Fire alarm decision generation method and device, medium and product

Abstract

The embodiment of the invention provides a fire alarm decision generation method and device, a medium and a product. The method comprises the following steps: acquiring first alarm information of a fire alarm event; generating first decision information according to the first alarm information through a fire-fighting decision generation model; and based on the first decision information, the firefighter arrives at the alarm address according to the police route, and obtains field information of a fire-fighting field of the fire-fighting alarm event in real time. And updating the first decision-making information according to the field information based on the fire-fighting decision-making generation model to obtain second decision-making information updated in real time, so that firefighters can carry out fire-fighting rescue according to the second decision-making information. And first decision information is generated according to the first alarm information through a fire-fighting decision generation model, so that a firefighter can obtain a detailed action guide before the firefighter leaves a police. Second decision information updated in real time is generated by acquiring field information of a fire protection field in real time.

Description

Technical Field

[0001] The present disclosure relates to the technical field of fire dispatching, and in particular to a method, device, medium and product for generating fire alarm situation decisions. Background Art

[0002] With the acceleration of urbanization, the complexity and urgency of fire alarms are increasing. In the related art, the fire decision-making method mainly relies on the experience and intuition of firefighters. This method is often difficult to make scientific and reasonable decisions quickly when facing complex and changeable alarms. Especially in emergency situations such as fires, timely and accurate decisions are crucial to protecting people's lives and property. In the related art, the dispatch of firefighters often relies mainly on the limited information provided by the alarm personnel, which leads to the problem of insufficient information during the dispatch of firefighters, affecting the accuracy of decision-making. For example, for fire disposal in residential areas, the fire scene documents usually only contain address information, and do not provide actual structural information of the residential area, such as the number of floors and surrounding environment. This makes it impossible for firefighters to quickly determine the building type of the residential area, which in turn affects the formulation of the disposal plan. For example, it is impossible to determine whether the residential area is a multi-story building, and it is impossible to obtain the surrounding road traffic information and available water source information in time. This causes firefighters to face the problem of information lag during the dispatch of firefighters, affecting the rescue effect. On the other hand, in related technologies, after firefighters arrive at the scene, there is often a lack of effective means to obtain and update on-site information in real time, resulting in the initial decision-making information being no longer applicable, affecting the rescue effect. Summary of the invention

[0003] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a method, device, medium and product for generating fire alarm decision-making to solve the problems in the related technology.

[0004] The first aspect of the present disclosure provides a method for generating a fire alarm situation decision, which includes:

[0005] Obtaining first alarm information of a fire alarm event; wherein the first alarm information includes: one or more of an alarm address, personnel situation information, and an alarm type;

[0006] Generate first decision information according to the first alarm information through a fire decision generation model; the first decision information includes one or more of an alarm route, an alarm force, and an alarm equipment;

[0007] Based on the first decision information, the firefighter arrives at the alarm address according to the alarm route, and obtains the on-site information of the fire scene of the fire alarm event in real time;

[0008] The first decision information is updated according to the on-site information based on the fire decision generation model to obtain second decision information updated in real time, so that firefighters can perform fire rescue according to the second decision information.

[0009] In an embodiment of the first aspect, before generating the first decision information according to the first alarm information by using a preset fire decision generation model, the method further includes:

[0010] Processing the first alarm information through a preset feature representation model to obtain a corresponding alarm information feature vector;

[0011] The alarm information feature vector is input into the firefighting decision generation model.

[0012] In an embodiment of the first aspect, generating first decision information according to the first alarm information by using a preset fire decision generation model includes:

[0013] Based on the preset fire analysis model, the surrounding road condition information of the alarm address is obtained according to the alarm address; the surrounding road condition information is used to calculate the alarm route; the alarm equipment and fire protection plan are obtained according to the alarm type; and the police force is obtained according to the personnel situation information;

[0014] Based on the preset firefighting decision generation model, the first decision information is generated according to the police response route, police response equipment, firefighting decision and the police response force.

[0015] In an embodiment of the first aspect, the fire analysis model includes a trained deep neural network model, and the training data of the deep neural network model is obtained based on a preset fire professional knowledge base; wherein, the fire professional knowledge base includes historical case information corresponding to different types of alarm situations, and the corresponding fire protection plan is obtained based on the historical information.

[0016] In an embodiment of the first aspect, the first warning information further includes one or more of the following:

[0017] 1) The building information of the incident location corresponding to the address of the alarm;

[0018] 2) When the alarm type is fire, available water source information obtained according to the alarm address;

[0019] 3) Obtaining fire-fighting equipment storage information based on the building information.

[0020] In an embodiment of the first aspect, the on-site information includes one or more of wind direction information, wind force information, and fire intensity information.

[0021] In an embodiment of the first aspect, the updating of the first decision information according to the on-site information based on the fire fighting decision generation model and generating the second decision information includes:

[0022] Acquiring the on-site information in real time;

[0023] Based on the fire fighting decision generation model, obtaining first sub-decision information according to the on-site information at a preset time point;

[0024] The first decision information is updated according to the first sub-decision information to obtain the second decision information.

[0025] A second aspect of the present disclosure provides a computer device, comprising:

[0026] Processor and memory;

[0027] The memory stores program instructions;

[0028] The processor is used to run the program instructions to execute the generation method described in any one of the above embodiments.

[0029] A third aspect of the present disclosure provides a computer-readable storage medium, wherein program instructions are stored, and the program instructions are executed to perform the generation method described in any one of the above embodiments.

[0030] A fourth aspect of the present disclosure provides a computer program product, which includes: program instructions for executing any one of the generation methods described in the above embodiments.

[0031] The beneficial effects of the present disclosure are as follows: by using a fire decision generation model, first decision information is generated according to the first alarm information, so that firefighters can obtain detailed action guidelines before going out on duty, thereby improving the accuracy and timeliness of decision-making. After the firefighters arrive at the scene, they obtain the on-site information of the fire scene in real time, and update the first decision information based on the fire decision generation model to generate second decision information updated in real time, so as to ensure the real-time and accuracy of the decision information, and better cope with the dynamic changes on the scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A flowchart showing a method for generating a fire alarm situation decision in one embodiment of the present disclosure is shown.

[0033] Figure 2 A schematic diagram of a process for processing the first alarm information for input into the fire decision model in a generation method in one embodiment of the present disclosure is shown.

[0034] Figure 3A schematic diagram of a process for generating first decision information based on the first alarm information in a generation method in one embodiment of the present disclosure is shown.

[0035] Figure 4 A schematic diagram of a process for updating the first decision information according to the field information to generate the second decision information in a generation method in one embodiment of the present disclosure is shown.

[0036] Figure 5 A schematic diagram showing the structure of a computer device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0037] The following is an explanation of the embodiments of the present disclosure by specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the information disclosed by the present disclosure. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in the present disclosure can also be modified or changed in various ways according to different viewpoints and application modules without departing from the spirit of the present disclosure. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0038] The following is a detailed description of the embodiments of the present disclosure with reference to the accompanying drawings so that those skilled in the art can easily implement the present disclosure. The present disclosure can be embodied in many different forms and is not limited to the embodiments described herein.

[0039] In the representations of the present disclosure, the reference terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" and the like mean that the specific features, structures, materials or characteristics represented in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. Moreover, the specific features, structures, materials or characteristics represented may be combined in any one or a group of embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples represented in the present disclosure and the features of different embodiments or examples, unless they are mutually contradictory.

[0040] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the representation of the present disclosure, "a group" means two or more, unless otherwise clearly and specifically defined.

[0041] In order to clearly describe the present disclosure, components not related to the description are omitted, and the same reference numerals are given to the same or similar components throughout the specification.

[0042] Throughout the specification, when a device is said to be "connected" to another device, this includes not only the case of "direct connection" but also the case of "indirect connection" by placing other elements therebetween. In addition, when a device is said to "include" a certain component, unless otherwise stated, it does not exclude other components, but means that other components may be included.

[0043] Although the terms first, second, etc. are used to represent various elements in this article in some examples, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first interface and the second interface, etc. are represented. Moreover, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising" and "including" indicate that there are the described features, steps, operations, elements, modules, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or a group of other features, steps, operations, elements, modules, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". Only when the combination of elements, functions, steps or operations is inherently mutually exclusive in some way, will there be an exception to this definition.

[0044] The technical terms used herein are only used to refer to specific embodiments and are not intended to limit the present disclosure. The singular form used herein also includes the plural form unless the sentence clearly indicates the contrary meaning. The meaning of "including" used in the specification is to specify specific characteristics, regions, integers, steps, operations, elements and / or components, and does not exclude the existence or addition of other characteristics, regions, integers, steps, operations, elements and / or components.

[0045] Although not defined differently, all terms, including technical and scientific terms used herein, have the same meaning as those generally understood by those skilled in the art to which the present disclosure belongs. Terms defined in commonly used dictionaries are additionally interpreted as having meanings consistent with relevant technical literature and the message of the present disclosure, and shall not be overly interpreted as ideal or very formal meanings unless defined.

[0046] In the related art, the dispatch of firefighters often relies mainly on the limited information provided by the alarm personnel, which may cause firefighters to face the problem of insufficient information during the dispatch process, affecting the accuracy of decision-making. For example, for fire disposal in residential areas, the fire scene documents usually only contain address information, and do not provide the actual structural information of the residential area, such as the number of building floors, surrounding environment, etc. This makes it impossible for firefighters to quickly determine the building type of the residential area, which in turn affects the formulation of the disposal plan. For example, it is impossible to determine whether the residential area is a multi-story building, and it is impossible to obtain the surrounding road traffic information and available water source information in time. This causes firefighters to face the problem of information lag during the dispatch process, affecting the rescue effect. On the other hand, when firefighters arrive at the scene, they often lack effective means to obtain and update the on-site information in real time, resulting in the initial decision-making information may no longer be applicable, affecting the rescue effect.

[0047] Therefore, in order to solve the above problems, the present disclosure provides a method for generating fire alarm decision, which generates first decision information based on first alarm information through a fire decision generation model, so that firefighters can obtain detailed action guidelines before going out on duty, thereby improving the accuracy and timeliness of decision making. After the firefighters arrive at the scene, they can obtain the on-site information of the fire scene in real time, and can also use the fire decision generation model to update the first decision information and generate second decision information updated in real time, so as to ensure the real-time and accuracy of the decision information and better cope with the dynamic changes on the scene.

[0048] Figure 1 A flowchart showing a method for generating a fire alarm situation decision in one embodiment of the present disclosure is shown.

[0049] exist Figure 1 In this example, the method for generating fire alarm decisions includes:

[0050] Step S1, obtaining the first alarm information of a fire alarm event.

[0051] The first alarm information includes: one or more of the alarm address, personnel situation information and alarm type. When a fire incident occurs and rescue is needed, the on-site personnel send a distress signal to the firefighters and describe the on-site situation to form the first alarm information corresponding to the fire alarm event. The first alarm information can be the alarm information directly described by the on-site rescue personnel, or it can be the alarm information obtained after the alarm receiving personnel sort out the information. There are no excessive restrictions on the format of the first alarm information.

[0052] Specifically, when a fire alarm occurs, the caller can report the alarm to the fire command center through various methods such as phone calls, text messages, and mobile applications. The fire command center can record the exact alarm address through automatic voice recognition technology or the person who receives the alarm. Optionally, when the alarm device has a GPS positioning function, the fire command center can directly obtain the geographic location of the caller to ensure the accuracy of the address information. In addition to the alarm address, the caller must also provide the personnel situation at the scene, including whether there are people trapped, the number of injured and the degree of injury, etc. To provide certain basic information for the subsequent strategy generation. The alarm type provided by the caller when reporting the alarm, such as fire, gas leakage, explosion, etc. Different alarm types may require different response strategies and rescue methods.

[0053] Optionally, the first alarm information also includes one or more of the following: 1) building information of the incident site corresponding to the alarm address; 2) when the alarm type is fire, available water source information obtained based on the alarm address; 3) fire-fighting equipment storage information obtained based on the building information.

[0054] As an example, after obtaining the first alarm information, the Geographic Information System (GIS) and Building Information Model (BIM) can be used to quickly obtain key data such as the building structure, entrance and exit locations, and floor plans corresponding to the alarm address as building information. This can help firefighters understand the internal structure of the building in advance, plan the best entry path, reduce rescue time, and improve rescue efficiency.

[0055] For example, when the alarm type is confirmed to be a fire, the alarm address is matched with nearby water sources, such as fire hydrants, lakes, rivers, etc., and the distance and accessibility of each water source to the fire scene are calculated to ensure the continuity and effectiveness of the firefighting operation.

[0056] As an example, based on the above-mentioned alarm address and / or building information, the location of the fire station closest to the alarm address and its equipment configuration details can also be obtained, including but not limited to fire extinguishers, hoses, demolition tools, etc. At the same time, for high-rise buildings or special-purpose places (such as chemical plants, hospitals, etc.), the locations of safety facilities equipped inside them will be specially marked, such as emergency evacuation passages, smoke-proof stairwells, automatic sprinkler systems, etc., so that firefighters can quickly locate and use these resources for effective disposal.

[0057] Furthermore, in some embodiments, the first alarm information may also include the floor where the fire started, the type of burning material, and the spread of smoke and fire, so as to assess the development trend of the fire and formulate corresponding fire extinguishing strategies through the subsequent fire fighting decision generation model. It is worth noting that the first alarm information may be any one or more of the above, or may not be the above-mentioned content. The first alarm information is changed according to the actual situation. The first alarm information is to represent the alarm situation at the scene, and the various alarm situations should be included in the protection scope of this disclosure.

[0058] Step S2, generating first decision information according to the first alarm information through a fire decision generation model; the first decision information includes one or more of the alarm route, the alarm force and the alarm equipment.

[0059] The police officer inputs the first alarm information into a trained fire decision generation model, and the fire decision generation model integrates and generates the first decision information based on the first alarm information. The first decision information includes detailed on-site conditions and relevant information that can be used by firefighters to quickly respond to the call. This solves the problem in the related art that firefighters delay rescue time and affect rescue effects due to the lack of detailed rescue plans.

[0060] Specifically, the first alarm information obtained (including the basic alarm information provided by the alarm personnel and the supplementary information further obtained based on the basic alarm information) is used as input and passed into the fire decision generation model.

[0061] Figure 2 A schematic diagram of a process for processing the first alarm information for input into the fire decision model in a generation method in one embodiment of the present disclosure is shown.

[0062] Optionally, before generating the first decision information according to the first alarm information by using the preset fire decision generation model, Figure 2 In the example, the generating method further includes:

[0063] Step S21, processing the first alarm information through a preset feature representation model to obtain a corresponding alarm information feature vector;

[0064] Step S22, inputting the alarm information feature vector into the fire fighting decision generation model.

[0065] Specifically, in some embodiments, a feature representation model is pre-set. The model needs to be pre-trained, and the training data includes a large number of historical cases to ensure that the model can accurately generate feature vectors corresponding to case texts associated with historical cases.

[0066] In some embodiments, the feature representation model may be One-Hot, and the One-Hot representation method may effectively convert text information into a binary vector to indicate which words appear in the text, thereby retaining the semantic information of the text.

[0067] In some embodiments, the feature representation model may also be TF-IDF, which can convert text information into a numerical feature vector and is suitable for processing warning information in text form.

[0068] In another embodiment, the feature representation model may also be word2vector. Both of the above models have a disadvantage that if the text is very long, many feature words / phrases will be extracted, and the vector representing a sentence will be longer. Word2vector is based on a large amount of text corpus and maps each word into a vector of a fixed dimension through training similar to a neural network model.

[0069] Figure 3 A schematic diagram of a process for generating first decision information based on the first alarm information in a generation method in one embodiment of the present disclosure is shown.

[0070] Optionally, generating first decision information according to the first alarm information by using a preset fire decision generation model includes:

[0071] Step S121, based on a preset fire analysis model, obtain the surrounding road condition information of the alarm address according to the alarm address; use the surrounding road condition information to calculate the alarm route; obtain the alarm equipment and fire protection plan according to the alarm type; and obtain the police force according to the personnel situation information;

[0072] Step S122, based on the preset fire decision generation model, the first decision information is generated according to the police route, police equipment, fire decision and the police force.

[0073] Specifically, the fire analysis model may include multiple small models, including a fire analysis sub-model, a route planning sub-module, an equipment selection sub-module and a police force allocation sub-module.

[0074] Through the fire analysis model, the data of the traffic management department is connected to obtain the surrounding road condition information in real time, so as to obtain the surrounding road condition information of the alarm address according to the alarm address. This includes real-time traffic data, road closures, traffic congestion, etc.

[0075] Based on the surrounding road condition information, the route planning submodule is used to calculate the optimal dispatch route, including the specific driving path, estimated arrival time and precautions.

[0076] According to the type of alarm, use the equipment selection submodule to determine the required alarm equipment. For example, for a high-rise building fire, the system will recommend carrying equipment such as a ladder truck and a high-pressure water gun; for a chemical leak, professional chemical accident handling equipment is required.

[0077] Generate corresponding fire fighting plans based on the alarm type and building information, including fire fighting strategies, evacuation plans and rescue measures.

[0078] Based on the personnel information, the police force sub-allocation module is used to determine the required police force. For example, for fires with trapped personnel, it is recommended to send more firefighters and special rescue teams; for fires with no trapped personnel, the police force can be appropriately reduced.

[0079] The above-calculated dispatching routes, dispatching equipment, firefighting plans and dispatching police forces are integrated to generate the first decision information.

[0080] Optionally, the fire analysis model includes a trained deep neural network model, and the training data of the deep neural network model is obtained based on a preset fire professional knowledge base; wherein, the fire professional knowledge base includes historical case information corresponding to different types of alarm situations, and the corresponding fire protection plan is obtained based on the historical information.

[0081] Specifically, in some embodiments, first, a fire protection professional knowledge base is constructed, which contains a large amount of historical case information, which covers a variety of different types of alarm situations. Each case information includes but is not limited to the following aspects: Alarm type: fire, explosion, chemical leakage, rescue, etc. Case description: Details of the accident, including time, location, environmental conditions, etc. Casualties: number of injured, degree of casualties, etc. Property loss: type and value of damaged property. Fire response measures: number of fire trucks and personnel dispatched, specific measures taken, etc. Final processing results: final processing effect, including whether the fire was successfully extinguished, whether the rescue was successful, etc. The above content is extracted into feature vectors through the feature representation model, and deep feature extraction is performed through a deep neural network model. The input of the deep neural network model is the preprocessed case features, and the output is the fire protection plan corresponding to each case feature. The model structure may include multiple hidden layers to improve the expression ability of the model. Finally, it is integrated through the fire decision generation model to form the first decision information.

[0082] exist Figure 1 In the example, in step S13, based on the first decision information, the firefighters arrive at the alarm address according to the alarm route and obtain the on-site information of the fire scene of the fire alarm event in real time.

[0083] Specifically, in some embodiments, the first decision information generated by the fire decision generation model includes the best dispatch route, the estimated arrival time, and the required firefighting resources. After receiving this information, the firefighters immediately start the dispatch procedure and go to the alarm address according to the route provided by the navigation system. During the dispatch, the navigation system updates the traffic conditions in real time to ensure that the fire truck can choose the optimal path to quickly arrive at the scene. After arriving at the alarm address, the firefighters quickly confirm the location and make a preliminary assessment. In some embodiments, drones can also be used for aerial reconnaissance to obtain a bird's-eye view and thermal imaging of the scene. Temperature sensors, smoke sensors and other equipment installed on site transmit data to the command center in real time, and firefighters report the on-site situation in real time through handheld terminals or walkie-talkies, including information such as the development of the fire and casualties.

[0084] exist Figure 1 In the example, step S14 updates the first decision information according to the on-site information based on the fire decision generation model to obtain real-time updated second decision information for firefighters to perform fire rescue according to the second decision information.

[0085] When the rescuers arrive at the scene, the first decision information can be updated in real time according to the on-site information, so as to solve the problem in the related technology that the decision information may no longer be suitable for the rescue scene due to untimely information, thereby affecting the rescue effect.

[0086] Specifically, in some embodiments, when firefighters arrive at the scene and collect on-site information including fire development, casualties, environmental conditions, etc. in real time, this information is transmitted to the command center in real time through a handheld terminal or sensor device. Optionally, the on-site information includes one or more of wind direction information, wind force information, and fire information. After receiving this on-site information, the fire decision generation model analyzes and processes it, and dynamically adjusts and optimizes the first decision information. The generated second decision information includes updated police dispatch plans, resource allocation, rescue measures, etc., to ensure that firefighters can take the most effective actions based on the latest situation. Specifically, for example, if the fire on the scene is more serious than expected, the second decision information may increase the dispatch of fire trucks and personnel, or adjust the priority of fire extinguishing and rescue. In this way, firefighters can carry out fire rescue more accurately and efficiently based on the second decision information updated in real time, ensuring personnel safety and reducing property losses.

[0087] Figure 4 A schematic diagram of a process for updating the first decision information according to the field information to generate the second decision information in a generation method in one embodiment of the present disclosure is shown.

[0088] Optionally, updating the first decision information according to the on-site information based on the fire fighting decision generation model and generating second decision information includes:

[0089] Step S141, acquiring the on-site information in real time;

[0090] Step S142, based on the fire decision generation model, obtaining first sub-decision information according to the on-site information at a preset time point;

[0091] Step S143: Update the first decision information according to the first sub-decision information to obtain the second decision information.

[0092] Specifically, in some embodiments, the information processing system of the command center automatically triggers an information analysis at a preset time point (e.g., every 5 minutes). The real-time on-site information (including wind direction, wind force, and fire information) is input into the pre-trained fire decision generation model. The fire decision generation model generates the first sub-decision information based on this information, combined with historical cases and expert knowledge. For example, the model may suggest adjusting the route of the fire truck, increasing the amount of fire extinguishing agent used, or changing the angle and direction of the fire extinguishing equipment. The staff of the command center updates the original first decision information based on the first sub-decision information. For example, if the first sub-decision information suggests increasing the amount of fire extinguishing agent used, the command center will adjust the resource allocation to ensure that there is enough fire extinguishing agent supply on site. The updated second decision information includes new alarm plans, resource allocation, rescue measures, etc., to ensure that firefighters can take the most effective actions based on the latest situation. For example, if the fire suddenly intensifies, the second decision information may send more firefighting forces or change the priority of rescue. The updated second decision information is conveyed to the firefighters on site through the communication system to guide them to perform rescue tasks according to the new instructions. At the same time, the command center continues to monitor the progress of the rescue and further adjusts its decisions based on subsequent feedback information.

[0093] Optionally, in some embodiments, when there is a discrepancy between the information reported by the on-site personnel and the information provided by the drone, for example, if the drone image shows that there is no open fire in a certain area, but the on-site personnel report that there is smoke in the area, the system may call other drones or ground monitoring equipment to conduct further inspections of the area. In some cases, the system may not be able to fully automatically resolve information conflicts. At this time, the staff of the command center needs to intervene and decide which information to use as the basis for decision-making based on their experience and judgment. Furthermore, in order to prevent the data transmitted on-site within a period of time from being updated too quickly, resulting in the second decision information being updated too quickly, the update time can be set according to the on-site situation, and the first decision information can be updated based on the latest on-site transmission to obtain the latest second decision information.

[0094] like Figure 5 , which shows a schematic diagram of the structure of a computer device in one embodiment of the present disclosure.

[0095] The computer device 100 may be exemplified as a processing terminal in a cloud platform, such as a server, a desktop computer, a laptop computer, a tablet computer, a smart phone or other terminals.

[0096] The computer device 100 includes a bus 101, a processor 102, and a memory 103. The processor 102 and the memory 103 can communicate with each other through the bus 101. The memory 103 can store program instructions. The processor 102 implements the steps of the generation method in the previous embodiment by running the program instructions in the memory 103, for example Figure 1 .

[0097] The bus 101 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, although only one thick line is used in the figure, it does not mean that there is only one bus or one type of bus.

[0098] In some embodiments, the processor 102 may be implemented as a central processing unit (CPU), a microprocessing unit (MCU), a system on chip (System On Chip), or a field programmable logic array (FPGA). The memory 103 may include a volatile memory (Volatile Memory) for temporary storage of data when running a program, such as a random access memory (Random Access Memory, RAM).

[0099] The memory 103 may also include a non-volatile memory for data storage, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid-state disk (SSD).

[0100] In some embodiments, the computer device 100 may further include a communicator 104. The communicator 104 is used to communicate with the outside. In a specific example, the communicator 104 may include one or a group of wired and / or wireless communication circuit modules. For example, the communicator 104 may include one or more of a wired network card, a USB module, a serial interface module, etc. The wireless communication protocols followed by the wireless communication module include: for example, near field communication (NFC) technology, infrared (IR) technology, Global System for Mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Time-Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), Bluetooth (BT), Global Navigation Satellite System (GNSS), etc. One or more.

[0101] In an embodiment of the present disclosure, a computer-readable storage medium may be provided, storing program instructions, which implement the generation method in any of the previous embodiments when executed.

[0102] That is, the method steps in the above embodiments are implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or are implemented as computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded via a network and to be stored in a local recording medium, so that the method represented herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA).

[0103] A computer program product may also be provided in an embodiment of the present disclosure, including: program instructions for executing any of the generation methods described above.

Claims

1. A method for generating fire alarm decision, characterized in that: include: Obtaining first alarm information of a fire alarm event; wherein the first alarm information includes: one or more of an alarm address, personnel situation information, and an alarm type; Generate first decision information according to the first alarm information through a fire decision generation model; the first decision information includes one or more of an alarm route, an alarm force, and an alarm equipment; Based on the first decision information, the firefighter arrives at the alarm address according to the alarm route, and obtains the on-site information of the fire scene of the fire alarm event in real time; The first decision information is updated according to the on-site information based on the fire decision generation model to obtain second decision information updated in real time, so that firefighters can perform fire rescue according to the second decision information.

2. The generation method according to claim 1, characterized in that: Before generating the first decision information according to the first alarm information by using the preset fire decision generation model, the method further includes: Processing the first alarm information through a preset feature representation model to obtain a corresponding alarm information feature vector; The alarm information feature vector is input into the firefighting decision generation model.

3. The generation method according to claim 1, characterized in that: Generating first decision information according to the first alarm information by using a preset fire decision generation model includes: Based on the preset fire analysis model, the surrounding road condition information of the alarm address is obtained according to the alarm address; the surrounding road condition information is used to calculate the alarm route; the alarm equipment and fire protection plan are obtained according to the alarm type; and the police force is obtained according to the personnel situation information; Based on the preset firefighting decision generation model, the first decision information is generated according to the police response route, police response equipment, firefighting decision and the police response force.

4. The generation method according to claim 3, characterized in that: The fire analysis model includes a trained deep neural network model, and the training data of the deep neural network model is obtained based on a preset fire professional knowledge base; wherein the fire professional knowledge base includes historical case information corresponding to different types of alarm situations, and the corresponding fire protection plan is obtained based on the historical information.

5. The generation method according to claim 1, characterized in that: The first warning information also includes one or more of the following: 1) The building information of the incident location corresponding to the address of the alarm; 2) When the alarm type is fire, available water source information obtained according to the alarm address; 3) Obtaining fire-fighting equipment storage information based on the building information.

6. The generation method according to claim 1, characterized in that: The on-site information includes one or more of wind direction information, wind force information and fire intensity information.

7. The generation method according to claim 1, characterized in that: The updating of the first decision information based on the fire fighting decision generation model according to the on-site information and generating the second decision information includes: Acquiring the on-site information in real time; Based on the fire fighting decision generation model, obtaining first sub-decision information according to the on-site information at a preset time point; The first decision information is updated according to the first sub-decision information to obtain the second decision information.

8. A computer device, characterized in that: include: Processor and memory; The memory stores program instructions; The processor is used to run the program instructions to execute the generation method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: Program instructions are stored, and the program instructions are executed to perform the generation method according to any one of claims 1 to 7.

10. A computer program product, characterized in that include: Program instructions for executing the generation method according to any one of claims 1 to 7.

Images