CN120911907A - Digital twin-driven multi-source information intelligent decision system and method - Google Patents

Abstract

This invention relates to the field of community governance data processing technology, specifically to a digital twin-driven multi-source information intelligent decision-making system and method. The method includes: collecting operational data of the community, buildings, and facilities; generating a three-dimensional virtual model of the community; establishing a data correspondence between the virtual model and the entities; and performing data association. It also includes: acquiring environmental status data in real time, fusing the environmental status data, and analyzing potential problems in community governance; generating decision-making schemes based on the data analysis results; converting the decision-making schemes into execution instructions; and sending them to the corresponding execution entities. The system includes: a community virtual modeling module, a data fusion and analysis module, and a decision execution module. Through the above methods, real-time virtual mapping of community space is achieved, real-time simulation and prediction of community dynamics are realized, and decision support capabilities are improved.

Description

Digital twin-driven multi-source information intelligent decision system and method

Technical Field

The invention relates to the technical field of community management data processing, in particular to a digital twin-driven multi-source information intelligent decision system and method.

Background

Along with the acceleration of the urban process, communities are taken as basic units for urban management, and the management difficulty is continuously increased. Traditional community governance modes are difficult to meet increasingly complex community demands, and improvement of governance capacity by means of emerging technologies is urgently needed. The digital twin technology realizes real-time monitoring, analysis and optimization of physical entities by constructing virtual mapping of the physical entities, and has been widely applied in the fields of urban planning, intelligent manufacturing and the like. The artificial intelligence technology has the capabilities of autonomous perception, decision making and action, can autonomously complete specific tasks in a virtual space environment, and provides possibility for the intellectualization of community management.

At present, part of communities are beginning to introduce informatization technologies for treatment, such as building community information systems, installing monitoring equipment and the like. However, most of the systems are operated independently, data are difficult to communicate, population information, property information, security information and the like of communities are integrated in the existing digital scheme, digital management of basic conditions of communities can be achieved, real-time virtual mapping of community space is lacking, real-time simulation and prediction of community dynamics cannot be achieved, manual analysis and judgment are relied on, and decision support capability is weak.

Disclosure of Invention

The invention aims to provide a digital twin-driven multi-source information intelligent decision system and a digital twin-driven multi-source information intelligent decision method, and aims to solve the technical problems that real-time virtual mapping of community space is lacking in the prior art, real-time simulation and prediction of community dynamics cannot be realized, manual analysis and judgment are relied on, and decision support capability is weak.

In order to achieve the above purpose, the invention adopts a digital twin-driven multi-source information intelligent decision method, which comprises the following steps:

Collecting community, building and facility operation data, generating a community three-dimensional virtual model, establishing a data corresponding relation between the virtual model and an entity, and carrying out data association;

Acquiring environmental state data in real time, fusing the environmental state data, and analyzing potential problems of community management;

and generating a decision scheme according to the data analysis result, converting the decision scheme into an execution instruction, and sending the execution instruction to a corresponding execution main body.

The method comprises the steps of collecting community, building and facility operation data, generating a community three-dimensional virtual model, establishing a data corresponding relation between the virtual model and an entity, and carrying out data association:

respectively collecting geometric data of community, building and facility operation, and integrating and preprocessing the geometric data;

reducing and refining the building model according to the geometric data, and adding elements to generate a community three-dimensional virtual model;

Each element in the three-dimensional virtual model of the community is assigned a unique identifier that corresponds to the actual entity.

Wherein, after the step of assigning a unique identifier to each element in the three-dimensional virtual model of the community, the identifier corresponds to the actual entity:

and correlating the collected community, building and facility operation data with corresponding elements in the virtual model, and establishing a data table to store correlation information.

The method comprises the steps of acquiring environmental state data in real time, fusing the environmental state data and analyzing potential problems of community management:

Deploying an environment sensor, collecting environment state data in real time, and outputting multi-source heterogeneous data;

after preprocessing the multi-source heterogeneous data, fusing the measurement data of the plurality of sensors about the same environmental parameter in a data fusion mode;

Constructing association rules, analyzing association relations among different environment parameters, and outputting frequently-occurring parameter combinations and association rules thereof;

and respectively carrying out time sequence analysis and spatial distribution analysis on the multi-source heterogeneous data, and outputting analysis results.

After the step of constructing association rules, analyzing association relations among different environment parameters and outputting frequently-occurring parameter combinations and association rules thereof:

and taking each environmental parameter as a node, taking the association relation among the parameters as an edge, and drawing an association map.

Wherein, in the steps of respectively carrying out time sequence analysis and space distribution analysis on the multi-source heterogeneous data and outputting analysis results:

and respectively carrying out trend, periodicity and seasonal analysis on the historical multi-source heterogeneous data, and establishing a prediction model to predict the data based on the trend, periodicity and seasonal characteristics of the historical data.

Wherein, in the steps of respectively carrying out time sequence analysis and space distribution analysis on the multi-source heterogeneous data and outputting analysis results:

And combining the geographic information and the multi-source heterogeneous data to perform spatial mode identification and problem diagnosis.

Wherein, in the step of generating a decision scheme according to the data analysis result, converting the decision scheme into an execution instruction and sending the execution instruction to a corresponding execution subject:

And generating a decision scheme according to the data analysis result, and converting each measure in the scheme into an execution instruction, wherein the execution instruction comprises operation content, an execution object, execution time and an execution standard.

After the decision scheme is generated according to the data analysis result and each measure in the scheme is converted into an execution instruction:

And transmitting the generated execution instruction to a corresponding execution subject by adopting a communication channel.

The invention also provides a digital twin-driven multi-source information intelligent decision system, which comprises a community virtual modeling module, a data fusion analysis module and a decision execution module, wherein:

the community virtual modeling module is used for collecting community, building and facility operation data, generating a community three-dimensional virtual model, establishing a data corresponding relation between the virtual model and an entity, and carrying out data association;

The data fusion analysis module is used for acquiring environmental state data in real time, fusing the environmental state data and analyzing potential problems of community management;

The decision execution module is used for generating a decision scheme according to the data analysis result, converting the decision scheme into an execution instruction and sending the execution instruction to a corresponding execution main body.

The digital twin-driven multi-source information intelligent decision system and method adopt the community virtual modeling module, the data fusion analysis module and the decision execution module to perform the following steps of collecting community, building and facility operation data, generating a community three-dimensional virtual model, establishing a data corresponding relation between the virtual model and an entity, performing data association, acquiring environment state data in real time, fusing the environment state data, analyzing potential problems of community treatment, generating a decision scheme according to a data analysis result, converting the decision scheme into an execution instruction, and sending the execution instruction to a corresponding execution subject, and realizing real-time virtual mapping of a community space, simulating and predicting community dynamics in real time, and improving decision support capability.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of steps of a digital twin driven multi-source information intelligent decision method of the present invention.

Fig. 2 is a flow chart of the steps of S100 of the present invention.

Fig. 3 is a flowchart of the steps of S200 of the present invention.

Fig. 4 is a flowchart of the steps of S300 of the present invention.

Fig. 5 is a schematic structural diagram of the digital twin-driven multi-source information intelligent decision system of the present invention.

Fig. 6 is a schematic structural diagram of the electronic device of the present invention.

A 401-community virtual modeling module, a 402-data fusion analysis module and a 403-decision execution module.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the application. The term "if" as used herein may be interpreted as "at..once" or "when..once" or "in response to a determination", depending on the context.

Referring to fig. 1 to 4, the invention provides a digital twin-driven multi-source information intelligent decision method, which comprises the following steps:

And S100, collecting community, building and facility operation data, generating a community three-dimensional virtual model, establishing a data corresponding relation between the virtual model and an entity, and carrying out data association.

In the embodiment, community, building and facility operation data are collected, a three-dimensional community virtual model is generated, and a data corresponding relation between the virtual model and an entity is established to perform data association. The specific process is as follows:

s101, respectively collecting geometric data of community, building and facility operation, and integrating and preprocessing the geometric data;

S102, reducing and refining a building model according to geometric data, and adding elements to generate a community three-dimensional virtual model;

S103, distributing a unique identifier for each element in the three-dimensional virtual model of the community, wherein the identifier corresponds to an actual entity;

and S104, associating the collected community, building and facility operation data with corresponding elements in the virtual model, and establishing a data table to store association information.

In the process, geometric data of community, building and facility operation are respectively acquired, wherein the community data acquisition is to comprehensively acquire information such as boundaries, road layout and public area positions of communities by using professional community geographic information acquisition equipment such as a high-precision satellite positioning instrument, an unmanned aerial vehicle and the like. Meanwhile, the community management department obtains the demographic data of the community, including basic information such as the number of residents, age distribution, occupation constitution and the like.

And acquiring building data, namely precisely scanning the appearance of the building by adopting a three-dimensional laser scanner aiming at various buildings in communities to acquire the data such as the outline, the elevation detail and the like of the building. For the internal structure of the building, the handheld three-dimensional scanning equipment is used for collecting information such as the layout of a room, the positions of doors and windows, the height of a floor and the like in detail. In addition, document data such as planning design drawings, construction records and the like of the building are collected so as to supplement and perfect the building data.

And the facility operation data acquisition is to install sensors on various facilities in the community, such as a water meter sensor for acquiring water and electricity usage data, an elevator sensor for monitoring the operation state, fault information and the like of an elevator, and a fire-fighting facility sensor for feeding back key parameters such as pressure, electric quantity and the like of fire-fighting equipment in real time. The sensors are connected with the data acquisition terminal through the internet of things technology, so that automatic acquisition and transmission of facility operation data are realized.

The acquired geometric data of communities, buildings and facilities are integrated and processed by using three-dimensional modeling software such as 3D MAX, sketchup and the like. Building three-dimensional model of building according to building appearance scanning data, accurately restoring appearance and elevation features of building, and refining room layout and internal facility position in the three-dimensional model according to internal structure scanning data. For the community environment, a terrain model is created according to geographic information acquisition data, elements such as roads and greening are added, and finally a complete three-dimensional community virtual model is generated.

Each element (building, facility, etc.) in the three-dimensional virtual model of the community is assigned a unique identifier that corresponds one-to-one to the actual entity. For example, a specific building number is generated for each building, and that number is used for identification in the management system of both the virtual model and the actual building.

And associating the collected various data (community basic data, building data and facility operation data) with corresponding elements in the virtual model. Through the database management system, a data table is established to store the associated information, so that when a certain building or facility is clicked in the virtual model, all data related to the building or facility can be quickly queried, and data intercommunication and dynamic association between the virtual model and the entity are realized.

And S200, acquiring environmental state data in real time, fusing the environmental state data, and analyzing potential problems of community management.

In this embodiment, environmental status data is acquired in real time, the environmental status data is fused, and potential problems of community management are analyzed. The specific process is as follows:

s201, deploying an environment sensor, collecting environment state data in real time, and outputting multi-source heterogeneous data;

s202, after preprocessing multi-source heterogeneous data, fusing measurement data of a plurality of sensors about the same environmental parameter in a data fusion mode;

S203, constructing association rules, analyzing association relations among different environment parameters, and outputting frequently-occurring parameter combinations and association rules thereof;

S204, taking each environmental parameter as a node, taking the association relation among the parameters as an edge, and drawing an association map;

s205, respectively carrying out trend, periodicity and seasonal analysis on the historical multi-source heterogeneous data, and establishing a prediction model to predict the data based on the trend, periodicity and seasonal characteristics of the historical data;

S206, combining the geographic information and the multi-source heterogeneous data to perform space pattern recognition and problem diagnosis.

In the process, various environmental sensors are widely deployed in communities, including air quality sensors (used for monitoring concentration of pollutants such as PM2.5, PM10 and sulfur dioxide), temperature and humidity sensors (used for acquiring temperature and humidity data in communities in real time), noise sensors (used for measuring noise levels in different areas of communities), and water quality sensors (used for monitoring water quality of rivers, lakes or drinking water sources in communities, and including indexes such as pH value, dissolved oxygen and heavy metal content). These sensors constantly collect environmental status data and transmit the data to a data center via a wireless communication network (e.g., wi-Fi, zigBee, 4G/5G, etc.).

And after the data center receives the environmental state data from each sensor, integrating the multi-source heterogeneous data by adopting a data fusion algorithm. Because of possible differences in data formats, sampling frequencies, and accuracy of different sensors, the data is first preprocessed, including operations such as data cleansing (removing noise data and outliers), data normalization (unifying the data to the same dimension and range), and the like. And then, fusion of the measurement data of the plurality of sensors about the same environmental parameter is carried out by using data fusion methods such as weighted average, kalman filtering and the like, so that the accuracy and the reliability of the data are improved. For example, for air quality monitoring, data from multiple air quality sensors are integrated to obtain a more accurate overall air quality condition for the community.

The community environment is a complex system, and the mutual correlation and influence exist among different environment parameters. For example, there is a certain relation between air humidity and temperature, bacteria and mold can be more easily bred in a high-temperature and high-humidity environment to influence the sanitary condition of communities, air quality and traffic flow are also related, and the emission of automobile exhaust is increased in the peak period of traffic, so that the air quality is possibly reduced. And (3) analyzing the association relation among different environment parameters through an association rule mining algorithm (such as an Apriori algorithm) in the data mining technology, and finding out frequently-occurring parameter combinations and association rules thereof. For example, it was found that when the temperature is above 30 ℃ and the humidity is above 70%, the probability of bacterial growth within the community increases significantly.

And drawing the association graph, namely drawing the association graph in order to more intuitively show the association relation between different environment parameters. And taking each environmental parameter as a node in the map, taking the association relation between the parameters as an edge, and representing the association strength by the thickness or the color shade of the edge. Through the association graph, the complex relation among all parameters in the community environment can be clearly seen, and visual basis is provided for deep analysis of potential problems of community treatment. For example, where a close correlation is found between air quality, traffic flow, and resident health complaints in a correlation map, further analysis may infer that traffic pollution may be an important factor leading to resident health problems.

Trend, periodicity and seasonal analysis are respectively carried out on the historical multi-source heterogeneous data, wherein:

And (3) carrying out trend analysis, calculating the long-term trend of the data, and adopting a moving average method, an exponential smoothing method and the like. The moving average method highlights long-term trends by smoothing fluctuations in data by calculating an average of the data over a period of time. For example, a 3 month moving average of the community's monthly Air Quality Index (AQI) over the past year is calculated, and the long-term trend of AQI can be seen more clearly. The exponential smoothing method gives more weight to recent data, and can reflect the change trend of the data more quickly. By adjusting the different smoothing coefficients, different types of data changes can be accommodated. A linear regression model may also be used to fit the long-term trend line of the data, and the slope of the regression equation may be used to determine whether the trend is rising, falling, or stationary. For example, linear regression analysis is performed on greening coverage data of the community over the last several years, and if the slope is positive, it is indicated that the greening coverage is in an ascending trend.

Periodic analysis, the periodic variation of the data, such as a daily period, a weekly period, a monthly period, or a yearly period, is observed. For example, community electricity usage typically has a daily periodicity, a higher daytime electricity usage and a lower night, traffic flow may have a weekly periodicity, heavy weekdays and relatively less weekends. And decomposing the time series data into periodic components with different frequencies by adopting methods such as Fourier analysis and the like, and accurately identifying periodic characteristics in the data. The degree of influence of different periods on data is known by analyzing the amplitude and phase of each period component.

Seasonal analysis, which mainly focuses on the change rule of data in different seasons of the year. For example, the number of people traveling in a community may increase substantially during holidays and traveling in a busy season, but relatively less in a low season, and the incidence of certain diseases may vary significantly from season to season. The seasonal index, which is the ratio of the average value of a certain season to the average value of the whole year, is calculated to measure the seasonal fluctuation level. By comparing the season indexes of different seasons, which seasons are peak periods or valley periods can be determined, and a basis is provided for reasonable allocation of community resources.

And (3) predictive analysis, namely establishing a predictive model to predict future data based on the trend, periodicity and seasonal characteristics of the historical data. Common predictive models include autoregressive moving average (ARMA), autoregressive integrated moving average (ARIMA), and the like. The model is trained and parameter estimated by using the historical data, and the prediction accuracy and reliability of the model are evaluated through model inspection. For example, an index such as Mean Square Error (MSE) or Mean Absolute Error (MAE) is used to measure the deviation between the predicted value and the actual value.

And collecting geographic basic data of communities, including vector data such as community boundaries, road networks, building distribution and the like, and raster data such as topography, land utilization and the like. Such data may be obtained by Geographic Information System (GIS) software or purchased from related departments. Accuracy and behavior of geographic information data are ensured, and the data are updated in time to reflect the latest change of communities. For example, if there is a new building or road in the community, it needs to be added to the geographic information database in time.

And associating community management related data (such as environmental quality data, potential safety hazard data, public service facility use data and the like) to be analyzed with the geographic information data. Address information in the data can be converted into specific geographic coordinates through a geographic coding technology, so that accurate matching of the data and space is realized.

And integrating data of different sources and types to construct a unified community space database. For example, air quality monitoring data, noise monitoring data, garbage distribution data and the like are integrated into one database, so that comprehensive analysis and visual display are facilitated.

And the spatial autocorrelation analysis is used for analyzing the spatial correlation of the data and judging whether the data values of the adjacent areas are similar or not. For example, by calculating the Moran index (Moran's I) of air quality data, it is determined whether space accumulation exists in the air quality of the community. If the Morgan index is positive and significant, it is indicated that regions of similar air quality tend to spatially accumulate, and if it is negative and significant, it is indicated that regions of greater difference in air quality are spatially adjacent.

Hotspot analysis identifies high value aggregate areas (hotspots) and low value aggregate areas (cold spots) of data values within a community. For example, using Getis-Ord Gi statistics to perform hotspot analysis on crime event data in a community, finding out a crime high-incidence area, and providing basis for strengthening security and protection control.

Spatial interpolation, when the data of some areas are missing, the data value of the missing area is estimated by using the data of the surrounding known areas to perform spatial interpolation. Common spatial interpolation methods include inverse distance weighted interpolation, kriging interpolation, and the like. For example, for an area where no air quality monitoring points are set, the air quality condition of the area can be estimated by performing kriging interpolation through data of surrounding monitoring points.

And identifying spatial modes and problems existing in the community according to the spatial visualization result and the spatial statistical analysis conclusion. For example, public service facilities (such as schools, hospitals, parks, etc.) in some areas of communities are found to be unevenly distributed, which results in inconvenience for some residents to enjoy public service, or some industrial areas are too close to the residents, which presents environmental pollution and safety risks.

And analyzing the reason of the formation of the space mode, and comprehensively considering various factors such as geography, society, economy and the like. For example, public service facility maldistribution may be due to historical planning reasons, land use restrictions, or insufficient capital investment.

And S300, generating a decision scheme according to the data analysis result, converting the decision scheme into an execution instruction, and transmitting the execution instruction to a corresponding execution main body.

In this embodiment, a decision scheme is generated according to the data analysis result, and the decision scheme is converted into an execution instruction and sent to a corresponding execution subject. The specific process is as follows:

S301, generating a decision scheme according to a data analysis result, and converting each measure in the scheme into an execution instruction, wherein the execution instruction comprises operation content, an execution object, execution time and an execution standard;

s302, adopting a communication channel to send the generated execution instruction to a corresponding execution main body.

In the process, according to the data analysis result, combining the actual condition, the resource condition and the related policy and regulation of the community, a targeted decision scheme is formulated. For example, if analysis finds that a certain area of a community has serious noise pollution in a specific period, a decision scheme may include measures such as enhancing supervision on commercial activities, setting noise isolation facilities, adjusting traffic flow and the like in the period, and if the air quality of the community has a trend of deterioration, the decision scheme may involve enhancing emission monitoring on surrounding industrial enterprises, promoting a green trip mode, increasing a greening area of the community and the like. The decision scheme should be clear of specific objectives, measures, implementation time and responsibility principals, ensuring that the scheme is operational and efficient.

According to the generated decision scheme, each measure in the scheme is converted into a specific execution instruction by utilizing a decision support system or a special instruction generation tool. The execution instruction should contain explicit operation content, execution objects, execution time, execution criteria, and the like. For example, for the provision of noise isolation facilities, the execution instructions specify the type, specification, installation location, installation time, acceptance criteria, etc. of the isolation facilities, and for the enhancement of the commercial activity supervision, the execution instructions specify the specific content (such as business hours, noise emission limits, etc.), the supervision mode, the responsible personnel, etc.

And the generated execution instruction is accurately sent to the corresponding execution subject through a management information system or a special communication channel in the community. The enforcement agent may include community property management, environmental law enforcement, traffic management, community volunteer organization, and the like. When an instruction is sent, the execution main body is ensured to receive and understand the instruction content in time, and meanwhile, an instruction feedback mechanism is established, so that the execution main body is required to feed back the execution progress and the result periodically in the execution process, the community treatment decision team can monitor and adjust the execution condition of the decision scheme in real time, and the community treatment work is ensured to be smoothly advanced according to a preset target.

Corresponding to the embodiment of the digital twin-driven multi-source information intelligent decision method, the application also provides an embodiment of a digital twin-driven multi-source information intelligent decision system.

FIG. 5 is a block diagram of a digital twinned multi-source information intelligent decision system, according to an exemplary embodiment. Referring to FIG. 5, the system may include a community virtual modeling module 401, a data fusion analysis module 402, a decision execution module 403, wherein:

The community virtual modeling module 401 is configured to collect community, building, and facility operation data, generate a three-dimensional community virtual model, and establish a data correspondence between the virtual model and an entity, and perform data association;

the data fusion analysis module 402 is configured to acquire environmental status data in real time, fuse the environmental status data, and analyze potential problems of community management;

the decision execution module 403 is configured to generate a decision scheme according to the data analysis result, convert the decision scheme into an execution instruction, and send the execution instruction to a corresponding execution subject.

In this embodiment, the community virtual modeling module 401 collects community, building and facility operation data, generates a three-dimensional virtual model of the community, establishes a data correspondence between the virtual model and an entity, and performs data association, the data fusion analysis module 402 acquires environmental status data in real time, fuses the environmental status data, analyzes potential problems of community management, the decision executing module 403 generates a decision scheme according to the data analysis result, converts the decision scheme into an executing instruction, and sends the executing instruction to a corresponding executing subject, thereby realizing real-time virtual mapping of the community space, simulating and predicting community dynamics in real time, and improving decision support capability.

The specific manner in which the various modules perform the operations in relation to the systems of the above embodiments have been described in detail in relation to the embodiments of the method and will not be described in detail herein.

For system embodiments, reference is made to the description of method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present application. Those of ordinary skill in the art will understand and implement the present application without undue burden.

Correspondingly, the application further provides electronic equipment, which comprises one or more processors, a memory and a control unit, wherein the memory is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the digital twin-driven multi-source information intelligent decision method. As shown in fig. 6, a hardware structure diagram of an arbitrary device with data processing capability, where the digital twin-driven multi-source information intelligent decision system is located, is provided in the embodiment of the present application, except for the processor, the memory and the network interface shown in fig. 6, where the arbitrary device with data processing capability is located in the embodiment, generally, according to the actual function of the arbitrary device with data processing capability, other hardware may also be included, which is not described herein again.

Correspondingly, the application also provides a computer readable storage medium, wherein computer instructions are stored on the computer readable storage medium, and the instructions realize the digital twin-driven multi-source information intelligent decision method when being executed by a processor. The computer readable storage medium may be an internal storage unit, such as a hard disk or a memory, of any of the data processing enabled devices described in any of the previous embodiments. The computer readable storage medium may also be an external storage device, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), an SD card, a flash memory card (FLASH CARD), etc. provided on the device. Further, the computer readable storage medium may include both internal storage units and external storage devices of any device having data processing capabilities. The computer readable storage medium is used for storing the computer program and other programs and data required by the arbitrary data processing apparatus, and may also be used for temporarily storing data that has been output or is to be output.

Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.

It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof.

Claims (10)

1. The intelligent decision method for the digital twin-driven multi-source information is characterized by comprising the following steps of:

Collecting community, building and facility operation data, generating a community three-dimensional virtual model, establishing a data corresponding relation between the virtual model and an entity, and carrying out data association;

Acquiring environmental state data in real time, fusing the environmental state data, and analyzing potential problems of community management;

and generating a decision scheme according to the data analysis result, converting the decision scheme into an execution instruction, and sending the execution instruction to a corresponding execution main body.

2. The intelligent decision-making method of digital twin driven multisource information according to claim 1, wherein in the steps of collecting community, building and facility operation data, generating a three-dimensional virtual model of the community, establishing a data correspondence between the virtual model and an entity, and performing data association:

respectively collecting geometric data of community, building and facility operation, and integrating and preprocessing the geometric data;

reducing and refining the building model according to the geometric data, and adding elements to generate a community three-dimensional virtual model;

Each element in the three-dimensional virtual model of the community is assigned a unique identifier that corresponds to the actual entity.

3. The digital twin driven multi-source information intelligent decision method of claim 2, wherein after the step of assigning a unique identifier to each element in the three-dimensional virtual model of the community, the identifier corresponds to an actual entity:

and correlating the collected community, building and facility operation data with corresponding elements in the virtual model, and establishing a data table to store correlation information.

4. The digital twin driven multi-source information intelligent decision method of claim 1, wherein in the step of acquiring environmental status data in real time, fusing the environmental status data, and analyzing the community governance potential problem:

Deploying an environment sensor, collecting environment state data in real time, and outputting multi-source heterogeneous data;

after preprocessing the multi-source heterogeneous data, fusing the measurement data of the plurality of sensors about the same environmental parameter in a data fusion mode;

Constructing association rules, analyzing association relations among different environment parameters, and outputting frequently-occurring parameter combinations and association rules thereof;

and respectively carrying out time sequence analysis and spatial distribution analysis on the multi-source heterogeneous data, and outputting analysis results.

5. The intelligent decision-making method of digital twin driven multisource information according to claim 4, wherein after the steps of constructing association rules, analyzing association relations between different environmental parameters, outputting frequently occurring parameter combinations and their association rules:

and taking each environmental parameter as a node, taking the association relation among the parameters as an edge, and drawing an association map.

6. The intelligent decision-making method of digital twin driven multisource information according to claim 4, wherein in the steps of performing time series analysis and spatial distribution analysis on multisource heterogeneous data, respectively, and outputting the analysis result:

and respectively carrying out trend, periodicity and seasonal analysis on the historical multi-source heterogeneous data, and establishing a prediction model to predict the data based on the trend, periodicity and seasonal characteristics of the historical data.

7. The intelligent decision-making method of digital twin driven multisource information according to claim 6, wherein in the steps of performing time series analysis and spatial distribution analysis on multisource heterogeneous data, respectively, and outputting the analysis result:

And combining the geographic information and the multi-source heterogeneous data to perform spatial mode identification and problem diagnosis.

8. The digital twin-driven multi-source information intelligent decision-making method according to claim 1, wherein in the step of generating a decision-making scheme according to the data analysis result, converting the decision-making scheme into an execution instruction, and transmitting the execution instruction to a corresponding execution subject:

And generating a decision scheme according to the data analysis result, and converting each measure in the scheme into an execution instruction, wherein the execution instruction comprises operation content, an execution object, execution time and an execution standard.

9. The digital twin driven multisource information intelligent decision method of claim 8, wherein after the steps of generating a decision scheme based on the data analysis results and converting each measure in the scheme into an execution instruction:

And transmitting the generated execution instruction to a corresponding execution subject by adopting a communication channel.

10. The intelligent decision system for the digital twin-driven multi-source information is applied to the intelligent decision method for the digital twin-driven multi-source information as claimed in claim 1, and is characterized by comprising a community virtual modeling module, a data fusion analysis module and a decision execution module, wherein:

the community virtual modeling module is used for collecting community, building and facility operation data, generating a community three-dimensional virtual model, establishing a data corresponding relation between the virtual model and an entity, and carrying out data association;

The data fusion analysis module is used for acquiring environmental state data in real time, fusing the environmental state data and analyzing potential problems of community management;

The decision execution module is used for generating a decision scheme according to the data analysis result, converting the decision scheme into an execution instruction and sending the execution instruction to a corresponding execution main body.