Data processing method for intelligent emergency command platform

Abstract

The invention discloses a data processing method for an intelligent emergency command platform, and relates to the technical field of emergency command data processing, and the method comprises the steps: starting a plurality of data import interfaces when the intelligent emergency command platform has an event response, issuing a data interaction key, and extracting the uploaded data of the plurality of data import interfaces; determining the maximum data capacity of the intelligent emergency command platform in unit time; performing periodic segmented import processing on the extracted uploaded data of the plurality of data import interfaces, and determining access data in a unit period; based on the access data in the unit period, extracting data characteristics of the access data in the unit period, determining a calling data type in the mixed storage database, and determining a data capacity ratio of the single data to the composite data; and forming a reference plan decision of the emergency event, and feeding back to the administrator port. According to the invention, the problem of data pressure caused by sudden data increase of the intelligent emergency command platform when an emergency event occurs can be effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency command data processing, and specifically to a data processing method for a smart emergency command platform. Background Art

[0002] With the acceleration of the urbanization process and the frequent occurrence of emergencies such as natural disasters, accident disasters, and public health events, the traditional emergency management mode has been difficult to meet the requirements of rapid response and accurate decision-making. The smart emergency command platform realizes the real-time monitoring, early warning judgment, and intelligent dispatching of emergency events through technologies such as big data, artificial intelligence, and the Internet of Things.

[0003] However, when an emergency occurs, the amount of data grows exponentially, bringing huge challenges to the stability, computing power, and decision-making efficiency of the platform. When an emergency occurs, the data sources are extensive and the data volume surges, and a large number of multi-source heterogeneous data pour in, including sensor data, video surveillance data, UAV aerial photography data, social media public opinion, and emergency communication data, etc. At the same time, the data scale gradually surges. Currently, the smart emergency command platform often relies on a large amount of historical data and real-time data transmission to construct a decision support model when making decisions. On the basis of a large amount of real-time data, the same type of historical data is called. If the call is unrestricted, a large amount of original data of the data model will be generated, causing data congestion in the emergency command platform. If the call is controlled, there is a lack of control standards, and at the same time, it is impossible to ensure whether the controlled original data meets the modeling requirements.

[0004] Therefore, in the current smart emergency command platform, the process of data call lacks certain research and processing. How to balance the state between the platform data capacity and data modeling in the data call process is one of the problems that the current smart emergency command platform needs to solve. Summary of the Invention

[0005] The purpose of the present invention is to provide a data processing method for a smart emergency command platform to solve the problems raised in the prior art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A data processing method for a smart emergency command platform, the method includes the following steps: S1. When an event response exists in the smart emergency command platform, start a number of data import interfaces, issue a data interaction key, and extract the upload data of the number of data import interfaces; S2. Based on the rated data interaction threshold of the smart emergency command platform and the occupied value of the decision-making party's data resources that have been issued, determine the maximum data capacity of the smart emergency command platform per unit time; S3. Establish a hybrid storage database to store all the data of emergency command events in historical events. Based on the maximum data capacity per unit time of the intelligent emergency command platform, perform periodic segmented import processing on the uploaded data of several data import interfaces that are extracted, and determine the access data within a unit period. S4. Based on the access data within a unit period, extract the data characteristics of the access data within a unit period, determine the data types to be called in the hybrid storage database. The data types include single data and composite data. Determine the proportion of the data capacities of single data and composite data based on the maximum data capacity per unit time of the intelligent emergency command platform. S5. Based on the historical data called in the hybrid storage database, form a reference plan decision for emergency events and feedback it to the administrator port.

[0007] According to the above technical solution, when there is an event response on the intelligent emergency command platform, several data import interfaces are started, a data interaction key is issued, and the extraction of the uploaded data of several data import interfaces includes: When there is an event response, the intelligent emergency command platform constructs several data import interfaces based on system settings, sets a data interaction key for each data import interface, and uniformly issues it by the administrator terminal. Each data import interface realizes data interaction with the administrator terminal based on its own data interaction key and uploads the on-site event data. The intelligent emergency command platform uniformly extracts the uploaded data of several data import interfaces.

[0008] According to the above technical solution, the determination of the maximum data capacity per unit time of the intelligent emergency command platform based on the rated data interaction threshold of the intelligent emergency command platform and the occupied value of the decision-making party's data resources that has been issued includes: The system sets the maximum occupied value of a single decision-making party's data resources. Based on the number of decision-making parties set in real time under different events, calculate the occupied value of the decision-making party's data resources. Determine the maximum data capacity per unit time of the intelligent emergency command platform through the difference between the rated data interaction threshold of the intelligent emergency command platform and the issued occupied value of the decision-making party's data resources.

[0009] According to the above technical solution, the periodic segmented import processing of the uploaded data of several data import interfaces that are extracted based on the maximum data capacity per unit time of the intelligent emergency command platform, and the determination of the access data within a unit period includes: The maximum data capacity per unit time based on the intelligent emergency command platform is divided into the maximum upload traffic and the maximum call traffic. The upload data of several data import interfaces is processed based on the maximum upload traffic. If the total upload data of several data import interfaces per unit time is not higher than the maximum upload traffic, then it is determined that the access data within the unit period is equal to the total upload data of several data import interfaces. If the total upload data of several data import interfaces per unit time is higher than the maximum upload traffic, it is imported in cycles according to the maximum upload traffic per unit time.

[0010] According to the above technical solution, based on the access data within the unit period, the data characteristics of the access data within the unit period are extracted, and the call data types determined in the hybrid storage database include: The access data within the unit period is obtained, and the access data is feature-extracted based on unstructured data feature extraction and emergency domain-specific feature extraction. The unstructured data feature extraction includes text data features, video data features, and voice data features; the emergency domain-specific features include event evolution features, resource scheduling features, and event situation assessment features. The event evolution features include event diffusion parameters, influence range boundaries, and event level assessment indicators; the resource scheduling features include demand-resource matching degree, path reachability analysis features, and resource utility assessment; the event situation assessment features include event comprehensive risk index and event-related impact area. The access data within the unit period is obtained, the data characteristics existing in the access data are determined, and based on the data characteristics existing in the access data, the event historical data with the same data characteristics is called in the hybrid storage database.

[0011] According to the above technical solution, the single data refers to the data containing a single data characteristic; the composite data refers to the data containing all the existing data characteristics.

[0012] According to the above technical solution, the determination of the data capacity ratio of single data and composite data based on the maximum data capacity per unit time of the intelligent emergency command platform includes: The data characteristics existing in the access data within the unit period are obtained, the first data analysis port is set, the data characteristic ratio threshold is set, the capacity ratio of the data characteristics existing in the access data within the unit period in the access data within the unit period is calculated, and the data with the ratio value higher than the data characteristic ratio threshold enters the next stage; The processing of the next stage includes: For the access data within the current unit cycle starting from the beginning of the event response, if there is only one set of data features, the corresponding event history data of this set of data features is called in the hybrid storage database until the data volume reaches the maximum data volume within the unit time of the intelligent emergency command platform; if there are multiple sets of data features, several single data and a set of composite data are formed. The several single data refer to each data feature type existing in the access data within the current unit cycle, and the set of composite data refers to all data feature types existing in the access data from the start of the event response to the current unit cycle. Construct a digital model and create a digital model database. There are several sets of data in the database, and each set of data has at least one data feature. The several sets of data can have the same data feature among them: S701. Build an emergency event processing model based on the data in the digital model database, and use real data to test the loss function of the emergency event processing model. The real data includes various single data of the data features existing in the database and the composite data of all data features existing in the database. Each time the test outputs the average value of the loss function outputs of various single data and composite data. S702. Each time, take several sets of data groups and add them to the digital model database, ensuring that each time the several sets of data added can increase and only increase one data feature for the digital model database. Repeat step S701 until the set number of additions set by the system is reached. S703. Based on the average value of the loss function outputs of various single data and composite data output each time, perform data fitting, analyze the functional relationship between the change of the loss function of the composite data and the number of data features in the composite data, and establish a linear fitting relationship formula. Construct a composite data volume relationship formula:

[0013] Among them, is the composite data volume in the current cycle; is the composite data volume in the previous cycle; represents the average value of the loss function when the number of data features in the composite data is x - 1; represents the average value of the loss function when the number of data features in the composite data is x; If there is only one data feature in the first cycle, the composite data volume in the first cycle is defined as half of the maximum data volume within the unit time of the intelligent emergency command platform. Subtract the composite data volume in the current cycle from the maximum data volume within the unit time of the intelligent emergency command platform, and divide the remaining data volume according to the proportion of each single data volume.

[0014] According to the above technical solution, forming a reference plan decision for emergency events based on the historical data called in the hybrid storage database and feeding it back to the administrator port includes: Call the emergency command reference model configured by the administrator in the system, and form a reference plan decision for emergency events based on the event historical data called in the hybrid storage database; If there is a set of composite data for which no event historical data can be called in the hybrid storage database, an alarm is initiated to the administrator port.

[0015] Compared with the prior art, the beneficial effects of the present invention are: The present invention can solve the challenge of the sudden increase in data volume faced by the intelligent emergency command platform in emergency events, and combine technologies such as big data storage, intelligent analysis, and data collaboration to build an efficient and stable data processing system to support rapid and accurate emergency decision-making. It effectively balances the state between the platform data capacity and data modeling during the data call process, and provides stronger support for the data management of the emergency command platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a step schematic diagram of a data processing method for an intelligent emergency command platform of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present invention.

[0018] Specifically, in this embodiment, a data processing method for an intelligent emergency command platform is provided, and the method includes: when an event response exists in the intelligent emergency command platform, several data import interfaces are started, a data interaction key is issued, and the uploaded data of several data import interfaces is extracted; The starting of several data import interfaces, issuing of data interaction keys, and extraction of the uploaded data of several data import interfaces when an event response exists in the intelligent emergency command platform includes: When an event response exists, the intelligent emergency command platform constructs several data import interfaces based on the system settings, sets data interaction keys for each data import interface, and uniformly issues them by the administrator side. Each data import interface realizes data interaction with the administrator side based on its own data interaction key, uploads event site data, and the intelligent emergency command platform uniformly extracts the uploaded data of several data import interfaces.

[0019] Determine the maximum data capacity per unit time of the intelligent emergency command platform based on the rated data interaction threshold of the intelligent emergency command platform and the occupied value of the decision-making party data resources already issued; Determining the maximum data capacity per unit time of the intelligent emergency command platform based on the rated data interaction threshold of the intelligent emergency command platform and the occupied value of the decision-making party data resources that have been issued includes: The system sets the maximum occupied value of the data resources of a single decision-making party. Based on the number of decision-making parties set in real time under different events, the occupied value of the decision-making party data resources is calculated. The difference between the rated data interaction threshold of the intelligent emergency command platform and the issued occupied value of the decision-making party data resources is used to determine the maximum data capacity per unit time of the intelligent emergency command platform.

[0020] A hybrid storage database is established to store all the data of emergency command events in historical events. Based on the maximum data capacity per unit time of the intelligent emergency command platform, the upload data of several data import interfaces extracted is processed for periodic segmented import, and the access data within a unit period is determined. The processing of the upload data of several data import interfaces extracted for periodic segmented import based on the maximum data capacity per unit time of the intelligent emergency command platform to determine the access data within a unit period includes: Based on the maximum data capacity per unit time of the intelligent emergency command platform, it is divided into the maximum upload traffic and the maximum call traffic. Based on the maximum upload traffic, the upload data of several data import interfaces is processed. If the total upload data volume of several data import interfaces within a unit time is not higher than the maximum upload traffic, it is determined that the access data within a unit period is equal to the total upload data volume of several data import interfaces; if the total upload data volume of several data import interfaces within a unit time is higher than the maximum upload traffic, it is imported in cycles according to the maximum upload traffic per unit time.

[0021] Based on the access data within a unit period, the data characteristics of the access data within a unit period are extracted, and the call data types are determined in the hybrid storage database. The data types include single data and composite data. The data capacity ratios of single data and composite data are determined based on the maximum data capacity per unit time of the intelligent emergency command platform. The determining of the call data types in the hybrid storage database by extracting the data characteristics of the access data within a unit period based on the access data within a unit period includes: Obtain the access data within a unit period, and perform feature extraction on the access data based on unstructured data feature extraction and emergency domain-specific feature extraction. The unstructured data feature extraction includes text data features, video data features, and voice data features; the emergency domain-specific features include event evolution features, resource scheduling features, and event situation assessment features. The described event evolution characteristics include event diffusion parameters, the boundary of the influence range, and event level evaluation indicators; the resource scheduling characteristics include the matching degree of demand and resources, path reachability analysis characteristics, and resource utility evaluation; the event situation evaluation characteristics include the event comprehensive risk index and the event associated impact area. Obtain the access data within a unit period, determine the data characteristics existing in the access data, and call the event historical data with the same data characteristics in the hybrid storage database based on the data characteristics existing in the access data.

[0022] The single data refers to the data containing a single data characteristic; the composite data refers to the data containing all the existing data characteristics.

[0023] The determination of the data capacity ratio of single data and composite data based on the maximum data capacity per unit time of the intelligent emergency command platform includes: Obtain the data characteristics existing in the access data within a unit period, set the first data analysis port, set the data characteristic ratio threshold, calculate the capacity ratio of the data characteristics existing in the access data within a unit period in the access data within a unit period, and take the data with a ratio value higher than the data characteristic ratio threshold into the next stage; The processing of the next stage includes: For the access data from the start of event response to the current unit period, if there is only one set of data characteristics, call the event historical data corresponding to this set of data characteristics in the hybrid storage database until the data capacity reaches the maximum data capacity per unit time of the intelligent emergency command platform; if there are multiple sets of data characteristics, form several single data and one set of composite data. The several single data refer to each data characteristic type existing in the access data within the current unit period, and the one set of composite data refers to all the data characteristic types existing in the access data from the start of event response to the current unit period; Construct a digital model, create a digital model database. There are several sets of data in the database, and each set of data has at least one data characteristic. There can be the same data characteristics among several sets of data: S701. Build an emergency event processing model based on the data in the digital model database, and take the real data to test the loss function of the emergency event processing model. The real data includes various single data containing the data characteristics existing in the database and composite data containing all the data characteristics existing in the database. Each time of testing, output the average value of the loss function outputs of various single data and composite data; S702. Each time, take several groups of data and add them to the digital model database, ensuring that each time the several groups of data added can add and only add one data characteristic to the digital model database. Repeat step S701 until the set number of additions of the system is reached; S703. Based on the average value of the loss function outputs of various single data and composite data for each test, perform data fitting, analyze the functional relationship between the change of the loss function of the composite data and the number of data features in the composite data, and establish a linear fitting relationship formula; Construct a composite data capacity relationship formula:

[0024] wherein, is the composite data capacity of the current cycle; is the composite data capacity of the previous cycle; represents the average value of the loss function when the number of data features in the composite data is x - 1; represents the average value of the loss function when the number of data features in the composite data is x; If there is only one type of data feature in the first cycle, the composite data capacity of the first cycle is defined as one - half of the maximum data capacity per unit time of the intelligent emergency command platform; Remove the composite data capacity of the current cycle from the maximum data capacity per unit time of the intelligent emergency command platform, and divide the remaining data capacity according to the ratio of each single data capacity.

[0025] Based on the historical data called from the hybrid storage database, form a reference pre - plan decision for emergency events, and feedback to the administrator port, including: Call the emergency command reference model configured by the administrator in the system, and based on the event historical data called from the hybrid storage database, form a reference pre - plan decision for emergency events; If there is a set of composite data for which no event historical data can be called from the hybrid storage database, initiate an alarm to the administrator port.

[0026] Those skilled in the art can clearly understand that for the sake of convenience and brevity of description, the specific working processes of the above - described platform, device, and unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0027] In the embodiments of the present application, prefix words such as "first" and "second" are only used to distinguish different described objects, and have no restrictive effect on the position, order, priority, quantity, or content of the described objects, etc. The use of ordinal words and other prefix words for distinguishing described objects in the embodiments of the present application does not constitute a restriction on the described objects. The statement of the described objects refers to the description in the context of the claims or embodiments, and should not constitute redundant restrictions because of the use of such prefix words. In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical, or other forms. In each embodiment of the present application, if there is no special explanation and logical conflict, the terms and / or descriptions between the embodiments are consistent and can be referred to each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships. The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0028] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0029] As mentioned above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A data processing method for a smart emergency command platform, characterized in that: The method includes the following steps: S1. When there is an event response on the intelligent emergency command platform, start several data import interfaces, issue data interaction keys, and extract the upload data of several data import interfaces; S2. Based on the rated data interaction threshold of the intelligent emergency command platform and the occupied value of the decision-making party's data resources that has been issued, determine the maximum data capacity of the intelligent emergency command platform per unit time; S3. Establish a hybrid storage database to store all the data of emergency command events in historical events. Based on the maximum data capacity of the intelligent emergency command platform per unit time, perform periodic segmented import processing on the upload data of several data import interfaces that have been extracted, and determine the access data within a unit period; S4. Based on the access data within a unit period, extract the data characteristics of the access data within a unit period, determine the called data types in the hybrid storage database, where the data types include single data and composite data, and determine the data capacity proportion of single data and composite data based on the maximum data capacity of the intelligent emergency command platform per unit time; S5. Based on the historical data called in the hybrid storage database, form a reference plan decision for emergency events and feedback it to the administrator port.

2. A data processing method for a smart emergency command platform according to claim 1, characterized in that: The step of starting several data import interfaces, issuing data interaction keys, and extracting the upload data of several data import interfaces when there is an event response on the intelligent emergency command platform includes: When there is an event response, the intelligent emergency command platform constructs several data import interfaces based on system settings, sets data interaction keys for each data import interface, and issues them uniformly by the administrator terminal. Each data import interface realizes data interaction with the administrator terminal based on its own data interaction key and uploads the on-site event data. The intelligent emergency command platform uniformly extracts the upload data of several data import interfaces.

3. A data processing method for a smart emergency command platform according to claim 1, characterized in that: The step of determining the maximum data capacity of the intelligent emergency command platform per unit time based on the rated data interaction threshold of the intelligent emergency command platform and the occupied value of the decision-making party's data resources that has been issued includes: The system sets the maximum occupied value of the data resources of a single decision-making party. Based on the number of decision-making parties set in real time under different events, calculate the occupied value of the decision-making party's data resources. Determine the maximum data capacity of the intelligent emergency command platform per unit time through the difference between the rated data interaction threshold of the intelligent emergency command platform and the issued occupied value of the decision-making party's data resources.

4. A data processing method for a smart emergency command platform according to claim 1, characterized in that: The step of performing periodic segmented import processing on the upload data of several data import interfaces that have been extracted based on the maximum data capacity of the intelligent emergency command platform per unit time and determining the access data within a unit period includes: Based on the maximum data capacity of the intelligent emergency command platform per unit time, it is divided into the maximum upload traffic and the maximum call traffic. Process the upload data of several data import interfaces based on the maximum upload traffic. If the total upload data volume of several data import interfaces within a unit time is not higher than the maximum upload traffic, then determine that the access data within a unit period is equal to the total upload data volume of several data import interfaces; if the total upload data volume of several data import interfaces within a unit time is higher than the maximum upload traffic, import it in cycles according to the maximum upload traffic per unit time.

5. A data processing method for a smart emergency command platform according to claim 1, characterized in that: Based on the access data within a unit period, extracting the data features of the access data within the unit period, and determining the call data types in the hybrid storage database includes: Obtaining the access data within a unit period, and performing feature extraction on the access data based on unstructured data feature extraction and emergency domain-specific feature extraction. The unstructured data feature extraction includes text data features, video data features, and voice data features; the emergency domain-specific features include event evolution features, resource scheduling features, and event situation assessment features; The event evolution features include event diffusion parameters, influence range boundaries, and event level assessment indicators; the resource scheduling features include demand-resource matching degree, path reachability analysis features, and resource utility assessment; the event situation assessment features include event comprehensive risk index and event associated impact area; Obtaining the access data within a unit period, determining the data features existing in the access data, and based on the data features existing in the access data, calling the event historical data with the same data features in the hybrid storage database.

6. A data processing method for a smart emergency command platform according to claim 1, characterized in that: The single data refers to the data containing a single data feature; the composite data refers to the data containing all the existing data features.

7. A data processing method for a smart emergency command platform according to claim 6, characterized in that: The determination of the data capacity ratio of single data and composite data based on the maximum data capacity within a unit time of the intelligent emergency command platform includes: Obtaining the data features existing in the access data within a unit period, setting a first data analysis port, setting a data feature ratio threshold, calculating the capacity ratio of the data features existing in the access data within the unit period in the access data within the unit period, and taking the data with a ratio value higher than the data feature ratio threshold into the next stage; The processing of the next stage includes: For the access data from the start of event response to the current unit period, if there is only one set of data features, call the event historical data corresponding to this set of data features in the hybrid storage database until the data capacity reaches the maximum data capacity within a unit time of the intelligent emergency command platform; if there are multiple sets of data features, form several single data and one set of composite data. The several single data refer to each data feature type existing in the access data within the current unit period, and the one set of composite data refers to all the data feature types existing in the access data from the start of event response to the current unit period; Constructing a digital model, creating a digital model database, where there are several sets of data in the database, each set of data has at least one data feature, and there can be the same data features among several sets of data: S701. Constructing an emergency event processing model based on the data in the digital model database, and taking the real data to test the loss function of the emergency event processing model. The real data includes various single data with the data features existing in the database and the composite data with all the data features existing in the database, and the average value of the loss function outputs of various single data and composite data is output each time of testing; S702. Each time, take several groups of data sets and add them to the digital modeling database, ensuring that the several groups of data added each time can add and only add one type of data feature to the digital modeling database. Repeat step S701 until the system-set addition times are reached; S703. Based on the average value of the loss function outputs of various single data and composite data output each time during testing, perform data fitting, analyze the functional relationship between the change of the loss function of the composite data and the number of data features in the composite data, and establish a linear fitting relationship; Construct a composite data capacity relationship: Among them, is the composite data capacity of the current cycle; is the composite data capacity of the previous cycle; represents the average value of the loss function when the number of data features in the composite data is x - 1; represents the average value of the loss function when the number of data features in the composite data is x; If there is only one type of data feature in the first period, the composite data capacity of the first period is defined as one-half of the maximum data capacity per unit time of the intelligent emergency command platform; Remove the current period's composite data capacity from the maximum data capacity per unit time of the intelligent emergency command platform, and divide the remaining data capacity according to the ratio of each single data capacity.

8. A data processing method for a smart emergency command platform according to claim 7, characterized in that: The formation of a reference plan decision for an emergency event based on the historical data called from the hybrid storage database and feedback to the administrator port includes: Call the emergency command reference model configured by the administrator in the system, and form a reference plan decision for the emergency event based on the event historical data called from the hybrid storage database; If there is a group of composite data from which no event historical data can be called in the hybrid storage database, initiate an alarm to the administrator port.

Images