CN-121992862-A - Smart city gully emergency supervision Internet of things large model system, method and medium

CN121992862ACN 121992862 ACN121992862 ACN 121992862ACN-121992862-A

Abstract

The invention provides a large model system, a method and a medium of an Internet of things for smart city gully emergency supervision, wherein the system comprises an emergency supervision management platform, a gully plugged and a gully unplugged gully are distinguished based on real-time accumulated water data of the gully through the emergency supervision management platform, accumulated water data sequences of the plugged gully are obtained, accumulated water growth characteristics are analyzed, a first cleaning point and a corresponding first priority are determined based on the accumulated water growth characteristics, a blocking probability distribution of the unplugged gully is predicted, a second cleaning point is determined based on the blocking probability distribution, cleaning instructions comprising cleaning paths and cleaning sequences are generated based on the first cleaning point, the first priority and the second cleaning point information, and the cleaning instructions are used for controlling an automatic cleaning machine to move along the optimal paths and cleaning the gully corresponding to the first cleaning point and the second cleaning point according to the cleaning sequences. The method improves the emergency response speed and the resource utilization efficiency, is beneficial to guaranteeing the urban drainage function and restraining the expansion of ponding disasters.

Inventors

Shao Hanshu
Zhou Qiayan
ZENG SIWEI

Assignees

成都秦川物联网科技股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260403

Claims (9)

1. The utility model provides a smart city inlet for stom water emergent supervision thing networking large model system which characterized in that includes emergent supervision management platform, emergent supervision management platform is configured as: Determining a blocked inlet for stom water and an unblocked inlet for stom water based on real-time ponding data of the inlet for stom water; Acquiring a ponding data sequence of the blocked gully, and determining ponding growth characteristics of the blocked gully based on the ponding data sequence; determining a first cleaning point and a first priority corresponding to the first cleaning point based on the ponding growth characteristics; determining a blockage probability distribution of the non-blocked gully, and determining a second cleaning point based on the blockage probability distribution; And generating a cleaning instruction based on the first cleaning point, the first priority and the second cleaning point, wherein the cleaning instruction comprises a cleaning path and a cleaning sequence, controlling an automatic cleaner to move along the cleaning path based on the cleaning instruction, and cleaning the gutter inlet corresponding to the first cleaning point and the gutter inlet corresponding to the second cleaning point respectively based on the cleaning sequence.
2. The system of claim 1, wherein the emergency supervisory management platform is further configured to: Determining associated gullies and associated features corresponding to the associated gullies based on urban pipe network data and position information of the gullies; constructing a drainage map based on the real-time image data of the gully, the real-time ponding data, the future meteorological data, the associated gully and the corresponding associated features; Based on the drainage map, predicting the blockage probability distribution of the unplugged gullies through a blockage prediction model, wherein the blockage prediction model is a machine learning model.
3. The system of claim 2, wherein the emergency supervisory management platform is further configured to: Determining a blockage feature of the blocked gully based on the real-time image data of the blocked gully; Adjusting the first priority based on the blockage feature and the zone type of the gully; Determining a second priority based on the blockage probability distribution of the unblocked gullies and the region type of the gullies; And adjusting the cleaning path based on the adjusted first priority and the second priority, and controlling the automatic cleaner to move along the adjusted cleaning path to clean the gully on the adjusted cleaning path.
4. The system of claim 1, wherein the emergency supervisory management platform is further configured to: Determining a ponding early warning area and corresponding early warning information based on the blocking characteristics of the blocked gully and the real-time ponding data; and generating a ponding early warning instruction based on the ponding early warning area and the early warning information, and controlling a mobile terminal, a display device and a vehicle-mounted terminal in the early warning area to display the early warning information based on the ponding early warning instruction.
5. A smart city gutter inlet emergency supervision method, characterized in that the method is performed by an emergency supervision management platform of a smart city gutter inlet emergency supervision internet of things large model system, the method comprising: Determining a blocked inlet for stom water and an unblocked inlet for stom water based on real-time ponding data of the inlet for stom water; Acquiring a ponding data sequence of the blocked gully, and determining ponding growth characteristics of the blocked gully based on the ponding data sequence; determining a first cleaning point and a first priority corresponding to the first cleaning point based on the ponding growth characteristics; determining a blockage probability distribution of the non-blocked gully, and determining a second cleaning point based on the blockage probability distribution; And generating a cleaning instruction based on the first cleaning point, the first priority and the second cleaning point, wherein the cleaning instruction comprises a cleaning path and a cleaning sequence, and the cleaning instruction is configured to control an automatic cleaning machine to move along the cleaning path and clean the rainwater inlet corresponding to the first cleaning point and the second cleaning point respectively based on the cleaning sequence.
6. The method of claim 5, wherein the determining a blockage probability distribution for the unblocked gullies comprises: Determining associated gullies and associated features corresponding to the associated gullies based on urban pipe network data and position information of the gullies; constructing a drainage map based on the real-time image data of the gully, the real-time ponding data, the future meteorological data, the associated gully and the corresponding associated features; Based on the drainage map, predicting the blockage probability distribution of the unplugged gullies through a blockage prediction model, wherein the blockage prediction model is a machine learning model.
7. The method of claim 6, wherein the method further comprises: Determining a blockage feature of the blocked gully based on the real-time image data of the blocked gully; Adjusting the first priority based on the blockage feature and the zone type of the gully; Determining a second priority based on the blockage probability distribution of the unblocked gullies and the region type of the gullies; And adjusting the cleaning path based on the adjusted first priority and the second priority, and controlling the automatic cleaner to move along the adjusted cleaning path to clean the gully on the adjusted cleaning path.
8. The method of claim 5, wherein the method further comprises: Determining a ponding early warning area and corresponding early warning information based on the blocking characteristics of the blocked gully and the real-time ponding data; And generating a water accumulation early warning instruction based on the water accumulation early warning area and the early warning information, wherein the water accumulation early warning instruction is configured to control a mobile terminal, a display device and a vehicle-mounted terminal in the early warning area to display the early warning information.
9. A computer readable storage medium storing computer instructions, wherein when the computer instructions in the storage medium are read by a computer, the computer performs the smart city gully emergency supervision method according to claim 5.

Description

Smart city gully emergency supervision Internet of things large model system, method and medium Technical Field The specification relates to the field of road monitoring, in particular to a large model system, a method and a medium for intelligent city gully emergency supervision Internet of things. Background In urban drainage systems, the rain grate (also called gully) plays a key role in collecting road runoffs. However, in the fallen leaf season, in the strong wind weather or in the vicinity of the construction area, the rain grate is extremely liable to be covered or blocked by sundries such as leaves, garbage, silt and the like. The blockage causes that rainwater cannot enter an underground drainage pipe network in time, and is one of important reasons for causing urban road surface ponding. The existing blockage monitoring and processing mode mainly relies on manual inspection or deployment of isolated sensors. The manual inspection is low in efficiency, limited in coverage range and safe in risk, sudden blockage is difficult to find and position in time, and the isolated sensor data is difficult to accurately distinguish ponding causes and cannot effectively identify the property and coverage degree of the blockage. This results in a delayed response, and the inability to perform accurate risk assessment and predictive maintenance under complex and varying environmental conditions, and passive cleanup operations are often initiated after the water accumulation has formed. Therefore, it is hoped that the large model system, method and medium of the internet of things for intelligent city gully emergency supervision can be provided, and the problem of road surface ponding caused by gully blockage can be effectively prevented and solved. Disclosure of Invention The intelligent city rain water inlet emergency supervision Internet of things large model system comprises a intelligent city rain water inlet emergency supervision Internet of things large model system. The intelligent city water inlet emergency supervision Internet of things large model system comprises an emergency supervision management platform, wherein the emergency supervision management platform is configured to execute an intelligent city water inlet emergency supervision method. The method comprises the steps of determining a blocked rain inlet and a non-blocked rain inlet based on real-time accumulated water data of the rain inlet, obtaining an accumulated water data sequence of the blocked rain inlet, determining accumulated water growth characteristics of the blocked rain inlet based on the accumulated water data sequence, determining a first cleaning point and a first priority corresponding to the first cleaning point based on the accumulated water growth characteristics, determining a blocking probability distribution of the non-blocked rain inlet, determining a second cleaning point based on the blocking probability distribution, and generating cleaning instructions based on the first cleaning point, the first priority and the second cleaning point, wherein the cleaning instructions comprise a cleaning path and a cleaning sequence, and the cleaning instructions are configured to control an automatic cleaning machine to move along the cleaning path and clean the rain inlet respectively corresponding to the first cleaning point and the second point based on the cleaning sequence. The invention comprises a computer readable storage medium, wherein the storage medium stores computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes the smart city gully emergency supervision method. Based on the content of the invention, potential risk points are identified by analyzing the blockage probability distribution of the non-blocked gully, and the emergency degree of disaster development is accurately judged by analyzing the ponding growth characteristics of the blocked gully, so that the global optimization strategy ensures that limited emergency resources are effectively applied, improves the emergency response speed and the resource utilization efficiency, is beneficial to recovering urban drainage function in a short time and inhibits the expansion of ponding disasters. Drawings The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein: FIG. 1 is an exemplary schematic diagram of a smart city gully emergency supervision Internet of things large model system shown in accordance with some embodiments of the present disclosure; FIG. 2 is an exemplary flow chart of a smart city gully emergency supervision method according to some embodiments of the present disclosure; FIG. 3 is an exemplary schematic diagram of a jam prediction model shown according to some embodiments of the present disclos