Data processing methods and apparatus for generating emergency response plans

Abstract

This application discloses a data processing method and apparatus for generating emergency response plans. The method includes: acquiring emergency data to be processed, wherein the emergency data to be processed is relevant data representing an emergency event; performing emergency event classification processing on the emergency data to be processed to obtain emergency category data, wherein the emergency category data is data representing emergency event categories; matching emergency case data corresponding to the category feature data in a preset emergency database to obtain emergency case data; and performing emergency response plan generation processing on the emergency category data and the emergency case data to obtain target emergency response plan data. By performing emergency event classification and emergency response plan generation processing on the emergency events to be processed, the problem of low emergency event processing efficiency in the prior art is solved, and the technical effect of improving emergency event processing efficiency is achieved.

Description

Technical Field

[0001] This application relates to the field of computers, and more specifically, to a data processing method and apparatus for generating emergency response plans. Background Technology

[0002] Emergency management plays a crucial role in various scenarios. Emergency scenarios, such as fires, earthquakes, and floods, are typically characterized by their suddenness, unpredictability, urgency, and complexity. Therefore, handling emergency events requires accurate and efficient analysis and assessment of the events, as well as the development of effective emergency plans.

[0003] In existing technologies, emergency events are handled by searching for relevant data stored in static text, such as natural disaster emergency standards, emergency plans, and regulations. However, this method of searching and matching static text results in low efficiency and inaccurate matching.

[0004] Therefore, existing technologies for emergency response suffer from low efficiency. Summary of the Invention

[0005] The main objective of this application is to provide a data processing method and apparatus for generating emergency response plans, so as to solve the technical problem of low efficiency in emergency response processing in the prior art, and to achieve the technical effect of improving the efficiency of emergency response processing.

[0006] To achieve the above objectives, the first aspect of this application proposes a data processing method for generating emergency response plans, comprising:

[0007] Acquire emergency data to be processed, wherein the emergency data to be processed is relevant data used to represent emergency events;

[0008] The emergency data to be processed is classified into emergency events to obtain emergency category data, wherein the emergency category data is data used to represent the category of emergency events;

[0009] Emergency case data is obtained by matching the emergency case data corresponding to the category feature data in the preset emergency database;

[0010] The emergency category data and the emergency case data are processed to generate emergency plans, resulting in target emergency plan data.

[0011] In some embodiments of this application, the emergency data to be processed is subjected to emergency event classification processing to obtain emergency category data, including:

[0012] The emergency data to be processed is processed by extracting content based on a preset content extraction model to obtain emergency feature data to be processed, wherein the emergency feature data to be processed is data used to represent the content features of the emergency event;

[0013] The emergency feature data to be processed is subjected to category feature extraction processing using a preset emergency event classification model to obtain emergency category feature data, wherein the emergency category feature data is data used to represent the category features of emergency events;

[0014] The emergency category feature data is processed by emergency classification to obtain the emergency category data.

[0015] In some embodiments of this application, emergency response plan generation processing is performed on the emergency data to be processed and the emergency case data to obtain target emergency response plan data, including:

[0016] The emergency case data is processed based on emergency plan feature data to obtain emergency plan feature data, wherein the emergency plan feature data is data used to represent the characteristics of historical emergency plans;

[0017] Match the business system database corresponding to the emergency category data, and retrieve the real-time business data from the corresponding business system database to obtain the emergency real-time business data;

[0018] The emergency plan feature data and the emergency real-time business data are processed based on a preset plan generation model to obtain the target emergency plan data.

[0019] In some embodiments of this application, the method further includes, before acquiring the emergency data to be processed:

[0020] Acquire emergency sample data, wherein the emergency sample data is relevant data used to represent emergency samples;

[0021] The emergency sample data is preprocessed based on content extraction to obtain sample emergency feature data, wherein the sample emergency features are data used to represent the content features in the emergency samples;

[0022] The preset language model is trained based on the sample emergency feature data to obtain the preset model.

[0023] In some embodiments of this application, a preset language model is trained based on the sample emergency feature data to obtain the preset model, including:

[0024] The emergency feature data of the samples are identified and processed to obtain the first emergency feature data, the second emergency feature data, and the third emergency feature data of the samples.

[0025] The preset language model is trained based on the first emergency feature data of the sample to obtain a preset first language model, wherein the preset first language model is a preset content extraction model.

[0026] The preset language model is trained based on the sample's second emergency feature data to obtain a preset second language model, wherein the preset second language model is a preset emergency event classification model;

[0027] The preset language model is trained based on the sample's third emergency feature data to obtain a preset third language model, wherein the preset third language model is a preset scheme generation model;

[0028] The preset model is obtained based on the preset first language model, the preset second language model, and the preset third language model.

[0029] In some embodiments of this application, the method further includes, before acquiring the emergency data to be processed:

[0030] Obtain emergency sample data;

[0031] The emergency sample data is segmented based on a preset segmentation rule to obtain sample text block data;

[0032] The sample text block data is subjected to feature processing based on a semantic vector model to obtain featured text data, and the featured text data is stored in a preset emergency database.

[0033] According to a second aspect of this application, a data processing apparatus for generating emergency response plans is proposed, comprising:

[0034] The data acquisition module is used to acquire emergency data to be processed, wherein the emergency data to be processed is relevant data used to represent emergency events;

[0035] The event classification module is used to classify the emergency data to be processed into emergency event categories to obtain emergency category data, wherein the emergency category data is data used to represent the category of emergency event;

[0036] The matching module is used to match emergency case data corresponding to the category feature data in a preset emergency database to obtain emergency case data;

[0037] The solution generation module is used to process the emergency category data and the emergency case data to generate emergency solutions, thereby obtaining target emergency solution data.

[0038] In some embodiments of this application, the emergency data to be processed is subjected to emergency event classification processing to obtain emergency category data, including:

[0039] The content extraction module is used to extract the emergency data to be processed based on a preset content extraction model to obtain emergency feature data to be processed, wherein the emergency feature data to be processed is data used to represent the content features of the emergency event;

[0040] The category feature extraction module is used to perform category feature extraction processing on the emergency feature data to be processed using a preset emergency event classification model to obtain emergency category feature data, wherein the emergency category feature data is data used to represent the category features of emergency events;

[0041] An emergency classification module is used to perform emergency classification processing on the emergency category feature data to obtain the emergency category data.

[0042] According to a third aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing the computer to perform the above-described data processing method for generating emergency response plans.

[0043] According to a fourth aspect of this application, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the data processing method described above for generating emergency response plans.

[0044] The technical solutions provided by the embodiments of this application may include the following beneficial effects:

[0045] In this application, emergency data to be processed is acquired, wherein the emergency data to be processed is relevant data used to represent emergency events; the emergency data to be processed is classified into emergency event categories to obtain emergency category data, wherein the emergency category data is data used to represent emergency event categories; emergency case data corresponding to the category feature data is matched in a preset emergency database to obtain emergency case data; and emergency plan generation processing is performed on the emergency category data and the emergency case data to obtain target emergency plan data. By performing emergency event classification and emergency plan generation on the emergency events to be processed, the problem of low emergency event processing efficiency in the prior art is solved, and the technical effect of improving the efficiency of emergency event processing is achieved. Attached Figure Description

[0046] The accompanying drawings, which form part of this application, are used to provide a further understanding of the application and to make other features, objects, and advantages of the application more apparent. The illustrative embodiments and descriptions of this application are used to explain the application and do not constitute an undue limitation of the application. In the drawings:

[0047] Figure 1 A flowchart of a data processing method for generating emergency response plans is provided in this application;

[0048] Figure 2 A flowchart of a data processing method for generating emergency response plans is provided in this application;

[0049] Figure 3 A flowchart of a data processing method for generating emergency response plans is provided in this application;

[0050] Figure 4 A schematic diagram of a data processing device for generating emergency response plans provided in this application;

[0051] Figure 5 A schematic diagram of another data processing device for generating emergency response plans provided in this application. Detailed Implementation

[0052] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0053] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0054] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing this application and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.

[0055] Furthermore, in addition to indicating location or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this application based on the specific circumstances.

[0056] Furthermore, the terms "installation," "setup," "equipped with," "connection," "linked," and "socketing" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or an internal connection between two devices, components, or parts. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0057] In existing technologies, emergency response mainly involves searching for relevant data on emergency events stored in static text, such as natural disaster emergency standards, emergency plans, and regulations. This method of searching and matching static text to handle emergency events is inefficient and prone to inaccurate matching.

[0058] With the continuous development of information technology and artificial intelligence, AI is widely used in various fields. Applying AI to emergency management, the data processing and analysis capabilities of AI models play a crucial role in improving emergency management capabilities. The applicant has found that using large AI models for emergency management can improve efficiency; however, training such models requires a large amount of sample data, and models trained with limited sample data have low accuracy in emergency management. Therefore, this application is filed.

[0059] In some optional embodiments of this application, a data processing method for generating emergency response plans is provided. Figure 1 A flowchart of a data processing method for generating emergency response plans provided in this application is shown below. Figure 1 As shown, the method includes the following steps:

[0060] S101: Acquire emergency data to be processed;

[0061] Emergency data to be processed refers to data related to emergency events, such as data related to disasters like fires and floods.

[0062] S102: Perform emergency event classification processing on the emergency data to be processed to obtain emergency category data;

[0063] Emergency category data refers to data used to represent the categories of emergency events. By processing the emergency data to be processed, including content extraction and emergency event classification, the category data of emergency events is obtained. Emergency event classification processing includes extracting emergency event information from the emergency data to be processed based on a first preset model, and then classifying the extracted emergency event feature data based on a second preset model to achieve the classification of emergency events. Emergency event classification processing includes classification based on event type, severity, and event stage.

[0064] In some optional embodiments of this application, a data processing method for generating emergency response plans is provided, which performs emergency event classification processing on the emergency data to be processed. Figure 2 A flowchart of a data processing method for generating emergency response plans provided in this application is shown below. Figure 2 As shown, the method includes the following steps:

[0065] S201: Extract the emergency data to be processed based on the preset content extraction model to obtain the emergency feature data to be processed;

[0066] The emergency feature data to be processed is data used to represent the content characteristics of emergency events. The emergency data to be processed is processed by a disaster feature-based model extraction process to obtain the emergency feature data to be processed. Among them, the disaster features include time, location, disaster description, scope of impact, current situation and other features. The emergency feature data to be processed is data used to represent the disaster features of the above-mentioned emergency events to be processed.

[0067] In an optional embodiment of this application, the preset content extraction model is a pre-trained text recognition model. Based on the preset content extraction model, the data of the disaster features mentioned above are extracted from the text in the emergency data to be processed, and the emergency feature data to be processed is obtained so as to carry out subsequent processing of the emergency feature data to be processed.

[0068] S202: Extract category features from the emergency feature data to be processed using a pre-defined emergency event classification model to obtain emergency category feature data;

[0069] Emergency category feature data is data used to represent the category features of emergency events. The emergency feature data to be processed is processed by identifying disaster type features to obtain emergency category feature data. Among them, disaster type features include disaster type, disaster severity, disaster handling stage, etc. The emergency category feature data is data used to represent the above disaster type features.

[0070] S203: Perform emergency category feature data processing to obtain emergency category data.

[0071] In an optional embodiment of this application, the preset emergency event classification model is a pre-trained model. Based on the preset emergency event classification model, the emergency feature data to be processed is classified to obtain emergency category data, so as to match emergency case data according to the emergency category data, so as to generate an emergency rescue plan according to the emergency case data.

[0072] S103: Match emergency case data with category feature data in the preset emergency database to obtain emergency case data;

[0073] Based on the emergency event classification results, the system retrieves and matches corresponding emergency case data from the emergency data, which includes historical cases or contingency plan data. Emergency rescue plans are then generated based on the retrieved emergency case data and the emergency data to be processed.

[0074] S104: Process emergency response plans by analyzing emergency category data and emergency case data to obtain target emergency response plan data.

[0075] In some optional embodiments of this application, a data processing method for emergency response plan generation is provided, which performs emergency response plan generation processing on the emergency data to be processed and the emergency case data. The method includes:

[0076] Emergency case data is processed based on emergency plan feature data to obtain emergency plan feature data, which is used to represent the characteristics of historical emergency plans. The emergency case data is then processed for content extraction based on a preset content extraction model to obtain emergency plan feature data.

[0077] The system matches the business system database corresponding to the emergency category data, retrieves real-time business data from the corresponding business system database, and obtains real-time emergency business data. It matches the corresponding business system based on the emergency category data. This business system stores real-time business data, including time-sensitive data such as available resources, available materials, and routes around the disaster site. For example, if the emergency is a fire, it matches the business system required for fire rescue, i.e., the fire business system, which stores real-time business data such as available fire rescue equipment, available fire rescue forces, and routes. The system then retrieves the real-time business data from the corresponding business system. In this embodiment, Llama 3.1-8B can be used to retrieve real-time emergency business information based on the input emergency category data.

[0078] Emergency plan feature data and real-time emergency business data are processed based on a preset plan generation model to obtain target emergency plan data. The emergency plan feature data and real-time emergency business data are then merged and processed into prompt data. The preset plan generation model generates the target emergency plan based on this prompt data.

[0079] In some optional embodiments of this application, a data processing method for generating emergency response plans is provided. Figure 3 A flowchart of a data processing method for generating emergency response plans provided in this application is shown below. Figure 3 As shown, the method includes the following steps:

[0080] S301: Obtain emergency sample data;

[0081] Emergency sample data refers to relevant data used to represent emergency samples, which includes historically reported disaster data and corresponding rescue plan data.

[0082] S302: Perform content-based preprocessing on the emergency sample data to obtain sample emergency feature data;

[0083] The emergency features of the sample are data used to represent the content features in the emergency sample. The above-mentioned reported disaster data and corresponding rescue plan data are extracted according to disaster content, disaster classification and rescue plan, respectively, to obtain three types of data sets: disaster content extraction, disaster classification and rescue plan. The above three types of data sets are processed in a preset dataset format to obtain the emergency feature data of the sample.

[0084] S303: Train the preset language model based on the sample emergency feature data to obtain the preset model.

[0085] In some optional embodiments of this application, a data processing method for generating emergency response plans is provided, which trains a preset language model based on sample emergency feature data. The method includes:

[0086] The emergency feature data of the samples are identified and processed to obtain the first emergency feature data, the second emergency feature data, and the third emergency feature data. The first emergency feature data is the dataset extracted from the disaster content mentioned above, the second emergency feature data is the dataset of the disaster classification mentioned above, and the third emergency feature data is the dataset of the rescue plan mentioned above. Based on these three datasets, the language model is trained to obtain the corresponding three models.

[0087] The preset language model is trained based on the first emergency feature data of the sample to obtain a preset first language model, wherein the preset first language model is a preset content extraction model; the preset language model is trained based on the first emergency feature data of the sample to obtain a preset second language model, wherein the preset second language model is a preset emergency event classification model; the preset language model is trained based on the first emergency feature data of the sample to obtain a preset third language model, wherein the preset third language model is a preset scheme generation model;

[0088] In this embodiment, the preset language model is a lightweight generative AI model, such as the Qwen2-7B model, or models like Llama3.1-8B, GLM4-9B, etc. By employing a lightweight generative AI model, lower hardware costs for model operation can be achieved, reducing computational power and memory requirements, facilitating local and device deployment, and improving security. Furthermore, when the model is used, only a small amount of data samples are needed for training or fine-tuning for specific domains or tasks, improving efficiency.

[0089] For example, the preset language model is Qwen2-7B. Based on the three datasets mentioned above, Qwen2-7B is fine-tuned and trained to obtain three specialized small models for content extraction, disaster classification, and emergency rescue plan generation, resulting in the preset first language model, preset second language model, and preset third language model.

[0090] The preset model is obtained based on the preset first language model, the preset second language model, and the preset third language model.

[0091] In some optional embodiments of this application, a data processing method for generating emergency response plans is provided, the method comprising:

[0092] Acquire emergency sample data; perform data segmentation processing on the emergency sample data based on preset segmentation rules to obtain sample text block data; perform feature processing on the sample text block data based on semantic vector model to obtain featured text data and store the featured text data in a preset emergency database.

[0093] The emergency sample data is divided into uniform small blocks to obtain sample text block data. Each text block contains a segment of original text information. The preset segmentation rules can be based on paragraphs, sentences, or other custom rules. A text vector is generated for each text block based on a semantic vector model. Based on the text vector corresponding to each text block, the text content in the emergency sample data is characterized so that it can be retrieved and identified in the formed emergency database.

[0094] In some optional embodiments of this application, a data processing apparatus for generating emergency response plans is provided. Figure 4 A schematic diagram of a data processing apparatus for generating emergency response plans provided in this application, the apparatus comprising:

[0095] The data acquisition module 41 is used to acquire emergency data to be processed, wherein the emergency data to be processed is relevant data used to represent emergency events;

[0096] The event classification module 42 is used to classify the emergency data to be processed into emergency event categories to obtain emergency category data, wherein the emergency category data is data used to represent the category of emergency event;

[0097] Matching module 43 is used to match emergency case data corresponding to category feature data in a preset emergency database to obtain emergency case data;

[0098] The solution generation module 44 is used to process emergency category data and emergency case data to generate emergency solutions and obtain target emergency solution data.

[0099] In some optional embodiments of this application, a data processing apparatus for generating emergency response plans is provided. Figure 5 A schematic diagram of another data processing apparatus for generating emergency response plans provided in this application, the apparatus comprising:

[0100] The content extraction module 51 is used to extract the emergency data to be processed based on a preset content extraction model to obtain emergency feature data to be processed, wherein the emergency feature data to be processed is data used to represent the content features of the emergency event.

[0101] The category feature extraction module 52 is used to perform category feature extraction processing on the emergency feature data to be processed using a preset emergency event classification model to obtain emergency category feature data, wherein the emergency category feature data is data used to represent the category features of emergency events;

[0102] The emergency classification module 53 is used to perform emergency classification processing on the emergency category feature data to obtain the emergency category data.

[0103] The specific methods of execution of each unit in the above embodiments have been described in detail in the embodiments of the method, and will not be elaborated here.

[0104] In summary, this application involves acquiring emergency data to be processed, wherein the emergency data to be processed is relevant data representing emergency events; classifying the emergency data to be processed into emergency event categories, wherein the emergency category data is data representing emergency event categories; matching emergency case data corresponding to the category feature data in a preset emergency database to obtain emergency case data; and performing emergency plan generation processing on the emergency category data and the emergency case data to obtain target emergency plan data. By performing emergency event classification and emergency plan generation on the emergency events to be processed, the problem of low emergency event processing efficiency in the prior art is solved, and the technical effect of improving emergency event processing efficiency is achieved.

[0105] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0106] Obviously, those skilled in the art should understand that the various units or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps into a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0107] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A data processing method for generating emergency response plans, characterized in that, include: Acquire emergency data to be processed, wherein the emergency data to be processed is relevant data used to represent emergency events; The emergency data to be processed is classified into emergency events to obtain emergency category data, wherein the emergency category data is data used to represent the category of emergency events; The emergency data to be processed is subjected to extraction processing based on a preset content extraction model to obtain emergency feature data to be processed, wherein the emergency feature data to be processed is data used to represent the content features of the emergency event; the emergency feature data to be processed is subjected to category feature extraction processing based on a preset emergency event classification model to obtain emergency category feature data, wherein the emergency category feature data is data used to represent the category features of the emergency event; the emergency category feature data is subjected to emergency classification processing to obtain the emergency category data; the preset content extraction model and the preset emergency event classification model are obtained by training a preset language model based on the first sample emergency feature data and the second sample emergency feature data, respectively, and the preset language model is a lightweight generative AI model; The preset language model is trained based on the first emergency feature data of the sample to obtain the preset content extraction model; the preset language model is trained based on the second emergency feature data of the sample to obtain the preset emergency event classification model; and the preset language model is trained based on the third emergency feature data of the sample to obtain the preset solution generation model. Emergency case data is obtained by matching the emergency case data corresponding to the category feature data in the preset emergency database; Emergency response plan generation processing is performed on the emergency category data and the emergency case data to obtain target emergency response plan data; Based on a preset content extraction model, the emergency case data is processed to extract emergency plan feature data. The data is then matched with the business system database corresponding to the emergency category data. Real-time business data is retrieved from the corresponding business system database to obtain real-time emergency business data. The corresponding business system is matched based on the emergency category data, and the real-time business data is stored in the business system. The emergency plan feature data and the real-time emergency business data are merged and processed into prompt word data. A preset plan generation model then generates a target emergency plan based on this prompt word data.

2. The data processing method according to claim 1, characterized in that, Emergency response plan generation processing is performed on the emergency category data and the emergency case data to obtain target emergency response plan data, including: The emergency case data is processed based on emergency plan feature data to obtain emergency plan feature data, wherein the emergency plan feature data is data used to represent the characteristics of historical emergency plans; Match the business system database corresponding to the emergency category data, and retrieve the real-time business data from the corresponding business system database to obtain the emergency real-time business data; The emergency plan feature data and the emergency real-time business data are processed based on a preset plan generation model to obtain the target emergency plan data.

3. The data processing method according to claim 1, characterized in that, Before acquiring the emergency data to be processed, the method further includes: Acquire emergency sample data, wherein the emergency sample data is relevant data used to represent emergency samples; The emergency sample data is preprocessed based on content extraction to obtain sample emergency feature data, wherein the sample emergency features are data used to represent the content features in the emergency samples; The preset language model is trained based on the sample emergency feature data to obtain the preset model.

4. The data processing method according to claim 3, characterized in that, The preset language model is trained based on the sample emergency feature data to obtain the preset model, which includes: The emergency feature data of the samples are identified and processed to obtain the first emergency feature data, the second emergency feature data, and the third emergency feature data of the samples. The preset language model is trained based on the first emergency feature data of the sample to obtain a preset first language model, wherein the preset first language model is a preset content extraction model. The preset language model is trained based on the sample's second emergency feature data to obtain a preset second language model, wherein the preset second language model is a preset emergency event classification model; The preset language model is trained based on the sample's third emergency feature data to obtain a preset third language model, wherein the preset third language model is a preset scheme generation model; The preset model is obtained based on the preset first language model, the preset second language model, and the preset third language model.

5. The data processing method according to claim 1, characterized in that, Before acquiring the emergency data to be processed, the method further includes: Obtain emergency sample data; The emergency sample data is segmented based on a preset segmentation rule to obtain sample text block data; The sample text block data is subjected to feature processing based on a semantic vector model to obtain featured text data, and the featured text data is stored in a preset emergency database.

6. A data processing device for generating emergency response plans, characterized in that, include: The data acquisition module is used to acquire emergency data to be processed, wherein the emergency data to be processed is relevant data used to represent emergency events; The event classification module is used to classify the emergency data to be processed into emergency event categories to obtain emergency category data, wherein the emergency category data is data used to represent the category of emergency event; The content extraction module is used to extract the emergency data to be processed based on a preset content extraction model to obtain emergency feature data to be processed, wherein the emergency feature data to be processed is data used to represent the content features of the emergency event; the category feature extraction module is used to extract the category features of the emergency feature data to be processed based on a preset emergency event classification model to obtain emergency category feature data, wherein the emergency category feature data is data used to represent the category features of the emergency event; the emergency classification module is used to perform emergency classification processing on the emergency category feature data to obtain the emergency category data; the preset content extraction model and the preset emergency event classification model are obtained by training a preset language model based on the first sample emergency feature data and the second sample emergency feature data, respectively, and the preset language model is a lightweight generative AI model; The preset language model is trained based on the first emergency feature data of the sample to obtain the preset content extraction model; the preset language model is trained based on the second emergency feature data of the sample to obtain the preset emergency event classification model; and the preset language model is trained based on the third emergency feature data of the sample to obtain the preset solution generation model. The matching module is used to match emergency case data corresponding to the category feature data in a preset emergency database to obtain emergency case data; The solution generation module is used to process the emergency category data and the emergency case data to generate emergency solutions, thereby obtaining target emergency solution data. Based on a preset content extraction model, the emergency case data is processed to extract emergency plan feature data. The data is then matched with the business system database corresponding to the emergency category data. Real-time business data is retrieved from the corresponding business system database to obtain real-time emergency business data. The corresponding business system is matched based on the emergency category data, and the real-time business data is stored in the business system. The emergency plan feature data and the real-time emergency business data are merged and processed into prompt word data. A preset plan generation model then generates a target emergency plan based on this prompt word data.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the data processing method for generating emergency response plans as described in any one of claims 1-5.

8. An electronic device, characterized in that, include: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the data processing method for generating emergency response plans as described in any one of claims 1-5.

Images