A multi-source heterogeneous data driven emergency simulation deduction method

Abstract

The present application relates to the technical field of simulation deduction, and particularly relates to a multi-source heterogeneous data driven emergency simulation deduction method. According to the differences between each data set of an emergency link and the data types in the remaining data sets, the simulation time length differences, and the differences between the simulation time length and the ideal time length of each data set, the time delay significance is obtained. According to the data type with the same structure type generated by any two information sources of the data set and the time delay significance acquisition scheme, the conflict delay degree is obtained. According to the differences between the time delay degree caused by data conflicts in data fusion of the data set and the scheme conflict delay degree, the data fusion delay degree is determined. According to the data fusion delay degree of the data set of each emergency link and the simulation time length of the data set of the subsequent emergency link, the conflict delay attenuation degree is obtained, and the simulation time length is adjusted to obtain the simulation correction time length. The present application reduces the interference of multi-source heterogeneous delay on simulation deduction, and improves the reliability of simulation deduction results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of simulation deduction, and particularly relates to a multi-source heterogeneous data driven emergency simulation deduction method. BACKGROUND

[0002] Emergency simulation deduction simulates emergency scenes such as earthquakes, fires and traffic accidents, detects operation blind spots, process loopholes and response mechanism defects in emergency plans, and then optimizes emergency processes, resource allocation and multi-party collaboration modes. The prior art is constructed through three aspects of emergency simulation, digital plan and fine modeling of key units. The virtual platform models the accident scene and assumes an emergency accident, generates a 3D digital emergency plan, and assists enterprises and rescue departments in selecting the optimal emergency deduction scheme.

[0003] In the emergency deduction process, in order to ensure the integrity of the simulation, the virtual platform needs to integrate multi-source heterogeneous data from multiple information sources. These information sources have different data structures. In order to determine the best emergency scheme, the operator will call different multi-source heterogeneous data for combination multiple times to select the emergency deduction scheme with the shortest disposal time. However, when the multi-source heterogeneous data is combined, the data exclusion effect caused by inconsistent data structures causes time delay in multi-source data fusion, which causes errors in the disposal time simulation results of the multiple emergency simulation schemes listed by the operator, and thus the decision reliability of the optimal emergency deduction scheme. SUMMARY

[0004] In order to solve the technical problem that the time delay in multi-source heterogeneous data fusion causes errors in the disposal time simulation results of the emergency simulation scheme, the purpose of the present application is to provide a multi-source heterogeneous data driven emergency simulation deduction method, and the technical solution adopted is as follows:

[0005] The present application provides a multi-source heterogeneous data driven emergency simulation deduction method, which comprises:

[0006] Obtain the simulation time and ideal time of the data set of different link deduction schemes of different emergency links in the emergency simulation scheme of the emergency accident for simulation deduction; the data set contains data from different information sources;

[0007] According to the data type difference, simulation time difference of each data set of the emergency link and the remaining data sets, and the difference between the simulation time and the ideal time of each data set, obtain the time delay significance of each data set;

[0008] According to the time delay degree of each data set, the time delay degree of each data set is obtained according to the time delay degree of each data set and the time delay degree of each data set.

[0009] According to the data fusion delay degree of each data set of each emergency link and the simulation time length of the data set of the subsequent emergency link, the conflict delay attenuation degree of the corresponding data set is obtained; and the simulation time length of the data set is adjusted by using the conflict delay attenuation degree to obtain a simulation modified time length.

[0010] Further, the time delay degree of each data set comprises:

[0011] The difference between the simulation time length and the ideal time length of the data set is denoted as a time delay degree;

[0012] The difference between each data set of the emergency link and the simulation time length of the remaining data sets is averaged to obtain the deduction efficiency difference of each data set.

[0013] The average of the difference between each data set of the emergency link and the number of data types in the remaining data sets is denoted as the heterogeneous prominence of each data set.

[0014] According to the time delay degree, the deduction efficiency difference and the heterogeneous prominence, the time delay degree of each data set of the emergency link is obtained.

[0015] Further, the scheme conflict delay degree of each data set comprises:

[0016] The maximum value of the number of data types of all information sources in the data set is counted, and the maximum value is used as the denominator to obtain the ratio as the structure conflict degree between any two information sources in the data set.

[0017] The sum of the structure conflict degrees between all information sources in the data set is denoted as the structure overall conflict degree.

[0018] According to the time delay degree and the structure overall conflict degree, the scheme conflict delay degree of the data set is obtained.

[0019] Further, the data fusion delay degree of each data set comprises:

[0020] extracting entities from the data set corresponding to the link, defining the relationship of the entities, and generating a directed graph, denoted as a deduction scheme graph; assigning data in the data set to nodes in the deduction scheme graph, and obtaining a process conflict delay degree of each node in the deduction scheme graph;

[0021] According to the difference between the process conflict delay degree and the scheme conflict delay degree of the node in the deduction scheme graph corresponding to the data set, and the number of data categories corresponding to the node, a data fusion delay degree of the data set is obtained.

[0022] Further, the method for obtaining the data fusion delay degree comprises:

[0023] The absolute value of the difference between the process conflict delay degree and the scheme conflict delay degree of each node in the deduction scheme graph corresponding to the data set is calculated, and the product of each node and the number of data categories corresponding to the node is obtained, and the average of all products is obtained to obtain the data fusion delay degree of the data set.

[0024] Further, the method for obtaining the conflict delay attenuation degree comprises:

[0025] The cumulative sum of the simulation time length of all data sets of all emergency links after each emergency link is denoted as the deduction continuous influence degree of each emergency link.

[0026] The product of the time delay degree, the data fusion delay degree and the deduction continuous influence degree of each data set of each emergency link is negatively correlated and normalized to obtain the conflict delay attenuation degree of the corresponding data set.

[0027] Further, the method for obtaining the simulation correction time length comprises:

[0028] For each data set of each emergency link, the simulation time length of the data set is weighted by using a constant and the difference between the conflict delay attenuation degree of the data set to obtain the simulation correction time length of the data set.

[0029] Further, the method for defining the relationship of the entities is a Drools rule engine.

[0030] Further, the process conflict delay degree is the scheme conflict delay degree of the data set corresponding to each node in the deduction scheme graph.

[0031] Further, the different emergency links in the emergency simulation scheme have a time sequence.

[0032] The present application has the following beneficial effects:

[0033] In the embodiment of the present application, the difference between the simulation duration and the ideal duration of the data set directly presents the distinguishability of the time delay of the data set corresponding link deduction scheme caused by data conflict, and the difference between each data set and the data type difference in the remaining data sets, the simulation duration difference, in turn, through the time synchronization of the two, the data diversity analysis time delay effect existence possibility, the time delay significance is obtained; The difference between the time delay degree caused by data conflict in the data fusion process of the data in the data set and the scheme conflict delay degree, by connecting the time delay effect and the data fusion effect, the details of the multi-source heterogeneous data in driving the emergency simulation deduction are more obvious, the influence of the delay effect caused by data conflict on the reserved result after fusion is analyzed, the data fusion delay degree is determined, and the clear degree of conflict of multi-source heterogeneous data in data fusion is improved; Finally, the influence of different data sets on the subsequent other emergency links is analyzed, the conflict delay attenuation degree of the data set is determined, the simulation duration of the data set is adjusted by using the conflict delay attenuation degree, on the basis of ensuring the overall emergency process real and effective as much as possible, the interference of the delay effect on the simulation deduction duration is reduced, and the reliability of the simulation deduction duration is improved. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0035] Figure 1 A step flow chart of a multi-source heterogeneous data driven emergency simulation deduction method provided by an embodiment of the present application;

[0036] Figure 2 A flow chart of a data fusion delay degree acquisition method provided by an embodiment of the present application;

[0037] Figure 3 A computer device schematic diagram of a multi-source heterogeneous data driven emergency simulation deduction device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined inventive purpose, the following describes in detail the specific implementation, structure, features and effects of a multi-source heterogeneous data driven emergency simulation deduction method according to the present application, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0040] The specific scheme of the multi-source heterogeneous data driven emergency simulation deduction method provided by the present application is described in detail below in combination with the accompanying drawings.

[0041] Embodiment 1:

[0042] The present application proposes a multi-source heterogeneous data driven emergency simulation deduction method, please refer to Figure 1 which shows the step flowchart of a multi-source heterogeneous data driven emergency simulation deduction method provided by one embodiment of the present application, which includes:

[0043] Step S1: Obtain the simulation duration and ideal duration of the data set of different link deduction schemes of different emergency links in the emergency simulation scheme of the emergency accident for simulation deduction; the data set contains data from different information sources.

[0044] Each emergency simulation scheme of an emergency accident contains multiple emergency links, and this scheme is in turn an accident occurrence link, an information reporting link, a start emergency response link, an emergency group response link, and an end response link. Each emergency link has multiple link deduction schemes, and each link deduction scheme in the same emergency link represents a deduction attempt of the emergency process. One link deduction scheme corresponds to one data set, and the data set of the link deduction scheme is composed of data from different information sources in the link deduction scheme. The timestamp difference from the start of the virtual platform from one link deduction scheme to the end of the emergency simulation deduction is recorded as the simulation duration of the data set of the link deduction scheme. Each emergency link has an evaluation personnel who evaluates a reasonable duration on the corresponding link in advance for reference, and this duration is recorded as the ideal duration of the corresponding emergency link.

[0045] As an example, the specific content of the emergency simulation scheme is as follows:

[0046] The accident occurred at 9:25 am. A project scaffold operation team was performing a three-story scaffold erection operation when the collapse of the entire scaffold structure occurred due to improper setting of the sweeping rod. In this accident, the workers were unfortunately injured by the collapsed scaffold. Information reporting: After the accident, the scaffold worker immediately reported the incident to the scaffold team leader, who then reported it to the project manager. Emergency response initiation: The project manager quickly took charge of the scene and decisively initiated the special emergency plan, dispatching various emergency teams to the accident site to ensure rapid response and effective cooperation to control the situation and minimize losses. Emergency team response: The on-site rescue team quickly assessed the injury and death situation, rescued the injured and surveyed the scene; the security and evacuation team blocked the scene and maintained order; the logistics support team allocated resources, took photos and collected information; the medical rescue team provided emergency treatment to the injured and contacted the emergency center; the communication team investigated the accident and reported the situation to the superior department. Response completion: The accident site was effectively controlled, and the treatment measures met the relevant standards. After confirmation and approval by the on-site command center, the emergency response was successfully completed, and the emergency rescue team withdrew; after the cleanup and follow-up work was completed, the on-site command center carefully prepared an emergency rescue summary report and made a detailed report to the superior department.

[0047] The link deduction scheme for each emergency link can be as follows:

[0048] The first link deduction scheme TA1 for the accident occurrence link: assume that the scaffold collapse is detected in real-time by Internet of Things sensors (inclination meter + vibration sensor) and automatically reported; the second link deduction scheme TA2: the collapse accident is reported by the workers on site. The first link deduction scheme TB1 for the information reporting link: report to the superior department in layers, workers → team leader → project manager, report by phone or intercom; the second link deduction scheme TB2: workers report to the command center through the emergency APP, skipping the intermediate level. The first link deduction scheme TC1 for the emergency response initiation link: the system automatically matches the emergency plan according to the accident type and pushes it to the project manager's terminal; the second link deduction scheme TC2: the project manager manually starts the plan after discussing in the meeting. The first link deduction scheme TD1 for the emergency team response link: each team performs fixed duties according to the plan, such as the medical team only responsible for treating the injured; the second link deduction scheme TD2: according to the real-time injury and death situation, temporarily assign the logistics team to support the medical team. The first link deduction scheme TE1 for the response completion link: the command center checks the completion of the plan item by item and declares the end; the second link deduction scheme TE2: the system automatically analyzes the on-site data such as injury and death clearance and hidden danger elimination, and generates an end suggestion.

[0049] Taking the link deduction scheme TA1 and TB2 as examples, the information sources of TA1 include: a scaffold inclination sensor, a vibration monitoring device, and a structure safety evaluation system log. The inclination angle is collected in JSON format by the sensor, the vibration amplitude is collected in binary stream by the vibration monitoring device, and the historical maintenance data is collected in CSV table by the system log. The data collected by all information sources constitute the data set of TA1. The information sources of TB2 include: a worker's mobile phone APP, a field emergency button trigger signal, and a command center receiving record. The GPS positioning and the worker's text description of the emergency accident scene are collected by the worker's mobile phone APP, the trigger signal is an HTTP request message, and the receiving record contains a database entry. The data collected by all information sources constitute the data set of TB2.

[0050] It should be noted that the types and quantities of data contained in different data sets are not necessarily completely the same; the order of emergency links in different emergency simulation schemes is the same.

[0051] Step S2: According to the differences in data types, simulation time length, and the differences between the simulation time length and the ideal time length of each data set and the rest of the data sets, the time delay significance of each data set is obtained.

[0052] Although the emergency simulation schemes are consistent in the structure and order of emergency links, the link simulation content planned for the same emergency link in different emergency simulation schemes is not completely consistent, which causes differences in the multi-source heterogeneous data involved in the link simulation content, leading to the formation of multiple data sets for the same emergency link, i.e., multiple data sets corresponding to each emergency link. Due to the different degrees of inconsistency in data structure between these multi-source heterogeneous data in the data sets, there are different degrees of repulsion effects between the data in the data sets, which causes different degrees of time delay effects after the fusion of the data in the data sets, and further causes errors in the simulation time length of each emergency simulation scheme listed by the operator.

[0053] In order to effectively intervene and control the time delay effect caused by multi-source heterogeneous data conflict, it is necessary to analyze the degree of time delay effect caused by multi-source heterogeneous data conflict. The time delay effect is mainly reflected by the overall response time length of the emergency link. The difference between the simulation time length and the ideal time length of the data set directly presents the easily distinguishable degree of the time delay caused by data conflict in the link deduction scheme corresponding to the data set, and combined with the differences in data types and simulation time length between each data set and the rest of the data sets, the possibility of time delay effect caused by multi-source heterogeneous data conflict in the emergency link is analyzed in turn through the time synchronization and data diversity of the two, and whether the time delay is easily distinguished is comprehensively analyzed to obtain the time delay significance.

[0054] Step S3: obtaining a scheme conflict delay degree of each data set according to the time delay significance of the same data category and structure type generated by any two information sources of each data set; and obtaining a data fusion delay degree of each data set according to the difference between the time delay degree caused by data conflict in the data fusion process of the data in each data set and the scheme conflict delay degree.

[0055] The scheme content of each link deduction scheme is composed of a text description, which has a clear semantic expression, but the computer cannot recognize the semantic information expressed by the scheme content. Therefore, in the actual environment, the knowledge graph technology is usually used to assign the corresponding relationship between entities to the multi-source heterogeneous data, to upgrade the "data simulation" to "cognitive simulation", and to assign the computer the function of converting data and semantics to each other, so that the multi-source heterogeneous data forms a corresponding data relationship in the knowledge graph.

[0056] The time delay significance reflects the delay effect of the data conflict of the internal multi-source information when the link deduction scheme is implemented, and does not consider the detailed performance of the multi-source heterogeneous data after the mapping transformation. In the actual environment, the same semantic expression can be jointly expressed by different information source data, but there is a certain gap between these information source data in terms of structure type, etc., thereby forming different conflict states.

[0057] After the data set corresponding to the link deduction scheme is mapped by the graph, the data in the set will be allocated to the logical flow steps, i.e. nodes, to realize data fusion in the data set. According to the difference between the flow conflict delay degree and the scheme conflict delay degree of each node in the deduction scheme graph, the obvious degree of the time delay effect of the node compared to other nodes corresponding to the flow step is presented, the influence of the delay effect caused by the original data conflict on the result after fusion is determined, and the data fusion delay degree is obtained.

[0058] Step S4: obtaining a conflict delay attenuation degree of the corresponding data set according to the data fusion delay degree of each data set of each emergency link and the simulation time length of the data set of the subsequent emergency link; and adjusting the simulation time length of the data set by using the conflict delay attenuation degree to obtain a simulation correction time length.

[0059] When a simulation scenario for any emergency response link is selected and run on a virtual platform, that link will be connected to other links, driving the overall progress of the emergency process. If data conflicts cause significant delays in the simulation of that link, this will interfere with the response timeline of subsequent emergency response links, leading to data conflicts in the data sets used by subsequent emergency response links. For example, if an accident occurs during normal working hours, if data conflicts cause delays in the information reporting phase, causing the accident report to be delayed until after get off work hours, when some response teams are already off-duty, the efficiency of handling the emergency incident will be significantly reduced compared to during working hours, further impacting the progress of subsequent emergency response links. Therefore, it is necessary to analyze the impact of the data set on subsequent emergency response links based on the degree of delay, namely the data fusion delay, and determine the data set's conflict delay attenuation. Using the conflict delay attenuation to adjust the simulation duration of the data set can maximize the authenticity of the overall emergency response process and effectively reduce the impact of delays on the simulation duration, thereby improving the reliability of the simulation duration.

[0060] Preferably, in some possible implementation methods of the embodiments of the present invention, the method for obtaining delay significance includes: recording the difference between the simulation duration of the data set and the ideal duration as the delay discrimination; averaging the difference between the simulation duration of each data set in the emergency link and the remaining data sets to obtain the deduction efficiency difference of each data set; recording the average of the difference between the number of types of data in each data set in the emergency link and the remaining data sets as the heterogeneous prominence of each data set; and obtaining the delay significance of each data set in the emergency link based on the delay discrimination, the deduction efficiency difference and the heterogeneous prominence.

[0061] It should be noted that if the difference in deduction efficiency and the heterogeneous prominence are greater, it means that the time synchronization between each data set in the emergency link and the other data sets is worse, and the data diversity in each data set is significantly higher than that of the other sets. In this case, the possibility of the existence of a time delay effect due to the conflict of multi-source heterogeneous data in the emergency link is greater, that is, the simulation time consumed by the emergency link is more likely to be mixed with the time delay effect.

[0062] Generally, the multi-source heterogeneous data conflict with each other and the time delay usually occupies a relatively short time length. In the case that the simulation time length of the emergency link is far less than the ideal time length, that is, the time delay degree is smaller, the characteristics of the time delay effect are more easily submerged, and the time delay effect is more difficult to be distinguished. If the deduction efficiency difference and the heterogeneity prominence are greater, it indicates that the time synchronization of each data set of the emergency link and the remaining data sets is poorer, and the data diversity in each data set is significantly higher than that in the remaining sets. Therefore, the possibility of the time delay effect caused by the multi-source heterogeneous data conflict in the emergency link is greater, that is, the simulation time length consumed by the emergency link is more likely to be mixed with the time delay effect. In the case that the simulation time length consumed by the emergency link is mixed with the time delay effect, the greater the time delay degree is, the more difficult the characteristics of the time delay effect are to be submerged in the simulation time length of the emergency link, and the time delay is more easily distinguished. Therefore, the time delay degree, the deduction efficiency difference and the heterogeneity prominence are all positively correlated with the time delay prominence. In the embodiment of the present application, the product of the time delay degree, the deduction efficiency difference and the heterogeneity prominence of each data set is normalized to obtain the time delay prominence.

[0063] It should be noted that in the embodiment of the present application, the maximum and minimum normalization is used for normalization processing, and other normalization methods such as Sigmoid function and function conversion can also be selected, which are not limited herein.

[0064] Preferably, in some possible implementation manners of the embodiment of the present application, the method for obtaining the scheme conflict delay degree comprises: calculating the maximum value of the number of data types of all information sources in the data set, taking the maximum value as the denominator and the number of data types of the same structure between any two information sources in the data set as the numerator to obtain the structure conflict degree between the two information sources; summing the structure conflict degrees between all information sources in the data set to obtain the structure overall conflict degree; and obtaining the scheme conflict delay degree of the data set according to the time delay prominence and the structure overall conflict degree.

[0065] It should be noted that, if the structure conflict degree is smaller, that is, the number of data types with the same structure type between the two information sources is larger, the correlation degree of the data generated by the two information sources on the data structure is larger, the possibility of being two independent information sources is larger, the conflict strength between the data from the two information sources is weaker, and the time delay effect caused by the data conflict of the data set corresponding link deduction scheme in the simulation deduction is less obvious. If the time delay salience is larger, it indicates that the time delay effect in the actual simulation time length of the emergency link is easier to be distinguished, and the time delay effect caused by the data conflict is more obvious. Therefore, the time delay salience and the structure overall conflict degree are positively correlated with the scheme conflict delay degree. In the embodiment of the present application, the product of the time delay salience and the structure overall conflict degree of the data set is normalized to obtain the scheme conflict delay degree.

[0066] It should be noted that, in the embodiment of the present application, the maximum minimum normalization is used for normalization processing, and normalization methods such as Sigmoid function and function conversion can also be selected, which are not limited here.

[0067] As an example, assuming that the data set is (a, b, c, d), the data a comes from the information source A and the structure type is JSON, the data b comes from the information source A and the structure type is CSV, the data c comes from the information source B and the structure type is CSV, and the data d comes from the information source B and the structure type is Extensible Markup Language (XML), there is only the same CSV structure type in the data from the information sources A and B, and the number of data types with the same structure type between the information sources A and B is 1.

[0068] Preferably, in some possible implementation manners of the embodiment of the present application, the acquisition method of the data fusion delay degree can refer to Figure 2 which shows a flowchart of a data fusion delay degree acquisition method provided by an embodiment of the present application, and the method comprises the following steps:

[0069] Step S310: extracting entities from the data set corresponding link deduction scheme, defining relationships of the entities, and generating a directed graph, denoted as a deduction scheme graph; assigning the data in the data set to the nodes in the deduction scheme graph, and acquiring the flow conflict delay degree of each node in the deduction scheme graph.

[0070] It should be noted that the embodiment uses natural language processing (NLP) tools such as Spacy, BERT, etc. to extract entities from the link deduction scheme text, generates relationships between entities through the Drools rule engine, and can also generate relationships through artificial annotation methods defined by domain experts, such as machine learning using the TransE model. The entity is directly mapped to the node. Since the entity relationship in the emergency link has directionality, the deduction scheme graph is a directed graph.

[0071] In an embodiment of the application, the method of assigning data in the data set to the nodes in the deduction scheme graph is to match the data in the data set with the input requirements of the nodes in the deduction scheme graph through pre-defined semantic rules such as production rules, and if the matching is successful, the data is assigned to the node.

[0072] In another embodiment of the application, a bidirectional encoder representation from a transformer is used to train a classification model to predict the node in the deduction scheme graph to which the data in the data set belongs. Specifically, a neural network model is used to analyze the data in the data set and output the probability of the node in the deduction scheme graph to which it belongs. If the probability exceeds a threshold, the data is assigned to the node.

[0073] In other embodiments of the application, the data in the data set is pushed to the currently active node in the deduction scheme graph according to the context state of the dynamic workflow engine such as Camunda.

[0074] It should be noted that the process conflict delay degree is the scheme conflict delay degree of each node in the deduction scheme graph corresponding to the data set. The scheme conflict delay degree is obtained in the same way as the data set, except that when analyzing the time delay significance, each data set of the emergency link is replaced by each node corresponding set of the data set corresponding deduction scheme graph and the rest of the node corresponding set.

[0075] Step S320: According to the difference between the process conflict delay degree and the scheme conflict delay degree of the node in the deduction scheme graph corresponding to the data set, and the number of data categories corresponding to the node, the data fusion delay degree of the data set is obtained.

[0076] In an embodiment of the application, the data fusion delay degree is obtained by calculating the absolute value of the difference between the process conflict delay degree and the scheme conflict delay degree of each node in the deduction scheme graph corresponding to the data set, and the number of data categories corresponding to each node. The average of all products is obtained, and the data fusion delay degree of the data set is obtained.

[0077] It should be noted that the greater the difference between the process conflict delay degree of each node in the deduction scheme graph and the scheme conflict delay degree, the more obvious the time delay effect of the corresponding process step of the node compared to other nodes, so that the influence of the delay effect caused by the original data conflict on the fused result is greater after the data set is fused using the knowledge graph.

[0078] Preferably, in some possible implementation manners of the embodiment of the present application, the acquisition method of the conflict delay attenuation degree comprises: taking the sum of the simulation time lengths of all data sets of all emergency links after each emergency link as the deduction continuous influence degree of each emergency link; and performing negative correlation and normalization processing on the product of the time delay differentiation degree, the data fusion delay degree and the deduction continuous influence degree of each data set of each emergency link to obtain the conflict delay attenuation degree of the corresponding data set.

[0079] It should be noted that the greater the deduction continuous influence degree, the more complex the deduction progress of the link after each emergency link, and the more serious the continuous influence of the delay effect of the emergency link on the subsequent overall deduction progress; the greater the data fusion degree of the data set, the greater the influence of the delay effect caused by the original data conflict on the fused result after the data set is fused using the knowledge graph; the greater the time delay differentiation degree, the more likely it is to have a time delay effect in the simulation time length consumed by the emergency link, and the greater the influence of the time delay effect. The greater the conflict delay attenuation degree of the data set, the stronger the attenuation of the delay effect caused by the data conflict during the simulation of the data set, and the weaker the interference on the subsequent emergency process. Therefore, the time delay differentiation degree, the data fusion delay degree and the deduction continuous influence degree are negatively correlated with the conflict delay attenuation degree.

[0080] In this embodiment, the to-be-tested data is taken as the index of an exponential function with a natural constant as the base, so as to perform negative correlation and normalization processing on the to-be-tested data.

[0081] Preferably, in some possible implementation manners of the embodiment of the present application, the acquisition method of the simulation correction time length comprises: for each data set of each emergency link, weighting the simulation time length of the data set by using the difference between a constant and the conflict delay attenuation degree of the data set to obtain the simulation correction time length of the data set.

[0082] It should be noted that the greater the conflict delay attenuation degree of the data set, the stronger the delay effect of the data conflict exists in the simulation simulation, and the weaker the interference degree of the emergency link, so that the original time length redundancy does not need to be reserved, and should be shortened to reflect the actual efficient processing, so that the simulation correction time is shorter.

[0083] In the embodiment of the application, the minimum value of the simulation correction time of the data set of each emergency link deduction scheme from each emergency link deduction scheme of the emergency simulation scheme corresponds to the link deduction scheme, and the link deduction scheme is generated in text form to form a complete virtual simulation deduction reference scheme from the virtual platform, and the required processing time of the scheme is the shortest.

[0084] So far, the application is completed.

[0085] Embodiment 2:

[0086] The application also provides a computer device schematic diagram of the multi-source heterogeneous data driven emergency simulation deduction device, please refer to Figure 3 The computer device comprises a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502, wherein when the processor 502 executes the computer program 503, the computer device can execute any one of the multi-source heterogeneous data driven emergency simulation deduction methods introduced above.

[0087] In addition, the embodiment of the application also protects a device, which can comprise a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute the multi-source heterogeneous data driven emergency simulation deduction method provided by the embodiment of the application.

[0088] The embodiment can divide the device into functional modules according to the above method examples, for example, each functional module can be corresponding, or two or more functions can be integrated in one processing module, and the integrated module can be realized in the form of hardware. It should be noted that the division of modules in the embodiment is illustrative, and is only a logical function division, and another division mode can be used in actual implementation.

[0089] In the case of dividing each module corresponding to each function, the device can also comprise a communication module, a signal analysis module, a complexity analysis module, and a positioning module, etc. It should be noted that all related contents of each step involved in the above method embodiment can be referred to the function description of the corresponding functional module, and will not be repeated here.

[0090] It should be understood that the device provided in the embodiment is used to execute the above-mentioned multi-source heterogeneous data driven emergency simulation deduction method, and thus the same effects as the implementation method can be achieved.

[0091] In the case of using the integrated unit, the device can include a processing module and a storage module. When the device is applied to equipment, the processing module can be used to control and manage the actions of the equipment. The storage module can be used to support the equipment to execute mutual program codes and the like.

[0092] The processing module can be a processor or a controller, which can realize or execute various exemplary logical blocks, modules and circuits included in the disclosure. The processor can also be a combination of computing functions, such as one or more microprocessor combinations, a combination of digital signal processing (DSP) and microprocessor, and the like. The storage module can be a memory.

[0093] Embodiment 3:

[0094] The embodiment also provides a computer readable storage medium, which stores computer program codes. When the computer program codes run on a computer, the computer executes the above-mentioned related method steps to realize the multi-source heterogeneous data driven emergency simulation deduction method provided in the above-mentioned embodiment.

[0095] Embodiment 4:

[0096] The embodiment also provides a computer program product. When the computer program product runs on a computer, the computer executes the above-mentioned related steps to realize the multi-source heterogeneous data driven emergency simulation deduction method provided in the above-mentioned embodiment.

[0097] The device, the computer readable storage medium, the computer program product or the chip provided in the embodiment are used to execute the corresponding method provided above, and thus the beneficial effects achieved by the device, the computer readable storage medium, the computer program product or the chip can refer to the beneficial effects of the corresponding method provided above, which will not be described here.

[0098] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner. For example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0099] It should be noted that the progressive order of the above-mentioned embodiments of the application is only for the purpose of description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0100] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment mainly explains the difference from other embodiments.

Claims

1. A multi-source heterogeneous data-driven emergency simulation method, characterized in that: The method includes: Acquire a data set of simulation plans for different emergency links in an emergency simulation plan for an emergency accident, and perform simulation deduction on the simulation duration and ideal duration; the data set includes data from different information sources; Obtain the delay significance of each data set based on the data type differences and simulation duration differences between each data set and the rest of the data sets in the emergency phase, as well as the difference between the simulation duration and the ideal duration of each data set; Obtain the solution conflict delay of each data set based on the data types of the same structural type generated by any two information sources of each data set and the delay significance; obtain the data fusion delay of each data set based on the difference between the time delay degree caused by data conflict during data fusion of each data set and the solution conflict delay; Obtaining a conflict delay attenuation degree of the corresponding data set based on the data fusion delay of each data set of each emergency link and the simulation duration of the data set of the subsequent emergency link; and adjusting the simulation duration of the data set using the conflict delay attenuation degree to obtain a simulation correction duration; The obtaining of the delay significance of each data set includes: The difference between the simulated duration and the ideal duration of the data set is recorded as the delay discrimination; The difference in simulation time between each data set of the emergency phase and the rest of the data sets was averaged to obtain the difference in deduction efficiency of each data set; The mean of the difference between the number of types of data in each data set of the emergency link and the rest of the data sets is recorded as the heterogeneous prominence of each data set; Obtaining delay significance of each data set of the emergency link according to the delay differentiation, the deduction efficiency difference and the heterogeneous prominence; The obtaining of the solution conflict delay of each data set includes: The maximum value of the number of data types of all information sources in the data set is calculated, and the ratio of the maximum value and the number of data types with the same structural type between any two information sources in the data set is used as the numerator and the maximum value as the denominator to obtain the structural conflict degree between the corresponding two information sources; The sum of the structural conflict degrees between all information sources of the data set is recorded as the overall structural conflict degree; Obtaining a solution conflict delay degree of a data set according to the delay significance and the overall structural conflict degree; The obtaining of the data fusion delay of each data set includes: Obtain the deduction plan for each link of the data set; extract entities from the deduction plan for the corresponding link of the data set, define the relationship between the entities, and generate a directed graph, which is recorded as the deduction plan graph; assign the data in the data set to the nodes in the deduction plan graph, and obtain the process conflict delay degree of each node in the deduction plan graph; Obtaining the data fusion delay of the data set according to the difference between the process conflict delay and the solution conflict delay of the node in the deduction solution diagram corresponding to the data set, and the number of data types corresponding to the node; The method for obtaining the data fusion delay comprises: Calculate the product of the absolute value of the difference between the process conflict delay and the solution conflict delay of each node in the deduction solution diagram corresponding to the data set and the number of data types corresponding to each node, and average all products to obtain the data fusion delay of the data set; The method for obtaining the conflict delay attenuation degree includes: The cumulative sum of the simulation durations of all data sets of all emergency links after each emergency link is recorded as the deduced continuous impact of each emergency link; The product of the delay differentiation, the data fusion delay and the deduction continuous influence of each data set in each emergency link is negatively correlated and normalized to obtain the conflict delay attenuation of the corresponding data set.

2. The multi-source heterogeneous data-driven emergency simulation method according to claim 1 is characterized in that: The method for obtaining the simulation correction duration includes: For each data set of each emergency link, the simulation duration of the data set is weighted using the difference between the constant and the conflict delay attenuation of the data set to obtain the simulation corrected duration of the data set.

3. The multi-source heterogeneous data driven emergency simulation method according to claim 1 is characterized in that: The method for defining relationships between entities is the Drools rule engine.

4. The multi-source heterogeneous data driven emergency simulation method according to claim 1, characterized in that: The process conflict delay is the solution conflict delay of the set of data corresponding to each node in the deduction solution diagram.

5. The multi-source heterogeneous data driven emergency simulation method according to claim 1, characterized in that: There is a time sequence for different emergency links in the emergency simulation plan.

Images