CN114528396A - Method and device for monitoring emergency, electronic equipment and storage medium - Google Patents

Method and device for monitoring emergency, electronic equipment and storage medium Download PDF

Info

Publication number
CN114528396A
CN114528396A CN202111640233.4A CN202111640233A CN114528396A CN 114528396 A CN114528396 A CN 114528396A CN 202111640233 A CN202111640233 A CN 202111640233A CN 114528396 A CN114528396 A CN 114528396A
Authority
CN
China
Prior art keywords
emergency
entity
similarity
associated text
text
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111640233.4A
Other languages
Chinese (zh)
Inventor
陈建国
陈涛
黄丽达
刘一青
陈杨
史盼盼
王晓萌
刘春慧
赵晨阳
狄文杰
刘连顺
秦阳阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Global Safety Technology Co Ltd
Original Assignee
Beijing Global Safety Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Global Safety Technology Co Ltd filed Critical Beijing Global Safety Technology Co Ltd
Priority to CN202111640233.4A priority Critical patent/CN114528396A/en
Publication of CN114528396A publication Critical patent/CN114528396A/en
Priority to PCT/CN2022/142554 priority patent/WO2023125589A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
    • Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Machine Translation (AREA)

Abstract

The disclosure provides a method and a device for monitoring an emergency event, electronic equipment and a storage medium, and relates to the technical field of information management. The method comprises the following steps: based on the reference words, extracting candidate texts containing the reference words from the network information in a traversal process; performing semantic analysis on the candidate texts to determine associated texts associated with the emergency events; entity extraction is carried out on the associated text to determine a first entity set corresponding to the associated text; determining a first similarity between the first entity set and a second entity set corresponding to each emergency in the emergency data set; and under the condition that the first similarity between the first entity set and any second entity set is greater than a first threshold value, determining that the associated text is the associated text of the first emergency corresponding to any second entity set. Therefore, the emergency text contained in the network information is analyzed and arranged, so that new emergency can be found in time from massive network information, and the related information of the emergency can be accurately mined.

Description

Method and device for monitoring emergency, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of information management technologies, and in particular, to a method and an apparatus for monitoring an emergency event, an electronic device, and a storage medium.
Background
With the development of internet technology, more and more users can distribute various information on the internet. Also included are emergencies such as infectious diseases, typhoons, floods, explosions, nuclear accidents, and the like. Emergency management personnel of the emergency can know the emergency situation in time through the information on the network. However, it is not easy to accurately and timely mine information related to an emergency from a huge amount of network information. Therefore, how to obtain the information related to the emergency from a large amount of network information becomes an important research direction.
Disclosure of Invention
The present disclosure is directed to solving, at least to some extent, one of the technical problems in the related art.
An embodiment of a first aspect of the present disclosure provides a method for monitoring an emergency event, including:
traversing the network information based on the reference words contained in the word bank to extract candidate texts containing the reference words;
performing semantic analysis on the candidate texts to determine associated texts which are contained in the candidate texts and are associated with the emergency;
entity extraction is carried out on the associated text to determine a first entity set corresponding to the associated text;
determining a first similarity between the first entity set and a second entity set corresponding to each emergency in the emergency data set;
and determining the associated text to be the associated text of the first emergency corresponding to any second entity set under the condition that the first similarity between the first entity set and any second entity set is greater than a first threshold value.
An embodiment of a second aspect of the present disclosure provides an emergency monitoring device, including:
the first acquisition module is used for traversing the network information based on the reference words contained in the word bank so as to extract candidate texts containing the reference words;
the first determining module is used for performing semantic analysis on the candidate texts to determine associated texts which are contained in the candidate texts and are associated with the emergency;
a second determining module, configured to perform entity extraction on the associated text to determine a first entity set corresponding to the associated text;
a third determining module, configured to determine a first similarity between the first entity set and a second entity set corresponding to each emergency in the emergency data set;
a fourth determining module, configured to determine that the associated text is an associated text of a first emergency corresponding to any one of the second entity sets when a first similarity between the first entity set and the any one of the second entity sets is greater than a first threshold.
An embodiment of a third aspect of the present disclosure provides an electronic device, including: the monitoring system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the monitoring method for the emergency event as set forth in the embodiment of the first aspect of the disclosure.
A fourth aspect of the present disclosure provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for monitoring an emergency event as set forth in the first aspect of the present disclosure is implemented.
An embodiment of a fifth aspect of the present disclosure provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the method for monitoring an emergency event as set forth in the embodiment of the first aspect of the present disclosure.
The monitoring method and device for the emergency event, the electronic device and the storage medium have the following beneficial effects:
in the embodiment of the disclosure, firstly, based on reference words contained in a word bank, network information is traversed to extract candidate texts containing the reference words from the network information, then, semantic analysis is performed on the candidate texts to determine associated texts contained in the candidate texts and associated with emergency events, then, entity extraction is performed on the associated texts to determine first entity sets corresponding to the associated texts, then, first similarity between the first entity sets and second entity sets corresponding to each emergency event in an emergency event data set is determined, and finally, under the condition that the first similarity between the first entity sets and any second entity set is greater than a first threshold value, the associated texts are determined to be associated texts of the first emergency events corresponding to any second entity set. Therefore, the emergency texts contained in the network information are analyzed and sorted, so that the related information of the emergency can be timely and accurately mined from massive network information, and the texts describing the same emergency can be clustered, thereby timely discovering new emergency.
Additional aspects and advantages of the disclosure will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart illustrating a method for monitoring an emergency event according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart illustrating a method for monitoring an emergency event according to another embodiment of the present disclosure;
FIG. 3 is a diagram illustrating semantic analysis of candidate texts according to an embodiment of the present disclosure;
fig. 4 is a schematic flowchart illustrating a method for monitoring an emergency event according to another embodiment of the present disclosure;
fig. 5 is a schematic flowchart illustrating a method for monitoring an emergency event according to another embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an emergency monitoring apparatus according to an embodiment of the present disclosure;
FIG. 7 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and intended to be illustrative of the present disclosure, and should not be construed as limiting the present disclosure.
The following describes a method, an apparatus, an electronic device, and a storage medium for monitoring an emergency according to an embodiment of the present disclosure with reference to the drawings.
Fig. 1 is a schematic flow chart of a method for monitoring an emergency event according to an embodiment of the present disclosure.
The embodiment of the present disclosure is exemplified by the method for monitoring an emergency event being configured in a monitoring device for an emergency event, and the monitoring device for an emergency event can be applied to any electronic device, so that the electronic device can perform a monitoring function for an emergency event.
The electronic device may be a Personal Computer (PC), a cloud device, a mobile device, and the like, and the mobile device may be a hardware device having various operating systems, touch screens, and/or display screens, such as a mobile phone, a tablet Computer, a Personal digital assistant, a wearable device, and an in-vehicle device.
As shown in fig. 1, the method for monitoring an emergency event may include the following steps:
step 101, traversing the network information based on the reference words contained in the word bank to extract candidate texts containing the reference words.
Optionally, the word bank may include reference words corresponding to each type of emergency event, and the reference words included in the word bank may be predetermined.
The emergency event may include a natural disaster, an accident disaster, a public health event, a social security event, and the like. Natural disasters, for example, may also include: rainstorms, tornadoes, earthquakes, and the like; the accident disaster may include: car accidents, fires, etc.; public health events may include infectious diseases, food poisoning, and the like; social security events may include: terrorist attack events, mass congregation events, etc.
It is understood that each type of reference event has its corresponding reference word. For example, a storm event is often accompanied by a strong wind, and thus, the strong wind may be a reference word corresponding to the storm event. The candidate text containing the strong wind extracted from the network information can be 'strong wind yellow early warning issued in a certain area today'.
And 102, performing semantic analysis on the candidate texts to determine associated texts which are contained in the candidate texts and are associated with the emergency.
It should be noted that an emergency is an irregular event that does not occur frequently, and therefore, even if the candidate text obtained includes a candidate word, the candidate text is not a text related to the emergency. Thus, after the candidate text is obtained, semantic analysis may be performed on the candidate text to determine whether the candidate text describes an emergency.
Optionally, the candidate text may be subjected to semantic analysis by using a bidirectional long-and-short-term memory model with enhanced attention (BERT-Att-BiLSTM model) to determine associated text associated with the emergency contained in the candidate text.
Alternatively, semantic analysis may be performed on the candidate text by using Latent Dirichlet Allocation (LDA) to determine associated text contained in the candidate text and associated with the emergency.
It should be noted that, in the embodiment of the present disclosure, the candidate text may also be subjected to semantic analysis in any other desirable manner, so as to determine the associated text included in the candidate text and associated with the emergency. The present disclosure is not limited thereto.
And 103, performing entity extraction on the associated text to determine a first entity set corresponding to the associated text.
Optionally, the first set of entities may include a first event type, a first geographic location, and a first time of occurrence.
The first event type may be a type of an emergency described by the associated text. For example, the first event type corresponding to the associated text may be rainstorm, tornado, etc., which is not limited by this disclosure.
Wherein the first geographical location may be a geographical location where the emergency event described by the associated text occurs. For example, the first geographic location corresponding to the associated text may be XX prefecture XX county of XX province, etc., which is not limited by the disclosure.
The first occurrence time may be event information associated with occurrence of an emergency event described in the text. For example, the first occurrence time corresponding to the associated text may be 10/2020/20/2008, and the disclosure does not limit this.
It should be noted that, if the associated text does not include the occurrence time corresponding to the emergency, the first occurrence time in the first entity set corresponding to the associated text is null; or if the associated text does not include the geographic position corresponding to the burst time, the first geographic position in the first entity set corresponding to the associated text is null.
Step 104, determining a first similarity between the first entity set and a second entity set corresponding to each emergency in the emergency data set.
Optionally, the second entity set corresponding to each emergency event may include a second event type, a second geographic location, and a second occurrence time.
Optionally, under the condition that the first event type, the first geographic location, and the first occurrence time included in the first entity set are not empty, the first similarity between the first entity set and the second entity set corresponding to each emergency in the emergency data set may be determined according to a second similarity between the first event type and the second event type, a third similarity between the first geographic location and the second geographic location in the second entity set, and a fourth similarity between the first occurrence time and the second occurrence time in the second entity set.
Or, under the condition that the first event type, the first geographic location, and the first occurrence time included in the first entity set are not null, the first similarity between the first entity set and the second entity set is calculated by using a euclidean distance formula and a manhattan distance formula, or the cosine similarity between the first entity set and the second entity set is calculated and is used as the first similarity between the first entity set and the second entity set, which is not limited in this disclosure.
Step 105, determining that the associated text is the associated text of the first emergency corresponding to any second entity set when the first similarity between the first entity set and any second entity set is greater than a first threshold.
It can be understood that, if the first similarity between the first entity set and any second entity set is greater than the first threshold, it indicates that the associated text and the first emergency corresponding to any second entity set describe the same emergency, and therefore, the associated text may be associated with the first emergency corresponding to any second entity set, that is, the associated text may be stored in a set corresponding to the first emergency corresponding to any second entity set in the emergency data set.
Optionally, each of the first similarity degrees is smaller than or equal to the first threshold, which indicates that the emergency data set does not include the emergency described by the associated text, and therefore, the associated text and the first entity set may be stored in the emergency data set in an associated manner as a new emergency. Therefore, the occurrence of a new emergency can be accurately monitored, so that emergency management personnel can timely monitor the occurrence of the new emergency, and timely take emergency measures for the emergency according to the type of the first event, the first geographical position and the first occurrence event in the first entity set corresponding to the emergency.
In the embodiment of the disclosure, firstly, based on reference words contained in a word bank, network information is traversed to extract candidate texts containing the reference words from the network information, then, semantic analysis is performed on the candidate texts to determine associated texts contained in the candidate texts and associated with emergency events, then, entity extraction is performed on the associated texts to determine first entity sets corresponding to the associated texts, then, first similarity between the first entity sets and second entity sets corresponding to each emergency event in an emergency event data set is determined, and finally, under the condition that the first similarity between the first entity sets and any second entity set is greater than a first threshold value, the associated texts are determined to be associated texts of the first emergency events corresponding to any second entity set. Therefore, the emergency texts contained in the network information are analyzed and sorted, so that the related information of the emergency can be timely and accurately mined from massive network information, and the texts describing the same emergency can be clustered, thereby timely discovering new emergency.
Fig. 2 is a schematic flow chart of a method for monitoring an emergency event according to an embodiment of the present disclosure, as shown in fig. 2, the method for monitoring an emergency event may include the following steps:
step 201, traversing the network information based on the reference words contained in the word stock to extract candidate texts containing the reference words.
In the embodiment of the disclosure, a plurality of texts related to each type of emergency event may be randomly acquired, the plurality of texts are merged into one text, then word segmentation processing is performed on the merged text to acquire words included in the merged text, word frequency statistics is performed on each word, that is, the number of times that each word appears in the merged text is acquired, and then the word with the word frequency greater than a preset threshold value is used as a reference word corresponding to the type of emergency event.
It should be noted that, one or more reference words may be used for each type of emergency, and the disclosure is not limited thereto.
Optionally, after the reference words are obtained, the weight corresponding to each reference word may be determined according to the word frequency corresponding to each reference word. The weight and the word frequency are in positive correlation, namely, the larger the word frequency corresponding to the reference word is, the larger the corresponding weight is.
Optionally, after the candidate text is captured by using the reference word, the reference word and the corresponding weight may be adjusted according to the candidate text.
In the embodiment of the present disclosure, after obtaining a plurality of texts related to each type of emergency, each text may be subjected to a preprocessing operation such as deleting a Uniform Resource Locator (URL), a space, a punctuation mark, and then each preprocessed text is encoded into the same encoding format. For example, each text is unified into an encoding Format of UTF-8(Universal Character Set/Unicode Transformation Format). UTF-8 is a variable length character code for Unicode (Unicode), among others.
And step 202, performing semantic analysis on the candidate texts to determine associated texts contained in the candidate texts and associated with the emergency events.
In the embodiment of the present disclosure, fig. 3 is a schematic diagram of performing semantic analysis on a candidate text according to an embodiment of the present disclosure, and as shown in fig. 3, a bidirectional long-time and short-time memory model (BERT-Att-BiLSTM model) with enhanced attention may be used to perform semantic analysis on the candidate text to determine an associated text associated with an emergency included in the candidate text. Firstly inputting the candidate text into BERT to obtain semantic representation of the candidate text, then inputting the semantic representation of the candidate text into Att-BilSTM to further carry out semantic analysis on the semantic representation of the candidate text, and judging whether the candidate text is the associated text of the emergency.
In the embodiment of the present disclosure, bert (bidirectional Encoder replication from transforms) is a word vector generation model, which may adopt a bidirectional transform architecture, and can train in combination with contexts in all layers of the model. Here, a pre-trained BERT Chinese basis model (BERT-Base-Chinese) is used, which may include a 12-layer transform structure and 12 self-attention mechanisms, with vector dimensions of 768.
It should be noted that, in the embodiment of the present disclosure, the number of layer self-attention mechanisms and the vector dimension of the transform structure are not limited.
In the disclosed embodiment, the bidirectional Long Short-Term Memory (BilSTM) layer includes a forward LSTM
Figure BDA0003443220320000061
And inverse LSTM
Figure BDA0003443220320000062
The output is expressed as:
Figure BDA0003443220320000063
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0003443220320000064
is the forward information of the character i of the sentence s,
Figure BDA0003443220320000065
which is the backward information of character i of sentence s, both are hidden vectors. The attention weight of each character is expressed as follows:
Figure BDA0003443220320000071
wherein the content of the first and second substances,
Figure BDA0003443220320000072
in order to score the attention of the user,v is the weight, the T power of V is the transpose of V, ωsFor the weight corresponding to sentence s in the attention mechanism, bsTo note the corresponding bias of sentence s in the mechanism, tanh (.) is a hyperbolic tangent function, T is the number of characters,
Figure BDA0003443220320000073
is the attention weight of the character i in the sentence s.
Wherein the output of the context representation is:
Figure BDA0003443220320000074
and F is the semantic feature of the candidate text.
And the logistic regression (Softmax) layer is used for generating conditional probability on the class space according to the semantic features of the candidate texts, so as to judge whether the candidate texts are the associated texts of the emergency events.
Step 203, performing entity extraction on the associated text to determine a first entity set corresponding to the associated text.
Optionally, the reference word set corresponding to each event type may be obtained from the reference word library, then the association probability value between the associated text and each event type is determined according to the number of occurrences of each reference word in the associated text in the reference word set corresponding to each event type and the weight of each reference word, and then the first event type corresponding to the associated text is determined according to the second threshold value corresponding to each association probability value and each event type.
The calculation formula of the association probability value may be:
Pe＝∑kCkWk
wherein, PeThe associated probability value between the associated text and each event type e is CkFor reference to the number of occurrences of word k, WkIs the weight corresponding to the reference word k.
If PeIs greater than the second threshold corresponding to the event type e, the first event type corresponding to the associated text is determinedFor event type e.
It should be noted that, since there are often chain reactions between natural disasters, for example, a typhoon usually occurs along with a rainstorm, one associated text may also correspond to a plurality of event types. If the associated post describes both a typhoon and a rainstorm due to a typhoon, the associated post may correspond to a type of the rainstorm event and a type of the typhoon event.
Optionally, position extraction may be performed on the associated text according to a position entity included in the position entity library to determine a first geographic position corresponding to the associated text.
Optionally, the associated text may include a specific location, such as XX prefecture; or may not include a specific location, but include a building that may represent the specific location, and then the location corresponding to the emergency described in the associated text may be determined according to the building.
In the embodiment of the present disclosure, the specific location entity extraction may be performed on the associated text according to the first location entity library to obtain the specific occurrence location of the emergency described in the associated text. If the specific position is not extracted, further extracting the building entity from the content contained in the associated text according to the second position entity library, and further acquiring the specific occurrence position of the emergency described by the associated text according to the geographical position of the building entity.
Wherein, the first position entity library contains specific geographic positions, and the second entity library contains buildings and the like which can represent the geographic positions.
Optionally, after determining the specific occurrence location of the emergency described by the associated text, the specific occurrence location may be structurally represented, i.e. represented in the form of XX county/XX district/village/town of XX city.
In the embodiment of the present disclosure, if the associated text does not include the location information, the associated text is deleted, and the emergency event associated with the associated text is no longer determined.
Optionally, time extraction may be performed on the associated text based on a preset algorithm to determine a first occurrence time corresponding to the associated text.
Optionally, in this embodiment of the present disclosure, any desirable manner may be adopted to perform time extraction on the associated text, so as to determine the first occurrence time corresponding to the associated text. For example, a regular expression may be used to extract the time information contained in the associated text. The present disclosure is not limited thereto.
In the embodiment of the present disclosure, if the time information extracted from the associated text is an absolute time, for example, XX minutes in XXXX year, XX month, XX day, XX minute, the absolute information may be directly used as the first occurrence time corresponding to the associated text. If the time information extracted from the associated text is yesterday, early morning, three days ago and the like, determining the first generation time corresponding to the associated text according to the release time of the associated text, wherein the first generation time at the moment is relative to the relative time. For example, if the release time of the associated text is 3/5/2020, and the time information included in the associated text is yesterday, the first time information corresponding to the associated text is 3/4/2020.
Step 204, determining a second similarity between the first event type and a second event type in the second entity set, a third similarity between the first geographic location and a second geographic location in the second entity set, and a fourth similarity between the first occurrence time and a second occurrence time in the second entity set.
It can be understood that, in a case that the associated text describes the same emergency as a certain first emergency in the emergency data set, the first event type corresponding to the associated text should be the same as the second event type corresponding to the first emergency, and therefore, if the first event type is the same as the second event type, the second similarity is 1; if the first event type is the same as the second event type, the second similarity is 0.
In this embodiment of the disclosure, if the first event type is the same as the second event type, the difference between the first geographic location and the second geographic location is smaller, and the difference between the first occurrence time and the second occurrence time is also smaller, the associated event may describe a first emergency corresponding to the second entity set. Therefore, in the case where the first event type is the same as the second event type, the third similarity between the first geographical position and the second geographical position in the second entity set and the fourth similarity between the first occurrence time and the second occurrence time in the second entity set can be further calculated, so that the amount of calculation can be reduced.
Optionally, a third similarity between the first geographical location and the second geographical location in the second entity set may be determined according to the rank of the first geographical location and the rank of the second geographical location. Wherein the more detailed the geographic location, the higher the ranking. For example, the first geographic location includes XX counties/XX districts/towns of XX city XX provinces, and the level is highest.
For example, if the first geographic location and the second geographic location are in the same village/town, the third similarity may be 0.8; if the first geographic location and the second geographic location are in the same county/district and the village/town information is missing from the first geographic location or the second geographic location, the third similarity may be 0.6; if the first geographical location and the second geographical location are in the same city and the county/district information is missing from the first geographical location or the second geographical location, the third similarity may be 0.4; if the first geographical position and the second geographical position are the same province and the first geographical position or the second geographical position lacks city information, the third similarity may be 0.2; otherwise, the third similarity may be 0.
It should be noted that the above examples are only simple examples, and cannot be used as a specific limitation of the third similarity in the embodiments of the present disclosure.
Optionally, the fourth similarity may be determined according to a first time difference between the first occurrence time and the second occurrence time.
For example, if the first time difference is less than 1 minute, the fourth similarity may be 0.9; the first time difference is less than 1 hour, the fourth similarity may be 0.7; if the first time difference is less than 1 day, the fourth similarity may be 0.5; if the first time difference is less than 3 days, the fourth similarity may be 0.3; otherwise, the fourth similarity may be 0.
It should be noted that the foregoing examples are only simple illustrations, and should not be taken as specific limitations of the fourth similarity in the embodiments of the present disclosure.
Step 205, determining a first similarity between the first entity set and the second entity set according to the second similarity, the third similarity and the fourth similarity.
It should be noted that, if the associated text and a certain first emergency in the emergency data set describe the same emergency, the first event type corresponding to the associated text should be completely the same as the second event type corresponding to the first emergency, and therefore, the second similarity plays a decisive role in determining the first similarity.
The calculation formula of the first similarity may be:
S1＝S2×(aS3+bS4)
wherein S is1Is the first similarity, S2Is the second degree of similarity, S3Is the third degree of similarity, S4Is the fourth similarity, a is the weight corresponding to the third similarity, and b is the weight corresponding to the fourth similarity.
Wherein, the value of a can be 0.5, and the value of b can be 0.5. The present disclosure is not limited thereto.
Step 206, determining that the associated text is the associated text of the first emergency corresponding to any second entity set when the first similarity between the first entity set and any second entity set is greater than the first threshold.
Step 207, updating any second entity set according to the first entity set to obtain any updated second entity set.
It is understood that the second occurrence time and the second geographic location in the second entity set corresponding to each first emergency in the emergency data set may not be particularly detailed, and if the newly detected associated text includes a more specific first occurrence event and a more specific first geographic location, the second entity set corresponding to the first emergency described in the associated text may be updated to make the information of the first emergency more accurate.
Optionally, under the condition that the level of the first geographic location is higher than the level of the second geographic location in any second entity set, the second geographic location in any second entity set is updated according to the first geographic location, so as to obtain any updated second entity set.
For example, if the first geographic location corresponding to the associated text is XX province XX city XX town, and the second geographic location included in any one of the second entity sets is XX province, the first geographic location is higher in level than the second geographic location, and the second geographic location in the second entity set can be updated to be XX province XX city XX town.
Or under the condition that the first occurrence time is absolute time and the second occurrence time in any second entity set is relative time, updating the second occurrence event in any second entity set according to the first occurrence time to obtain any updated second entity set.
For example, if the first occurrence time corresponding to the related text is 2016 year 10 month 22 day 10 in absolute time and the second occurrence time included in any one of the second entity sets is a relative time estimated from time information such as "morning" and "yesterday", the second occurrence time in the second entity set can be updated to 2016 year 10 month 22 day 10.
In the embodiment of the present disclosure, if the first entity set is identical to any of the second entity sets, it is not necessary to update any of the second entity sets according to the first entity set.
In the embodiment of the disclosure, the second entity set corresponding to the first emergency described by the associated text is updated according to the first entity set corresponding to the associated text to obtain the updated second entity set, so that the occurrence time and the occurrence position corresponding to each emergency in the emergency database can be more accurate, and relevant workers can take processing measures according to the specific information of the emergency.
At step 208, a fifth similarity between any of the updated second entity sets and each of the remaining second entity sets is determined.
The specific implementation form of determining the fifth similarity in step 208 may refer to the specific description of determining the first similarity in the embodiments of the present disclosure, and details are not repeated here.
Step 209, in response to any fifth similarity being greater than the first threshold, associating the emergency corresponding to the second entity set corresponding to any fifth similarity with the updated emergency corresponding to any second entity set.
It is understood that, in the case that any fifth similarity is greater than the first threshold, it indicates that there are other first emergencies in the emergency data set that are the same as the first emergencies described by the associated text, so that the two sets describing the same emergencies may be merged.
In the embodiment of the present disclosure, after the emergency corresponding to the second entity set corresponding to any fifth similarity is associated with the updated emergency corresponding to any second entity set, the second entity set corresponding to any fifth similarity may also be updated according to any updated second entity set, that is, step 207, step 208, and step 209 are cycled until the entity sets corresponding to the two emergency are completely the same.
In the embodiment of the disclosure, first, based on a reference word contained in a word bank, traversing network information to extract a candidate text containing the reference word from the candidate text, then performing semantic analysis on the candidate text to determine an associated text contained in the candidate text and associated with an emergency, performing entity extraction on the associated text to determine a first entity set corresponding to the associated text, then obtaining a first similarity between the first entity set and a second entity set corresponding to each first emergency, determining that the associated text is an associated text of the first emergency corresponding to any second entity set when the first similarity between the first entity set and any second entity set is greater than a first threshold, then updating any second entity set according to the first entity set to obtain any updated second entity set, and determining a fifth similarity between any updated second entity set and each of the remaining second entity sets, and in response to any fifth similarity being larger than the first threshold, associating the emergency corresponding to the second entity set corresponding to any fifth similarity with the updated emergency corresponding to any second entity set. Therefore, the emergency text contained in the network information is analyzed and sorted, and the information of the emergency contained in the emergency time data set can be updated according to the specific information of the emergency contained in the newly found associated text, so that the acquired related information of the emergency is more accurate.
Fig. 4 is a schematic flow chart of a method for monitoring an emergency event according to another embodiment of the present disclosure, as shown in fig. 4, the method for monitoring an emergency event may include the following steps:
step 401, traversing the network information based on the reference words contained in the word stock to extract candidate texts containing the reference words.
And 402, performing semantic analysis on the candidate texts to determine associated texts which are contained in the candidate texts and are associated with the emergency.
And 403, performing entity extraction on the associated text to determine a first entity set corresponding to the associated text.
The specific implementation forms of steps 401 to 403 may refer to detailed descriptions in other embodiments of the present disclosure, and are not described in detail here.
In step 404, in response to that the first entity set does not include the first occurrence time, according to the second occurrence time corresponding to each second emergency in the emergency data set, a plurality of second emergency with the same type as the first event included in the first entity set within a preset time period is obtained.
It can be understood that the first entity set does not include the first occurrence time, that is, the first occurrence time is null, which indicates that the associated text does not include the occurrence time corresponding to the emergency event, that is, the first entity set corresponding to the associated text only includes the first geographical location of the first event type set.
Optionally, under the condition that the associated text does not include the emergency, a plurality of second emergency events which are similar to the release time of the associated text and have the same event type can be obtained from the emergency included in the emergency data set according to the type of the emergency described by the associated text, that is, the type of the first event in the first entity set and the release time of the associated text, so as to determine whether the associated text describes a certain second emergency.
The preset time period may be 5 days, 10 days, and the like, which is not limited in this disclosure.
For example, the release time of the associated text is 2021 year 9 month 15 day, the event type corresponding to the associated text is heavy rain, and the preset time period is 5 days, then the second incident time from 2021 year 9 month 10 day to 2021 year 9 month 15 day may be obtained from the emergency data set, and the second event type is a plurality of second emergency events of heavy rain.
Or, under the condition that the associated text does not include the emergency, a plurality of second emergency which is close to the release time of the associated text, has the same event type and is close to the geographic position may be obtained from the emergency included in the emergency data set according to the first event type, the first geographic position and the release time of the associated text corresponding to the associated text.
For example, the release time of the associated text is 2021 year 8 month 10 day, the first event type corresponding to the associated text is rainstorm, the first geographic location is XX province city, and the preset time period is 3 days, then a plurality of second emergency events with second occurrence time from 2021 year 8 month 7 day to 2021 year 8 month 10 day can be obtained from the emergency data set, the second geographic location is XX province city or XX province, and the second event type is rainstorm.
It should be noted that the above example is only a simple example, and cannot be taken as a specific limitation of the publication time, the first event type, the first geographic location, and the like of the associated text in the embodiment of the present disclosure.
Step 405, acquiring the total quantity of texts associated with each second emergency, the same number of characters between the associated texts and the texts associated with each second emergency, and a second time difference between the issuing time of the associated texts and a second occurrence time corresponding to each second emergency.
It should be noted that each emergency in the emergency data set may be associated with a plurality of texts describing the emergency.
In the embodiment of the present disclosure, if the total number of texts associated with the second emergency exceeds the third threshold, the third threshold number of texts associated with the emergency may be randomly selected to calculate the same number of characters between the texts associated with the second emergency and the associated texts, so that the calculation amount may be reduced.
Wherein, the third threshold may be 60, 80, etc., which is not limited by the present disclosure.
For example, if the total number of texts associated with the second emergency is 200 and the third threshold is 60, 60 texts may be randomly selected from the 200 texts associated with the second emergency to calculate the same number of characters as the associated texts. And combining 60 texts associated with the second emergency into one text, then performing word segmentation on the combined text and the associated text respectively, calculating whether each character in the associated text appears in the combined text, and finally determining the total number of characters appearing in the combined text of the characters in the associated text, namely the number of characters which is the same between the associated text and the text associated with the second emergency.
Optionally, in the embodiment of the present disclosure, word segmentation processing may be performed on the combined text and the associated text in any desirable manner. For example, a word segmentation device (Jieba) may be used to perform word segmentation on the combined text and the associated text. The present disclosure is not limited thereto.
And step 406, determining a second emergency associated with the associated text according to the total amount of texts associated with the second emergency, the same number of characters and the second time difference.
Optionally, the total amount of text, the same number of characters, and the second time difference associated with the second emergency may be input into a Logistic Regression (LR) model to determine whether the associated text describes the second emergency.
Alternatively, the calculation formula of the logistic regression model may be:
Logit(P)＝β0+β1Nw+β2Δt+β3Np
wherein N isWIs to turn offThe same number of characters between the associated text and the text associated with the second emergency, Δ t is a second time difference, NPThe total amount of text associated with the second incident. Beta is a beta0、β1、β2、β3The parameters of the logistic regression model may be determined during the training process of the logistic regression model, which is not limited in this disclosure.
Wherein, logit (P) is the output of the logistic regression model, and if P is 0, it indicates that the associated text description is not the second emergency, the associated text is deleted; if P is 1, it indicates that the associated text describes the second emergency, and further, the associated text may be associated with the second emergency, that is, the associated text is merged into the text set corresponding to the second emergency.
According to the embodiment of the disclosure, firstly, traversing is performed on the network information based on the reference words contained in the word stock so as to extract the candidate texts containing the reference words. Then, performing semantic analysis on the candidate text to determine an associated text which is contained in the candidate text and associated with the emergency, performing entity extraction on the associated text to determine a first entity set corresponding to the associated text, under the condition that the first entity set does not contain the first occurrence time, obtaining a plurality of second emergency events which are the same as the first event type contained in the first entity set in a preset time period according to the second occurrence time corresponding to each second emergency in the emergency data set, then obtaining the total quantity of texts associated with each second emergency, the same number of characters between the associated text and each second emergency, and a second time difference between the release time of the associated text and the second occurrence time corresponding to each second emergency, and finally obtaining the associated text quantity, the same number of characters and the second time difference according to the second emergency, a second incident associated with the associated text is determined. Therefore, under the condition that the associated text does not contain the first occurrence time, the second emergency described by the associated text can be accurately determined, and the arrangement of the text describing the emergency in the network information is realized.
Fig. 5 is a flowchart illustrating a method for monitoring an emergency event according to another embodiment of the disclosure. As shown in fig. 5, the method for monitoring an emergency event includes:
stage 1: traversing the network information based on the reference words contained in the word bank to extract candidate texts containing the reference words, and then performing semantic analysis on the candidate texts to determine whether the candidate texts are associated with the emergency or not, wherein if the candidate texts are associated with the emergency, the candidate texts are associated with the emergency.
And (2) stage: and performing entity extraction on the associated text to acquire a first event type, a first geographical position and a first generation time corresponding to the associated text.
And (3) stage: after three entities of a first event type, a first geographical position and a first occurrence time are successfully extracted from the associated text, a first similarity between a first entity set and a second entity set corresponding to each first emergency in the emergency data set is obtained, wherein the first entity set comprises the first event type, the first geographical position and the first occurrence time, the second entity set comprises a second event type, a second geographical position and a second occurrence time, the first emergency described by the associated text is determined according to the first similarity, and the associated text is stored in the first emergency corresponding to the associated text in the emergency data set.
Under the condition that the first occurrence time is not extracted from the associated text, a plurality of second emergencies close to the issuing time of the associated text are obtained from the emergency data set according to the issuing time of the associated text, then the second emergencies described by the associated text are judged by adopting a logistic regression model, and after the second emergencies described by the associated text are determined, the associated text is associated with the corresponding second emergencies.
In order to implement the above embodiments, the present disclosure further provides an emergency monitoring device.
Fig. 6 is a schematic structural diagram of an emergency monitoring device according to an embodiment of the present disclosure. As shown in fig. 6, the emergency monitoring apparatus 600 may include: a first obtaining module 610, a first determining module 620, a second determining module 630, a third determining module 640, and a fourth determining module 650.
The first obtaining module 610 is configured to traverse the network information based on the reference words included in the word bank, so as to extract candidate texts including the reference words from the network information;
a first determining module 620, configured to perform semantic analysis on the candidate texts to determine associated texts included in the candidate texts and associated with the emergency;
a second determining module 630, configured to perform entity extraction on the associated text to determine a first entity set corresponding to the associated text;
a third determining module 640, configured to determine a first similarity between the first entity set and a second entity set corresponding to each emergency in the emergency data set;
the fourth determining module 650 is configured to determine, when the first similarity between the first entity set and any one of the second entity sets is greater than the first threshold, that the associated text is an associated text of the first emergency corresponding to any one of the second entity sets.
Optionally, the second determining module 630 is specifically configured to:
acquiring a reference word set corresponding to each event type from a reference word library;
determining an association probability value between the associated text and each event type according to the occurrence frequency of each reference word in the reference word set corresponding to each event type in the associated text and the weight of each reference word;
determining a first event type corresponding to the associated text according to a second threshold value corresponding to each associated probability value and each event type;
according to the position entities contained in the position entity library, position extraction is carried out on the associated text so as to determine a first geographical position corresponding to the associated text;
and time extraction is carried out on the associated text based on a preset algorithm so as to determine the first generation time corresponding to the associated text.
Optionally, the third determining module 640 is specifically configured to:
determining a second similarity between the first event type and a second event type in the second set of entities, a third similarity between the first geographic location and a second geographic location in the second set of entities, and a fourth similarity between the first time of occurrence and a second time of occurrence in the second set of entities;
and determining the first similarity between the first entity set and the second entity set according to the second similarity, the third similarity and the fourth similarity.
Optionally, the third determining module 640 is specifically configured to:
and determining a fourth similarity according to the first time difference between the first occurrence time and the second occurrence time.
Optionally, the system further includes an update module, specifically configured to:
in response to the first geographic position being higher in grade than the second geographic position in any one of the second entity sets, updating the second geographic position in any one of the second entity sets according to the first geographic position to obtain any one of the updated second entity sets;
alternatively, the first and second electrodes may be,
and in response to the first occurrence time being absolute time and the second occurrence time in any one of the second entity sets being relative time, updating the second occurrence time in any one of the second entity sets according to the first occurrence time to obtain any one of the updated second entity sets.
Optionally, the system further includes an association module, specifically configured to:
determining a fifth similarity between any updated second entity set and each of the remaining second entity sets;
and in response to any fifth similarity being larger than the first threshold, associating the emergency corresponding to the second entity set corresponding to any fifth similarity with the updated emergency corresponding to any second entity set.
Optionally, the method further includes:
and the storage module is used for storing the association text and the first entity set into the emergency data set in an association manner in response to the fact that each first similarity is smaller than or equal to a first threshold value.
Optionally, the system further includes a fifth determining module, specifically configured to:
in response to that the first entity set does not contain the first occurrence time, acquiring a plurality of second emergency events with the same type as the first events contained in the first entity set in a preset time period according to the second occurrence time corresponding to each second emergency event in the emergency data set;
acquiring the total quantity of texts associated with each second emergency, the same number of characters between the associated texts and the texts associated with each second emergency, and a second time difference between the release time of the associated texts and a second occurrence time corresponding to each second emergency;
and determining the second emergency associated with the associated text according to the total quantity of the text associated with the second emergency, the same character number and the second time difference.
The functions and specific implementation principles of the modules in the embodiments of the present disclosure may refer to the embodiments of the methods, and are not described herein again.
The monitoring device for the emergency according to the embodiment of the disclosure first traverses network information based on reference words contained in a word bank to extract candidate texts containing the reference words from the network information, then performs semantic analysis on the candidate texts to determine associated texts contained in the candidate texts and associated with the emergency, then performs entity extraction on the associated texts to determine first entity sets corresponding to the associated texts, then determines a first similarity between the first entity sets and second entity sets corresponding to each emergency in an emergency data set, and finally determines that the associated texts are associated texts of the first emergency corresponding to any second entity sets under the condition that the first similarity between the first entity sets and any second entity sets is greater than a first threshold. Therefore, the emergency texts contained in the network information are analyzed and sorted, so that the related information of the emergency can be timely and accurately mined from massive network information, and the texts describing the same emergency can be clustered, thereby timely discovering new emergency.
In order to implement the above embodiments, the present disclosure also provides an electronic device, including: the monitoring system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the program, the monitoring system realizes the monitoring method for the emergency event according to the embodiment of the disclosure.
In order to implement the foregoing embodiments, the present disclosure further provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the method for monitoring an emergency event as set forth in the foregoing embodiments of the present disclosure.
In order to implement the foregoing embodiments, the present disclosure also proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the method for monitoring an emergency event as proposed by the foregoing embodiments of the present disclosure.
FIG. 7 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure. The electronic device 12 shown in fig. 7 is only an example and should not bring any limitations to the function and scope of use of the disclosed embodiments.
As shown in FIG. 7, electronic device 12 is embodied in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
Memory 28 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, and commonly referred to as a "hard drive"). Although not shown in FIG. 7, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the disclosure.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the embodiments described in this disclosure.
Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Moreover, computer device 12 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public Network such as the Internet via Network adapter 20. As shown, network adapter 20 communicates with the other modules of computer device 12 via bus 18. It should be appreciated that although not shown in FIG. 7, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing, for example, implementing the methods mentioned in the foregoing embodiments, by executing programs stored in the system memory 28.
According to the technical scheme, firstly, based on reference words contained in a word bank, network information is traversed, candidate texts containing the reference words are extracted from the candidate texts, then semantic analysis is carried out on the candidate texts, associated texts which are contained in the candidate texts and are associated with emergency events are determined, then entity extraction is carried out on the associated texts, a first entity set corresponding to the associated texts is determined, then first similarity between the first entity set and a second entity set corresponding to each emergency event in an emergency event data set is determined, and finally the associated texts are determined to be associated texts of the first emergency events corresponding to any second entity set under the condition that the first similarity between the first entity set and any second entity set is larger than a first threshold value. Therefore, the emergency texts contained in the network information are analyzed and sorted, so that the related information of the emergency can be timely and accurately mined from massive network information, and the texts describing the same emergency can be clustered, thereby timely discovering new emergency.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present disclosure in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present disclosure may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure, and that changes, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present disclosure.

Claims (19)

1. A method for monitoring an emergency event, comprising:
traversing the network information based on the reference words contained in the word bank to extract candidate texts containing the reference words;
performing semantic analysis on the candidate texts to determine associated texts which are contained in the candidate texts and are associated with the emergency;
entity extraction is carried out on the associated text to determine a first entity set corresponding to the associated text;
determining a first similarity between the first entity set and a second entity set corresponding to each emergency in the emergency data set;
and determining the associated text to be the associated text of the first emergency corresponding to any second entity set under the condition that the first similarity between the first entity set and any second entity set is greater than a first threshold value.
2. The method of claim 1, wherein the entity extracting the associated text to determine a first entity set corresponding to the associated text comprises:
acquiring a reference word set corresponding to each event type from the reference word library;
determining an association probability value between the associated text and each event type according to the occurrence frequency of each reference word in the reference word set corresponding to each event type in the associated text and the weight of each reference word;
determining a first event type corresponding to the associated text according to a second threshold value corresponding to each associated probability value and each event type;
according to a position entity contained in a position entity library, position extraction is carried out on the associated text so as to determine a first geographical position corresponding to the associated text;
and time extraction is carried out on the associated text based on a preset algorithm so as to determine the first generation time corresponding to the associated text.
3. The method of claim 2, wherein the determining a first similarity between the first set of entities and a second set of entities corresponding to each first emergency in the emergency data set comprises:
determining a second similarity between the first event type and a second event type in the second set of entities, a third similarity between the first geographic location and a second geographic location in the second set of entities, a fourth similarity between the first time of occurrence and a second time of occurrence in the second set of entities;
determining a first similarity between the first entity set and the second entity set according to the second similarity, the third similarity and the fourth similarity.
4. The method of claim 3, wherein determining a fourth similarity between the first occurrence time and the second occurrence time in the second set of entities comprises:
determining the fourth similarity according to a first time difference between the first occurrence time and the second occurrence time.
5. The method according to claim 3, further comprising, after the determining that the associated text is associated text of the first emergency corresponding to any of the second entity sets:
in response to the first geographic location being higher than the second geographic location in any of the second entity sets, updating the second geographic location in any of the second entity sets according to the first geographic location to obtain any of the updated second entity sets;
alternatively, the first and second electrodes may be,
and in response to that the first occurrence time is absolute time and the second occurrence time in any one of the second entity sets is relative time, updating the second occurrence time in any one of the second entity sets according to the first occurrence time to obtain any one of the updated second entity sets.
6. The method of claim 5, further comprising, after the obtaining any updated second set of entities:
determining a fifth similarity between any of the updated second entity sets and each of the remaining second entity sets;
and in response to any fifth similarity being larger than the first threshold, associating the emergency corresponding to the second entity set corresponding to the any fifth similarity with the updated emergency corresponding to any second entity set.
7. The method of claims 1-6, wherein after the determining the first similarity between the first set of entities and the second set of entities corresponding to each emergency in the emergency data set, further comprising:
and in response to each first similarity being smaller than or equal to the first threshold, associating the associated text and the first entity set into the emergency data set.
8. The method of claim 2, wherein after the entity extracting the associated text to determine the first entity set corresponding to the associated text, further comprising:
in response to that the first entity set does not contain the first occurrence time, acquiring a plurality of second emergency events with the same type as the first event contained in the first entity set in a preset time period according to the second occurrence time corresponding to each second emergency event in the emergency data set;
acquiring the total quantity of texts associated with each second emergency, the same number of characters between the associated texts and the texts associated with each second emergency, and a second time difference between the issuing time of the associated texts and a second occurrence time corresponding to each second emergency;
and determining a second emergency associated with the associated text according to the total amount of the text associated with the second emergency, the same number of characters and the second time difference.
9. An emergency monitoring device, comprising:
the first acquisition module is used for traversing the network information based on the reference words contained in the word bank so as to extract candidate texts containing the reference words;
the first determining module is used for performing semantic analysis on the candidate texts to determine associated texts which are contained in the candidate texts and are associated with the emergency;
a second determining module, configured to perform entity extraction on the associated text to determine a first entity set corresponding to the associated text;
a third determining module, configured to determine a first similarity between the first entity set and a second entity set corresponding to each emergency in the emergency data set;
a fourth determining module, configured to determine that the associated text is an associated text of a first emergency corresponding to any one of the second entity sets when a first similarity between the first entity set and the any one of the second entity sets is greater than a first threshold.
10. The apparatus of claim 9, wherein the second determining module is specifically configured to:
acquiring a reference word set corresponding to each event type from the reference word library;
determining an association probability value between the associated text and each event type according to the occurrence frequency of each reference word in the reference word set corresponding to each event type in the associated text and the weight of each reference word;
determining a first event type corresponding to the associated text according to a second threshold value corresponding to each associated probability value and each event type;
according to a position entity contained in a position entity library, position extraction is carried out on the associated text so as to determine a first geographical position corresponding to the associated text;
and time extraction is carried out on the associated text based on a preset algorithm so as to determine the first generation time corresponding to the associated text.
11. The apparatus of claim 10, wherein the third determining module is specifically configured to:
determining a second similarity between the first event type and a second event type in the second set of entities, a third similarity between the first geographic location and a second geographic location in the second set of entities, a fourth similarity between the first time of occurrence and a second time of occurrence in the second set of entities;
determining a first similarity between the first entity set and the second entity set according to the second similarity, the third similarity and the fourth similarity.
12. The apparatus of claim 11, wherein the third determining module is specifically configured to:
determining the fourth similarity according to a first time difference between the first occurrence time and the second occurrence time.
13. The apparatus according to claim 11, further comprising an update module, specifically configured to:
in response to the first geographic location being higher than the second geographic location in any of the second entity sets, updating the second geographic location in any of the second entity sets according to the first geographic location to obtain any of the updated second entity sets;
alternatively, the first and second electrodes may be,
and in response to that the first occurrence time is absolute time and the second occurrence time in any one of the second entity sets is relative time, updating the second occurrence time in any one of the second entity sets according to the first occurrence time to obtain any one of the updated second entity sets.
14. The apparatus according to claim 13, further comprising an association module, specifically configured to:
determining a fifth similarity between any of the updated second entity sets and each of the remaining second entity sets;
and in response to any fifth similarity being greater than the first threshold, associating the emergency corresponding to the second entity set corresponding to the any fifth similarity with the updated emergency corresponding to any second entity set.
15. The apparatus of claims 9-14, further comprising:
and the storage module is used for storing the association text and the first entity set into the emergency data set in an association manner in response to the fact that each first similarity is smaller than or equal to the first threshold value.
16. The apparatus of claim 10, further comprising a fifth determining module, specifically configured to:
in response to that the first entity set does not contain the first occurrence time, acquiring a plurality of second emergency events with the same type as the first event contained in the first entity set in a preset time period according to the second occurrence time corresponding to each second emergency event in the emergency data set;
acquiring the total quantity of texts associated with each second emergency, the same number of characters between the associated texts and the texts associated with each second emergency, and a second time difference between the issuing time of the associated texts and a second occurrence time corresponding to each second emergency;
and determining a second emergency associated with the associated text according to the total amount of the text associated with the second emergency, the same number of characters and the second time difference.
17. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the method for monitoring an emergency event according to any one of claims 1 to 8.
18. A computer-readable storage medium, storing a computer program, wherein the computer program, when executed by a processor, implements the method for monitoring an emergency event according to any one of claims 1-8.
19. A computer program product, characterized in that it comprises a computer program which, when being executed by a processor, carries out the method of monitoring of emergency events according to any one of claims 1-8.
CN202111640233.4A 2021-12-29 2021-12-29 Method and device for monitoring emergency, electronic equipment and storage medium Pending CN114528396A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202111640233.4A CN114528396A (en) 2021-12-29 2021-12-29 Method and device for monitoring emergency, electronic equipment and storage medium
PCT/CN2022/142554 WO2023125589A1 (en) 2021-12-29 2022-12-27 Emergency monitoring method and apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111640233.4A CN114528396A (en) 2021-12-29 2021-12-29 Method and device for monitoring emergency, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114528396A true CN114528396A (en) 2022-05-24

Family

ID=81620207

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111640233.4A Pending CN114528396A (en) 2021-12-29 2021-12-29 Method and device for monitoring emergency, electronic equipment and storage medium

Country Status (2)

Country Link
CN (1) CN114528396A (en)
WO (1) WO2023125589A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023125589A1 (en) * 2021-12-29 2023-07-06 北京辰安科技股份有限公司 Emergency monitoring method and apparatus
CN117557946A (en) * 2024-01-10 2024-02-13 中国科学技术大学 Video event description and attribution generation method, system, equipment and storage medium
CN117557946B (en) * 2024-01-10 2024-05-17 中国科学技术大学 Video event description and attribution generation method, system, equipment and storage medium

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117713386B (en) * 2024-02-05 2024-04-16 国网山东省电力公司东营市河口区供电公司 Intelligent monitoring control method and device for power grid

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106886567B (en) * 2017-01-12 2019-11-08 北京航空航天大学 Microblogging incident detection method and device based on semantic extension
CN108595519A (en) * 2018-03-26 2018-09-28 平安科技（深圳）有限公司 Focus incident sorting technique, device and storage medium
CN112100374A (en) * 2020-08-28 2020-12-18 清华大学 Text clustering method and device, electronic equipment and storage medium
CN113836267A (en) * 2021-09-24 2021-12-24 国家市场监督管理总局信息中心 Method and device for detecting emergency
CN114528396A (en) * 2021-12-29 2022-05-24 北京辰安科技股份有限公司 Method and device for monitoring emergency, electronic equipment and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023125589A1 (en) * 2021-12-29 2023-07-06 北京辰安科技股份有限公司 Emergency monitoring method and apparatus
CN117557946A (en) * 2024-01-10 2024-02-13 中国科学技术大学 Video event description and attribution generation method, system, equipment and storage medium
CN117557946B (en) * 2024-01-10 2024-05-17 中国科学技术大学 Video event description and attribution generation method, system, equipment and storage medium

Also Published As

Publication number Publication date
WO2023125589A1 (en) 2023-07-06

Similar Documents

Publication Publication Date Title
Zou et al. Mining Twitter data for improved understanding of disaster resilience
Yao et al. Towards resilient and smart cities: A real-time urban analytical and geo-visual system for social media streaming data
Wang et al. Spatiotemporal and semantic information extraction from Web news reports about natural hazards
Middleton et al. Real-time crisis mapping of natural disasters using social media
Zhou et al. VictimFinder: Harvesting rescue requests in disaster response from social media with BERT
WO2023125589A1 (en) Emergency monitoring method and apparatus
CN110188979B (en) Water industry emergency decision generation method and device
KR101644429B1 (en) System and method for extraction performance improvement of unstructured text
CN112863683B (en) Medical record quality control method and device based on artificial intelligence, computer equipment and storage medium
Farnaghi et al. Dynamic spatio-temporal tweet mining for event detection: a case study of hurricane florence
CN111723260A (en) Method and device for acquiring recommended content, electronic equipment and readable storage medium
Wang et al. Urban crisis detection technique: A spatial and data driven approach based on latent Dirichlet allocation (LDA) topic modeling
Liu et al. Online urban-waterlogging monitoring based on a recurrent neural network for classification of microblogging text
CN114240552A (en) Product recommendation method, device, equipment and medium based on deep clustering algorithm
Yue et al. Using twitter data to determine hurricane category: An experiment
Xu et al. Hierarchical difference in attention allocation of local governments: explaining change and stability in safety management
Zhai A multi-level analytic framework for disaster situational awareness using Twitter data
CN114637847A (en) Model training method, text classification method and device, equipment and medium
Hao et al. Assessing disaster impact in real time: Data-driven system integrating humans, hazards, and the built environment
Han et al. Multi-spatial scale event detection from geo-tagged tweet streams via power-law verification
CN113761867A (en) Address recognition method and device, computer equipment and storage medium
CN114625971B (en) Interest point recommendation method and device based on user sign-in
CN113836308B (en) Network big data long text multi-label classification method, system, device and medium
Duong et al. Neurosymbolic AI for mining public opinions about wildfires
Huang Integration degree of risk in terms of scene and application

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination