This module uses quantum encryption technology to encrypt and transmit user card swipe data, leveraging the non-cloning nature of quantum states and the uncertainty principle to ensure absolute data security during transmission. Simultaneously, a user behavioral signature recognition model is established. By collecting behavioral data such as card swipe force, speed, and time interval, and combining it with machine learning algorithms, a unique behavioral signature template is generated for each user. When a user swipes their card, not only is the card information verified, but the behavioral signature is also compared. Only when both match is the user allowed to use the elevator.

[0008] An intelligent elevator scheduling module based on improved particle swarm optimization (PSO) improves upon the traditional PSO algorithm by introducing adaptive inertia weighting and a local search strategy. Information such as the elevator's operating status, the number of people waiting on each floor, and the passenger's destination floor is used as particle position parameters. The adaptive inertia weighting is dynamically adjusted based on the algorithm's iteration count and search progress, accelerating the global search in the early stages and enhancing local search capabilities as the optimal solution is approached. The local search strategy guides particles out of local optima and toward a more optimal solution when they become trapped. This algorithm enables real-time optimization of elevator routes, reducing passenger wait times and elevator idleness.

[0009] Multi-dimensional user profiling and personalized service module: This module collects multi-dimensional data, including basic user information, historical card swipe data, elevator travel time, and frequently used floors, and applies deep learning algorithms to build a user profiling model. By analyzing this data, it uncovers user habits and preferences, such as peak travel times, frequently visited floors, and preferred elevator travel times. Based on this user profile, personalized services are provided, such as automatically selecting a frequently used floor when the user swipes their card; and pushing relevant service information, such as promotional offers on the dining floors, during specific time periods.

[0010] The fault warning module based on spatiotemporal sequence prediction collects elevator operating data, including speed, current, voltage, and door status, as well as data related to the card swiping system, such as swipe time and user permission change records. Using a spatiotemporal sequence prediction algorithm, it combines information from both temporal and spatial dimensions to predict the elevator's operating status. When a potential fault is predicted, an early warning is issued and sent to maintenance and management personnel, along with possible fault causes and suggested solutions.

[0011] The blockchain-powered data management and sharing module leverages the decentralized and tamper-proof nature of blockchain technology to store and manage data within the elevator card management system. User permissions, card swipe records, and elevator operation data are stored on-chain to ensure data authenticity and integrity. Smart contracts enable data sharing and access control between different management departments, such as property management, elevator maintenance, and security, allowing them to access data based on their respective permissions, improving management efficiency and collaborative work.

[0012] Beneficial effects

[0013] Flexible and efficient authority management: The dynamic authority allocation module based on the chaos genetic hybrid algorithm realizes dynamic and accurate allocation of authority, which can quickly respond to the diverse needs of different users, improve the flexibility and efficiency of authority management, and reduce management costs.

[0014] Enhanced security protection level: The dual-insurance security module of quantum encryption and behavioral feature recognition provides high-intensity security protection from both data transmission and user identity verification, effectively resisting security threats such as data theft and card copying, and ensuring user and building safety.

[0015] Elevator dispatch optimization: The intelligent elevator dispatch module based on improved particle swarm optimization significantly improves elevator operation efficiency, reduces passenger waiting time and elevator idle rate, improves elevator service quality, and alleviates elevator congestion during peak hours.

[0016] Personalized service experience: Multi-dimensional user portraits and personalized service modules provide users with personalized services, enhance the convenience and comfort of using elevators, improve user satisfaction, and reflect the characteristics of intelligent services.

[0017] Timely and effective fault warning: The fault warning module based on spatiotemporal sequence prediction realizes the early prediction of elevator faults, enabling maintenance personnel to take timely measures to reduce the fault rate, shorten elevator downtime, and improve elevator reliability and operating efficiency.

[0018] Data management security and collaboration: The blockchain-enabled data management and sharing module ensures the secure storage and reliable sharing of data, enables collaboration between management departments through smart contracts, and improves the overall efficiency and transparency of elevator management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 Flowchart of the fault warning module based on spatiotemporal sequence prediction;

[0020] Figure 2 Schematic diagram of the elevator intelligent scheduling module based on improved particle swarm optimization: Describes the application of the improved particle swarm optimization algorithm in elevator scheduling, including processes such as particle position update and adaptive inertia weight adjustment. DETAILED DESCRIPTION

[0021] Example 1

[0022] Application of Chaos-Genetic Hybrid Algorithm: This innovative combination of chaos theory and genetic algorithm is applied to the dynamic allocation of elevator card swiping permissions, breaking the traditional fixed permission model and achieving efficient, accurate, and dynamic adjustment of permissions to meet the needs of diverse scenarios.

[0023] Combination of quantum encryption and behavioral feature recognition: For the first time, quantum encryption technology and user behavioral feature recognition technology are applied to the field of elevator card swiping security, building a dual security protection system, effectively preventing data leakage and illegal access, and greatly improving system security.

[0024] Improved Particle Swarm Optimization Algorithm Scheduling: The particle swarm optimization algorithm is improved by introducing adaptive inertia weight and local search strategy, which is applied to intelligent elevator scheduling. Compared with traditional scheduling algorithms, it significantly improves elevator operation efficiency and reduces passenger waiting time.

[0025] Multi-dimensional user portrait construction: Through multi-dimensional data collection and deep learning algorithms, a user portrait model is constructed to provide users with personalized services, improve user experience, and create a new model of personalized service for elevator card swiping management.

[0026] Spatiotemporal sequence prediction fault warning: Based on the spatiotemporal sequence prediction algorithm, comprehensive analysis of elevator operation data and card swiping data can achieve early warning of faults, change the traditional post-fault maintenance model, and improve elevator operation reliability and maintenance efficiency.

[0027] Data management using blockchain technology: Applying blockchain technology to the data management of the elevator card swiping management system, leveraging blockchain characteristics to ensure data security and reliability, enabling data sharing and access control through smart contracts, optimizing management processes, and enhancing management collaboration.

[0028] Innovative algorithm model modeling and solution

[0029] Chaos genetic hybrid algorithm modeling and solution process

[0030] Initialization: Generate the initial population using chaotic mapping. The chaotic mapping formula is xn+1=4×xn×(1-xn)

[0031] , where xn is a chaotic variable with a value range of (0,1). By adjusting the initial value x0

[0032] Generate different chaotic sequences and map them to the solution space of authority allocation to form the initial population.

[0033] Fitness calculation: Evaluate the pros and cons of each individual according to the set fitness function. The fitness function comprehensively considers the rationality, flexibility, security and other factors of authority allocation, such as Fitness = w1×R+w2×F+w3×S, where R

[0034] It represents the rationality index of authority allocation, F represents the flexibility index, S represents the security index, and w1, w2, and w3 are weight coefficients.

[0035] Genetic operation: selection operation is performed using the roulette wheel selection method, and the probability of being selected is calculated based on the individual fitness; the crossover operation uses the partial matching crossover method to exchange part of the genes of two individuals with a certain crossover probability; the mutation operation uses the uniform mutation method to mutate the individual genes with a certain mutation probability.

[0036] Iterative optimization: Repeat the fitness calculation and genetic operation steps until the termination conditions are met, such as reaching the maximum number of iterations or the fitness value converges, and output the optimal permission allocation plan.

[0037] Modeling and solving process of spatiotemporal series prediction algorithm

[0038] Data preprocessing: The collected elevator operation data and card swiping data are cleaned to remove outliers and noise, and then normalized to map the data to the [0,1] interval to meet the model input requirements.

[0039] Model Construction: We built a spatiotemporal sequence prediction model using a combination of a convolutional neural network (CNN) and a gated recurrent unit (GRU). CNN extracts spatial features of the data, such as the correlation between different elevator components; GRU learns the temporal sequence features of the data, capturing how the data changes over time.

[0040] Model training: The preprocessed data is divided into training, validation, and test sets. The model is trained using the Adam optimizer, using the mean squared error (MSE) as the loss function. During training, model parameters, such as the convolution kernel size of the CNN and the number of GRU units, are continuously adjusted to improve the model's prediction accuracy.

[0041] Model Evaluation and Prediction: The trained model is evaluated on a test set, using metrics such as mean absolute error (MAE) and root mean square error (RMSE) to measure model performance. The model is optimized based on the evaluation results and used to predict elevator operating status in real time. When the predicted value deviates from the normal range by more than a threshold, a fault warning is triggered.

[0042] Example 2

[0043] A dynamic permissions allocation module based on a chaotic genetic hybrid algorithm was implemented at a large business park. This module uses a chaotic genetic hybrid algorithm to assign permissions to employees within the park based on their work hours, department affiliation, and project requirements. During project collaboration, temporary permissions are dynamically generated for external personnel temporarily participating in the project, with permissions accurately assigned to specific floors and time periods. Through practical application, the accuracy and efficiency of permission allocation have been significantly improved, meeting the complex and ever-changing permission management needs of the park.

[0044] A dual-security module combining quantum encryption and behavioral signature recognition has been deployed in a high-end residential complex. Residents are issued quantum encryption cards, and their card swiping behavior data is collected to create behavioral signature templates. Quantum encryption technology is used to ensure data security during data transmission. After a period of operation, this module has effectively prevented card duplication and unauthorized access, significantly improving residents' satisfaction with elevator safety.

[0045] An intelligent elevator dispatching module based on improved particle swarm optimization has been implemented in a high-rise office building. During the morning rush hour, the system uses an improved particle swarm optimization algorithm to optimize elevator routes in real time based on information such as the number of people waiting for elevators on each floor and elevator operating status. Compared to traditional dispatching methods, this has reduced average passenger waiting times by 40% and reduced elevator idle rates by 30%, effectively alleviating elevator congestion during peak hours.

[0046] Implementation of a multi-dimensional user profiling and personalized service module: This module was implemented at a large hotel. By collecting guest check-in information and historical elevator ride data, a multi-dimensional user profile was constructed. When a guest swipes their card upon re-checking in, the system automatically selects their frequently used floor and pushes relevant service information based on their spending habits. This personalized service has received positive feedback from guests, improving the hotel's service quality.

[0047] Implementation of a fault warning module based on spatiotemporal sequence prediction: This module was deployed in the elevator system of a commercial complex in a certain city. The system collected elevator operation and card swipe data in real time and analyzed it using a spatiotemporal sequence prediction model. During one operation, it successfully predicted a potential fault in the door operator system of a particular elevator, notifying maintenance personnel in advance for repairs, thus avoiding the failure and ensuring normal operation of the elevator.

[0048] Implementation of a blockchain-enabled data management and sharing module: This module has been applied to multiple elevator management projects. Property management, elevator maintenance, and security departments, among others, use the blockchain platform to achieve data sharing and collaborative work. Maintenance personnel can view elevator operating data and historical maintenance records in real time, improving repair efficiency. Security departments can promptly access abnormal card swipe information to enhance safety precautions. Blockchain technology enables secure and efficient management of elevator management data.

Claims

1. An intelligent elevator card swiping management method integrating algorithms, characterized in that: Includes the following modules and steps: Identity verification and permission classification module: collects user card information through card swiping devices, combines biometric technology to verify identity, and classifies user permissions according to preset rules; Floor allocation module based on dynamic weight optimization algorithm: The dynamic weight optimization algorithm is used to allocate the user's target floor. The dynamic weight optimization algorithm adopts the formula Calculate the weight of each floor, where W is the target floor weight, αi is the weight coefficient of influencing factor i, Fi is the value of influencing factor i, and n is the number of influencing factors; Abnormal behavior detection and early warning module: uses an abnormal detection algorithm based on spatiotemporal correlation analysis to monitor user card swiping and elevator riding behaviors, triggering an early warning when abnormal behavior is detected; Data encryption and secure transmission module: encrypts user card swiping data, permission data, etc., and transmits them through a secure protocol; Historical data backtracking and analysis module: stores user card swiping historical data and analyzes and mines the data; System adaptive optimization module: Adaptively optimize the parameters and algorithms of each module based on historical data and real-time operation conditions; In the identity verification and authority classification module, biometric recognition technology includes at least one of fingerprint recognition, face recognition, and iris recognition, and the authority classification rules are set based on user identity type, usage time, and usage frequency.

2. The smart elevator card swiping management method according to claim 1, characterized in that: In the floor allocation module based on the dynamic weight optimization algorithm, the influencing factors i include but are not limited to the elevator load on the current floor, the difference in the number of floors between the user's target floor and the current floor, and the usage priority of each floor. The weight coefficient αi is dynamically adjusted according to real-time data and historical data.

3. The smart elevator card swiping management method according to claim 1, characterized in that: The anomaly detection algorithm based on spatiotemporal correlation analysis adopts the formula Calculate the behavior difference, where D is the behavior difference value, Tj is the j-th time dimension feature value, T is the time dimension feature mean, Sk is the k-th space dimension feature value, S is the space dimension feature mean, m is the number of time dimension features, and l is the number of space dimension features. When D exceeds the preset threshold, it is determined to be abnormal behavior.

4. The smart elevator card swiping management method according to claim 1, characterized in that: In the data encryption and secure transmission module, the encryption method adopts a combination of symmetric encryption algorithm and asymmetric encryption algorithm, and the security protocol adopts SSL / TLS protocol.

5. The smart elevator card swiping management method according to claim 1, characterized in that: In the historical data backtracking and analysis module, the analysis and mining content includes peak hours of users taking the elevator, frequency of use of each floor, and patterns of abnormal behavior.

6. The smart elevator card swiping management method according to claim 1, characterized in that: In the system adaptive optimization module, the weight coefficient of the dynamic weight optimization algorithm and the threshold of the anomaly detection algorithm based on spatiotemporal correlation analysis are adaptively adjusted.

7. The smart elevator card swiping management method according to claim 1, characterized in that: When the identity verification and authority classification module performs identity verification, if the card swiping information is inconsistent with the biometric information, the authority granting is rejected and the exception is recorded.

8. The smart elevator card swiping management method according to claim 1, characterized in that: After triggering the warning, the abnormal behavior detection and warning module sends the abnormal information to the property management terminal and the security terminal.

9. The intelligent elevator card swiping management method according to claim 1, characterized in that: The historical data backtracking and analysis module feeds back the analysis results to the system adaptive optimization module to provide a basis for parameter adjustment and algorithm optimization.

Images