Urban digital resource visual management system and method based on GIS platform

Abstract

The invention discloses a city digital resource visual management system and method based on a GIS platform, and the system comprises an access module which is used for accessing video monitoring and Internet of Things equipment of a whole city based on the GI platform, and carrying out the placement of the video monitoring and Internet of Things equipment of the whole city in a map; the aggregation module is used for analyzing the video monitoring and Internet of Things equipment after the point falling in the map and creating an aggregation effect; the early warning module is used for acquiring video monitoring data corresponding to video monitoring and Internet of Things equipment acquisition data corresponding to Internet of Things equipment in real time, analyzing the video monitoring data and the Internet of Things equipment acquisition data, and performing early warning reminding on an area where an abnormal condition exists when the abnormal condition exists; the converged communication module is used for establishing converged communication for conference terminal data and government affair personnel data of districts and counties of the whole city, and carrying out one-key conference holding based on the converged communication; and comprehensive monitoring and management of city-wide video monitoring and Internet of Things equipment management are realized on a unified map platform.

Description

Technical Field

[0001] The present invention relates to, in particular, a city digital resource visualization management system and method based on a GIS platform. Background Art

[0002] In the field of urban management, with the continuous expansion of cities and the increasing level of informatization, the demand for efficient management of urban digital resources is becoming increasingly urgent. Traditional urban management systems have numerous drawbacks. For one thing, they lack effective integration and visualization methods for managing city-wide video surveillance and IoT devices. Numerous video surveillance and IoT devices are distributed throughout the city, operating independently, making it difficult to visually display their locations on a unified map platform. This makes it difficult for managers to quickly understand the geographical distribution of devices, hindering comprehensive monitoring and management across the entire city.

[0003] On the other hand, the data collected by these devices cannot be deeply analyzed or efficiently utilized. When anomalies appear in the areas where video surveillance data and IoT devices are collecting data, it is impossible to accurately identify the abnormal areas and issue warnings in a timely manner, resulting in potential safety hazards or problems in urban management not being addressed in a timely manner.

[0004] Furthermore, in terms of conference communications for city government affairs, the data from conference rooms and terminals across the city's districts and counties, as well as government personnel, has not been effectively integrated. Organizing meetings between different districts and counties often requires cumbersome procedures, and converging meetings with a single click is impossible based on converged communications. This significantly impacts communication efficiency and collaborative effectiveness in government affairs.

[0005] Therefore, there is an urgent need for a city digital resource visualization management system based on a GIS platform to solve the above technical difficulties. Summary of the Invention

[0006] The present invention aims to at least partially address one of the technical problems encountered in the aforementioned technologies. To this end, a first aspect of the present invention is to propose a GIS-based urban digital resource visualization management system that visually displays the entire city's video surveillance and IoT device management on a unified map platform, enabling comprehensive monitoring and management, and enabling timely resolution of potential safety hazards or issues in urban management.

[0007] The second aspect of the present invention aims to propose a method for visual management of urban digital resources based on a GIS platform.

[0008] To achieve the above objectives, the first embodiment of the present invention proposes a city digital resource visualization management system based on a GIS platform, comprising:

[0009] The access module is used to access the city's video surveillance and IoT devices based on the GIS platform, and locate the city's video surveillance and IoT devices on the map;

[0010] Aggregation module, used to analyze video surveillance and IoT devices after landing on the map to create an aggregated effect;

[0011] An early warning module is used to obtain video surveillance data corresponding to video surveillance and IoT device collection data corresponding to IoT devices in real time, analyze the video surveillance data and IoT device collection data, and issue an early warning reminder to the area where the abnormal situation is located when an abnormal situation is determined;

[0012] The converged communication module is used to establish converged communication between conference terminal data and government personnel data in all districts and counties of the city, and to hold a meeting with one click based on the converged communication.

[0013] Preferably, the access module includes:

[0014] The first acquisition submodule is used to obtain the city's video surveillance information and IoT device information;

[0015] The conversion submodule is used to convert the city’s video surveillance information and IoT device information into GIS data;

[0016] Access submodule, used to input GIS data into the GIS platform;

[0017] The landing point submodule is used to divide the map area into four sub-areas based on geospatial indexing technology, recursively divide the area, and determine the landing point of video surveillance and IoT devices on the map according to the latitude and longitude coordinates in the GIS data.

[0018] Preferably, the aggregation module includes:

[0019] Aggregate evaluation submodule, used for:

[0020] Any one of the video surveillance and IoT devices after the landing point on the map is selected as the device to be aggregated;

[0021] Determine the aggregation range with the device to be aggregated as the center and the preset distance as the radius;

[0022] Obtain the number of video surveillance and IoT devices within the aggregation range as the aggregated evaluation value of the devices to be aggregated;

[0023] Traverse all the video surveillance and IoT devices behind the landing points on the map to obtain several aggregated evaluation values;

[0024] Aggregation submodule, used for:

[0025] Sort several aggregation evaluation values in descending order, and take the devices to be aggregated corresponding to the first K aggregation evaluation values as the target aggregation centers, and obtain K target aggregation centers;

[0026] Cluster the video surveillance and IoT devices behind the points on the map based on K target aggregation centers to obtain K target aggregation ranges;

[0027] Aggregate the K target aggregation ranges into K aggregation icons respectively;

[0028] Determine a submodule for taking K aggregation icons as the aggregation effect.

[0029] Preferably, the aggregation module further includes:

[0030] The adjustment submodule is used to adjust the aggregation effect according to the current zoom level by listening to the map layer zoom events of the map platform.

[0031] Preferably, the aggregation module further includes:

[0032] The custom query submodule is used to custom draw polygons and circles on the map, query the video surveillance and IoT devices within the polygons and circles, and view the attribute information of the video surveillance and IoT devices by clicking on the video surveillance and IoT devices within the polygons and circles.

[0033] Preferably, the early warning module includes:

[0034] The second acquisition submodule is used to obtain video surveillance data corresponding to the video surveillance and IoT device collection data corresponding to the IoT device in real time;

[0035] A preprocessing submodule, used to preprocess the video surveillance data and the data collected by the Internet of Things devices;

[0036] The early warning submodule is used to calculate the risk coefficient of risks occurring in the map area based on the preprocessed video surveillance data and the collected data of the Internet of Things devices, and to issue early warning reminders to the map area when the risk coefficient is greater than or equal to the preset risk threshold.

[0037] Preferably, the early warning submodule includes:

[0038] The first computing unit is configured to:

[0039] Randomly select one video surveillance data from the pre-processed video surveillance data as the target video surveillance data;

[0040] Extracting features from the target video surveillance data to obtain target features;

[0041] Calculating the similarity between the target feature and a preset risk feature database, and when it is determined that the similarity is greater than or equal to a preset similarity threshold, obtaining the target video surveillance data corresponding to the target video surveillance data;

[0042] The second computing unit is configured to:

[0043] Determine the target area with the target video surveillance as the center and the preset distance as the radius;

[0044] Acquire other video surveillance and Internet of Things devices in the target area except the target video surveillance, and obtain a plurality of first video surveillance and a plurality of first Internet of Things devices;

[0045] Acquire a plurality of first video surveillance data corresponding to the plurality of first video surveillances, and acquire a plurality of first Internet of Things device collection data corresponding to the plurality of first Internet of Things devices;

[0046] Evaluate the risk factor of the target area based on the plurality of first IoT device data and the plurality of first IoT device collected data;

[0047] Early warning unit, used to:

[0048] The risk coefficient is compared with a preset assessment threshold. When it is determined that the risk coefficient is greater than or equal to the preset risk threshold, the target area is regarded as a risk area and an early warning reminder is issued.

[0049] Preferably, the integrated communication module includes:

[0050] The acquisition submodule is used to obtain conference terminal data and government personnel data of all districts and counties in the city;

[0051] Feature extraction submodule, used to:

[0052] Extract features from conference terminal data across all districts and counties in the city to determine the static and dynamic features corresponding to the conference terminal data;

[0053] Extract features from government personnel data to determine the structural features and behavioral characteristics corresponding to the government personnel data;

[0054] Extracting the relationship between government officials and meeting rooms based on graph neural networks;

[0055] Mapping submodule for:

[0056] Generate static feature vectors based on static features and structured features;

[0057] Generate dynamic feature vectors based on dynamic features and behavioral features;

[0058] Generate composite node embedding based on the government staff-meeting room association relationship;

[0059] The fusion submodule is used to embed and splice the static feature vector, dynamic feature vector and composite node, and then reduce the dimension through the fully connected layer to obtain the target feature vector;

[0060] A construction submodule is used to construct a fusion communication database based on the target feature vector and to construct a fusion communication system based on the fusion communication database;

[0061] The conference convening submodule is used to convene a conference with one click based on the converged communication system.

[0062] Preferably, the preprocessing submodule includes:

[0063] An image enhancement unit, configured to perform image enhancement on the video surveillance data to obtain enhanced video surveillance data;

[0064] A data cleaning unit, used to clean the collected data of the IoT device to obtain the cleaned collected data of the IoT device;

[0065] a determination unit, configured to use the enhanced video surveillance data and the cleaned collected data of the Internet of Things device as the preprocessed video surveillance data and the collected data of the Internet of Things device;

[0066] The data cleaning unit includes:

[0067] Take any collected data from an IoT device as the target data;

[0068] Divide the target data evenly into several target sub-data;

[0069] Take any target sub-data;

[0070] Calculate the abnormality value corresponding to the target sub-data;

[0071] Comparing the abnormality level value with a preset abnormality level threshold;

[0072] When it is determined that the abnormality level value is greater than or equal to a preset abnormality level threshold, the target sub-data is used as the first abnormal data;

[0073] Traverse all target sub-data to obtain several first abnormal data;

[0074] Randomly select a first abnormal data, calculate the abnormal fluctuation value of each data point in the first abnormal data, and obtain a plurality of abnormal fluctuation values;

[0075] Comparing the abnormal fluctuation value with a preset abnormal fluctuation threshold, and taking a data point when the abnormal fluctuation value is greater than or equal to the preset abnormal fluctuation threshold as a first abnormal data point;

[0076] Traversing all first abnormal data to obtain an abnormal data set consisting of several first abnormal data points;

[0077] The similarity between the abnormal data set and other target sub-data in the target data except the first abnormal data is calculated, and the target sub-data with a similarity greater than or equal to a preset similarity threshold is taken as the second abnormal data to obtain a plurality of second abnormal data;

[0078] Deleting a plurality of first abnormal data and a plurality of second abnormal data to obtain target sub-data after data cleaning;

[0079] Traverse all target sub-data to obtain the target data after data cleaning;

[0080] Traverse all target data to obtain the cleaned collection data of IoT devices.

[0081] To achieve the above objectives, a second embodiment of the present invention proposes a method for visual management of urban digital resources based on a GIS platform, comprising:

[0082] Based on the GIS platform, the city's video surveillance and IoT devices are connected and located on the map.

[0083] Analyze video surveillance and IoT devices after they are placed on the map to create an aggregated effect;

[0084] Acquire video surveillance data corresponding to video surveillance and IoT device collection data corresponding to IoT devices in real time, analyze the video surveillance data and IoT device collection data, and issue early warning alerts to areas where abnormal situations are found when abnormal situations are identified;

[0085] Establish converged communications for conference terminal data and government personnel data across all districts and counties in the city, and hold meetings with one click based on converged communications.

[0086] The present invention discloses a city digital resource visualization management system and method based on a GIS platform. The system locates the city's video surveillance and Internet of Things devices on a GIS map, enabling intuitive understanding of the distribution of various types of devices in the city. This helps city managers fully grasp the layout of digital resources, facilitates overall planning and reasonable allocation of resources, and improves the efficiency of resource management; analyzes the devices after placement to create an aggregation effect, and can mine valuable information from massive amounts of device data; obtains and analyzes data from video surveillance and Internet of Things devices in real time, and can quickly detect abnormal situations and issue early warning alerts to the area where they are located; because abnormal areas can be accurately located, relevant departments can more specifically allocate resources for emergency response; establishes integrated communication between conference terminal data in district and county conference rooms and government personnel data, and enables one-click convening of meetings. This greatly improves the efficiency of government communication, reduces the time and labor costs of organizing meetings, and helps break down information barriers between departments, enabling government personnel to share information in a timely manner.

[0087] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0088] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0090] Figure 1 This is a block diagram of a city digital resource visualization management system based on a GIS platform according to one embodiment of the present invention;

[0091] Figure 2 is a block diagram of an access module according to one embodiment of the present invention;

[0092] Figure 3 is a block diagram of an aggregation module according to one embodiment of the present invention. DETAILED DESCRIPTION

[0093] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0094] Example 1

[0095] like Figure 1As shown in FIG, a city digital resource visualization management system based on a GIS platform includes:

[0096] The access module is used to access the city's video surveillance and IoT devices based on the GIS platform, and locate the city's video surveillance and IoT devices on the map;

[0097] Aggregation module, used to analyze video surveillance and IoT devices after landing on the map to create an aggregated effect;

[0098] An early warning module is used to obtain video surveillance data corresponding to video surveillance and IoT device collection data corresponding to IoT devices in real time, analyze the video surveillance data and IoT device collection data, and issue an early warning reminder to the area where the abnormal situation is located when an abnormal situation is determined;

[0099] The converged communication module is used to establish converged communication between conference terminal data and government personnel data in all districts and counties of the city, and to hold meetings with one click based on converged communication.

[0100] The beneficial effects of the above technical solution are as follows: By mapping the city's video surveillance and IoT devices on a GIS map, one can intuitively understand the distribution of various types of devices within the city. This helps city managers fully understand the layout of digital resources, facilitate overall planning and rational resource allocation, and improve resource management efficiency. By analyzing and creating aggregated effects for the devices after they are mapped, valuable information can be extracted from massive amounts of device data. By acquiring and analyzing data from video surveillance and IoT devices in real time, anomalies can be quickly detected and early warning alerts can be issued to the area. By accurately locating abnormal areas, relevant departments can more effectively allocate resources for emergency response. By establishing integrated communication between conference terminal data in district and county meeting rooms and government personnel data, meetings can be convened with a single click. This significantly improves the efficiency of government communication, reduces the time and labor costs of organizing meetings, and helps break down information barriers between departments, enabling government personnel to share information in a timely manner.

[0101] Example 2

[0102] like Figure 2 As shown, the access module includes:

[0103] The first acquisition submodule is used to obtain the city's video surveillance information and IoT device information;

[0104] The conversion submodule is used to convert the city’s video surveillance information and IoT device information into GIS data;

[0105] Access submodule, used to input GIS data into the GIS platform;

[0106] The landing point submodule is used to divide the map area into four sub-areas based on geospatial indexing technology, recursively divide the area, and determine the landing point of video surveillance and IoT devices on the map according to the latitude and longitude coordinates in the GIS data.

[0107] In this embodiment, video surveillance information includes the device name, unique identifier (such as a serial number), detailed address of the installation location (accurate to the street address), longitude and latitude coordinates (if available), region (such as district, county, street, etc.), and device type (such as dome camera, box camera, etc.). If some devices do not have longitude and latitude coordinates, they can be converted from the address information using a geocoding service.

[0108] In this embodiment, IoT device information includes a device ledger that records the device name, ID, installation location description, corresponding geographic coordinates (if available), industry (such as environmental monitoring, intelligent transportation, etc.), and function type (such as temperature and humidity sensor, air quality monitor, etc.). Similarly, for devices with only a location description, geocoding technology is used to obtain the coordinates.

[0109] In this embodiment, geospatial indexing technology, such as R-tree index or Quad-tree index (Quad-tree index, i.e., quadtree index, is used here), is used to divide the map area into four sub-areas. First, the boundary range of the map is determined, and the entire map area is used as the root node. Then, the root node is divided into four equal sub-areas, and each sub-area is used as a child node of the root node. For each child node, if the sub-area still contains a large number of video surveillance or Internet of Things devices (exceeding the set threshold), the sub-area is recursively divided into four smaller sub-areas again until the number of devices in each sub-area is within a reasonable range. The quadtree index constructed in this way can quickly locate the device in a certain area of the map, thereby improving the efficiency of the landing point search.

[0110] In this embodiment, based on the longitude and latitude coordinates of the video surveillance and IoT devices in the GIS data, the landing point submodule searches in the constructed quadtree index. Starting from the root node, determine in which sub-area the longitude and latitude coordinates of the device are located. For example, if the longitude value of the device is less than the center longitude value of the root node area, and the latitude value is less than the center latitude value, then the device is located in the lower left sub-area of the root node. Then, continue searching in the sub-nodes corresponding to the sub-area until the smallest sub-area containing the device is found. Once the sub-area where the device is located is determined, the landing point of the device can be accurately drawn on the map. At the same time, the relevant attribute information of the device is associated with the landing point for visual display and query in the map. For example, when a user clicks on the landing point of a device on the map, detailed information such as the name, type, and real-time status of the device can be displayed.

[0111] The beneficial effects of the above technical solution are: converting video surveillance information and IoT device information into GIS data solves the compatibility issues between different types of data and the GIS platform; inputting GIS data into the GIS platform ensures that the data can be accurately entered into the GIS system for subsequent processing. This helps to build an accurate basic data layer for the urban digital resource visualization management system, providing reliable data support for upper-level analysis, early warning and other functions; dividing map areas based on geospatial indexing technology, and through recursive division, can more meticulously process geospatial information. Determining the location of video surveillance and IoT devices based on the latitude and longitude coordinates in the GIS data can achieve high-precision positioning; accurate location determination helps to clearly and accurately display the layout of video surveillance and IoT devices on the GIS platform.

[0112] Example 3

[0113] like Figure 3 As shown, the aggregation module includes:

[0114] Aggregate evaluation submodule, used for:

[0115] Any one of the video surveillance and IoT devices after the landing point on the map is selected as the device to be aggregated;

[0116] Determine the aggregation range with the device to be aggregated as the center and the preset distance as the radius;

[0117] Obtain the number of video surveillance and IoT devices within the aggregation range as the aggregated evaluation value of the devices to be aggregated;

[0118] Traverse all the video surveillance and IoT devices behind the landing points on the map to obtain several aggregated evaluation values;

[0119] Aggregation submodule, used for:

[0120] Sort several aggregation evaluation values in descending order, and take the devices to be aggregated corresponding to the first K aggregation evaluation values as the target aggregation centers, and obtain K target aggregation centers;

[0121] Cluster the video surveillance and IoT devices behind the points on the map based on K target aggregation centers to obtain K target aggregation ranges;

[0122] Aggregate the K target aggregation ranges into K aggregation icons respectively;

[0123] Determine a submodule for taking K aggregation icons as the aggregation effect.

[0124] The beneficial effects of the above technical solution are as follows: by determining the aggregation range centered on each device and counting the number of devices within the range as the aggregation evaluation value, the degree of association between devices can be quantified; after traversing all the devices at the landing point, multiple aggregation evaluation values are obtained, which can comprehensively analyze the relationship between devices in the entire city. Whether it is a device in a densely populated area or a relatively remote area, it can be included in the analysis system, thus avoiding the one-sidedness that may be caused by local analysis, so that city managers have a more accurate grasp of the overall layout relationship of the equipment; sorting by the aggregation evaluation value and taking the top K as the target aggregation center can focus on key devices with a large number of related devices; aggregating multiple devices into K aggregation icons reduces the number of elements displayed on the map. In the case of a large city with a large number of devices, this simplification can avoid the map display being too complicated and improve the readability and visualization of the map; using K aggregation icons as the aggregation effect, this aggregation result helps to understand the distribution pattern of urban digital resources from a holistic perspective.

[0125] Example 4

[0126] The aggregation module also includes:

[0127] The adjustment submodule is used to adjust the aggregation effect according to the current zoom level by listening to the map layer zoom events of the map platform.

[0128] The working principle and beneficial effects of the above technical solution are as follows: Map-level zoom events are common operations performed by users when operating GIS maps, such as zooming in or out of a map in map software. This monitoring mechanism enables the module to perceive changes in the user's demand for map viewing range and level of detail in real time; when a map-level zoom event is detected, the adjustment submodule obtains the current map zoom level. The zoom level is usually a numerical value that represents the level of detail displayed on the map. For example, a smaller value may indicate a larger display range but fewer details (such as an overall overview of a city), while a larger value may indicate a smaller display range but more details (such as a detailed view of a block). At different zoom levels, the display requirements for devices on the map are different. When at a larger zoom level (large display range, few details), displaying a single device in too much detail may make the map appear cluttered and is not conducive to grasping the overall distribution of devices from a macro perspective. At this time, it is necessary to highlight the aggregation effect and aggregate more devices into icons to show the overall layout. At a smaller zoom level (small display range, more details), users may be more concerned about the specific conditions of devices in a specific area, and need to appropriately adjust the aggregation effect to display more individual devices or smaller-scale aggregations; based on the current zoom level obtained, the adjustment submodule will adjust the previously obtained aggregation effect (K aggregation icons). If it is a zoom-in operation (increasing the zoom level), some originally aggregated devices may be re-decomposed into individual devices or smaller aggregations to display more details; if it is a zoom-out operation (decreasing the zoom level), devices may be further merged to expand the aggregation range, making the elements displayed on the map more concise and better reflecting the overall layout characteristics. This adjustment is dynamic, and the aggregation effect changes in real time as the user continues to zoom in and out of the map to adapt to different viewing needs.

[0129] Example 5

[0130] The aggregation module also includes:

[0131] The custom query submodule is used to custom draw polygons and circles on the map, query the video surveillance and IoT devices within the polygons and circles, and view the attribute information of the video surveillance and IoT devices by clicking on the video surveillance and IoT devices within the polygons and circles.

[0132] The beneficial effects of the above technical solution are: by directly clicking on the device within the custom query range, its attribute information can be viewed, which greatly improves the convenience of obtaining detailed information about the device; by combining the custom query area and device attribute viewing function, users can more accurately locate and analyze devices in a specific area.

[0133] Example 6

[0134] Early warning module, including:

[0135] The second acquisition submodule is used to obtain video surveillance data corresponding to the video surveillance and IoT device collection data corresponding to the IoT device in real time;

[0136] A preprocessing submodule, for preprocessing the video surveillance data and the data collected by the IoT device;

[0137] The early warning submodule is used to calculate the risk coefficient of risks occurring in the map area based on the preprocessed video surveillance data and the collected data of the Internet of Things devices, and to issue early warning reminders to the map area when the risk coefficient is greater than or equal to the preset risk threshold.

[0138] The beneficial effects of the above technical solution are: real-time acquisition of video surveillance data and data collected by IoT devices, covering two important data sources. Video surveillance data can intuitively reflect the visual information in the map area, such as personnel activities, vehicle flow, etc.; IoT device collected data can include various environmental parameters (such as temperature, humidity, air quality, etc.) or equipment status information, etc. The risk coefficient of the map area is calculated based on the pre-processed multi-source data. This calculation method that integrates multi-source data can more comprehensively and accurately reflect the actual risk status in the area; when the risk coefficient is greater than or equal to the preset risk threshold, the corresponding map area will be warned. This helps relevant personnel (such as security personnel, management personnel, etc.) to take timely measures to deal with possible risk situations.

[0139] Example 7

[0140] Early warning submodule, including:

[0141] The first computing unit is configured to:

[0142] Randomly select one video surveillance data from the pre-processed video surveillance data as the target video surveillance data;

[0143] Extracting features from the target video surveillance data to obtain target features;

[0144] Calculating the similarity between the target feature and a preset risk feature database, and when it is determined that the similarity is greater than or equal to a preset similarity threshold, obtaining the target video surveillance data corresponding to the target video surveillance data;

[0145] The second computing unit is configured to:

[0146] Determine the target area with the target video surveillance as the center and the preset distance as the radius;

[0147] Acquire other video surveillance and Internet of Things devices in the target area except the target video surveillance, and obtain a plurality of first video surveillance and a plurality of first Internet of Things devices;

[0148] Acquire a plurality of first video surveillance data corresponding to the plurality of first video surveillances, and acquire a plurality of first Internet of Things device collection data corresponding to the plurality of first Internet of Things devices;

[0149] Evaluate the risk factor of the target area based on the plurality of first IoT device data and the plurality of first IoT device collected data;

[0150] Early warning unit, used to:

[0151] The risk coefficient is compared with a preset assessment threshold. When it is determined that the risk coefficient is greater than or equal to the preset risk threshold, the target area is regarded as a risk area and an early warning reminder is issued.

[0152] In this embodiment,

[0153]

[0154] Where γ represents the risk coefficient of the target area; T 1,a T represents the characteristics of the video surveillance data of the a-th first video surveillance in the target area; 1,x The feature of the video surveillance data of the xth first video surveillance in the target area; d 1,a,x Y represents the distance between the ath first video surveillance in the target area and the xth first video surveillance in the target area; 2,b Y represents the characteristics of the collected data of the bth first IoT device in the target area; 2,y Represents the characteristics of the collected data of the yth first IoT device in the target area; d 2,b,y represents the distance between the bth first IoT device and the yth first IoT device in the target area; S 1i represents the similarity between the data of the i-th first video surveillance in the target area and the preset risk feature database; m represents the number of first video surveillance in the target area; S 2j It represents the similarity between the collected data of the jth first IoT device in the target area and the preset risk feature database; n represents the number of first IoT devices in the target area; norm() represents the normalization function; exp() represents the exponential function with a natural constant as the base.

[0155] The beneficial effects of the above technical solution are: by arbitrarily selecting one of the pre-processed video surveillance data as the target video surveillance data, and then performing feature extraction and similarity calculation with the preset risk feature database. This method can accurately screen out target video surveillance that may be risky; with the target video surveillance as the center and the preset distance as the radius, the target area is determined. This method of determining the target area takes into account the scope of association with the potential risk source (target video surveillance); obtains data from other video surveillance and IoT devices in the target area, and evaluates the risk factor of the target area based on these multi-source data; the comprehensive video surveillance data and IoT device collection data can more comprehensively reflect the actual situation of the target area; the assessed risk factor is compared with the preset assessment threshold, and when the risk factor is greater than or equal to the preset risk threshold, the target area is treated as a risk area and an early warning reminder is issued.

[0156] Example 8

[0157] Converged communication module, including:

[0158] The acquisition submodule is used to obtain conference terminal data and government personnel data of all districts and counties in the city;

[0159] Feature extraction submodule, used to:

[0160] Extract features from conference terminal data across all districts and counties in the city to determine the static and dynamic features corresponding to the conference terminal data;

[0161] Extract features from government personnel data to determine the structural features and behavioral characteristics corresponding to the government personnel data;

[0162] Extracting the relationship between government officials and meeting rooms based on graph neural networks;

[0163] Mapping submodule for:

[0164] Generate static feature vectors based on static features and structured features;

[0165] Generate dynamic feature vectors based on dynamic features and behavioral features;

[0166] Generate composite node embedding based on the government staff-meeting room association relationship;

[0167] The fusion submodule is used to embed and splice the static feature vector, dynamic feature vector and composite node, and then reduce the dimension through the fully connected layer to obtain the target feature vector;

[0168] A construction submodule is used to construct a fusion communication database based on the target feature vector and to construct a fusion communication system based on the fusion communication database;

[0169] The conference convening submodule is used to convene a conference with one click based on the converged communication system.

[0170] In this embodiment, the static features include inherent attributes of the device, such as the terminal model, brand, processor performance, memory size, etc.; the location information of the conference room, such as floor, room number, longitude and latitude (if any), etc.

[0171] Dynamic features include the device usage status, such as online time, usage rate, failure frequency, etc.; meeting-related information, such as meeting duration, number of participants, and meeting type (video conference, telephone conference, etc.).

[0172] Structured features include basic personnel information, such as name, gender, age, department, position, etc.; and personnel authority information, such as whether they have the right to initiate and approve meetings.

[0173] Behavioral characteristics include meeting participation behavior, such as the frequency of attending meetings, the time period of attending meetings, the duration of attending meetings, etc.; communication behavior, such as the frequency of communication with other people and the communication method (email, phone, instant messaging, etc.).

[0174] In this embodiment, the relationship between government officials and conference rooms is extracted based on a graph neural network to construct a graph structure: government officials and conference rooms are used as nodes of the graph, and the relationship between them (such as government officials attending meetings in a certain conference room) is used as the edge of the graph. The attributes of the edge may include information such as the time of the meeting and the subject of the meeting. Graph neural network training: The constructed graph structure is trained using a graph neural network model (such as Graph Convolutional Network, GCN). During the training process, the model will learn the relationship and feature representation between nodes. By continuously iteratively optimizing the parameters of the model, the model can accurately capture the complex relationship between government officials and conference rooms.

[0175] In this embodiment, static feature vector generation: the static features of the extracted conference room terminal data and the structured features of the government personnel data are quantified. For categorical features, such as the model of the terminal, the department to which the personnel belong, etc., they are converted into binary vectors using One-Hot Encoding. For numerical features, such as the processor performance of the terminal, the age of the personnel, etc., they are normalized and mapped to the interval of [0,1]. The processed static feature vector of the conference room and the structured feature vector of the government personnel are spliced to generate a static feature vector. The static feature vector can comprehensively reflect the inherent attribute information of the conference room and the government personnel.

[0176] Dynamic feature vector generation: The extracted dynamic features of conference room terminal data and the behavioral features of government personnel data are processed. For time series features, such as device online time and personnel meeting attendance frequency, a sliding window approach can be used to extract feature trends. Categorical features, such as meeting type and communication method, are similarly processed using one-hot encoding. The processed conference room dynamic feature vector and government personnel behavioral feature vector are concatenated to generate a dynamic feature vector. The dynamic feature vector reflects the real-time status and behavioral patterns of the conference room and government personnel.

[0177] Composite Node Embedding Generation: Based on the staff-meeting room relationships obtained through graph neural network training, a node embedding algorithm (such as Node2Vec) is used to map the nodes in the graph (staff and meeting rooms) into a low-dimensional vector space. The vector corresponding to each node is the composite node embedding, which contains the node's association information and feature representation in the graph structure. Composite node embeddings can capture the complex relationship between staff and meeting rooms, providing richer information for subsequent fusion.

[0178] In this embodiment, the converged communication database is constructed by selecting an appropriate database management system (such as MySQL or MongoDB) and designing a database table structure based on the structure and meaning of the target feature vector. The target feature vector is stored in the database, and corresponding indexes are established to facilitate fast query and retrieval of data. Metadata information, such as the source of the data, acquisition time, and the meaning of the features, is added to the database to facilitate subsequent data management and maintenance.

[0179] In this embodiment, the converged communication system is constructed by developing the core functional modules of the converged communication platform based on the converged communication database. These modules include a conference scheduling module that automatically arranges appropriate conference rooms and meeting times based on the needs of government officials and conference room usage; a communication protocol adaptation module that supports multiple communication protocols (such as SIP and H.323) to achieve interconnection between different conference terminals; a user management module that manages the permissions and information of government officials; and the integration of the converged communication platform with existing government systems (such as office automation systems and video conferencing systems). Through interface calls and data interaction, information sharing and business collaboration are achieved.

[0180] The working principle and beneficial effects of the above technical solution are as follows: static and dynamic features are extracted from conference room terminal data, and structured and behavioral features are extracted from government personnel data. This multi-dimensional feature extraction method can comprehensively mine information from both types of data. Static and structured features reflect basic attributes, such as conference room equipment configuration and government personnel positions; dynamic and behavioral features capture information that changes over time, such as conference room usage frequency and government personnel work dynamics, helping to gain a deeper understanding of the data's nature. The graph neural network is used to extract government personnel-conference room associations, which can deeply explore the complex relationships between the two. Graph neural networks are well-suited to handling relational data between entities. By learning the association patterns between government personnel and conference rooms in different scenarios, such as which government personnel frequently use which conference rooms and the matching relationship between government personnel and conference rooms in specific meeting scenarios, they provide more valuable relationship information for subsequent converged communications. Static feature vectors, dynamic feature vectors, and composite node embeddings are generated based on different types of features. The fusion submodule concatenates these vectors and then reduces the dimensionality through a fully connected layer to obtain the target feature vector. This feature fusion approach organically combines multi-source features, preserving the important information of the original features while reducing data redundancy through dimensionality reduction. This allows the target feature vector to comprehensively reflect key information about conference room terminals and government personnel, providing a high-quality data foundation for building a converged communications database. This target feature vector is then used to construct a converged communications database, and based on this, a converged communications system is built. This approach, based on deep data mining and effective fusion, can create a system that more efficiently and accurately reflects government communications needs.

[0181] Example 9

[0182] Preprocessing submodule, including:

[0183] An image enhancement unit, configured to perform image enhancement on the video surveillance data to obtain enhanced video surveillance data;

[0184] A data cleaning unit, used to clean the collected data of the IoT device to obtain the cleaned collected data of the IoT device;

[0185] a determination unit, configured to use the enhanced video surveillance data and the cleaned collected data of the Internet of Things device as the preprocessed video surveillance data and the collected data of the Internet of Things device;

[0186] The data cleaning unit includes:

[0187] Take any collected data from an IoT device as the target data;

[0188] Divide the target data evenly into several target sub-data;

[0189] Take any target sub-data;

[0190] Calculate the abnormality value corresponding to the target sub-data;

[0191] Comparing the abnormality level value with a preset abnormality level threshold;

[0192] When it is determined that the abnormality level value is greater than or equal to a preset abnormality level threshold, the target sub-data is used as the first abnormal data;

[0193] Traverse all target sub-data to obtain several first abnormal data;

[0194] Randomly select a first abnormal data, calculate the abnormal fluctuation value of each data point in the first abnormal data, and obtain a plurality of abnormal fluctuation values;

[0195] Comparing the abnormal fluctuation value with a preset abnormal fluctuation threshold, and taking a data point when the abnormal fluctuation value is greater than or equal to the preset abnormal fluctuation threshold as a first abnormal data point;

[0196] Traversing all first abnormal data to obtain an abnormal data set consisting of several first abnormal data points;

[0197] The similarity between the abnormal data set and other target sub-data in the target data except the first abnormal data is calculated, and the target sub-data with a similarity greater than or equal to a preset similarity threshold is taken as the second abnormal data to obtain a plurality of second abnormal data;

[0198] Deleting a plurality of first abnormal data and a plurality of second abnormal data to obtain target sub-data after data cleaning;

[0199] Traverse all target sub-data to obtain the target data after data cleaning;

[0200] Traverse all target data to obtain the cleaned collection data of IoT devices.

[0201] The above technical solution has the beneficial effect of removing a number of first and second abnormal data to obtain cleaned target sub-data, ultimately obtaining cleaned IoT device collected data. This rigorously cleaned data removes interference factors such as noise, erroneous data, and abnormal fluctuations, ensuring the validity and reliability of IoT device collected data.

[0202] Example 10

[0203] Based on the GIS platform, the city's video surveillance and IoT devices are connected and located on the map.

[0204] Analyze video surveillance and IoT devices after they are placed on the map to create an aggregated effect;

[0205] Acquire video surveillance data corresponding to video surveillance and IoT device collection data corresponding to IoT devices in real time, analyze the video surveillance data and IoT device collection data, and issue early warning alerts to areas where abnormal situations are found when abnormal situations are identified;

[0206] Establish converged communications for conference terminal data and government personnel data across all districts and counties in the city, and hold meetings with one click based on converged communications.

[0207] The beneficial effects of the above technical solution are as follows: By mapping the city's video surveillance and IoT devices on a GIS map, one can intuitively understand the distribution of various types of devices within the city. This helps city managers fully understand the layout of digital resources, facilitate overall planning and rational resource allocation, and improve resource management efficiency. By analyzing and creating aggregated effects for the devices after they are mapped, valuable information can be extracted from massive amounts of device data. By acquiring and analyzing data from video surveillance and IoT devices in real time, anomalies can be quickly detected and early warning alerts can be issued to the area. By accurately locating abnormal areas, relevant departments can more effectively allocate resources for emergency response. By establishing integrated communication between conference terminal data in district and county meeting rooms and government personnel data, meetings can be convened with a single click. This significantly improves the efficiency of government communication, reduces the time and labor costs of organizing meetings, and helps break down information barriers between departments, enabling government personnel to share information in a timely manner.

[0208] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A city digital resource visualization management system based on GIS platform, characterized by: include: The access module is used to access the city's video surveillance and IoT devices based on the GIS platform, and locate the city's video surveillance and IoT devices on the map; Aggregation module, used to analyze video surveillance and IoT devices after landing on the map to create an aggregated effect; An early warning module is used to obtain video surveillance data corresponding to video surveillance and IoT device collection data corresponding to IoT devices in real time, analyze the video surveillance data and IoT device collection data, and issue an early warning reminder to the area where the abnormal situation is located when an abnormal situation is determined; The converged communication module is used to establish converged communication between conference terminal data and government personnel data in all districts and counties of the city, and to hold meetings with one click based on converged communication.

2. The urban digital resource visualization management system based on the GIS platform according to claim 1, characterized in that: Access module, including: The first acquisition submodule is used to obtain the city's video surveillance information and IoT device information; The conversion submodule is used to convert the city’s video surveillance information and IoT device information into GIS data; Access submodule, used to input GIS data into the GIS platform; The landing point submodule is used to divide the map area into four sub-areas based on geospatial indexing technology, recursively divide the area, and determine the landing point of video surveillance and IoT devices on the map according to the latitude and longitude coordinates in the GIS data.

3. The urban digital resource visualization management system based on the GIS platform according to claim 1, characterized in that: Aggregation modules, including: Aggregate evaluation submodule, used for: Any one of the video surveillance and IoT devices located at the point on the map is selected as the device to be aggregated; Determine the aggregation range with the device to be aggregated as the center and the preset distance as the radius; Obtain the number of video surveillance and IoT devices within the aggregation range as the aggregation evaluation value of the devices to be aggregated; Traverse all the video surveillance and IoT devices behind the landing points on the map to obtain several aggregated evaluation values; Aggregation submodule, used for: Sort several aggregation evaluation values in descending order, and take the devices to be aggregated corresponding to the first K aggregation evaluation values as the target aggregation centers, and obtain K target aggregation centers; Cluster the video surveillance and IoT devices behind the points on the map based on K target aggregation centers to obtain K target aggregation ranges; Aggregate the K target aggregation ranges into K aggregation icons respectively; Determine a submodule for taking K aggregation icons as the aggregation effect.

4. The urban digital resource visualization management system based on the GIS platform as claimed in claim 3, characterized in that: The aggregation module also includes: The adjustment submodule is used to adjust the aggregation effect according to the current zoom level by listening to the map layer zoom events of the map platform.

5. The urban digital resource visualization management system based on the GIS platform as claimed in claim 3, characterized in that: The aggregation module also includes: The custom query submodule is used to custom draw polygons and circles on the map, query the video surveillance and IoT devices within the polygons and circles, and view the attribute information of the video surveillance and IoT devices by clicking on the video surveillance and IoT devices within the polygons and circles.

6. The urban digital resource visualization management system based on the GIS platform according to claim 1, characterized in that: Early warning module, including: The second acquisition submodule is used to obtain video surveillance data corresponding to the video surveillance and IoT device collection data corresponding to the IoT device in real time; A preprocessing submodule, used to preprocess the video surveillance data and the data collected by the Internet of Things devices; The early warning submodule is used to calculate the risk coefficient of risks occurring in the map area based on the preprocessed video surveillance data and the collected data of the Internet of Things devices, and to issue early warning reminders to the map area when the risk coefficient is greater than or equal to the preset risk threshold.

7. The urban digital resource visualization management system based on the GIS platform according to claim 6, characterized in that: Early warning submodule, including: The first computing unit is configured to: Randomly select one video surveillance data from the pre-processed video surveillance data as the target video surveillance data; Extracting features from the target video surveillance data to obtain target features; Calculating the similarity between the target feature and a preset risk feature database, and when it is determined that the similarity is greater than or equal to a preset similarity threshold, obtaining the target video surveillance data corresponding to the target video surveillance data; The second computing unit is configured to: Determine the target area with the target video surveillance as the center and the preset distance as the radius; Acquire other video surveillance and Internet of Things devices in the target area except the target video surveillance, and obtain a plurality of first video surveillance and a plurality of first Internet of Things devices; Acquire a plurality of first video surveillance data corresponding to the plurality of first video surveillances, and acquire a plurality of first Internet of Things device collection data corresponding to the plurality of first Internet of Things devices; Evaluate the risk factor of the target area based on the plurality of first IoT device data and the plurality of first IoT device collected data; Early warning unit, used to: The risk coefficient is compared with a preset assessment threshold. When it is determined that the risk coefficient is greater than or equal to the preset risk threshold, the target area is regarded as a risk area and an early warning reminder is issued.

8. The urban digital resource visualization management system based on the GIS platform according to claim 1, characterized in that: Converged communication module, including: The acquisition submodule is used to obtain conference terminal data and government personnel data of all districts and counties in the city; Feature extraction submodule, used to: Extract features from conference terminal data across all districts and counties in the city to determine the static and dynamic features corresponding to the conference terminal data; Extract features from government personnel data to determine the structural features and behavioral characteristics corresponding to the government personnel data; Extracting the relationship between government officials and meeting rooms based on graph neural networks; Mapping submodule for: Generate static feature vectors based on static features and structured features; Generate dynamic feature vectors based on dynamic features and behavioral features; Generate composite node embedding based on the government staff-meeting room association relationship; The fusion submodule is used to embed and splice the static feature vector, dynamic feature vector and composite node, and then reduce the dimension through the fully connected layer to obtain the target feature vector; A construction submodule is used to construct a fusion communication database based on the target feature vector and to construct a fusion communication system based on the fusion communication database; The conference convening submodule is used to convene a conference with one click based on the converged communication system.

9. The urban digital resource visualization management system based on the GIS platform according to claim 6, characterized in that: Preprocessing submodule, including: An image enhancement unit, configured to perform image enhancement on the video surveillance data to obtain enhanced video surveillance data; A data cleaning unit, used to clean the collected data of the IoT device to obtain the cleaned collected data of the IoT device; a determination unit, configured to use the enhanced video surveillance data and the cleaned collected data of the Internet of Things device as the preprocessed video surveillance data and the collected data of the Internet of Things device; The data cleaning unit includes: Take any collected data from an IoT device as the target data; Divide the target data evenly into several target sub-data; Take any target sub-data; Calculate the abnormality value corresponding to the target sub-data; Comparing the abnormality level value with a preset abnormality level threshold; When it is determined that the abnormality level value is greater than or equal to a preset abnormality level threshold, the target sub-data is used as the first abnormal data; Traverse all target sub-data to obtain several first abnormal data; Randomly select a first abnormal data, calculate the abnormal fluctuation value of each data point in the first abnormal data, and obtain a plurality of abnormal fluctuation values; Comparing the abnormal fluctuation value with a preset abnormal fluctuation threshold, and taking a data point when the abnormal fluctuation value is greater than or equal to the preset abnormal fluctuation threshold as a first abnormal data point; Traversing all first abnormal data to obtain an abnormal data set consisting of several first abnormal data points; The similarity between the abnormal data set and other target sub-data in the target data except the first abnormal data is calculated, and the target sub-data with a similarity greater than or equal to a preset similarity threshold is taken as the second abnormal data to obtain a plurality of second abnormal data; Deleting a plurality of first abnormal data and a plurality of second abnormal data to obtain target sub-data after data cleaning; Traverse all target sub-data to obtain the target data after data cleaning; Traverse all target data to obtain the cleaned collection data of IoT devices.

10. The management method of the urban digital resource visualization management system based on the GIS platform according to any one of claims 1 to 9, characterized in that: include: Based on the GIS platform, the city's video surveillance and IoT devices are connected and located on the map. Analyze video surveillance and IoT devices after they are placed on the map to create an aggregated effect; Acquire video surveillance data corresponding to video surveillance and IoT device collection data corresponding to IoT devices in real time, analyze the video surveillance data and IoT device collection data, and issue early warning alerts to areas where abnormal situations are found when abnormal situations are identified; Establish converged communications for conference terminal data and government personnel data across all districts and counties in the city, and hold meetings with one click based on converged communications.

Images