Event processing method and device, equipment and storage medium

Abstract

The invention provides an event processing method and device, equipment and a storage medium, and the method comprises the steps: carrying out the information extraction of a to-be-processed event instance based on the information carried by an event, obtaining the event identification information, carrying out the grading of the to-be-processed event instance based on the event identification information, obtaining the event grade information, and carrying out the grading of the to-be-processed event instance. And finally, performing event collection on the to-be-processed event instances based on the event level information to obtain an associated event set of the to-be-processed event instances, and processing the to-be-processed event instances based on the associated event set. According to the method, the events can be collected, so that the handling flexibility and practicability of repeated events, range events and major events are improved, and the event handling efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular to an event processing method, device, equipment and storage medium. Background Art

[0002] The intelligent event management platform is a platform for process-based processing and management of events. In the current intelligent event management platform, the occurrence of events, event collection, event processing, and event archiving are executed repeatedly as a complete event processing process. Event handling personnel handle events as a link in the event processing node.

[0003] However, events are processed independently using existing technologies. Therefore, when processing events with multi-dimensional complexity and correlation, such as important events, repeated events, and range events, there are problems such as low flexibility, redundant workload, and low processing efficiency. Summary of the invention

[0004] The purpose of this application is to provide an event processing method, device, equipment and storage medium to address the deficiencies in the above-mentioned prior art, so as to solve the problems of low event processing flexibility, redundant workload and low processing efficiency in the prior art.

[0005] To achieve the above objectives, the technical solutions adopted in this application are as follows:

[0006] In a first aspect, the present application provides an event processing method, the method comprising:

[0007] Extract information from the event instance to be processed to obtain event identification information of the event instance to be processed, wherein the event identification information includes event type, event keywords, entity information, and subject information of the event instance to be processed;

[0008] Determine the event level information of the event instance to be processed according to the event identification information and a preset event level feature set, wherein the event level information includes: event level, event label, time range of the event, and spatial range of the event, and the event level feature set includes multiple event level features, each of which is used to characterize event information under an event level;

[0009] According to the event level information of the event instance to be processed, matching processing is performed on the event instance to be processed in the historical event set to obtain the associated event set of the event instance to be processed;

[0010] According to the associated event set and the preset event process set, the target event process of the event instance to be processed is determined, and event processing is performed on the event instance to be processed based on the target event process.

[0011] Optionally, extracting information from the event instance to be processed to obtain event identification information of the event instance to be processed includes:

[0012] Performing keyword recognition on the event instance to be processed to obtain an event type and at least one event keyword of the event instance to be processed;

[0013] Performing entity recognition on the event instance to be processed to obtain entity information of the event instance to be processed;

[0014] Perform topic modeling on the event instance to be processed to obtain topic information of the event instance to be processed.

[0015] Optionally, the event level feature includes: tag values ​​of multiple tags;

[0016] The determining, according to the event identification information and a preset event level feature set, the event level information of the event instance to be processed includes:

[0017] Matching the event identification information with the label value of each event level feature in the event level feature set to obtain at least one matching label of each event level feature for the event instance to be processed;

[0018] Determining a first matching degree between the event instance to be processed and each event level feature according to the attribute information of each matching tag;

[0019] The event level information of the event instance to be processed is determined based on a first matching degree between the event instance to be processed and each event level feature.

[0020] Optionally, the attribute information of the matching tag includes: a weight value;

[0021] The determining, according to the attribute information of each matching tag, a first matching degree between the event instance to be processed and each event level feature includes:

[0022] Calculating the tag matching degree of each matching tag based on the weight value of each matching tag;

[0023] The sum of the tag matching degrees is used as the first matching degree between the event instance to be processed and the event level feature.

[0024] Optionally, the determining the event level information of the event instance to be processed based on the first matching degree between the event instance to be processed and each event level feature includes:

[0025] Determining a target event level feature corresponding to the event instance to be processed according to a first matching degree between the event instance to be processed and each event level feature;

[0026] The event information under the target event level feature is used as the event level information of the event instance to be processed.

[0027] Optionally, matching the event instance to be processed in a historical event set according to the event level information of the event instance to be processed to obtain a set of associated events of the event instance to be processed includes:

[0028] Performing a first matching process in the historical event set based on the spatial range and the time range corresponding to the event level to obtain a set of events to be selected;

[0029] A second matching process is performed on the event set to be selected based on the event tag to obtain an associated event set of the event instance to be processed.

[0030] Optionally, the event tag based on the event level is subjected to a second matching process in the event set to be selected to obtain a set of associated events of the event instance to be processed, including:

[0031] Determining a second matching degree between the event instance to be processed and each historical event according to the event label of the event level and the event label of each historical event in the event set to be selected;

[0032] Based on the second matching degree and a preset matching degree threshold, the associated events of the event instance to be processed are determined in each of the historical events, and added to the associated event set.

[0033] In a second aspect, the present application provides an event processing device, the device comprising:

[0034] An information extraction module is used to extract information of an event instance to be processed, and obtain event identification information of the event instance to be processed, wherein the event identification information includes an event type, event keywords, entity information, and subject information of the event instance to be processed;

[0035] A level determination module, used to determine the event level information of the event instance to be processed according to the event identification information and a preset event level feature set, wherein the event level information includes: event level, event label, time range of the event, and spatial range of the event, and the event level feature set includes multiple event level features, each of which is used to characterize event information under an event level;

[0036] An event set determination module, configured to match the event instance to be processed in the historical event set according to the event level information of the event instance to be processed, and obtain an associated event set of the event instance to be processed;

[0037] The event processing module is used to determine the target event process of the event instance to be processed according to the associated event set and the preset event process set, and perform event processing on the event instance to be processed based on the target event process.

[0038] Optionally, the information extraction module is specifically used to:

[0039] Performing keyword recognition on the event instance to be processed to obtain an event type and at least one event keyword of the event instance to be processed;

[0040] Performing entity recognition on the event instance to be processed to obtain entity information of the event instance to be processed;

[0041] Perform topic modeling on the event instance to be processed to obtain topic information of the event instance to be processed.

[0042] Optionally, the event level feature includes: tag values ​​of multiple tags; and the level determination module is specifically used to:

[0043] Matching the event identification information with the label value of each event level feature in the event level feature set to obtain at least one matching label of each event level feature for the event instance to be processed;

[0044] Determining a first matching degree between the event instance to be processed and each event level feature according to the attribute information of each matching tag;

[0045] The event level information of the event instance to be processed is determined based on a first matching degree between the event instance to be processed and each event level feature.

[0046] Optionally, the attribute information of the matching tag includes: a weight value; and the level determination module is specifically used to:

[0047] Calculating the tag matching degree of each matching tag based on the weight value of each matching tag;

[0048] The sum of the tag matching degrees is used as the first matching degree between the event instance to be processed and the event level feature.

[0049] Optionally, the level determination module is specifically used to:

[0050] Determining a target event level feature corresponding to the event instance to be processed according to a first matching degree between the event instance to be processed and each event level feature;

[0051] The event information under the target event level feature is used as the event level information of the event instance to be processed.

[0052] Optionally, the event set determination module is specifically used to:

[0053] Performing a first matching process in the historical event set based on the spatial range and the time range corresponding to the event level to obtain a set of events to be selected;

[0054] A second matching process is performed on the event set to be selected based on the event tag to obtain an associated event set of the event instance to be processed.

[0055] Optionally, the event set determination module is specifically used to:

[0056] Determining a second matching degree between the event instance to be processed and each historical event according to the event label of the event level and the event label of each historical event in the event set to be selected;

[0057] Based on the second matching degree and a preset matching degree threshold, the associated events of the event instance to be processed are determined in each of the historical events, and added to the associated event set.

[0058] In the third aspect, an embodiment of the present application also provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of the event processing method as described in any one of the first aspects.

[0059] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the event processing method described in any one of the first aspects are executed.

[0060] The beneficial effects of the present application are as follows: by extracting information from the event instances to be processed and obtaining event identification information, more information about the event can be obtained from multiple dimensions such as keywords, entities, and themes, which is conducive to further handling of the event processing. By classifying the event identification information based on the event level feature set, the events can be classified and clustered from multiple dimensions such as time, space, and event tags. By determining the associated event set for the event instances to be processed based on the event level information, the data with a high degree of association can be associated, thereby avoiding redundant processing of repeated events and improving the response speed of hot events and key events. By handling the event set as a whole, each department can handle the events with identification, thereby improving the flexibility of event processing.

[0061] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 A flow chart of an event processing method provided by an embodiment of the present application is shown;

[0064] Figure 2 A flow chart for extracting event identification information provided by an embodiment of the present application is shown;

[0065] Figure 3 A flow chart for determining event level information provided by an embodiment of the present application is shown;

[0066] Figure 4 A flow chart for determining a first matching degree provided in an embodiment of the present application is shown;

[0067] Figure 5 A flowchart of another method of determining event level information provided by an embodiment of the present application is shown;

[0068] Figure 6 A flowchart for determining a set of associated events provided by an embodiment of the present application is shown;

[0069] Figure 7 A flowchart of another method of determining a set of associated events provided by an embodiment of the present application is shown;

[0070] Figure 8An overall flow chart of an event processing method provided by an embodiment of the present application is shown;

[0071] Fig. 9 A schematic diagram of the structure of an event processing device provided in an embodiment of the present application is shown;

[0072] Fig.10 A schematic structural diagram of an electronic device 100 provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0073] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0074] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0075] The event processing process in the intelligent event management platform in the prior art includes: event occurrence, event collection, event processing, and event archiving. As a link in the time processing node, the event handler inputs the events to be processed into the platform one by one, so that the platform can process the events in a pipeline.

[0076] However, current urbanization events are characterized by high complexity and strong correlation, and the platform-based pipeline processing approach is too independent in handling major events, scope events, and repeated events.

[0077] The independent handling of major incidents leads to a lack of adequate preparation at the beginning of incident handling. Often, more and more incidents occur, or even until the incident archiving stage, they are listed as major incidents, resulting in a lack of flexibility and real-time nature in the overall handling process.

[0078] Range events are caused by various types of events within a similar spatial and temporal range, and often require joint processing by multiple management departments and commissions. Any single event will encounter many bottlenecks when being handled alone.

[0079] Duplicate events are caused by a problem affecting multiple parties, resulting in multiple events of the same type. However, the event owners and impactors are different. During the handling process, the event handlers repeatedly handle each event, resulting in redundant workload and low processing efficiency.

[0080] In summary, the current event processing methods have problems such as low processing efficiency, poor flexibility and real-time performance, and system barriers in event processing.

[0081] Based on this, the present application proposes an event processing method, which extracts information from events based on the information carried by the events to obtain event identification information, then classifies the events based on the event identification information to obtain event level information, and finally classifies the events based on the event level information to obtain a set of associated events, and processes the events based on the associated event set. The method of the present application can realize the classification of events, thereby improving the flexibility and practicality of handling repeated events, range events, and major events, and improving the efficiency of event processing.

[0082] Next, combine Figure 1 The event processing method of the present application is described. The execution subject of the method may be an electronic device, such as Figure 1 As shown, the method includes:

[0083] S101. Extract information from an event instance to be processed to obtain event identification information of the event instance to be processed. The event identification information includes event type, event keywords, entity information, and subject information of the event instance to be processed.

[0084] After an event occurs, the collector can collect the location, time, type and basic description information of the event to obtain the event instance to be processed.

[0085] Among them, the event type can be obtained based on the classification of the event-related processing departments, such as traffic accident type, road administration type, power failure type, environmental pollution type, etc. Event keywords, entity information and subject information can describe the multi-dimensional information of the event, and can also be used to classify events based on event keywords, entity information and subject information to obtain the event type of the event instance to be processed.

[0086] By extracting information from the event instance to be processed, the event identification information of the event instance to be processed can be obtained. Specifically, the information extraction of the event instance to be processed can be to extract information from the event type of the event instance to be processed to obtain the event type of the event instance to be processed, and to extract information from the occurrence location, occurrence time and basic description information of the event to be processed to obtain the event keyword of the event instance to be processed.

[0087] Entity information can be the target words identified in the information of the event instance to be processed, such as time entity, location entity, place entity, event type entity, etc. Topic information can represent the topic to which the event instance to be processed belongs, such as road administration topic, environmental protection topic, accident topic, etc.

[0088] As a possible implementation method, entity recognition can be performed on the information of the event instance to be processed to obtain the entity information of the event instance to be processed, and relationship extraction and modeling can be performed on the entity information to obtain the subject information of the event instance to be processed.

[0089] S102. Determine the event level information of the event instance to be processed based on the event identification information and a preset event level feature set. The event level information includes: event level, event label, time range of the event, and spatial range of the event. The event level feature set includes multiple event level features, and each event level feature is used to characterize event information under an event level.

[0090] The preset event level feature set can be obtained based on data processing of real-time hot events and default common events, including multiple event level features, each of which is used to characterize an event level and event information under an event level. The event information can include event labels, event time ranges, and event spatial ranges.

[0091] As a possible implementation method, real-time hot events and default common events can be divided into different levels according to importance or event type, and corresponding event tags can be added according to event type, theme, etc. Each level corresponds to a time range and a spatial range, and is distinguished based on different event tags to obtain an event level feature set. The time range and spatial range can be preset. Among them, the event tag can be the entity, keyword and theme of the event. As an example, the event type of road flooding can be classified as a secondary event, with a spatial range of less than 500 meters and a time range of one day.

[0092] Optionally, the event type, event keywords, entity information and subject information in the event identification information can be used as labels for the event instance to be processed. By matching the event identification information with the event labels in the event level feature set, the event level information of the event instance to be processed can be determined.

[0093] S103: According to the event level information of the event instance to be processed, matching processing is performed on the event instance to be processed in the historical event set to obtain the associated event set of the event instance to be processed.

[0094] The historical event set may include multiple historical events, and the information of the historical events includes: location information of the event, time information of the event, event type, event label, etc. The location information of the event may be the longitude and latitude of the location where the event occurred.

[0095] Each event level information corresponds to a time range and a space range. By filtering historical events based on the time range and the space range, multiple historical events within the range can be obtained. Then, by further filtering the multiple historical events within the range, a set of associated events consisting of multiple associated events corresponding to the event instance to be processed can be determined.

[0096] Optionally, the associated event set includes multiple event instances, each of which has a high degree of association with the event instance to be processed, and specifically may have the same time range and space range, and are all related to a certain factor. For example, if multiple traffic accidents occur on road A due to waterlogging on road A, the event level information of the waterlogging event on road A can be determined, and based on the event level information, the traffic accident events on road A within the corresponding time and space range are regarded as associated events and classified into an event set.

[0097] In another example, suppose the current event 1 indicates that the vehicle had a flat tire due to the uneven road surface of road A at 14:00 on April 5, 2024. Based on the event identification information of event 1, the event level information of event 1 can be obtained. Then, based on the event level information of event 1, all events within the time range and spatial range corresponding to the event level information can be screened, and at least one event associated with event 1 is determined based on the labels of these events and added to the associated event set. For example, there is event 2 in the historical event set indicating that the vehicle had a flat tire due to the uneven road surface of road A at 14:20 on April 5, 2024, which meets the time range and spatial range of event 1, and the labels of the events are also the same. Then, event 2 can be determined as an associated event of event 1, and event 2 can be added to the associated event set of event 1. It can be understood that the labels of event 1 and event 2 are highly associated, and it is inferred that the causes of their occurrence may be the same. Events with a high degree of label association can be regarded as repeated events and marked.

[0098] As a possible implementation method, the correlation degree can be calculated based on the event tag of the event instance to be processed, multiple events whose correlation degree with the event instance to be processed meets preset conditions can be determined, and these events can be used as the correlation event set of the event instance to be processed.

[0099] S104: Determine a target event process of the event instance to be processed according to the associated event set and the preset event process set, and perform event processing on the event instance to be processed based on the target event process.

[0100] For each associated event set, a matter process can be pre-set. The matter process can be an allocation template for handling events in the associated event set. Based on the matter process, the events can be allocated to the corresponding handling departments. The matter process set can be a set of matter processes corresponding to all events in the associated event set.

[0101] As a possible implementation method, the events in the associated event set can be processed as a unified event task. The events in the associated event set can correspond to the same matter process, and each matter process corresponds to at least one handling department. Based on the matter process, the events in the associated event set can be assigned to the corresponding handling department, and the handling department processes the events in the associated event set to obtain the processing results of each event.

[0102] It is worth noting that when handling the associated event set, the unprocessed tasks in the associated event set can be assigned to the corresponding handling department for processing. When assigning events that need to be processed, the events can be marked based on the degree of correlation between the events in the associated event set. For example, events that appear repeatedly in the associated event set are marked as repeated events, and the repeated events are sent to the handling department for processing at one time. If the events in the associated event set are related to hot events, the events in the associated event set related to hot events are marked as hot events. If the events in the associated event set are related to major events, the events in the associated event set related to major events are marked as important events, etc., so that the handling department can determine the urgency of the current event processing based on the label.

[0103] In the embodiment of the present application, by extracting information from the event instance to be processed and obtaining event identification information, more information about the event can be obtained from multiple dimensions such as keywords, entities, and themes, which is conducive to the further disposal of event processing. By classifying the event identification information based on the event level feature set, the events can be classified and clustered from multiple dimensions such as time, space, and event tags. By determining the associated event set for the event instance to be processed based on the event level information, the data with a high degree of association can be associated, thereby avoiding redundant processing of repeated events and improving the response speed of hot events and key events. By disposing of the event set as a whole, each department can process the event with identification, thereby improving the flexibility of event processing.

[0104] Next, the steps of extracting information from the event instance to be processed and obtaining the event identification information of the event instance to be processed are described. Figure 2 As shown, the above step S101 includes:

[0105] S201. Perform keyword recognition on an event instance to be processed to obtain an event type and at least one event keyword of the event instance to be processed.

[0106] Optionally, keyword extraction technology can be used to identify keywords based on a preset keyword set for the event instance to be processed. The keyword set can be obtained based on the description information of historical events, common events, and hot events. The keyword extraction technology can be, for example, TF-IDF technology.

[0107] In a first implementation manner, if the description information of the event instance to be processed includes the event type, the event type of the event instance to be processed can be directly identified.

[0108] In a second implementation manner, if the description information of the event instance to be processed does not include keywords of the event type, only keyword recognition may be performed to obtain at least one event keyword.

[0109] S202: Perform entity recognition on the event instance to be processed to obtain entity information of the event instance to be processed.

[0110] Optionally, entity recognition technology (Named Entity Recognition, NER) can be used to identify the event instance to be processed based on a preset entity set, and at least one entity of the event instance to be processed can be obtained, and the at least one entity can be used as the entity information of the event instance to be processed. The entity set can be pre-constructed based on the description information of historical events, common events, and hot events.

[0111] S203: Perform topic modeling on the event instance to be processed to obtain topic information of the event instance to be processed.

[0112] Optionally, topic modeling (Latent Dirichlet Allocation, LDA) can be performed on the description information of the event instance to be processed based on NLP technology to obtain topic information of the event instance to be processed.

[0113] It should be noted that the present application only uses the above-mentioned S201-S202 steps as a method for extracting keywords, entity information and subject information. It should be understood that those skilled in the art can also extract keywords, entity information and subject information of the event instance to be processed by other methods, and should not be limited to this.

[0114] Optionally, the event level feature includes: label values ​​of multiple labels. The labels of the event level feature and the label values ​​of the labels can represent the event labels, spatial range of events and time range of events under an event level. It should be understood that the same event level can include multiple event level features, and the event labels, spatial ranges of events and time ranges of events of each event level feature are different.

[0115] The above step of determining the event level information of the event instance to be processed according to the event identification information and the preset event level feature set is as follows: Figure 3 As shown, including:

[0116] S301. Match event identification information with a label value of each event level feature in an event level feature set to obtain at least one matching label of each event level feature for an event instance to be processed.

[0117] The event level features include multiple tags and the tag values ​​of each tag, such as the tag "time" and the tag value "July 26, 2024 14:48:46", the tag "location" and the specific tag value "intersection of road A and road B", the tag "event type" and the specific tag value "road waterlogging", etc.

[0118] Matching the event identification information with the tag value of the event level feature can be done by matching the keywords, entity information, and subject information in the event identification information with the tag value of the event level feature. If the keyword, entity information, or subject information has the same tag value as the event level feature, the tag corresponding to the tag value can be used as a matching tag.

[0119] As a possible implementation, all event level features may be traversed, and event identification information may be matched with the traversed event level features to obtain matching labels between the event identification information and each event level feature.

[0120] Event level features may also include labels obtained by converting entities and keywords. At this time, the event identification information may be matched with the labels of each event level feature in the event level feature set to obtain at least one matching label for each event level feature for the event instance to be processed.

[0121] S302: Determine a first matching degree between the event instance to be processed and each event level feature according to the attribute information of each matching tag.

[0122] For event level features with matching tags, a first matching degree between the event instance to be processed and the event level features may be calculated based on the attribute information of each matching tag.

[0123] The attribute information of the matching tag can represent the importance of the matching tag. For example, the matching tags of hot events and important events can be given a higher weight, so that the events related to hot events and important events can have a higher matching degree, thereby quickly identifying hot events and important events.

[0124] Exemplarily, assuming that the matching tag "traffic accident" is a major event, a large weight can be assigned to the matching tag "traffic accident". If the keywords, entities or topics of the event instance to be processed include "traffic accident", it can be determined that the matching tag of the event instance to be processed includes "traffic accident", and the first matching degree of the event instance to be processed is calculated based on the weight of "traffic accident". As a possible implementation method, when the matching tag of a major event is included in the event instance to be processed, the first matching degree of the event instance to be processed can be directly determined as the upper limit value of the matching degree.

[0125] As another possible implementation, the first matching degree between the event instance to be processed and each event level feature may also be determined based on the number of matching tags. For example, the total number of matching tags is used as the first matching degree.

[0126] S303: Determine event level information of the event instance to be processed based on a first matching degree between the event instance to be processed and each event level feature.

[0127] Optionally, the event level information of the event instance to be processed may be determined based on the event level feature with the highest first matching degree.

[0128] Optionally, the attribute information of the matching tag includes: a weight value. Among them, the matching tags of major events and hot events may have a higher weight value. The above step of determining the first matching degree between the event instance to be processed and each event level feature according to the attribute information of each matching tag is as follows: Figure 4 As shown, including:

[0129] S401: Calculate the tag matching degree of each matching tag based on the weight value of each matching tag.

[0130] The tag matching degree may be the product of the reference matching degree and the weight value.

[0131] S402: The sum of the matching degrees of each label is used as the first matching degree between the event instance to be processed and the event level feature.

[0132] Exemplarily, the matching labels of the event instance to be processed and the event level feature include "road waterlogging" and "traffic accident". Assuming that the weight value of the matching label "road waterlogging" is 1 and the weight value of "traffic accident" is 3, the label matching degree of the matching label "road waterlogging" can be 1×1=1, and the label matching degree of "traffic accident" can be 1×3=3. The first matching degree of the event instance to be processed and the event level feature is 1+3=4.

[0133] In another example, assuming that the weight value of "traffic accident" is 100, the label matching degree of the matching label "road surface water" can be 1×1=1, and the label matching degree of "traffic accident" can be 1×100=100. The first matching degree between the event instance to be processed and the event level feature is 1+100=101. Since the first matching degree exceeds the matching degree upper limit of 100, it can be determined that the first matching degree is 100. In this way, major events can have a higher matching degree, thereby realizing rapid identification of major events.

[0134] By performing the above steps S401-S402 on the event instance to be processed and each event level feature, the first matching degree between the event instance to be processed and each event level feature can be obtained. Then, based on the first matching degree between the event instance to be processed and each event level feature, the event level information of the event instance to be processed is determined, such as Figure 5 As shown, the above step S303 includes:

[0135] S501: Determine a target event level feature corresponding to the event instance to be processed according to a first matching degree between the event instance to be processed and each event level feature.

[0136] As a possible implementation manner, the event level feature with the highest first matching degree may be used as the target event level feature corresponding to the event instance to be processed.

[0137] S502: Use the event information under the target event level feature as the event level information of the event instance to be processed.

[0138] The event information under the target event level feature includes: event label, time range of the event, and spatial range of the event. The event information under the target event level feature is used as the event level information of the event instance to be processed, which can be that the event label, time range of the event, and spatial range of the event under the target event level feature are used as the event level information of the event instance to be processed, and the event level of the target event level feature is used as the event level of the event instance to be processed.

[0139] After determining the event level information of the event instance to be processed, the event instance to be processed can be matched in the historical event set according to the event level information of the event instance to be processed to obtain the associated event set of the event instance to be processed, such as Figure 6 As shown, the above step S103 includes:

[0140] S601: Perform a first matching process in a historical event set based on a spatial range and a time range corresponding to an event level to obtain a candidate event set.

[0141] The historical event set may include multiple historical events, and include event identification information and event level information of each historical event. The historical events in the historical event set may be processed based on the above steps S101-S102 to obtain event identification information and event level information of each historical event.

[0142] In a first implementation, a first matching process is performed in the historical event set based on the spatial range and time range corresponding to the event level, and the historical events with the same event level and the same event label in the historical event set are added to the candidate event set.

[0143] It should be noted that when the same event level has different event labels, its time range and spatial range may be different. Therefore, matching can be performed based on the event level and event label to determine historical events with the same time range and the same spatial range.

[0144] In the second implementation, the time and space information of historical events can be traversed and compared with the time range and space range corresponding to the event level of the event instance to be processed, and the historical events within the time range and space range are added to the event set to be selected.

[0145] By grouping events based on time and space ranges, it is possible to classify and cluster range events, which is beneficial for subsequent correlation processing of range events.

[0146] S602: Perform a second matching process on the event set to be selected based on the event tag to obtain a set of associated events of the event instance to be processed.

[0147] In order to further classify and group events based on their correlation degree, a second matching process can be performed on each historical event in the selected event set and the event instance to be processed based on the event label to obtain at least one associated event of the event instance to be processed, and the associated event is added to the associated event set.

[0148] Furthermore, the event labels based on the event level are subjected to a second matching process in the event set to be selected, and the associated event set of the event instance to be processed is obtained, such as Figure 7 As shown, including:

[0149] S701: Determine a second matching degree between the event instance to be processed and each historical event according to the event label of the event level and the event label of each historical event in the event set to be selected.

[0150] Among them, different weights can be pre-set for each event tag, and a higher weight can be set for event tags related to hot events and important events, so that the event instances to be processed related to hot events and important events have a higher second matching degree.

[0151] In a first implementation, the event label of the event level and the event label of each historical event may be weightedly calculated based on the weight value of the event label to obtain a second matching degree between the event instance to be processed and each historical event.

[0152] In a second implementation, the number of identical labels in the event labels of the event level and the event labels of each historical event in the event set to be selected may be used as the second matching degree between the event instance to be processed and each historical event.

[0153] S702: Based on the second matching degree and a preset matching degree threshold, determine the associated events of the event instance to be processed in each historical event, and add them to the associated event set.

[0154] Among them, the preset matching degree threshold can divide historical events into high-correlation events and medium-low correlation events. If the second matching degree is higher than the matching degree threshold, the historical event corresponding to the second matching degree can be determined as a high-correlation event and automatically added to the high-correlation event set. If the second matching degree is lower than the matching degree threshold, the historical event corresponding to the second matching degree can be determined as a medium-low correlation event. At this time, the user can be prompted to reconfirm the historical event, and the historical event that needs to be added to the correlation event set is determined in response to the user's instructions.

[0155] It should be noted that the event labels of repeated events generally have a high degree of similarity, so repeated events can be classified into the same associated event set based on the event labels, thereby avoiding subsequent redundant processing of repeated events.

[0156] In the embodiment of the present application, by associating events according to event tags, events with a high degree of association are divided into the same associated event set, which is beneficial to the subsequent overall handling of the event set, thereby improving the flexibility of event processing.

[0157] Next, combine Figure 8 , an overall description of the event handling method of this application is given.

[0158] Reference Figure 8After extracting information from an event instance, the event identification information of the event instance can be obtained. Then, by matching the event instance based on a preset event level feature set, the event level information corresponding to the event instance can be obtained. The event level information includes event level, event label, time range, and spatial range.

[0159] After obtaining the event identification information and event level information of the event instance, we can first filter out the event set within the level range based on the time range and spatial range of the event, and then perform deep classification based on the event label of the event instance to obtain a high-correlation event set and a medium- and low-correlation event set. For the high-correlation event set, we can directly perform event correlation, and for the medium- and low-correlation event set, we can perform secondary confirmation to finally obtain the correlation event set.

[0160] After obtaining the associated event set, the event instances in the associated event set may be sent to the corresponding handling department for processing based on the corresponding matter flow to obtain the processing result of the event.

[0161] Based on the same inventive concept, an event processing device corresponding to the event processing method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned event processing method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0162] Fig. 9 A schematic diagram of the structure of an event processing device provided in an embodiment of the present application is shown.

[0163] An information extraction module 901 is used to extract information from an event instance to be processed, and obtain event identification information of the event instance to be processed, wherein the event identification information includes an event type, event keywords, entity information, and subject information of the event instance to be processed;

[0164] The level determination module 902 is used to determine the event level information of the event instance to be processed according to the event identification information and the preset event level feature set, wherein the event level information includes: event level, event label, time range of the event and spatial range of the event, and the event level feature set includes multiple event level features, each of which is used to characterize event information under an event level;

[0165] An event set determination module 903 is used to match the event instance to be processed in the historical event set according to the event level information of the event instance to be processed, and obtain the associated event set of the event instance to be processed;

[0166] The event processing module 904 is used to determine the target event process of the event instance to be processed according to the associated event set and the preset event process set, and perform event processing on the event instance to be processed based on the target event process.

[0167] Optionally, the information extraction module 901 is specifically used for:

[0168] Perform keyword recognition on the event instance to be processed to obtain the event type and at least one event keyword of the event instance to be processed;

[0169] Perform entity recognition on the event instance to be processed to obtain entity information of the event instance to be processed;

[0170] Perform topic modeling on the event instance to be processed to obtain the topic information of the event instance to be processed.

[0171] Optionally, the event level feature includes: tag values ​​of multiple tags; the level determination module 902 is specifically used to:

[0172] Matching the event identification information with the label value of each event level feature in the event level feature set to obtain at least one matching label of each event level feature for the event instance to be processed;

[0173] Determine a first matching degree between the event instance to be processed and each event level feature according to the attribute information of each matching tag;

[0174] The event level information of the event instance to be processed is determined based on the first matching degree between the event instance to be processed and each event level feature.

[0175] Optionally, the attribute information of the matching tag includes: a weight value; the level determination module 902 is specifically used to:

[0176] Calculate the tag matching degree of each matching tag based on the weight value of each matching tag;

[0177] The sum of the matching degrees of each label is used as the first matching degree between the event instance to be processed and the event level feature.

[0178] Optionally, the level determination module 902 is specifically configured to:

[0179] Determine the target event level feature corresponding to the event instance to be processed according to the first matching degree between the event instance to be processed and each event level feature;

[0180] The event information under the target event level feature is used as the event level information of the event instance to be processed.

[0181] Optionally, the event set determination module 903 is specifically configured to:

[0182] Perform a first matching process in the historical event set based on the spatial range and time range corresponding to the event level to obtain a candidate event set;

[0183] A second matching process is performed on the event set to be selected based on the event tag to obtain a set of associated events of the event instance to be processed.

[0184] Optionally, the event set determination module 903 is specifically configured to:

[0185] Determine a second matching degree between the event instance to be processed and each historical event according to the event label of the event level and the event label of each historical event in the event set to be selected;

[0186] Based on the second matching degree and a preset matching degree threshold, associated events of the event instance to be processed are determined in each historical event and added to the associated event set.

[0187] The embodiment of the present application obtains event identification information by extracting information from the event instance to be processed, and can obtain more information about the event from multiple dimensions such as keywords, entities and themes, which is conducive to the further disposal of event processing. By classifying the event identification information based on the event level feature set, the events can be classified and clustered from multiple dimensions such as time, space, and event tags. By determining the associated event set for the event instance to be processed based on the event level information, the data with a high degree of association can be associated, thereby avoiding redundant processing of repeated events and improving the response speed of hot events and key events. By disposing of the event set as a whole, each department can process the event with identification, thereby improving the flexibility of event processing.

[0188] Fig.10 A structural schematic diagram of an electronic device 100 provided in an embodiment of the present application is shown, comprising: a processor 1001, a storage medium 1002 and a bus 1003, wherein the storage medium 1002 stores machine-readable instructions executable by the processor 1001, and when the electronic device runs the event processing method in the embodiment, the processor 1001 communicates with the storage medium 1002 via the bus 1003, and the processor 1001 executes the machine-readable instructions, and the processor 1001 executes the preamble of the method item to execute the steps of the above-mentioned event processing method.

[0189] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program is executed when a processor is running, and the processor executes the steps of the above event processing method.

[0190] In the embodiment of the present application, the computer program can also execute other machine-readable instructions when run by the processor to execute other methods described in the embodiment. For the specific execution method steps and principles, please refer to the description of the embodiment, which will not be repeated here.

[0191] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0192] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0193] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0194] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0195] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0196] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An event processing method, characterized in that: include: Extract information from the event instance to be processed to obtain event identification information of the event instance to be processed, wherein the event identification information includes event type, event keywords, entity information, and subject information of the event instance to be processed; Determine the event level information of the event instance to be processed according to the event identification information and a preset event level feature set, wherein the event level information includes: event level, event label, time range of the event, and spatial range of the event, and the event level feature set includes multiple event level features, each of which is used to characterize event information under an event level; According to the event level information of the event instance to be processed, matching processing is performed on the event instance to be processed in the historical event set to obtain the associated event set of the event instance to be processed; According to the associated event set and the preset event process set, the target event process of the event instance to be processed is determined, and event processing is performed on the event instance to be processed based on the target event process.

2. The method according to claim 1, characterized in that The extracting information from the event instance to be processed to obtain event identification information of the event instance to be processed includes: Performing keyword recognition on the event instance to be processed to obtain an event type and at least one event keyword of the event instance to be processed; Performing entity recognition on the event instance to be processed to obtain entity information of the event instance to be processed; Perform topic modeling on the event instance to be processed to obtain topic information of the event instance to be processed.

3. The method according to claim 1, characterized in that The event level features include: tag values ​​of multiple tags; The determining, according to the event identification information and a preset event level feature set, the event level information of the event instance to be processed includes: Matching the event identification information with the label value of each event level feature in the event level feature set to obtain at least one matching label of each event level feature for the event instance to be processed; Determining a first matching degree between the event instance to be processed and each event level feature according to the attribute information of each matching tag; The event level information of the event instance to be processed is determined based on a first matching degree between the event instance to be processed and each event level feature.

4. The method according to claim 3, characterized in that The attribute information of the matching tag includes: a weight value; The determining, according to the attribute information of each matching tag, a first matching degree between the event instance to be processed and each event level feature includes: Calculating the tag matching degree of each matching tag based on the weight value of each matching tag; The sum of the tag matching degrees is used as the first matching degree between the event instance to be processed and the event level feature.

5. The method according to claim 3, characterized in that: The determining the event level information of the event instance to be processed based on the first matching degree between the event instance to be processed and each event level feature includes: Determining a target event level feature corresponding to the event instance to be processed according to a first matching degree between the event instance to be processed and each event level feature; The event information under the target event level feature is used as the event level information of the event instance to be processed.

6. The method according to claim 1, characterized in that According to the event level information of the event instance to be processed, matching the event instance to be processed in the historical event set to obtain the associated event set of the event instance to be processed includes: Performing a first matching process in the historical event set based on the spatial range and the time range corresponding to the event level to obtain a candidate event set; A second matching process is performed on the event set to be selected based on the event tag to obtain an associated event set of the event instance to be processed.

7. The method according to claim 6, characterized in that The event tag based on the event level performs a second matching process on the event set to be selected to obtain an associated event set of the event instance to be processed, including: Determining a second matching degree between the event instance to be processed and each historical event according to the event label of the event level and the event label of each historical event in the event set to be selected; Based on the second matching degree and a preset matching degree threshold, the associated events of the event instance to be processed are determined in each of the historical events, and added to the associated event set.

8. An event processing device, characterized in that: include: An information extraction module is used to extract information of an event instance to be processed, and obtain event identification information of the event instance to be processed, wherein the event identification information includes an event type, event keywords, entity information, and subject information of the event instance to be processed; A level determination module, used to determine the event level information of the event instance to be processed according to the event identification information and a preset event level feature set, wherein the event level information includes: event level, event label, time range of the event, and spatial range of the event, and the event level feature set includes multiple event level features, each of which is used to characterize event information under an event level; An event set determination module, configured to match the event instance to be processed in the historical event set according to the event level information of the event instance to be processed, and obtain an associated event set of the event instance to be processed; The event processing module is used to determine the target event process of the event instance to be processed according to the associated event set and the preset event process set, and perform event processing on the event instance to be processed based on the target event process.

9. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the event processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the event processing method according to any one of claims 1 to 7 are executed.

Images