Parking guidance decision-making method based on mamdani algorithm
A technology of parking induction and decision-making method, which is applied in the direction of calculation, data processing applications, instruments, etc., and can solve the problems that the parking lot cannot accurately grasp the needs of the served, the system has not found meaning, and the analysis of user needs is unclear.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0139] The user is an office worker in the CBD complex, and he went to work for 26 days last month. When the user drove into the parking lot to recognize the license plate, he said "I often work here", the voice was 58 decibels, and it took 1.953 seconds. Among them, the degreed word corresponding to the keyword Keyword was Often, and Speed=1.953 / 6=0.3255, which was normal Speech rate, sound decibel is 58, greater than 40, take Loud=1. Therefore, the reliability index of natural language input is obtained Calculated,
[0140] Through Fuzzy Editor's 18 fuzzy rule operations (such as Figure 8 ), based on the center of gravity method, the system automatically obtains the target parking space of the car as 1.9. The induction parking decision based on Mamdani shows that the most suitable parking position is the 1.9 position near the elevator of the office building. The mapping surface between Type, Frequency, Reliability and Target is as follows Figure 9 shown.
[0141] ...
Embodiment 2
[0143] The user parked 12 times last month and drove into the CBD complex again today. There is no natural language input when entering the parking lot. Assume that according to the result of the system's last self-learning, its target parking space is 0.03. The system calculates its reliability index Reliability Index=0.67*(0.45+(12-13.5) / 30=0.268. According to the Mamdani model, its target position is 0.015, such as Figure 10 . When it drives out of the parking lot, the system finds that the parking time is 3 hours, then the system self-learning results are as follows: That is to say, the next target parking space will find a new balance between the elevator for shopping and watching movies. 0.31 is between 0 and 1. According to the result of system learning, on the one hand, the system concludes that the user’s recent parking purpose is between shopping (escalator) and watching movies and eating (movie elevator); on the other hand, the user Every time I come to park, ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


