Intelligent elevator networking route optimization method

Abstract

The application provides a smart elevator networking routing optimization method, relates to the technical field of intelligent routing optimization, and comprises the following steps: determining key performance indicators of different service types based on elevator operation data; generating a quality of service policy of the different service types according to the key performance indicators, wherein the quality of service policy is a priority setting and a quality of service parameter; constructing a network environment based on the quality of service policy through deployment of 5G network slices and edge computing nodes; and optimizing network conditions through an intelligent routing mechanism based on the constructed network environment.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of intelligent elevator networking routing optimization, and particularly relates to an intelligent elevator networking routing optimization method. BACKGROUND

[0002] With the acceleration of urbanization, large commercial complexes and high-rise buildings are increasing, and the importance of elevators as vertical transportation tools is increasingly prominent. Traditional elevator control systems rely heavily on local hardware devices, making it difficult to meet the needs of modern intelligent management. In recent years, the development of 5G network slicing technology and edge computing nodes has provided new opportunities for the construction of elevator networking systems. Through 5G network slicing, customized network services can be provided for different types of businesses (such as video monitoring, control system instructions, security alarms, etc.), ensuring high bandwidth, low latency, and high reliability. At the same time, edge computing nodes can perform real-time processing close to the data source, reducing transmission delay and improving response speed. However, despite these technological advances, existing systems still face many challenges in complex and changing network environments.

[0003] The main drawback of existing elevator networking systems is the lack of intelligent routing mechanisms and dynamic adjustment capabilities. First, routing decisions in traditional network environments are often based on static configurations and cannot be adjusted flexibly according to real-time network conditions, resulting in a decline in service quality when the network is congested or fails. Second, while 5G network slicing and edge computing have improved transmission efficiency, they have not fully combined deep learning algorithms to analyze network performance data, making it difficult to predict future trends and optimize path selection in advance. In addition, existing QoS strategies are usually set once and lack periodic evaluation and dynamic adjustment mechanisms, making it difficult to respond to changing business needs and technical environments in a timely manner. SUMMARY

[0004] The present application provides an intelligent elevator networking routing optimization method to address the technical problems of the lack of intelligent dynamic routing mechanisms and real-time network performance optimization in existing technologies.

[0005] The technical solution adopted by the present application is as follows: The present application provides an intelligent elevator networking routing optimization method, comprising: Based on elevator operation data, determine the key performance indicators of different business types; According to the key performance indicators, generate service quality strategies for different business types, including setting priorities and service quality parameters; Based on the service quality strategy, deploy 5G network slicing and edge computing nodes to build a network environment; Based on the constructed network environment, optimize the network conditions through an intelligent routing mechanism.

[0006] According to one embodiment of this application, determining the key performance indicators for different business types based on elevator operation data specifically includes: The elevator's operating data is collected using various sensors inside the elevator; The elevator operation data includes: physical status data, electrical system data, environmental conditions, user interaction data, safety and alarm information, maintenance and service history, video surveillance data, and other special data; Deep learning is used to analyze the elevator operation data to identify data characteristics under different business scenarios; Based on the data characteristics, the key performance indicators for the different business types are determined; The key performance indicators include: bandwidth, latency, jitter, and packet loss rate.

[0007] According to one embodiment of this application, the step of generating service quality strategies for different business types based on the key performance indicators, wherein the service quality strategy sets priorities and service quality parameters, specifically: Assign different priorities based on the importance of different business types; Set specific service quality parameters for each business type; The generated Quality of Service (QoS) policy is applied to all relevant network devices to ensure that the network devices can identify and process different types of data streams according to the set QoS policy.

[0008] According to one embodiment of this application, the quality of service parameters include: quality of service level and maximum number of connections.

[0009] According to one embodiment of this application, the construction of the network environment based on the quality of service strategy through the deployment of 5G network slicing and edge computing nodes specifically includes: According to the service quality policy, a request to create a dedicated 5G network slice is submitted through the API interface provided by the operator. Parameters that meet the needs of the elevator network service are customized. After receiving the confirmation information, the slice configuration is completed and integrated with the existing network architecture. Select a suitable geographical location near an area with high elevator density to install pre-configured edge computing server hardware, and remotely install and configure the operating system and the required application stack.

[0010] According to one embodiment of this application, the optimization of network conditions based on the constructed network environment through an intelligent routing mechanism specifically includes: Collect network status data and train a dynamic routing algorithm model in the cloud. The model can predict changes in network conditions over a period of time and generate the optimal path selection strategy. A multi-objective optimization algorithm is introduced to balance the relationship between multiple key performance indicators. The trained model is pushed to each edge computing node. The model on the node receives real-time network status updates and adjusts routing decisions according to the algorithm. When network congestion or failure is detected, it automatically switches to an alternative path.

[0011] According to one embodiment of this application, it further includes: setting a periodic evaluation mechanism to dynamically adjust by comparing expected goals with actual results; The dynamic adjustment specifically refers to: periodically collecting network performance data; The network performance data was analyzed in depth using big data analytics tools to identify potential problems and optimization opportunities. The collected network performance data is compared with pre-defined key performance indicators to evaluate whether the system performance meets expectations. Analyze the causes of the deviations and determine which parts need adjustment or improvement; Based on the analysis results, a detailed adjustment plan was developed, specifying the specific adjustment content, timetable, and responsible persons. Perform the corresponding operations according to the adjustment plan. After the adjustment is completed, continue to track the system performance to verify whether the adjustment has achieved the expected results.

[0012] An electronic device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method.

[0013] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method.

[0014] A computer program product containing instructions that, when run on a device, causes the device to perform the steps in implementing the method.

[0015] Due to the adoption of the above technical solution, the beneficial effects achieved by this application are as follows: This application significantly improves the transmission efficiency and service quality of the elevator network system by introducing an intelligent dynamic routing mechanism and real-time network performance optimization. First, based on the deployment of 5G network slicing and edge computing nodes, a flexible and efficient network environment is constructed, ensuring that different service types (such as video surveillance, control system commands, and security alarms) can obtain customized Quality of Service (QoS). Second, by collecting network status data and training a dynamic routing algorithm model in the cloud, accurate prediction of network condition changes over a future period is achieved, generating optimal path selection strategies, thereby effectively avoiding the impact of network congestion and failures on services. Furthermore, a multi-objective optimization algorithm is introduced to balance the relationship between multiple key performance indicators such as bandwidth, latency, jitter, and packet loss rate, ensuring that various service requirements are fully met. More importantly, a periodic evaluation mechanism is established to regularly collect network performance data and use big data analytics tools for in-depth analysis, identifying potential problems and optimization opportunities. The actual results are compared with preset targets, the causes of deviations are analyzed, detailed adjustment plans are formulated and strictly implemented, forming a closed-loop control to ensure that the system performance always meets expectations. These measures not only improved the system's intelligent management level but also enhanced its ability to adapt to complex and ever-changing network environments, further ensuring user experience and system security. This enabled the elevator network system to be continuously optimized on the basis of high efficiency, stability, and reliability, providing solid technical support for the construction of future smart cities. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a method for optimizing routing in an intelligent elevator network, as provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0017] Figure label: 810, Processor; 820, Communication interface; 830, Memory; 840, Communication bus. Detailed Implementation

[0018] To more clearly illustrate the overall concept of this application, a detailed explanation is provided below with reference to the accompanying drawings.

[0019] Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application may also be implemented in other ways different from those described herein. Therefore, the scope of protection of this application is not limited to the specific embodiments disclosed below. It should be noted that, unless otherwise specified, the embodiments of this application and the features thereof can be combined with each other.

[0020] In this application, unless otherwise expressly specified and limited, the "above" or "below" of the second feature can mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediate medium. In the description of this specification, references to terms such as "an embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples.

[0021] like Figure 1 As shown, a method for optimizing routing in an intelligent elevator network includes: Based on elevator operation data, key performance indicators for different business types are determined.

[0022] Specifically, the collection of elevator operation data Sensor deployment: Deploy various types of sensors in each elevator, including but not limited to physical status sensors (such as position, speed, door status, load weight, vibration), electrical system sensors (such as voltage, current, energy consumption, fault codes), environmental condition sensors (such as temperature, humidity, air quality), and user interaction devices (such as button operation records, call request panels).

[0023] Video surveillance system: Cameras are installed to obtain real-time video data inside and outside the elevator for safety monitoring and accident retrieval.

[0024] Data Analysis and Feature Recognition Historical data analysis: Utilizing big data analytics tools to perform deep learning on collected historical data to identify data characteristics under different business scenarios. For example: Video surveillance: requirements for high definition, frame rate, etc.

[0025] Status monitoring: frequency requirements, response time, etc.

[0026] Security alarm: The speed and accuracy of information transmission in emergency situations.

[0027] Maintenance and service: Regular inspection reports, predictive maintenance indicators, etc.

[0028] Define Key Performance Indicators (KPIs) Based on the above analysis, specific Key Performance Indicators (KPIs) are set for different service types. These KPIs will serve as the basis for subsequent Quality of Service (QoS) policies, ensuring that various applications receive appropriate processing and priority in complex network environments. Common KPIs include: Bandwidth: The amount of data that can be transmitted per unit of time. For example, video surveillance may require higher bandwidth to ensure image quality, while status monitoring may only require lower bandwidth.

[0029] Latency: The time interval between data transmission and reception. Low latency is crucial for applications with high real-time requirements, such as control system commands.

[0030] Jitter: Variation in the arrival time of data packets. Controlling jitter helps maintain stable communication, especially for latency-sensitive applications such as voice calls or video streaming.

[0031] Packet Loss Rate: The proportion of data packets lost during network transmission. Minimizing packet loss ensures the complete and error-free transmission of information, especially for reliability-sensitive data streams.

[0032] Availability: The percentage of time a system or service is up-to-date. Ensure that the elevator network system remains online and available almost at all times.

[0033] Reliability: The ability of a system to continuously provide its intended functionality. System reliability is enhanced by reducing the frequency of failures and improving recovery speed.

[0034] Response time: The time required for a system to respond to a request. Faster response times improve efficiency and enhance user experience.

[0035] Throughput: The amount of data successfully transmitted per unit of time. It measures the actual transmission capacity of a network and ensures efficient processing of large amounts of data.

[0036] Security: The ability to protect a system from unauthorized access or attacks. Ensuring all transmitted data is encrypted and secure.

[0037] Energy Consumption: The energy consumed by a system in operation. Optimizing energy consumption not only helps reduce operating costs but also extends equipment lifespan and meets energy conservation and environmental protection requirements.

[0038] Business type classification and priority setting Assign different priorities based on the importance of different business tasks. For example: Safety alert information: Highest priority, must be handled immediately to ensure passenger safety.

[0039] Control system commands: High priority, involving elevator operation and management, requiring timely response.

[0040] Video surveillance: Medium priority, important but some degree of delay is permissible.

[0041] Routine maintenance report: Low priority, to be processed without affecting other critical business operations.

[0042] For example, the collection of elevator operation data Data source Physical state sensors include position (floor), speed, door status, load weight, vibration, etc.

[0043] Electrical system sensors: voltage, current, energy consumption, fault codes.

[0044] Environmental condition sensors: temperature, humidity, air quality.

[0045] User interaction devices: button operation logs, call request panel.

[0046] Video surveillance system: Video data captured by cameras.

[0047] Data collection tools Built-in sensors, such as accelerometers, pressure sensors, and temperature sensors, are directly installed in key parts of the elevator to collect information on physical status and environmental conditions in real time.

[0048] Control system interface: Connects to the elevator's built-in control board or PLC to read electrical system and user interaction data.

[0049] External APIs or cloud platforms: For some advanced functions, such as video surveillance and remote management, data transmission and storage can be achieved by using APIs or cloud service platforms provided by third parties.

[0050] Data Analysis and Feature Recognition Use big data analytics tools to perform deep learning on collected historical data to identify data characteristics in different business scenarios. For example: Video surveillance: High definition is required at 720p / 1080p with a frame rate of 30fps to ensure clarity and smoothness.

[0051] Status monitoring: The frequency requirement is to update once per second, with a response time of less than 50ms, to ensure timely feedback on the elevator's operating status.

[0052] Security Alarm: In emergency situations, information transmission must be completed within 10ms to ensure a rapid response.

[0053] Maintenance and service: Regular inspection reports are generated weekly, and predictive maintenance indicators provide early warnings of potential problems one month in advance.

[0054] Define Key Performance Indicators (KPIs) Based on the above analysis, specific Key Performance Indicators (KPIs) are set for different business types. Here are a few specific examples: Video surveillance business Bandwidth: Approximately 10Mbps of uplink bandwidth is required per day on average to support high-definition video streaming.

[0055] Latency: The maximum allowable latency is 100ms to ensure the real-time performance and smoothness of the video stream.

[0056] Jitter: Keep it within 10ms to avoid video stuttering.

[0057] Packet loss rate: not exceeding 0.1%, ensuring that video quality is not affected.

[0058] Control system commands Delay: The maximum delay is no more than 10ms to ensure that control system commands can be executed quickly.

[0059] Jitter: Controlled within 1ms to maintain the stability of command transmission.

[0060] Packet loss rate: strictly controlled within 0.01% to ensure that instructions are transmitted completely and without error.

[0061] Security Alarm Priority: Highest priority, must be processed immediately.

[0062] Delay: The maximum delay is no more than 10ms, ensuring that passenger safety is guaranteed in a timely manner.

[0063] Reliability: Over 99.99% reliability ensures that alarm information will not be lost.

[0064] Routine maintenance report Bandwidth: Low bandwidth requirement, approximately 1Mbps is sufficient for daily upload needs.

[0065] Delay: The maximum delay shall not exceed 5 minutes, and a certain degree of delay is allowed.

[0066] Reliability: Over 99% reliability ensures timely report uploads.

[0067] Business type classification and priority setting Assign different priorities based on the importance of different business tasks. For example: Safety alert information: Highest priority, must be handled immediately to ensure passenger safety.

[0068] Control system commands: High priority, involving elevator operation and management, requiring timely response.

[0069] Video surveillance: Medium priority, important but some degree of delay is permissible.

[0070] Routine maintenance report: Low priority, to be processed without affecting other critical business operations.

[0071] Application scenario examples Suppose hundreds of elevators are deployed in a large commercial complex, generating massive amounts of surveillance video and other operational data daily. The optimization method provided by this invention: Demand Analysis: Through the automatic demand assessment module, it is determined that an average of about 10Mbps of uplink bandwidth is required per day, with a maximum latency of no more than 10ms and a maximum allowable packet loss rate of 0.1%.

[0072] KPI definition: For video surveillance services, the minimum guaranteed bandwidth is set at 10Mbps, the maximum allowable latency is 100ms, jitter is controlled within 10ms, and the packet loss rate is not more than 0.1%.

[0073] For control system commands, the maximum delay is set to 10ms, jitter is controlled within 1ms, and packet loss rate is strictly controlled within 0.01%.

[0074] For security alarm information, set the highest priority, with a maximum delay of no more than 10ms, and a reliability of over 99.99%.

[0075] For routine maintenance reports, set low bandwidth requirements (approximately 1 Mbps), maximum latency of no more than 5 minutes, and reliability of over 99%.

[0076] Furthermore, fault prediction can be introduced: by analyzing abnormal patterns in historical data through machine learning algorithms, potential faults can be predicted in advance, reducing sudden downtime.

[0077] Furthermore, preventative maintenance can be introduced: based on the forecast results, detailed maintenance plans can be developed, such as replacing worn parts or adjusting mechanical parameters, to extend equipment life and reduce maintenance costs.

[0078] Based on the key performance indicators, service quality strategies for different business types are generated, wherein the service quality strategies set priorities and service quality parameters.

[0079] Specifically, understanding Key Performance Indicators (KPIs) First, ensure that key performance indicators (KPIs) for different business types have been identified using elevator operation data. These KPIs include, but are not limited to, bandwidth, latency, jitter, and packet loss rate. For example: Video surveillance requires high bandwidth (e.g., 10Mbps), low latency (e.g., 100ms), and low jitter (e.g., 10ms).

[0080] Control system commands require very low latency (e.g., 10ms), minimal jitter (e.g., 1ms), and almost zero packet loss (e.g., 0.01%).

[0081] Security alarms require the highest priority, extremely low latency (e.g., 10ms), and high reliability (e.g., above 99.99%).

[0082] Set priority Different priorities are assigned based on the importance of different service types and their impact on the overall system. This step is crucial because it determines which types of traffic should be prioritized when network resources are limited. Specifically: Highest priority: Safety alerts. These messages are directly related to passenger safety and must be processed immediately without any delay.

[0083] High priority: Control system commands. These pertain to elevator operation and management; any delay could lead to operational errors or safety hazards.

[0084] Medium priority: Video surveillance. While important, a certain degree of delay is permissible; primarily used for post-event review or real-time monitoring.

[0085] Low priority: Routine maintenance reports and other non-critical business operations. These can be processed without affecting other critical business operations.

[0086] Define service quality parameters Specific Quality of Service (QoS) parameters are set for each service type. These parameters guide network devices on how to handle different types of data flows, ensuring they meet pre-defined performance standards. Common QoS parameters include: Bandwidth: Reserve sufficient bandwidth resources for different types of data streams to ensure that basic service quality can be maintained even when the network is congested.

[0087] Latency: Strictly control the latency of data transmission, especially for applications with high real-time requirements.

[0088] Jitter: Controls the variation in data packet arrival time to ensure stable transmission.

[0089] Packet Loss Rate: Minimize packet loss to ensure information is transmitted completely and accurately.

[0090] Maximum Connections: Limits the maximum number of concurrent connections allowed, ensuring that each connection receives appropriate resource allocation.

[0091] Quality of Service (or DSCP Marking): Differential Service Code Points (DSCP) or other similar markers are used to identify different types of data packets, allowing network devices to distinguish them and apply different processing strategies based on the markers.

[0092] Deployment and Implementation The generated Quality of Service (QoS) policy is applied to all relevant network devices to ensure that these devices can identify and process different types of data streams according to the set rules. The specific steps are as follows: Automation tools: Use automation tools to generate and deploy QoS policies, and easily set and modify parameters via command line or graphical user interface.

[0093] Hardware support: Ensure that the network devices used (such as routers and switches) have good QoS function support, can identify and distinguish different types of data packets, and perform corresponding scheduling and processing.

[0094] Configuration Updates: Regularly check and update QoS configurations to adapt to changing business needs and the technical environment.

[0095] Application scenario examples Suppose that hundreds of elevators are deployed in a large commercial complex, and the following business types and their corresponding KPIs have been identified: Video surveillance Bandwidth: 10Mbps Latency: 100ms Jitter: 10ms Packet loss rate: 0.1% Control system commands Latency: 10ms Jitter: 1ms Packet loss rate: 0.01% Security Alarm Priority: Highest Latency: 10ms Reliability: 99.99% Routine maintenance report Bandwidth: 1Mbps Delay: 5 minutes Reliability: 99% Based on the above KPIs, a corresponding service quality strategy can be generated: Video surveillance: The minimum guaranteed bandwidth is set to 10Mbps, the maximum allowable latency is 100ms, the jitter is controlled within 10ms, and the packet loss rate is not more than 0.1%.

[0096] Control system instructions: Set the maximum delay to 10ms, jitter to within 1ms, and packet loss rate to within 0.01%.

[0097] Security alarm: Set to the highest priority, with a maximum delay of no more than 10ms and a reliability of over 99.99%.

[0098] Routine maintenance report: Set low bandwidth requirements (approximately 1Mbps), maximum latency not exceeding 5 minutes, and reliability exceeding 99%.

[0099] For example, an application scenario: elevator network systems in large commercial complexes. Identify Key Performance Indicators (KPIs) Assume that the following KPIs for different business types have been obtained through data analysis: Video surveillance: Bandwidth: 10Mbps Latency: 100ms Jitter: 10ms Packet loss rate: 0.1% Control system commands: Latency: 10ms Jitter: 1ms Packet loss rate: 0.01% Security Alarm: Priority: Highest Latency: 10ms Reliability: 99.99% Routine maintenance report: Bandwidth: 1Mbps Delay: 5 minutes Reliability: 99% Set priority Different priorities are assigned based on the importance of different business operations and their impact on the overall system: Safety alarm information: highest priority, must be handled immediately to ensure passenger safety.

[0100] Control system commands: High priority, involving elevator operation and management, requiring timely response.

[0101] Video surveillance: Medium priority, important but some degree of delay is permissible.

[0102] Routine maintenance report: Low priority, to be processed without affecting other critical business operations.

[0103] Define Quality of Service (QoS) parameters. Specific service quality parameters are set for each service type to ensure that it meets pre-defined performance standards: Video surveillance: Bandwidth: Minimum guaranteed bandwidth is 10Mbps.

[0104] Latency: The maximum allowed latency is 100ms.

[0105] Jitter: Controlled within 10ms.

[0106] Packet loss rate: not exceeding 0.1%.

[0107] Control system commands: Latency: Maximum latency is 10ms.

[0108] Jitter: Controlled within 1ms.

[0109] Packet loss rate: strictly controlled within 0.01%.

[0110] Security Alarm: Priority: Highest.

[0111] Latency: Maximum latency not exceeding 10ms.

[0112] Reliability: 99.99% or higher.

[0113] Routine maintenance report: Bandwidth: Low bandwidth requirement, approximately 1 Mbps.

[0114] Delay: Maximum delay not exceeding 5 minutes.

[0115] Reliability: Over 99%.

[0116] Generate service quality strategy Based on the above KPIs and priority settings, a corresponding quality of service policy is generated and applied to all relevant network devices. For example: Video surveillance: QoS Policy: Set the DSCP flag to "AF41" to ensure that this type of data flow receives high priority processing even during network congestion. Simultaneously, configure routers and switches to guarantee at least 10Mbps bandwidth, limit the maximum latency to 100ms, control jitter within 10ms, and ensure a packet loss rate of no more than 0.1%.

[0117] Control system commands: QoS Policy: Set the DSCP flag to "EF" (Expedited Forwarding) and give it the highest priority to ensure real-time performance and reliability. Configure routers and switches to guarantee a maximum latency of 10ms, jitter within 1ms, and packet loss rate strictly controlled within 0.01%.

[0118] Security Alarm: QoS Policy: Set the DSCP flag to "CS7" and assign it the highest absolute priority to ensure rapid information transmission in emergencies. Configure routers and switches to guarantee a maximum latency of no more than 10ms and a reliability of over 99.99%.

[0119] Routine maintenance report: QoS Policy: Set the DSCP flag to "BE" (Best Effort) for lower priority, but process it without affecting other critical services. Configure routers and switches to guarantee at least 1Mbps bandwidth, maximum latency of no more than 5 minutes, and reliability of over 99%.

[0120] Deployment and Implementation The generated Quality of Service (QoS) policy is applied to all relevant network devices to ensure that these devices can identify and process different types of data streams according to the set rules: Automation tools: Use automation tools to generate and deploy QoS policies, and easily set and modify parameters via command line or graphical user interface.

[0121] Hardware support: Ensure that the network devices used (such as routers and switches) have good QoS function support, can identify and distinguish different types of data packets, and perform corresponding scheduling and processing.

[0122] Configuration Updates: Regularly check and update QoS configurations to adapt to changing business needs and the technical environment.

[0123] Specific examples Suppose that hundreds of elevators are deployed in a large commercial complex, and the following business types and their corresponding KPIs have been identified: Video surveillance Bandwidth: 10Mbps Latency: 100ms Jitter: 10ms Packet loss rate: 0.1% Control system commands Latency: 10ms Jitter: 1ms Packet loss rate: 0.01% Security Alarm Priority: Highest Latency: 10ms Reliability: 99.99% Routine maintenance report Bandwidth: 1Mbps Delay: 5 minutes Reliability: 99% Based on the above KPIs, the corresponding service quality strategy can be generated as follows: Video surveillance: QoS policy: Set the minimum guaranteed bandwidth to 10Mbps, the maximum allowable latency to 100ms, jitter to within 10ms, and packet loss rate to no more than 0.1%.

[0124] DSCP Mark: AF41 Control system commands: QoS policy: Set the maximum latency to 10ms, jitter to within 1ms, and packet loss rate to within 0.01%.

[0125] DSCP Marker: EF Security Alarm: QoS policy: Set the highest priority, with a maximum latency of no more than 10ms and a reliability of over 99.99%.

[0126] DSCP Marker: CS7 Routine maintenance report: QoS policy: Set low bandwidth requirements (approximately 1Mbps), maximum latency not exceeding 5 minutes, and reliability exceeding 99%.

[0127] DSCP Marker: BE Furthermore, real-time monitoring and feedback can be introduced: establish a real-time monitoring system to continuously track changes in network performance and business requirements.

[0128] Furthermore, adaptive QoS policies can be introduced: automatically adjusting the quality of service policy based on real-time data to ensure optimal service is provided even when network conditions change. Furthermore, passenger flow prediction can be introduced: by combining elevator operation data and other sensor information, passenger flow at different times can be predicted to optimize elevator scheduling.

[0129] Furthermore, personalized user experiences can be introduced: based on user behavior data analysis, customized services can be provided, such as fast track reservations and floor recommendations.

[0130] Based on the aforementioned quality of service strategy, a network environment is constructed through the deployment of 5G network slicing and edge computing nodes.

[0131] Specifically, understand the Quality of Service (QoS) policy. Before constructing the network environment, service quality policies for different types of services were generated based on key performance indicators (KPIs). These policies include setting priorities and service quality parameters such as bandwidth, latency, jitter, and packet loss rate. For example: Video surveillance: minimum guaranteed bandwidth of 10Mbps, maximum allowable latency of 100ms, jitter control within 10ms, and packet loss rate not exceeding 0.1%.

[0132] Control system instructions: maximum delay is 10ms, jitter is controlled within 1ms, and packet loss rate is strictly controlled within 0.01%.

[0133] Security alarm: highest priority, maximum delay not exceeding 10ms, reliability reaching over 99.99%.

[0134] Routine maintenance report: Low bandwidth requirement (approximately 1 Mbps), maximum latency not exceeding 5 minutes, and reliability exceeding 99%.

[0135] 5G network slicing application and configuration To meet the specific needs of different service types, dedicated 5G network slices need to be created. This involves the following steps: Requirements Analysis: Based on the performance requirements in the QoS policy, determine the required network slicing parameters, such as bandwidth, number of connections, and latency.

[0136] API calls: Submitting requests to create dedicated 5G network slices through the APIs provided by the operator. These APIs typically include: Create a slice: Define the slice name, type, service level agreement (SLA), and other information.

[0137] Configuration parameters: Set specific network parameters, such as bandwidth allocation, maximum number of connections, latency limits, etc.

[0138] Confirmation and Integration: Upon receiving confirmation from the operator, complete the slice configuration and integrate it with the existing network architecture. Ensure that the new slice can seamlessly connect to the existing elevator network system.

[0139] Deployment of edge computing nodes The deployment of edge computing nodes aims to enable local data processing and rapid response, reducing pressure on the core network and lowering latency. The specific steps are as follows: Site selection planning: Choose a suitable geographical location near areas with high elevator density to install the pre-configured edge computing server hardware. The following factors should be considered when selecting a location: Physical distance: Get as close as possible to the elevator equipment to reduce transmission delay.

[0140] Network coverage: Ensure good 5G signal coverage and guarantee a stable communication link.

[0141] Power supply: It has reliable power supply facilities to avoid service interruptions due to power outages.

[0142] Hardware installation: Install the edge computing server hardware according to the manufacturer's guidelines and make the necessary physical connections (such as power cords and network cables).

[0143] Remote configuration: Installing and configuring the operating system and required application stack using remote management tools. Configuration includes: Operating System: Choose an operating system suitable for the edge computing environment, such as a Linux distribution.

[0144] Applications: Deploy necessary application software, such as tools for video processing and data analysis.

[0145] Security settings: Configure security measures such as firewalls and intrusion detection systems (IDS) to protect edge nodes from attacks.

[0146] Network environment construction and optimization Once 5G network slicing and edge computing nodes are deployed, the next step is to build a complete network environment and optimize it to ensure efficient operation: Resource allocation: Allocate network resources reasonably according to QoS policies to ensure that each service type can obtain the required bandwidth, latency and other performance parameters.

[0147] Intelligent routing mechanism: Introduces intelligent routing algorithms to monitor network status in real time and dynamically adjust data transmission paths. For example: Path selection: Select the optimal path based on the current network conditions to improve transmission efficiency.

[0148] Fault recovery: When network congestion or failure is detected, the system automatically switches to a backup path to ensure service continuity.

[0149] Multi-objective optimization: Using multi-objective optimization algorithms to balance the relationship between multiple performance metrics, such as latency, bandwidth and reliability, to ensure that overall transmission efficiency is maximized.

[0150] Continuous monitoring and feedback: Establish a continuous monitoring platform to collect network performance data and regularly evaluate system performance. Continuously adjust and optimize QoS policies and network configurations based on actual results.

[0151] Application scenario examples Suppose that hundreds of elevators are deployed in a large commercial complex, and an efficient elevator network system has been built using the method described above: 5G network slicing: Video surveillance slicing: Reserve at least 10Mbps of bandwidth for video surveillance services to ensure high-definition image transmission.

[0152] Control system command slice: Provides a communication channel with extremely low latency (less than 10ms) and high reliability (above 99.99%).

[0153] Security Alarm Slicing: Assigned the highest priority to ensure rapid information transmission in emergency situations.

[0154] Edge computing nodes: Edge computing servers are installed in areas with a high concentration of elevators to handle local video processing, data analysis, and other functions.

[0155] Configure the server to support tasks such as video stream decoding and image recognition, reducing reliance on the core network.

[0156] Network environment optimization: Intelligent routing algorithms are used to dynamically adjust transmission paths, ensuring that high-quality service levels are maintained even when network conditions change.

[0157] Regularly check network performance and adjust QoS parameters based on actual results to maintain optimal system operation.

[0158] For example, understanding Quality of Service (QoS) policies. The following service types and their corresponding QoS policies have been identified: Video surveillance: Bandwidth: Minimum guaranteed bandwidth is 10Mbps.

[0159] Latency: The maximum allowed latency is 100ms.

[0160] Jitter: Controlled within 10ms.

[0161] Packet loss rate: not exceeding 0.1%.

[0162] Control system commands: Latency: Maximum latency is 10ms.

[0163] Jitter: Controlled within 1ms.

[0164] Packet loss rate: strictly controlled within 0.01%.

[0165] Security Alarm: Priority: Highest.

[0166] Latency: Maximum latency not exceeding 10ms.

[0167] Reliability: 99.99% or higher.

[0168] Routine maintenance report: Bandwidth: Low bandwidth requirement, approximately 1 Mbps.

[0169] Delay: Maximum delay not exceeding 5 minutes.

[0170] Reliability: Over 99%.

[0171] 5G network slicing application and configuration Requirements Analysis Based on the above QoS policy, determine the required network slice parameters: Video surveillance slices: Bandwidth: 10Mbps Maximum latency: 100ms Jitter: 10ms Packet loss rate: 0.1% Control system instruction slices: Latency: 10ms Jitter: 1ms Packet loss rate: 0.01% Security alarm slice: Priority: Highest Latency: 10ms Reliability: 99.99% Routine maintenance report slice: Bandwidth: 1Mbps Delay: 5 minutes Reliability: 99% API interface call Submit a request to create a dedicated 5G network slice through the API interface provided by the operator: Create a slice: Define the slice name, type, and service level agreement (SLA), such as "video surveillance slice" or "control system command slice".

[0172] Configuration parameters: Set specific network parameters, such as bandwidth allocation, maximum number of connections, latency limits, etc.

[0173] Confirmation and Integration: Upon receiving confirmation from the operator, complete the slice configuration and integrate it with the existing network architecture. Ensure that the new slice can seamlessly connect to the existing elevator network system.

[0174] For example, for "control system instruction slices", a possible API call example is as follows: { "slice_name": "Control System Command Slice", "type": "high priority", "sla": { "delay": "10ms", "jitter": "1ms", "packet_loss_rate": "0.01%" } } Deployment of edge computing nodes Site selection planning Choose a suitable geographical location to install pre-configured edge computing server hardware. For example, select a location near areas with high elevator density (such as the main entrance of a shopping mall or the exit of a parking lot) to reduce transmission latency and ensure good 5G signal coverage.

[0175] Hardware installation Install the edge computing server hardware according to the manufacturer's guidelines and make the necessary physical connections (such as power cords and network cables).

[0176] Remote configuration Install and configure the operating system and required application stack using remote management tools: Operating System: Choose an operating system suitable for the edge computing environment, such as Ubuntu Server.

[0177] Applications: Deploy necessary application software, such as video processing and data analysis tools.

[0178] Security settings: Configure security measures such as firewalls and intrusion detection systems (IDS) to protect edge nodes from attacks.

[0179] For example, possible configurations for video surveillance edge nodes include: Operating System: Ubuntu Server 20.04 LTS Applications: FFmpeg for video stream decoding, TensorFlow for image recognition. Security settings: UFW firewall, Suricata IDS Network environment construction and optimization Once 5G network slicing and edge computing nodes are deployed, the next step is to build a complete network environment and optimize it to ensure efficient operation: Resource allocation Network resources should be allocated reasonably according to QoS policies to ensure that each service type receives the required bandwidth, latency, and other performance parameters. For example: Video surveillance: Allocate 10Mbps bandwidth to ensure high-definition image transmission.

[0180] Control system commands: Provides a communication channel with extremely low latency (less than 10ms) and high reliability (above 99.99%).

[0181] Security Alarm: Assign the highest priority to ensure rapid information transmission in emergency situations.

[0182] Intelligent routing mechanism Intelligent routing algorithms are introduced to monitor network status in real time and dynamically adjust data transmission paths. For example: Path selection: Select the optimal path based on the current network conditions to improve transmission efficiency.

[0183] Fault recovery: When network congestion or failure is detected, the system automatically switches to a backup path to ensure service continuity.

[0184] Multi-objective optimization Multi-objective optimization algorithms are used to balance the relationship between multiple performance metrics, such as latency, bandwidth, and reliability, to ensure that overall transmission efficiency is maximized.

[0185] Continuous monitoring and feedback Establish a continuous monitoring platform to collect network performance data and regularly evaluate system performance. Continuously adjust and optimize QoS policies and network configurations based on actual results.

[0186] Specific examples Suppose that hundreds of elevators are deployed in a large commercial complex, and an efficient elevator network system has been built using the method described above: 5G network slicing: Video surveillance slicing: Reserve at least 10Mbps of bandwidth for video surveillance services to ensure high-definition image transmission.

[0187] Control system command slice: Provides a communication channel with extremely low latency (less than 10ms) and high reliability (above 99.99%).

[0188] Security Alarm Slicing: Assigned the highest priority to ensure rapid information transmission in emergency situations.

[0189] Edge computing nodes: Edge computing servers are installed in areas with a high concentration of elevators to handle local video processing, data analysis, and other functions.

[0190] Configure the server to support tasks such as video stream decoding and image recognition, reducing reliance on the core network.

[0191] Network environment optimization: Intelligent routing algorithms are used to dynamically adjust transmission paths, ensuring that high-quality service levels are maintained even when network conditions change.

[0192] Regularly check network performance and adjust QoS parameters based on actual results to maintain optimal system operation.

[0193] Furthermore, an intelligent scheduling system can be introduced: develop an intelligent scheduling system to dynamically adjust the elevator allocation scheme and improve transportation efficiency.

[0194] Furthermore, a mobile application could be introduced: a companion mobile application could be launched, allowing users to book elevators, check arrival times, and obtain other relevant information.

[0195] Furthermore, a comprehensive scoring mechanism can be introduced: establish a multi-dimensional performance evaluation system that not only considers traditional indicators such as bandwidth and latency, but also incorporates factors such as user experience and environmental impact.

[0196] Furthermore, a feedback loop can be introduced: forming a continuously improving feedback loop that optimizes various KPIs and their corresponding QoS strategies based on actual results.

[0197] Based on the constructed network environment, the network conditions are optimized through an intelligent routing mechanism.

[0198] Specifically, understanding intelligent routing mechanisms Intelligent routing mechanisms refer to the introduction of intelligent algorithms and technologies into the network environment to dynamically adjust data transmission paths, ensuring a high-quality service level even when network conditions change. This mechanism can predict network condition changes over a future period and generate optimal path selection strategies, thereby improving transmission efficiency, reducing latency and jitter, and decreasing packet loss.

[0199] Key components of intelligent routing mechanisms Data collection and analysis Network status data: Real-time collection of network status data from 5G network slices, edge computing nodes and other related devices, including key performance indicators (KPIs) such as bandwidth utilization, latency, jitter and packet loss rate.

[0200] Machine learning model training: Train dynamic routing algorithm models on cloud or edge computing nodes. These models can predict future changes in network conditions based on historical data and real-time updated data.

[0201] Dynamic routing algorithm Multi-objective optimization algorithms: Introducing multi-objective optimization algorithms, such as linear programming and genetic algorithms, to balance the relationships between multiple KPIs and ensure maximum overall transmission efficiency. For example, minimizing bandwidth usage while maintaining low latency.

[0202] Path selection strategy: Based on the prediction results, an optimal path selection strategy is generated to select the best transmission path to meet the needs of different service types. For example, for high-priority security alarm information, the shortest path is selected to ensure minimal latency; while for video surveillance, a certain degree of latency can be tolerated, but higher bandwidth is required.

[0203] Automated decision-making and execution Real-time adjustment: The intelligent routing algorithm on the node receives real-time network status updates and automatically adjusts routing decisions according to preset rules. When network congestion or failure is detected, it automatically switches to an alternative path to ensure service continuity.

[0204] Feedback loop: Establish a continuous monitoring platform to periodically evaluate the effectiveness of the intelligent routing mechanism and continuously optimize the algorithm parameters based on the actual results, forming a closed-loop control system.

[0205] Specific implementation steps Collect network status data Sensors and API Interfaces: Utilize various sensors deployed in the network (such as traffic monitors and QoS probes) and API interfaces provided by operators to acquire network status data in real time.

[0206] Data aggregation and storage: The collected data is sent to the cloud or edge computing nodes for aggregation and storage, providing a foundation for subsequent analysis.

[0207] Training the dynamic routing algorithm model Data preprocessing: Perform preprocessing operations such as cleaning and normalization on the raw data to ensure the quality of the data used for training.

[0208] Model selection and training: Select a suitable machine learning model (such as random forest, support vector machine, neural network) and train it using historical data and real-time updated data so that it can accurately predict future changes in network conditions.

[0209] Model validation and optimization: Model parameters are optimized through methods such as cross-validation and grid search to ensure their generalization ability and prediction accuracy.

[0210] Deployment and application of intelligent routing algorithms Model distribution: The trained model is pushed to each edge computing node to ensure that each node can make the optimal routing decision based on the latest network conditions.

[0211] Real-time adjustment: The intelligent routing algorithm on the node receives real-time network status updates and dynamically adjusts routing decisions based on the prediction results. For example, when congestion is detected on a certain path, it automatically switches to another available path to avoid data transmission interruption.

[0212] Continuous monitoring and feedback Performance evaluation: Regularly collect network performance data to evaluate the actual effectiveness of the intelligent routing mechanism. For example, check whether the expected latency, jitter, and packet loss rates have been achieved.

[0213] Feedback optimization: Adjust the parameter settings of the intelligent routing algorithm based on the evaluation results to continuously improve the system's performance.

[0214] Application scenario examples Suppose a large commercial complex has deployed hundreds of elevators and has already built an efficient elevator network system: Network status data collection: By using sensors and APIs deployed in the network, network status data such as bandwidth utilization, latency, jitter, and packet loss rate can be collected in real time.

[0215] This data is sent to the cloud or edge computing nodes for aggregation and storage, providing a foundation for subsequent analysis.

[0216] Training the dynamic routing algorithm model: A dynamic routing algorithm model is trained in the cloud, which can predict changes in network conditions over a future period and generate the optimal path selection strategy.

[0217] The model is trained using historical and real-time updated data, and its parameters are optimized through cross-validation and grid search to ensure its predictive accuracy.

[0218] Deploying and applying intelligent routing algorithms: The trained model is pushed to each edge computing node to ensure that each node can make the optimal routing decision based on the latest network conditions.

[0219] When network congestion or failure is detected, the system automatically switches to an alternative path to ensure service continuity and data transmission stability.

[0220] Continuous monitoring and feedback: Regularly collect network performance data to evaluate the actual effectiveness of the intelligent routing mechanism.

[0221] Adjust the parameter settings of the intelligent routing algorithm based on the evaluation results to continuously improve the system's performance.

[0222] For example, understanding the current network environment A network environment incorporating 5G network slices and edge computing nodes was constructed based on a Quality of Service (QoS) policy. This environment includes the following service types and their corresponding QoS requirements: Video surveillance: Bandwidth: Minimum guaranteed bandwidth is 10Mbps.

[0223] Latency: The maximum allowed latency is 100ms.

[0224] Jitter: Controlled within 10ms.

[0225] Packet loss rate: not exceeding 0.1%.

[0226] Control system commands: Latency: Maximum latency is 10ms.

[0227] Jitter: Controlled within 1ms.

[0228] Packet loss rate: strictly controlled within 0.01%.

[0229] Security Alarm: Priority: Highest.

[0230] Latency: Maximum latency not exceeding 10ms.

[0231] Reliability: 99.99% or higher.

[0232] Routine maintenance report: Bandwidth: Low bandwidth requirement, approximately 1 Mbps.

[0233] Delay: Maximum delay not exceeding 5 minutes.

[0234] Reliability: Over 99%.

[0235] Key components of intelligent routing mechanisms Data collection and analysis Network status data: Real-time collection of network status data from 5G network slices, edge computing nodes and other related devices, including key performance indicators (KPIs) such as bandwidth utilization, latency, jitter and packet loss rate.

[0236] Machine learning model training: Train dynamic routing algorithm models on cloud or edge computing nodes. These models can predict future changes in network conditions based on historical data and real-time updated data.

[0237] Dynamic routing algorithm Multi-objective optimization algorithm: Introduce multi-objective optimization algorithms, such as linear programming and genetic algorithms, to balance the relationship between multiple KPIs and ensure that the overall transmission efficiency is maximized.

[0238] Path selection strategy: Generate the optimal path selection strategy based on the prediction results, and select the best transmission path to meet the needs of different service types.

[0239] Automated decision-making and execution Real-time adjustment: The intelligent routing algorithm on the node receives real-time network status updates and automatically adjusts routing decisions according to preset rules.

[0240] Feedback loop: Establish a continuous monitoring platform to periodically evaluate the effectiveness of the intelligent routing mechanism and continuously optimize the algorithm parameters based on the actual results.

[0241] Specific implementation steps Collect network status data Sensors and API Interfaces: Utilize various sensors deployed in the network (such as traffic monitors and QoS probes) and API interfaces provided by operators to acquire network status data in real time.

[0242] Data aggregation and storage: The collected data is sent to the cloud or edge computing nodes for aggregation and storage, providing a foundation for subsequent analysis.

[0243] Training the dynamic routing algorithm model Data preprocessing: Perform preprocessing operations such as cleaning and normalization on the raw data to ensure the quality of the data used for training.

[0244] Model selection and training: Select a suitable machine learning model (such as random forest, support vector machine, neural network) and train it using historical data and real-time updated data so that it can accurately predict future changes in network conditions.

[0245] Model validation and optimization: Model parameters are optimized through methods such as cross-validation and grid search to ensure their generalization ability and prediction accuracy.

[0246] Deployment and application of intelligent routing algorithms Model distribution: The trained model is pushed to each edge computing node to ensure that each node can make the optimal routing decision based on the latest network conditions.

[0247] Real-time adjustment: The intelligent routing algorithm on the node receives real-time network status updates and dynamically adjusts routing decisions based on the prediction results. For example, when congestion is detected on a certain path, it automatically switches to another available path to avoid data transmission interruption.

[0248] Continuous monitoring and feedback Performance evaluation: Regularly collect network performance data to evaluate the actual effectiveness of the intelligent routing mechanism.

[0249] Feedback optimization: Adjust the parameter settings of the intelligent routing algorithm based on the evaluation results to continuously improve the system's performance.

[0250] Specific examples Suppose a large commercial complex has deployed hundreds of elevators and has already built an efficient elevator network system: Network status data collection: By using sensors and APIs deployed in the network, network status data such as bandwidth utilization, latency, jitter, and packet loss rate can be collected in real time.

[0251] This data is sent to the cloud or edge computing nodes for aggregation and storage, providing a foundation for subsequent analysis.

[0252] Training the dynamic routing algorithm model: A dynamic routing algorithm model is trained in the cloud, which can predict changes in network conditions over a future period and generate the optimal path selection strategy.

[0253] The model is trained using historical and real-time updated data, and its parameters are optimized through cross-validation and grid search to ensure its predictive accuracy.

[0254] Deploying and applying intelligent routing algorithms: The trained model is pushed to each edge computing node to ensure that each node can make the optimal routing decision based on the latest network conditions.

[0255] When network congestion or failure is detected, the system automatically switches to an alternative path to ensure service continuity and data transmission stability.

[0256] Continuous monitoring and feedback: Regularly collect network performance data to evaluate the actual effectiveness of the intelligent routing mechanism.

[0257] Adjust the parameter settings of the intelligent routing algorithm based on the evaluation results to continuously improve the system's performance.

[0258] Examples of practical application scenarios Example 1: Optimization of video surveillance services Background: Video surveillance requires high bandwidth and low jitter to ensure the clarity and smoothness of image transmission.

[0259] Problem: During peak hours, the simultaneous uploading of a large number of video streams may cause network congestion, affecting video quality.

[0260] Solution: Data collection: Real-time monitoring of bandwidth utilization and jitter on each path using sensors deployed in the network.

[0261] Model training: Use historical data to train a prediction model to predict which paths are likely to become congested in the future.

[0262] Path selection: The intelligent routing algorithm adjusts the transmission path of the video stream in advance based on the prediction results, selecting a path with sufficient bandwidth and less jitter.

[0263] Real-time adjustment: When congestion is detected on a certain path, it automatically switches to another available path to ensure the stability and quality of video transmission.

[0264] Example 2: Optimization of Control System Commands Background: Control system commands require extremely low latency and high reliability; any delay may lead to operational errors or safety hazards.

[0265] Problem: In the event of network instability, control system commands may be affected by delays.

[0266] Solution: Data collection: Real-time monitoring of network latency and packet loss rate, especially for dedicated 5G slices for control system commands.

[0267] Model training: Train a specialized prediction model, focusing on optimizing the selection of low-latency paths.

[0268] Path selection: The intelligent routing algorithm prioritizes the shortest path to ensure that control system commands can reach the destination within 10ms.

[0269] Real-time adjustment: Once a delay exceeds the set threshold, immediately switch to the backup path to ensure timely delivery of instructions.

[0270] Example 3: Optimization of security alarm information Background: Security alarm information must have the highest priority to ensure that information can be transmitted quickly in emergency situations.

[0271] Problem: Security alerts may not be delivered in a timely manner during network congestion or failure.

[0272] Solution: Data collection: Real-time monitoring of network status, especially dedicated 5G slices for security alarm information.

[0273] Model training: Train a specialized prediction model to ensure that the optimal path can be found under any circumstances.

[0274] Path selection: The intelligent routing algorithm assigns the highest priority to security alarm information, ensuring that it always selects the shortest path.

[0275] Real-time adjustment: Once a network failure or congestion is detected, an alternative path is immediately activated to ensure that alarm information can be transmitted within 10ms.

[0276] Furthermore, cross-system data sharing can be introduced: connecting the elevator network with other urban infrastructure (such as traffic management, public safety, etc.) to form a smart city ecosystem on a larger scale.

[0277] Furthermore, we can explore synergistic effects: study the synergistic effects between different systems, such as optimizing elevator scheduling through traffic data, or using elevator passenger flow data to assist urban planning decisions.

[0278] In some embodiments of this application, determining the key performance indicators for different business types based on elevator operation data specifically includes: The elevator's operating data is collected using various sensors inside the elevator; The elevator operation data includes: physical status data, electrical system data, environmental conditions, user interaction data, safety and alarm information, maintenance and service history, video surveillance data, and other special data; Deep learning is used to analyze the elevator operation data to identify data characteristics under different business scenarios; Based on the data characteristics, the key performance indicators for the different business types are determined; The key performance indicators include: bandwidth, latency, jitter, and packet loss rate.

[0279] Specifically, the type of sensor and the data collected. Physical state data: including elevator position, speed, acceleration, door status, etc.

[0280] Electrical system data: such as current, voltage, power consumption, motor temperature, etc.

[0281] Environmental conditions: such as temperature, humidity, and air quality inside the car.

[0282] User interaction data includes passenger button operations, call buttons, floor selections, etc.

[0283] Safety and alarm information: such as emergency stop button activation, fault alarm, smoke detector trigger, etc.

[0284] Maintenance and service history: Records information such as the time, content, and parts replaced for each maintenance.

[0285] Video surveillance data: Video streams from cameras installed inside the elevator, used for monitoring and playback.

[0286] Other special data: such as elevator vibration, abnormal noise detection, etc.

[0287] Data acquisition methods Real-time monitoring: Various types of sensors are used to monitor the above parameters in real time and transmit the data to the central processing unit or cloud platform.

[0288] Regular uploads: Certain data (such as maintenance and service history) can be uploaded to the cloud regularly for long-term analysis and archiving.

[0289] Deep learning is used to analyze elevator operation data and identify data characteristics in different business scenarios. Applications of deep learning Model training: Deep learning models, such as convolutional neural networks (CNN), recurrent neural networks (RNN), or long short-term memory networks (LSTM), are trained using a large amount of historical elevator operation data to identify feature patterns in different business scenarios.

[0290] Feature extraction: Extracting meaningful feature representations from raw data using an autoencoder or other unsupervised learning methods.

[0291] Classification and Prediction: Use the trained model to classify and predict newly collected data, identify the current business scenario, and predict possible events (such as fault warnings).

[0292] Business Scenario Examples Normal operation: The elevator moves up and down as planned without any abnormalities.

[0293] Peak hours: A large number of passengers using the elevator at the same time may increase waiting time.

[0294] Emergency situations: such as fires and earthquakes, trigger emergency response mechanisms.

[0295] During maintenance: Technicians perform routine inspections or repairs.

[0296] Based on data characteristics, the key performance indicators for different business types are determined. Key Performance Indicators (KPIs) Bandwidth: refers to the amount of data that can be transmitted per unit of time, affecting video surveillance quality, response speed of control system commands, etc.

[0297] Delay: refers to the time required for data to travel from the sending end to the receiving end, which is especially important for control system commands and safety alarms.

[0298] Jitter: refers to the degree of variation in latency. Excessive jitter can affect the smoothness of the video stream and the accuracy of control system commands.

[0299] Packet loss rate: refers to the proportion of data packets lost during network transmission. A high rate can lead to incomplete or incorrect information.

[0300] KPI settings for different business types Video surveillance business Bandwidth: Minimum guaranteed bandwidth of 10Mbps to ensure high-definition image transmission.

[0301] Delay: The maximum allowable delay is 100ms to maintain the real-time nature of the video.

[0302] Jitter: Controlled within 10ms to ensure smooth video playback.

[0303] Packet loss rate: not exceeding 0.1%, ensuring video integrity.

[0304] Control system command business Delay: The maximum delay is 10ms to ensure that instructions are transmitted quickly.

[0305] Jitter: Controlled within 1ms to ensure accurate command execution.

[0306] Packet loss rate: strictly controlled within 0.01% to ensure reliability.

[0307] Security alarm services Priority: Highest.

[0308] Delay: The maximum delay is no more than 10ms to ensure that emergency information is transmitted quickly.

[0309] Reliability: Reaches over 99.99%, ensuring high availability.

[0310] Routine maintenance report service Bandwidth: Low bandwidth requirement, approximately 1Mbps, sufficient for text and a small number of image transmissions.

[0311] Delay: The maximum delay shall not exceed 5 minutes, and a certain time difference is allowed.

[0312] Reliability: Reaches over 99%, ensuring basic information integrity.

[0313] In some embodiments of this application, the step of generating service quality strategies for different service types based on the key performance indicators, wherein the service quality strategy involves setting priorities and service quality parameters, specifically: Assign different priorities based on the importance of different business types; Set specific service quality parameters for each business type; The generated Quality of Service (QoS) policy is applied to all relevant network devices to ensure that the network devices can identify and process different types of data streams according to the set QoS policy.

[0314] Specifically, determining business importance First, it's necessary to assess the importance and urgency of each service type within the elevator network system. This typically involves a comprehensive consideration of factors such as service impact, security risks, and user experience. For example: Safety alarms: These are directly related to passenger safety and must be handled immediately.

[0315] Control system commands: These are related to the operation and management of the elevator. Any delay may lead to operational errors or safety hazards.

[0316] Video surveillance: Used for real-time monitoring and post-event review; while important, a certain degree of delay is permissible.

[0317] Routine maintenance reports can be processed without affecting other critical business operations.

[0318] Priority allocation Based on the above evaluation results, a corresponding priority is assigned to each business type: Highest priority: Security alarm information, ensuring rapid information transmission in emergency situations.

[0319] High priority: Control system commands to ensure the timeliness and accuracy of elevator operation.

[0320] Medium priority: Video surveillance, maintaining a certain level of real-time performance and image quality.

[0321] Low priority: Routine maintenance reports, processed without affecting other critical business operations.

[0322] Set specific service quality parameters for each business type. Define Quality of Service (QoS) parameters. For each type of business, specific service quality parameters are set, including but not limited to the following: Bandwidth: Reserve sufficient bandwidth resources for different types of data streams to ensure that basic service quality can be maintained even when the network is congested.

[0323] Latency: Strictly control the latency of data transmission, especially for applications with high real-time requirements.

[0324] Jitter: Controls the variation in data packet arrival time to ensure stable transmission.

[0325] Packet Loss Rate: Minimize packet loss to ensure information is transmitted completely and accurately.

[0326] Maximum Connections: Limits the maximum number of concurrent connections allowed, ensuring that each connection receives appropriate resource allocation.

[0327] Quality of Service (or DSCP Marking): Differential Service Code Points (DSCP) or other similar markers are used to identify different types of data packets, allowing network devices to distinguish them and apply different processing strategies based on the markers.

[0328] Set specific parameters Based on the previously determined key performance indicators (KPIs), specific service quality parameters are set for each business type: Video surveillance: Bandwidth: Minimum guaranteed bandwidth is 10Mbps.

[0329] Latency: The maximum allowed latency is 100ms.

[0330] Jitter: Controlled within 10ms.

[0331] Packet loss rate: not exceeding 0.1%.

[0332] Control system commands: Latency: Maximum latency is 10ms.

[0333] Jitter: Controlled within 1ms.

[0334] Packet loss rate: strictly controlled within 0.01%.

[0335] Security Alarm: Priority: Highest.

[0336] Latency: Maximum latency not exceeding 10ms.

[0337] Reliability: 99.99% or higher.

[0338] Routine maintenance report: Bandwidth: Low bandwidth requirement, approximately 1 Mbps.

[0339] Delay: Maximum delay not exceeding 5 minutes.

[0340] Reliability: Over 99%.

[0341] The generated Quality of Service (QoS) policy will be applied to all relevant network devices. Application Service Quality Strategy To ensure that all network devices can identify and process different types of data streams according to the configured Quality of Service (QoS) policies, the following steps are required: Configuration Updates: Configure Quality of Service (QoS) policies on routers, switches, and other network devices via command-line interface or graphical user interface (GUI).

[0342] Automation tools: Use automation tools to automatically generate and deploy QoS policies, simplifying the configuration process and reducing human error.

[0343] Hardware support: Ensure that the network equipment used has good QoS function support, can identify and distinguish different types of data packets, and perform corresponding scheduling and processing.

[0344] Verification and Testing: Verify the effectiveness of the configuration in a real-world environment to ensure that network devices can correctly implement QoS policies and make adjustments as needed.

[0345] Specific implementation steps Configure network devices Routers and switches: Configure DSCP flags and other QoS parameters, such as queue management and bandwidth allocation, to ensure that data flows are processed according to priority.

[0346] Firewalls and other security devices: Ensure these devices also follow the same quality of service policies to avoid blocking critical business traffic due to security rules.

[0347] Automated deployment Script writing: Write automated scripts to configure the quality of service (QoS) policies for multiple network devices in batches.

[0348] API integration: Utilize the API interfaces provided by network devices to achieve remote management and automatic configuration.

[0349] Continuous monitoring and optimization Monitoring Platform: Establish a continuous monitoring platform to track network performance in real time and ensure the effectiveness of service quality strategies.

[0350] Feedback mechanism: QoS configuration is continuously adjusted and optimized based on actual results, forming a closed-loop control system.

[0351] In some embodiments of this application, the quality of service parameters include: quality of service level and maximum number of connections.

[0352] Specifically, Service Class (or DSCP Marking) definition Quality of Service (QoS) refers to the use of Differentiated Services Code Points (DSCPs) or similar markers to identify different types of data packets, allowing network devices to classify and prioritize data flows based on these markers. The DSCP is a 6-bit field in the IP header that distinguishes different service types and instructs network devices on how to process these packets.

[0353] effect Traffic classification: Network devices (such as routers and switches) can classify inbound data streams into different queues based on their DSCP values.

[0354] Priority processing: High-priority data packets (such as control system commands and safety alarm information) can be processed first during congestion to ensure real-time performance and reliability.

[0355] Resource allocation: Based on the DSCP value, network devices can allocate different bandwidth, latency, and other resources to different types of data streams to ensure the quality of service for critical businesses.

[0356] Specific application examples Video surveillance: Set the DSCP flag to "AF41" to ensure that this type of data stream receives high priority processing even when the network is congested.

[0357] Control system command: Set the DSCP flag to "EF" (Expedited Forwarding) to give it the highest priority, ensuring real-time performance and reliability.

[0358] Security Alarm: Set the DSCP flag to "CS7" and assign it the highest absolute priority to ensure that information can be transmitted rapidly in emergency situations.

[0359] Routine maintenance report: Set the DSCP flag to "BE" (Best Effort), give it a lower priority, and process it without affecting other critical business operations.

[0360] Maximum number of connections definition Maximum connections refers to the maximum number of concurrent connections that can be established at the same time. This parameter is mainly used to limit the number of clients or data streams that can communicate with the network device at the same time, in order to prevent excessive connections from overloading the network device or degrading its performance.

[0361] effect Resource protection: By limiting the maximum number of connections, network devices can be prevented from running out of resources due to handling too many connections, thereby maintaining system stability and responsiveness.

[0362] Load balancing: When multiple network devices share the same task, the maximum number of connections can help achieve a more even load distribution and improve overall efficiency.

[0363] Quality of Service Assurance: Ensuring that each connection receives appropriate resource allocation, especially for applications requiring high bandwidth or low latency.

[0364] Specific application examples Video surveillance system: Set the maximum number of connections per camera to 5 to ensure that even if multiple devices access the video stream at the same time, it will not cause network congestion.

[0365] Control system commands: Since this type of data usually comes from a fixed control terminal, its maximum number of connections can be set to 1 or 2 to ensure that each operation is responded to in a timely manner.

[0366] Security alarm system: Considering the importance of alarm information, the maximum number of connections can be appropriately relaxed to ensure that all alarm information can be received in a timely manner in emergency situations.

[0367] Routine maintenance report: Because this type of data is relatively non-urgent, a higher maximum number of connections can be set, such as 100, to accommodate batch upload needs.

[0368] in conclusion By appropriately configuring service quality levels and maximum connection limits, the intelligent management level and service quality of elevator network systems can be effectively improved. Specifically: Quality of Service (DSCP) Marking ensures that different types of data streams are processed in the network according to their importance and urgency, improving overall transmission efficiency and reliability.

[0369] The maximum number of connections provides a resource protection mechanism, preventing network devices from experiencing performance degradation or failure due to handling too many connections, thus ensuring system stability and user experience.

[0370] In some embodiments of this application, the construction of the network environment based on the quality of service strategy through the deployment of 5G network slicing and edge computing nodes specifically includes: According to the quality of service policy, a request to create a dedicated 5G network slice is submitted through the API interface provided by the operator. Parameters that meet the needs of the elevator network service are customized. After receiving the confirmation information, the slice configuration is completed and integrated with the existing network architecture. Select a suitable geographical location near an area with high elevator density to install pre-configured edge computing server hardware, and remotely install and configure the operating system and the required application stack.

[0371] Specifically, Step 1: Requirements Analysis and Parameter Customization Define business requirements: Based on the previously defined Quality of Service (QoS) policy, clarify the specific requirements for different business types (such as video surveillance, control system commands, security alarms, and routine maintenance reports).

[0372] Customized slicing parameters: Set specific 5G network slicing parameters for each service type, including but not limited to: Bandwidth: Ensure sufficient bandwidth to support high-definition video streaming or real-time control signal transmission.

[0373] Delay: Strictly control the delay time of data transmission, especially for control system commands and safety alarm information.

[0374] Jitter: Controls the variation in data packet arrival time to ensure stable transmission.

[0375] Packet loss rate: Minimize data packet loss to ensure the complete and error-free transmission of information.

[0376] Example parameter configuration Video surveillance slices: Bandwidth: Minimum guaranteed bandwidth is 10Mbps.

[0377] Latency: The maximum allowed latency is 100ms.

[0378] Jitter: Controlled within 10ms.

[0379] Packet loss rate: not exceeding 0.1%.

[0380] Control system instruction slices: Latency: Maximum latency is 10ms.

[0381] Jitter: Controlled within 1ms.

[0382] Packet loss rate: strictly controlled within 0.01%.

[0383] Security alarm slice: Priority: Highest.

[0384] Latency: Maximum latency not exceeding 10ms.

[0385] Reliability: 99.99% or higher.

[0386] Routine maintenance report slice: Bandwidth: Low bandwidth requirement, approximately 1 Mbps.

[0387] Delay: Maximum delay not exceeding 5 minutes.

[0388] Reliability: Over 99%.

[0389] Step 2: API Interface Call and Slice Creation API calls: Submitting requests to create dedicated 5G network slices using the API interfaces provided by the operator. These APIs typically include: Create a slice: Define the slice name, type, service level agreement (SLA), and other information.

[0390] Configuration parameters: Set specific network parameters, such as bandwidth allocation, maximum number of connections, latency limits, etc.

[0391] Example API request (using a control system instruction slice as an example): { "slice_name": "Control System Command Slice", "type": "high priority", "sla": { "delay": "10ms", "jitter": "1ms", "packet_loss_rate": "0.01%" } } Step 3: Confirmation and Integration Receive confirmation information: After receiving the confirmation information returned by the operator, complete the slice configuration and integrate it with the existing network architecture.

[0392] Testing and Verification: Conduct preliminary testing to ensure that the new slice can seamlessly integrate with the existing elevator network system and meet the set service quality requirements.

[0393] Select a suitable geographical location near areas with high elevator density to install pre-configured edge computing server hardware. Step 1: Site Selection Planning Physical distance: Get as close as possible to the elevator equipment to reduce transmission delay.

[0394] Network coverage: Ensure good 5G signal coverage and guarantee a stable communication link.

[0395] Power supply: It has reliable power supply facilities to avoid service interruptions due to power outages.

[0396] Step 2: Hardware Installation Installation location: Install the edge computing server hardware in the selected location according to the manufacturer's guidelines and make the necessary physical connections (such as power cords and network cables).

[0397] Hardware configuration: Ensure that the hardware meets the preset specifications, such as a high-performance CPU, sufficient memory and storage space, to support complex data processing tasks.

[0398] Step 3: Remotely install and configure the operating system and the required application stack. Operating system configuration Choose an operating system: Select an operating system suitable for the edge computing environment, such as Ubuntu Server, CentOS, etc.

[0399] Security settings: Configure security measures such as firewalls and intrusion detection systems (IDS) to protect edge nodes from attacks.

[0400] Application stack configuration Video processing: Deploy necessary application software, such as FFmpeg for video stream decoding and TensorFlow for image recognition.

[0401] Data analysis: Install data analysis tools, such as Apache Spark or Flink, for real-time processing and analysis of elevator operation data.

[0402] Communication protocols: Ensure support for required communication protocols, such as MQTT, HTTP / HTTPS, etc., to facilitate data exchange with other systems.

[0403] Example configuration process Remote access: Connect to the edge computing node via SSH or other remote management tools.

[0404] Operating system installation: Install and configure the operating system using automated scripts or manual operations.

[0405] Application deployment: Deploy the required application using containerization technologies such as Docker or by direct installation.

[0406] Security hardening: Configure firewall rules, enable intrusion detection systems, and ensure that all communications are encrypted.

[0407] Functionality verification: Start all services and conduct preliminary tests to ensure that all functions are working properly.

[0408] In some embodiments of this application, the optimization of network conditions based on the constructed network environment through an intelligent routing mechanism specifically includes: Collect network status data and train a dynamic routing algorithm model in the cloud. The model can predict changes in network conditions over a period of time and generate the optimal path selection strategy. A multi-objective optimization algorithm is introduced to balance the relationship between multiple key performance indicators. The trained model is pushed to each edge computing node. The model on the node receives real-time network status updates and adjusts routing decisions according to the algorithm. When network congestion or failure is detected, it automatically switches to an alternative path.

[0409] Specifically, collecting network status data Data source Sensors and API Interfaces: Utilize various sensors deployed in the network (such as traffic monitors and QoS probes) and API interfaces provided by operators to acquire network status data in real time.

[0410] 5G Slice Monitoring: Extract key performance indicators (KPIs) such as bandwidth utilization, latency, jitter, and packet loss rate from each 5G network slice.

[0411] Edge computing nodes: Monitoring tools on edge computing nodes collect local network conditions and process load information.

[0412] Data types Physical layer data: such as signal strength, channel quality, etc.

[0413] Transport layer data: such as TCP / UDP connection status, number of retransmissions, etc.

[0414] Application layer data: such as video stream quality, control system command response time, etc.

[0415] Implementation Data aggregation and storage: The collected data is sent to the cloud or edge computing nodes for aggregation and storage, providing a foundation for subsequent analysis.

[0416] Real-time performance guarantee: Ensure that the data collection frequency is high enough to reflect network changes in a timely manner.

[0417] Training dynamic routing algorithm models in the cloud Model training process Data preprocessing: Perform preprocessing operations such as cleaning and normalization on the raw data to ensure the quality of the data used for training.

[0418] Feature engineering: Extracting features that help predict future changes in network conditions, such as historical traffic patterns and time series trends.

[0419] Model selection: Choose a suitable machine learning model (such as random forest, support vector machine, neural network) and train it using historical data and real-time updated data.

[0420] Model validation and optimization: Model parameters are optimized through methods such as cross-validation and grid search to ensure their generalization ability and prediction accuracy.

[0421] Predictive ability Short-term forecasting: Predicting changes in network conditions over the next few minutes to hours to help plan route selection in advance.

[0422] Long-term forecasting: Based on data over a longer time span, it identifies cyclical and seasonal patterns of change to aid in the formulation of long-term strategies.

[0423] Example model configuration Video surveillance slices: Using an LSTM (Long Short-Term Memory) model, predict the bandwidth utilization and jitter of each path in the next hour.

[0424] Control system instruction slices: Using the XGBoost model, predict high-latency events that may occur within the next 5 minutes and their impact range.

[0425] Introducing a multi-objective optimization algorithm to balance the relationships between multiple key performance indicators. The objective of multi-objective optimization Take multiple KPIs into account: When setting QoS parameters, not only should individual KPIs (such as latency) be considered, but also the relationship between multiple performance indicators such as bandwidth, jitter, and packet loss rate should be taken into account.

[0426] Balancing different business needs: For business types with conflicting needs (such as high-bandwidth video surveillance and low-latency control system commands), the optimal solution is found through multi-objective optimization algorithms.

[0427] Optimization Algorithm Examples Linear programming: used to solve resource allocation problems and ensure that the overall quality of service is maximized under limited bandwidth.

[0428] Genetic algorithms simulate the natural selection process, progressively optimizing path selection strategies to find the globally optimal solution.

[0429] Reinforcement learning: Enables intelligent routing mechanisms to learn and adapt to new network conditions autonomously, further improving optimization performance.

[0430] Implementation Model optimization: Taking multiple KPIs into account, the above algorithm is used to solve for the optimal configuration.

[0431] Simulation testing: Simulate network performance under different scenarios using a simulation platform to verify the effectiveness of the optimization results.

[0432] The trained model is pushed to each edge computing node. Model distribution Automated deployment: Use automated tools to automatically generate and deploy QoS policies, simplifying the configuration process and reducing human error.

[0433] Hardware support: Ensure that the network equipment used has good QoS function support, can identify and distinguish different types of data packets, and perform corresponding scheduling and processing.

[0434] Real-time adjustments on nodes Receive real-time updates: The intelligent routing algorithm on the node receives real-time network status updates from the cloud and dynamically adjusts routing decisions based on the prediction results.

[0435] Feedback loop: Establish a continuous monitoring platform to periodically evaluate the effectiveness of the intelligent routing mechanism and continuously optimize the algorithm parameters based on the actual results, forming a closed-loop control system.

[0436] Automatic path switching Fault detection: When network congestion or faults are detected, an alternative path is immediately activated to ensure service continuity and data transmission stability.

[0437] Path selection strategy: Generate the optimal path selection strategy based on the prediction results, and select the best transmission path to meet the needs of different service types.

[0438] Example implementation steps Model distribution: The trained model is pushed to each edge computing node to ensure that each node can make the optimal routing decision based on the latest network conditions.

[0439] Real-time adjustment: The intelligent routing algorithm on the node receives real-time network status updates and dynamically adjusts the routing decisions based on the prediction results.

[0440] Automatic switching: When congestion or failure is detected on a certain path, it automatically switches to another available path to avoid data transmission interruption.

[0441] in conclusion Through the steps described above, network conditions can be optimized using intelligent routing mechanisms based on the constructed network environment. This approach not only improves the system's intelligent management level and service quality but also lays a solid foundation for future continuous optimization and development. The rational configuration of intelligent routing algorithms and automated decision-making tools further guarantees user experience and system security, ensuring that the elevator network system can operate efficiently, stably, and reliably in complex and ever-changing network environments.

[0442] Application scenarios Example 1: Optimization of video surveillance services Background: Video surveillance requires high bandwidth and low jitter to ensure the clarity and smoothness of image transmission.

[0443] Problem: During peak hours, the simultaneous uploading of a large number of video streams may cause network congestion, affecting video quality.

[0444] Solution: Data collection: Real-time monitoring of bandwidth utilization and jitter on each path using sensors deployed in the network.

[0445] Model training: Use historical data to train a prediction model to predict which paths are likely to become congested in the future.

[0446] Path selection: The intelligent routing algorithm adjusts the transmission path of the video stream in advance based on the prediction results, selecting a path with sufficient bandwidth and less jitter.

[0447] Real-time adjustment: When congestion is detected on a certain path, it automatically switches to another available path to ensure the stability and quality of video transmission.

[0448] Example 2: Optimization of Control System Commands Background: Control system commands require extremely low latency and high reliability; any delay may lead to operational errors or safety hazards.

[0449] Problem: In the event of network instability, control system commands may be affected by delays.

[0450] Solution: Data collection: Real-time monitoring of network latency and packet loss rate, especially for dedicated 5G slices for control system commands.

[0451] Model training: Train a specialized prediction model, focusing on optimizing the selection of low-latency paths.

[0452] Path selection: The intelligent routing algorithm prioritizes the shortest path to ensure that control system commands can reach the destination within 10ms.

[0453] Real-time adjustment: Once a delay exceeds the set threshold, immediately switch to the backup path to ensure timely delivery of instructions.

[0454] Example 3: Optimization of security alarm information Background: Security alarm information must have the highest priority to ensure that information can be transmitted quickly in emergency situations.

[0455] Problem: Security alerts may not be delivered in a timely manner during network congestion or failure.

[0456] Solution: Data collection: Real-time monitoring of network status, especially dedicated 5G slices for security alarm information.

[0457] Model training: Train a specialized prediction model to ensure that the optimal path can be found under any circumstances.

[0458] Path selection: The intelligent routing algorithm assigns the highest priority to security alarm information, ensuring that it always selects the shortest path.

[0459] Real-time adjustment: Once a network failure or congestion is detected, an alternative path is immediately activated to ensure that alarm information can be transmitted within 10ms.

[0460] In some embodiments of this application, it further includes: setting a periodic evaluation mechanism to dynamically adjust by comparing the expected goals with the actual results; The dynamic adjustment specifically refers to: periodically collecting network performance data; The network performance data was analyzed in depth using big data analytics tools to identify potential problems and optimization opportunities. The collected network performance data is compared with pre-defined key performance indicators to evaluate whether the system performance meets expectations. Analyze the causes of the deviations and determine which parts need adjustment or improvement; Based on the analysis results, a detailed adjustment plan was developed, specifying the specific adjustment content, timetable, and responsible persons. Perform the corresponding operations according to the adjustment plan. After the adjustment is completed, continue to track the system performance to verify whether the adjustment has achieved the expected results.

[0461] Specifically, establish a periodic evaluation mechanism. Target Continuous improvement: Ensure that system performance consistently meets expected service quality standards.

[0462] Timely response: Quickly identify and resolve potential problems to prevent them from escalating into larger failures.

[0463] Implementation Time cycle: Set a fixed evaluation cycle, such as weekly, monthly or quarterly, to ensure regular checks.

[0464] Automation tools: Utilize automated monitoring tools and scripts to simplify data collection and preliminary analysis.

[0465] Responsibility allocation: Clearly define the person responsible for each evaluation cycle to ensure that tasks are completed on time.

[0466] Regularly collect network performance data Data source Sensors and API interfaces: Real-time acquisition of network status data from 5G network slices, edge computing nodes and other related devices.

[0467] Log files: Extract log information from devices such as routers, switches, and servers to record historical operations and events.

[0468] User feedback: We collect user feedback through surveys, customer service hotlines, and other means.

[0469] Data types Bandwidth utilization: Monitor the bandwidth usage of each path.

[0470] Delay: Measures the time delay of data packet transmission.

[0471] Jitter: Assess the degree of variation in latency.

[0472] Packet loss rate: The percentage of data packets lost during network transmission.

[0473] User satisfaction: Understanding passengers' true feelings about service quality.

[0474] Implementation Automated data collection: Deploy automated scripts or use dedicated tools to automatically collect data on a regular schedule.

[0475] Data storage: The collected data is stored in the cloud or a local database for easy analysis later.

[0476] The network performance data was analyzed in depth using big data analytics tools. Tool Selection Hadoop / Spark: Used to process large-scale datasets and supports distributed computing.

[0477] ELK Stack (Elasticsearch, Logstash, Kibana): Provides log management and visualization capabilities.

[0478] Machine learning platforms, such as TensorFlow and PyTorch, are used to build predictive models and anomaly detection algorithms.

[0479] In-depth content exploration Trend analysis: Identifying long-term trends in data to predict future changes.

[0480] Anomaly detection: Data points that deviate from the normal pattern are detected, indicating potential problems.

[0481] Association rules: Identify the relationships between different variables and reveal hidden causal chains.

[0482] Implementation Data cleaning: Remove noise and invalid data to ensure the accuracy of analysis results.

[0483] Feature extraction: Extracting meaningful feature representations from raw data to prepare for subsequent modeling.

[0484] Model training: Use historical data to train the prediction model, identify potential problems and optimization opportunities.

[0485] The collected network performance data is compared with pre-defined key performance indicators. Comparison Methods Threshold comparison: Directly compare the actual data with the preset threshold to determine whether it exceeds the standard.

[0486] Percentage difference: Calculates the percentage difference between the actual value and the target value, quantifying the degree of deviation.

[0487] Scoring system: Scores are assigned to each indicator to comprehensively evaluate the overall system performance.

[0488] Key Performance Indicators (KPIs) Video surveillance: Bandwidth: Minimum guaranteed bandwidth is 10Mbps.

[0489] Latency: The maximum allowed latency is 100ms.

[0490] Jitter: Controlled within 10ms.

[0491] Packet loss rate: not exceeding 0.1%.

[0492] Control system commands: Latency: Maximum latency is 10ms.

[0493] Jitter: Controlled within 1ms.

[0494] Packet loss rate: strictly controlled within 0.01%.

[0495] Security Alarm: Priority: Highest.

[0496] Latency: Maximum latency not exceeding 10ms.

[0497] Reliability: 99.99% or higher.

[0498] Routine maintenance report: Bandwidth: Low bandwidth requirement, approximately 1 Mbps.

[0499] Delay: Maximum delay not exceeding 5 minutes.

[0500] Reliability: Over 99%.

[0501] Implementation Automated Reports: Generates regular performance evaluation reports, providing a clear overview of the performance of various metrics.

[0502] Visualization tools: Using charts, dashboards, and other formats, help managers quickly understand data.

[0503] Analyze the causes of deviations and determine which parts need adjustment or improvement. Analytical methods Root Cause Analysis (RCA): Delve into the root cause of a problem and avoid superficial treatment.

[0504] Multifactor analysis: Considering multiple possible influencing factors to comprehensively assess the background of the problem.

[0505] Expert consultation: Invite experts in the field to participate in discussions and provide professional opinions and technical support.

[0506] Determine areas for improvement Hardware-level upgrades include upgrading network equipment and adding redundant paths.

[0507] On the software side: optimize intelligent routing algorithms, update application versions, etc.

[0508] Management processes: Improve maintenance plans, enhance employee training, etc.

[0509] Based on the analysis results, a detailed adjustment plan was formulated. Plan content Adjustment details: Specify the specific adjustment measures, such as modifying QoS parameters or adjusting routing policies.

[0510] Schedule: Set adjustment time points to ensure tasks are completed on schedule.

[0511] Person in charge: Designate a specific person in charge for each task and clarify the division of responsibilities.

[0512] Resource allocation: The resources required for planning, such as human, material and financial support.

[0513] Example Adjustment Plan Adjustments include: optimizing bandwidth allocation for video surveillance slices to reduce congestion during peak hours.

[0514] Timeline: Data analysis to be completed this week, and adjustments to be implemented next week.

[0515] Responsible Person: The head of the IT department is the primary person in charge, with network engineers assisting in the execution.

[0516] Resource allocation: Two network engineers will be assigned to participate in the adjustment work, which is expected to take two days.

[0517] Perform the corresponding operations according to the aforementioned adjustment plan. Execution process Preparation: Ensure all prerequisites are met, such as backing up configuration files and notifying relevant personnel.

[0518] Implementation will proceed gradually: Each adjustment measure will be implemented one by one according to the predetermined timetable and steps.

[0519] Monitoring and feedback: Monitor network performance in real time during the adjustment process and respond promptly to emergencies.

[0520] Continue to monitor system performance to verify whether the adjustments have achieved the expected results. Tracking methods Short-term observation: Closely monitor system performance in the short term after the adjustment to ensure the new settings take effect.

[0521] Long-term evaluation: After a period of operation, a comprehensive evaluation will be conducted to confirm whether the effects of the adjustments are lasting.

[0522] User feedback: We will collect user opinions again to understand whether the actual user experience has been improved.

[0523] Verification method Before and after comparison: Compare the performance data before and after the adjustment to evaluate the improvement effect.

[0524] User satisfaction survey: Understanding passengers' feelings about service improvements through questionnaires and other methods.

[0525] Continuous optimization: Based on the validation results, decide whether further adjustments are needed or whether to maintain the status quo.

[0526] A second aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in any of the embodiments of the first aspect above.

[0527] Figure 2 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 2 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 can call logical instructions in the memory 830 to execute the intelligent elevator network routing optimization method in any embodiment of the first aspect described above, the method including: Based on elevator operation data, key performance indicators for different business types are determined. Based on the key performance indicators, service quality strategies for different business types are generated, wherein the service quality strategies set priorities and service quality parameters. Based on the aforementioned quality of service strategy, a network environment is constructed through the deployment of 5G network slicing and edge computing nodes; Based on the constructed network environment, the network conditions are optimized through an intelligent routing mechanism.

[0528] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0529] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is able to execute the intelligent elevator network routing optimization method provided by the above methods, the method comprising: Based on elevator operation data, key performance indicators for different business types are determined. Based on the key performance indicators, service quality strategies for different business types are generated, wherein the service quality strategies are defined by setting priorities and service quality parameters. Based on the aforementioned quality of service strategy, a network environment is constructed through the deployment of 5G network slicing and edge computing nodes; Based on the constructed network environment, the network conditions are optimized through an intelligent routing mechanism.

[0530] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the intelligent elevator network routing optimization method provided by the methods described above, the method comprising: Based on elevator operation data, key performance indicators for different business types are determined. Based on the key performance indicators, service quality strategies for different business types are generated, wherein the service quality strategies are defined by setting priorities and service quality parameters. Based on the aforementioned quality of service strategy, a network environment is constructed through the deployment of 5G network slicing and edge computing nodes; Based on the constructed network environment, the network conditions are optimized through an intelligent routing mechanism.

[0531] For any parts not mentioned in this application, existing technologies may be used or referenced.

[0532] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0533] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for optimizing routing in an intelligent elevator network, characterized in that, include: Based on elevator operation data, key performance indicators for different business types are determined. Based on the key performance indicators, service quality strategies for different business types are generated, wherein the service quality strategies set priorities and service quality parameters. Based on the aforementioned quality of service strategy, a network environment is constructed through the deployment of 5G network slicing and edge computing nodes; Based on the constructed network environment, the network conditions are optimized through an intelligent routing mechanism.

2. The method according to claim 1, characterized in that, The key performance indicators for different business types, determined based on elevator operation data, are as follows: The elevator's operating data is collected using various sensors inside the elevator; The elevator operation data includes: physical status data, electrical system data, environmental conditions, user interaction data, safety and alarm information, maintenance and service history, video surveillance data, and other special data; Deep learning is used to analyze the elevator operation data to identify data characteristics under different business scenarios; Based on the data characteristics, the key performance indicators for the different business types are determined; The key performance indicators include: bandwidth, latency, jitter, and packet loss rate.

3. The method according to claim 1, characterized in that, The process involves generating service quality strategies for different business types based on the key performance indicators. These service quality strategies define priorities and service quality parameters, specifically: Assign different priorities based on the importance of different business types; Set specific service quality parameters for each business type; The generated Quality of Service (QoS) policy is applied to all relevant network devices to ensure that the network devices can identify and process different types of data streams according to the set QoS policy.

4. The method according to claim 3, characterized in that, The service quality parameters include: service quality level and maximum number of connections.

5. The method according to claim 1, characterized in that, The network environment is constructed based on the aforementioned quality of service strategy through the deployment of 5G network slicing and edge computing nodes, specifically as follows: According to the service quality policy, a request to create a dedicated 5G network slice is submitted through the API interface provided by the operator. Parameters that meet the needs of the elevator network service are customized. After receiving the confirmation information, the slice configuration is completed and integrated with the existing network architecture. Select a suitable geographical location near an area with high elevator density to install pre-configured edge computing server hardware, and remotely install and configure the operating system and the required application stack.

6. The method according to claim 1, characterized in that, The constructed network environment optimizes network conditions through an intelligent routing mechanism, specifically as follows: Collect network status data and train a dynamic routing algorithm model in the cloud. The model can predict changes in network conditions over a period of time and generate the optimal path selection strategy. A multi-objective optimization algorithm is introduced to balance the relationship between multiple key performance indicators. The trained model is pushed to each edge computing node. The model on the node receives real-time network status updates and adjusts routing decisions according to the algorithm. When network congestion or failure is detected, it automatically switches to an alternative path.

7. The method according to claim 1, characterized in that, Also includes: Establish a periodic evaluation mechanism to make dynamic adjustments by comparing expected goals with actual results; The dynamic adjustment specifically refers to: periodically collecting network performance data; The network performance data was analyzed in depth using big data analytics tools to identify potential problems and optimization opportunities. The collected network performance data is compared with pre-defined key performance indicators to evaluate whether the system performance meets expectations. Analyze the causes of the deviations and determine which parts need adjustment or improvement; Based on the analysis results, a detailed adjustment plan was developed, specifying the specific adjustment content, timetable, and responsible persons. Perform the corresponding operations according to the adjustment plan. After the adjustment is completed, continue to track the system performance to verify whether the adjustment has achieved the expected results.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer program product containing instructions, characterized in that, when run on a device, This causes the device to perform the steps of the method as described in any one of claims 1 to 7.

Images