Emergency report generation method and device, equipment and storage medium

Abstract

The invention discloses an emergency report generation method and device, equipment and a storage medium, and belongs to the technical field of data processing. The method comprises the following steps: acquiring and preprocessing original data corresponding to a target event to obtain first preprocessed data; inputting the first preprocessed data into a preset event recognition model, and recognizing to obtain an event type and an event progress stage of the target event; based on the event type and the event progress stage, determining a corresponding target template from a preset report template library; calculating contribution degrees of different data in the first preprocessed data to event levels based on a preset data screening model, and determining key data; and based on a natural language processing algorithm, converting the key data into a descriptive text, and filling the target template to obtain an emergency report. According to the method, the readability of the emergency report is improved on the whole, and the method is suitable for report generation of various emergencies.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method, apparatus, device, and storage medium for generating an emergency event report. Background Art

[0002] In the event of an emergency mass incident (such as natural disasters, major traffic accidents, public health incidents, etc.), in order to ensure the effective organization of rescue and incident handling, it is often necessary for emergency management departments, medical institutions, and relevant units at all levels to respond quickly. During this process, it is necessary to report the emergency event report in a timely and accurate manner, including conveying key information such as the number of casualties, the progress of personnel treatment, and resource seeking. However, in related technologies, the automatic report generation system can only generate reports for single-type events, and the generated report content is usually structured text, which cannot fully reflect the logical relationship between data, is not convenient for comprehensively understanding the overall situation of the event, and at the same time, the data information is redundant and the key points of the report content are not prominent, thus resulting in poor readability of the report content.

[0003] Therefore, in the process of generating an event report in related technologies, there are technical problems of single report type and poor readability of the report content. Summary of the Invention

[0004] The main purpose of the present invention is to provide a method, apparatus, device, and storage medium for generating an emergency event report, aiming to solve the technical problems of single report type and poor readability of the report content in related technologies.

[0005] To achieve the above object, the present invention provides a method for generating an emergency event report, the method including the following steps: S1, obtaining the original data corresponding to the target event and performing preprocessing to obtain the first preprocessed data; S2, inputting the first preprocessed data into a preset event recognition model to identify the event type and the event progress stage of the target event; S3, determining the corresponding target template from a preset report template library based on the event type and the event progress stage; S4, calculating the contribution degree of different data in the first preprocessed data to the event level based on a preset data screening model, and determining the key data; S5, converting the key data into descriptive text based on a natural language processing algorithm, filling the target template, and obtaining the emergency event report.

[0006] Optionally, in step S4, the construction steps of the preset data screening model specifically include: Obtain the first historical emergency event data, and perform preprocessing to obtain the first training set; the first historical emergency event data includes at least the event level, event occurrence time, event affected range, event type, total number of people affected by the event, number of casualties, number of people in the first-level triage, number of people in the second-level triage, and resource consumption; Input the first training set into a decision tree model, and perform model training based on the dynamic weighted information gain formula to obtain a preset data screening model; the dynamic weighted information gain formula is: ; where, S is the first training set, is the dynamic information gain of the first training set S, is the feature i the associated weight with the event level at time t, is the subset divided according to the feature i , is the size of the first training set S, is the size of the subset , is the entropy of the first training set S , is the entropy of the subset ; The calculation formula of the associated weight is: ; where, is t the duration of the event corresponding to time t, is t the resource consumption corresponding to time t, is the adjustment coefficient of the feature i on the event duration, is the adjustment coefficient of the feature i on the resource consumption. Optionally, in step S2, the construction steps of the preset event recognition model specifically include: Obtain the second historical emergency event data, and perform preprocessing to obtain multiple historical emergency event reports; Perform event type annotation and event progress stage annotation for each historical emergency event report to obtain the second training set; the event type annotation includes at least natural disasters, traffic accidents, and public health events, and the event progress stage annotation includes at least the initial stage of the event, the middle stage of the event, and the later stage of the event; Extract the relevant features of each historical emergency event report; the relevant features include at least the event occurrence time, event duration, event occurrence location, total number of people affected by the event, number of casualties, number of people in the first-level triage, number of people in the second-level triage, and resource consumption; Input the second training set into the deep learning model, train it based on relevant features, and obtain a preset event recognition model.

[0007] Optionally, the target template has a specific report framework. Step S5 specifically includes: Based on natural language processing algorithms, identify the mapping relationship between key data and fields in the predefined sentence template; Based on the mapping relationship, fill the key data into the corresponding fields of the predefined sentence template to obtain descriptive text; Based on the report framework, insert the descriptive text into the target template to obtain an emergency event report.

[0008] Optionally, step S1 specifically includes: Extract the original data corresponding to the target event to obtain plain text data; Perform standardization processing and data completion processing on the plain text data to obtain first preprocessed data.

[0009] Optionally, after step S5, the method further includes: a1, Based on the file format requirements of the receiving department corresponding to the emergency event report, perform format conversion on the emergency event report to obtain a target format report that meets the file format requirements; a2, In response to the user's one-key reporting instruction, select the reporting channel corresponding to the receiving department; a3, Based on the reporting channel, upload the target format report to the receiving department.

[0010] Optionally, after step a3, the method further includes: a4, Based on a preset time interval, obtain and monitor the processing progress of the target format report; a5, If the processing progress changes, record the current processing progress in chronological order to form a historical processing record arranged in chronological order.

[0011] In addition, to achieve the above object, the present invention also provides an emergency event report generation device, the device includes: A data preprocessing module, configured to obtain the original data corresponding to the target event and perform preprocessing to obtain first preprocessed data; An event recognition module, configured to input the first preprocessed data into a preset event recognition model to identify the event type and event progress stage of the target event; A template selection module, configured to determine a corresponding target template from a preset report template library based on the event type and event progress stage; A data screening module, configured to calculate the contribution degree of different data in the first preprocessed data to the event level based on a preset data screening model, and determine key data; A report generation module, configured to convert key data into descriptive text based on natural language processing algorithms, fill a target template, and obtain an emergency incident report.

[0012] Furthermore, to achieve the above object, the present invention also provides an emergency incident report generation device, which includes: a memory, a processor, and an emergency incident report generation program stored on the memory and executable on the processor. The emergency incident report generation program is configured to implement the steps of the emergency incident report generation method as described above.

[0013] Even further, to achieve the above object, the present invention also provides a computer-readable storage medium, on which an emergency incident report generation program is stored. When the emergency incident report generation program is executed by a processor, it implements the steps of the emergency incident report generation method as described above.

[0014] The present invention presets different report templates for different event types and different event progress stages, constructs a preset template library, and can realize the generation of event reports for various emergency incidents. Secondly, according to the contribution degree of different data to the event level, key data is screened out, which can avoid data redundancy in the report content and make the key information more prominent. On this basis, after converting the key data in the form of structured text into descriptive text using natural language processing algorithms, template filling is performed, making the logical relationship between information elements in the emergency incident report content clear and helping the report receiving department to accurately understand the overall event. Therefore, the present invention improves the readability of emergency incident reports as a whole. Description of the Drawings

[0015] Figure 1 is a schematic structural diagram of an emergency incident report generation device in the hardware operating environment related to the embodiment solution of the present invention; Figure 2 is a schematic flowchart of the first embodiment of the emergency incident report generation method of the present invention; Figure 3 is a schematic flowchart of the second embodiment of the emergency incident report generation method of the present invention; Figure 4 is a schematic flowchart of the third embodiment of the emergency incident report generation method of the present invention.

[0016] The realization, functional characteristics, and advantages of the object of the present invention will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0017] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] The following further elaborates on the inventive concept of the present application in combination with some specific embodiments and specific implementation manners.

[0019] Refer to Figure 1 , Figure 1 which is a schematic structural diagram of an emergency report generation device for the hardware operating environment involved in the solution of the embodiment of the present invention.

[0020] As Figure 1 shown, the emergency report generation device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0021] Those skilled in the art can understand that Figure 1 the structure shown in

[0022] does not constitute a limitation on the emergency report generation device, and may include more or fewer components than shown, or combine some components, or have different component arrangements. Figure 1 As

[0023] shown, the memory 1005, as a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and an emergency report generation program. Figure 1 In the emergency report generation device shown in

[0024] the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with users; the processor 1001 and the memory 1005 in the emergency report generation device of the present invention may be provided in the emergency report generation device. The emergency report generation device calls the emergency report generation program stored in the memory 1005 through the processor 1001 and executes the emergency report generation method provided by the embodiment of the present invention. Figure 2, Figure 2 It is a schematic flowchart of the first embodiment of a method for generating an emergency report according to the present invention.

[0025] In this embodiment, the method for generating an emergency report includes: Step S1: Obtain the original data corresponding to the target event and perform preprocessing to obtain the first preprocessed data.

[0026] In step S1, the specific steps of preprocessing include: Step S11: Extract the original data corresponding to the target event to obtain plain text data.

[0027] Step S12: Perform standardization processing and data completion processing on the plain text data to obtain the first preprocessed data.

[0028] In this embodiment, the target events include but are not limited to group emergencies such as traffic accidents, natural disasters, and public health events. In the specific implementation process, after a target event occurs, the emergency report generation device can obtain the original data from multiple data sources. Among them, the data sources include but are not limited to hospital information systems, emergency management platforms, sensors, and monitoring devices, etc.

[0029] Specifically, the original data can be in various data forms such as tables, statistical charts, and plain text. First, use specific data extraction methods to extract the original data from different data sources to obtain plain text data that is convenient for processing. The data extraction method can adopt one or more of OCR technology, chart data extraction software, and machine learning methods.

[0030] Perform standardization processing on the obtained plain text data. For example, convert time or temperature data with different units into a unified standard format; another example is to scale data with different dimensions to a unified numerical range for data processing and analysis.

[0031] If there are data missing problems in the standardized plain text data, use a preset data completion algorithm to complete the missing data. Among them, the preset data completion algorithm can specifically adopt one or more of interpolation method, mean filling method, median filling method, KNN filling method, and multiple imputation method.

[0032] Step S2: Input the first preprocessed data into a preset event recognition model to identify the event type and event progress stage of the target event.

[0033] In step S2, the specific steps for constructing the preset event recognition model include: Step S21: Obtain the second historical emergency data and perform preprocessing to obtain multiple historical emergency reports.

[0034] Specifically, the second historical emergency data covers different types of emergencies and covers as many characteristics of the events as possible (such as the time of the event, the duration of the event, the location of the event, the total number of people affected by the event, the number of casualties, the number of first-level triage, the number of second-level triage, and resource consumption, etc.). Preprocessing includes but is not limited to denoising, standardization, and missing value processing.

[0035] Step S22: annotate each historical emergency event report with respect to the event type and the event progress stage to obtain a second training set.

[0036] Among them, the event type labeling includes at least natural disasters, traffic accidents and public health events, and the event progress stage labeling includes at least the early stage of the event, the middle stage of the event and the late stage of the event.

[0037] Labeling can be done manually or semi-automatically. Manual labeling requires labelers to classify events according to their descriptions, but it can ensure high accuracy. Semi-automatic labeling can use natural language processing (NLP) technology to extract key information and make preliminary labels, which can then be manually corrected.

[0038] Finally, the labeled data will be used as the second training set. The historical emergency reports in the second training set contain event type labels and event progress stage labels.

[0039] Step S23: extract relevant features of each historical emergency report.

[0040] Among them, the relevant characteristics include at least the time of the incident, the duration of the incident, the location of the incident, the total number of people affected by the incident, the number of casualties, the number of first-level triage patients, the number of second-level triage patients, and resource consumption.

[0041] Step S24: Input the second training set into the deep learning model, perform training based on relevant features, and obtain a preset event recognition model.

[0042] Specifically, for each historical emergency report, relevant features associated with the event type and the stage of event progress, such as the time of event, duration of event, location of event, total number of people affected by the event, number of casualties, number of first-level triage patients, number of second-level triage patients, and resource consumption, are extracted. The second training set is input into the deep learning model, and the deep learning model is trained to learn the mapping relationship between relevant features and event types and event stages. After multiple rounds of iterations, a preset event recognition model is obtained.

[0043] Finally, the preset event recognition model is used to identify the event type and event progress stage corresponding to the target event from the first preprocessed data.

[0044] Step S3: Based on the event type and the event progress stage, determine the corresponding target template from the preset report template library.

[0045] In this embodiment, a preset template library is constructed in advance to meet the generation of emergency incident reports in multiple scenarios. Specifically, corresponding report templates are preset for different event progress stages of different event types and stored in the preset template library. In the specific implementation process, first, according to the event type, multiple report templates corresponding to this event type can be queried from the preset template library, and then further queried according to the event progress stage to obtain the target template corresponding to the event progress stage from the multiple report templates corresponding to this event type.

[0046] In some specific embodiments, this query process can be implemented through Function 1: Function 1: ; Wherein, is the event type, is the event progress stage, is the target template, represents the query operation. Specifically, the event type and the event progress stage are used as known data and input into Function 1, and then according to the input known conditions, the query operation involved in Function 1 is executed to obtain the target template .

[0047] For example, for different event progress stages of the same emergency incident, an initial report template, a follow-up report template, and a final report template can be preset respectively. Among them, the initial report template can focus on reporting the general situation of the event, the follow-up report template can focus on reporting the consumption of treatment resources and the progress of treatment, and the final report template can focus on reporting the summary and analysis of the event.

[0048] Step S4: Based on the preset data screening model, calculate the contribution degree of different data in the first preprocessed data to the event level, and determine the key data.

[0049] Specifically, first input the preprocessed data into the preset data screening model to calculate the contribution degree of different data to the event level. Based on the contribution degree, sort the different data according to the contribution degree, and determine the data with a contribution degree greater than the first preset value as the key data.

[0050] In step S4, the construction steps of the preset data screening model specifically include: Step S41: Obtain the first historical emergency incident data and perform preprocessing to obtain the first training set.

[0051] Among them, the first historical emergency event data includes at least the event level, event occurrence time, event affected scope, event type, total number of people affected by the event, number of casualties, number of people in the first-level triage, number of people in the second-level triage, and resource consumption.

[0052] The preprocessing of the first historical emergency event data includes but is not limited to missing value processing, normalization processing, and categorical feature encoding processing to obtain the first training set. Among them, the categorical features include but are not limited to features such as event occurrence time, event affected scope, event type, total number of people affected by the event, number of casualties, number of people in the first-level triage, number of people in the second-level triage, and resource consumption.

[0053] Step S42: Input the first training set into the decision tree model, and perform model training based on the dynamic weighted information gain formula to obtain a preset data screening model.

[0054] Among them, the dynamic weighted information gain formula is: ; where S is the first training set, is the dynamic information gain of the first training set S, is the feature i the associated weight with the event level at time t, is based on the feature i the subset divided, is the first training set S the size of, is the subset the size of, is the first training set S the entropy of, is the subset the entropy of.

[0055] The calculation formula for the associated weight is: ; where is t the duration of the event corresponding to time t, is t the resource consumption corresponding to time t, is the feature i the adjustment coefficient on the event duration, is the feature i the adjustment coefficient on the resource consumption.

[0056] Specifically, the decision tree model repeatedly performs feature selection and splitting through the first training set, and each time according to the information gain calculation result, selects the feature with the largest information gain for splitting until a complete tree structure is obtained, and finally obtains a preset data screening model.

[0057] It is worth mentioning that during the decision tree training process, the information gain formula is improved by introducing dynamic weighting. Based on the original information gain of the feature i while comprehensively considering the influence of the duration of the event and the resource consumption on the contribution degree of the feature i further dynamic weighting is performed to obtain the dynamic weighted information gain value of the feature i at time t. Thus, the preset data screening model obtained through training can screen out the key data that is most important for the current event progress stage according to the event progress stage. Then, an emergency event report is generated based on the key data, thereby avoiding information redundancy in the emergency event report, making the content of the emergency event report more focused and more readable.

[0058] Among them, the adjustment coefficient is t at time i the change rate of the feature with the increase of the duration of the event. The adjustment coefficient t is i at time

[0059] Step S5: Based on the natural language processing algorithm, convert the key data into descriptive text, fill in the target template, and obtain the emergency event report.

[0060] Step S5 specifically includes: Step S51: Based on the natural language processing algorithm, identify the mapping relationship between the key data and the fields in the predefined sentence template.

[0061] Step S52: Based on the mapping relationship, fill the key data into the corresponding fields of the predefined sentence template to obtain descriptive text.

[0062] Step S53: Based on the report framework, insert the descriptive text into the target template to obtain the emergency event report.

[0063] Specifically, using the natural language processing algorithm, the input key data is first preprocessed such as word segmentation, part-of-speech tagging, named entity recognition, etc., and then the mapping relationship between the key data and the fields of the predefined sentence template is identified through a machine learning model.

[0064] For example: The key data is "Casualties: 50; Seriously injured: 15; flesh wound: 35", and the corresponding predefined sentence template 1 is "In this accident, a total of (field 1) people were injured, among which (field 2) people were seriously injured and (field 3) people had minor injuries". Then the identified mapping relationship is: the data "50" is mapped to "field 1", the data "15" is mapped to "field 2", and the data "35" is mapped to "field 3".

[0065] According to the recognized mapping relationship, fill the key data into the corresponding fields, and the complete descriptive text in the above example is "In this accident, a total of 50 people were injured, including 15 seriously injured and 35 slightly injured."

[0066] It is worth mentioning that the target template has a specific report framework, which determines the structural hierarchy and filling rules of the emergency event report. According to the structural hierarchy and filling rules of the report, insert the obtained descriptive text into the corresponding position of the target template to obtain the emergency event report.

[0067] For example, the report framework of the target template consists of structural hierarchies such as event summary, event cause, and emergency measures, and the filling rules specify the mapping relationship between the predefined sentence templates and the structural hierarchies (e.g., predefined sentence template 1 maps to the event summary). According to this mapping relationship, insert the descriptive text generated based on the predefined sentence template into the position where the corresponding structural hierarchy is located (e.g., insert the descriptive text generated based on predefined sentence template 1 into the event summary).

[0068] In some other specific embodiments, the filling process of the key data can be implemented by Function Two: Function Two: ; where the target template is a predefined natural language generation model is the key data is the generated emergency event report text is the filled template.

[0069] Specifically, Function Two first executes the step of filling the key data into the target template to obtain the filled emergency event report; then execute the step of optimizing the content of the emergency event report using the predefined natural language generation model to obtain the final report that is smooth and natural.

[0070] In this embodiment, according to different event types and event progress stages, a variety of report templates are preset and a preset template library is constructed, so that event reports for various emergencies can be generated. At the same time, key data is screened out based on the contribution degree of different data to the event level, avoiding data redundancy in the report content and making the focus of information more prominent. On this basis, through natural language processing algorithms, the key data in the form of structured text is converted into descriptive text and filled into the target template, so that the information elements in the emergency event report are logically clear and facilitate the receiving department to accurately understand the overall situation of the event. Therefore, the present invention improves the readability of the emergency event report as a whole. Furthermore, it helps relevant departments respond to emergencies more efficiently and make scientific decisions.

[0071] Further, a second embodiment is proposed based on the first embodiment. Refer to Figure 3 , Figure 3 which is a schematic flowchart of the second embodiment of the method for generating an emergency event report of the present invention.

[0072] In this embodiment, after step S5, the method further includes: Step a1: Based on the file format requirements of the receiving department corresponding to the emergency event report, perform format conversion on the emergency event report to obtain a target format report that meets the file format requirements.

[0073] Step a2: In response to the user's one-key reporting instruction, select the reporting channel corresponding to the receiving department.

[0074] Step a3: Based on the reporting channel, upload the target format report to the receiving department.

[0075] Specifically, first, it is necessary to obtain the file format requirements of the receiving department for the emergency event report, including file types (such as PDF, Word, Excel, etc.), document structures (such as whether specific headers, field names, and timestamp formats are required), and supported types of attachments.

[0076] In the specific implementation process, the format requirements can be extracted from the document templates, interface documents, or configuration files obtained from the receiving department. When performing format conversion, the corresponding document conversion tools or document conversion services can be directly called to complete it.

[0077] In some specific embodiments, this upload process can be implemented through Function Three: Function Three: ; where is the current emergency event report, is the target format, is the converted emergency event report, represents the conversion operation.

[0078] Specifically, the current emergency event report and the target format are input into Function Three as known data. Then, according to the input known conditions, the corresponding document conversion tool or document conversion service is called through Function Three to complete the conversion operation, and the converted emergency event report is obtained. .

[0079] Furthermore, in this embodiment, the user can quickly complete the upload of the emergency event report through one-key reporting. Specifically, when the user issues the "one-key reporting" instruction, the appropriate reporting channel is automatically selected according to the receiving department. Specifically, the appropriate reporting channel can be selected according to the configuration file of the receiving department. In the specific implementation process, the reporting channel can be one or more of email upload, cloud storage upload, and FTP upload.

[0080] In some specific embodiments, this upload process can be implemented through Function Four: Function Four: ; wherein, is the converted emergency event report, is the reporting channel, represents the upload operation.

[0081] Specifically, the converted emergency event report and the reporting channel are input into Function Four as known data. Then, according to the input known conditions, the upload operation involved in Function Four is executed to complete the upload task of the emergency event report.

[0082] During the upload process of the emergency event report, to ensure the visibility of the upload result of the emergency event report, the file can be confirmed whether it is successfully uploaded according to the upload result returned by the reporting channel, and feedback to the user (such as success prompt, failure retry prompt, etc.).

[0083] In this embodiment, by performing format conversion on the emergency event report to make it meet the file format requirements of the receiving department, the format of the report is ensured to be highly consistent with the department requirements. On this basis, in response to the user's one-key reporting instruction, the corresponding reporting channel is automatically selected, simplifying the user operation process, improving work efficiency and reducing manual intervention. It not only improves the accuracy and timeliness of report transmission, but also enhances the user experience, saving time and resources.

[0084] Furthermore, based on the second embodiment, a third embodiment is proposed. Refer to Figure 4 , Figure 4 which is the flowchart of the third embodiment of the method for generating an emergency event report of the present invention.

[0085] In this embodiment, after step a3, the method further includes: Step a4: Obtain and monitor the processing progress of the target format report based on a preset time interval.

[0086] Step a5: If the processing progress changes, record the current processing progress in chronological order to form a historical processing record arranged in chronological order.

[0087] Specifically, during the upload process of the target format report, continuously obtain the current status of the target format report and relevant log information through the upload channel according to the preset time interval, and extract the processing progress information therefrom. Once it is monitored that the processing progress changes, record the current progress information and store it in chronological order to form a historical processing record. Among them, the progress information may include information such as upload progress, process status, and report time.

[0088] In addition, in some specific embodiments, for the convenience of subsequent analysis and tracking, a query interface may be provided, and users can query according to dimensions such as time, event type, and upload progress through the query interface.

[0089] In this embodiment, by setting a predetermined time interval, the processing progress of the target format report can be continuously monitored, and the processing progress can be timely tracked. If the processing progress changes, the system will automatically record the latest processing status in chronological order, thus forming a clear historical processing record arranged in time. This can not only provide real-time tracking of the processing progress, but also provide detailed data basis for subsequent analysis and decision-making. Through the combination of this dynamic monitoring and historical record, the transparency and efficiency of emergency event reporting can be significantly improved.

[0090] Furthermore, to achieve the above object, the present invention also provides an emergency event report generation device, which may include: A data preprocessing module, configured to obtain the original data corresponding to the target event and perform preprocessing to obtain first preprocessed data; An event recognition module, configured to input the first preprocessed data into a preset event recognition model to recognize the event type and event progress stage of the target event; A template selection module, configured to determine a corresponding target template from a preset report template library based on the event type and event progress stage; A data screening module, configured to calculate the contribution degree of different data in the first preprocessed data to the event level based on a preset data screening model, and determine key data; A report generation module, configured to convert the key data into descriptive text based on a natural language processing algorithm, fill the target template, and obtain an emergency event report.

[0091] It should be noted that the functions that can be realized by each module in the emergency event report generation device provided in this embodiment and the corresponding technical effects achieved can refer to the descriptions of the specific implementation manners in the embodiments of the emergency event report generation method of the present invention. For the sake of brevity of the specification, they will not be elaborated here.

[0092] In addition, an embodiment of the present invention also provides a computer-readable storage medium, on which an emergency event report generation program is stored. When the emergency event report generation program is executed by a processor, the steps of the emergency event report generation method as described above are implemented. Therefore, it will not be elaborated here. In addition, the description of the beneficial effects of using the same method will also not be elaborated. For the technical details not disclosed in the embodiment of the computer-readable storage medium involved in the present invention, please refer to the description of the method embodiment of the present invention. By way of example, the program instructions can be deployed to be executed on one computing device, or on multiple computing devices located at one location, or, on multiple computing devices distributed at multiple locations and interconnected by a communication network.

[0093] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0094] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for generating an emergency report, characterized in that, The method includes: S1. Obtain the original data corresponding to the target event and perform preprocessing to obtain the first preprocessed data; S2. Input the first preprocessed data into a preset event recognition model to identify the event type and event progress stage of the target event; S3. Based on the event type and the event progress stage, determine the corresponding target template from a preset report template library; S4. Based on a preset data screening model, calculate the contribution degrees of different data in the first preprocessed data to the event level, and determine the key data; S5. Based on a natural language processing algorithm, convert the key data into descriptive text, fill the target template, and obtain an emergency event report.

2. The emergency event report generation method according to claim 1, characterized in that, In the above S4, the construction steps of the preset data screening model specifically include: Obtain the first historical emergency event data and perform preprocessing to obtain a first training set; the first historical emergency event data at least includes the event level, event occurrence time, event affected range, event type, total number of people affected by the event, number of casualties, number of people in the first-level triage, number of people in the second-level triage, and resource consumption; Input the first training set into a decision tree model, and perform model training based on the dynamic weighted information gain formula to obtain the preset data screening model; the dynamic weighted information gain formula is: ； Among them, S is the first training set, is the first training set S 's dynamic information gain, is the feature i at t the association weight at the moment and the event level, is the subset divided according to the feature i ; is the size of the first training set S ; is the size of the subset ; is the entropy of the first training set S ; is the entropy of the subset ; The associated weight is calculated by the following formula: ； wherein, is t the duration of the event corresponding to the moment, is t the resource consumption corresponding to the moment, is the i adjustment coefficient of the feature on the duration of the event, i andis the adjustment coefficient of the feature on the resource consumption.

3. The emergency event report generation method according to claim 1, characterized in that In the above S2, the construction steps of the preset event recognition model specifically include: Obtain the second historical emergency event data and perform preprocessing to obtain multiple historical emergency event reports; Perform event type annotation and event progress stage annotation on each historical emergency event report to obtain a second training set; the event type annotation at least includes natural disasters, traffic accidents, and public health events, and the event progress stage annotation at least includes the initial stage of the event, the middle stage of the event, and the later stage of the event; Extract the relevant features of each historical emergency event report; the relevant features at least include the event occurrence time, event duration, event occurrence location, total number of people affected by the event, number of casualties, number of people in the first-level triage, number of people in the second-level triage, and resource consumption; Input the second training set into a deep learning model and perform training based on the relevant features to obtain the preset event recognition model.

4. The emergency report generation method according to claim 1, wherein The target template has a specific report framework, and the above S5 specifically includes: Based on the natural language processing algorithm, identify the mapping relationship between the key data and the fields in the predefined sentence template; Based on the mapping relationship, fill the key data into the corresponding fields of the predefined sentence template to obtain the descriptive text; Based on the report framework, insert the descriptive text into the target template to obtain the emergency event report.

5. The emergency report generation method according to claim 1, characterized in that, The above S1 specifically includes: Extract the original data corresponding to the target event to obtain plain text data; Perform standardization processing and data completion processing on the plain text data to obtain the first preprocessed data.

6. The emergency event report generation method according to claim 1, characterized in that After the above S5, the method further includes: a1. Based on the file format requirements of the receiving department corresponding to the emergency event report, perform format conversion on the emergency event report to obtain a target format report that meets the file format requirements; a2. Select the reporting channel corresponding to the receiving department in response to the user's one-key reporting instruction; a3. Upload the report in the target format to the receiving department based on the reporting channel.

7. The emergency event reporting generation method according to claim 6, wherein After a3, the method further includes: a4. Obtain and monitor the processing progress of the report in the target format based on a preset time interval; a5. If the processing progress changes, record the current processing progress in chronological order to form a historical processing record arranged in chronological order.

8. An emergency report generation device, characterized in that, The device includes: A data preprocessing module, configured to obtain the original data corresponding to the target event and perform preprocessing to obtain first preprocessed data; An event recognition module, configured to input the first preprocessed data into a preset event recognition model to identify the event type and event progress stage of the target event; A template selection module, configured to determine the corresponding target template from a preset report template library based on the event type and the event progress stage; A data screening module, configured to calculate the contribution degree of different data in the first preprocessed data to the event level based on a preset data screening model, and determine the key data; A report generation module, configured to convert the key data into descriptive text based on a natural language processing algorithm, fill the target template, and obtain an emergency event report.

9. An emergency report generation device, characterized in that, The device includes: a memory, a processor, and an emergency event report generation program stored on the memory and executable on the processor, and the emergency event report generation program is configured to implement the steps of the emergency event report generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, An emergency event report generation program is stored on the computer-readable storage medium, and when the emergency event report generation program is executed by a processor, it implements the steps of the emergency event report generation method according to any one of claims 1 to 7.

Images