AI intelligent city service calculation method based on big data

Abstract

The invention relates to the technical field of city service calculation, in particular to an AI intelligent city service calculation method based on big data, comprising a data integration end, a data calculation end and a data application simulation end, the data integration end is composed of a data integration system and a data management storage system, the data calculation end is composed of a data conversion system and a data analysis system, and the data application simulation end is composed of a data receiving system, a model building system, a model simulation system and an optimization system. According to the AI intelligent city service calculation method based on big data, an image processing technology and algorithm are used for simulating and predicting images of future scenes, a contrastive analysis and statistical method is used for evaluating the difference between a prediction result of a model and actual data, and manual work is matched with a robot for calculation; the algorithm and the technology are used for processing and analyzing a large amount of data to extract useful information and insight, and the data processing efficiency and accuracy can be remarkably improved by matching with a data robot.

Description

Technical Field

[0001] The present invention relates to the field of urban service computing technology, and specifically to an AI smart city service computing method based on big data. Background Art

[0002] AI city services, or smart city services, refer to a system that uses artificial intelligence (AI) and Internet of Things (IoT) technologies as its core, and uses big data, cloud computing and other cutting-edge technologies to achieve intelligent, information-based and efficient urban management and services.

[0003] AI city services are widely used in the field of transportation. The calculation method of AI smart city services based on big data is a complex and evolving field. Improvements are made through optimizing data processing processes, enhancing algorithm flexibility and scalability, strengthening data security and privacy protection, and improving the level of intelligent services.

[0004] Cities need to manually manage traffic and monitor traffic flow, speed, vehicle type and other information in real time. Manual management is not convenient and efficient enough, so it is proposed to build AI smart city services. However, the collection, processing and analysis of big data is a complex and time-consuming process, which requires efficient methods and technologies to support it. Therefore, we designed an AI smart city service calculation method based on big data and applied it to smart city services. Summary of the invention

[0005] The purpose of the present invention is to provide an AI smart city service calculation method based on big data to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A big data-based AI smart city service computing method, comprising a data integration end, a data computing end and a data application simulation end, wherein the data integration end is composed of a data integration system and a data management and storage system, wherein the data integration system is composed of a sensor acquisition system, an image recognition system, a positioning system and a big data platform system, and wherein the data management and storage system is composed of a data preprocessing system, a data storage system and a data security system;

[0008] The data computing end is composed of a data conversion system and a data analysis system, wherein the data conversion system includes a data conversion system and a data output system, and the data analysis system includes an intelligent system;

[0009] The data application simulation end is composed of a data receiving system, a model building system, a model simulation system and an optimization system. The model building system includes a model selection system and a model building system. The model simulation system includes a scenario system. The optimization system includes a verification system and an adjustment system.

[0010] Preferably, the sensor acquisition system includes a geomagnetic sensor, an infrared sensor and a pressure sensor;

[0011] The image recognition system includes an image sensor and a camera;

[0012] The positioning system includes a GPS locator;

[0013] The big data platform system includes public platform data and mobile phone signaling data.

[0014] Preferably, the data preprocessing system comprises a data processor;

[0015] The data storage system includes a data storage device;

[0016] Data security systems include cloud processing systems, firewalls, intrusion detection systems, intrusion prevention systems, security event management systems, etc.

[0017] Preferably, the data conversion system comprises a numerical converter;

[0018] The data output system includes a numerical output device, a screen display, an internal memory and numerical calculation software.

[0019] Preferably, the intelligent system includes an artificial computing system, a data analyzer and a data robot.

[0020] Preferably, the model selection system includes a machine learning model, a digital model, and a statistical model;

[0021] The model building system includes a parameter output system;

[0022] The scenario system includes an image simulator;

[0023] The verification system includes a data comparison analyzer;

[0024] The adjustment system includes an improvement system and a parameter value adjustment system.

[0025] Preferably, the method comprises the following steps:

[0026] Data integration end:

[0027] S1. Data Integration:

[0028] By installing various sensors such as geomagnetic sensors and infrared sensors at traffic intersections, road sections and vehicles, various sensors can be used to monitor traffic flow, vehicle speed, vehicle type and other information in real time;

[0029] Install cameras at traffic intersections or road sections to capture real-time images of traffic scenes, use computer vision and deep learning technology to identify and analyze images, and extract information about traffic participants such as vehicles and pedestrians, as well as their behaviors and movement trajectories;

[0030] Install GPS devices on vehicles to obtain real-time information such as the vehicle's precise location, speed, and direction of travel, analyze the vehicle's driving trajectory and traffic flow dynamics, and provide important basis for traffic planning and management;

[0031] Collect and analyze the communication signaling data of mobile phone users, infer the users' travel routes, dwelling time, transportation methods and other information, and use the traffic statistics, accident records, road network conditions and other data provided by the public data platform.

[0032] S2. Data processing:

[0033] The data processor in the master control system removes duplicate data collected in the database, fills in missing data, processes abnormal data, etc., and converts data from different sources into a unified format to facilitate subsequent processing and analysis.

[0034] S3, Data Storage:

[0035] Large-scale data is stored in the database through storage for subsequent retrieval and analysis.

[0036] S4. Data security:

[0037] Sensitive data is encrypted through firewalls, intrusion prevention systems, etc. to ensure data security.

[0038] Data calculation end:

[0039] S5. Data conversion:

[0040] The collected values ​​are input into the numerical converter, and the input values ​​are converted according to the specified format.

[0041] S6. Data output:

[0042] The numerical values ​​are converted into numerical values ​​of different formats and output to a screen display through a numerical output device so that the staff can view them.

[0043] S7. Data analysis and calculation:

[0044] Analyze and compare the converted values ​​through the data analyzer;

[0045] Through manual calculation or analysis, convert the raw data into standard scores or Z scores for comparison, conduct preliminary exploration of the data through manual statistical analysis, drawing charts, etc., understand the distribution, trends and associations of the data, and use visual elements such as charts and images to intuitively display the characteristics of the data;

[0046] Use machine learning algorithms and deep learning models to train and learn from traffic data to predict future traffic flow and congestion.

[0047] Data application simulation end:

[0048] S8. Model establishment:

[0049] Select multiple different machine models, and output the values ​​obtained after analysis and calculation to different models through the parameter output system to facilitate subsequent simulation tests.

[0050] S9, scenario simulation:

[0051] The image simulator is used to refract and display the simulated traffic situation images, and the established model is used to simulate specific situations or problems. The simulation may involve the adjustment of input data, optimization of model parameters, etc.

[0052] S10. Data verification and analysis:

[0053] The data obtained by simulating multiple models is compared and analyzed through the data comparison analyzer, and the optimal model is obtained by comparison.

[0054] S11. Model adjustment:

[0055] The optimal data is calculated based on multiple models, and the model structure is improved, the model complexity is increased, the model parameters are adjusted, etc. based on the verification results. After adjustment to the optimal level, it is applied to urban transportation services.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] The present invention uses manual calculations with robots, and utilizes algorithms and techniques to process and analyze large amounts of data to extract useful information and insights. The combination of data robots can significantly improve the efficiency and accuracy of data processing, making the calculated data accurate and reliable.

[0058] In the present invention, a model system is established, and image processing technology and algorithms are used through an image simulator to simulate and predict images of future scenarios. Comparative analysis and statistical methods are used to evaluate the difference between the predicted results of the model and the actual data. The numerical parameters are adjusted according to the verification results to make the calculated data more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic diagram of the implementation process of an AI smart city service calculation method based on big data;

[0060] Figure 2 A schematic diagram of the data integration end structure of an AI smart city service computing method based on big data;

[0061] Figure 3 A schematic diagram of the data computing end structure of an AI smart city service computing method based on big data;

[0062] Figure 4 The present invention is a structural diagram of the data application simulation end of an AI smart city service computing method based on big data. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technical personnel in this field without creative work are within the scope of protection of the present invention.

[0064] See also Figures 1 to 4 , the present invention provides a technical solution: an AI smart city service calculation method based on big data, including a data integration end, a data calculation end and a data application simulation end, the data integration end is composed of a data integration system and a data management and storage system, the data integration system is composed of a sensor acquisition system, an image recognition system, a positioning system and a big data platform system, and the data management and storage system is composed of a data preprocessing system, a data storage system and a data security system;

[0065] The data computing end is composed of a data conversion system and a data analysis system. The data conversion system includes a data conversion system and a data output system, and the data analysis system includes an intelligent system.

[0066] The data application simulation end is composed of a data receiving system, a model building system, a model simulation system and an optimization system. The model building system includes a model selection system and a model building system. The model simulation system includes a scenario system. The optimization system includes a verification system and an adjustment system.

[0067] Furthermore, the sensor acquisition system includes a geomagnetic sensor, which can be embedded in the road surface to detect vehicle entry, exit, parking, speed and density in real time. These data can help urban traffic management departments better understand traffic conditions, including peak hours, congested sections and vehicle flow. Infrared sensors are sensors that can sense and detect high-speed moving targets through infrared optical principles. When a vehicle passes through an infrared sensor, an infrared signal is generated, which is sensed by the infrared sensor. The infrared sensor can monitor the number of vehicles on the road in real time and provide accurate traffic flow data for the traffic management department. By analyzing the infrared signal sensed by the infrared sensor, the speed of the vehicle can be calculated, thereby realizing real-time monitoring of the vehicle speed. Combined with the traffic flow data collected by the infrared sensor, the traffic management department can optimize and adjust the traffic lights to improve the efficiency and smoothness of road traffic pressure.

[0068] By measuring the pressure of the wheels on the road through sensors, the weight of the vehicle can be calculated, thereby realizing real-time monitoring of vehicle overload. Pressure sensors can monitor the stress conditions of the road when vehicles pass through, thereby evaluating the health and carrying capacity of the road. In rail transit, pressure sensors can be used to monitor the pressure of the train on the track, as well as the wear of the track and wheels.

[0069] The image recognition system includes an image sensor and a camera; the image sensor can capture high-definition images of vehicles and identify the type, color, license plate number and other information of the vehicle through image analysis technology. With the help of image sensors, the traffic management system can achieve real-time tracking and monitoring of vehicles, providing strong support for traffic law enforcement, vehicle dispatching, etc. In addition, the traffic images captured by the image sensor can analyze the traffic flow information such as vehicle density and speed on the road. These data have important reference value for traffic planning, signal light control, etc. The image sensor can monitor the vehicle situation at the traffic intersection in real time and dynamically adjust the control strategy of the signal light according to the number of vehicles, speed and other information, so as to reduce congestion and improve road traffic efficiency. The camera can capture traffic scenes in real time and provide image or video data for calculation and analysis. In addition, it can capture the dynamic information of pedestrians, such as walking speed and direction. By analyzing the behavior of pedestrians, it can predict the walking trajectory of pedestrians, provide data support for traffic planning, pedestrian protection, etc., and reduce traffic hazards caused by congestion.

[0070] The positioning system includes a GPS locator, which can provide real-time vehicle location information, enabling traffic management departments or vehicle owners to know the specific location of the vehicle at any time, helping to achieve accurate tracking and monitoring of vehicles, and improving the efficiency and safety of vehicle management. It can also collect vehicle location information and analyze data on traffic flow information such as vehicle density and speed on the road. This data is of great reference value for traffic planning, signal light control, traffic diversion, etc. It can also record information such as the vehicle's driving trajectory and speed, and provide data support for traffic violation detection.

[0071] The big data platform system includes public platform data and mobile phone signaling data. Public platform data can reflect the changes in traffic flow in real time, help traffic management departments to grasp the road congestion situation in a timely manner, and realize comprehensive monitoring and analysis of traffic conditions. By analyzing historical data, future traffic flow trends can be predicted, providing a scientific basis for traffic planning and management, and helping to more accurately grasp information such as changes in traffic flow, road congestion conditions, and user travel needs.

[0072] Further, the data preprocessing system includes a data processor;

[0073] The data storage system cleans, transforms and integrates the raw data to improve the quality and usability of the data. The data processor may use various algorithms and techniques, such as data smoothing, data transformation, data integration, etc., to eliminate noise, correct errors, fill missing values, and convert data into a form suitable for subsequent analysis or application. The data storage system includes data storage for long-term storage and management of data.

[0074] Data security systems include cloud processing systems, firewalls, intrusion detection systems, intrusion prevention systems, security event management systems, etc. Cloud processing systems provide cloud computing-based data processing and management services, which can ensure the secure storage and efficient processing of data in the cloud. Cloud processing systems usually have strong data encryption, access control and auditing functions to protect the confidentiality, integrity and availability of data. Firewalls are used to monitor and control traffic in and out of the network to prevent unauthorized access and data leakage. Firewalls can block the intrusion of malware and protect sensitive data in the network according to pre-set security policies, and intrusion detection systems can identify potential attack behaviors or abnormal activities. IDS analyzes traffic patterns or system logs and sends alerts to administrators once suspicious behavior is detected, thereby helping organizations to detect and respond to security threats in a timely manner and prevent data loss.

[0075] Further, the data conversion system includes a numerical converter;

[0076] The data output system includes a numerical output device, a screen display, internal memory, and numerical calculation software. The numerical output device converts raw data into a form suitable for a specific application or analysis, such as converting an analog signal into a digital signal, or converting one data format into another. This conversion helps to eliminate incompatibility issues between data and improve the processability and analyzability of data. The numerical output device is used to output the processed data in numerical form. This can include printouts, electronic displays, or other forms of numerical presentation. The numerical output device ensures the accuracy and readability of the data, allowing users to easily understand the meaning and trends of the data.

[0077] In the data output system, the screen display is used to present the processed data in the form of graphics, charts, text, etc. It helps users to understand the meaning and trend of the data more intuitively and improve the efficiency of data analysis and decision-making. The internal memory is used to store the processed data for subsequent use or analysis. The internal memory has the advantages of high-speed access and storage capacity, which can ensure fast reading and writing of data. Numerical calculation software is used to process and analyze data and generate visual output results. These software usually have powerful calculation and analysis functions and can handle various complex data sets and algorithms.

[0078] Furthermore, intelligent systems include artificial computing systems, data analyzers, and data robots. Data processing and analysis work performed by human experts or teams. Artificial computing systems can handle complex data sets and use professional knowledge and experience for in-depth analysis; use algorithms and techniques to process and analyze large amounts of data to extract useful information and insights. Data analyzers can process various types of data, including numerical data, text data, image data, etc., and are tools for automated processing and analysis of data. They can perform preset tasks such as data cleaning, data conversion, data visualization, etc. Data robots can significantly improve the efficiency and accuracy of data processing.

[0079] Furthermore, the model selection system includes machine learning models, digital models, and statistical models;

[0080] The model building system includes a parameter output system, which is responsible for outputting the parameters and configuration information of the model. These parameters and configuration information are crucial to the performance and accuracy of the model;

[0081] The scenario system includes an image simulator that uses image processing technology and algorithms to simulate and predict images of future scenarios. This helps us better understand future development trends and potential risks;

[0082] The validation system includes a data comparison analyzer, which uses comparative analysis and statistical methods to evaluate the difference between the model's prediction results and the actual data. This helps us identify potential problems in the model and directions for improvement;

[0083] The adjustment system includes the improvement system and the parameter value adjustment system, which is responsible for fine-tuning the parameters of the model according to the verification results. This helps us improve the accuracy and reliability of the model.

[0084] Further, the following steps are included:

[0085] Data integration end:

[0086] S1. Data Integration:

[0087] By installing various sensors such as geomagnetic sensors and infrared sensors at traffic intersections, road sections and vehicles, various sensors can be used to monitor traffic flow, vehicle speed, vehicle type and other information in real time;

[0088] Install cameras at traffic intersections or road sections to capture real-time images of traffic scenes, use computer vision and deep learning technology to identify and analyze images, and extract information about traffic participants such as vehicles and pedestrians, as well as their behaviors and movement trajectories;

[0089] Install GPS devices on vehicles to obtain real-time information such as the vehicle's precise location, speed, and direction of travel, analyze the vehicle's driving trajectory and traffic flow dynamics, and provide important basis for traffic planning and management;

[0090] Collect and analyze the communication signaling data of mobile phone users, infer the users' travel routes, dwelling time, transportation methods and other information, and use the traffic statistics, accident records, road network conditions and other data provided by the public data platform.

[0091] S2. Data processing:

[0092] The data processor in the master control system removes duplicate data collected in the database, fills in missing data, processes abnormal data, etc., and converts data from different sources into a unified format to facilitate subsequent processing and analysis.

[0093] S3, Data Storage:

[0094] Large-scale data is stored in the database through storage for subsequent retrieval and analysis.

[0095] S4. Data security:

[0096] Sensitive data is encrypted through firewalls, intrusion prevention systems, etc. to ensure data security.

[0097] Data calculation end:

[0098] S5. Data conversion:

[0099] The collected values ​​are input into the numerical converter, and the input values ​​are converted according to the specified format.

[0100] S6. Data output:

[0101] The numerical values ​​are converted into numerical values ​​of different formats and output to a screen display through a numerical output device so that the staff can view them.

[0102] S7. Data analysis and calculation:

[0103] Analyze and compare the converted values ​​through the data analyzer;

[0104] Through manual calculation or analysis, convert the raw data into standard scores or Z scores for comparison, conduct preliminary exploration of the data through manual statistical analysis, drawing charts, etc., understand the distribution, trends and associations of the data, and use visual elements such as charts and images to intuitively display the characteristics of the data;

[0105] Use machine learning algorithms and deep learning models to train and learn from traffic data to predict future traffic flow and congestion.

[0106] Data application simulation end:

[0107] S8. Model establishment:

[0108] Select multiple different machine models, and output the values ​​obtained after analysis and calculation to different models through the parameter output system to facilitate subsequent simulation tests.

[0109] S9, scenario simulation:

[0110] The image simulator is used to refract and display the simulated traffic situation images, and the established model is used to simulate specific situations or problems. The simulation may involve the adjustment of input data, optimization of model parameters, etc.

[0111] S10. Data verification and analysis:

[0112] The data obtained by simulating multiple models is compared and analyzed through the data comparison analyzer, and the optimal model is obtained by comparison.

[0113] S11. Model adjustment:

[0114] The optimal data is calculated based on multiple models, and the model structure is improved, the model complexity is increased, the model parameters are adjusted, etc. based on the verification results. After adjustment to the optimal level, it is applied to urban transportation services.

[0115] The above shows and describes the basic principles, main features and advantages of the present invention. Technical personnel in this industry should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A big data-based AI smart city service computing method, comprising a data integration end, a data computing end and a data application simulation end, characterized in that: The data integration end is composed of a data integration system and a data management and storage system. The data integration system is composed of a sensor acquisition system, an image recognition system, a positioning system and a big data platform system. The data management and storage system is composed of a data preprocessing system, a data storage system and a data security system. The data computing end is composed of a data conversion system and a data analysis system, wherein the data conversion system includes a data conversion system and a data output system, and the data analysis system includes an intelligent system; The data application simulation end is composed of a data receiving system, a model building system, a model simulation system and an optimization system. The model building system includes a model selection system and a model building system. The model simulation system includes a scenario system. The optimization system includes a verification system and an adjustment system.

2. The AI ​​smart city service calculation method based on big data according to claim 1 is characterized by: The sensor acquisition system includes a geomagnetic sensor, an infrared sensor and a pressure sensor; The image recognition system includes an image sensor and a camera; The positioning system includes a GPS locator; The big data platform system includes public platform data and mobile phone signaling data.

3. The AI ​​smart city service calculation method based on big data according to claim 1 is characterized by: The data preprocessing system includes a data processor; The data storage system includes a data storage device; Data security systems include cloud processing systems, firewalls, intrusion detection systems, intrusion prevention systems, security event management systems, etc.

4. The AI ​​smart city service calculation method based on big data according to claim 1 is characterized by: The data conversion system includes a numerical converter; The data output system includes a numerical output device, a screen display, an internal memory and numerical calculation software.

5. The AI ​​smart city service calculation method based on big data according to claim 1 is characterized by: The intelligent system includes an artificial computing system, a data analyzer and a data robot.

6. The AI ​​smart city service calculation method based on big data according to claim 1 is characterized by: The model selection system includes machine learning models, digital models, and statistical models; The model building system includes a parameter output system; The scenario system includes an image simulator; The verification system includes a data comparison analyzer; The adjustment system includes an improvement system and a parameter value adjustment system.

7. The big data-based AI smart city service calculation method according to claim 1 is characterized in that: The following steps are involved: Data integration end: S1. Data Integration: By installing various sensors such as geomagnetic sensors and infrared sensors at traffic intersections, road sections and vehicles, various sensors can be used to monitor traffic flow, vehicle speed, vehicle type and other information in real time; Install cameras at traffic intersections or road sections to capture real-time images of traffic scenes, use computer vision and deep learning technology to identify and analyze images, and extract information about traffic participants such as vehicles and pedestrians, as well as their behaviors and movement trajectories; Install GPS devices on vehicles to obtain real-time information such as the vehicle's precise location, speed, and direction of travel, analyze the vehicle's driving trajectory and traffic flow dynamics, and provide important basis for traffic planning and management; Collect and analyze the communication signaling data of mobile phone users, infer the users' travel routes, stay time and transportation methods, and use the traffic statistics, accident records, road network conditions and other data provided by the public data platform; S2. Data processing: The data processor in the master control system removes duplicate data collected in the database, fills in missing data, processes abnormal data, etc., and converts data from different sources into a unified format for subsequent processing and analysis; S3, Data Storage: Use storage to store large amounts of data in a database for subsequent retrieval and analysis; S4. Data security: Encrypt sensitive data through firewalls, intrusion prevention systems, etc. to ensure data security; Data calculation end: S5. Data conversion: Input the collected values ​​into the numerical converter and convert the input values ​​according to the specified format; S6. Data output: Convert the numerical value into a numerical value of a different format and output it to a screen display through a numerical output device so that the staff can view it; S7. Data analysis and calculation: Analyze and compare the converted values ​​through the data analyzer; Through manual calculation or analysis, convert the raw data into standard scores or Z scores for comparison, conduct preliminary exploration of the data through manual statistical analysis, drawing charts, etc., understand the distribution, trends and associations of the data, and use visual elements such as charts and images to intuitively display the characteristics of the data; Use machine learning algorithms and deep learning models to train and learn from traffic data to predict future traffic flow and congestion; Data application simulation end: S8. Model establishment: Select multiple different machine models, and output the values ​​obtained after analysis and calculation to different models through the parameter output system to facilitate subsequent simulation tests; S9, scenario simulation: The image simulator is used to refract and display the simulated traffic situation image, and the established model is used to simulate specific situations or problems. The simulation may involve the adjustment of input data, optimization of model parameters, etc. S10. Data verification analysis: The data obtained by simulating multiple models is compared and analyzed through the data comparison analyzer, and the optimal model is obtained by comparison; S11. Model adjustment: The optimal data is calculated based on multiple models, and the model structure is improved, the model complexity is increased, the model parameters are adjusted, etc. based on the verification results. After adjustment to the optimal level, it is applied to urban transportation services.

Images