Emergency monitoring method, device, electronic equipment and storage medium

Abstract

The present disclosure proposes a monitoring method, device, electronic device and storage medium for emergencies, and relates to the field of information management technology. The method includes: based on reference words, extracting candidate texts containing reference words from network information by traversing; performing semantic analysis on the candidate texts to determine the associated texts associated with the emergencies; performing entity extraction on the associated texts to determine the first entity set corresponding to the associated texts; determining the first similarity between the first entity set and the second entity set corresponding to each emergencies in the emergencies data set; and determining that the associated text is the associated text of the first emergencies 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. Thus, by analyzing and sorting the emergencies texts contained in the network information, new emergencies can be discovered in a timely manner from the massive network information, and relevant information of emergencies can be accurately mined.

Description

Technical Field

[0001] The present disclosure relates to the field of information management technology, and in particular to a monitoring method, device, electronic device and storage medium for emergencies. Background Art

[0002] With the development of Internet technology, more and more users will publish various information on the Internet. This includes emergencies, such as infectious diseases, typhoons, floods, explosions, nuclear accidents, etc. Emergency management personnel of emergencies can learn about the situation of emergencies in a timely manner through information on the Internet. However, it is not easy to mine relevant information about emergencies in a timely and accurate manner from massive amounts of network information. Therefore, how to obtain relevant information about emergencies from a large amount of network information has become a key research direction. Summary of the invention

[0003] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0004] The first embodiment of the present disclosure provides a method for monitoring an emergency, including:

[0005] Based on the reference words contained in the vocabulary, traversing the network information to extract candidate texts containing the reference words;

[0006] Performing semantic analysis on the candidate text to determine associated texts contained in the candidate text that are associated with the emergency event;

[0007] Performing entity extraction on the associated text to determine a first entity set corresponding to the associated text;

[0008] Determine a first similarity between the first entity set and a second entity set corresponding to each emergency event in the emergency event data set;

[0009] When the first similarity between the first entity set and any second entity set is greater than a first threshold, the associated text is determined to be the associated text of the first emergency event corresponding to any second entity set.

[0010] The second embodiment of the present disclosure provides a monitoring device for an emergency, including:

[0011] A first acquisition module, configured to traverse network information based on reference words contained in the vocabulary to extract candidate texts containing the reference words;

[0012] A first determination module is used to perform semantic analysis on the candidate text to determine associated texts contained in the candidate text that are associated with the emergency event;

[0013] A second determination module is used to perform entity extraction on the associated text to determine a first entity set corresponding to the associated text;

[0014] A third determination module, configured to determine a first similarity between the first entity set and a second entity set corresponding to each emergency event in the emergency event data set;

[0015] The fourth determination module is configured to determine, when the first similarity between the first entity set and any second entity set is greater than a first threshold, that the associated text is associated text of a first emergency event corresponding to any second entity set.

[0016] The third aspect embodiment of the present disclosure proposes an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the emergency event monitoring method proposed in the first aspect embodiment of the present disclosure is implemented.

[0017] The fourth aspect of the present disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for monitoring emergencies provided in the first aspect of the present disclosure is implemented.

[0018] The fifth aspect of the present disclosure provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the emergency event monitoring method provided in the first aspect of the present disclosure.

[0019] The emergency monitoring method, device, electronic device and storage medium provided by the present disclosure have the following beneficial effects:

[0020] In the disclosed embodiment, firstly, based on the reference words contained in the word library, the network information is traversed to extract the candidate text containing the reference words, then the candidate text is semantically analyzed to determine the associated text associated with the emergency contained in the candidate text, then the associated text is entity extracted to determine the first entity set corresponding to the associated text, then the first similarity between the first entity set and the second entity set corresponding to each emergency in the emergency data set is determined, and finally, when the first similarity between the first entity set and any second entity set is greater than the first threshold, the associated text is determined to be the associated text of the first emergency corresponding to any second entity set. Thus, the emergency text contained in the network information is analyzed and sorted, which can not only timely and accurately mine the relevant information of the emergency from the massive network information, but also cluster the text describing the same emergency, so that new emergencies can be discovered in a timely manner.

[0021] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0023] Figure 1 A flowchart of a method for monitoring an emergency event provided by an embodiment of the present disclosure;

[0024] Figure 2 A schematic diagram of a flow chart of a method for monitoring an emergency event provided by another embodiment of the present disclosure;

[0025] Figure 3 A schematic diagram of performing semantic analysis on a candidate text provided by an embodiment of the present disclosure;

[0026] Figure 4 A schematic diagram of a flow chart of a method for monitoring an emergency event provided by another embodiment of the present disclosure;

[0027] Figure 5 A schematic diagram of a flow chart of a method for monitoring an emergency event provided by another embodiment of the present disclosure;

[0028] Figure 6 A schematic diagram of the structure of a monitoring device for an emergency event provided by an embodiment of the present disclosure;

[0029] Figure 7 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0030] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0031] The following describes the emergency monitoring method, device, electronic device and storage medium according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0032] Figure 1 A flowchart of a method for monitoring an emergency event provided by an embodiment of the present disclosure is provided.

[0033] The embodiment of the present disclosure takes the example of the emergency event monitoring method being configured in an emergency event monitoring device. The emergency event monitoring device can be applied to any electronic device so that the electronic device can perform the emergency event monitoring function.

[0034] Among them, the electronic device can be a personal computer (PC), a cloud device, a mobile device, etc. The mobile device can be, for example, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, a car device, etc., which are hardware devices with various operating systems, touch screens and / or display screens.

[0035] like Figure 1 As shown, the method for monitoring an emergency may include the following steps:

[0036] Step 101 , based on the reference words contained in the vocabulary, traverse the network information to extract candidate texts containing the reference words.

[0037] Optionally, the word library may include reference words corresponding to each type of emergency event, and the reference words included in the word library may be predetermined.

[0038] Among them, emergencies can include natural disasters, accidents and disasters, public health incidents and social security incidents, etc. For example, natural disasters can also include: rainstorms, tornadoes, earthquakes, etc.; accidents and disasters can include: car accidents, fires, etc.; public health incidents can include infectious diseases, food poisoning, etc.; social security incidents can include: terrorist attacks, large-scale gatherings, etc.

[0039] It is understandable that each type of reference event has its corresponding reference word. For example, a rainstorm event is usually accompanied by a strong wind, so strong wind can be a reference word corresponding to the rainstorm event. The candidate text containing "strong wind" extracted from network information can be "a yellow warning for strong winds was issued in a certain area today."

[0040] Step 102: semantically analyze the candidate text to determine the associated text contained in the candidate text and associated with the emergency event.

[0041] It should be noted that an emergency event refers to an unconventional event that does not occur frequently, so even if the candidate text obtained contains a candidate word, the candidate text is not a text related to the emergency event. Therefore, after obtaining the candidate text, a semantic analysis can be performed on the candidate text to determine whether the candidate text describes an emergency event.

[0042] Optionally, an attention-enhanced bidirectional long short-term memory model (BERT-Att-BiLSTM model) may be used to perform semantic analysis on the candidate texts to determine associated texts contained in the candidate texts that are associated with the emergency.

[0043] Alternatively, Latent Dirichlet Allocation (LDA) may be used to perform semantic analysis on the candidate texts to determine associated texts contained in the candidate texts that are associated with the emergency event.

[0044] It should be noted that, in the embodiments of the present disclosure, any other desirable manner may be adopted to perform semantic analysis on the candidate text to determine the associated text associated with the emergency event contained in the candidate text. The present disclosure does not limit this.

[0045] Step 103: perform entity extraction on the associated text to determine a first entity set corresponding to the associated text.

[0046] Optionally, the first entity set may include a first event type, a first geographical location, and a first occurrence time.

[0047] The first event type may be the type of the emergency event described in the associated text. For example, the first event type corresponding to the associated text may be a rainstorm, a tornado, etc., which is not limited in the present disclosure.

[0048] The first geographical location may be the geographical location where the emergency described in the associated text occurs. For example, the first geographical location corresponding to the associated text may be XX county, XX city, XX province, or XX province, etc., which is not limited in the present disclosure.

[0049] Among them, the first occurrence time can be the event information of the occurrence of the emergency described in the associated text. For example, the first occurrence time corresponding to the associated text can be October 20, 2020, 2008, etc., and this disclosure does not limit this.

[0050] It should be noted that if the associated text does not contain the occurrence time corresponding to the emergency, the first occurrence time in the first entity set corresponding to the associated text is empty; or, if the associated text does not contain the geographical location corresponding to the emergency time, the first geographical location in the first entity set corresponding to the associated text is empty.

[0051] Step 104: determine a first similarity between the first entity set and a second entity set corresponding to each emergency event in the emergency event data set.

[0052] Optionally, the second entity set corresponding to each emergency event may include a second event type, a second geographical location, and a second occurrence time.

[0053] Optionally, when 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 event in the emergency event data set can be determined based on the second similarity between the first event type and the second event type, the third similarity between the first geographic location and the second geographic location in the second entity set, and the fourth similarity between the first occurrence time and the second occurrence time in the second entity set.

[0054] Alternatively, when 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 is calculated using the Euclidean distance formula or the Manhattan distance formula. Alternatively, the cosine similarity between the first entity set and the second entity set can be calculated and the cosine similarity can be used as the first similarity between the first entity set and the second entity set. This disclosure does not limit this.

[0055] Step 105 : when the first similarity between the first entity set and any second entity set is greater than a first threshold, determining that the associated text is the associated text of the first emergency event corresponding to any second entity set.

[0056] 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 means that the associated text and the first emergency event corresponding to any second entity set describe the same emergency event. Therefore, the associated text can be associated with the first emergency event corresponding to any second entity set, that is, the associated text can be stored in the set corresponding to the first emergency event corresponding to any second entity set in the emergency data set.

[0057] Optionally, if each first similarity is less than or equal to the first threshold, it means that the emergency data set does not contain the emergency described by the associated text, so the associated text and the first entity set can be associated and stored in the emergency data set as a new emergency. In this way, the occurrence of new emergencies can be accurately monitored, so that emergency management personnel can monitor the occurrence of new emergencies in a timely manner, and take emergency measures for the emergencies in a timely manner according to the first event type, the first geographical location, and the first occurrence event in the first entity set corresponding to the emergency.

[0058] In the disclosed embodiment, firstly, based on the reference words contained in the word library, the network information is traversed to extract the candidate text containing the reference words, then the candidate text is semantically analyzed to determine the associated text associated with the emergency contained in the candidate text, then the associated text is entity extracted to determine the first entity set corresponding to the associated text, then the first similarity between the first entity set and the second entity set corresponding to each emergency in the emergency data set is determined, and finally, when the first similarity between the first entity set and any second entity set is greater than the first threshold, the associated text is determined to be the associated text of the first emergency corresponding to any second entity set. Thus, the emergency text contained in the network information is analyzed and sorted, which can not only timely and accurately mine the relevant information of the emergency from the massive network information, but also cluster the text describing the same emergency, so that new emergencies can be discovered in a timely manner.

[0059] Figure 2 A flow chart of a method for monitoring an emergency event provided by an embodiment of the present disclosure is shown as follows: Figure 2 As shown, the method for monitoring an emergency may include the following steps:

[0060] Step 201 , based on the reference words contained in the vocabulary, traverse the network information to extract candidate texts containing the reference words.

[0061] In the disclosed embodiment, multiple texts related to each type of emergency event can be randomly obtained first, and the multiple texts can be merged into one text. Then, the merged text can be segmented to obtain the words contained in the merged text, and the word frequency statistics are performed on each word, that is, the number of times each word appears in the merged text is obtained, and then the words with a word frequency greater than a preset threshold are used as reference words corresponding to this type of emergency event.

[0062] It should be noted that the number of reference words corresponding to each type of emergency event may be one or more, and the present disclosure does not limit this.

[0063] Optionally, after obtaining the reference words, the weight corresponding to each reference word may be determined according to the word frequency corresponding to each reference word, wherein the weight is positively correlated with the word frequency, that is, the greater the word frequency corresponding to the reference word, the greater the corresponding weight.

[0064] Optionally, after using the reference words to capture the candidate texts, the reference words and the corresponding weights may be adjusted according to the candidate texts.

[0065] In the disclosed embodiment, after obtaining multiple texts related to each type of emergency, each text may be preprocessed by deleting uniform resource locators (URLs), spaces, punctuation marks, etc., and then each preprocessed text may be encoded into the same encoding format. For example, each text may be unified into the encoding format of UTF-8 (Universal Character Set / Unicode Transformation Format). UTF-8 is a variable-length character encoding for Unicode.

[0066] Step 202: semantically analyze the candidate text to determine the associated text contained in the candidate text and associated with the emergency event.

[0067] In the disclosed embodiment, Figure 3 A schematic diagram of performing semantic analysis on a candidate text provided by an embodiment of the present disclosure is shown in FIG. Figure 3 As shown in FIG. 1 , the attention-enhanced bidirectional long short-term memory model (BERT-Att-BiLSTM model) can be used to perform semantic analysis on the candidate text to determine the associated text contained in the candidate text that is associated with the emergency. That is, the candidate text is first input into BERT to obtain the semantic representation of the candidate text, and then the semantic representation of the candidate text is input into Att-BiLSTM to further perform semantic analysis on the semantic representation of the candidate text to determine whether the candidate text is the associated text of the emergency.

[0068] In the disclosed embodiment, BERT (Bidirectional Encoder Representation from Transformers) is a word vector generation model that can adopt a bidirectional transformer architecture and can be trained with context in all layers of the model. The pre-trained BERT Chinese basic model (BERT-Base-Chinese) is used here, which can include a 12-layer transformer structure and 12 self-attention mechanisms, and the vector dimension is 768.

[0069] It should be noted that in the embodiments of the present disclosure, there is no limitation on the number of layers of the transformer structure, the number of self-attention mechanisms, and the vector dimension.

[0070] In the embodiment of the present disclosure, the bidirectional long short-term memory model (Bi-directional Long Short-Term Memory, BiLSTM) layer includes a forward LSTM and reverse LSTM Its output is expressed as:

[0071]

[0072] in, is the forward information of character i in sentence s, is the backward information of character i in sentence s, both of which are hidden vectors. The attention weight of each character is expressed as follows:

[0073]

[0074] in, is the attention score, V is the weight, V to the power of T is the transposed matrix of V, ω s is the weight corresponding to sentence s in the attention mechanism, b s is the bias corresponding to sentence s in the attention mechanism, tanh(.) is the hyperbolic tangent function, T is the number of characters, is the attention weight of character i in sentence s.

[0075] Among them, the output of the context representation is:

[0076]

[0077] Among them, F is the semantic feature of the candidate text.

[0078] Among them, the logistic regression (Softmax) layer is used to generate conditional probabilities in the class space according to the semantic features of the candidate text, so as to determine whether the candidate text is the associated text of the emergency.

[0079] Step 203: perform entity extraction on the associated text to determine a first entity set corresponding to the associated text.

[0080] Optionally, you can first obtain a reference word set corresponding to each event type from a reference word library, and then determine the association probability value between the associated text and each event type based on the number of occurrences 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. Then, based on each association probability value and a second threshold corresponding to each event type, determine the first event type corresponding to the associated text.

[0081] The calculation formula of the association probability value can be:

[0082] P e =∑ k C k W k

[0083] Among them, P e The association probability value between the associated text and each event type e is C kis the number of occurrences of the reference word k, W k is the weight corresponding to the reference word k.

[0084] If P e If the value of is greater than the second threshold corresponding to event type e, the first event type corresponding to the associated text is for event type e.

[0085] It should be noted that since there are often chain reactions between natural disasters, for example, typhoons are usually accompanied by heavy rains, one related text can also correspond to multiple event types. If a related post describes both a typhoon and the heavy rain caused by the typhoon, the related post can correspond to the heavy rain event type and the typhoon event type.

[0086] Optionally, the location of the associated text may be extracted according to the location entities included in the location entity library to determine the first geographical location corresponding to the associated text.

[0087] Optionally, the associated text may contain a specific location, such as XX county, XX city, XX province; or it may not contain a specific location, but contain a building that can represent the specific location, and then the location corresponding to the emergency described in the associated text can be determined based on the building.

[0088] In the embodiment of the present disclosure, the specific location entity extraction can be performed on the associated text according to the first location entity library to obtain the specific location of the emergency described in the associated text. If the specific location is not extracted, the building entity is further extracted from the content contained in the associated text according to the second location entity library, and then the specific location of the emergency described in the associated text is obtained according to the geographical location of the building entity.

[0089] The first location entity library contains specific geographical locations, and the second entity library contains buildings that can represent geographical locations.

[0090] Optionally, after determining the specific location of the emergency described in the associated text, the specific location may be structured, that is, represented in the form of XX village / town, XX county / district, XX province, XX city.

[0091] In the disclosed embodiment, if the associated text does not contain location information, the associated text is deleted and the emergency event associated with it is no longer determined.

[0092] Optionally, time extraction may be performed on the associated text based on a preset algorithm to determine the first occurrence time corresponding to the associated text.

[0093] Optionally, in the embodiment of the present disclosure, any desirable method can be adopted to extract the time of the associated text to determine the first occurrence time corresponding to the associated text. For example, a regular expression can be used to extract the time information contained in the associated text. The present disclosure does not limit this.

[0094] In the disclosed embodiment, if the time information extracted from the associated text is an absolute time, such as XX hours and XX minutes on XX month and XX day of XXXX year, the absolute information can be directly used as the first occurrence time corresponding to the associated text. If the time information extracted from the associated text is information such as yesterday, early morning, three days ago, etc., and then the first occurrence time corresponding to the associated text is determined according to the release time of the associated text, the first occurrence time at this time is relative time. For example, if the release time of the associated text is March 5, 2020, and the time information contained in the associated text is yesterday, then the first time information corresponding to the associated text is March 4, 2020.

[0095] Step 204 , determine a second similarity between the first event type and the second event type in the second entity set, 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.

[0096] It can be understood that if the associated text and a first emergency event in the emergency data set describe the same emergency event, the first event type corresponding to the associated text should be the same as the second event type corresponding to the first emergency event. 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.

[0097] In the embodiment of the present disclosure, if the first event type is the same as the second event type, the difference between the first geographical location and the second geographical location is small, and the difference between the first occurrence time and the second occurrence time is also small, then the associated event may describe the first emergency event corresponding to the second entity set. Therefore, when the first event type is the same as the second event type, the third similarity between the first geographical location and the second geographical location 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, thereby reducing the amount of calculation.

[0098] Optionally, the third similarity between the first geographical location and the second geographical location in the second entity set can be determined based on the level of the first geographical location and the level of the second geographical location. The more detailed the geographical location is, the higher the level is. For example, if the first geographical location includes XX province XX city XX county / district XX village / town, its level is the highest.

[0099] For example, if the first geographical location and the second geographical location are in the same village / town, the third similarity can be 0.8; if the first geographical location and the second geographical location are in the same county / district, and the first geographical location or the second geographical location lacks village / town information, the third similarity can be 0.6; if the first geographical location and the second geographical location are in the same city, and the first geographical location or the second geographical location lacks county / district information, the third similarity can be 0.4; if the first geographical location and the second geographical location are in the same province, and the first geographical location or the second geographical location lacks urban area information, the third similarity can be 0.2; otherwise, the third similarity can be 0.

[0100] It should be noted that the above examples are merely simple illustrations and cannot be used as specific limitations on the third similarity in the embodiments of the present disclosure.

[0101] Optionally, the fourth similarity may be determined according to a first time difference between the first occurrence time and the second occurrence time.

[0102] For example, if the first time difference is less than 1 minute, the fourth similarity may be 0.9; if 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.

[0103] It should be noted that the above examples are merely simple illustrations and cannot be used as specific limitations on the fourth similarity in the embodiments of the present disclosure.

[0104] 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.

[0105] It should be noted that if the associated text and a first emergency in the emergency data set describe the same emergency, the first event type corresponding to the associated text should be exactly the same as the second event type corresponding to the first emergency. Therefore, the second similarity plays a decisive role in determining the first similarity.

[0106] The calculation formula of the first similarity may be:

[0107] S1=S2×(aS3+bS4)

[0108] Among them, S1 is the first similarity, S2 is the second similarity, S3 is the third similarity, S4 is the fourth similarity, a is the weight corresponding to the third similarity, and b is the weight corresponding to the fourth similarity.

[0109] The value of a may be 0.5, and the value of b may be 0.5, which is not limited in the present disclosure.

[0110] Step 206 : when the first similarity between the first entity set and any second entity set is greater than a first threshold, determine that the associated text is the associated text of the first emergency event corresponding to any second entity set.

[0111] Step 207: Update any second entity set according to the first entity set to obtain any updated second entity set.

[0112] It is understandable that the second occurrence time and the second geographic location in the second entity set corresponding to each first emergency event in the emergency data set may not be particularly detailed. If the newly detected associated text contains more specific first occurrence events and first geographic locations, the second entity set corresponding to the first emergency event described in the associated text can be updated to make the information of the first emergency event more accurate.

[0113] Optionally, when the level of the first geographical location is higher than the level of the second geographical location in any second entity set, the second geographical location in any second entity set is updated according to the first geographical location to obtain an updated second entity set.

[0114] For example, the first geographical location corresponding to the associated text is XX town, XX city, XX county, XX province, and the second geographical location included in any second entity set is XX province. The level of the first geographical location is higher than the level of the second geographical location. The second geographical location in the second entity set can be updated to XX town, XX city, XX county, XX province.

[0115] Alternatively, when the first occurrence time is an absolute time and the second occurrence time in any second entity set is a relative time, the second occurrence event in any second entity set is updated according to the first occurrence time to obtain an updated second entity set.

[0116] For example, the first occurrence time corresponding to the associated text is the absolute time 10:00 on October 22, 2016, and the second occurrence time contained in any second entity set is a relative time calculated based on time information such as "early morning" or "yesterday", then the second occurrence time in the second entity set can be updated to 10:00 on October 22, 2016.

[0117] In the embodiment of the present disclosure, if the first entity set is completely identical to any second entity set, there is no need to update any second entity set according to the first entity set.

[0118] In the disclosed embodiment, the second entity set corresponding to the first emergency event described by the associated text is updated according to the first entity set corresponding to the associated text to obtain an updated second entity set, so that the occurrence time and location corresponding to each emergency event in the emergency database can be more accurate, thereby facilitating relevant staff to take processing measures based on the specific information of the emergency time.

[0119] Step 208 : determining a fifth similarity between any updated second entity set and each of the remaining second entity sets.

[0120] 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 embodiment of the present disclosure, and will not be described in detail here.

[0121] Step 209 : in response to any fifth similarity being greater than the first threshold, associating the emergency event corresponding to the second entity set corresponding to any fifth similarity with the emergency event corresponding to any updated second entity set.

[0122] It can be understood that when any fifth similarity is greater than the first threshold, it means that there are other first emergency events in the emergency data set that are the same as the first emergency event described in the associated text, so the two sets describing the same emergency event can be merged.

[0123] In the disclosed embodiment, after associating the emergency event corresponding to the second entity set corresponding to any fifth similarity with the emergency event corresponding to any updated second entity set, the second entity set corresponding to any fifth similarity can also be updated according to any updated second entity set, that is, step 207, step 208 and step 209 are looped until the entity sets corresponding to the two emergencies are exactly the same.

[0124] In the disclosed embodiment, first, based on the reference words contained in the word library, the network information is traversed to extract the candidate text containing the reference words, then the candidate text is semantically analyzed to determine the associated text associated with the emergency contained in the candidate text, the associated text is entity extracted to determine the first entity set corresponding to the associated text, then the first similarity between the first entity set and the second entity set corresponding to each first emergency is obtained, and when the first similarity between the first entity set and any second entity set is greater than the first threshold, the associated text is determined to be the associated text of the first emergency corresponding to any second entity set, and then any second entity set is updated according to the first entity set to obtain any updated second entity set, and the fifth similarity between any updated second entity set and each of the remaining second entity sets is determined, and in response to any fifth similarity being greater than the first threshold, the emergency corresponding to the second entity set corresponding to any fifth similarity is associated with the emergency corresponding to any updated second entity set. Thus, 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 discovered associated text, so that the relevant information of the acquired emergency is more accurate.

[0125] Figure 4 A flow chart of a method for monitoring an emergency event provided by another embodiment of the present disclosure is shown as follows: Figure 4 As shown, the method for monitoring an emergency may include the following steps:

[0126] Step 401 , based on the reference words contained in the vocabulary, traverse the network information to extract candidate texts containing the reference words.

[0127] Step 402: semantically analyze the candidate text to determine the associated text contained in the candidate text and associated with the emergency event.

[0128] Step 403: perform entity extraction on the associated text to determine a first entity set corresponding to the associated text.

[0129] The specific implementation forms of steps 401 to 403 may refer to the detailed descriptions in other embodiments of the present disclosure and will not be described in detail here.

[0130] Step 404 , in response to the first entity set not including the first occurrence time, a plurality of second emergency events of the same type as the first event included in the first entity set within a preset time period are acquired according to the second occurrence time corresponding to each second emergency event in the emergency event data set.

[0131] It is understandable that the first entity set does not include the first occurrence time, that is, the first occurrence time is empty, which means 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 event type set and the first geographic location.

[0132] Optionally, when the associated text does not contain an emergency event, based on the type of emergency event described in the associated text, i.e., the first event type in the first entity set, and the release time of the associated text, multiple second emergency events with a similar release time to the associated text and the same event type can be obtained from the emergency events included in the emergency event data set, thereby determining whether the associated text describes a certain second emergency event.

[0133] The preset period may be 5 days, 10 days, etc., which is not limited in the present disclosure.

[0134] For example, the release time of the associated text is September 15, 2021, the event type corresponding to the associated text is heavy rain, and the preset time period is 5 days. Then, multiple second emergency events with the second occurrence time between September 10, 2021 and September 15, 2021 and the second event type being heavy rain can be obtained from the emergency data set.

[0135] Alternatively, when the associated text does not contain any emergency events, it is also possible to obtain multiple second emergency events with a similar release time to the associated text, the same event type, and a similar geographical location from the emergencies included in the emergency event data set based on the first event type corresponding to the associated text, the first geographical location, and the release time of the associated text.

[0136] For example, the release time of the associated text is August 10, 2021, the first event type corresponding to the associated text is heavy rain, the first geographical location is XX city, XX province, and the preset time period is 3 days. Then, multiple second emergencies with the second occurrence time between August 7, 2021 and August 10, 2021, the second geographical location is XX city, XX province or XX province, and the second event type is heavy rain can be obtained from the emergency data set.

[0137] It should be noted that the above examples are merely simple illustrations and cannot be used as specific limitations on the release time of the associated text, the first event type, the first geographical location, etc. in the embodiments of the present disclosure.

[0138] Step 405 , obtaining the total number of texts associated with each second emergency event, the number of identical characters between the associated text and the text associated with each second emergency event, and the second time difference between the release time of the associated text and the second occurrence time corresponding to each second emergency event.

[0139] It should be noted that each emergency event in the emergency event dataset may be associated with multiple texts describing the emergency event.

[0140] In an embodiment of the present disclosure, if the total number of texts associated with the second emergency event exceeds a third threshold, a third threshold number of texts associated with the emergency event can be randomly selected to calculate the number of identical characters between the text associated with the second emergency event and the associated text, thereby reducing the amount of calculation.

[0141] The third threshold may be 60, 80, etc., which is not limited in the present disclosure.

[0142] For example, if the total number of texts associated with the second emergency event is 200 and the third threshold is 60, 60 texts can be randomly selected from the 200 texts associated with the second emergency event to calculate the number of identical characters between the associated texts. The 60 texts associated with the second emergency event are merged into one text, and then the merged text and the associated text are segmented to calculate whether each character in the associated text appears in the merged text. Finally, the total number of characters in the associated text that appear in the merged text is determined, which is the number of identical characters between the associated text and the text associated with the second emergency event.

[0143] Optionally, in the embodiment of the present disclosure, any desirable method can be adopted to perform word segmentation processing on the merged text and the associated text. For example, Jieba word segmenter can be used to perform word segmentation processing on the merged text and the associated text respectively. The present disclosure does not limit this.

[0144] Step 406: Determine the second emergency event associated with the associated text according to the total number of texts associated with the second emergency, the number of identical characters, and the second time difference.

[0145] Optionally, the total number of texts associated with the second emergency event, the number of identical characters, and the second time difference may be input into a logistic regression (LR) model to determine whether the associated texts describe the second emergency event.

[0146] Optionally, the calculation formula of the logistic regression model can be:

[0147] Logit(P)=β0+β1N w +β2Δt+β3N p

[0148] Among them, N W is the number of identical characters between the associated text and the text associated with the second emergency event, Δt is the second time difference, N Pis the total number of texts associated with the second emergency event. β0, β1, β2, and β3 are parameters of the logistic regression model, which can be determined during the training process of the logistic regression model, and the present disclosure does not limit this.

[0149] Among them, Logit(P) is the output of the logistic regression model. If P is 0, it means that the associated text does not describe the second emergency event, and the associated text is deleted; if P is 1, it means that the associated text describes the second emergency event, and the associated text can be associated with the second emergency event, that is, the associated text is merged into the text set corresponding to the second emergency event.

[0150] In the disclosed embodiment, network information is first traversed based on the reference words contained in the word library to extract candidate texts containing the reference words. Afterwards, semantic analysis is performed on the candidate texts to determine the associated texts associated with the emergency contained in the candidate texts, and then entity extraction is performed on the associated texts to determine the first entity set corresponding to the associated texts. In the case where the first occurrence time is not included in the first entity set, multiple second emergency events of the same type as the first event contained in the first entity set are obtained according to the second occurrence time corresponding to each second emergency in the emergency data set, and then the total number of texts associated with each second emergency, the number of identical characters between the associated text and the text associated with each second emergency, and the second time difference between the release time of the associated text and the second occurrence time corresponding to each second emergency, and finally the second emergency associated with the associated text is determined according to the total number of texts associated with the second emergency, the number of identical characters and the second time difference. Thus, in the case where the associated text does not contain the first occurrence time, the second emergency described by the associated text can also be accurately determined, thereby realizing the arrangement of the text describing the emergency in the network information.

[0151] Figure 5 FIG. 1 is a flow chart of a method for monitoring an emergency event provided by another embodiment of the present disclosure. Figure 5 As shown, the monitoring method of the emergency event includes:

[0152] Phase 1: Based on the reference words contained in the vocabulary, the network information is traversed to extract candidate texts containing the reference words, and then the candidate texts are semantically analyzed to determine whether the candidate texts are associated with the emergency. If so, the candidate texts are associated with the emergency.

[0153] Phase 2: Entity extraction is performed on the associated text to obtain the first event type, first geographic location, and first occurrence time corresponding to the associated text.

[0154] Phase 3: After successfully extracting the three entities of the first event type, the first geographic location, and the first occurrence time from the associated text, obtain the first similarity between the first entity set and the second entity set corresponding to each first emergency event in the emergency data set, wherein the first entity set includes the first event type, the first geographic location, and the first occurrence time, and the second entity set includes the second event type, the second geographic location, and the second occurrence time. Then, determine the first emergency event described by the associated text based on the first similarity, and store the associated text in the first emergency event corresponding to it in the emergency data set.

[0155] When the first occurrence time is not extracted from the associated text, multiple second emergency events close to the release time of the associated text are obtained from the emergency event dataset according to the release time of the associated text, and then a logistic regression model is used to determine the second emergency event described by the associated text. After determining the second emergency event described by the associated text, the associated text is associated with its corresponding second emergency event.

[0156] In order to implement the above embodiments, the present disclosure also proposes a monitoring device for emergencies.

[0157] Figure 6 The structure diagram of a monitoring device for an emergency event provided by an embodiment of the present disclosure is shown in FIG. Figure 6 As shown, the emergency monitoring device 600 may include: a first acquisition module 610 , a first determination module 620 , a second determination module 630 , a third determination module 640 , and a fourth determination module 650 .

[0158] The first acquisition module 610 is used to traverse the network information based on the reference words contained in the word library to extract candidate texts containing the reference words;

[0159] A first determination module 620 is used to perform semantic analysis on the candidate text to determine the associated text associated with the emergency event contained in the candidate text;

[0160] A second determination module 630 is used to perform entity extraction on the associated text to determine a first entity set corresponding to the associated text;

[0161] A third determination module 640 is used to determine a first similarity between the first entity set and a second entity set corresponding to each emergency event in the emergency event data set;

[0162] The fourth determination module 650 is configured to determine that the associated text is the associated text of the first emergency event 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.

[0163] Optionally, the second determining module 630 is specifically configured to:

[0164] Obtain a reference word set corresponding to each event type from a reference word library;

[0165] Determine the association probability value between the associated text and each event type according to the number of occurrences 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;

[0166] Determine the first event type corresponding to the associated text according to each associated probability value and the second threshold value corresponding to each event type;

[0167] Performing location extraction on the associated text according to the location entities included in the location entity library to determine a first geographical location corresponding to the associated text;

[0168] Based on a preset algorithm, time extraction is performed on the associated text to determine the first occurrence time corresponding to the associated text.

[0169] Optionally, the third determining module 640 is specifically configured to:

[0170] Determine a second similarity between the first event type and the second event type in the second entity set, 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;

[0171] A first similarity between the first entity set and the second entity set is determined according to the second similarity, the third similarity, and the fourth similarity.

[0172] Optionally, the third determining module 640 is specifically configured to:

[0173] A fourth similarity is determined according to a first time difference between the first occurrence time and the second occurrence time.

[0174] Optionally, an update module is also included, which is specifically used to:

[0175] In response to the first geographic location having a higher rank than the second geographic location in any second entity set, updating the second geographic location in any second entity set according to the first geographic location to obtain an updated second entity set;

[0176] or,

[0177] In response to the first occurrence time being an absolute time and the second occurrence time in any second entity set being a relative time, the second occurrence time in any second entity set is updated according to the first occurrence time to obtain an updated any second entity set.

[0178] Optionally, an associated module is also included, which is specifically used to:

[0179] determining a fifth similarity between any updated second entity set and each of the remaining second entity sets;

[0180] In response to any fifth similarity being greater than the first threshold, an emergency event corresponding to the second entity set corresponding to any fifth similarity is associated with an updated emergency event corresponding to any second entity set.

[0181] Optionally, also include:

[0182] The storage module is used for storing the associated text and the first entity set in an emergency event data set in association in response to each first similarity being less than or equal to a first threshold.

[0183] Optionally, a fifth determining module is further included, which is specifically used to:

[0184] In response to the first entity set not including the first occurrence time, acquiring a plurality of second emergency events of the same type as the first event included in the first entity set within a preset time period according to the second occurrence time corresponding to each second emergency event in the emergency event data set;

[0185] Obtaining the total number of texts associated with each second emergency event, the number of identical characters between the associated text and the text associated with each second emergency event, and the second time difference between the publishing time of the associated text and the second occurrence time corresponding to each second emergency event;

[0186] The second emergency event associated with the associated text is determined according to the total number of texts associated with the second emergency event, the number of identical characters, and the second time difference.

[0187] The functions and specific implementation principles of the above modules in the embodiments of the present disclosure can be referred to the above method embodiments, and will not be repeated here.

[0188] The monitoring device for emergencies of the disclosed embodiment first traverses network information based on the reference words contained in the word library to extract candidate texts containing the reference words, then performs semantic analysis on the candidate texts to determine the associated texts associated with the emergencies contained in the candidate texts, then performs entity extraction on the associated texts to determine the first entity set corresponding to the associated texts, then determines the first similarity between the first entity set and the second entity set corresponding to each emergencies in the emergencies data set, and finally determines that the associated texts are the associated texts of the first emergencies 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. Thus, the emergencies texts contained in the network information are analyzed and sorted, which can not only timely and accurately mine the relevant information of emergencies from the massive network information, but also cluster the texts describing the same emergencies, so that new emergencies can be discovered in a timely manner.

[0189] In order to implement the above embodiments, the present disclosure also proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for monitoring emergencies proposed in the above embodiments of the present disclosure is implemented.

[0190] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for monitoring emergencies proposed in the above embodiments of the present disclosure is implemented.

[0191] In order to implement the above embodiments, the present disclosure further proposes a computer program product, including a computer program, which, when executed by a processor, implements the emergency event monitoring method proposed in the above embodiments of the present disclosure.

[0192] Figure 7 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Figure 7 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0193] like Figure 7 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the 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 connects various system components (including the system memory 28 and the processing unit 16).

[0194] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these 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 Interconnection (PCI) bus.

[0195] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0196] The 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. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the various embodiments of the present disclosure.

[0197] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the 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 or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described in the present disclosure.

[0198] The computer device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, a pointing device, a display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 22. In addition, the 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) through a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via the bus 18. It should be understood that although Figure 7 Not shown, 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.

[0199] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the methods mentioned in the above embodiments.

[0200] The technical solution disclosed in the present invention first traverses network information based on reference words contained in the word library to extract candidate texts containing reference words, then performs semantic analysis on the candidate texts to determine the associated texts associated with the emergency contained in the candidate texts, then performs entity extraction on the associated texts to determine the first entity set corresponding to the associated texts, then determines the first similarity between the first entity set and the second entity set corresponding to each emergency in the emergency data set, and finally determines 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. Thus, the emergency texts contained in the network information are analyzed and sorted, which can not only timely and accurately mine relevant information of the emergency from the massive network information, but also cluster the texts describing the same emergency, so that new emergencies can be discovered in a timely manner.

[0201] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0202] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0203] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present disclosure belong.

[0204] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0205] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0206] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0207] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0208] The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present disclosure. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present disclosure.

Claims

1. A method for monitoring an emergency, characterized in that: include: Based on the reference words contained in the vocabulary, traversing the network information to extract candidate texts containing the reference words; Using an attention-enhanced bidirectional long short-term memory model to perform semantic analysis on the candidate text to determine associated texts contained in the candidate text that are associated with the emergency; Performing entity extraction on the associated text to determine a first entity set corresponding to the associated text, the first entity set including a first event type, a first geographic location, and a first occurrence time; Determine a second similarity between the first event type and a second event type in a second entity set corresponding to each emergency event in the emergency event data set, determine whether the first event type is the same as the second event type according to the second similarity, and if the first event type is the same as the second event type, determine 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, and determine 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, wherein a formula for determining the first similarity is: S1=S2×(aS3+bS4) Wherein, S1 is the first similarity, S2 is the second similarity, S3 is the third similarity, S4 is the fourth similarity, a is the weight corresponding to the third similarity, and b is the weight corresponding to the fourth similarity; When the first similarity between the first entity set and any second entity set is greater than a first threshold, determining that the associated text is the associated text of the first emergency event corresponding to any second entity set; In the case where each of the first similarities is less than or equal to the first threshold, the associated text and the first entity set are associated and stored in the emergency event data set.

2. The method according to claim 1, characterized in that The performing entity extraction on the associated text to determine a first entity set corresponding to the associated text includes: Obtain a reference word set corresponding to each event type from a reference word library; Determine the association probability value between the associated text and each event type according to the number of occurrences 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; Determine the first event type corresponding to the associated text according to each of the associated probability values ​​and a second threshold value corresponding to each event type; Performing location extraction on the associated text according to the location entities included in the location entity library to determine a first geographical location corresponding to the associated text; Based on a preset algorithm, time extraction is performed on the associated text to determine the first occurrence time corresponding to the associated text.

3. The method according to claim 1, characterized in that The fourth similarity is determined according to a first time difference between the first occurrence time and the second occurrence time.

4. The method according to claim 1, characterized in that: After determining that the associated text is the associated text of the first emergency event corresponding to any second entity set, the method further includes: In response to the first geographic location having a higher rank than the second geographic location in any second entity set, updating the second geographic location in any second entity set according to the first geographic location to obtain an updated second entity set; or, In response to the first occurrence time being an absolute time and the second occurrence time in any second entity set being a relative time, the second occurrence time in any second entity set is updated according to the first occurrence time to obtain an updated any second entity set.

5. The method according to claim 4, characterized in that After obtaining any updated second entity set, the method further includes: determining a fifth similarity between any updated second entity set and each of the remaining second entity sets; In response to any fifth similarity being greater than the first threshold, an emergency event corresponding to the second entity set corresponding to the any fifth similarity is associated with an emergency event corresponding to the updated any second entity set.

6. The method according to claim 2, characterized in that After performing entity extraction on the associated text to determine a first entity set corresponding to the associated text, the method further includes: In response to the first entity set not including the first occurrence time, acquiring a plurality of second emergency events of the same type as the first event included in the first entity set within a preset time period according to the second occurrence time corresponding to each second emergency event in the emergency event data set; Obtaining the total number of texts associated with each of the second emergency events, the number of identical characters between the associated text and the text associated with each of the second emergency events, and the second time difference between the publishing time of the associated text and the second occurrence time corresponding to each of the second emergency events; The second emergency event associated with the associated text is determined according to the total number of texts associated with the second emergency event, the number of identical characters, and the second time difference.

7. A monitoring device for emergencies, characterized in that: include: A first acquisition module, configured to traverse network information based on reference words contained in the vocabulary to extract candidate texts containing the reference words; A first determination module is used to perform semantic analysis on the candidate text using an attention-enhanced bidirectional long short-term memory model to determine associated texts contained in the candidate text that are associated with the emergency; A second determination module is used to perform entity extraction on the associated text to determine a first entity set corresponding to the associated text, wherein the first entity set includes a first event type, a first geographical location, and a first occurrence time; The third determination module is used to determine the second similarity between the first event type and the second event type in the second entity set corresponding to each emergency event in the emergency event data set, determine whether the first event type is the same as the second event type according to the second similarity, and when the first event type is the same as the second event type, determine the third similarity between the first geographical location and the second geographical location in the second entity set, and the fourth similarity between the first occurrence time and the second occurrence time in the second entity set, and determine 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, wherein the formula for determining the first similarity is: S1=S2×(aS3+bS4) Wherein, S1 is the first similarity, S2 is the second similarity, S3 is the third similarity, S4 is the fourth similarity, a is the weight corresponding to the third similarity, and b is the weight corresponding to the fourth similarity; a fourth determination module, configured to determine, when a first similarity between the first entity set and any second entity set is greater than a first threshold, that the associated text is associated text of a first emergency event corresponding to any second entity set; A storage module is used to associate the associated text and the first entity set and store them in the emergency data set when each of the first similarities is less than or equal to the first threshold.

8. The device according to claim 7, characterized in that The second determining module is specifically used to: Obtain a reference word set corresponding to each event type from a reference word library; Determine the association probability value between the associated text and each event type according to the number of occurrences 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; Determine the first event type corresponding to the associated text according to each of the associated probability values ​​and a second threshold value corresponding to each event type; Performing location extraction on the associated text according to the location entities included in the location entity library to determine a first geographical location corresponding to the associated text; Based on a preset algorithm, time extraction is performed on the associated text to determine the first occurrence time corresponding to the associated text.

9. The device according to claim 7, characterized in that The fourth similarity is determined according to a first time difference between the first occurrence time and the second occurrence time.

10. The device according to claim 7, characterized in that Also includes update modules, specifically for: In response to the first geographic location having a higher rank than the second geographic location in any second entity set, updating the second geographic location in any second entity set according to the first geographic location to obtain an updated second entity set; or, In response to the first occurrence time being an absolute time and the second occurrence time in any second entity set being a relative time, the second occurrence time in any second entity set is updated according to the first occurrence time to obtain an updated any second entity set.

11. The device according to claim 10, characterized in that It also includes associated modules, specifically for: determining a fifth similarity between any updated second entity set and each of the remaining second entity sets; In response to any fifth similarity being greater than the first threshold, an emergency event corresponding to the second entity set corresponding to the any fifth similarity is associated with an emergency event corresponding to the updated any second entity set.

12. The device according to claim 7, characterized in that The fifth determining module is further included, which is specifically used for: In response to the first entity set not including the first occurrence time, acquiring a plurality of second emergency events of the same type as the first event included in the first entity set within a preset time period according to the second occurrence time corresponding to each second emergency event in the emergency event data set; Obtaining the total number of texts associated with each of the second emergency events, the number of identical characters between the associated text and the text associated with each of the second emergency events, and the second time difference between the publishing time of the associated text and the second occurrence time corresponding to each of the second emergency events; The second emergency event associated with the associated text is determined according to the total number of texts associated with the second emergency event, the number of identical characters, and the second time difference.

13. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for monitoring emergencies as claimed in any one of claims 1 to 6 is implemented.

14. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for monitoring emergencies as described in any one of claims 1 to 6 is implemented.

15. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for monitoring emergencies according to any one of claims 1 to 6.

Images