Intelligent station interaction method and device based on cloud side end

Abstract

The invention provides an intelligent station interaction method and device based on a cloud side, which are applied to a station side and relate to the technical field of interaction engineering.The method comprises the steps that station environment data collected by a station environment sensor and a user request initiated by a user through an interaction interface are obtained; preprocessing and filtering the station environment data to obtain filtered data; performing real-time data analysis and decision based on the user request and the filtered data, and generating a local feedback instruction corresponding to the user request; and controlling the station local equipment to execute the target operation according to the local feedback instruction to respond to the user request. The method is used for overcoming the defects of low real-time performance and large limitation of an interaction mode of an intelligent station in the prior art, and realizing quick response to user requirements.

Description

Technical Field

[0001] This invention relates to the field of interactive engineering technology, and in particular to a cloud-edge-device-based intelligent station interaction method and device. Background Technology

[0002] With the acceleration of urbanization and the increasing complexity of transportation networks, traditional station management models are gradually failing to meet people's needs for convenient transportation and high-quality service.

[0003] In existing technologies, some intelligent station systems rely on traditional cloud architectures, with data processing and decision-making mainly concentrated on cloud servers. This results in drawbacks such as large data transmission latency and high requirements for network stability.

[0004] It is evident that the interactive methods of intelligent stations in related technologies suffer from technical problems such as low real-time performance and significant limitations. Summary of the Invention

[0005] This invention provides a cloud-edge-device-based intelligent station interaction method and device to solve the shortcomings of existing intelligent station interaction methods, which have low real-time performance and large limitations, and to achieve rapid response to user needs.

[0006] This invention provides a cloud-edge-device-based intelligent station interaction method applied to the station edge, comprising: acquiring station environmental data collected by station environmental sensors and user requests initiated by users through an interactive interface; preprocessing and filtering the station environmental data to obtain filtered data; performing real-time data analysis and decision-making based on the user requests and the filtered data to generate local feedback instructions corresponding to the user requests; and controlling local station devices to perform target operations in response to the user requests according to the local feedback instructions.

[0007] According to the present invention, a cloud-edge-device based intelligent station interaction method is provided, the method further includes: uploading the filtered data to a pre-connected cloud; visualizing the station operation results when receiving station operation results issued by the cloud, the station operation results including: current passenger flow, station utilization rate, and passenger flow prediction; and updating the data model used to generate the local feedback instruction based on the received operation optimization strategy when receiving the operation optimization strategy issued by the cloud.

[0008] According to the present invention, a cloud-edge-device based intelligent station interaction method is provided, wherein the station environment data includes video image data and environmental audio data; the preprocessing and filtering of the station environment data to obtain filtered data includes: performing image recognition processing on the video image data to obtain passenger count statistics; performing voiceprint event detection on the environmental audio data to obtain specific sound events in the station environment; and using the passenger count statistics and the specific sound events together as filtered data.

[0009] According to the present invention, a cloud-edge-device-based intelligent station interaction method is provided, wherein the step of performing real-time data analysis based on the user request and the filtered data to generate a local feedback instruction corresponding to the user request includes: when the user request type is information query, performing congestion prediction based on the passenger number statistics in the filtered data to obtain congestion information of the target train in the user request; generating a display instruction as the local feedback instruction based on the congestion information of the target train, wherein the display instruction is used to display the target train information containing the congestion information; when the user request type is voice reminder, performing abnormal behavior matching based on specific sound events in the filtered data to obtain a matching result corresponding to the specific sound event; when the matching result indicates a safety anomaly, generating a voice broadcast instruction as the local feedback instruction, wherein the voice broadcast instruction is used to broadcast safety prompt information corresponding to the specific sound event.

[0010] According to the present invention, a cloud-edge-device-based intelligent station interaction method, after controlling the station local device to perform a target operation in response to the user request according to the local feedback instruction, the method further includes: monitoring the execution status of the target operation; when the target operation fails or the station local device is unresponsive, initiating a backup operation process, and recording and uploading the operation exception information to the cloud.

[0011] According to the present invention, a cloud-edge-device-based intelligent station interaction method is provided, wherein the step of performing real-time data analysis and decision-making based on the user request and the filtered data to generate a local feedback instruction corresponding to the user request includes: receiving a resource preloading strategy issued by the cloud, wherein the resource preloading strategy is generated by the cloud based on the fusion analysis of historical passenger flow data of the station and the filtered data; according to the resource preloading strategy, before the predicted high passenger flow period, preloading train information, navigation maps and multimedia content with a query count greater than a threshold from the cloud to the local cache; and when the user request matches the target information in the local cache, generating a local feedback instruction based on the target information in the local cache.

[0012] This invention also provides a cloud-edge-device-based intelligent station interaction device, comprising the following modules: an acquisition module for acquiring station environment data collected by station environment sensors and user requests initiated by the user through an interactive interface; a filtering module for preprocessing and filtering the station environment data to obtain filtered data; a generation module for performing real-time data analysis and decision-making based on the user request and the filtered data to generate a local feedback instruction corresponding to the user request; and a feedback module for controlling local station equipment to perform a target operation in response to the user request according to the local feedback instruction.

[0013] The present invention also 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 computer program to implement the cloud-edge-device intelligent station interaction method as described above.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the cloud-edge-device intelligent station interaction method as described above.

[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the cloud-edge-device intelligent station interaction method as described above.

[0016] The present invention provides a cloud-edge-device-based intelligent station interaction method and device. The station edge directly acquires station environmental data and user requests. First, the multi-source environmental data is preprocessed and filtered to remove redundancy and noise. Then, combined with the user requests and filtered data, real-time data analysis and local decision-making are performed at the edge to generate corresponding local feedback instructions. This avoids the delay caused by uploading all data to the cloud and significantly reduces the interaction response time. Finally, by controlling the local station equipment to execute the target operation, the immediate processing of user requests is ensured, and the computing and communication pressure on the cloud is alleviated, achieving an efficient, low-latency, and highly reliable intelligent station service. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced one by one below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the intelligent station interaction method based on cloud, edge, and terminal provided by the present invention.

[0019] Figure 2 This is a schematic diagram of a cloud-edge-device-based intelligent station interaction device provided by the present invention.

[0020] Figure 3 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0022] With the acceleration of urbanization and the increasing complexity of transportation networks, traditional station management models are gradually failing to meet people's demands for convenient transportation and high-quality service. While existing intelligent transportation systems have improved station management efficiency and passenger experience to some extent, they still face problems such as low data processing efficiency and poor real-time response capabilities. Therefore, how to achieve efficient management and high-quality service of intelligent stations through cloud-edge-device technology has become one of the current hot topics in technological research.

[0023] In existing technologies, some intelligent station systems rely on traditional cloud architectures, with data processing and decision-making mainly concentrated on cloud servers. This results in drawbacks such as high data transmission latency and high requirements for network stability. Furthermore, while some systems have attempted to utilize edge computing technology to improve real-time performance, further optimization is still needed in system architecture design and data processing strategies.

[0024] Therefore, designing an efficient intelligent station interaction method and system that combines the advantages of cloud and edge computing has become one of the current technological challenges in the field of intelligent transportation.

[0025] This invention aims to overcome the shortcomings of existing technologies and provide a cloud-edge-device-based intelligent station interaction method and device. Through reasonable system architecture design and data processing strategies, it achieves the advantages of high data real-time performance and fast service response, thereby improving station management efficiency and passenger travel experience.

[0026] Figure 1 This is a flowchart illustrating the cloud-edge-device-based intelligent station interaction method provided by the present invention, as shown below. Figure 1 As shown, the method includes the following steps.

[0027] Step 101: Obtain station environment data collected by station environment sensors and user requests initiated by the user through the interactive interface.

[0028] In this embodiment of the invention, station environment sensors (e.g., cameras, sound sensors, etc.) are deployed in various key areas of the station to continuously collect raw station environment data, including but not limited to passenger flow density, environmental noise, temperature, and equipment operating status.

[0029] Users can initiate specific user requests through interactive interfaces deployed in the station, such as station information touch screens, voice interaction terminals, or their own mobile applications. These requests can include things like querying train information, requesting navigation guidance, or reporting equipment malfunctions.

[0030] The station edge terminal receives and aggregates station environmental data collected by station environmental sensors and user requests initiated by users through the interactive interface in real time through predefined data interfaces and communication protocols.

[0031] Step 102: Preprocess and filter the station environment data to obtain filtered data.

[0032] In this embodiment of the invention, the raw station environment data is directly collected from sensors and may contain invalid values, outliers, inconsistent formats, or errors generated during transmission. Therefore, the station edge performs data cleaning operations, such as identifying and removing illegal values ​​(e.g., negative passenger flow) caused by momentary sensor malfunctions, reasonably interpolating or marking missing values, and converting data from different types of sensors (e.g., cameras, sound sensors) into a unified format and standard units to ensure data consistency and processability.

[0033] Based on preprocessing, the station edge filters data according to pre-defined rules and algorithms related to business logic. For example, for video data, edge computing capabilities can be used to analyze the video stream in real time, extracting and outputting only key feature information, such as the real-time number of passengers in a specific area and the direction of passenger flow, instead of uploading the complete video footage, thus greatly reducing the amount of data. For sound sensor data, ambient background noise can be filtered out, and only valid audio features that may be related to user requests (such as cries for help or specific command keywords) can be identified and retained. In addition, a valid data threshold can be set, so that only data values ​​exceeding a specific range (such as passenger density in a certain area exceeding a set value) are retained as valid data.

[0034] Through the preprocessing and filtering operations described above, the raw, redundant, and potentially noisy station environment data is transformed into high-quality, concise, and information-rich filtered data. This process is completed at the edge, significantly reducing the amount of data transmitted to the cloud.

[0035] Step 103: Perform real-time data analysis and decision-making based on user requests and filtered data, and generate local feedback instructions corresponding to user requests.

[0036] In this embodiment of the invention, after receiving a clear user request and obtaining preprocessed and filtered data, the station edge terminal will immediately initiate a real-time data analysis and decision-making process.

[0037] Specifically, the lightweight analysis engine or rule base built into the edge device will associate and match the specific content of the user's request with the latest filtered data and perform logical operations.

[0038] For example, when a user requests information about "the next train to a certain destination," the edge device immediately retrieves information about real-time train arrivals and departures, platform status, and line operation from the filtered data. It then uses built-in scheduling logic to quickly calculate and determine the most relevant train number, platform, and departure time. When a user requests a voice request for help, the edge device can combine audio features from the filtered data (such as sound source localization and keyword recognition) with relevant information obtained after filtering video data to determine the urgency and specific location of the request.

[0039] The entire analysis and decision-making process is completed locally at the edge, based on pre-loaded decision models and business rules. Its characteristics include fast response speed and low network dependence. Ultimately, based on the analysis and decision results, an executable local feedback command directly corresponding to the user's request is generated. For example, this could be a command to display specific information, a command to trigger voice announcement, or a command to control changes in device status.

[0040] Step 104: Control the station's local equipment to perform the target operation in response to the user request based on the local feedback instructions.

[0041] In this embodiment of the invention, the station edge terminal parses the received local feedback instructions to identify the operation type, target device identifier, and operation parameters contained in the instructions. For example, if the instruction is an information display type, the content to be displayed, the target display screen ID, and the display format are parsed out.

[0042] Subsequently, the station edge terminal uses a built-in device driver interface or standard industrial control protocols (such as Modbus, OPC UA, etc.) to convert the parsed local feedback commands into control commands that can be recognized and executed by specific station local devices. These station local devices include, but are not limited to, station information display screens, broadcast voice announcement units, indicator lights, turnstiles, air conditioning systems, etc.

[0043] The edge device sends the generated control commands to the corresponding station local equipment via a local network (such as Ethernet, RS485 bus, etc.). After receiving the control commands, the equipment drives its actuators to complete the target operation.

[0044] For example, when a local feedback command requests the display of train information, the target display screen will refresh its content, showing the specified text and graphics. When a control command requests voice prompts, the broadcast unit in the target area will broadcast pre-stored or real-time synthesized voice content. When a control command requests environmental adjustments, the relevant air conditioning or lighting equipment will adjust its operating status according to parameters.

[0045] Through this embodiment of the invention, the station edge directly acquires station environmental data and user requests. First, the multi-source environmental data is preprocessed and filtered to remove redundancy and noise. Then, combining the user requests and the filtered data, real-time data analysis and local decision-making are performed at the edge to generate corresponding local feedback instructions. This avoids the delay caused by uploading all data to the cloud and significantly reduces the interaction response time. Finally, by controlling the local station equipment to execute the target operation, the immediate processing of user requests is ensured, and the computing and communication pressure on the cloud is alleviated, achieving an efficient, low-latency, and highly reliable intelligent station service.

[0046] According to the intelligent station interaction method provided by the present invention, the method further includes: Upload the filtered data to the pre-connected cloud; Upon receiving station operation results from the cloud, the system visualizes these results, which include: current passenger flow, station utilization rate, and passenger flow forecast. Upon receiving an operational optimization strategy from the cloud, the data model used to generate local feedback instructions is updated based on the received operational optimization strategy.

[0047] In this embodiment of the invention, after generating filtered data locally, the station edge terminal asynchronously or periodically uploads the filtered data to the cloud in batches via a stable communication link (such as broadband internet, 5G private network, etc.) established between itself and the cloud. This ensures that the cloud can obtain data from the edge terminal that has undergone preliminary purification and compression, avoiding the bandwidth pressure and storage costs caused by directly uploading raw data. The uploaded data includes, but is not limited to, processed passenger flow statistics, equipment operation status logs, environmental parameters, etc.

[0048] The station edge continuously monitors the downlink data channel from the cloud. Once the cloud has completed analysis and calculations based on the aggregated and filtered data, it generates comprehensive station operation results (such as current passenger flow, station utilization, and passenger flow forecasts) and sends them to the station edge. Upon receiving these results, the station edge immediately invokes its integrated visualization engine to convert the data into intuitive charts, graphs, or text information. This information is then rendered and visualized in real-time on designated local station devices (such as the integrated management dashboard or administrator workstation display), providing users with a global operational view.

[0049] The cloud uses machine learning or operations research algorithms to analyze and derive better operational optimization strategies (e.g., more accurate passenger flow management suggestions, more efficient equipment scheduling schemes). Once these operational optimization strategies are distributed to the station edge, the edge receives and parses them. Subsequently, based on the specific content of the operational optimization strategy, the station edge incrementally updates or replaces versions of the locally stored data models (such as decision rule bases and algorithm parameters) used for real-time data analysis and decision-making. This update process ensures that the local decision-making logic at the edge remains synchronized with the latest optimization suggestions from the cloud.

[0050] Through the embodiments of the present invention, efficient collaboration between cloud-based global optimization and edge-end real-time response is achieved, enabling the station system to not only have rapid response capabilities, but also to continuously learn and optimize, thereby constantly improving operational efficiency and user experience.

[0051] According to the present invention, a cloud-edge-device intelligent station interaction method is provided, wherein the station environment data includes video image data and environmental audio data; The station environment data is preprocessed and filtered to obtain filtered data, including: Image recognition processing is performed on the video image data to obtain passenger count statistics; Voiceprint event detection is performed on environmental audio data to obtain specific sound events within the station environment; Passenger count statistics and specific sound events are used together as filtered data.

[0052] In this embodiment of the invention, for video image data, the station edge terminal utilizes its integrated lightweight computer vision model to perform real-time analysis of the video stream. By performing image recognition processing on the video frames, such as using algorithms for background subtraction, target detection and tracking, passenger targets in the image are automatically identified and counted, and finally, a structured passenger count is output. The passenger count can be correlated with specific monitoring areas and time periods, thereby transforming the massive video data stream into a key indicator characterizing passenger flow density.

[0053] For environmental audio data, the station edge uses audio analysis technology to detect voiceprint events in continuous audio signals collected by microphones. This process extracts the time-frequency features of the audio and performs pattern matching with pre-set acoustic event models (such as sudden high-decibel noise, specific keywords, abnormal equipment sounds, etc.) to identify and determine whether specific sound events requiring attention (such as passenger shouts, emergency broadcasts, equipment malfunction alarms, etc.) have occurred, and outputs the event type and its occurrence time in a structured manner.

[0054] The station edge integrates the structured information obtained from the above processing, namely the passenger number statistics extracted from the video data and the specific sound events identified from the audio data, and uses them together as the final filtered data.

[0055] Through the embodiments of the present invention, by performing image recognition processing on video image data in the station environment to count the number of passengers, and by performing voiceprint event detection on environmental audio data to obtain specific sound events, and using both as filtering data, the station environment can be comprehensively and accurately grasped.

[0056] According to the present invention, a cloud-edge-device intelligent station interaction method performs real-time data analysis based on user requests and filtered data to generate local feedback instructions corresponding to user requests, including: When the user's request type is information query, the congestion level is predicted based on the passenger number statistics in the filtered data to obtain the congestion level information of the target train in the user's request. Based on the congestion information of the target train, a display command is generated as a local feedback command. The display command is used to display the target train information, which includes congestion information. When the user's request type is a voice reminder, abnormal behavior matching is performed based on specific sound events in the filtered data to obtain the matching results corresponding to the specific sound events; When the matching result indicates a security anomaly, a voice broadcast command is generated as a local feedback command. The voice broadcast command is used to broadcast the security prompt information corresponding to the specific sound event.

[0057] In this embodiment of the invention, the station edge terminal performs targeted real-time data analysis and decision-making based on the specific type of the received user request and the obtained filtered data (i.e., passenger count statistics and specific sound events) to generate corresponding local feedback instructions.

[0058] When a user requests information, the station edge terminal first parses the request to identify the user's query intent, such as querying real-time information for a specific train. Then, based on passenger count statistics from filtered data (which are associated with the platform or carriage area corresponding to the target train), a pre-defined algorithm model is used to predict congestion. This prediction process can combine historical passenger flow patterns with real-time statistical data for trend analysis, ultimately obtaining congestion information for the target train (such as qualitative or quantitative descriptions like "comfortable," "crowded," or "extremely crowded"). Based on this congestion information, the station edge terminal generates a display command as a local feedback instruction. This display command includes the target train information and its congestion information to be displayed.

[0059] When a user requests a voice alert, the station edge terminal first determines whether the request is an active voice interaction or a system-triggered alert. Based on specific sound events in the filtered data, it matches and compares them with a pre-stored abnormal behavior voiceprint feature library at the edge terminal. For example, it matches detected specific sound events (such as high-decibel shouts or the sound of breaking glass) with samples in the feature library to obtain a matching result, which is used to determine the nature of the event. When the matching result indicates a safety anomaly (i.e., the matching degree exceeds a preset threshold), the edge terminal immediately generates a voice broadcast command as a local feedback instruction. This voice broadcast command is used to control the broadcast system to output safety prompts corresponding to the specific sound event (such as "Please remain calm and pay attention to safety" or voice content guiding evacuation), to achieve rapid safety warnings and responses.

[0060] Through the embodiments of the present invention, when querying information, the congestion level of the target train is predicted based on the passenger number statistics and a display instruction is generated; when providing voice reminders, abnormal behavior is matched through specific sound events, and a voice broadcast instruction is generated if a safety abnormality is found, which effectively improves the timeliness and pertinence of station interaction and ensures the travel experience and safety of passengers.

[0061] According to the intelligent station interaction method provided by the present invention, after controlling the local station equipment to perform a target operation in response to a user request based on local feedback instructions, the method further includes: Monitor the execution status of the target operation; When the target operation fails or the local station equipment is unresponsive, the backup operation process is initiated, and the operation anomaly information is recorded and uploaded to the cloud.

[0062] In this embodiment of the invention, after the station edge terminal issues a control command to the station local device to execute the target operation, it does not immediately end the interaction process, but instead initiates a status monitoring mechanism. The station edge terminal actively queries the feedback status of the station local device through a predefined communication protocol, or receives heartbeat signals and execution results automatically reported by the device.

[0063] The monitoring includes, but is not limited to: whether the device successfully receives and confirms the instruction, whether the target operation (such as screen content refresh or voice announcement completion) has been executed as expected, and whether the device returns error codes or fault signals. This continuous monitoring process ensures that the system can promptly detect abnormalities in the execution process.

[0064] When the station edge determines that the target operation has failed (e.g., the device returns an execution error) or the local station equipment is unresponsive (e.g., no valid feedback is received within a preset timeout period), a pre-set backup operation procedure will be automatically triggered. For example, when the main information screen fails to control, the system will switch to controlling the backup display screen in a nearby area to broadcast information; when the designated broadcasting equipment fails, the system will switch to the emergency broadcasting channel to provide voice prompts.

[0065] The station edge terminal generates operational anomaly information, which includes at least the abnormal equipment identifier, anomaly type, occurrence time, and contingency measures taken. This operational anomaly information is recorded in the edge terminal's local log and then uploaded to the cloud via the communication link, providing data support for subsequent equipment maintenance, fault diagnosis, and system optimization.

[0066] Through the embodiments of the present invention, after the device is controlled to perform an operation according to the local feedback instructions, the execution status of the target operation is monitored. When the operation fails or the device is unresponsive, a backup process is initiated, and abnormal information is recorded and uploaded to the cloud. This allows for timely response to operational failures, ensuring the stable operation of the station's interactive system and reducing the impact on passenger services caused by equipment or operational problems.

[0067] According to the present invention, a cloud-edge-device intelligent station interaction method performs real-time data analysis and decision-making based on user requests and filtered data, and generates local feedback instructions corresponding to user requests, including: Receive resource preloading strategy issued by the cloud, which is generated by the cloud based on the fusion analysis of historical passenger flow data and filtered data of the station; According to the resource preloading strategy, before the predicted high passenger flow period, train information, navigation maps and multimedia content with more than the number of queries in the cloud are preloaded to the local cache. When a user request matches the target information in the local cache, a local feedback instruction is generated based on the target information in the local cache.

[0068] In this embodiment of the invention, the station edge terminal receives and parses the resource preloading strategy issued by the cloud through its communication link with the cloud. This strategy is used to predict high passenger flow periods that may occur in specific future periods (such as holidays, morning and evening peak hours) and the information resources that are frequently requested during those periods.

[0069] According to the resource preloading strategy, resource preloading is performed. Before the actual arrival of the peak passenger flow period predicted by the cloud, the station edge terminal proactively pulls (i.e., preloads) a batch of resources predicted to have a high access probability from the cloud to the local storage space (i.e., local cache) in accordance with the resource preloading strategy. These resources typically include train information with more than a threshold number of queries, internal station navigation maps, and related announcement multimedia content. The preloading operation is completed when the network load is low, avoiding the impact of network congestion that may occur during peak passenger flow periods on data acquisition speed.

[0070] Local feedback instructions are generated using local caching during request matching. Upon receiving a user request, during real-time data analysis and decision-making, the request content is first matched against resources in the local cache. When the user request matches the target information in the local cache (for example, the user is querying pre-loaded train information), the edge device directly reads the target information from the local cache and quickly generates local feedback instructions based on this. By eliminating the network transmission time for real-time data requests to the cloud, this process can achieve millisecond-level instruction generation, greatly improving the perceived response speed for the user.

[0071] Through the embodiments of the present invention, by leveraging the resource preloading strategy generated by the cloud based on historical passenger flow and filtered data, frequently queried train information, navigation maps and multimedia content are preloaded into the local cache before high passenger flow periods. This allows user requests to directly generate feedback instructions based on local information when they match the target information in the local cache, effectively reducing cloud data transmission latency and improving response speed.

[0072] The following describes an example of a cloud-edge-device-based intelligent station interaction method provided by the present invention in a practical application, specifically including the following steps.

[0073] S1: Requirements analysis and user research.

[0074] In this embodiment of the invention, demand analysis and user research determine the user group and needs of the smart station; and study user usage scenarios and interaction preferences.

[0075] S2: System design and architecture planning.

[0076] In this embodiment of the invention, the system design and architecture planning design the cloud-edge architecture, including cloud and edge components; and determine the data flow and information transmission paths.

[0077] S3: Sensor and device selection.

[0078] In this embodiment of the invention, the sensors and devices selected are those suitable for the station environment, including cameras and sound sensors; ensuring that the devices can exchange and process data with the cloud.

[0079] S4: Data acquisition and processing.

[0080] In this embodiment of the invention, data acquisition and processing involves collecting data from sensors at the edge; the data undergoes preliminary processing and filtering to reduce the amount of data transmitted to the cloud.

[0081] S5: Local decision-making and feedback.

[0082] In this embodiment of the invention, local decision-making and feedback are performed at the edge, involving basic data analysis and decision-making; responding to user requests and triggering local operations, including displaying station information and responding to voice commands.

[0083] S6: Cloud-based data analysis and optimization.

[0084] In this embodiment of the invention, cloud data analysis and optimization transmits the collected data to the cloud for in-depth analysis; it analyzes data such as passenger flow and station utilization to optimize services and station operations.

[0085] S7: User interface design and interaction.

[0086] In this embodiment of the invention, the user interface design and interaction design include a station display screen and a mobile application interface; providing real-time information, train schedule query, and traffic warning functions.

[0087] S8: System integration and testing.

[0088] In this embodiment of the invention, system integration and testing integrate all components into the intelligent station system; comprehensive testing and user experience testing are conducted to ensure system stability and user-friendliness, and improve management efficiency.

[0089] Through the embodiments of this invention, station managers can monitor passenger flow, station operation status, and equipment operation in real time, enabling precise resource allocation and operational management, thereby improving the overall management efficiency of the station and optimizing the passenger experience. Through real-time data analysis and local decision-making capabilities, the system can quickly respond to passenger needs, such as providing real-time train information and traffic alerts, significantly improving passenger convenience and comfort while reducing data processing costs. Employing edge computing technology allows for preliminary processing and filtering during the data acquisition phase, reducing the need for large amounts of data to be transmitted to the cloud, lowering data processing and storage costs, and enhancing system stability. Moving some decision-making and feedback functions to the edge reduces reliance on cloud network stability, improving system stability and reliability, and supporting intelligent decision-making. Through in-depth data analysis in the cloud, the system can identify potential optimization opportunities from long-term data trends and support intelligent operational decisions, including optimizing passenger flow plans or resource allocation strategies.

[0090] The following describes the cloud-edge-device-based intelligent station interaction device provided by the present invention. The cloud-edge-device-based intelligent station interaction device described below can be referred to in correspondence with the cloud-edge-device-based intelligent station interaction method described above.

[0091] refer to Figure 2 , Figure 2 This is a schematic diagram of a cloud-edge-device-based intelligent station interaction device provided by the present invention.

[0092] The acquisition module 201 is used to acquire station environment data collected by station environment sensors and user requests initiated by users through the interactive interface; Filtering module 202 is used to preprocess and filter station environmental data to obtain filtered data; The generation module 203 is used to perform real-time data analysis and decision-making based on user requests and filtered data, and to generate local feedback instructions corresponding to user requests. Feedback module 204 is used to control the station's local equipment to perform the target operation in response to user requests based on local feedback instructions.

[0093] Specifically, the cloud-edge-device-based intelligent station interaction device provided by the present invention can implement all the method steps implemented in the above-mentioned cloud-edge-device-based intelligent station interaction method embodiment, and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0094] Figure 3 This is a schematic diagram of the physical structure of the electronic device provided by the present invention, such as... Figure 3 As shown, the electronic device may include a processor 310, a communications interface 320, a memory 330, and a communication bus 340. The processor 310, communications interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions stored in the memory 330 to execute a cloud-edge-device-based intelligent station interaction method. This method includes: acquiring station environmental data collected by station environmental sensors and user requests initiated by the user through the interactive interface; preprocessing and filtering the station environmental data to obtain filtered data; performing real-time data analysis and decision-making based on the user request and the filtered data to generate local feedback instructions corresponding to the user request; and controlling local station equipment to perform target operations in response to the user request based on the local feedback instructions.

[0095] Furthermore, the logical instructions in the aforementioned memory 330 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, in essence, 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 of 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.

[0096] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the cloud-edge-device-based intelligent station interaction method provided by the above methods. The method includes: acquiring station environment data collected by station environment sensors and user requests initiated by users through an interactive interface; preprocessing and filtering the station environment data to obtain filtered data; performing real-time data analysis and decision-making based on user requests and filtered data to generate local feedback instructions corresponding to user requests; and controlling local station equipment to perform target operations in response to user requests according to the local feedback instructions.

[0097] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program is implemented to perform the cloud-edge-device-based intelligent station interaction method provided by the above methods. The method includes: acquiring station environmental data collected by station environmental sensors and user requests initiated by users through an interactive interface; preprocessing and filtering the station environmental data to obtain filtered data; performing real-time data analysis and decision-making based on user requests and filtered data to generate local feedback instructions corresponding to user requests; and controlling local station equipment to perform target operations in response to user requests according to the local feedback instructions.

[0098] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0099] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A cloud-edge-device-based intelligent station interaction method, characterized in that, Applied to the edge of the station, including: Acquire station environmental data collected by station environmental sensors and user requests initiated by users through the interactive interface; The station environment data is preprocessed and filtered to obtain filtered data; Based on the user request and the filtered data, real-time data analysis and decision-making are performed to generate local feedback instructions corresponding to the user request. The station's local equipment is controlled to perform the target operation in response to the user request, based on the local feedback instructions.

2. The cloud-edge-device intelligent station interaction method according to claim 1, characterized in that, The method further includes: Upload the filtered data to the pre-connected cloud; Upon receiving the station operation results from the cloud, the station operation results are visualized and displayed, including: current passenger flow, station utilization rate, and passenger flow forecast. Upon receiving the operation optimization strategy issued by the cloud, the data model used to generate the local feedback instruction is updated based on the received operation optimization strategy.

3. The cloud-edge-device intelligent station interaction method according to claim 1, characterized in that, The station environment data includes video image data and environmental audio data; The preprocessing and filtering of the station environment data to obtain filtered data includes: The video image data is processed by image recognition to obtain passenger count statistics. Voiceprint event detection is performed on the environmental audio data to obtain specific sound events within the station environment; The passenger count statistics and the specific sound events are used together as the filtered data.

4. The cloud-edge-device intelligent station interaction method according to claim 3, characterized in that, The step of performing real-time data analysis based on the user request and the filtered data to generate a local feedback instruction corresponding to the user request includes: When the user's request type is information query, the congestion level is predicted based on the passenger number statistics in the filtered data to obtain the congestion level information of the target train in the user's request. Based on the congestion information of the target train, a display instruction is generated as the local feedback instruction, wherein the display instruction is used to display the target train information containing the congestion information; When the user's request type is a voice reminder, abnormal behavior matching is performed based on specific sound events in the filtered data to obtain the matching result corresponding to the specific sound event; When the matching result indicates a security anomaly, a voice broadcast instruction is generated as the local feedback instruction, wherein the voice broadcast instruction is used to broadcast the security prompt information corresponding to the specific sound event.

5. The cloud-edge-device intelligent station interaction method according to claim 1, characterized in that, After controlling the station's local equipment to perform the target operation in response to the user request according to the local feedback instruction, the method further includes: Monitor the execution status of the target operation; When the target operation fails or the local station equipment is unresponsive, a backup operation process is initiated, and the operation anomaly information is recorded and uploaded to the cloud.

6. The cloud-edge-device intelligent station interaction method according to claim 1, characterized in that, The step of performing real-time data analysis and decision-making based on the user request and the filtered data, and generating a local feedback instruction corresponding to the user request, includes: Receive a resource preloading strategy issued by the cloud, wherein the resource preloading strategy is generated by the cloud based on the fusion analysis of the station's historical passenger flow data and the filtered data; According to the resource preloading strategy, before the predicted high passenger flow period, train information, navigation maps and multimedia content with more than the number of queries in the cloud are preloaded to the local cache. When the user request matches the target information in the local cache, a local feedback instruction is generated based on the target information in the local cache.

7. A cloud-edge-device based intelligent station interaction device, characterized in that, include: The acquisition module is used to acquire station environmental data collected by station environmental sensors and user requests initiated by users through the interactive interface; The filtering module is used to preprocess and filter the station environment data to obtain filtered data; The generation module is used to perform real-time data analysis and decision-making based on the user request and the filtered data, and generate local feedback instructions corresponding to the user request. The feedback module is used to control the station's local equipment to perform the target operation in response to the user request, based on the local feedback instructions.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the cloud-edge-device-based intelligent station interaction method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the cloud-edge-device-based intelligent station interaction method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the cloud-edge-device-based intelligent station interaction method as described in any one of claims 1 to 6.

Images