Channel dynamic data monitoring method and system, electronic equipment and storage medium
By receiving and analyzing the dynamic data of the waterway in the waterway monitoring system and identifying risk events using prediction models, the problem of difficult to predict data change trends in the existing technology is solved, and the intelligent management level and safety of the waterway are improved.
Patent Information
- Application Number
- CN202411363260.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-27
- Publication Date
- 2024-11-12
AI Technical Summary
The existing technology is difficult to predict data change trends in the monitoring of waterway dynamic data, resulting in a low degree of digitalization and intelligence of smart waterways, and the inability to effectively identify potential risk events.
By receiving real-time dynamic data collected from the channel monitoring point, input it to the prediction model for analysis, determining the data change trend and risk level, pushing the data change trend to the channel monitoring end based on the risk level, and generating a channel dynamic report and use efficiency evaluation report, scheduling Ship navigation route.
It has realized intelligent monitoring of the dynamic data of the waterway, timely and accurately identify risk events, improved the accuracy and intelligence of waterway maintenance, and improved monitoring effect and resource utilization efficiency.
Smart Images

Figure CN118941095A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of waterway monitoring technology or other related fields, and in particular to a method and system for monitoring waterway dynamic data, an electronic device and a storage medium. Background Art
[0002] Monitoring based on waterway dynamic data helps to timely detect potential risk events (such as water level exceeding warning levels, waterway overload, ship deviation from the waterway, etc.), thereby achieving the level of intelligence in waterway maintenance.
[0003] In the related technologies, when monitoring the dynamic data of waterways, the basic navigation operation data of ports and waterways is mainly monitored, and then the shipping information is presented in the form of data charts. For example, the position, speed and course of ships sailing in the waterway are monitored by radar technology to detect potential collision hazards, or the image data of the waterway area is obtained by satellite remote sensing technology to obtain the dynamic information of the waterway. However, the related technologies do not involve how to use the monitored data to predict the changing trend of the waterway dynamic data in a certain period of time in the future, and cannot identify potential risk events, and have not effectively improved the digitization and intelligence of smart waterways.
[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention
[0005] The embodiments of the present invention provide a method and system for monitoring waterway dynamic data, an electronic device and a storage medium, so as to at least solve the technical problems in the related art that it is difficult to predict the changing trend of waterway dynamic data when monitoring waterway dynamic data, and the degree of intelligence of waterway maintenance is low.
[0006] According to one aspect of an embodiment of the present invention, a method for monitoring waterway dynamic data is provided, comprising: receiving real-time dynamic data collected by N waterway monitoring points through Internet of Things sensing devices, where N is a positive integer; inputting the real-time dynamic data into a prediction model, and having the prediction model analyze each of the real-time dynamic data to determine a data change trend and a risk level corresponding to the target dynamic data, wherein the prediction model indicates a linear relationship, a time series relationship, a causal relationship, and a coupling relationship between multiple dynamic data; and based on the risk level, pushing the data change trend to a waterway monitoring terminal.
[0007] Optionally, the method for monitoring waterway dynamic data also includes: generating a waterway dynamic report and a waterway utilization efficiency evaluation report based on data change trends corresponding to multiple target dynamic data; and scheduling the navigation route of the ship according to the waterway dynamic report and the waterway utilization efficiency evaluation report.
[0008] Optionally, the method for monitoring waterway dynamic data also includes a model training step: acquiring historical dynamic data collected from multiple waterway monitoring points, and performing feature extraction on the historical dynamic data to obtain linear relationship features, time series relationship features, causal relationship features, and coupling relationship features; and obtaining the prediction model based on the historical dynamic data and the extracted feature training.
[0009] Optionally, the method for monitoring the waterway dynamic data also includes: based on the waterway business rules, setting multiple risk levels and the numerical ranges corresponding to each dynamic data at each risk level, and constructing a risk level comparison table according to the risk levels and the numerical ranges; determining the confidence space of the prediction results output by the prediction model, and determining the risk level indicated by the data change trend corresponding to the target dynamic data according to the confidence space and the risk level comparison table.
[0010] Optionally, after receiving real-time dynamic data collected by N waterway monitoring points through Internet of Things sensing devices, the method for monitoring waterway dynamic data also includes: preprocessing the real-time dynamic data uploaded by the Internet of Things sensing devices, wherein the preprocessing includes data cleaning, missing value filling and normalization; fusing the preprocessed real-time dynamic data with the waterway geographic data to generate a visual waterway map including waterway direction and ship distribution.
[0011] Optionally, the method also includes pre-setting a dynamic data anomaly threshold. After receiving real-time dynamic data collected by N waterway monitoring points through IoT sensing devices, the waterway dynamic data monitoring method also includes: comparing the real-time dynamic data with the dynamic data anomaly threshold to determine abnormal dynamic data; and sending the abnormal dynamic data to data monitoring related parties.
[0012] Optionally, before the step of obtaining real-time dynamic data corresponding to multiple waterway monitoring points, the method for monitoring waterway dynamic data also includes: establishing device access standards so that each of the IoT sensing devices can upload the collected data based on the device access standards; setting a data upload frequency to determine the IoT sensing device that has failed based on the data upload frequency.
[0013] According to another aspect of an embodiment of the present invention, a monitoring system for waterway dynamic data is also provided, including: a data receiving unit, used to receive real-time dynamic data collected by N waterway monitoring points through Internet of Things sensing devices, N is a positive integer; a data processing unit, used to input the real-time dynamic data into a prediction model, and the prediction model analyzes each of the real-time dynamic data to determine the data change trend and risk level corresponding to the target dynamic data, wherein the prediction model indicates the linear relationship, time series relationship, causal relationship and coupling relationship between multiple dynamic data; a target push unit, used to push the data change trend to the waterway monitoring end based on the risk level.
[0014] Optionally, the monitoring system for waterway dynamic data also includes: a report generation unit, used to generate a waterway dynamic report and a waterway utilization efficiency evaluation report based on the data change trends corresponding to multiple target dynamic data; and a ship route scheduling unit, used to schedule the navigation route of the ship according to the waterway dynamic report and the waterway utilization efficiency evaluation report.
[0015] Optionally, when training the model, the waterway dynamic data monitoring system includes: a data acquisition unit, used to acquire historical dynamic data collected from multiple waterway monitoring points, and perform feature extraction on the historical dynamic data to obtain linear relationship features, time series relationship features, causal relationship features, and coupling relationship features; a model training unit, used to obtain the prediction model based on the historical dynamic data and the extracted feature training.
[0016] Optionally, the monitoring system for the waterway dynamic data also includes: a risk level comparison table construction unit, which is used to set multiple risk levels and the numerical ranges corresponding to each dynamic data at each risk level based on the waterway business rules, and construct a risk level comparison table according to the risk levels and the numerical ranges; a risk level determination unit, which is used to determine the confidence space of the prediction results output by the prediction model, and determine the risk level indicated by the data change trend corresponding to the target dynamic data according to the confidence space and the risk level comparison table.
[0017] Optionally, the monitoring system for waterway dynamic data also includes: a preprocessing unit, which is used to preprocess the real-time dynamic data uploaded by the Internet of Things sensing devices after receiving the real-time dynamic data collected by N waterway monitoring points through the Internet of Things sensing devices, wherein the preprocessing includes data cleaning, missing value filling and normalization; the preprocessed real-time dynamic data is merged with the waterway geographic data to generate a visual waterway map including the direction of the waterway and the distribution of ships.
[0018] Optionally, the waterway dynamic data monitoring system also includes: a threshold setting unit, used to pre-set a dynamic data abnormality threshold. After receiving real-time dynamic data collected by N waterway monitoring points through Internet of Things sensing devices, the waterway dynamic data monitoring system also includes: an abnormal dynamic data determination unit, used to compare the real-time dynamic data with the dynamic data abnormality threshold to determine the abnormal dynamic data; and send the abnormal dynamic data to data monitoring related parties.
[0019] Optionally, the waterway dynamic data monitoring system also includes: an access standard establishing unit, used to establish a device access standard before the step of obtaining real-time dynamic data corresponding to multiple waterway monitoring points, so that each of the IoT sensing devices can upload the collected data based on the device access standard; an upload frequency setting unit, used to set the data upload frequency, so as to determine the IoT sensing device that has failed according to the data upload frequency.
[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for monitoring waterway dynamic data.
[0021] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned methods for monitoring waterway dynamic data.
[0022] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of any one of the above-mentioned methods for monitoring waterway dynamic data are implemented.
[0023] In the present disclosure, real-time dynamic data collected by N waterway monitoring points through Internet of Things sensing devices are received, and then the real-time dynamic data are input into a prediction model, and the prediction model analyzes each real-time dynamic data to determine the data change trend and risk level corresponding to the target dynamic data, and based on the risk level, the data change trend is pushed to the waterway monitoring end, wherein the prediction model indicates the linear relationship, time series relationship, causal relationship and coupling relationship between multiple dynamic data, realizes intelligent monitoring of waterway dynamic data based on Internet of Things technology, and predicts the change trend and risk level of waterway dynamic data according to the monitored data, timely and accurately identifies risk events, improves monitoring effects, and improves the precision and intelligence of waterway maintenance. The technical effect solves the technical problem in the related technology that it is difficult to predict the change trend of waterway dynamic data when monitoring waterway dynamic data, and the intelligence level of waterway maintenance is low. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0025] Figure 1 is a flow chart of an optional method for monitoring waterway dynamic data according to an embodiment of the present invention;
[0026] Figure 2 is a flow chart of another method for monitoring waterway dynamic data according to an embodiment of the present invention;
[0027] Figure 3 is a schematic diagram of an optional system for monitoring waterway dynamic data according to an embodiment of the present invention;
[0028] Figure 4 The present invention is a hardware structure block diagram of an electronic device (or mobile device) for a method for monitoring waterway dynamic data according to an embodiment of the present invention. DETAILED DESCRIPTION
[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0031] To facilitate those skilled in the art to understand the present invention, some terms involved in various embodiments of the present invention are explained below:
[0032] Terminal production management system is a software system used to manage and monitor the loading and unloading operations of ships at the terminal. The system can help terminal managers monitor the entry and exit of ships, the progress of ship operations, cargo loading and unloading in real time, and improve operational efficiency and accuracy.
[0033] At present, smart ports and smart waterways are the leading areas for accelerating the construction of smart transportation and an important part of the construction of new transportation infrastructure. However, the construction of smart ports and smart waterways still faces some problems and shortcomings, such as the depth and breadth of digital and intelligent applications need to be expanded, network security and data security protection need to be strengthened, the terminal production management system (TOS) is not standardized enough, and the intelligent level of waterway maintenance management is not high. At the same time, the relevant technologies mainly monitor the basic navigation operation data in the operation of ports and waterways, and then present the shipping information in the form of data charts, but do not involve how to use the monitored data to predict the changing trend of waterway dynamic data in a certain period of time in the future, and cannot identify potential risk events, and have not effectively improved the digitalization and intelligence of smart waterways.
[0034] The following embodiments of the present invention can be applied to various systems / applications / devices for monitoring waterway dynamic data. In order to solve the above-mentioned problems in the process of monitoring waterway dynamic data, the present invention realizes intelligent monitoring of waterway dynamic data based on the Internet of Things technology, and predicts the change trend and risk level of waterway dynamic data based on the monitored data, timely and accurately identifies risk events, and improves the waterway monitoring effect.
[0035] The present invention is described in detail below in conjunction with various embodiments.
[0036] Embodiment 1
[0037] According to an embodiment of the present invention, an embodiment of a method for monitoring waterway dynamic data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0038] Figure 1 is a flow chart of an optional method for monitoring waterway dynamic data according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:
[0039] Step S101, receiving real-time dynamic data collected by N waterway monitoring points through IoT sensing devices, where N is a positive integer.
[0040] Among them, the dynamic data provided by the embodiment of the present invention includes dynamic data such as channel water depth, water flow, water quality, weather, ship position, navigation status (including navigation status data such as speed, heading, tonnage, etc.).
[0041] By installing and deploying IoT sensing devices at key locations of the waterway (i.e. the above-mentioned waterway monitoring points), it is ensured that the monitoring needs of all data elements of the waterway are covered. Specifically, IoT sensing devices include water level meters, flow meters, water quality monitors, weather stations, video surveillance cameras, AIS (Automatic Identification System) base stations, VTS (Vessel Traffic Service) radars and other sensor devices selected according to the waterway monitoring needs.
[0042] In one embodiment, before the step of obtaining real-time dynamic data waterway spatial geographic data corresponding to multiple waterway monitoring points, the above method also includes: establishing a device access standard so that each IoT sensing device can upload the collected data based on the device access standard; setting a data upload frequency to determine the IoT sensing device that has a fault according to the data upload frequency.
[0043] During the data collection process, by starting the Internet of Things device, it can automatically collect the waterway dynamic data according to the preset parameters. However, since the monitoring needs of the waterway dynamic data indicate multiple categories of sensing devices, and each device may come from different manufacturers and have multiple specifications and models, in order to achieve the compatibility and standardization of various types of IoT sensing devices and ensure that devices of different manufacturers and different specifications and models can exchange data / upload data according to a unified communication protocol, this can be achieved through the standardization of hardware interfaces and the design of software adaptation layers. Through the above settings, device access standards are established, and the Internet of Things technology is integrated with the intelligent management of waterways, expanding the application of waterway dynamic data monitoring in various river and sea scenarios; at the same time, the real-time and accuracy of the acquired monitoring data are improved, providing data support for the subsequent prediction of the changing trend of waterway dynamic data.
[0044] At the same time, by setting a fixed data upload frequency, faulty IoT sensing devices can be discovered in a timely manner to avoid affecting the data collection process and improve the stability of data monitoring.
[0045] In another embodiment, before the step of receiving the real-time dynamic data corresponding to multiple waterway monitoring points, the above method also includes: preprocessing the real-time dynamic data uploaded by the Internet of Things sensing device; wherein the preprocessing includes data cleaning, missing value filling and normalization processing; fusing the preprocessed real-time dynamic data with the waterway geographic data to generate a visual waterway map including the direction of the waterway and the distribution of ships.
[0046] After receiving the real-time dynamic data corresponding to multiple waterway monitoring points, the real-time dynamic data can be pre-processed by performing data cleaning, missing value filling, normalization and other pre-processing operations to meet subsequent data fusion or modeling requirements.
[0047] By fusing the dynamic data on the waterway (including the spatial information of various monitoring points, lines, surfaces, and volumes) with the geographical data of the waterway and presenting them in a graphical manner, such as displaying the direction of the waterway, the distribution of ships, the layout of facilities, etc. through the GIS map system, business personnel can intuitively understand the spatial situation of the waterway. Furthermore, according to the timestamps corresponding to the data, visual waterway maps corresponding to each timestamp can be generated, so that business personnel can check the visual waterway maps corresponding to the monitoring data (covering hydrology, meteorology, ship operation, waterway facilities, etc.) at any time granularity (year, month, day, hour, minute, second).
[0048] It should be noted that the above method also includes pre-setting a dynamic data anomaly threshold. After the step of receiving real-time dynamic data, the real-time dynamic data can also be compared with the dynamic data anomaly threshold to determine abnormal dynamic data; and the abnormal dynamic data can be sent to data monitoring related parties.
[0049] Risk events (such as water level exceeding warning level, channel overload, ship deviation from channel, etc.) may occur at some point in the future, or may have already occurred during monitoring. In order to improve channel maintenance, enhance monitoring effectiveness, and protect the personal and property safety of ships and accompanying personnel, dynamic data abnormality thresholds can be set in advance. After collecting real-time dynamic data, it can be immediately determined whether a potential risk event has occurred, so as to improve the timeliness of early warning.
[0050] Step S102, input the real-time dynamic data into the prediction model, and the prediction model analyzes each real-time dynamic data to determine the data change trend and risk level corresponding to the target dynamic data.
[0051] Through the above settings, the predictive model that indicates the correlation relationship characteristics between waterway dynamic data is the core component of the smart waterway. Through the predictive analysis of real-time dynamic data, real-time perception, intelligent analysis and decision support of waterway status can be achieved, promoting the digital, networked and intelligent transformation of waterway management.
[0052] Among them, the prediction model indicates the linear relationship, temporal relationship, causal relationship and coupling relationship among multiple dynamic data.
[0053] The prediction model can predict the future waterway status based on historical data (referenced when the model is built) and current status (reflected from real-time dynamic data), identify potential risks in advance, such as abnormal water levels, ship congestion, and bad weather, and provide early warning information to management departments so that timely response measures can be taken to reduce the possibility of accidents. It can also predict future waterway flow, ship types, navigation needs, etc. to meet the waterway maintenance needs of rationally allocating waterway maintenance, rescue forces, service facilities and other resources, improve resource utilization efficiency, and reduce operating costs. At the same time, the risk level in the prediction results provides a quantitative basis for waterway management decisions, and provides a basis for adjusting navigation mark distribution, dispatching ships, issuing navigation notices, and launching emergency plans, which helps to improve the accuracy and efficiency of decision-making.
[0054] Furthermore, the above method also includes a model training step: obtaining historical dynamic data collected from multiple waterway monitoring points, and performing feature extraction on the historical dynamic data to obtain linear relationship features, time series relationship features, causal relationship features, and coupling relationship features; and obtaining a prediction model based on the historical dynamic data and the extracted feature training.
[0055] The prediction model mentioned in this embodiment can be a model that incorporates a plug-in multimodal retrieval module. The plug-in multimodal retrieval module learns an embedding space, retrieves multiple data features, and uses a unified encoder model to encode the retrieved features to reduce the modal differences between the detection data and the features. Specifically, the data features encoded by the feature module can be used as input to enhance the data understanding ability of a well-trained dense retriever. At the same time, in order to promote multimodal retrieval tasks, this embodiment can construct a ClueWeb22-MM data set, through which the received monitoring data is used as anchor text and as a query specimen, and the waterway management data and collected image documents in the historical process are extracted from the anchor-linked web pages. In this way, the waterway features can be retrieved through multimodality (monitoring data, data features, and waterway images) to achieve reasoning about the changing trend of the waterway features.
[0056] Based on the historical waterway dynamic data, a prediction model is constructed and trained to predict the future trend of a specific dynamic data (such as waterway water level, ship flow, waterway occupancy rate, etc.) and its corresponding risk level. Before model training, the historical dynamic data can be preprocessed to meet the modeling requirements. During the model construction and training process, feature engineering is used to extract the relationship characteristics between waterway dynamic data, including linear relationship characteristics, time series relationship characteristics (time series data often have characteristics such as autocorrelation and seasonality, which can be used to capture the trend and periodicity of data changes over time), causal relationship characteristics (waterway water level may have a causal relationship with upstream reservoir water release, rainfall, evaporation and other factors) and coupling relationship characteristics (different waterway data elements may have coupling effects, such as water level and flow rate, ship flow and waterway occupancy rate, etc., these data elements interact with each other), etc. Furthermore, considering that the waterway conditions may be affected by the external environment (such as climate conditions, holidays, special events, etc.), historical data can be clustered according to similar environmental characteristics to find typical patterns in different situations, and then predicted in combination with situational characteristics. There may be cross-influences between various waterway dynamic data, such as the relationship between waterway width and depth and ship traffic efficiency, or the interactive effects between waterway congestion and weather conditions and ship types. These cross-terms can also be included in the model for joint prediction.
[0057] For the linear relationship characteristics mentioned above, for example, changes in water level have a direct linear relationship with tides; the periodic rise and fall of tides causes water levels to rise or fall. In some cases, there is also a linear relationship between the speed of water flow and water level; when the water level rises, the speed of water flow may increase, and vice versa. There may be a linear relationship between the speed of a ship and its fuel consumption; generally speaking, the faster the speed, the greater the fuel consumption, although this relationship may become nonlinear at high speeds. When the number of ships on a waterway increases, the occupancy rate of the waterway will also increase. This relationship is usually linear at low to medium flows; however, at near full load, this relationship may become nonlinear because the physical limitations of the waterway affect the rate of occupancy growth. Increased emissions from pollution sources may cause water quality deterioration indicators (such as reduced dissolved oxygen content or increased pollutant concentrations) to change in a certain proportion, etc.
[0058] By comprehensively applying the above-mentioned relationships and characteristics, a more complex and accurate prediction model can be constructed to adapt to the complex changing characteristics of waterway dynamic data, thereby improving the accuracy and reliability of the prediction of waterway conditions in the future.
[0059] In another embodiment, the above method also includes: based on the waterway business rules, setting multiple risk levels and the numerical ranges corresponding to each dynamic data at each risk level, and constructing a risk level comparison table according to the risk levels and numerical ranges; determining the confidence space of the prediction results output by the prediction model, and determining the risk level indicated by the data change trend corresponding to the target dynamic data according to the confidence space and the risk level comparison table.
[0060] According to an embodiment of the present invention, risk level evaluation criteria are set based on the prediction results. For example, when it is predicted that the water level of the channel is lower than the safety threshold, the ship flow exceeds the carrying capacity of the channel, the weather conditions are bad, etc., it can be judged as a high risk level. In combination with expert knowledge and business rules, a risk level indicator system is established, and the risk score is calculated through a quantitative model.
[0061] In order to further improve the accuracy of the risk level indicated by the prediction results, methods such as Monte Carlo simulation, interval prediction, confidence interval, etc. can be used to determine the risk level, providing decision-making support and risk prevention basis for waterway management departments.
[0062] Step S103: based on the risk level, push the data change trend to the waterway monitoring terminal.
[0063] Based on the risk level, the corresponding data change trends are sent to the waterway monitoring end / data monitoring related parties, such as waterway management personnel, crew members, port dispatching departments, etc., so that they can take timely measures to prevent or respond to possible problems, achieving early warning and accurate push, and significantly improving the safety and efficiency of waterway management and use.
[0064] In some of the embodiments, the above method also includes: generating a channel dynamics report and a channel utilization efficiency evaluation report based on the data change trends corresponding to multiple target dynamic data; and scheduling the navigation route of the ship according to the channel dynamics report and the channel utilization efficiency evaluation report.
[0065] The waterway dynamics report may include: hydrological data such as water level, water flow speed, flow direction, water depth, water temperature, etc.; meteorological data such as wind direction, visibility, precipitation, etc.; ship data such as the number of ships in the waterway, ship position, speed, course, tonnage, etc.; environmental data such as water quality; event record data such as fault events and maintenance activities; a waterway dynamics report including any one or more of the above data will help the management and relevant personnel monitor and optimize waterway operations.
[0066] The waterway efficiency assessment report may include data such as waterway utilization rate (the ratio between actual waterway use and designed capacity), ship traffic (the number of ships passing through the waterway in a specific time period, reflecting the traffic density of the waterway), average waiting time (the average waiting time before ships enter the waterway or dock at a port), and traffic efficiency (the amount of cargo or number of ships passing through the waterway per unit time, reflecting the transportation efficiency of the waterway). The assessment report including the above data can provide data support for waterway adjustment, ship scheduling, waterway improvement, etc.
[0067] Through the above settings, valuable information products such as waterway status reports, navigation risk warnings, and waterway efficiency assessments are generated based on the data change trends corresponding to multiple dynamic data, serving waterway management decisions, navigation scheduling optimization, and emergency response to emergencies. Through the deep integration and application of the above Internet of Things technology and model prediction technology, an all-round, all-weather, and three-dimensional waterway IoT perception system is ultimately built to comprehensively improve the level of waterway informationization and intelligent management, ensure the safety and smooth flow of waterways, and improve the efficiency of waterway resource utilization and service levels.
[0068] Through the above steps, the real-time dynamic data collected by N waterway monitoring points through the IoT sensing devices can be received, and the real-time dynamic data can be input into the prediction model. The prediction model analyzes each real-time dynamic data to determine the data change trend and risk level corresponding to the target dynamic data. Based on the risk level, the data change trend is pushed to the waterway monitoring end, wherein the prediction model indicates the linear relationship, time series relationship, causal relationship and coupling relationship between multiple dynamic data. In this embodiment, intelligent monitoring of waterway dynamic data based on the Internet of Things technology is realized, and the change trend and risk level of waterway dynamic data are predicted based on the monitored data, and the risk events are identified in a timely and accurate manner, the monitoring effect is improved, and the accuracy and intelligence of waterway maintenance are improved. The technical effect is thus solved, and the technical problem that it is difficult to predict the change trend of waterway dynamic data when monitoring waterway dynamic data in the related technology, and the intelligence level of waterway maintenance is low.
[0069] The embodiment of the present invention is described in detail below in combination with the above steps.
[0070] In order to solve the above problems, an embodiment of the present invention further provides a method for monitoring waterway dynamic data, which is applied to a waterway dynamic data monitoring scenario based on the Internet of Things. Figure 2 As shown, the method for monitoring waterway dynamic data provided by the embodiment of the present invention mainly includes:
[0071] Step S201, deploy IoT sensing devices at multiple waterway monitoring points, and establish device access standards so that each IoT sensing device can upload the collected data based on the device access standards.
[0072] Among them, the IoT sensing devices provided by the embodiments of the present invention include water level meters, flow meters, water quality monitors, weather stations, video surveillance cameras, AIS base stations, VTS radars and other sensor devices selected according to waterway monitoring needs.
[0073] After the deployment is completed, the IoT device can be started to automatically collect waterway dynamic data according to preset parameters. Since the monitoring requirements of waterway dynamic data indicate multiple categories of sensing devices, and each device may come from different manufacturers and have multiple specifications and models, in order to achieve the compatibility and standardization of various IoT sensing devices and ensure that devices of different manufacturers and different specifications and models can exchange data / upload data according to a unified communication protocol, this can be achieved through the standardization of hardware interfaces and the design of software adaptation layers. Through the above settings, device access standards are established, and the IoT technology is integrated with the intelligent management of waterways, expanding the application of waterway dynamic data monitoring in various river and sea scenarios; at the same time, the real-time and accuracy of the acquired monitoring data are improved, providing data support for the subsequent prediction of the changing trend of waterway dynamic data.
[0074] In some of the embodiments, the method further includes: setting a data upload frequency to determine a failed IoT sensing device based on the data upload frequency.
[0075] By setting a fixed data upload frequency, faulty IoT sensing devices can be discovered in a timely manner to avoid affecting the data collection process and improve the stability of data monitoring.
[0076] Step S202, receiving real-time dynamic data corresponding to multiple waterway monitoring points, and preprocessing the real-time dynamic data uploaded by the IoT sensing device; wherein the preprocessing includes data cleaning, missing value filling and normalization processing.
[0077] The dynamic data provided by the embodiment of the present invention includes dynamic data such as waterway depth, water flow, water quality, weather, ship position, navigation status, etc. After receiving the real-time dynamic data corresponding to multiple waterway monitoring points, the real-time dynamic data can be preprocessed to meet subsequent data fusion requirements or modeling requirements.
[0078] In some of the embodiments, the method further includes: fusing the pre-processed real-time dynamic data with the waterway geographic data to generate a visual waterway map including the direction of the waterway and the distribution of ships.
[0079] By fusing the dynamic data on the waterway with the waterway geographic data and displaying them in a graphical way, business personnel can intuitively understand the spatial situation of the waterway. Furthermore, according to the timestamps corresponding to the data, a visualized waterway map corresponding to each timestamp can be generated, so that business personnel can check the visualized waterway map corresponding to the monitoring data of any time granularity at any time.
[0080] In some of the embodiments, the method further includes pre-setting a dynamic data anomaly threshold. After the step of receiving real-time dynamic data, the method further includes: comparing the real-time dynamic data with the dynamic data anomaly threshold to determine abnormal dynamic data; and sending the abnormal dynamic data to data monitoring related parties.
[0081] By pre-setting the abnormal threshold of dynamic data, after collecting real-time dynamic data, it is immediately determined whether a potential risk event has occurred, so as to improve the timeliness of early warning.
[0082] Step S203, obtaining historical dynamic data collected from multiple waterway monitoring points, and extracting features from the historical dynamic data to obtain linear relationship features, temporal relationship features, causal relationship features, and coupling relationship features; and obtaining a prediction model based on the historical dynamic data and the extracted features.
[0083] By comprehensively applying the above relationships and characteristics, a more complex and accurate prediction model can be constructed to adapt to the complex changing characteristics of waterway dynamic data, thereby improving the accuracy and reliability of the prediction of waterway conditions in the future.
[0084] Specifically, a prediction model is constructed and trained based on historical waterway dynamic data to predict the future change trend of a certain dynamic data (such as waterway water level, ship flow, waterway occupancy rate, etc.) and its corresponding risk level. Before model training, the historical dynamic data can be preprocessed to meet the modeling requirements. During the model construction and training process, feature engineering is used to extract the relationship characteristics between waterway dynamic data, including linear relationship characteristics, time series relationship characteristics, causal relationship characteristics, and coupling relationship characteristics. Furthermore, considering that the waterway conditions may be affected by the external environment, historical data can be clustered according to similar environmental characteristics, typical patterns in different scenarios can be found, and then predictions can be made based on the scenario characteristics. There may be cross-influences between various waterway dynamic data, such as the relationship between waterway width, depth and ship traffic efficiency, or the interaction between waterway congestion and weather conditions and ship types. These cross-terms can also be included in the model for joint prediction.
[0085] According to another embodiment of the present invention, multiple sub-models can be constructed according to the extracted feature types, such as constructing a linear regression sub-model for linear relationships, constructing a time series sub-model based on temporal relationship characteristics, constructing a causal prediction sub-model based on causal relationship characteristics, and constructing a coupling system model based on coupling relationship characteristics, so as to improve the prediction and analysis efficiency of real-time dynamic data, and determine risk events and corresponding risk levels based on the prediction results of multiple sub-models.
[0086] Step S204, based on the waterway business rules, multiple risk levels and corresponding numerical ranges of various dynamic data at each risk level are set, and a risk level comparison table is constructed according to the risk levels and numerical ranges.
[0087] According to an embodiment of the present invention, risk level evaluation criteria are set based on the prediction results. For example, when it is predicted that the water level of the channel is lower than the safety threshold, the ship flow exceeds the carrying capacity of the channel, the weather conditions are bad, etc., it can be judged as a high risk level. In combination with expert knowledge and business rules, a risk level indicator system is established, and the risk score is calculated through a quantitative model.
[0088] Step S205, input the real-time dynamic data into the prediction model for data processing to determine the data change trend corresponding to the target dynamic data; and determine the confidence space corresponding to the data change trend output by the prediction model, and determine the risk level indicated by the data change trend corresponding to the target dynamic data based on the confidence space and the risk level comparison table.
[0089] Through the above settings, the predictive model that indicates the correlation relationship characteristics between waterway dynamic data is the core component of the smart waterway. Through the predictive analysis of real-time dynamic data, real-time perception, intelligent analysis and decision support of waterway status can be achieved, promoting the digital, networked and intelligent transformation of waterway management.
[0090] The prediction model can predict the future waterway status based on historical data (referenced when the model is built) and current status (reflected from real-time dynamic data), identify potential risks in advance, such as abnormal water levels, ship congestion, and bad weather, and provide early warning information to management departments so that timely response measures can be taken to reduce the possibility of accidents. It can also predict future waterway flow, ship types, navigation needs, etc. to meet the waterway maintenance needs of rationally allocating waterway maintenance, rescue forces, service facilities and other resources, improve resource utilization efficiency, and reduce operating costs. At the same time, the risk level in the prediction results provides a quantitative basis for waterway management decisions, and provides a basis for adjusting navigation mark distribution, dispatching ships, issuing navigation notices, and launching emergency plans, which helps to improve the accuracy and efficiency of decision-making.
[0091] Step S206: Based on the risk level, the corresponding data change trend is pushed to data monitoring related parties.
[0092] Based on the risk level, the corresponding data change trends are sent to data monitoring stakeholders, such as waterway managers, crew members, port dispatch departments, etc., so that they can take timely measures to prevent or respond to possible problems, achieving early warning and accurate push, and significantly improving the safety and efficiency of waterway management and use.
[0093] In some of the embodiments, the above method also includes: generating a channel dynamics report and a channel utilization efficiency evaluation report based on the data change trends corresponding to multiple dynamic data; and scheduling the navigation route of the ship according to the channel dynamics report and the channel utilization efficiency evaluation report.
[0094] Through the above settings, valuable information products such as waterway status reports, navigation risk warnings, and waterway efficiency assessments are generated based on the data change trends corresponding to multiple dynamic data, serving waterway management decisions, navigation scheduling optimization, and emergency response to emergencies. Through the deep integration and application of the above Internet of Things technology and model prediction technology, an all-round, all-weather, and three-dimensional waterway IoT perception system is ultimately built to comprehensively improve the level of waterway informationization and intelligent management, ensure the safety and smooth flow of waterways, and improve the efficiency of waterway resource utilization and service levels.
[0095] The above-mentioned waterway dynamic data monitoring method provided by the embodiment of the present invention adopts the method of receiving real-time dynamic data corresponding to multiple waterway monitoring points; wherein the real-time dynamic data is collected and uploaded by the Internet of Things sensing devices deployed at each waterway monitoring point; the real-time dynamic data is input into the prediction model for data processing to determine the data change trend and risk level corresponding to the target dynamic data; wherein the prediction model indicates the linear relationship, time series relationship, causal relationship and coupling relationship between multiple dynamic data; based on the risk level, the corresponding data change trend is pushed to the data monitoring related parties by technical means, which overcomes the problems of insufficient application depth and breadth of waterway dynamic data monitoring in related technologies, difficulty in predicting the change trend of waterway dynamic data, and low precision and intelligence of waterway maintenance, and realizes intelligent monitoring of waterway dynamic data based on Internet of Things technology, and predicts the change trend and risk level of waterway dynamic data according to the monitored data, timely and accurately identifies risk events, improves monitoring effects, and improves the precision and intelligence of waterway maintenance.
[0096] The following is a detailed description in conjunction with another embodiment.
[0097] Embodiment 2
[0098] A waterway dynamic data monitoring system provided in this embodiment includes multiple implementation units, each implementation unit corresponding to each implementation step in the above-mentioned embodiment 1.
[0099] Figure 3 is a schematic diagram of an optional waterway dynamic data monitoring system according to an embodiment of the present invention, such as Figure 3 As shown, the waterway dynamic data monitoring system may include: a data receiving unit 31 , a data processing unit 32 , and a target pushing unit 33 .
[0100] The data receiving unit 31 is used to receive real-time dynamic data collected by N waterway monitoring points through IoT sensing devices, where N is a positive integer.
[0101] The data processing unit 32 is used to input the real-time dynamic data into the prediction model, and the prediction model analyzes each real-time dynamic data to determine the data change trend and risk level corresponding to the target dynamic data, wherein the prediction model indicates the linear relationship, time series relationship, causal relationship and coupling relationship between multiple dynamic data.
[0102] The target push unit 33 is used to push the data change trend to the waterway monitoring terminal based on the risk level.
[0103] The above-mentioned waterway dynamic data monitoring system can receive the real-time dynamic data collected by the IoT sensing device at N waterway monitoring points through the data receiving unit 31, input the real-time dynamic data into the prediction model through the data processing unit 32, and analyze each real-time dynamic data by the prediction model to determine the data change trend and risk level corresponding to the target dynamic data, wherein the prediction model indicates the linear relationship, temporal relationship, causal relationship and coupling relationship between multiple dynamic data, and pushes the data change trend to the waterway monitoring end based on the risk level through the target push unit 33. In this embodiment, the intelligent monitoring of waterway dynamic data based on the Internet of Things technology is realized, and the change trend and risk level of waterway dynamic data are predicted according to the monitored data, and the technical effect of timely and accurately identifying risk events, improving the monitoring effect, and improving the accuracy and intelligence of waterway maintenance is achieved, thereby solving the technical problem that it is difficult to predict the change trend of waterway dynamic data when monitoring waterway dynamic data in the related technology, and the intelligence level of waterway maintenance is low.
[0104] Optionally, the monitoring system for waterway dynamic data also includes: a report generation unit, which is used to generate a waterway dynamic report and a waterway utilization efficiency evaluation report based on the data change trends corresponding to multiple target dynamic data; and a ship route scheduling unit, which is used to schedule the navigation route of the ship according to the waterway dynamic report and the waterway utilization efficiency evaluation report.
[0105] Optionally, when training a model, the waterway dynamic data monitoring system includes: a data acquisition unit, used to acquire historical dynamic data collected from multiple waterway monitoring points, and perform feature extraction on the historical dynamic data to obtain linear relationship features, time series relationship features, causal relationship features, and coupling relationship features; and a model training unit, used to obtain a prediction model based on the historical dynamic data and the extracted feature training.
[0106] Optionally, the monitoring system for waterway dynamic data also includes: a risk level comparison table construction unit, which is used to set multiple risk levels and numerical ranges corresponding to each dynamic data at each risk level based on waterway business rules, and construct a risk level comparison table according to the risk levels and numerical ranges; a risk level determination unit, which is used to determine the confidence space of the prediction results output by the prediction model, and determine the risk level indicated by the data change trend corresponding to the target dynamic data according to the confidence space and the risk level comparison table.
[0107] Optionally, the monitoring system for waterway dynamic data also includes: a preprocessing unit, which is used to preprocess the real-time dynamic data uploaded by the Internet of Things sensing devices after receiving the real-time dynamic data collected by N waterway monitoring points through the Internet of Things sensing devices, wherein the preprocessing includes data cleaning, missing value filling and normalization; the preprocessed real-time dynamic data is merged with the waterway geographic data to generate a visual waterway map including the direction of the waterway and the distribution of ships.
[0108] Optionally, the monitoring system for waterway dynamic data also includes: a threshold setting unit, used to pre-set a dynamic data abnormality threshold. After receiving real-time dynamic data collected by N waterway monitoring points through Internet of Things sensing devices, the monitoring system for waterway dynamic data also includes: an abnormal dynamic data determination unit, used to compare the real-time dynamic data with the dynamic data abnormality threshold to determine the abnormal dynamic data; and send the abnormal dynamic data to data monitoring related parties.
[0109] Optionally, the waterway dynamic data monitoring system also includes: an access standard establishing unit, used to establish a device access standard before the step of obtaining real-time dynamic data corresponding to multiple waterway monitoring points, so that each IoT sensing device can upload the collected data based on the device access standard; an upload frequency setting unit, used to set the data upload frequency to determine the IoT sensing device that has failed according to the data upload frequency.
[0110] The above-mentioned waterway dynamic data monitoring system may also include a processor and a memory. The above-mentioned data receiving unit 31, data processing unit 32, target pushing unit 33, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.
[0111] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the intelligent monitoring of waterway dynamic data based on the Internet of Things technology is realized by adjusting the kernel parameters, and the change trend and risk level of the waterway dynamic data are predicted based on the monitored data.
[0112] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.
[0113] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for monitoring waterway dynamic data of any one of the above-mentioned embodiments one.
[0114] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the method for monitoring waterway dynamic data of any one of the above-mentioned embodiments one.
[0115] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method for monitoring waterway dynamic data described in each embodiment of the present application.
[0116] The present application also provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for monitoring waterway dynamic data described in each embodiment of the present application are implemented.
[0117] Figure 4 1 is a hardware structure block diagram of an electronic device (or mobile device) for a method for monitoring waterway dynamic data according to an embodiment of the present invention. Figure 4 As shown, the electronic device may include one or more ( Figure 4 402a, 402b, ..., 402n are used to illustrate) a processor (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), and a memory 404 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 4 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 4 More or fewer components as shown, or with Figure 4 Different configurations shown.
[0118] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0119] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0120] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0121] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0122] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0123] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it 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 all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0124] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for monitoring waterway dynamic data, characterized in that: include: Receive real-time dynamic data collected by N waterway monitoring points through IoT sensing devices, where N is a positive integer; Input the real-time dynamic data into a prediction model, and analyze each of the real-time dynamic data by the prediction model to determine the data change trend and risk level corresponding to the target dynamic data, wherein the prediction model indicates the linear relationship, temporal relationship, causal relationship and coupling relationship between multiple dynamic data; Based on the risk level, the data change trend is pushed to the waterway monitoring terminal.
2. The monitoring method according to claim 1, characterized in that: Also includes: Generate waterway dynamic report and waterway utilization efficiency evaluation report based on the data change trend corresponding to multiple target dynamic data; The navigation route of the ship is scheduled according to the waterway dynamic report and the waterway utilization efficiency evaluation report.
3. The monitoring method according to claim 1, characterized in that: The method also includes a model training step: Acquire historical dynamic data collected from multiple waterway monitoring points, and perform feature extraction on the historical dynamic data to obtain linear relationship features, temporal relationship features, causal relationship features, and coupling relationship features; The prediction model is obtained based on the historical dynamic data and the extracted feature training.
4. The monitoring method according to claim 3, characterized in that: The method further comprises: Based on the waterway business rules, multiple risk levels and corresponding numerical ranges of various dynamic data at each risk level are set, and a risk level comparison table is constructed according to the risk levels and the numerical ranges; A confidence space of the prediction result output by the prediction model is determined, and the risk level indicated by the data change trend corresponding to the target dynamic data is determined according to the confidence space and the risk level comparison table.
5. The monitoring method according to claim 1, characterized in that: After receiving the real-time dynamic data collected by the IoT sensing devices at N waterway monitoring points, it also includes: Preprocessing the real-time dynamic data uploaded by the IoT sensing device, wherein the preprocessing includes data cleaning, missing value filling and normalization processing; The pre-processed real-time dynamic data is fused with the waterway geographic data to generate a visual waterway map including the waterway direction and ship distribution.
6. The monitoring method according to claim 1, characterized in that: The method further includes presetting a dynamic data abnormality threshold, and after receiving real-time dynamic data collected by N waterway monitoring points through IoT sensing devices, the method further includes: Comparing the real-time dynamic data with the dynamic data abnormality threshold to determine abnormal dynamic data; The abnormal dynamic data is sent to data monitoring related parties.
7. The monitoring method according to claim 1, characterized in that: Before the step of acquiring real-time dynamic data corresponding to a plurality of waterway monitoring points, the method further comprises: Establishing a device access standard so that each of the IoT sensing devices can upload the collected data based on the device access standard; The data upload frequency is set to determine the IoT sensing device that has failed according to the data upload frequency.
8. A waterway dynamic data monitoring system, characterized in that: include: A data receiving unit, used to receive real-time dynamic data collected by N waterway monitoring points through IoT sensing devices, where N is a positive integer; A data processing unit, used for inputting the real-time dynamic data into a prediction model, and having the prediction model analyze each of the real-time dynamic data to determine a data change trend and a risk level corresponding to the target dynamic data, wherein the prediction model indicates a linear relationship, a temporal relationship, a causal relationship, and a coupling relationship between a plurality of dynamic data; The target push unit is used to push the data change trend to the waterway monitoring terminal based on the risk level.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for monitoring waterway dynamic data according to any one of claims 1 to 7.
10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for monitoring waterway dynamic data as described in any one of claims 1 to 7.
Citation Information
Cited By
Smart channel data processing method, system and device based on multi-source data fusion and storage medium
CN121810467A
