Abnormal event emergency scheduling method and device, equipment and storage medium

Abstract

The invention relates to the technical field of big data, in particular to an abnormal event emergency scheduling method, device and equipment and a storage medium, and the method comprises the steps: carrying out the statistics of feedback information related to an abnormal event, carrying out the feature extraction of the field feedback information, obtaining key elements of the abnormal event, and carrying out the emergency scheduling of the abnormal event based on the extracted key elements and a historical abnormal event data set. The target collaborative linkage scheme for the abnormal event is generated, the collaborative linkage efficiency in the face of the abnormal event is improved, finally, multi-department emergency collaborative linkage scheduling is performed on the abnormal event based on the target collaborative linkage scheme, the operation efficiency among the departments is improved, and the situation that in the prior art, in the face of the sudden abnormal event, the collaborative linkage efficiency is reduced is avoided. The reaction speed is slow; and the operation efficiency is low.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to an abnormal event emergency dispatch method, device, equipment and storage medium. Background Art

[0002] When an unexpected abnormal event occurs in a city, it is often necessary for multiple emergency rescue departments to work together to handle it. When faced with an abnormal event, it is generally handled according to the experience of on-site staff, decision-making by department leaders, expert consultation or pre-made emergency plans. In particular, when each department handles it based on past experience, there is no timely communication between departments, resulting in confusion in the command of each department and difficulty in effective execution, which further leads to a vicious development of the situation and is not conducive to the economic development of the city. It can be seen that the above-mentioned emergency handling methods all have the problems of slow response speed and low operating efficiency.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide an abnormal event emergency dispatch method, device, equipment and storage medium, aiming to solve the technical problems of slow response speed and low operating efficiency in the prior art when facing sudden abnormal events.

[0005] To achieve the above object, the present invention provides an abnormal event emergency dispatch method, the method comprising the following steps:

[0006] Collect on-site feedback information of statistical abnormal events;

[0007] Extracting features from the on-site feedback information to obtain key elements of the abnormal event;

[0008] Generate a target collaborative linkage plan based on the key elements and historical abnormal event data sets;

[0009] Based on the target collaborative linkage plan, multi-department emergency collaborative linkage dispatch is carried out for the abnormal event.

[0010] Optionally, the extracting features of the on-site feedback information to obtain key elements of the abnormal event includes:

[0011] Integrate the on-site feedback information to obtain a description text of the abnormal event;

[0012] Perform feature extraction on the abnormal event description text by using a preset feature extraction model to obtain a full-factor feature representation matrix of the abnormal event;

[0013] Performing element mining on the full-element feature representation matrix to obtain a current status description set of the abnormal event, wherein the current status description set includes at least a number of abnormal events and key elements corresponding to each abnormal event;

[0014] Accordingly, the target collaborative linkage scheme is generated based on the key elements and the historical abnormal event data set, including:

[0015] Based on the current situation description set and the historical abnormal event data set, a target collaborative linkage plan is generated.

[0016] Optionally, the performing element mining on the full-element feature representation matrix to obtain a current status description set of the abnormal event further includes:

[0017] Performing factor mining on the full-factor feature representation matrix to obtain a candidate factor set;

[0018] Classifying the abnormal event description text by a preset classification model to obtain an abnormal event type set, wherein the abnormal event type set includes several types of abnormal events;

[0019] Key elements of various abnormal events are extracted from the candidate element set, and a current status description set of the abnormal events is constructed based on various abnormal events and the key elements corresponding to the abnormal events.

[0020] Optionally, generating a target collaborative linkage scheme based on the current status description set and the historical abnormal event data set includes:

[0021] Matching corresponding candidate solution sets from the historical abnormal event data set based on various abnormal events in the current state description set;

[0022] Calculating the similarity between the candidate element set of the abnormal event and each processing solution in the candidate solution set;

[0023] Determine a candidate processing solution according to the similarity calculation result, wherein the candidate processing solution is a processing solution in the candidate solution set that has the greatest similarity with the candidate element set of the abnormal event;

[0024] The candidate processing solutions are updated according to the on-site feedback information to obtain a target collaborative linkage solution.

[0025] Optionally, updating the candidate processing scheme according to the on-site feedback information to obtain a target collaborative linkage scheme includes:

[0026] Extracting on-site element information from the on-site feedback information;

[0027] The corresponding element information in the target collaborative linkage scheme is updated according to the on-site element information to obtain the target collaborative linkage scheme.

[0028] Optionally, before generating a target collaborative linkage solution based on the key elements and the historical abnormal event data set, the method further includes:

[0029] Obtain historical processing solutions, joint exercise records, and preset emergency plans corresponding to historical abnormal events;

[0030] Constructing a basic data set of an abnormal event collaborative linkage solution based on the historical processing solution, the joint exercise record and the preset emergency plan;

[0031] Based on the basic data set, a historical abnormal event data set is generated through a semi-supervised learning model.

[0032] Optionally, generating a historical abnormal event dataset based on a basic dataset through a semi-supervised learning model includes:

[0033] extracting a target data stream from the basic data set;

[0034] marking the target data stream;

[0035] The labeled target data stream is supplemented with data through a semi-supervised learning model to generate a historical abnormal event dataset.

[0036] In addition, to achieve the above-mentioned purpose, the present invention also proposes an abnormal event emergency dispatch device, the abnormal event emergency dispatch device comprising:

[0037] Statistics module, used for on-site feedback information of abnormal events;

[0038] An extraction module, used to extract features from the on-site feedback information to obtain key elements of the abnormal event;

[0039] A generation module, used to generate a target collaborative linkage plan based on the key elements and the historical abnormal event data set;

[0040] A scheduling module is used to perform multi-department emergency coordinated linkage scheduling for the abnormal event based on the target coordinated linkage plan.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes an abnormal event emergency dispatch device, which includes: a memory, a processor, and an abnormal event emergency dispatch program stored in the memory and executable on the processor, and the abnormal event emergency dispatch program is configured to implement the steps of the abnormal event emergency dispatch method described above.

[0042] In addition, to achieve the above objectives, the present invention also proposes a storage medium, on which an abnormal event emergency scheduling program is stored, and when the abnormal event emergency scheduling program is executed by a processor, the steps of the abnormal event emergency scheduling method described above are implemented.

[0043] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the abnormal event emergency dispatch method as described above are implemented.

[0044] One or more technical solutions proposed in the present application have at least the following technical effects: The present application discloses an emergency dispatch method for abnormal events, and the emergency dispatch method for abnormal events includes: counting on-site feedback information of abnormal events; performing feature extraction on the on-site feedback information to obtain key elements of the abnormal events; generating a target collaborative linkage scheme based on the key elements and historical abnormal event data sets; and performing multi-department emergency collaborative linkage dispatch on the abnormal events based on the target collaborative linkage scheme. Compared with the prior art, the present application counts feedback information related to abnormal events and performs feature extraction on the on-site feedback information to obtain key elements of abnormal events, and then generates a target collaborative linkage scheme for abnormal events based on the extracted key elements and historical abnormal event data sets, thereby improving the efficiency of collaborative linkage when facing abnormal events; finally, based on the target collaborative linkage scheme, performing multi-department emergency collaborative linkage dispatch on abnormal events, thereby improving the operating efficiency between departments and avoiding the technical problems of slow response speed and low operating efficiency in the prior art when facing sudden abnormal events. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 It is a flow chart of the first embodiment of the abnormal event emergency dispatch method of the present invention;

[0048] Figure 2 A schematic diagram of constructing a historical abnormal event data set in an embodiment of an abnormal event emergency dispatch method of the present invention;

[0049] Figure 3A schematic diagram of a multi-department collaborative business process of an embodiment of an abnormal event emergency dispatch method of the present invention;

[0050] Figure 4 It is a flow chart of the second embodiment of the abnormal event emergency dispatch method of the present invention;

[0051] Figure 5 It is a structural block diagram of the first embodiment of the abnormal event emergency dispatch device of the present invention.

[0052] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] Based on this, the embodiment of the present invention provides an abnormal event emergency dispatch method, referring to Figure 1 , Figure 1 The figure is a flow chart of a first embodiment of an abnormal event emergency dispatch method according to the present invention.

[0056] In this embodiment, the abnormal event emergency dispatch method includes:

[0057] Step S10: Collecting statistics on on-site feedback information of abnormal events.

[0058] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a terminal device, a server, etc. capable of realizing the above functions. The following takes the terminal device as an example to illustrate this embodiment and the following embodiments.

[0059] It should be noted that in response to sudden abnormal events such as natural disasters, accidents, public health incidents, social security incidents, etc., in order to ensure the rapid, orderly and effective implementation of emergency rescue operations, reduce accident losses, and achieve emergency coordination and linkage dispatch and command, there are usually the following methods to formulate emergency coordination and linkage plans: 1. Experience guidance method; 2. Leadership decision-making method; 3. Expert consultation method and 4. Prior formulation method.

[0060] Among them, the experience-based guidance method, leadership decision-making method or expert consultation method all rely on the experience of the handling personnel to decide what specific measures should be taken to deal with sudden abnormal events, and request relevant help in resources and personnel from surrounding areas and superior departments. However, since the experience-based guidance basically relies on the experience of emergency response personnel to formulate abnormal event coordination and linkage plans, the efficiency is extremely low and time-consuming when generating plans. Sometimes, in order to design a reasonable plan, emergency response personnel need to revise it repeatedly, which takes a long time. In addition, once a small number of special, highly professional, difficult, major, and sensitive events occur, they cannot rely on past experience. The coordination and linkage plans formulated based on experience are neither accurate nor rigorous. In addition, in highly urgent situations, emergency response personnel need to master a large amount of event-related professional knowledge and background knowledge, such as profession, geography, laws and regulations, and emergency resource deployment, in order to make correct decisions quickly on sudden abnormal events. This large amount of knowledge cannot be achieved by memory alone for emergency response personnel, and any decision has an optimal timing problem. Since emergency decision-making has more stringent time requirements, even if experts are dispatched to the scene for consultation at the first time, it will take a lot of time, resulting in the loss of the best time to solve sudden abnormal events. Due to the uncertainty of emergencies and the ever-changing on-site conditions, experts are generally experts in a certain area and cannot be experts in all aspects. Therefore, there are risks in relying too much on experts to develop emergency action plans.

[0061] The pre-planning method refers to formulating a corresponding set of abnormal event collaborative linkage plans in advance. When a sudden abnormal event occurs, a set of abnormal event collaborative linkage plans that match the current event is retrieved from the collaborative linkage plan data set based on the current event information.

[0062] This method has the following problems: the pre-made coordination and linkage plan for abnormal events cannot include all categories of abnormal emergencies. The situation at the scene of an emergency event is complex and changeable, and the dynamic information of environmental factors associated with the event is different. For a certain type of event, the pre-made coordination and linkage plan cannot take into account all dynamic factor information.

[0063] Based on this, this embodiment extracts the key elements of abnormal events through training models, and matches the key elements with the processing solutions in the historical abnormal event data set in the database, so as to obtain solutions that can solve abnormal events to the greatest extent and reduce the impact of abnormal events.

[0064] It can be understood that the on-site feedback information includes but is not limited to the collection of urban Internet of Things, feedback information from people at risk and disposal personnel at the scene, basic geographic information at the scene and data reported by the business systems of various departments, such as: real-time collection and preservation of on-site urban spatial element information, urban infrastructure information, urban social demographic information, urban climate environment and other information, feedback information from people at risk and disposal personnel at the scene, data reported by various subordinate departments, real-time messages from the network, etc. This embodiment does not impose specific restrictions on this.

[0065] Step S20: extracting features from the on-site feedback information to obtain key elements of the abnormal event.

[0066] It should be understood that feature extraction of on-site feedback information can eliminate some of the confusing and invalid information caused by abnormal events, and can also determine the key elements of abnormal events so as to provide a collaborative processing plan more quickly. For example, if a fire occurs in a certain place, the on-site feedback information may contain fire alarm records of the masses, inspection records of relevant departments, and urban monitoring records. At this time, the key elements of this information can be extracted, such as location, time, size of the fire, and whether there are dangerous goods, so as to quickly provide a collaborative processing plan later.

[0067] Step S30: Generate a target collaborative linkage plan based on the key elements and historical abnormal event data set.

[0068] It should be noted that the historical abnormal event data set refers to a data set stored in the database that records various abnormal events and corresponding processing solutions. The historical abnormal event data set includes various types of abnormal events that have occurred in the local history and the corresponding processing records, as well as various types of abnormal times and corresponding processing records currently disclosed, and drill records organized by various departments for various emergencies.

[0069] Furthermore, before generating a target collaborative linkage solution based on the key elements and the historical abnormal event data set, the method further includes:

[0070] Obtain historical processing solutions, joint exercise records, and preset emergency plans corresponding to historical abnormal events;

[0071] Constructing a basic data set of an abnormal event collaborative linkage solution based on the historical processing solution, the joint exercise record and the preset emergency plan;

[0072] Based on the basic data set, a historical abnormal event data set is generated through a semi-supervised learning model.

[0073] In the specific implementation, urban disaster potential threat assessment, urban facility disaster resistance capacity assessment, major hazardous source risk assessment, etc. are carried out for major urban safety assurance systems (such as lifeline systems, refuge passages, refuge spaces, etc.), as well as hazardous sources that pose a major threat to urban safety (such as nuclear power plants, dangerous factories, etc.). At the same time, various types of abnormal events that have occurred in the city (county) emergency departments over the years and the corresponding detailed historical disposal plan records are collected and sorted out, and detailed records of joint drills organized by various departments for various emergencies are compiled. Combined with the pre-released emergency plans for dealing with various emergencies, a basic data set for abnormal event collaborative linkage plans is constructed.

[0074] After the basic data set is generated, a historical abnormal event data set is established through a semi-supervised learning method. Further, the historical abnormal event data set is generated through a semi-supervised learning model based on the basic data set, including:

[0075] extracting a target data stream from the basic data set;

[0076] marking the target data stream;

[0077] The labeled target data stream is supplemented with data through a semi-supervised learning model to generate a historical abnormal event dataset.

[0078] In the specific implementation, refer to Figure 2 , select a small amount of data from the basic data set of the abnormal event collaborative linkage plan, perform manual annotation, and complete the description of the abnormal event type and related components of the annotated data set. For example: there are only abnormal events such as fire, earthquake, and waterlogging in the historical data, but because the above abnormal events will cause traffic jams, when extracting the elements of existing abnormal events, the traffic jam can be extracted and labeled as a new abnormal event, and the processing plan for the abnormal event corresponding to the traffic jam can be completed according to the existing processing plan, forming a new data stream, increasing the data volume, adapting to more scenarios, and enriching the historical abnormal event data set.

[0079] Step S40: Perform multi-department emergency coordinated linkage dispatch for the abnormal event based on the target coordinated linkage plan.

[0080] Understandably, reference Figure 3 When conducting multi-department emergency coordination and linkage dispatch, the time, location, rescue object, rescue route and other elements of the abnormal event can be pushed to the IOC early warning screen of the command center to provide decision-making support for the command center and help comprehensively coordinate the emergency coordination and linkage dispatch command of various departments, thereby realizing efficient and rapid departmental coordination and dispatch and reducing the impact of abnormal events.

[0081] This embodiment obtains the key elements of the abnormal events by counting the feedback information related to the abnormal events and extracting the features of the on-site feedback information. Then, based on the extracted key elements and the historical abnormal event data set, a target collaborative linkage plan for the abnormal events is generated to improve the efficiency of collaborative linkage when facing abnormal events. Finally, based on the target collaborative linkage plan, multi-department emergency collaborative linkage scheduling is carried out for the abnormal events to improve the operating efficiency among various departments, avoiding the technical problems of slow response speed and low operating efficiency when facing sudden abnormal events in the prior art.

[0082] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 4 , step S20, comprising:

[0083] Step S201: Integrate the on-site feedback information to obtain a description text of the abnormal event.

[0084] Step S202: extracting features from the abnormal event description text using a preset feature extraction model to obtain a full-factor feature representation matrix of the abnormal event.

[0085] Step S203: performing element mining on the full-element feature representation matrix to obtain a current status description set of the abnormal event, wherein the current status description set includes at least a number of abnormal events and key elements corresponding to each abnormal event.

[0086] It should be noted that integrating on-site feedback information means classifying it according to the source of information and integrating it into one file to form a description text of the abnormal event. The description text of the abnormal event can be updated in real time according to the on-site data, thereby reducing resource waste while solving abnormal events. For example, a traffic jam occurred in a certain place due to a vehicle collision. Because the collision vehicles were not removed in time, the scale of the traffic jam was large. As long as the collision vehicles were removed, the traffic would be quickly unblocked. If the traffic police department was dispatched to clear the traffic, a lot of human resources would be wasted.

[0087] The preset feature extraction model may be a feature extraction model based on a deep learning algorithm, such as a Transformer model, or may be other models that can achieve the same or similar functions, and this embodiment does not impose any specific restrictions on this.

[0088] Furthermore, the performing of element mining on the full-element feature representation matrix to obtain a current status description set of the abnormal event also includes:

[0089] Performing factor mining on the full-factor feature representation matrix to obtain a candidate factor set;

[0090] Classifying the abnormal event description text by a preset classification model to obtain an abnormal event type set, wherein the abnormal event type set includes several types of abnormal events;

[0091] Key elements of various abnormal events are extracted from the candidate element set, and a current status description set of the abnormal events is constructed based on various abnormal events and the key elements corresponding to the abnormal events.

[0092] The preset classification model may be a classification model based on a conditional random field, or may be other models that can achieve the same or similar functions, and this embodiment does not impose any specific restrictions on this.

[0093] Specifically, the Transformer model is used to extract features from the description text of abnormal events to form a feature representation matrix of all elements of abnormal events. The Conditional Random Fields (CRF) method is then used to mine the feature representation matrix to obtain the candidate feature set E = {e1, e2, e3, ..., e m}, and then use the classic normalized exponential function (SoftMax) classifier to classify the abnormal event description text, and obtain the current abnormal event type set I = {i1, i2, ...i n}, where i1 is the main abnormal event and the rest are secondary abnormal events.

[0094] For each abnormal event i∈I, the attention mechanism is used to extract the key elements of the abnormal event from the candidate element set E to form a current status description set of the abnormal event

[0095]

[0096] Accordingly, in this embodiment, step S30 includes:

[0097] Step S301: matching corresponding candidate solution sets from the historical abnormal event data set based on various abnormal events in the current state description set.

[0098] Step S302: Calculate the similarity between the candidate element set of the abnormal event and each processing solution in the candidate solution set.

[0099] Step S303: determining a candidate processing solution according to the similarity calculation result, wherein the candidate processing solution is a processing solution in the candidate solution set that has the greatest similarity with the candidate element set of the abnormal event.

[0100] Step S304: Update the candidate processing solutions according to the on-site feedback information to obtain a target collaborative linkage solution.

[0101] In the specific implementation, first, for each type of abnormal event s in the current situation description set S i , obtain the corresponding candidate solution set {A1,A2...A k}, then, through the BM25 algorithm, calculate the candidate solution set and the current event element set E i The most similar solution, the calculation formula for the similarity of abnormal events is:

[0102]

[0103] Among them, W e represents the weight of factor e, R(e,A k ) means E i Element e and candidate solution A k The relevance score of .

[0104] Further, the updating of the candidate processing scheme according to the on-site feedback information to obtain a target collaborative linkage scheme includes:

[0105] Extracting on-site element information from the on-site feedback information;

[0106] The corresponding element information in the target collaborative linkage scheme is updated according to the on-site element information to obtain the target collaborative linkage scheme.

[0107] Finally, the time, location, rescue object, rescue route and other factors of the current abnormal event are used to replace the most similar plan to form a collaborative linkage plan, and the main abnormal events and secondary abnormal events are merged to form a collaborative linkage plan for the final abnormal event. Combined with the business work processes of each department, integrated communication means are used to conduct urban emergency collaborative linkage dispatch and command.

[0108] This embodiment obtains an abnormal event description text by integrating the on-site feedback information; performs feature extraction on the abnormal event description text through a preset feature extraction model to obtain a full-factor feature representation matrix of the abnormal event; performs element mining on the full-factor feature representation matrix to obtain a current status description set of the abnormal event, wherein the current status description set includes at least a number of abnormal events and key elements corresponding to each abnormal event, and generates a target collaborative linkage plan based on the current status description set and the historical abnormal event data set, thereby generating a target collaborative linkage plan by extracting the full-factor identification matrix and the current status description set of the abnormal event, thereby improving the collaborative efficiency between departments.

[0109] This application also provides an abnormal event emergency dispatch device, please refer to Figure 5 , the abnormal event emergency dispatch device comprises:

[0110] The statistical module 10 is used for on-site feedback information of abnormal events.

[0111] The extraction module 20 is used to extract features from the on-site feedback information to obtain key elements of the abnormal event.

[0112] The generation module 30 is used to generate a target collaborative linkage solution based on the key elements and the historical abnormal event data set.

[0113] The scheduling module 40 is used to perform multi-department emergency coordinated linkage scheduling for the abnormal event based on the target coordinated linkage plan.

[0114] This embodiment obtains the key elements of the abnormal events by counting the feedback information related to the abnormal events and extracting the features of the on-site feedback information. Then, based on the extracted key elements and the historical abnormal event data set, a target collaborative linkage plan for the abnormal events is generated to improve the efficiency of collaborative linkage when facing abnormal events. Finally, based on the target collaborative linkage plan, multi-department emergency collaborative linkage scheduling is carried out for the abnormal events to improve the operating efficiency among various departments, avoiding the technical problems of slow response speed and low operating efficiency when facing sudden abnormal events in the prior art.

[0115] In one embodiment, the extraction module 20 is also used to integrate the on-site feedback information to obtain an abnormal event description text; perform feature extraction on the abnormal event description text through a preset feature extraction model to obtain a full-factor feature representation matrix of the abnormal event; perform element mining on the full-factor feature representation matrix to obtain a current status description set of the abnormal event, and the current status description set includes at least a number of abnormal events and key elements corresponding to each abnormal event; accordingly, generating a target collaborative linkage plan based on the key elements and historical abnormal event data sets includes: generating a target collaborative linkage plan based on the current status description set and the historical abnormal event data sets.

[0116] In one embodiment, the generation module 30 is further used to perform element mining on the full-element feature representation matrix to obtain a candidate element set; classify the abnormal event description text through a preset classification model to obtain an abnormal event type set, and the abnormal event type set includes several types of abnormal events; extract key elements of each type of abnormal event from the candidate element set, and construct a current status description set of the abnormal event based on each type of abnormal event and the key elements corresponding to each type of abnormal event.

[0117] In one embodiment, the generation module 30 is also used to match a corresponding set of candidate solutions from the historical abnormal event data set based on various types of abnormal events in the current state description set; calculate the similarity between the candidate element set of the abnormal event and each processing solution in the candidate solution set; determine the candidate processing solution based on the similarity calculation result, and the candidate processing solution is the processing solution in the candidate solution set with the greatest similarity to the candidate element set of the abnormal event; update the candidate processing solution according to the on-site feedback information to obtain a target collaborative linkage solution.

[0118] In one embodiment, the generating module 30 is further used to extract on-site element information from the on-site feedback information; and update the corresponding element information in the target collaborative linkage scheme according to the on-site element information to obtain the target collaborative linkage scheme.

[0119] In one embodiment, the generation module 30 is also used to obtain historical processing plans, joint drill records and preset emergency plans corresponding to historical abnormal events; construct a basic data set of abnormal event collaborative linkage plans based on the historical processing plans, the joint drill records and the preset emergency plans; and generate a historical abnormal event data set based on the basic data set through a semi-supervised learning model.

[0120] In one embodiment, the generation module 30 is further used to extract a target data stream from the basic data set; label the target data stream; and perform data completion on the labeled target data stream through a semi-supervised learning model to generate a historical abnormal event data set.

[0121] The present application provides an abnormal event emergency dispatch device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the abnormal event emergency dispatch method in the above-mentioned embodiment one.

[0122] The abnormal event emergency dispatch device provided by the present application adopts the abnormal event emergency dispatch method in the above embodiment, which can solve the technical problems of abnormal event emergency dispatch. Compared with the prior art, the beneficial effects of the abnormal event emergency dispatch device provided by the present application are the same as the beneficial effects of the abnormal event emergency dispatch method provided by the above embodiment, and the other technical features in the abnormal event emergency dispatch device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0123] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0124] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0125] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the abnormal event emergency dispatch method in the above-mentioned embodiment.

[0126] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0127] The computer-readable storage medium may be included in the abnormal event emergency dispatch device; or may exist independently without being assembled into the abnormal event emergency dispatch device.

[0128] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the abnormal event emergency dispatch device, the abnormal event emergency dispatch device performs: abnormal event emergency dispatch.

[0129] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0130] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0131] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0132] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned emergency dispatch method for abnormal events, and can solve the technical problems of emergency dispatch for abnormal events. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the emergency dispatch method for abnormal events provided by the above-mentioned embodiments, and will not be elaborated here.

[0133] The present application also provides a computer program product, including a computer program, which implements the steps of the abnormal event emergency dispatch method as described above when executed by a processor.

[0134] The computer program product provided by this application can solve the technical problem of emergency dispatch of abnormal events. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the emergency dispatch method of abnormal events provided by the above embodiment, which will not be repeated here.

[0135] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An abnormal event emergency dispatch method, characterized in that: The abnormal event emergency dispatch method comprises: Collect on-site feedback information of statistical abnormal events; Extracting features from the on-site feedback information to obtain key elements of the abnormal event; Generate a target collaborative linkage plan based on the key elements and historical abnormal event data sets; Based on the target collaborative linkage plan, multi-department emergency collaborative linkage dispatch is carried out for the abnormal event.

2. The method according to claim 1, characterized in that The feature extraction of the on-site feedback information to obtain key elements of the abnormal event includes: Integrate the on-site feedback information to obtain a description text of the abnormal event; Perform feature extraction on the abnormal event description text by using a preset feature extraction model to obtain a full-factor feature representation matrix of the abnormal event; Performing element mining on the full-element feature representation matrix to obtain a current status description set of the abnormal event, wherein the current status description set includes at least a number of abnormal events and key elements corresponding to each abnormal event; Accordingly, the target collaborative linkage scheme is generated based on the key elements and the historical abnormal event data set, including: Based on the current situation description set and the historical abnormal event data set, a target collaborative linkage plan is generated.

3. The method according to claim 2, characterized in that The performing element mining on the full element feature representation matrix to obtain a current status description set of the abnormal event also includes: Performing factor mining on the full-factor feature representation matrix to obtain a candidate factor set; Classifying the abnormal event description text by a preset classification model to obtain an abnormal event type set, wherein the abnormal event type set includes several types of abnormal events; Key elements of various abnormal events are extracted from the candidate element set, and a current status description set of the abnormal events is constructed based on various abnormal events and the key elements corresponding to the abnormal events.

4. The method according to claim 2, characterized in that The generating a target collaborative linkage scheme based on the current status description set and the historical abnormal event data set includes: Matching corresponding candidate solution sets from the historical abnormal event data set based on various abnormal events in the current state description set; Calculating the similarity between the candidate element set of the abnormal event and each processing solution in the candidate solution set; Determine a candidate processing solution according to the similarity calculation result, wherein the candidate processing solution is a processing solution in the candidate solution set that has the greatest similarity with the candidate element set of the abnormal event; The candidate processing solutions are updated according to the on-site feedback information to obtain a target collaborative linkage solution.

5. The method according to claim 4, characterized in that The updating of the candidate processing scheme according to the on-site feedback information to obtain a target collaborative linkage scheme includes: Extracting on-site element information from the on-site feedback information; The corresponding element information in the target collaborative linkage scheme is updated according to the on-site element information to obtain the target collaborative linkage scheme.

6. The method according to claim 1, characterized in that Before generating a target collaborative linkage solution based on the key elements and the historical abnormal event data set, the method further includes: Obtain historical processing solutions, joint exercise records, and preset emergency plans corresponding to historical abnormal events; Constructing a basic data set of an abnormal event collaborative linkage solution based on the historical processing solution, the joint exercise record, and the preset emergency plan; Based on the basic data set, a historical abnormal event data set is generated through a semi-supervised learning model.

7. The method according to claim 6, characterized in that The method of generating a historical abnormal event dataset based on the basic dataset through a semi-supervised learning model includes: extracting a target data stream from the basic data set; marking the target data stream; The labeled target data stream is supplemented with data through a semi-supervised learning model to generate a historical abnormal event dataset.

8. An abnormal event emergency dispatch device, characterized in that: The abnormal event emergency dispatch device comprises: Statistics module, used for on-site feedback information of abnormal events; An extraction module, used to extract features from the on-site feedback information to obtain key elements of the abnormal event; A generation module, used to generate a target collaborative linkage plan based on the key elements and the historical abnormal event data set; A scheduling module is used to perform multi-department emergency coordinated linkage scheduling for the abnormal event based on the target coordinated linkage plan.

9. An abnormal event emergency dispatch device, characterized in that: The abnormal event emergency dispatch device comprises: a memory, a processor, and an abnormal event emergency dispatch program stored in the memory and executable on the processor, wherein the abnormal event emergency dispatch program is configured to implement the steps of the abnormal event emergency dispatch method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores an emergency dispatching program for abnormal events, and when the emergency dispatching program for abnormal events is executed by the processor, the steps of the emergency dispatching method for abnormal events according to any one of claims 1 to 7 are implemented.

Images