CN116340606A

CN116340606A - Analysis method, device, storage medium and equipment for major emergency

Info

Publication number: CN116340606A
Application number: CN202211500880.XA
Authority: CN
Inventors: 杨娟; 杨再飞; 翟士丹; 倪康
Original assignee: Beijing Haizhi Xingtu Technology Co ltd
Current assignee: Beijing Haizhi Xingtu Technology Co ltd
Priority date: 2022-11-28
Filing date: 2022-11-28
Publication date: 2023-06-27

Abstract

The invention provides a method, a device, a storage medium and equipment for analyzing a major emergency, wherein the method comprises the following steps: collecting the network public opinion corpus data related to the major emergency, identifying and extracting trigger words and related event elements of the major emergency from the network public opinion corpus data, and extracting logical evolution relations among the events by adopting a pattern matching method and a semantic dependency analysis method according to the trigger words and the related event elements; and constructing a rational map by using the trigger words, related event elements and the logical evolution relations among the events, storing the rational map in a map database, and carrying out visual display on the rational map so as to analyze and predict the evolution process of the major emergency. The invention can help clients to more intuitively and conveniently analyze the evolution path of the network public opinion in the major emergency, and can use the prediction and auxiliary decision of the major emergency.

Description

Analysis method, device, storage medium and equipment for major emergency

Technical Field

The present invention relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a storage medium, and a device for analyzing a significant emergency.

Background

With the development and perfection of internet technology, networks become an indispensable part of life of people, and network public opinion also gradually plays an important role in social public opinion. Because of the network virtualization and openness, the network public opinion is generated along with the evolution of social events, and the propagation of the network public opinion has the characteristic of repeated fluctuation by means of the aggregation of emotion, attitude, behavior and cognition of internet users propagated by a social network.

After major emergencies occur, the societies rapidly gather on the social platform to express views, mindsets and attitudes, or to develop panic and discontent moods, causing negative comments. The network plays an important role in social supervision, recognizes and analyzes the evolution of the network public opinion event, can discover the potential risk of public opinion development, and avoids the overdriving behavior of the masses.

The analysis of a large number of serious emergencies in early stage is realized through a knowledge graph, but the knowledge graph takes static entities as research objects, the relation among the entities is fixed, and the evolution process of the serious emergencies cannot be analyzed and deduced, so that the prior art cannot help the public to know the true phase of the whole event clearly and comprehensively in the evolution process of researching the network public opinion event, and the evolution reasoning analysis of the serious emergencies is inaccurate, and the emergency management and public opinion guidance cannot be carried out efficiently and accurately.

Disclosure of Invention

In view of the above, the invention provides a method, a device, a storage medium and equipment for analyzing a major emergency, which can accurately infer and analyze the evolution of the major emergency, and can efficiently and accurately conduct emergency management and public opinion guiding on the major emergency.

In a first aspect, an embodiment of the present invention provides a method for analyzing a major emergency, where the method includes:

collecting online public opinion corpus data related to major emergencies;

identifying and extracting trigger words and related event elements of major emergencies from the online public opinion corpus data;

extracting a logic evolution relation between events by adopting a pattern matching method and a semantic dependency analysis method according to the trigger words and related event elements;

constructing a rational map of the trigger words, related event elements and logical evolution relations among the events and storing the rational map into a map database;

and visually displaying the event map to analyze and predict the evolution process of the medium-law emergency.

Further, identifying and extracting trigger words and related event elements of the major emergency from the online public opinion corpus data includes:

extracting features from the online public opinion corpus data by using a bidirectional transducer as an encoder;

learning knowledge information of the entity in a word mask, phrase mask and entity mask mode to obtain semantic representation of the complete concept of the entity;

semantic coding is carried out on the semantic representation through a bidirectional LSTM layer to extract sentence level features;

and acquiring a global optimal tag sequence through the CRF conditional random field to acquire trigger words and related event elements of the major emergency.

Further, extracting the logical evolution relationship between the events by adopting a pattern matching method and a semantic dependency analysis method according to the trigger words and the related event elements comprises the following steps:

judging whether the online public opinion corpus data has obvious logic evolution relation according to the trigger words and the related event elements;

when the network public opinion corpus data has obvious logic evolution relation, extracting the logic evolution relation among events by adopting a pattern matching method;

and when the network public opinion corpus data does not have obvious logic evolution relations, extracting the logic evolution relations among the events by adopting a semantic dependency analysis method.

Further, extracting the logical evolution relationship between the events by adopting a pattern matching method comprises the following steps:

constructing a causal link word library, a result word library and a causal pattern library;

and extracting the logic evolution relation pair from the preprocessed online public opinion corpus data to obtain the logic evolution relation among the events.

Further, extracting the logical evolution relationship between the events by adopting the semantic dependency analysis method comprises the following steps:

acquiring semantic dependency relationship and deep semantic expression among trigger words by adopting a tree and graph mixed decoding mode;

and obtaining the logic evolution relation between the events according to the semantic dependency relation between the trigger words and the deep semantic expression.

Further, before identifying and extracting trigger words and related event elements of a major emergency from the online public opinion corpus data, the method further includes:

and cleaning the online public opinion corpus data.

In a second aspect, an embodiment of the present invention provides an apparatus for analyzing a significant emergency, the apparatus including:

the collection module is used for collecting online public opinion corpus data related to major emergencies;

the first extraction module is used for identifying and extracting trigger words and related event elements of major emergencies from the online public opinion corpus data;

the second extraction module is used for extracting the logic evolution relation between the events by adopting a pattern matching method and a semantic dependency analysis method according to the trigger words and the related event elements;

the event map construction module is used for constructing an event map from the trigger words, related event elements and the logic evolution relations among the events and storing the event map into a map database;

and the visual display module is used for visually displaying the event map so as to analyze and predict the evolution process of the medium-law emergency.

In a third aspect, an embodiment of the present invention provides a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the method of any of the first aspects when run.

In a fourth aspect, an embodiment of the invention provides an apparatus comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the method of any of the first aspects.

According to the technical scheme provided by the invention, the trigger words and related event elements of the major emergency are identified and extracted from the online public opinion corpus data, the logical evolution relation among the events is extracted by adopting a pattern matching method and a semantic dependency analysis method according to the trigger words and the related event elements, a situation map is constructed according to the logical evolution relation among the trigger words, the related event elements and the events, and finally the situation map is subjected to visual analysis so as to analyze and predict the evolution process of the major emergency. Therefore, the events in the event map constructed by the method are represented by abstract, generalized and semantically complete predicate phrases, event trigger words and other necessary components are contained in the event map to keep the semantic completeness of the major emergency, the event is represented by multiple groups with the dynamic property as the center, the event is more abundant knowledge is contained, clients can be helped to analyze the evolution path of the network public opinion in the major emergency more intuitively and conveniently, and the prediction and the auxiliary decision of the major emergency can be used.

Drawings

FIG. 1 is a flow chart of a method for analyzing a significant incident provided by an embodiment of the present invention;

FIG. 2 is a flow chart of an implementation process for extracting trigger words and related event elements provided by an embodiment of the present invention;

FIG. 3 is a block diagram of an analysis device for a significant incident according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Referring to fig. 1, fig. 1 is a flowchart of a method for analyzing a major emergency event according to an embodiment of the present invention, where the method includes the following steps:

and step 101, collecting online public opinion corpus data related to major emergencies.

In this step, an event is a change in a thing or state that consists of one or more actions that one or more characters are engaged in, that occurs at a certain point in time or period of time, within a certain geographical range.

The online public opinion corpus data needs to cover various fields such as news, novel, articles, dialogue, chat, comments, critique, etc. as much as possible. Most of common online public opinion corpus data is unstructured text data, the unstructured text data can be analyzed by a text analyzer, the text data can have clear paragraph relations, clear and coherent semantic logicals among paragraph contents, the text data can also not have clear paragraph relations, and the semantic logicals among paragraph contents can have hidden semantic logicals.

The common online public opinion corpus data acquisition method comprises the following steps: manual, reptile and by means of a network public opinion monitoring system. The method of manual searching adopts earliest, and related public opinion information is monitored and collected by arranging special persons to pass through various search engines every day/week or on a main stream media platform such as microblogs, knowledgements, forums, tremble sounds, redbooks and the like. The manual searching has the advantages of lowest cost, low collection efficiency, incomplete collection information and easy occurrence of missing report; the crawler collection method generally needs technical personnel to operate, needs to master some skills such as http related knowledge, browser interception, package grabbing, cookie processing, login and the like, comprehensively uses the skill points to carry out complete monitoring and crawling of network public opinion information, and has the advantages of high efficiency and convenience, and the method has the defects that the method needs technical personnel to support, and raw data is mostly needed to be processed and tidied manually; the public opinion monitoring and collecting method can monitor the whole network range, early warn 7 x 24 in real time and automatically analyze data. Therefore, the network public opinion corpus data collected by the public opinion monitoring system is the most comprehensive, accurate and efficient.

Step 102, identifying and extracting trigger words and related event elements of the major emergency from the online public opinion corpus data.

In a major emergency, event knowledge representation directly relates to application of knowledge reasoning and knowledge calculation and is a core part of a fact map. The ontology representation of the event map comprises trigger words, related event elements, logical evolution relations and the like. The trigger words may be entities and objects, and the related event elements may be events (such as "acquisition", "freezing", "financing") and event attributes (such as "job", "time", "amount", etc.), where the logical evolution relationship between events mainly includes a time sequence relationship, a causal relationship, etc.

In this step, an improved ERNIE algorithm may be used to identify the collected internet public opinion corpus data and extract the trigger words and related event elements of major emergencies, that is, an ERNIE layer is introduced to obtain a vector representation of each word, a bidirectional LSTM layer performs semantic coding to extract sentence level features, and a CRF layer obtains a global optimal tag sequence. In this step, the trigger words and related event elements are extracted, i.e. the event information of interest is extracted from the text describing the event information, and the representation is structured. Such as what person, when, where, and what is done.

As shown in fig. 2, fig. 2 is a flowchart of an implementation process for extracting trigger words and related event elements according to an embodiment of the present invention, that is, one possible implementation of step 102 includes the following steps:

and 1021, extracting features from the online public opinion corpus data by adopting a bidirectional transducer as an encoder.

ERNIE algorithm, collectively Enhanced Representation through Knowledge Integration, is an enhanced algorithm model based on knowledge masking strategies, in this application, using 12-layer bi-directional transducers as encoder extraction features.

Step 1022, learning knowledge information of the entity by means of word mask, phrase mask and entity mask to obtain semantic representation of the complete concept of the entity.

In this step, knowledge information such as entity attributes and entity relationships is learned by adopting three levels of masking modes including word masking, phrase masking and entity masking, so that semantic representation of the complete concept is learned.

Step 1023, extracting sentence level features by performing semantic coding on the semantic representation through a bidirectional LSTM layer.

In this step, the learned semantic representation is then semantically encoded through the bi-directional LSTM layer to extract sentence-level features.

Step 1024, obtaining a global optimal tag sequence through the CRF conditional random field to obtain trigger words and related event elements of the major emergency.

Finally, the global optimal tag sequence is obtained through the CRF conditional random field, so that the trigger words and related elements of the major emergency are identified.

And step 103, extracting the logic evolution relation between the events by adopting a pattern matching method and a semantic dependency analysis method according to the trigger words and the related event elements.

In this step, the logical evolution relationship between the extracted events uses the events as basic semantic units, and the logical relationship before the events is automatically extracted, including the co-fingered relationship, the causal relationship, the time sequence relationship, and the like between the events. The extraction and construction of the event relationship can reveal the time development rule, clear the time association and comprehensively understand the event. Wherein co-referencing relationship refers to representing the same target event. The alemba represents the same event as the 95 million dollar high priced full-resource acquisition hunger and the alemba group and hunger contracted acquisition agreement, and the co-fingering relationship needs to be resolved in general. The event affiliation refers to a plurality of sub-events contained under the same event topic. The time sequence relation refers to the sequence of events in time, is helpful for the discovery and reasoning of the events, and is a key element for the construction of the event knowledge graph. Causality refers to the relationship of action between events, i.e. that an event is the result of another event.

In this step, in step 103, according to the trigger words and related event elements, a possible implementation manner of extracting the logical evolution relationship between the events by using a pattern matching method and a semantic dependency analysis method is implemented by the following steps:

step 1031, judging whether the online public opinion corpus data has obvious logic evolution relation according to the trigger words and the related event elements;

step 1032, when the obvious logic evolution relationship exists in the network public opinion corpus data, extracting the logic evolution relationship between the events by adopting a pattern matching method;

step 1033, extracting the logic evolution relation among the events by adopting a semantic dependency analysis method when the network public opinion corpus data does not have obvious logic evolution relation.

In this embodiment, for sentences with obvious causal relationships, pattern matching is adopted to extract, and the core idea is to extract causal relationship pairs from the preprocessed text data by constructing a causal word bank, a result word bank and a causal pattern bank. For sentences without obvious causal pattern matching, semantic dependency analysis is adopted, semantic dependency relation results among word pairs are obtained by using a tree and graph mixed decoding mode, and the essence of deep semantic expression can be directly obtained across the surface layer structure of the sentences, so that hidden event relations are obtained.

And 104, constructing a situation map by using the trigger words, the related event elements and the logic evolution relations among the events, and storing the situation map into a map database.

In the step, the event map represents the event and the relation thereof by using a logic directed graph, the abstract and generalized event is taken as a node, the bearing relation and the causal relation are taken as directed edges, and the transition probability on the directed edges represents the logic possibility of event evolution.

And 105, visually displaying the event map to analyze and predict the evolution process of the major emergency.

In this step, in order to facilitate the clients to more intuitively and more conveniently analyze the evolution path of the network public opinion in the major emergency, the embodiment uses the Atlas knowledge graph platform independently developed by the applicant to visually display the fact graph stored in the graph database, and the evolution process of the major emergency can be conveniently and rapidly analyzed and predicted through visual display, so that guidance is provided for the public opinion dispersion and management and control of the major emergency. Atlas knowledge graph platform provides the full-flow computing capability supporting large-scale graph computation, graph analysis and graph storage. On the platform, the event map application meeting the service requirement can be quickly constructed, risks can be timely found out from massive unstructured data, business opportunities can be found, man-machine combination is realized, and intelligent analysis, research and decision making are provided for the service.

In some preferred embodiments, prior to step 102, the method further comprises:

step 102a, cleaning the online public opinion corpus data.

The online public opinion corpus data needs to be subjected to proper corpus cleaning before natural language processing. The washed corpus will become cleaner and facilitate later analysis. When the online public opinion corpus data is Chinese, the corpus cleaning method can be firstly performing outlier cleaning (Null and empty character strings), then performing duplication removal, then analyzing html by using BeautiffulSoup, then removing punctuation marks and non-Chinese characters, and performing simplified-complex conversion, case-case conversion, filtering and cutting text length, digital replacement or deletion, word segmentation, word stopping and the like. By cleaning the online public opinion corpus data, the speed and accuracy of subsequently identifying and extracting trigger words and related event elements of major emergencies can be improved.

Referring to fig. 3, fig. 3 is a block diagram of an analysis device for serious emergency according to an embodiment of the present invention, where the device includes:

the collection module 21 is configured to collect online public opinion corpus data related to major emergencies;

the first extraction module 22 is configured to identify and extract trigger words and related event elements of a major emergency from the online public opinion corpus data;

the second extraction module 23 is configured to extract a logical evolution relationship between events according to the trigger word and the related event elements by using a pattern matching method and a semantic dependency analysis method;

a situation map construction module 24, configured to construct a situation map from the trigger words, related event elements, and logical evolution relationships among events, and store the situation map in a map database;

the visual display module 25 is configured to visually display the event map, so as to analyze and predict an evolution process of the medium-law emergency.

In some embodiments, the first decimation module 22 may include:

a feature extraction unit 221, configured to extract features from the online public opinion corpus data using a bidirectional transducer as an encoder;

a knowledge acquisition unit 222, configured to learn knowledge information of an entity by means of word masks, phrase masks and entity masks, and obtain a semantic representation of a complete concept of the entity;

a semantic coding unit 223, configured to extract sentence-level features by performing semantic coding on the semantic representation through a bidirectional LSTM layer;

the optimal tag sequence obtaining unit 224 is configured to obtain the global optimal tag sequence through the CRF conditional random field, and obtain the trigger word and the related event element of the major emergency.

In some embodiments, the second decimation module 23 may include:

the judging unit 231 is configured to judge whether the online public opinion corpus data has an obvious logical evolution relationship according to the trigger word and the related event element;

the first processing unit 231 is configured to extract a logical evolution relationship between events by using a pattern matching method when the network public opinion corpus data has an obvious logical evolution relationship;

and the second processing unit 232 is configured to extract a logical evolution relationship between events by using a semantic dependency analysis method when the online public opinion corpus data does not have an obvious logical evolution relationship.

In some embodiments, the first processing unit 231 may include:

a constructing subunit 2311, configured to construct a causal link library, a result word library, and a causal pattern library;

the extraction subunit 232 is configured to perform extraction of a logical evolution relationship pair on the preprocessed online public opinion corpus data, so as to obtain a logical evolution relationship between the events.

In some embodiments, the second processing unit 232 may include:

a decoding subunit 2321, configured to obtain semantic dependency relationships and deep semantic expressions between trigger words by adopting a tree and graph hybrid decoding manner;

the logic evolution relationship obtaining subunit 2322 is configured to obtain a logic evolution relationship between events according to the semantic dependency relationship between the trigger words and the deep semantic expression.

In some embodiments, the apparatus further comprises:

and the cleaning module 22a is configured to clean the online public opinion corpus data.

It should be noted that, the analysis device for the major emergency in the embodiment of the present invention and the analysis method for the major emergency in the foregoing embodiment belong to the same inventive concept, and technical details not described in detail in the present device may be referred to the related description of the method, which is not repeated herein.

Furthermore, the embodiment of the invention also provides a storage medium, wherein the storage medium stores a computer program, and the computer program is configured to execute the method when running.

Fig. 4 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the idle detection method.

In some embodiments, the idle detection method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the idle detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the idle detection method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of analyzing a significant incident, the method comprising:

collecting online public opinion corpus data related to major emergencies;

and visually displaying the event map so as to analyze and predict the evolution process of the major emergency.

2. The method of claim 1, wherein identifying and extracting trigger words and related event elements for a significant incident from the internet public opinion corpus data comprises:

3. The method of claim 1, wherein extracting the logical evolution relationship between the events using a pattern matching method and a semantic dependency analysis method according to the trigger words and related event elements comprises:

4. The method of claim 3, wherein extracting the logical evolution relationship between events using pattern matching comprises:

5. The method of claim 3, wherein extracting logical evolution relationships between events using semantic dependency analysis methods comprises:

6. The method of claim 1, wherein prior to identifying and extracting trigger words and related event elements for a significant incident from the internet public opinion corpus data, the method further comprises:

and cleaning the online public opinion corpus data.

7. An apparatus for analyzing a significant incident, the apparatus comprising:

8. A storage medium having a computer program stored therein, wherein the computer program is arranged to perform the method of any of claims 1 to 7 when run.

9. An apparatus comprising a memory and a processor, wherein the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the method of any of claims 1 to 6.