A method and system for configuring rescue equipment of an emergency rescue vehicle

Abstract

A method and system for configuring rescue equipment of an emergency rescue vehicle, which relates to the field of disaster emergency rescue. The method is applied to an emergency rescue platform, and the method includes: obtaining basic information of an emergency event; extracting and standardizing keywords from the basic information of the emergency event to obtain multiple event attributes of the emergency event; inputting the multiple event attributes into a preset emergency event knowledge graph to obtain multiple associated attributes; generating a rescue equipment list for the multiple associated attributes and the multiple event attributes; and integrating the multiple rescue equipment lists to obtain a rescue equipment configuration plan for the emergency event. Implementing the technical solution provided by this application solves the problem that the existing rescue equipment list cannot provide a reasonable rescue equipment configuration plan for new combined events.

Description

Technical Field

[0001] This application relates to the technical field of disaster emergency rescue, and specifically relates to a method and system for configuring rescue equipment of an emergency rescue vehicle. Background Art

[0002] With the development of information technology, when an emergency occurs, the basic situation of the emergency can be quickly understood with the help of communication tools, so that corresponding emergency measures can be taken in a timely manner to ensure the safety of residents' lives and property.

[0003] However, in real life, emergencies often occur suddenly and unpredictably, which makes the rescue team need to set out within a very short time after receiving the task, resulting in insufficient time for event assessment and analysis, and further leading to incomplete configuration of rescue equipment and omission of some key equipment. At present, in order to respond to these sudden events in a timely manner, a standardized rescue equipment list has been established in advance. When an emergency occurs, the corresponding rescue equipment is queried from the rescue equipment list according to information such as the type, time, location, and scale of the emergency to complete the rapid configuration of rescue equipment. However, the above-mentioned rescue equipment list is established based on currently known emergencies, and there may be no corresponding equipment configuration plan for some new types of emergencies or combined events, resulting in unreasonable configuration of rescue equipment. Summary of the Invention

[0004] Aiming at the problem that the existing rescue equipment list cannot provide a reasonable rescue equipment configuration plan for new combined events, this application provides a method and system for configuring rescue equipment of an emergency rescue vehicle.

[0005] In the first aspect, this application provides a method for configuring rescue equipment of an emergency rescue vehicle, which is applied to an emergency rescue platform, and the method includes:

[0006] Obtain the basic information of the emergency;

[0007] Extract keywords from the basic information of the emergency and perform standardization processing to obtain multiple event attributes of the emergency;

[0008] Input multiple event attributes into a preset emergency event knowledge graph to obtain multiple associated attributes;

[0009] Generate a rescue equipment list for multiple associated attributes and multiple event attributes;

[0010] Integrate multiple rescue equipment lists to obtain a rescue equipment configuration plan for the emergency.

[0011] Optionally, parse the basic information of the emergency event to obtain multiple sub-information of the emergency event and the information sources corresponding to each of the multiple sub-information;

[0012] Classify the multiple sub-information according to the information sources corresponding to each of the multiple sub-information to obtain multiple classification clusters;

[0013] Extract keywords of the multiple classification clusters by using the keyword extraction algorithms corresponding to each of the multiple classification clusters.

[0014] Optionally, the step of extracting keywords of the multiple classification clusters by using the keyword extraction algorithms corresponding to each of the multiple classification clusters specifically further includes:

[0015] Obtain multiple non-keywords of a first classification cluster, where the first classification cluster is any one of the multiple classification clusters;

[0016] Screen the multiple non-keywords to obtain multiple non-keywords to be verified;

[0017] Perform part-of-speech tagging on the multiple non-keywords to be verified;

[0018] Based on the parts of speech of the multiple non-keywords to be verified, allocate the multiple non-keywords to be verified to a second classification cluster for keyword verification, so as to extract the missing keywords among the multiple non-keywords to be verified, where the second classification cluster is any classification cluster other than the first classification cluster among the multiple classification clusters.

[0019] Optionally, obtain a first association attribute among the multiple event attributes;

[0020] Input the multiple first association attributes into the emergency knowledge graph to generate multiple second association attributes;

[0021] Calculate the convergence value of the multiple second association attributes in the emergency event knowledge graph;

[0022] If the convergence value reaches the threshold, determine that the multiple first association attributes and the multiple second association attributes are the association attributes of the multiple event attributes.

[0023] Optionally, the step of if the convergence value reaches the threshold, determine that the multiple first association attributes and the multiple second association attributes are the association attributes of the multiple event attributes specifically further includes:

[0024] Match the multiple event attributes of the emergency event with a historical emergency event library to obtain multiple similar historical emergency events;

[0025] Calculate the similarity values between the emergency event and the multiple similar historical emergency events;

[0026] If the similarity value between the emergency event and the first similar historical emergency event is greater than or equal to a preset value, then use the convergence value threshold of the first similar historical emergency event as the threshold of the emergency event, where the first similar historical emergency event is any one of the multiple similar historical emergency events.

[0027] Optionally, after calculating the similarity values between the emergency event and the multiple similar historical emergency events, the method further includes:

[0028] If the similarity values between the multiple similar historical emergency events and the emergency event are all less than the preset value, then read the complexity and the number of iterations of the emergency event;

[0029] Based on the complexity and the number of iterations of the emergency event, adjust the convergence value threshold of the emergency event.

[0030] Optionally, perform a functional evaluation on the multiple rescue equipment lists to obtain the functional fitness of the multiple rescue equipment lists;

[0031] Based on the functional fitness of the multiple rescue equipment lists, generate a rescue equipment configuration plan for the emergency event.

[0032] In a second aspect, the present application provides a rescue equipment configuration system for an emergency rescue vehicle, where the system is an emergency rescue platform, and the emergency rescue platform includes an acquisition module and a processing module, where:

[0033] The acquisition module is configured to acquire the basic information of an emergency event;

[0034] The processing module is configured to perform keyword extraction and standardization processing on the basic information of the emergency event to obtain multiple event attributes of the emergency event;

[0035] Input the multiple event attributes into a preset emergency event knowledge graph to obtain multiple associated attributes;

[0036] Generate rescue equipment lists for the multiple associated attributes and the multiple event attributes; integrate the multiple rescue equipment lists to obtain a rescue equipment configuration plan for the emergency event.

[0037] In a third aspect, the present application provides an electronic device, including a processor, a memory, a user interface, and a network interface, where the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is configured to execute the instructions stored in the memory so that the electronic device executes the method according to any one of the first aspect.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method as described in any one of the first aspects is executed.

[0039] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0040] 1. For the new emergency events and combined events that are currently occurring, this application splits the basic information of these emergency events into multiple event attributes, and then inputs the multiple event attributes into a pre-established emergency event knowledge graph to query multiple historical event attributes that are similar or identical to the current multiple event attributes. At this time, the multiple historical event attributes are not from the same historical emergency event. Then, based on the associated attributes of the historical event attributes, the associated attributes corresponding to the multiple event attributes of the current emergency event are determined, so as to mine the risk information that may be ignored by the current emergency event, and finally generate the rescue equipment configuration plan for the current emergency event based on the information provided by the associated attributes and event attributes. Compared with the traditional rescue equipment list, this plan can better adapt to complex and changeable emergency events and make the configuration plan of the rescue equipment more reasonable.

[0041] 2. In the process of splitting the basic information of emergency events, since the composition of the basic information comes from different information channels, if a unified information processing method is used, the basic information splitting will be inaccurate. Therefore, this application performs cluster analysis on the basic information, divides the basic information into multiple classification clusters, and adopts targeted information processing algorithms in each classification cluster to improve the accuracy of basic information splitting. In the process of processing information, the classification cluster will cause some key information to be divided into non-key information due to different description methods; therefore, when performing cluster analysis, this application also divides the non-key information output by each classification cluster into other classification clusters for processing, so that other classification clusters re-verify whether the non-key information is key information, thereby ensuring the integrity of the basic information splitting.

[0042] 3. When querying the associated attributes of emergency events in the emergency knowledge graph, it is difficult to ensure the comprehensiveness of the associated attributes by relying on only one query; therefore, this application performs deep mining through iterative query to dig out some risk information hidden in emergency events. In addition, in order to prevent unlimited iteration, this application dynamically sets the convergence value threshold of each iteration according to the complexity of the emergency event and the number of iterations, so as to adapt to the mining depth and breadth of different emergency events. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of a method for configuring rescue equipment of an emergency rescue vehicle provided in an embodiment of the present application.

[0044] Figure 2 It is a schematic structural diagram of a rescue equipment configuration system for an emergency rescue vehicle provided by an embodiment of the present application.

[0045] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0046] Explanation of reference numerals: 1. Acquisition module; 2. Processing module; 300. Electronic device; 301. Processor; 302. Communication bus; 303. User interface; 304. Network interface; 505. Memory. Detailed implementation manners

[0047] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0048] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0049] In the description of the embodiments of the present application, the meaning of the term "a plurality of" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0050] Emergency events occur frequently in our country, including natural disasters (such as earthquakes, forest fires, debris flows, etc.) and man-made disasters (such as factory fires, car accidents, building collapses, etc.). Thanks to the current advanced information technology, even if thousands of miles away from the scene of an emergency event, relevant information about the emergency event can be understood in the first time. However, the occurrence of emergency events often has suddenness and unpredictability. For example, in the case of a sudden factory fire, as the rescue time lengthens, an explosion may occur, further increasing the harmfulness of the emergency event. Therefore, this also makes the rescue team need to set out within a very short time after receiving the task, but this will result in insufficient time for event assessment and analysis, and then lead to incomplete configuration of rescue equipment, missing some key equipment, and increasing the rescue difficulty.

[0051] Currently, in order to quickly respond to these emergency events, an event file will be established in advance based on the emergency events handled in the past. Then, according to the basic information described in the event file, how to configure rescue equipment when the same type of emergency event occurs in the future will be studied and discussed. Finally, the discussion results will be formulated into a rescue equipment list. Once a rescue task is received, according to the known situation of this rescue task, a rescue equipment configuration plan suitable for this rescue operation will be queried from the rescue equipment list to quickly complete the configuration work of rescue equipment, so as to promptly go to the area where the emergency event occurred to carry out the rescue.

[0052] However, the above rescue equipment list is established based on the currently known emergency events. For some new types of emergency events or combined events, there may be no corresponding equipment configuration plan in the rescue equipment list, resulting in unreasonable configuration of rescue equipment.

[0053] To solve the above problems, the present application provides a method for configuring rescue equipment for an emergency rescue vehicle. This method is applied to an emergency rescue platform, as Figure 1 shown. This method includes steps S101 to S105, and the above steps are as follows:

[0054] S101. Obtain the basic information of the emergency event.

[0055] In the above step, if an emergency event occurs in a certain place, the emergency rescue platform will collect relevant information about the emergency event through various information channels, and then perform preprocessing operations such as format conversion, duplicate removal, screening, and verification on the collected relevant information to generate the basic information of the emergency event. Among them, various information channels include descriptions by on-site witnesses, news reports, social media, and official announcements, etc. The relevant information of the emergency event includes voices, texts, images, and videos describing the emergency event.

[0056] S102. Extract keywords from the basic information of the emergency event and perform standardization processing to obtain multiple event attributes of the emergency event.

[0057] In the above steps, the basic information of the emergency event includes various types of event information, and there are differences in the accuracy of different types of event information. It can be understood that the video has the highest accuracy, followed by images, text, and voice in sequence. The lower the accuracy, the more interference there is, and the higher the accuracy, the less interference there is. Based on this, the present application performs cluster analysis on different types of information, and adopts corresponding keyword extraction algorithms for each cluster, so as to extract effective and accurate data from the basic information of the emergency event. Specifically: First, the basic information of the emergency event is parsed to obtain multiple sub-information of the emergency event and the information sources of the multiple sub-information; then, according to the information sources of the multiple sub-information, the multiple sub-information is classified to obtain multiple classification clusters. In the present application, the multiple classification clusters include a voice classification cluster, a text classification cluster, an image classification cluster, and a video classification cluster. Among them, there can be multiple sub-information in the same classification cluster. For example, the sub-information in the voice classification cluster can come from the descriptions of different on-site witnesses or from the reports of journalists; then, the keyword extraction algorithms corresponding to each classification cluster are used to extract the keywords of the multiple classification clusters.

[0058] Among them, for the voice classification cluster, speech recognition technology combined with sentiment analysis can be used to extract keywords. The speech recognition technology converts speech into text, and then performs sentiment analysis on the speech corresponding to the text. For example, when performing sentiment analysis, the content that the describer wants to emphasize can be determined according to the tone, coherence, and speech speed, so as to clarify the key information in the voice information.

[0059] For the text classification cluster, the term frequency - inverse document frequency (TF - IDF) technique combined with a text sorting algorithm can be used to extract keywords. The TF - IDF technique extracts fuzzy keywords from the document, and then the text sorting algorithm is used to verify the fuzzy keywords to obtain accurate keywords. Specifically, the text is tokenized to obtain multiple words, and then the term frequency and inverse document frequency of these multiple words are calculated. The term frequency reflects the frequency of a word in the current document, and the inverse document frequency reflects the rarity of a word in a collection of multiple documents. It can be understood that if a word appears frequently in a document, it indicates that the word is more important in the document. If a word does not appear frequently in a collection of multiple documents, it means that the word has strong discriminatory power and is important for determining the theme of the document. However, considering only the term frequency or inverse document frequency has certain limitations. By calculating the product of the term frequency and inverse document frequency, the importance value of each word is obtained. The higher the importance value, the more critical the word. Thus, multiple fuzzy keywords of the text classification cluster can be determined. At this time, the fuzzy keywords obtained by the TF - IDF technique ignore the semantic relationships between words and the structural information of the text. Therefore, the fuzzy keywords need to be further verified to be determined as accurate keywords. The text sorting algorithm constructs a relationship graph between words, considering the context relationship and co - occurrence situation of words in the text, and can capture the semantic connections between words. Specifically, first, a range window is used to construct a word relationship graph, and the fuzzy keywords are the nodes in the word relationship graph. For example, if two fuzzy keywords appear in a certain 5 - byte range window of the document at the same time, it means that there is an association relationship between these two fuzzy keywords, and an association edge is constructed between these two fuzzy keywords in the word relationship graph. Then, an iterative algorithm is used to calculate and update the weight value of each node in the word relationship graph. When the weight value of each node converges, the nodes with higher weight values are selected as accurate keywords.

[0060] For the image classification cluster, object detection technology combined with image annotation technology can be used to extract keywords. Object detection technology identifies entities related to emergency events such as people, vehicles, fires, floods, etc. in the image, and then image annotation technology adds labels to the objects, scenes, etc. in the image. Finally, text processing is performed on these labels to extract keywords.

[0061] For the video classification cluster, since the video contains speech, text, and images, when extracting keywords for the video classification cluster, the algorithms in the speech classification cluster, text classification cluster, and image classification cluster can be integrated to extract keywords. The specific processing methods have been described in the above document and will not be elaborated here.

[0062] In a possible implementation, specific information types are clustered in each classification cluster, and there are differences in the information expression methods of different information types, resulting in different presentation methods for the same concept. For example, the image and video classification clusters can more intuitively display certain scenes or objects, and the text classification cluster can provide more detailed background information and descriptions. However, this differential expression method is likely to cause keywords in a certain classification cluster to be classified as non-keywords, thus missing some keywords. For example, an object that appears in an image or video is regarded as a non-keyword because it lacks detailed context description. To solve this problem, this application further verifies the non-keywords of each classification cluster to improve the integrity of keyword extraction. Specifically: First, duplicate words are removed and stop words are screened out from the non-keywords of multiple classification clusters to obtain multiple non-keywords to be verified. Among them, stop words include words such as "le", "de", "zai", etc.; then, part-of-speech tagging is performed on multiple non-keywords to be verified, that is, the part-of-speech of the non-keywords to be verified is tagged as one of the parts of speech such as adjectives, nouns, verbs, etc.; then, according to the part-of-speech of the non-keywords to be verified, the part-of-speech of the non-keywords to be verified is input into multiple classification clusters in turn for keyword verification. It can be understood that the non-keywords to be verified will not be input into the original classification cluster again; if the non-keyword to be verified is defined as a keyword in a certain classification cluster, the non-keyword to be verified is output as a keyword. In the process of inputting the part-of-speech of the non-keywords to be verified into multiple classification clusters for verification in turn, in order to improve the verification efficiency and reduce unnecessary processing steps, according to the hit accuracy rates of multiple classification clusters for keywords of different parts of speech, the input verification order of the non-keywords to be verified is determined. For example, if the video classification cluster has a higher hit accuracy rate for adjectives, the non-keyword to be verified with the part-of-speech of an adjective is preferentially input into the video classification cluster for verification, thereby improving the verification efficiency.

[0063] Finally, after completing the keyword extraction of the emergency event, the keywords need to be standardized to obtain the event attributes of the emergency event; here, the standardization process is to convert heterogeneous data into homogeneous data and convert the expression method into a standard format to ensure more accurate and efficient subsequent processing.

[0064] S103. Input multiple event attributes into a preset emergency event knowledge graph to obtain multiple associated attributes.

[0065] In the above steps, the pre-constructed emergency event knowledge graph contains the correlation relationships between the event attributes of various types of emergency events. Therefore, when the occurred emergency event is a new type of emergency event or a combined event composed of multiple emergency events, by inputting the event attributes of the emergency event into the preset emergency event knowledge graph and then according to the correlation graph between the event attributes, the explicit attributes and implicit attributes related to the current emergency event can be quickly found, thereby providing a comprehensive information basis for the rescue equipment configuration. Among them, the explicit attribute can be understood as the event attribute directly related to the current emergency event, and the implicit attribute can be understood as the event attribute indirectly related to the current emergency event. For example, for a fire event, the explicit attributes include the fire location, the fire material, and the fire size, etc., and the implicit attributes include the surrounding important buildings, the weather conditions, and the structure of the building on fire, etc. In the above query process, for a new type of emergency event, by splitting the new type of emergency event into multiple event features (event attributes), then matching the similar features of the multiple event features one by one from the emergency event knowledge graph, and then mining more correlation information and hidden information according to the similar features of the multiple event features, thereby providing a true and effective information basis for the rescue equipment configuration of the new type of emergency event; for a combined event, the same processing method as that for the new type of emergency event is adopted to orderly mine the potential threats and obvious threats of the combined event, thereby reducing the occurrence of unreasonable resource utilization of the rescue equipment.

[0066] In a possible implementation manner, in the process of mining the associated attributes of the emergency event, it is difficult to directly obtain relatively comprehensive information only by inputting the event attributes into the emergency event knowledge graph once. Therefore, iterative processing is also required to deeply mine the associated information of the emergency event. Specifically: obtain the first query result of multiple event attributes in the emergency event knowledge graph, and the query result contains multiple first associated attributes; then input the first query result into the emergency event knowledge graph again to obtain the second query result, and the second query result contains multiple second associated attributes; at this time, calculate the convergence value of the second query result. If the convergence value of the second query result reaches the convergence value threshold, stop the iteration, and use the first query result and the second query result as the associated attributes of the current emergency event. If the convergence value of the second query result does not reach the convergence value threshold, input the second query result into the emergency event knowledge graph again until the convergence value of the query result of the current emergency event reaches the convergence value threshold, stop the iteration, and use the results of multiple iterations as the associated attributes of the current emergency event.

[0067] In a possible implementation, to avoid excessive iteration leading to information overload and inaccuracy, it is also necessary to reasonably set the convergence value threshold. Specifically: First, match multiple event attributes of the emergency event with the historical emergency event library to obtain multiple similar historical emergency events. Then, calculate the similarity values between the current emergency event and the multiple similar historical emergency events. If there is a similarity value greater than or equal to the preset value among the multiple similar historical emergency events, select the convergence value threshold of this similar historical emergency event as the convergence value threshold for the iterative processing of the current emergency event. This process matches with the historical emergency event library and directly adopts the convergence value threshold of the event with high similarity after finding it, which can avoid unnecessary multiple iterations, save a large amount of computing resources and computing time, improve the processing speed. In addition, using the convergence value threshold of the known similar emergency event for the current emergency event can ensure the consistency and stability of the processing results, thereby enhancing the reliability of the final decision.

[0068] In a possible implementation, if there is no historical emergency event with a high similarity to the current emergency event in the historical emergency event library, read the complexity and iteration times of the emergency event, and then generate a corresponding dynamic convergence value threshold for each iteration result. In this way, while realizing dynamic information mining, it can also ensure that the situation of processing overload caused by excessive iteration times does not occur. Specifically, the following formula can be used for calculation:

[0069]

[0070] where T is the convergence value threshold corresponding to each iteration, is the initial default convergence value threshold, is the number of associated attributes after the nth iteration, is the number of associated attributes after the (n - 1)th iteration, is a very small positive number, is the maximum number of iterations, and are adjustment coefficients, where, is used to control the sensitivity of the convergence value threshold to the change in the number of associated attributes, is used to control the speed at which the convergence value threshold decreases as the number of iterations increases.

[0071] In the above formula,

[0072]

[0073] During the iterative process, it is an adjustment parameter for the convergence value threshold generated based on the change rate of the number of associated attributes (complexity change rate). It can be understood that if the number of associated attributes generated in two consecutive iterations is very close, the change rate is very small, and then the adjustment factor is close to 1, indicating that the convergence trend of the algorithm is not obvious at this time, and there is no need to significantly reduce the convergence threshold; if the change in the number of associated attributes is large, the adjustment factor will be less than 1, and at this time, the convergence threshold is adaptively reduced to prompt the algorithm to more carefully judge whether to converge and avoid introducing too much interference information to affect the final result.

[0074]

[0075] During the iterative process, it is an adjustment parameter for the convergence value threshold generated based on the number of iterations. It can be understood that during the iterative process, relying solely on the change rate of the number of associated attributes to adjust the convergence value threshold is likely to fall into an iterative dead loop, especially when the number of iterations is large, this phenomenon is more obvious. For example, when the number of associated attributes in each iteration is only 1, the actual change in the convergence value threshold before and after adjustment is not obvious, and the current convergence value is far from reaching the convergence value threshold, resulting in a continuous loop state. Therefore, by introducing the number of iterations to adjust the convergence value threshold, the iteration can be stopped when an iterative dead loop occurs. Specifically, at the beginning of the algorithm, the number of iterations is small, the adjustment parameter is close to 1, and the impact on the convergence value threshold is small; as the number of iterations increases, the adjustment parameter gradually decreases, thereby reducing the convergence value threshold, making it easier for the algorithm to converge when approaching the maximum number of iterations.

[0076] In summary, by adjusting the convergence value threshold through the change rate of associated attributes in each iteration, the mining depth and breadth can be accurately grasped, and too much interference information can be avoided; in addition, to prevent the algorithm from entering a dead loop state, the number of iterations also needs to be introduced to adjust the convergence value threshold, thereby limiting the mining range of the algorithm and improving the reliability of subsequent decisions.

[0077] S104. Generate a rescue equipment table for multiple associated attributes and multiple event attributes.

[0078] S105. Integrate multiple rescue equipment tables to obtain a rescue equipment configuration plan for emergency events.

[0079] In the above steps S104 - S105, the rescue equipment table contains relevant parameters and quantities of rescue equipment that deal with associated attributes or event attributes. For example, if the associated attribute is an explosion of flammable and explosive chemicals, the rescue equipment table includes chemical protective clothing, gas detectors, etc. It can be understood that one associated attribute or event attribute can generate multiple rescue equipment tables, and multiple associated attributes or event attributes can also generate only one rescue equipment table. Therefore, finally, multiple rescue equipment tables need to be integrated to determine the rescue equipment to be configured finally and their corresponding quantities.

[0080] In a possible implementation, different rescue equipment may have the same function, but due to changes in the rescue scenario, there are differences in the rescue efficiency of different rescue equipment. For example, both fire trucks and portable fire extinguishers can extinguish fires, but fire trucks have stronger fire extinguishing capabilities, larger water volumes, and longer ranges, and are the main fire extinguishing equipment, while portable fire extinguishers are suitable for use in the initial stage of a fire or a small - scale fire and are secondary fire extinguishing equipment. Therefore, when integrating multiple rescue equipment tables, it is necessary to conduct a functional evaluation of multiple rescue equipment tables according to the current application scenario to obtain the functional fitness of multiple rescue equipment tables. Among them, the evaluation process can be obtained by calculating the functional score of the rescue equipment. Specifically: use the analytic hierarchy process to determine the weight values of multiple associated attributes and event attributes, and then calculate the weighted sum score of the rescue equipment according to the performance scores of the rescue equipment in dealing with multiple associated attributes and event attributes in the actual scenario. At this time, the weighted sum score of the rescue equipment is the functional score of the rescue equipment. Finally, if the functional score of the rescue equipment is greater than or equal to the preset score, it is determined that the rescue equipment needs to be configured into the rescue equipment configuration plan.

[0081] Refer to Figure 2 , this application also provides a rescue equipment configuration system for an emergency rescue vehicle. The system is an emergency rescue platform, and the emergency rescue platform includes an acquisition module 1 and a processing module 2, where:

[0082] The acquisition module 1 is used to acquire the basic information of an emergency event;

[0083] The processing module 2 is used to extract keywords and perform standardization processing on the basic information of the emergency event to obtain multiple event attributes of the emergency event;

[0084] Input the multiple event attributes into a preset emergency event knowledge graph to obtain multiple associated attributes;

[0085] Generate rescue equipment tables for multiple associated attributes and multiple event attributes; integrate multiple rescue equipment tables to obtain a rescue equipment configuration plan for the emergency event.

[0086] In a possible implementation, the basic information of an emergency event is parsed to obtain multiple sub-information of the emergency event and the information source corresponding to each of the multiple sub-information;

[0087] According to the information source corresponding to each of the multiple sub-information, the multiple sub-information is classified to obtain multiple classification clusters;

[0088] The keyword extraction algorithms corresponding to each of the multiple classification clusters are used to extract the keywords of the multiple classification clusters.

[0089] In a possible implementation, using the keyword extraction algorithms corresponding to each of the multiple classification clusters to extract the keywords of the multiple classification clusters specifically further includes:

[0090] Obtain multiple non-keywords of a first classification cluster, where the first classification cluster is any one of the multiple classification clusters;

[0091] Screen the multiple non-keywords to obtain multiple non-keywords to be verified;

[0092] Perform part-of-speech tagging on the multiple non-keywords to be verified;

[0093] Based on the part-of-speech of the multiple non-keywords to be verified, allocate the multiple non-keywords to a second classification cluster for keyword verification to extract the missing keywords among the multiple non-keywords to be verified, where the second classification cluster is any classification cluster other than the first classification cluster among the multiple classification clusters.

[0094] In a possible implementation, obtain a first association attribute between multiple event attributes;

[0095] Input the multiple first association attributes into an emergency knowledge graph to generate multiple second association attributes;

[0096] Calculate the convergence value of the multiple second association attributes in the emergency event knowledge graph;

[0097] If the convergence value reaches the threshold, determine that the multiple first association attributes and the multiple second association attributes are the association attributes of the multiple event attributes.

[0098] In a possible implementation, if the convergence value reaches the threshold, determining that the multiple first association attributes and the multiple second association attributes are the association attributes of the multiple event attributes specifically further includes:

[0099] Match the multiple event attributes of the emergency event with a historical emergency event library to obtain multiple similar historical emergency events;

[0100] Calculate the similarity value between the emergency event and the multiple similar historical emergency events;

[0101] If the similarity value between the emergency event and the first similar historical emergency event is greater than or equal to the preset value, the convergence value threshold of the first similar historical emergency event is used as the threshold of the emergency event, and the first similar historical emergency event is any one of multiple similar historical emergency events.

[0102] In a possible implementation, after calculating the similarity values between the emergency event and multiple similar historical emergency events, it further includes:

[0103] If the similarity values between multiple similar historical emergency events and the emergency event are all less than the preset value, read the complexity and the number of iterations of the emergency event;

[0104] Based on the complexity and the number of iterations of the emergency event, adjust the convergence value threshold of the emergency event.

[0105] In a possible implementation, perform a functional evaluation on multiple rescue equipment lists to obtain the functional fitness of multiple rescue equipment lists;

[0106] Based on the functional fitness of multiple rescue equipment lists, generate a rescue equipment configuration plan for the emergency event.

[0107] It should be noted that: when the device provided in the above embodiments realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be seen in the method embodiments, which will not be elaborated here.

[0108] This application also discloses an electronic device. Refer to Figure 3 , Figure 3 is a schematic structural diagram of an electronic device disclosed in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0109] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0110] Among them, the user interface 303 may include a display screen (Display), a camera (Camera), and optionally the user interface 303 may further include a standard wired interface and a wireless interface.

[0111] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0112] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines, and executes various functions of the server and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling the data stored in the memory 305. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0113] Among them, the memory 305 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store the data involved in the above-mentioned method embodiments. Optionally, the memory 305 may further be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , in the memory 305 as a computer storage medium, there may be included an operating system, a network communication module, a user interface module, and an application program of a rescue equipment configuration method for an emergency rescue vehicle.

[0114] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for a rescue equipment configuration method of an emergency rescue vehicle. When executed by one or more processors 301, the electronic device 300 is caused to execute one or more of the methods as described in the above embodiments. It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, some steps can be in other sequences or performed simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0115] In the above embodiments, each embodiment is described with emphasis. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] In several implementation manners provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0117] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit exists physically alone, or two or more units are integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0119] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0120] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and the disclosure of the practical truth, those skilled in the art will easily think of other implementation schemes of the present disclosure.

[0121] The present application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for configuring rescue equipment of an emergency rescue vehicle, characterized in that Applied to an emergency rescue platform, the method includes: Obtain the basic information of an emergency event; Perform keyword extraction and standardization processing on the basic information of the emergency event to obtain multiple event attributes of the emergency event; The keyword extraction from the basic information of the emergency event specifically includes: Parse the basic information of the emergency event to obtain multiple sub-information of the emergency event and the information source corresponding to each of the multiple sub-information; Classify the multiple sub-information according to the information source corresponding to each of the multiple sub-information to obtain multiple classification clusters; Use the keyword extraction algorithm corresponding to each of the multiple classification clusters to extract the keywords of the multiple classification clusters; The use of the keyword extraction algorithm corresponding to each of the multiple classification clusters to extract the keywords of the multiple classification clusters specifically further includes: Obtain multiple non-keywords of a first classification cluster, where the first classification cluster is any one of the multiple classification clusters; Screen the multiple non-keywords to obtain multiple non-keywords to be verified; Perform part-of-speech tagging on the multiple non-keywords to be verified; Based on the part-of-speech of the multiple non-keywords to be verified, allocate the multiple non-keywords to a second classification cluster for keyword verification to extract the missing keywords among the multiple non-keywords to be verified, where the second classification cluster is any classification cluster other than the first classification cluster among the multiple classification clusters; Input the multiple event attributes into a preset emergency event knowledge graph to obtain multiple associated attributes; Generate a rescue equipment table for the multiple associated attributes and the multiple event attributes; Integrate the multiple rescue equipment tables to obtain a rescue equipment configuration plan for the emergency event.

2. The method according to claim 1, wherein The inputting the multiple event attributes into a preset emergency event knowledge graph to obtain multiple associated attributes specifically includes: Obtain a first associated attribute between the multiple event attributes; Input the multiple first associated attributes into the emergency knowledge graph to generate multiple second associated attributes; Calculate the convergence value of the multiple second associated attributes in the emergency event knowledge graph; If the convergence value reaches the threshold, determine that the multiple first associated attributes and the multiple second associated attributes are the associated attributes of the multiple event attributes.

3. The method according to claim 2, wherein The if the convergence value reaches the threshold, determining that the multiple first associated attributes and the multiple second associated attributes are the associated attributes of the multiple event attributes specifically further includes: Match the multiple event attributes of the emergency event with a historical emergency event library to obtain multiple similar historical emergency events; Calculate the similarity value between the emergency event and the multiple similar historical emergency events; If the similarity value between the emergency event and the first similar historical emergency event is greater than or equal to a preset value, use the convergence value threshold of the first similar historical emergency event as the threshold of the emergency event, where the first similar historical emergency event is any one of the multiple similar historical emergency events.

4. The method according to claim 3, wherein After calculating the similarity value between the emergency event and the multiple similar historical emergency events, it further includes: If the similarity values of multiple said similar historical emergency events and the said emergency event are all less than a preset value, then read the complexity and the number of iterations of the said emergency event; Based on the complexity and the number of iterations of the said emergency event, adjust the convergence value threshold of the said emergency event.

5. The method according to claim 1, characterized in that The integration of multiple said rescue equipment lists to obtain the rescue equipment configuration plan for the said emergency event specifically includes: Conduct a functional evaluation of multiple said rescue equipment lists to obtain the functional fitness degrees of multiple rescue equipment lists; Based on the functional fitness degrees of multiple said rescue equipment lists, generate the rescue equipment configuration plan for the said emergency event.

6. A rescue equipment configuration system for an emergency rescue vehicle, characterized in that, The said system is an emergency rescue platform, and the emergency rescue platform includes an acquisition module (1) and a processing module (2), where: The acquisition module (1) is used to acquire the basic information of an emergency event; The processing module (2) is used to perform keyword extraction and standardization processing on the basic information of the said emergency event to obtain multiple event attributes of the said emergency event; The keyword extraction of the basic information of the said emergency event specifically includes: Analyze the basic information of the said emergency event to obtain multiple sub-information of the said emergency event and the information sources corresponding to each of the multiple sub-information; According to the information sources corresponding to each of the multiple sub-information, classify the multiple sub-information to obtain multiple classification clusters; Adopt the keyword extraction algorithms corresponding to each of the multiple classification clusters to extract the keywords of the multiple classification clusters; The adoption of the keyword extraction algorithms corresponding to each of the multiple classification clusters to extract the keywords of the multiple classification clusters specifically further includes: Obtain multiple non-keywords of a first classification cluster, where the first classification cluster is any one of the multiple classification clusters; Screen multiple said non-keywords to obtain multiple to-be-verified non-keywords; Perform part-of-speech tagging on multiple said to-be-verified non-keywords; Based on the parts of speech of multiple said to-be-verified non-keywords, allocate multiple said to-be-verified non-keywords to a second classification cluster for keyword verification to extract the missing keywords among multiple said to-be-verified non-keywords, where the second classification cluster is any classification cluster other than the first classification cluster among the multiple classification clusters; Input multiple said event attributes into a preset emergency event knowledge graph to obtain multiple associated attributes; Generate rescue equipment lists for multiple said associated attributes and multiple said event attributes; Integrate multiple said rescue equipment lists to obtain the rescue equipment configuration plan for the said emergency event.

7. An electronic device, characterized in that, It includes a processor (301), a memory (305), a user interface (303) and a network interface (304). The memory (305) is used to store instructions. The user interface (303) and the network interface (304) are used to communicate with other devices. The processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The said computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 5 is executed.

Images