Event processing method and device, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention provides an event processing method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of data processing. The electronic equipment obtains event data sent by the event obtaining platform; the event data corresponds to at least one event; analyzing the event data according to the event definition information to obtain event analysis data corresponding to each event; verifying the event analysis data of each event according to a preset verification format, if the event analysis data passes the verification, inputting the event analysis data into a pre-stored large model for processing to obtain supplementary information corresponding to the event, and generating a to-be-processed event according to the supplementary information of each event and the event analysis data, and processing the to-be-processed event according to the event type of the to-be-processed event. The method can be applied to various event management scenes.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular, to an event processing method, device, electronic device and computer-readable storage medium. Background Art

[0002] At present, event management is required in many scenarios. In the existing technology, users are generally required to fill in event information themselves and upload it to electronic devices. The electronic devices call multiple algorithms to process the event information to generate pending events, and then process the pending events.

[0003] As event management scenarios become more diverse, the sources of event data collection gradually increase, and the event data acquired by electronic devices often presents diversified forms, including structured data, unstructured data, semi-structured data, etc. The methods in the prior art cannot process event data in such diversified structural forms, and therefore cannot be applied to a variety of event management scenarios. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide an event processing method, device, electronic device and computer-readable storage medium to solve the problem that the event data parsing method in the prior art is single and cannot be applied to a variety of event management scenarios.

[0005] In order to achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows: In a first aspect, the present application provides an event processing method, which is applied to an electronic device, wherein the electronic device is communicatively connected to a plurality of event acquisition platforms, and event definition information is stored in the electronic device, wherein the event definition information is used to characterize event attributes, and the method comprises: Acquire event data sent by the event acquisition platform; the event data corresponds to at least one event; Parsing the event data according to the event definition information to obtain event parsing data corresponding to each of the events; The event parsing data of each of the events is verified according to a preset verification format. If the event parsing data passes the verification, the event parsing data is input into a pre-stored large model for processing to obtain supplementary information corresponding to the event. Based on the supplementary information and event parsing data of each of the events, an event to be processed is generated, and the event to be processed is processed according to the event type of the event to be processed.

[0006] In an optional implementation manner, parsing the event data according to the event definition information includes: In the case where the event data is a picture, a video stream or audio data, the event data is input into a pre-stored large model for processing to obtain event description information corresponding to the event data; The event description information is parsed according to the event definition information.

[0007] In an optional implementation, the event parsing data includes public parsing data and channel parsing data, and the verification format includes a public verification format and a channel verification format; and verifying the event parsing data of each of the events according to a preset verification format includes: Verifying the public parsed data and the channel parsed data according to the public verification format and the channel verification format respectively; The method further comprises: If both the public resolution data and the channel resolution data are verified successfully, it is determined that the event resolution data has passed the verification.

[0008] In an optional implementation manner, the electronic device stores a first correspondence between event types and processing personnel and a second correspondence between urgency thresholds and processing queues, and the processing of the event to be processed according to the event type of the event to be processed includes: Determine whether the event to be processed is a question-and-answer event according to the event type of the event to be processed; If the event to be processed is not a question-and-answer event, determining the urgency threshold of the event to be processed according to the weight value of the event to be processed; Determine a target processing person and a target processing queue corresponding to the event to be processed according to the first corresponding relationship, the event type of the event to be processed, the urgency threshold of the event to be processed, and the second corresponding relationship; The pending event is sent to the target processing queue of the target processing personnel, so that the target processing personnel obtains the pending event from the target processing queue and processes the pending event.

[0009] In an optional implementation, the electronic device is further connected to a database for communication, and the database stores processing information corresponding to a plurality of events. The method further includes: Acquire a first query request sent by a target processing person; the first query request includes a keyword and an event type of the event to be processed; According to the keyword and the event type, obtaining processing information of the target event from the database; the keyword and event type of the target event are consistent with the keyword and event type of the event to be processed; The processing information of the target event is sent to the target processing personnel so that the target processing personnel can process the event to be processed according to the processing information of the target event.

[0010] In an optional embodiment, the method further comprises: Acquire a second query request sent by the user; the second query request includes a query condition for the event to be queried; If the query condition is in natural language, the query condition is input into a preset large model for processing to obtain a database query statement for the event to be queried; The data corresponding to the event to be queried is acquired from the database according to the database query statement, and the data corresponding to the event to be queried is sent to the user.

[0011] In a second aspect, the present application provides an event processing device, which is applied to an electronic device, wherein the electronic device is communicatively connected to a plurality of event acquisition platforms, and event definition information is stored in the electronic device, wherein the event definition information is used to characterize event attributes, and the device comprises: An acquisition module, used to acquire event data sent by the event acquisition platform; the event data corresponds to at least one event; A parsing module, used to parse the event data according to the event definition information to obtain event parsing data corresponding to each of the events; A processing module is used to verify the event analysis data of each of the events according to a preset verification format. If the event analysis data passes the verification, the event analysis data is input into a pre-stored large model for processing to obtain supplementary information corresponding to the event, generate an event to be processed based on the supplementary information and event analysis data of each of the events, and process the event to be processed according to the event type of the event to be processed.

[0012] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the method described in any one of the aforementioned embodiments.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any one of the aforementioned implementations.

[0014] The event processing method, device, electronic device and computer-readable storage medium provided by the embodiments of the present application store event definition information for characterizing event attributes in the electronic device, and the electronic device can obtain event data corresponding to at least one event sent by the event acquisition platform, and parse the event data of each event according to the event definition information, thereby obtaining the event parsing data corresponding to each event, and then generate a to-be-processed event according to the event parsing data of each event, thereby processing the to-be-processed event according to the event type of the to-be-processed event. Since the event definition information is stored in the electronic device, and the event definition information can characterize event attributes, the electronic device can first parse the event data of different structural forms according to the event definition information after receiving the event data, and then generate the corresponding to-be-processed event according to the parsed data, so the method can be applied to a variety of event management scenarios.

[0015] 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

[0016] 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.

[0017] Figure 1 A block diagram of an electronic device provided by an embodiment of the present application is shown; Figure 2 A schematic diagram of a process flow of an event processing method provided by an embodiment of the present application is shown; Figure 3 An example diagram of events to be processed is shown; Figure 4 An example diagram of the analysis is shown; Figure 5 An example diagram of event definition information is shown; Figure 6 An example diagram of urgency thresholds is shown; Figure 7 A functional module diagram of an event processing device provided in an embodiment of the present application is shown.

[0018] Icon: 10 - electronic device; 100 - memory; 110 - processor; 120 - communication module; 200 - acquisition module; 210 - parsing module; 220 - processing module. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents 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 creative work are within the scope of protection of the present application.

[0021] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0022] At present, event management is required in many scenarios, such as some business event management within the enterprise, quick handling of urban public opinions, etc. The following will take the quick handling of urban public opinions as an example to introduce.

[0023] The public opinion quick handling refers to the centralized handling of various livelihood demands of citizens through a unified platform. It is a unified gathering center, dispatching center and management center for all urban events and public opinion demands. With the goal of "one network for unified management", focusing on "efficient handling of one matter", and taking "micro-grid real grid" as the starting point, we will explore and improve the joint operation mechanism of urban events and public opinion demands, provide a basis for supervision and assessment, and continuously promote the full-process closed-loop efficient handling of urban governance events in towns, communities and grids, and the full-process closed-loop display and presentation of the platform.

[0024] In the prior art, users are generally required to fill in event information themselves and upload it to the Public Opinion Quick Handling Platform, which then calls multiple algorithms to process the event information and generate pending events. The staff then distributes the pending events to the corresponding handlers according to the list of responsibilities, and the handlers handle the pending events.

[0025] However, this approach often has the following problems: 1. In the prior art, since only event information reported by users according to a preset format is obtained, the data format is relatively simple. Based on this, relevant algorithms can be directly called to parse the event information. However, with the enrichment of event management scenarios, the sources of event data collection are gradually increasing. On this basis, the event data obtained often presents a diversified form, including structured data, unstructured data, etc. Therefore, the method in the prior art cannot process event data in diversified structural forms, resulting in the inability to be applied to a variety of event management scenarios.

[0026] 2. When processing event information to generate events to be processed, it is often necessary to go through multiple processing processes. Each process requires calling multiple algorithms separately, so there is a problem of a long algorithm processing chain. In addition, since multiple algorithms are called multiple times and the correlation between the algorithms is low, they cannot be combined for analysis, resulting in a problem of low data quality.

[0027] 3. When dispatching pending events to the corresponding handlers, it is not possible to mark whether the event is urgent or not. Therefore, the handlers can only handle the events in the order in which they are received, and cannot perform special processing for emergency events. In addition, staff participation is required when dispatching events, which results in low event processing efficiency.

[0028] Based on this, embodiments of the present application provide an event processing method, device, electronic device and computer-readable storage medium to solve the above problems.

[0029] Specifically, Figure 1 For a block diagram of an electronic device 10 provided in an embodiment of the present application, see Figure 1 The electronic device 10 includes a memory 100, a processor 110 and a communication module 120. The memory 100, the processor 110 and the communication module 120 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0030] The memory 100 is used to store computer programs or data that can be executed by the processor. The memory 100 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0031] The processor 110 is used to read / write data or computer programs stored in the memory, and execute the computer program to implement the event processing method provided in the embodiment of the present application.

[0032] The communication module 120 is used to establish a communication connection between the electronic device 10 and other communication terminals through a network, and to send and receive data through the network.

[0033] Optionally, the electronic device may be communicatively connected with a plurality of event acquisition platforms.

[0034] Optionally, the event acquisition platform may include IoT devices, public opinion platforms, hotline platforms, etc.

[0035] Optionally, event definition information may also be stored in the electronic device, and the event definition information is used to characterize event attributes.

[0036] In one possible implementation, the electronic device may also be provided with a public opinion quick-handling platform to centrally process event data sent by different event acquisition platforms.

[0037] It should be understood that Figure 1 The structure shown is only a schematic diagram of the structure of the electronic device 10. The electronic device 10 may also include Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0038] Next, the above Figure 1 The electronic device in the embodiment is the execution subject, and the event processing method provided in the embodiment of the present application is exemplarily introduced in combination with the flow chart.

[0039] Specifically, Figure 2A flow chart of the event processing method provided in the embodiment of the present application is shown in Figure 2 The method is implemented through the following steps S20 to S22.

[0040] Step S20, obtaining event data sent by the event acquisition platform.

[0041] In this embodiment, the event data corresponds to at least one event.

[0042] Optionally, the event data may include data uploaded by users through the event acquisition platform, data collected and uploaded by IoT devices themselves, data crawled and uploaded by the event acquisition platform from other platforms, and so on.

[0043] It is understandable that these event data may include structured data, semi-structured data, unstructured data, etc.

[0044] Step S21, parsing the event data according to the event definition information to obtain event parsing data corresponding to each event.

[0045] Optionally, after acquiring the event data, the electronic device may first parse the event data according to the event definition information, thereby extracting the attributes of the event and obtaining event parsed data.

[0046] Step S22, verify the event analysis data of each event according to a preset verification format. If the event analysis data passes the verification, the event analysis data is input into the pre-stored large model for processing to obtain the supplementary information corresponding to the event. Based on the supplementary information and event analysis data of each event, an event to be processed is generated, and the event to be processed is processed according to the event type of the event to be processed.

[0047] Optionally, considering that the uploaded event data may be incomplete or uploaded incorrectly, which may cause some problems in the event parsing data and make it impossible to generate corresponding events to be processed, in order to improve the efficiency of generating events to be processed, the electronic device may verify the event parsing data before generating events to be processed.

[0048] In this embodiment, the electronic device can verify the event analysis data of each event according to a preset verification format. If the event analysis data passes the verification, the event analysis data is input into a pre-stored large model for processing to obtain supplementary information corresponding to the event. Then, based on the supplementary information and event analysis data of each event, an event to be processed is generated.

[0049] Optionally, the verification format is used to verify whether the event parsing data is complete. It is understandable that if the verification fails, it means that the event data is incomplete or erroneous, so the event parsing data is incomplete, resulting in failure to generate the data to be processed normally.

[0050] For example, if the verification format represents that complete event parsing data includes an event type, but the event type of the event parsing data actually generated is empty, it can be said that the event parsing data is incomplete and cannot pass the verification.

[0051] Optionally, if the verification fails, the electronic device may send verification failure information to a corresponding event acquisition platform so as to re-upload the event data.

[0052] Optionally, the supplementary information refers to other information other than the event parsing data that needs to be supplemented by the device itself.

[0053] In one possible implementation, different types of events may correspond to different event parsing data, and thus the supplementary information may also be different.

[0054] Optionally, the electronic device may generate an event to be processed by integrating the supplementary information and the event analysis information.

[0055] In an example, see Figure 3 For traffic incidents, the event analysis data may include event description, event location, responsible department, and priority. The supplementary information obtained after processing by the large model may include event type, urgency, keywords, and tags. Then, the electronic device can generate events to be processed by integrating the event analysis data and supplementary information.

[0056] It can be understood that in this embodiment, the event type can be selected by the user, or determined by the electronic device through a channel for acquiring event data, or generated by a large model after processing.

[0057] Optionally, if the event is a question-and-answer event, such as a user asking a question, the supplementary information may also include a recommended reply.

[0058] Optionally, in order to ensure the integrity and accuracy of the supplementary information, the electronic device may, after obtaining the event analysis data, search for events related to the event in the database based on the event analysis data, and input the supplementary information corresponding to the events related to the event and the event analysis data together with the event analysis data corresponding to the event into the big model, so that the big model can combine the supplementary information and event analysis data of the related events to generate corresponding supplementary information for the event.

[0059] Optionally, the large model may also integrate intelligent question-answering algorithms, attribute filling algorithms, keyword extraction algorithms, label recognition algorithms, etc.

[0060] Optionally, an intelligent question-answering algorithm can be used to automatically reply to relevant content based on the input; an attribute filling algorithm can be used to identify information such as event type, priority, and responsible department; a keyword extraction algorithm can be used to identify keywords in events; and a tag recognition algorithm can be used to match corresponding event tags based on event content.

[0061] In this embodiment, when generating an event to be processed, the electronic device can process the event analysis data according to the large model without calling multiple algorithms multiple times, thus shortening the algorithm processing chain and improving data quality.

[0062] Optionally, the electronic device may determine a specific processing method for the event to be processed according to the event type of the event to be processed, for example, assigning the event to a corresponding staff member for processing, or the electronic device processing the event itself, etc.

[0063] In the event processing method provided by the embodiment of the present application, event definition information for characterizing event attributes is stored in the electronic device, and the electronic device can obtain event data corresponding to at least one event sent by the event acquisition platform, and parse the event data of each event according to the event definition information, thereby obtaining the event parsing data corresponding to each event, and then generate a to-be-processed event according to the event parsing data of each event, so as to process the to-be-processed event according to the event type of the to-be-processed event. Since the event definition information is stored in the electronic device and the event definition information can characterize the event attributes, the electronic device can first parse the event data of different structural forms according to the event definition information after receiving the event data, and then generate the corresponding to-be-processed event according to the parsed data, so the method can be applied to a variety of event management scenarios.

[0064] Optionally, in order to solve the inconvenience of having to fill out a form every time a user uploads event data, facilitate user operation, simplify the event data uploading process, and improve data processing efficiency, users may be allowed to directly upload collected images, videos, audio and other information.

[0065] In addition to the images and other data uploaded by users through the event acquisition platform, some IoT devices also upload data in the form of images, videos, audio, etc., including cameras, recording devices, etc.

[0066] In this embodiment, after acquiring the event data, the electronic device may first determine whether the event data can be directly parsed through the event definition information.

[0067] It is understandable that since information such as images, videos, and audios are difficult to parse directly through event definition information, if the event data is in these forms, it is necessary to perform preliminary processing on the data in this form first.

[0068] Specifically, when the event data is a picture, video stream or audio data, the electronic device can input the event data into a pre-stored large model for processing, obtain event description information corresponding to the event data, and then parse the event description information according to the event definition information to obtain event analysis data corresponding to the event.

[0069] Optionally, a large model may be generated in advance according to actual application conditions and stored in an electronic device, and then the large model may be called by calling a large model interface to process event data.

[0070] In one possible implementation, the large model can be trained using data such as text data, question-and-answer data, named entity recognition data, relationship extraction data, public opinion data, voice data, image and video data, time series data, multimodal data, and historical event data.

[0071] Optionally, text data refers to data such as documents, for example, policy documents, regulations, government announcements, public service guidelines, etc., which help the model understand the language characteristics and expertise in the government field.

[0072] Optionally, question and answer data refers to frequently asked questions and general answers. For example, for a public opinion quick processing platform, it can be frequently asked questions and answers in government services. This data can be used to train large models to respond to citizens' inquiries and provide some information services.

[0073] Optionally, named entity recognition data refers to data containing entities such as names of people, places, and institutions, which helps large models understand and process government documents.

[0074] Optionally, relation extraction data helps the big model identify and extract relationships between entities in the text, such as associations between clauses in a policy document, relationships between positions in a government structure, and so on.

[0075] Optionally, public opinion data refers to social media posts, news reports, etc. These data can help big models monitor and analyze public sentiment and provide support for government decision-making.

[0076] Optionally, voice data refers to audio data, such as government hotline recordings, which can be used to train large models for automatic speech recognition and speech transcription.

[0077] Optionally, the image and video data can be government public security surveillance videos, official event photos, etc., which can be used for public security monitoring analysis and information release.

[0078] Alternatively, time series data can be government financial reports, demographic data, etc. These data can help the model perform trend analysis and forecasting.

[0079] Optionally, multimodal data refers to data formed by combining different types such as text, voice, and images, which can enhance the model's comprehensive understanding and processing capabilities of government information.

[0080] Optionally, historical event data refers to the event content and handling results of historical events, which can enhance the big model's ability to understand and handle event information.

[0081] In this embodiment, multiple algorithms can be integrated into the large model, so that multiple processing can be performed on event data in a centralized manner by calling the large model.

[0082] In one example, the large model may integrate a speech transcription algorithm, an image description algorithm, a video description algorithm, and the like.

[0083] In this example, the speech transcription algorithm can be used to transcribe speech into text; the image description algorithm can be used to generate image description text corresponding to the image; and the video description algorithm can be used to generate corresponding video description text based on the video.

[0084] Optionally, the event description information refers to a description text corresponding to the event.

[0085] In this embodiment, the electronic device can parse the event description information to obtain event parsing data corresponding to the event.

[0086] In an example, see Figure 4 ,To parse the example graph, the electronic device can obtain the image uploaded by the user through the event acquisition platform, or the image captured by the camera. At this time, the electronic device can call the large model to process the image, so as to obtain the description information corresponding to the event.

[0087] In this example, the description information corresponding to the event may be "a traffic accident occurred at an intersection involving three cars, one of which suffered serious damage."

[0088] In this embodiment, the electronic device may parse the event description information according to the event definition information, thereby obtaining event parsing data.

[0089] Optionally, in order to ensure the accuracy of the event analysis data generated and to facilitate users to confirm whether the event is uploaded accurately, the electronic device can send the generated description information or event analysis data to the corresponding event acquisition platform so that the event acquisition platform can feed back the information to the user for confirmation.

[0090] In this embodiment, after generating event analysis data for a picture, video or audio, the electronic device can determine whether the event data is uploaded by a user through an event acquisition platform, and if so, send the event analysis data to the corresponding event acquisition platform.

[0091] It is understandable that in some scenarios, event data may be more intuitive pictures, videos, audios, etc., but the public opinion quick processing platform in the existing technology cannot process these forms of event data, so it often misses the data collected by the IoT devices, or requires staff to perform relevant processing on the data uploaded by the IoT devices first. For data uploaded by users, users are often required to fill in the form themselves, which reduces data processing efficiency and is not conducive to the user's operating experience.

[0092] With the event processing method provided in the embodiment of the present application, the electronic device can process images, videos and audios through a pre-stored large model to obtain event description information corresponding to the event data, and then obtain event analysis data corresponding to the event by parsing the event description information. This can improve data processing efficiency, facilitate the user's operating experience, simplify the operating process, and reduce manual labor pressure.

[0093] Optionally, if the event data is not information such as images, videos, or audio, the electronic device may directly parse the event data according to the event definition information to obtain event parsed data.

[0094] In a possible implementation manner, the event definition information may include common attributes and channel attributes of the event.

[0095] Optionally, the common attribute refers to the common attributes of the event, such as event type, event status, reporting information, etc.; the channel attribute refers to the differentiated attributes caused by different event collection channels, such as the unique attributes corresponding to the events collected by the Internet of Things devices and the unique attributes corresponding to the events collected by the public opinion platform.

[0096] In one example, the event definition information may be as follows: Figure 5 shown.

[0097] In this embodiment, the electronic device may parse the event data according to the public attributes and the channel attributes respectively, thereby obtaining event parsed data.

[0098] Optionally, the electronic device may also store the original data of the event. It is understandable that the original data refers to the data of the event that has not been processed, that is, includes the above-mentioned event data and event analysis data.

[0099] In this embodiment, the electronic device may send the original data of the event to a database for storage.

[0100] In this embodiment, after parsing the event data, the electronic device may generate an event to be processed according to the event parsing data.

[0101] Optionally, since the event definition information includes the public attributes and channel attributes of the event, the event parsing data includes public parsing data and channel parsing data. Based on this, in order to facilitate the verification of the event parsing data, the verification format may include a public verification format and a channel verification format.

[0102] In this embodiment, the electronic device can verify the public parsing data and the channel parsing data according to the public verification format and the channel verification format respectively.

[0103] It can be understood that if both the public resolution data and the channel resolution data are verified successfully, it is determined that the event resolution data has passed the verification.

[0104] Optionally, each event acquisition platform may correspond to a channel verification format. For example, an IoT device may correspond to an IoT verification format, and a hotline platform may correspond to a hotline verification format.

[0105] Optionally, after generating an event to be processed, the electronic device may process the event to be processed according to its event type.

[0106] In a possible implementation, a first correspondence between event types and processing personnel and a second correspondence between urgency thresholds and processing queues are stored in the electronic device.

[0107] In this embodiment, the electronic device can determine whether a processing personnel is required to process the event to be processed based on the event type of the event to be processed. If necessary, the event to be processed is sent to the corresponding processing personnel. If not, the electronic device can process the event to be processed by itself.

[0108] In one possible implementation, if the event to be processed is a question-and-answer event, it can be determined that no processing personnel are required to process the event to be processed; if the event to be processed is not a question-and-answer event, it can be determined that a processing personnel is required to process the event to be processed.

[0109] Specifically, the electronic device may determine whether the event to be processed is a question-and-answer event according to the event type of the event to be processed.

[0110] In one example, if the event type is a traffic accident, it can be determined that the event to be processed is not a question-and-answer event, and if the event type is a traffic knowledge question-and-answer event, it can be determined that the event to be processed is a question-and-answer event. In this embodiment, if the event to be processed is not a question-and-answer event, the electronic device can determine the urgency threshold of the event to be processed according to the weight value of the event to be processed, and then determine the target processing personnel and target processing queue corresponding to the event to be processed according to the first corresponding relationship, the event type of the event to be processed, the urgency threshold of the event to be processed, and the second corresponding relationship.

[0111] Optionally, the weight value includes a first weight value corresponding to the event type of the event to be processed and a second weight value generated by the large model and representing the urgency of the event to be processed.

[0112] Optionally, the electronic device may calculate an emergency level threshold corresponding to the event to be processed according to the first weight value and the second weight value.

[0113] In one possible implementation, the electronic device may calculate the urgency threshold by adding the first weight value and the second weight value.

[0114] In an example, see Figure 6 The event types include traffic congestion, illegal road occupation, and complaint reports. The first weight values ​​corresponding to these three events are 4, 3, and 2 respectively, and the specific urgency levels are divided into emergency, high, medium, and low. The second weight values ​​corresponding to these four urgency levels are 4, 3, 2, and 1 respectively. If the event type of an event to be processed is traffic congestion and the urgency level is emergency, then its corresponding urgency threshold should be 8.

[0115] Optionally, the electronic device may first determine the corresponding responsible department according to the relevant information of the event to be processed, and then determine the corresponding target processing personnel according to the event type of the event to be processed and the first corresponding relationship.

[0116] Optionally, each processing personnel's matter queue may include multiple ones, for example, an urgent matter queue and a common matter queue, or a first urgent matter queue, a second urgent matter queue and a common queue, which may be specifically set according to actual application conditions.

[0117] Optionally, each matter queue may correspond to an urgency threshold range. For example, the urgency threshold range corresponding to the urgent matter queue is greater than 5, and the urgency threshold range corresponding to the common matter queue is less than or equal to 5.

[0118] In this embodiment, the electronic device can determine the corresponding target event queue according to the urgency threshold of the pending event and the second corresponding relationship. For example, for a pending event with an urgency threshold of 8, its target queue can be determined to be an emergency event queue.

[0119] In this embodiment, the electronic device can send the pending event to the target processing queue of the target processing personnel, so that the target processing personnel can obtain the pending event from the target processing queue and process the pending event.

[0120] Optionally, the electronic device may give priority to assigning more urgent pending events, and the target processing personnel may first obtain the pending events in the urgent event queue for processing when processing.

[0121] In this embodiment, since the electronic device can allocate pending events according to their urgency scores, thereby giving priority to allocating more urgent pending events to event processing queues with higher urgency, urgent events and ordinary events can be distinguished when allocating pending events, ensuring that urgent events are processed first.

[0122] In addition, since electronic devices can directly dispatch events without the involvement of staff, the efficiency of event handling can be improved.

[0123] Optionally, the electronic device may also be connected to a database for communication. To facilitate event processing by processing personnel, the processing personnel may obtain processing information of events associated with or similar to the event to be processed from the database for reference when processing the event to be processed.

[0124] In this embodiment, the electronic device may obtain a first query request sent by a target processing person.

[0125] Optionally, the first query request may include keywords and event types of the event to be processed, and the electronic device may obtain processing information of the target event from the database according to the keywords and event type.

[0126] It can be understood that the keywords and event type of the target event are consistent with the keywords and event type of the event to be processed, that is, the target event is related to the event to be processed.

[0127] Optionally, the electronic device may construct a query condition according to keywords and event types, and acquire processing information of the target event from a database according to the query condition.

[0128] Optionally, the processing information may include processing method, processing time, event processing time, user satisfaction with the processing, etc.

[0129] In this embodiment, the electronic device may send the processing information of the target event to the target processing personnel so that the target processing personnel may process the event to be processed according to the processing information of the target event.

[0130] It can be understood that the target processing personnel can determine the processing method for the event to be processed according to the processing information of the target event, and process the event to be processed.

[0131] Optionally, after the target processing personnel has processed the pending event, they can upload the processing information corresponding to the pending event, and the electronic device can store the processing information in a database for other processing personnel to review.

[0132] In addition, after the processing of the pending event is completed, the electronic device can also process the pending event through the large model to generate an event summary corresponding to the pending event.

[0133] In one possible implementation, the electronic device may input the event parsing data, processing information, and supplementary information of the event to be processed into a large model for processing, thereby generating an event summary.

[0134] It is understandable that a summary generation algorithm may also be integrated into the large model to generate an event summary based on the data of the event to be processed.

[0135] Optionally, the electronic device may also collect the user's evaluation of the event to be processed, such as keyword evaluation, event tag evaluation, processing result evaluation, satisfaction evaluation, etc.

[0136] Optionally, the electronic device may bind the evaluation of the event to be processed with other data of the event to be processed, and upload the data to a database.

[0137] Optionally, in order to ensure the accuracy of the large model, the electronic device may also iteratively train the large model at regular intervals, and at this time, sample data may be directly selected from the relevant data of each event in the database.

[0138] In one possible implementation method, the staff can review the relevant data of the pending events that have been processed during this period at regular intervals, and select data with better data quality to add sample labels. Based on this, when iteratively training the large model, the electronic device can obtain the data of the pending events with sample labels added from the database and use it as sample data for training.

[0139] Optionally, data with better quality may be data corresponding to an event to be processed that has a better evaluation status and is more complete.

[0140] Optionally, the user can also query the electronic device for specific circumstances of some events through the event acquisition platform, or directly query through the public opinion quick handling platform, such as processing results, processing progress, etc.

[0141] Optionally, considering that in the prior art, data can only be queried by entering query expressions, such as entering query conditions such as data ID, data type, etc., and this method is not convenient for operation, especially for users who are not familiar with related businesses. Therefore, in order to facilitate user operation and improve the query experience, in this embodiment, users can be allowed to query data through natural language.

[0142] Specifically, the electronic device may obtain the second query request sent by the user.

[0143] Optionally, the second query request includes query conditions for the event to be queried.

[0144] In this embodiment, if the query condition is in natural language, the electronic device can input the query condition into a preset large model for processing to obtain a database query statement for the event to be queried, obtain the data corresponding to the event to be queried from the database according to the database query statement, and send the data corresponding to the event to be queried to the user.

[0145] Optionally, users can send natural language query conditions through the intelligent query interface or AI question and answer interface.

[0146] Optionally, the large model may also be integrated with an NL2SQL algorithm for converting the natural language into database query statements.

[0147] Optionally, the query condition may not be a natural language, but a query parameter uploaded according to a common query interface, such as the event type, event ID, event location, etc. of the target event.

[0148] In this case, the electronic device may parse the query parameter, and obtain data corresponding to the event to be queried from the database according to the parsed query parameter, and send the data corresponding to the event to be queried to the user.

[0149] It can be understood that query parameter parsing refers to describing query parameters as query expressions.

[0150] In one example, if the query parameters include eventType='traffic accident', startTime='2024-06-01', and endTime='2024-06-30', the parsed query parameters are (eventType='traffic accident' and (startTime>='2024-06-01' and endTime<='2024-06-30')).

[0151] It should be noted that for different types of databases, the parsed query parameters may be different, and can be set in advance according to the actual database.

[0152] Optionally, in order to facilitate information sharing, some enterprises or institutions may be allowed to query data of related events, for example, traffic control departments may be allowed to query data of traffic events, newspapers and other enterprises may be allowed to query data of public opinion events, etc. In order to execute the corresponding steps in the above embodiments and various possible methods, an implementation method of an event processing device is given below. Optionally, the event processing device may adopt the above Figure 1 For further information, please refer to Figure 7 , Figure 7 A functional module diagram of an event processing device provided in an embodiment of the present application. It should be noted that the basic principle and technical effects of the event processing device provided in this embodiment are the same as those of the above-mentioned embodiments. For the sake of brief description, for parts not mentioned in this embodiment, reference can be made to the corresponding contents in the above-mentioned embodiments. The event processing device includes: an acquisition module 200, a parsing module 210, and a processing module 220.

[0153] The acquisition module 200 is used to acquire event data sent by the event acquisition platform; the event data corresponds to at least one event.

[0154] It can be understood that the acquisition module 200 can also be used to execute the above step S20.

[0155] The parsing module 210 is used to parse the event data according to the event definition information to obtain the event parsing data corresponding to each event.

[0156] It can be understood that the analysis module 210 can also be used to execute the above step S21.

[0157] The processing module 220 is used to verify the event analysis data of each event according to a preset verification format. If the event analysis data passes the verification, the event analysis data is input into a pre-stored large model for processing to obtain supplementary information corresponding to the event, and based on the supplementary information and event analysis data of each event, an event to be processed is generated, and the event to be processed is processed according to the event type of the event to be processed.

[0158] It can be understood that the processing module 220 can also be used to execute the above step S22.

[0159] Optionally, the parsing module 210 is also used to input the event data into a pre-stored large model for processing when the event data is a picture, video stream or audio data, to obtain event description information corresponding to the event data; and to parse the event description information according to the event definition information.

[0160] Optionally, the processing module 220 is further configured to verify the public resolution data and the channel resolution data according to the public verification format and the channel verification format respectively; if both the public resolution data and the channel resolution data are verified successfully, it is determined that the event resolution data passes the verification.

[0161] Optionally, the processing module 220 is also used to determine whether the event to be processed is a question-and-answer event based on the event type of the event to be processed; if the event to be processed is not a question-and-answer event, determine the urgency threshold of the event to be processed based on the weight value of the event to be processed; determine the target processing personnel and the target processing queue corresponding to the event to be processed based on the first correspondence, the event type of the event to be processed, the urgency threshold of the event to be processed and the second correspondence; send the event to be processed to the target processing queue of the target processing personnel, so that the target processing personnel obtains the event to be processed from the target processing queue and processes the event to be processed.

[0162] Optionally, the processing module 220 is also used to obtain a first query request sent by a target processing personnel; the first query request includes keywords and event types of the event to be processed; based on the keywords and event types, processing information of the target event is obtained from the database; the keywords and event type of the target event are consistent with the keywords and event type of the event to be processed; the processing information of the target event is sent to the target processing personnel, so that the target processing personnel processes the event to be processed according to the processing information of the target event.

[0163] Optionally, the processing module 220 is also used to obtain a second query request sent by the user; the second query request includes query conditions for the event to be queried; if the query conditions are natural language, the query conditions are input into a preset large model for processing to obtain a database query statement for the event to be queried; data corresponding to the event to be queried is obtained from the database according to the database query statement, and the data corresponding to the event to be queried is sent to the user.

[0164] Optionally, the above modules can be stored in the form of software or firmware. Figure 1 The memory shown in FIG. 1 or the operating system (OS) of the electronic device 10 may be fixed therein and may be Figure 1 Meanwhile, the data and program codes required for executing the above modules can be stored in the memory.

[0165] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the event processing method provided in the embodiment of the present application can be implemented.

[0166] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0167] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0168] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0169] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An event processing method, characterized in that: Applied to an electronic device, the electronic device is communicatively connected with a plurality of event acquisition platforms, and event definition information is stored in the electronic device, the event definition information is used to characterize event attributes, the method comprises: Acquire event data sent by the event acquisition platform; the event data corresponds to at least one event; Parsing the event data according to the event definition information to obtain event parsing data corresponding to each of the events; The event parsing data of each of the events is verified according to a preset verification format. If the event parsing data passes the verification, the event parsing data is input into a pre-stored large model for processing to obtain supplementary information corresponding to the event. Based on the supplementary information and event parsing data of each of the events, an event to be processed is generated, and the event to be processed is processed according to the event type of the event to be processed.

2. The method according to claim 1, characterized in that The parsing of the event data according to the event definition information includes: In the case where the event data is a picture, a video stream or audio data, the event data is input into a pre-stored large model for processing to obtain event description information corresponding to the event data; The event description information is parsed according to the event definition information.

3. The method according to claim 1, characterized in that The event parsing data includes public parsing data and channel parsing data, and the verification format includes a public verification format and a channel verification format; the verification of the event parsing data of each event according to the preset verification format includes: Verifying the public parsed data and the channel parsed data according to the public verification format and the channel verification format respectively; The method further comprises: If both the public resolution data and the channel resolution data are verified successfully, it is determined that the event resolution data has passed the verification.

4. The method according to claim 1, characterized in that: The electronic device stores a first correspondence between event types and processing personnel and a second correspondence between urgency thresholds and processing queues, and the processing of the event to be processed according to the event type of the event to be processed includes: Determine whether the event to be processed is a question-and-answer event according to the event type of the event to be processed; If the event to be processed is not a question-and-answer event, determining the urgency threshold of the event to be processed according to the weight value of the event to be processed; Determine a target processing person and a target processing queue corresponding to the event to be processed according to the first corresponding relationship, the event type of the event to be processed, the urgency threshold of the event to be processed, and the second corresponding relationship; The pending event is sent to the target processing queue of the target processing personnel, so that the target processing personnel obtains the pending event from the target processing queue and processes the pending event.

5. The method according to claim 4, characterized in that The electronic device is also in communication with a database, and the database stores processing information corresponding to a plurality of events. The method further includes: Acquire a first query request sent by a target processing person; the first query request includes a keyword and an event type of the event to be processed; According to the keyword and the event type, obtaining processing information of the target event from the database; the keyword and event type of the target event are consistent with the keyword and event type of the event to be processed; The processing information of the target event is sent to the target processing personnel so that the target processing personnel can process the event to be processed according to the processing information of the target event.

6. The method according to claim 1, characterized in that The method further comprises: Acquire a second query request sent by the user; the second query request includes a query condition for the event to be queried; If the query condition is in natural language, the query condition is input into a preset large model for processing to obtain a database query statement for the event to be queried; The data corresponding to the event to be queried is acquired from the database according to the database query statement, and the data corresponding to the event to be queried is sent to the user.

7. An event processing device, characterized in that: Applied to an electronic device, the electronic device is connected to multiple event acquisition platforms for communication, and the electronic device stores event definition information, the event definition information is used to characterize event attributes, and the device includes: An acquisition module, used to acquire event data sent by the event acquisition platform; the event data corresponds to at least one event; A parsing module, used to parse the event data according to the event definition information to obtain event parsing data corresponding to each of the events; A processing module is used to verify the event analysis data of each of the events according to a preset verification format. If the event analysis data passes the verification, the event analysis data is input into a pre-stored large model for processing to obtain supplementary information corresponding to the event, generate an event to be processed based on the supplementary information and event analysis data of each of the events, and process the event to be processed according to the event type of the event to be processed.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images