Emergency management process modeling method based on big data

Abstract

The application discloses an emergency management process modeling method based on big data, and comprises the following steps: step one, data preprocessing; step two, process instance analysis and statistics; step three, abstracting process instances into process variants; step four, merging process variants into a process model PM; step five, extracting a value arc set VA; step six, constructing an emergency management process model EMPM; and step seven, forming a process model library. The application can not only process multi-source heterogeneous data to realize modeling of management processes, but also can configure emergency resources and establish a multi-agent-oriented emergency management process model library. The emergency management process model library is a collection of process models, the process models contain participants of activities and value arcs between the activities, and a perfect process model library is beneficial to helping enterprises better cope with emergencies.

Description

Technical Field

[0001] The present invention belongs to the technical field of safe production and emergency management, and relates to a processing flow modeling method for emergency management, and specifically to a method for constructing an emergency processing flow model based on big data with a chemical park as the core. Background Art

[0002] Emergency management refers to the activities of governments and other public institutions during the process of emergency prevention, response, disposal, and post-emergency recovery. These activities involve establishing necessary response mechanisms, implementing a series of necessary measures, and applying scientific, technological, planning, and management methods to protect public life, health, and property, and promote the harmonious and healthy development of society. Emergency management is a key task for the state and governments at all levels, and is crucial for national security and the protection of people's lives and property.

[0003] The emergency management platform based on the Internet of Things / sensor network can collect various types of data required for the project in real time and accurately from various equipment and terminal systems, such as harmful gas concentrations, heavy metal content in sewage, vehicle entry and exit, item status, warehouse information, etc., providing a reliable data source for subsequent technologies; big data technology can not only fuse and analyze multi-source heterogeneous data, but also be combined with emergency management business to realize the modeling of management processes. At the same time, combined with the latest process mining technology, it can realize real-time dynamic monitoring based on data and predict and warn of possible risks.

[0004] Process mining is a technique for extracting process knowledge from actual business execution data collected by information systems and extracting structured process models. This technology can be used to discover, monitor, and improve actual system behavior. The α algorithm is a milestone in process mining. It constructs a process model represented by a Petri net by identifying activities in the process and mining the four basic relationships in the logs: follow-up, concurrency, causality, and irrelevance. However, because the α algorithm cannot address noise and anomaly detection, researchers have proposed a series of new algorithms from different perspectives to address these issues, such as inductive mining algorithms and heuristic mining algorithms.

[0005] Although these algorithms have been widely used in practical analysis, considering the characteristics and needs of the emergency management field, it is necessary to expand the application scenarios of process mining technology and propose new mining algorithms that are suitable for emergency management. Summary of the Invention

[0006] Given the current frequent occurrence of accidents in the chemical industry, which have a significant impact, coupled with inadequate early warning and monitoring, and imperfect emergency response, how can big data technology be integrated with emergency management? This paper proposes a big data-based emergency management process modeling method for constructing an emergency management process model (EMPM) from the big data generated by the industrial park. Based on event logs collected by an IoT-based emergency management platform, this method not only mines business processes from historical emergency response event logs, but also describes the configuration of emergency resources during the process. On this basis, a multi-agent emergency management process model library is established.

[0007] The purpose of the present invention is achieved through the following technical solutions:

[0008] A big data-based emergency management process modeling method includes the following steps:

[0009] Step 1: Data preprocessing:

[0010] Clean, filter, and classify event data stored in the emergency management platform to obtain event log collection;

[0011] Step 2: Process instance analysis and statistics:

[0012] Take the process instance set of a classification subject S as a sample, analyze and count the process instances T in it, and obtain the set {(T1,n1),(T2,n2),...,(T k ,n k )}, where T i Is a specific process instance i, n i is the number of instances of the process. The specific steps are as follows:

[0013] Step 2.1: Take a set of process instances of a classification subject S as a sample, map the events of process instance T to corresponding activities a with the same name, and mine the activity sequence relationship and parallel relationship based on the temporal relationship to determine the activities a and their relationships contained in process instance T;

[0014] Step 2: Merge the process instances T containing the same activity a and its relationship, count the number of identical instances, and obtain the set {(T1,n1),(T2,n2),...,(T k ,n k )};

[0015] Step 3: Abstract the process instance into a process variant:

[0016] Determine the process instance set {T1, T2, ..., T k}, merge the process instances T with the same cyclic relationship, and abstract the process instance set into a process variant set {VI1, VI2, ..., VI p};

[0017] Step 4: Merge process variants into process model PM:

[0018] For the variant set {VI1,VI2,...,VI p The process variants in} are merged in pairs in turn to determine the selection relationship of the variants, thereby obtaining a complete process model PM. The specific steps are as follows:

[0019] Step 4.1: For the variant set {VI1, VI2, ..., VI p The process variants in} are merged in pairs in turn, integrating and retaining the same parts of the two variants, while the different parts exist in the form of selection relationships, and the process variants with selection relationships are merged;

[0020] Step 42: Extract all non-repeated events, activities, and gateways from the original process variant. The gateways are identified based on the elements they are connected to.

[0021] Step 43: Traverse each edge (head, tail) in all original process variants and add them to the new process model without duplication. Due to the different parts between variants, there may be a non-gateway element with multiple outgoing edges in the new process model. It is necessary to add a selection gateway for this element, replace the head in all outgoing edges of this element with the selection gateway, delete all outgoing edges of this element, and finally add an edge from this element to the selection gateway to obtain the complete process model PM;

[0022] Step 5: Extract the value arc set VA:

[0023] Based on each activity in the activity set obtained in step 2, extract the corresponding participant ar and input value v from the corresponding event E in and output value v out , thereby obtaining the value arc set VA, the specific steps are as follows:

[0024] Step 5.1: Based on the activity a obtained in step 2, extract the corresponding participant ar from the corresponding event E, and extract the input value v of ar participating in activity a from the set of attributes and values ​​of event E attrVal. in and output value v out , thus determining the value arc va=(a,ar,v in ,v out );

[0025] Step 52: Perform the operation of step 51 for each activity to obtain the value arc set VA;

[0026] Step 6: Build the emergency management process model EMPM:

[0027] Mark each value arc in the value arc set VA to the corresponding activity a in the process model PM i On the basis of the above, the emergency management process model EMPM is established. The specific steps are as follows:

[0028] Step 6.1 If the value arc (a i ,ar j ,v in ,v out ) Activity a i and activity a in the process model PM i If they are the same, then mark the value arc to the corresponding activity a in the process model PM i superior;

[0029] Step 62: Repeat step 61 to establish the emergency management process model EMPM = (A, Actor, VA, Edge, GXOR, GAND, start, end), where: A is the set of service activities; Edge = {(head, tail)} is the set of sequence flows, head∈{A, GXOR, GAND, start}, tail∈{A, GXOR, GAND, end}; GXOR and GAND represent exclusive and parallel gateways respectively; start and end represent the start event and end event of the process respectively; Actor is the set of participants in the service process model; VA is the set of value arcs between A and Actor;

[0030] Step 7: Form a process model library:

[0031] The emergency management process model EMPM of the classification subject S is added to the process model library; steps 2 to 6 are repeated for the process instance set of each classification subject, and the emergency management process model corresponding to each classification entity is added to the process model library, thereby obtaining a complete process model library.

[0032] Compared with the prior art, the present invention has the following advantages:

[0033] 1. Based on the characteristics of process data in the chemical park emergency management platform, this paper proposes a big data emergency management process modeling method. This method not only processes multi-source heterogeneous data to achieve management process modeling, but also configures emergency resources and establishes a multi-agent emergency management process model library. The emergency management process model library is a collection of process models that include the participants in the activities and the value arcs between activities. A complete process model library helps enterprises better respond to emergencies.

[0034] 2. When analyzing the sequential relationship between events, the present invention proposes the concept of "process variants", explores the sequential, cyclic and parallel relationships, and abstracts them into process variants, making it easier to observe the sequential steps of each branch process.

[0035] 3. This invention uses event logs generated by the actual execution of service processes in the chemical park information system to automatically construct emergency management processes, avoiding the delays associated with manually constructing emergency processes. It also helps companies understand their business processes and describe the allocation of emergency resources during the process, helping them better respond to emergencies and reduce losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 Handle examples for circular relationships in process instances;

[0037] Figure 2 The process of merging process variants into a process model;

[0038] Figure 3 To abstract the process instance into a process entity, (a) false alarm, (b) small leakage, (c) large leakage - SO2 pipeline leakage, (d) large leakage - cylinder leakage (leak plugging failure);

[0039] Figure 4 This is the process model after the merger;

[0040] Figure 5 It is a complete emergency management process model. DETAILED DESCRIPTION

[0041] The technical solution of the present invention is further described below with reference to the accompanying drawings, but is not limited thereto. Any modification or equivalent replacement of the technical solution of the present invention that does not depart from the spirit and scope of the technical solution of the present invention should be included in the scope of protection of the present invention.

[0042] In order to more clearly illustrate the specific implementation method of the present invention, some related concepts are first described:

[0043] A large number of event logs are collected in the IoT-based emergency management platform, which include traces of executed emergency handling process instances. Trace consists of a series of events that occur in time sequence.

[0044] Event E is the basic element of Trace, represented by E s / E c =(eName, t, actor, attrVal), where: 1) E s and E c Represents different life cycle states of the same event E. Each event has two states: start and end. s Indicates the starting state of event E, E c Indicates the end state of event E, E s and E c 1) eName, t, actor, and attrVal are all the same; 2) eName is the name of event E, which can be represented by E(eName); 3) t is the timestamp of event E, indicating the time when the event occurred; 4) actor is the person, organization, or automation resource involved in event E. An actor can be represented as actor = {service provider, partner, customer, automation resource}, where an automation resource can be an external entity such as a sensor or software system. 5) attrVal = {(attr1,val1),...,(attr n ,val n )} is a collection of attributes and values ​​of event E, attr i is the i-th attribute of event E, val i Is the attribute attr i The value of .

[0045] An emergency response process instance T consists of a series of events arranged in chronological order, which can be expressed as T(tName)= <E(1) (s / c) ,E(2) (s / c) ,...,E(m) (s / c) >, where: 1) tName is the unique identifier of the process instance T; 2) E(i) is the i-th event in the process instance T.

[0046] A value arc represents the flow of value between an activity and a participant. When an activity is performed by a participant, there is a value arc between them, represented by va = (a, ar, v in ,v out ), where: 1) a is an activity; 2) ar is the actor that performs a; 3) v in is the value or cost entered into when AR participates in activity a; 4) vout It is the output value obtained after ar completes activity a.

[0047] The emergency management process model EMPM is a value-oriented business process BPMN model, defined as EMPM = (A, Actor, VA, Edge, GXOR, GAND, start, end), where: 1) A is a set of service activities; 2) Edge = {(head, tail)} is a set of sequence flows, where (head, tail) represents the sequence flow from head to tail, head∈{A, GXOR, GAND, start}, tail∈{A, GXOR, GAND, end}; 3) GXOR and GAND represent exclusive and parallel gateways, respectively; 4) start and end represent the start event and end event of the process, respectively; 5) Actor is a set of participants in the service process model; 6) VA is a set of value arcs between A and Actor.

[0048] The big data-based emergency management process modeling method provided by this invention is based on the chemical park environment and various event log data collected by various devices and terminal systems of the Internet of Things emergency management platform. After analyzing and statistically analyzing process instances, it abstracts them into process variants, merges the process variants into a process model, extracts valuable information from the data, and then constructs an emergency management process model. This is repeated for each set of process instances of the classification subject to establish a process model library. The specific implementation steps are as follows:

[0049] (1) Data preprocessing. The event data stored in the emergency management platform is cleaned, filtered, and classified to obtain the event log set. The cleaning operation mainly removes the non-time series data in the data, which cannot be used for model construction; the filtering operation includes noise filtering, incomplete process filtering, etc., to remove interference items; the classification operation uses the subject (sensor / device) that triggers the process as the classification basis, and the different time series events triggered by all events of a subject form the process instance set of the subject.

[0050] (2) Process instance analysis and statistics. Take the process instance set of a classification subject S as a sample, map the events of the process instance T to the corresponding activities with the same name, and mine the activity sequence relationship and parallel relationship based on the temporal relationship to determine the activities and their relationships contained in the process instance T; merge the process instances with the same activities and relationships, and count the number of the same instances to obtain the set {(T1,n1),(T2,n2),...,(T k ,n k )}, where T i Is a specific process instance i, n i is the number of instances of the process.

[0051] (3) Abstract the process instance into a process variant. Determine the process instance set {T1, T2, ..., T k}, that is, there is a set of repeated activities in the activity sequence of a process, such as<A(1),...,A(2),A(1)′,...> , then A(1) and A(2) are in a cyclic relationship, which means that after completing A(2), A(1) is executed repeatedly. The process instances with the same cyclic relationship are merged, so that the process instance set can be abstracted into a process variant set {VI1, VI2, ..., VI p}. The processing of circular relations is as follows Figure 1 shown.

[0052] (4) Merge process variants into process model PM. p The process variants in} are merged in pairs, integrating and retaining the same parts of the two variants, while the different parts exist in the form of selection relationships, that is, the same activities a in the two process instances s After completion, there are multiple different subsequent activities connected to it, which can be expressed as ×[(a s ,a i ),(a s ,a j ),...], merge the process variants with selection relationships; then the process model mainly includes four elements: events, activities, gateways and edges. First, extract all non-repeated events, activities and gateways in the original process model, and identify the gateways according to the elements they are connected to. Then, traverse each edge (head, tail) in all the original process models and add them to the new process model without duplication. Since there are different parts between variants, there may be a situation in the new process model where a non-gateway element has multiple outgoing edges. It is necessary to add a selection gateway for the element: replace the head in all outgoing edges of the element with a selection gateway, delete all outgoing edges of the element, and finally add an edge from the element to the selection gateway to obtain a complete process model PM. The process of merging variants into a process model is as follows: Figure 2 shown.

[0053] (5) Extract the value arc set VA. Based on the activity a obtained in step (2), extract the corresponding participant ar from the corresponding event E, and extract the input value v of ar participating in activity a from the set of attributes and values ​​of event E attrVal in and output value v out , thus determining the value arc va=(a,ar,v in ,v out). Perform the above operation for each activity to obtain the value arc set VA.

[0054] (6) Construct the emergency management process model EMPM. If the value arc (a i ,ar j ,v in ,v out ) Activity a i and activity a in the process model PM i If they are the same, then the value arc can be annotated to the corresponding activity a in the process model PM i By repeating the above process, the emergency management process model EMPM can be established.

[0055] (7) Form a process model library. Add the emergency management process model EMPM of the classification subject S to the process model library; repeat steps (2) to (6) for each process instance set of the classification subject, and add the emergency management process model corresponding to each classification entity to the process model library, thereby obtaining a complete process model library.

[0056] In the above steps, (3), (4) and (5) are executed in parallel.

[0057] The execution process algorithm of the entire method is described as follows:

[0058]

[0059] Example:

[0060] This example uses monitoring data from a chemical park's emergency management platform as a sample. Since the platform stores tens of millions of data points, data preprocessing is not the focus of this invention. Instead, we use the data set from a classification entity's emergency process as an example to verify the subsequent steps of this invention. The data sample is shown below:

[0061]

[0062]

[0063]

[0064]

[0065]

[0066] The emergency response process for sulfur dioxide begins with an alarm indicating abnormal sulfur dioxide concentration. On-duty personnel check to see if it's a false alarm. If so, the alarm is deactivated, ending the process. If not, the incident is immediately identified and the leak's location confirmed. The system then activates the emergency plan. Commanders then organize emergency personnel and allocate resources.

[0067] If the concentration indicates a small leak, the ventilation duct will be accelerated, and the operator will use a hose to capture the leak and transfer it to the supply tower. After the incident is handled, the results will be reported and the process will end.

[0068] If the concentration indicates a large leak, and the leak is located in a pipeline, the operator and the lead operator will initiate an emergency stop. The lead operator will then use specialized bamboo or wooden sticks to plug the leak and report it by phone to the team leader and workshop director. The lead operator and operator will evacuate to a safe location. Once the team leader and workshop director arrive on scene, they will organize a rescue operation. After the incident is resolved, a personnel count will be conducted and the results will be reported, ending the process.

[0069] If the concentration indicates a large leak and the leak originates from a cylinder, the operator and the lead operator initiate an emergency shutdown. The lead operator then uses a special bamboo or wooden stick to plug the leak and calls the team leader and workshop director. The lead operator and operator evacuate to a safe location. Once the team leader and workshop director arrive on scene, they organize a rescue operation. The cylinder is then immersed in an alkaline solution until the pH level in the sedimentation tank passes the test. After the incident is resolved, a personnel count is conducted, and the results are reported, concluding the process.

[0070] The detailed steps are as follows:

[0071] Step 1: Clean, filter, and classify the raw data to obtain the event log collection log.

[0072] Step 2: Parse and count process instances. Using a set of process instances from a classification entity S as a sample, map the events of process instance T to corresponding activities with the same name. Mining the sequential and parallel relationships contained in process instance T. Merge process instances with the same activities and relationships, and count the number of identical instances.

[0073] Step 3: Abstract the process instance into a process variant. Find the cyclic relationship in the process instance set and merge the process instances with the same cyclic relationship, and then extract the process variant set from the process instance. The extracted process variants are as follows: Figure 3 shown.

[0074] Step 4: Merge the process variants into a process model. Merge the process variants extracted in step 3 in pairs, retaining the same parts of the two variants and adding selection gateways to the different parts. The merged process model is as follows: Figure 4 shown.

[0075] Step 5: Extract the value arc set. Extract the participants in the event and extract the input value and output value from them to obtain the value arc.

[0076] Step 6: Obtain the emergency management process model. Mark the value arc extracted in step 5 on the process model obtained in step 4, and repeat the above process to obtain a complete emergency management process model as shown below: Figure 5 shown.

[0077] Step 7: Form a process model library. Repeat steps 2 to 6 for each classification subject to obtain a process model and add it to the model library to complete the construction of the complete model library.

Claims

1. A big data-based emergency management process modeling method, characterized by The method comprises the following steps: Step 1: Data preprocessing: Clean, filter, and classify event data stored in the emergency management platform to obtain event log collection; Step 2: Process instance analysis and statistics: Take the process instance set of a classification subject S as a sample, analyze and count the process instances T in it, and obtain the set {(T1,n1),(T2,n2),...,(T k ,n k )}, where T i Is a specific process instance i, n i is the number of instances of the process; Step 3: Abstract the process instance into a process variant: Determine the process instance set {T1, T2, ..., T k }, merge the process instances T with the same cyclic relationship, and abstract the process instance set into a process variant set {VI1, VI2, ..., VI p }; Step 4: Merge process variants into process model PM: For the variant set {VI1,VI2,...,VI p The process variants in} are merged in pairs in turn to determine the selection relationship of the variants, thereby obtaining a complete process model PM. The specific steps are as follows: Step 4.1: For the variant set {VI1, VI2, ..., VI p The process variants in} are merged in pairs in turn, integrating and retaining the same parts of the two variants, while the different parts exist in the form of selection relationships, and the process variants with selection relationships are merged; Step 42: Extract all non-repeated events, activities, and gateways from the original process variant. The gateways are identified based on the elements they are connected to. Step 43: Traverse each edge (head, tail) in all original process variants and add them to the new process model without duplication. Due to the different parts between variants, there may be a non-gateway element with multiple outgoing edges in the new process model. It is necessary to add a selection gateway for this element, replace the head in all outgoing edges of this element with the selection gateway, delete all outgoing edges of this element, and finally add an edge from this element to the selection gateway to obtain the complete process model PM; Step 5: Extract the value arc set VA: Based on each activity in the activity set obtained in step 2, extract the corresponding participant ar and input value v from the corresponding event E in and output value v out , thereby obtaining the value arc set VA; Step 6: Build the emergency management process model EMPM: Mark each value arc in the value arc set VA to the corresponding activity a in the process model PM i On the other hand, the emergency management process model EMPM is established; Step 7: Form a process model library: The emergency management process model EMPM of the classification subject S is added to the process model library; steps 2 to 6 are repeated for the process instance set of each classification subject, and the emergency management process model corresponding to each classification entity is added to the process model library, thereby obtaining a complete process model library.

2. The emergency management process modeling method based on big data according to claim 1 is characterized in that The specific steps of step 2 are as follows: Step 2.1: Take a set of process instances of a classification subject S as a sample, map the events of process instance T to corresponding activities a with the same name, and mine the activity sequence relationship and parallel relationship based on the temporal relationship to determine the activities a and their relationships contained in process instance T; Step 2: Merge the process instances T containing the same activity a and its relationship, count the number of identical instances, and obtain the set {(T1,n1),(T2,n2),...,(T k ,n k )}.

3. The emergency management process modeling method based on big data according to claim 1 is characterized in that The specific steps of step five are as follows: Step 5.1: Based on the activity a obtained in step 2, extract the corresponding participant ar from the corresponding event E, and extract the input value v of ar participating in activity a from the set of attributes and values ​​of event E attrVal. in and output value v out , thus determining the value arc va=(a,ar,v in ,v out ); Step 52: Perform the operation of step 51 for each activity to obtain the value arc set VA.

4. The emergency management process modeling method based on big data according to claim 1 is characterized in that The specific steps of step six are as follows: Step 6.1 If the value arc (a i ,ar j ,v in ,v out ) Activity a i and activity a in the process model PM i If they are the same, then mark the value arc to the corresponding activity a in the process model PM i superior; Step 62. Repeat step 61 to establish the emergency management process model EMPM = (A, Actor, VA, Edge, GXOR, GAND, start, end), where: A is the set of service activities; Edge = {(head, tail)} is the set of sequence flows, head∈{A, GXOR, GAND, start}, tail∈{A, GXOR, GAND, end}; GXOR and GAND represent exclusive and parallel gateways respectively; start and end represent the start event and end event of the process respectively; Actor is the set of participants in the service process model; VA is the set of value arcs between A and Actor.

Images