Emergency response method and system for high-risk environment operations based on intelligent communication equipment

Abstract

The present invention discloses a method and system for emergency response to high-risk environment operations based on intelligent communication equipment, which relates to the technical field of intelligent communication networks and equipment. The method includes: obtaining communication tasks in high-risk environments and constructing a communication-related topology network; then introducing a communication response risk analysis model to predict a communication response risk sequence; analyzing anomalies to determine communication optimization guidance features, adjusting the network to establish a first group of communication configuration adjustments; then optimizing to generate a second group; obtaining a strategy through multiple rounds of variation optimization, and combining the network to execute tasks. The present invention solves the technical problem that traditional wireless communication network methods are difficult to dynamically adapt to on-site communication tasks in high-risk environments, resulting in communication being easily interrupted, delayed, or having security vulnerabilities, and being unable to meet the high-precision requirements of emergency response for communication reliability and security. The present invention achieves the technical effect of dynamically adapting communication tasks in high-risk environments, improving the reliability and security of wireless communication networks, and meeting the high-precision requirements of emergency response for communication.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent communication networks and equipment, and in particular to an emergency response method and system for high-risk environment operations based on intelligent communication equipment. Background Art

[0002] When operating in high-risk environments, a stable and reliable wireless communication network is key to ensuring efficient emergency response and is directly related to worker safety and mission completion efficiency. Existing technologies often use conventional wireless communication equipment and network configuration methods to address communication needs in high-risk environments, which can be effective in ordinary scenarios. However, high-risk environments present complex and variable communication interference factors (such as strong electromagnetic fields and signal shielding), and the distribution and relationship relationships of equipment are complex. Traditional methods struggle to dynamically adapt to on-site communication tasks, often resulting in communication interruptions, delays, or security vulnerabilities, hindering emergency response and failing to meet the high-precision requirements for communication reliability and security in high-risk environments. Summary of the Invention

[0003] The present application provides a method and system for emergency response to high-risk environment operations based on intelligent communication equipment, which is used to solve the technical problem that traditional wireless communication network methods are difficult to dynamically adapt to on-site communication tasks in high-risk environments, resulting in communication interruptions, delays or security vulnerabilities, and cannot meet the high-precision requirements of emergency response for communication reliability and security.

[0004] The first aspect of the present application provides an emergency response method for high-risk environment operations based on intelligent communication equipment, the method comprising: obtaining communication tasks at a high-risk environment operation site, and associating and sorting the communication equipment set at the high-risk environment operation site according to the communication tasks to construct a communication association topology network; introducing a communication response risk analysis model, predicting the response risk of the communication association topology network in combination with the communication environment scenario flow, and determining a communication response risk sequence; performing anomaly analysis on the communication response risk sequence according to the communication response risk constraint, determining a communication optimization guidance feature, and adjusting the communication association topology network according to the communication optimization guidance feature to establish a first communication configuration adjustment group; performing response risk optimization on the first communication configuration adjustment group according to the communication response risk analysis model and the communication response risk constraint to generate a second communication configuration adjustment group; performing communication global risk variation optimization on the second communication configuration adjustment group according to a predetermined number of variation rounds to generate a communication configuration adjustment optimization strategy, and executing the communication task in combination with the communication association topology network.

[0005] According to a second aspect of the present application, a high-risk environment operation emergency response system based on intelligent communication devices is provided, the system comprising: a communication association topology network construction module, configured to obtain communication tasks at a high-risk environment operation site, and associate and sort the communication equipment set at the high-risk environment operation site according to the communication tasks to construct a communication association topology network; a communication response risk sequence acquisition module, configured to introduce a communication response risk analysis model, predict the response risk of the communication association topology network in combination with the communication environment scenario flow, and determine the communication response risk sequence; a communication configuration adjustment first group construction module, configured to perform anomaly analysis on the communication response risk sequence according to communication response risk constraints, determine communication optimization guidance features, and adjust the communication association topology network according to the communication optimization guidance features to establish a communication configuration adjustment first group; a communication configuration adjustment second group acquisition module, configured to perform response risk optimization on the communication configuration adjustment first group according to the communication response risk analysis model and the communication response risk constraints to generate a communication configuration adjustment second group; and a communication task execution module, configured to perform communication global risk variation optimization on the communication configuration adjustment second group according to a predetermined number of variation rounds, generate a communication configuration adjustment optimization strategy, and execute the communication task in combination with the communication association topology network.

[0006] One or more technical solutions provided in the present application have at least the following technical effects or advantages: the present application obtains communication tasks at high-risk environment operation sites, associates and sorts the on-site communication equipment sets to construct a communication association topology network, introduces a communication response risk analysis model combined with the communication environment scenario flow to predict the risk sequence, analyzes anomalies based on risk constraints and determines optimization guidance features to adjust the network, generates a communication configuration adjustment optimization strategy through multiple rounds of optimization, combines the topology network to execute tasks, thereby dynamically adapting to the communication needs of high-risk environments, improving the reliability and security of wireless communication networks, and meeting the high-precision requirements of emergency response, thereby achieving the technical effect of dynamically adapting to communication tasks in high-risk environments, improving the reliability and security of wireless communication networks, and meeting the high-precision requirements of emergency response for communication. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 This is a flow chart of an emergency response method for high-risk environment operations based on intelligent communication equipment provided in an embodiment of the present application. Figure 2This is a schematic diagram of the structure of the high-risk environment operation emergency response system based on intelligent communication devices provided in an embodiment of the present application. Explanation of the accompanying figures: Communication association topology network construction module 1, communication response risk sequence acquisition module 2, communication configuration adjustment first group construction module 3, communication configuration adjustment second group acquisition module 4, communication task execution module 5. DETAILED DESCRIPTION

[0009] This application provides a method and system for emergency response in high-risk environments based on intelligent communication devices. These methods are designed to address the technical problem that traditional wireless communication network methods have difficulty dynamically adapting to on-site communication tasks in high-risk environments, resulting in communication interruptions, delays, or security vulnerabilities, and failing to meet the high-precision requirements for communication reliability and security for emergency response. The following, in conjunction with the accompanying drawings, provides a clear and complete description of the technical solutions in the embodiments of this application. Obviously, the described embodiments are only some of the embodiments of this application, and not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application. It should be noted that the terms "first," "second," and so on, in the specification of this application and the accompanying drawings, are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such process, method, product, or device.

[0010] Example 1, as Figure 1 As shown, a high-risk environment operation emergency response method based on intelligent communication equipment, wherein the method includes:

[0011] Step A100: obtaining communication tasks of a high-risk environment operation site, and correlating and sorting out the communication equipment set of the high-risk environment operation site according to the communication tasks to construct a communication correlation topology network.

[0012] In the embodiment of the present application, the communication equipment set is a variety of intelligent communication equipment manufactured based on existing technologies that are adapted to high-risk environment operation scenarios. It has the ability to support multiple network modes, can adapt to complex communication environments, has long-term endurance performance, and can meet the basic functional requirements of emergency communications in high-risk environments. Some devices support multiple extended functions to adapt to different operation tasks.

[0013] Specifically, at high-risk work sites, the initiation of communication tasks is typically generated by the operation monitoring center or dispatch platform based on real-time operational needs. The monitoring center will combine information such as the type of work on-site, personnel distribution, and equipment operating status to define the core content of the communication task, including the task type (such as equipment status data transmission, real-time voice communication between personnel, and emergency command issuance), the scope of intelligent communication equipment involved, the time window for task execution, and its priority. For example, during underground mining operations, when abnormal gas concentrations occur in a certain area, the monitoring center will generate a communication task that transmits real-time gas sensor data in that area to the dispatch platform and initiates voice communication with personnel in that area. The generated communication task is then transmitted to the on-site intelligent communication equipment set via the wireless communication network. Various intelligent communication devices deployed on site receive tasks with their adapted network modes: the supported 5GNR frequency bands (n1 / n3 / n5 / n8, etc.) and 5G-SA / NSA modes can achieve high-speed and low-latency transmission in high-risk environments with complex signals, and the task transmission delay can be controlled within 10ms; the supported 4G frequency bands, FDD-LTEB1 / B3, TDD-LTEB38 / B40, etc., can still ensure stable task reception in areas with insufficient 5G signal coverage, with a transmission delay of approximately 50ms, meeting the real-time requirements of emergency tasks.

[0014] After receiving a task, the intelligent communication device uses its built-in processor to parse it. This processor, with its efficient data processing capabilities, can quickly extract key information from the task, such as the target device identifier, task execution instructions, and data transmission format. Parsing can reach up to 10 tasks per second, ensuring the device quickly understands the communication task it is participating in. After parsing, the device synchronizes the task information to its local task storage and management unit, which stores the parsed task information. It also sends a confirmation signal confirming successful task reception to the monitoring center, completing the task transmission cycle. During this process, the intelligent communication device's large battery capacity ensures the device's battery life while continuously receiving and processing tasks, preventing task interruptions due to power outages. Next, building a communication association topology network involves constructing a communication device topology network based on the communication device set and then identifying and associating these devices based on the communication tasks to generate the communication association topology network. The specific steps are detailed in A110-A120.

[0015] Through the coherent steps of task initiation, network transmission, device reception and analysis, and feedback confirmation, communication tasks at high-risk environment work sites can be obtained accurately and timely, providing a clear goal and basis for the subsequent correlation and sorting of communication equipment sets according to tasks and the construction of communication correlation topology networks.

[0016] Step A200: introducing a communication response risk analysis model, performing response risk prediction on the communication-related topology network in combination with the communication environment scenario flow, and determining a communication response risk sequence.

[0017] In this embodiment, the communication response risk analysis model is a machine learning model that takes confidence response simulation data as input and outputs a communication response risk sequence containing risk coefficients corresponding to three indicators: communication quality risk, communication security risk, and hardware reliability risk. This model is used to perform multi-indicator analysis and prediction of the response risk of communication-related topology networks. The communication environment scenario stream is a continuous data stream generated in a time series after data cleaning by collecting multimodal environment scenario parameters from high-risk work sites.

[0018] Optionally, multiple communication response simulation data are obtained based on the communication environment scenario flow and the communication associated topology network simulation response, and after fusion, they are input into a communication response risk analysis model containing multiple indicators of communication quality, security, and hardware reliability risks to obtain a communication response risk sequence. The specific steps are described in detail in A210-A230.

[0019] Step A300: performing abnormal analysis on the communication response risk sequence according to the communication response risk constraint, determining the communication optimization guidance feature, and adjusting the communication association topology network according to the communication optimization guidance feature to establish a first communication configuration adjustment group.

[0020] In this embodiment of the present application, communication response risk constraints are restrictions on indicators such as communication quality risk, communication security risk, and hardware reliability risk in the communication response risk sequence, used to determine whether the risk is abnormal. Communication optimization guidance features are generated based on the analysis of communication risk anomaly tracing results and are used to guide specific tuning features for adjusting the communication-related topology network. The first communication configuration adjustment group is a collection of multiple communication configuration adjustment schemes established after adjusting the communication-related topology network based on the communication optimization guidance features.

[0021] In one embodiment of the present application, first, according to the communication response risk constraint detection response risk abnormality feature, based on the communication risk abnormal event set, a traceability tree is built, the confidence response simulation data and the abnormal feature are input to obtain the traceability result, and then the communication optimization guidance feature is parsed and generated. The specific steps are described in detail in A310-A340. After obtaining the communication optimization guidance feature, the feature must first be converted into a specific network adjustment instruction. For example, if the guidance feature is to adjust the communication frequency band to the anti-interference frequency band n78 and start the equipment backup power module, it needs to be disassembled into executable parameter adjustment items: the link frequency band of the equipment involved in data transmission in the communication-related topology network is uniformly switched from the current n41 to n78. The anti-interference ability of this frequency band is improved in high-risk environments; for equipment with excessive hardware reliability risks, the backup power switching instruction is triggered to switch the battery power supply mode from a single battery to dual batteries in parallel, and the battery life is increased to 1.5 times the original.

[0022] Subsequently, the communication-related topology network is optimized for structure and parameters based on the network adjustment instructions. Structurally, the connection relationships between device nodes are redefined. For example, two core devices that were previously indirectly connected are now directly connected, reducing data transfer steps and lowering transmission latency. Parameters are adjusted, such as device transmit power and signal reception sensitivity, to ensure that the adjusted link stability meets the basic communication requirements of the actual project. After network adjustment is complete, all valid adjustment solutions are collected to form the first group of communication configuration adjustments. Each solution must include the device identifier, specific parameter values, and a comparison of risk factors before and after adjustment. For example, one solution records: Device A: frequency band n78, transmit power 27dBm, communication quality risk factor reduced from 0.72 to 0.55; Device B: enable backup power, hardware reliability risk factor reduced from 0.58 to 0.32. Multiple sets of such valid solutions are collected, examples of which are shown in Table 1. All valid adjustment solutions were obtained by technical personnel based on actual projects and constitute the initial set of the first group. Each set of solutions has passed basic risk verification, and each risk factor is below the constraint threshold.

[0023] By converting the optimization guidance features into specific adjustment instructions, optimizing the structure and parameters of the communication-related topology network, and integrating effective adjustment schemes to form the first group of communication configuration adjustment, a variety of basic solutions are provided for subsequent response risk optimization, ensuring the pertinence and feasibility of communication network adjustment in high-risk environments.

[0024] Table 1: Consolidated table of effective adjustment plans

[0025] ;

[0026] Step A400: Optimizing the response risk of the first communication configuration adjustment group according to the communication response risk analysis model and the communication response risk constraint to generate a second communication configuration adjustment group.

[0027] Specifically, the first group is adjusted from the communication configuration to extract solutions and optimize the network, and its response risk sequence is predicted. Solutions that meet the constraints are added to the second group, otherwise they are eliminated, and the optimization is continued to build the second group. The specific steps are detailed in A410-A450.

[0028] Step A500: performing communication global risk mutation optimization on the communication configuration adjustment second group according to a predetermined number of mutation rounds, generating a communication configuration adjustment optimization strategy, and executing the communication task in combination with the communication association topology network.

[0029] In an embodiment of the present application, the predetermined number of mutation rounds is a positive integer P greater than 2, which is used to determine the rounds of mutation optimization of the second group and subsequent optimization domains of communication configuration adjustment until a communication adjustment mutation Pth optimization domain that meets the number of rounds is generated.

[0030] Specifically, a global risk assessment model is constructed based on multiple indicators of communication response risk, and global risk minimization optimization is performed on the second group of communication configuration adjustment and the optimization domain generated by multiple rounds of mutation optimization until the predetermined number of mutation rounds is met. The specific steps are described in detail in A510-A550.

[0031] Next, when executing communication tasks in conjunction with a communication-related topology network, the generated communication configuration adjustment optimization strategy is implemented using this network as the basic framework, relying on the device node association relationships, link connection methods, and initial communication parameters it contains. First, based on the device adjustment parameters specified in the optimization strategy, such as switching the frequency band to n79, setting the transmit power to 26dBm, and using the AES-256 encryption protocol, configuration instructions are issued to the corresponding intelligent communication devices through the node communication links of the topology network to ensure that each device operates according to the optimal parameters.

[0032] During task execution, the topology network's relevance is leveraged to monitor the communication status of each device in real time. Core nodes regularly collect operational data from edge devices, such as signal strength, battery charge, and data transmission success rate, and aggregate it to the control center via network links. If a link experiences signal attenuation, the topology network quickly locates its associated upstream and downstream devices, triggering a predefined link switching mechanism to automatically switch data transmission to a backup link to avoid task interruption.

[0033] At the same time, combined with the dynamic changes of the communication environment scene flow, the task execution risk is continuously evaluated through the communication response risk analysis model. When the environmental interference intensity suddenly increases, based on the anti-interference capability correlation information of the devices in the topology network, the parameters of the devices with weaker anti-interference capabilities are adjusted first, such as increasing their transmission power, and using the distributed structure of the network to disperse the data transmission pressure, ensuring the continuity and reliability of communication tasks in high-risk environments.

[0034] By adjusting the communication configuration of the second group according to a predetermined number of mutation rounds to generate an optimization strategy for global communication risk mutation optimization, and combining it with the communication-related topology network to execute tasks, the technical effect of low-risk and efficient execution of communication tasks in a high-risk environment is achieved.

[0035] Furthermore, step A200 in the method provided in the embodiment of the present application includes:

[0036] A210: Based on the communication environment scenario flow, multiple simulated responses are performed on the communication task according to the communication association topology network to obtain multiple communication response simulation data.

[0037] A220: Perform confidence fusion on the multiple communication response simulation data to obtain confidence response simulation data.

[0038] A230: Input the confidence response simulation data into the communication response risk analysis model to obtain the communication response risk sequence, wherein the communication response risk analysis model includes multiple communication response risk indicators, and the multiple communication response risk indicators include communication quality risk, communication security risk and hardware reliability risk.

[0039] Specifically, in high-risk environments, the construction and training of a communication response risk analysis model requires the integration of multi-source data and machine learning techniques. The model input is confidence-fused simulated response data, which includes multi-dimensional parameters related to communication quality, security, and hardware reliability, such as signal strength (-50dBm to -120dBm), interference intensity (0-100%), and battery charge (0-100%). The output is three risk coefficients, corresponding to communication quality risk, communication security risk, and hardware reliability risk, with values ​​ranging from 0 to 1, with higher values ​​indicating greater risk.

[0040] During the model building phase, historical communication data must first be collected as a training set. For example, communication records from the chemical park over the past 12 months were collected, including signal strength during normal communication conditions, peak interference intensity corresponding to abnormal communication events (such as interruptions caused by interference), and battery power levels during equipment failures. Through feature engineering, three types of metrics were extracted: communication quality (bit error rate, signal attenuation rate), security (number of attack attempts, data integrity check failure rate), and hardware (battery consumption rate, device temperature fluctuations). This formed a training dataset containing 100,000 records.

[0041] The model is trained using a random forest algorithm, with 200 decision trees to balance computational efficiency and prediction accuracy. During training, the dataset is split into training and validation sets in an 8:2 ratio, and parameters are adjusted through cross-validation. For example, setting the maximum tree depth to 15 and the minimum number of leaf node samples to 5 resulted in a model with an accuracy of 92% and an F1 score of 0.89 on the validation set. During training, input data is normalized. For example, signal strength is mapped to a 0-1 scale, with -50dBm corresponding to 1 and -120dBm corresponding to 0. Hardware temperatures between -10°C and 60°C are converted to a 0-1 scale using the normalization formula (x-min) / (max-min). This ensures consistent model sensitivity to features of varying magnitudes.

[0042] During the risk prediction phase, multiple simulations of the communication-related topology network responses are performed based on the communication environment scenario flow. For example, for an underground gas monitoring task, Monte Carlo simulations were used to generate 1,000 simulation data runs, each including the response parameters of the communication equipment under varying interference intensities and battery levels. During the simulations, communication quality risks were quantified using signal transmission delay (50ms to 500ms) and bit error rate (1e-4 to 1e-2). Security risks were assessed using packet loss rates during simulated malicious attacks, and hardware risks were calculated using device operating time and temperature.

[0043] Subsequently, confidence fusion is performed on the simulated communication response data. Using the Dempster-Shafer evidence theory, each simulated data point is treated as an independent source of evidence, and the basic probability assignment (BPA) for each indicator is calculated. For example, for communication quality risk, if 80% of the simulated data indicates a bit error rate exceeding 1e-3, a confidence level of 0.8 is assigned to the high risk, and the remaining 0.2 is allocated to the unknown. Multi-source evidence is fused using combination rules to eliminate conflicting data, such as outliers where the bit error rate suddenly drops to 1e-6, ultimately generating confident response simulated data. The confidence threshold for the fused data is set to 0.95, ensuring 95% consistency in the simulation results.

[0044] Finally, the confidence response simulation data is fed into the trained communication response risk analysis model. The model outputs three risk factors through a voting mechanism involving 200 decision trees. For example, in one prediction, the communication quality risk factor is 0.72, corresponding to a bit error rate of 1.2e-3 and a signal delay of 350ms; the security risk factor is 0.65, with 3 attack attempts per minute; and the hardware reliability risk factor is 0.58, with a battery charge of 35% and a temperature of 48°C, forming a risk sequence of [0.72, 0.65, 0.58]. The system triggers an alert based on a preset threshold (e.g., 0.7), indicating the need to prioritize optimizing communication link stability.

[0045] By generating multiple sets of response data for confidence fusion and using the random forest model to achieve multi-indicator risk prediction, this method can dynamically evaluate communication reliability in high-risk environments, provide data support for emergency response, reduce the risk misjudgment rate, and significantly improve the stability and security of the communication system.

[0046] Furthermore, step A300 in the method provided in the embodiment of the present application includes:

[0047] A310: Perform anomaly detection on the communication response risk sequence according to the communication response risk constraint to obtain a response risk anomaly feature.

[0048] A320: Conduct accident tree learning based on the communication risk abnormal event set and build a communication risk abnormality tracing tree.

[0049] A330: Input the confidence response simulation data and the response risk anomaly characteristics into the communication risk anomaly tracing tree to obtain a communication risk anomaly tracing result.

[0050] A340: Perform communication optimization feature analysis based on the communication risk anomaly tracing result to generate the communication optimization guidance feature.

[0051] Optionally, in high-risk environment operations, communication response risk constraints include three dimensions: communication quality risk constraints, such as a coefficient ≤ 0.6; communication security risk constraints, such as a coefficient ≤ 0.5; and hardware reliability risk constraints, such as a coefficient ≤ 0.4. For a communication response risk sequence, such as the aforementioned risk sequence [0.72, 0.45, 0.58], each coefficient is compared with the corresponding constraint: if the communication quality risk coefficient of 0.72 is greater than 0.6 and the hardware reliability risk coefficient of 0.58 is greater than 0.4, these two items are judged as abnormal and integrated to form a response risk abnormality feature, recorded as exceeding the communication quality standard and exceeding the hardware reliability standard.

[0052] Next, based on the communication risk anomaly event set, identify the top event features, trace the intermediate events and basic event features, build multiple tracing paths, and then generate a communication risk anomaly tracing tree by associating and detecting the aggregated paths. The specific steps are described in detail in A321-A325.

[0053] The confidence response simulation data (including parameters such as signal strength, interference intensity, and battery charge) and the response risk anomaly characteristics are then input into the communication risk anomaly tracing tree. The tracing tree matches the paths and outputs communication risk anomaly tracing results. For example, the communication quality exceeded the standard due to signal attenuation caused by electromagnetic interference intensity of 65%, and the hardware reliability exceeded the standard due to performance degradation caused by battery charge of 32% and continuous operation for 5 hours. The confidence levels of each cause are annotated: 92% and 88%, respectively.

[0054] Finally, communication risk anomaly tracing results are used to analyze communication optimization features. For example, for electromagnetic interference, the communication frequency band can be adjusted to an anti-interference band; for battery issues, the backup power module can be activated and switched to low-power mode. These features are integrated to generate communication optimization guidance features, clarifying the specific direction for network adjustment and device configuration.

[0055] By locating risk points through anomaly detection, tracing root causes through accident trees, and analyzing and optimizing features, this process achieves a precise transformation from risk identification to optimization direction, provides a targeted basis for adjusting communication-related topology networks, and makes the management and control of communication risks in high-risk environments more targeted.

[0056] Furthermore, step A320 in the method provided in the embodiment of the present application includes:

[0057] A321: Identify top event features based on the communication risk abnormal event set to obtain features of each abnormal top event.

[0058] A322: Based on the communication risk abnormal event set, intermediate event tracing is performed on the features of each abnormal top event to obtain features of each abnormal intermediate event.

[0059] A323: Based on the communication risk abnormal event set, basic event tracing is performed on the characteristics of each abnormal intermediate event to obtain each abnormal basic event characteristic.

[0060] A324: Construct multiple communication risk anomaly tracing paths based on the characteristics of each abnormal top event, the characteristics of each abnormal intermediate event, and the characteristics of each abnormal basic event.

[0061] A325: Perform association detection based on the communication risk anomaly event set to determine a risk anomaly association feature set, and aggregate the multiple communication risk anomaly tracing paths based on the risk anomaly association feature set to generate the communication risk anomaly tracing tree.

[0062] Specifically, in high-risk environment communication scenarios, the communication risk abnormal event set covers various types of communication abnormal events that have occurred in history, including information such as event type, occurrence time, impact scope and root cause. For example, it includes 800 communication interruption, data transmission error, equipment downtime and other events recorded in the past three years, of which communication interruption events account for 45%, data transmission errors account for 30%, and equipment downtime accounts for 25%.

[0063] Based on the communication risk abnormal event set, the top event features are first identified. The top event refers to the final abnormal result that directly affects the execution of the communication task. Through statistical analysis of the communication risk abnormal event set, technical personnel in this field can extract the characteristics of various abnormal top events such as communication task failure, key data loss, and device cluster offline. For example, the specific number of times and corresponding proportions of the top event of communication task failure appear in the communication risk abnormal event set are characterized by task execution interruption and target device unresponsiveness. Similarly, the specific number of times and corresponding proportions of the other abnormal top event features appear in the communication risk abnormal event set can also be obtained.

[0064] Next, we trace the source of each abnormal top event. Intermediate events are indirect causes of the top event. By correlating and analyzing the relationship between the top event and the preceding abnormal phenomena in the communication risk abnormal event set, we determine the characteristics of each abnormal intermediate event. Taking communication task failure as an example, we traced the source of three intermediate event characteristics: signal transmission link interruption, core equipment computing power overload, and data encryption verification failure. The number and proportion of signal transmission link interruption in communication task failure events were correlated. Similarly, the number and proportion of correlated abnormal intermediate event characteristics of the remaining abnormal intermediate events can be obtained.

[0065] Then, we conduct basic event tracing on each abnormal intermediate event feature to identify the root cause of the intermediate event. For example, for the intermediate event of signal transmission link interruption, we mine the basic abnormal event features of various abnormal events, such as strong electromagnetic interference, equipment antenna failure, and transmission frequency band conflict, from the communication risk abnormal event set. The frequency and proportion of strong electromagnetic interference in signal transmission link interruption events are characterized by the ambient electromagnetic intensity exceeding the equipment tolerance threshold, such as >80dBμV / m. The frequency and proportion of the other basic abnormal event features can be obtained similarly.

[0066] Based on the characteristics of each of the aforementioned abnormal top events, intermediate events, and basic events, multiple communication risk anomaly tracing paths are constructed. For example, communication task failure → signal transmission link interruption → strong electromagnetic interference, communication task failure → core device computing power overload → excessive memory usage, etc. Multiple tracing paths are constructed, and the probability of the event occurring is annotated on each path. The probability is calculated by multiplying the proportion of the corresponding events on each path.

[0067] Finally, when performing correlation detection on a set of abnormal communication risk events, all events involved in each traceability path are first extracted from the event set, including top events, intermediate events, basic events, and their attributes, such as event type, occurrence timestamp, associated device ID, and impact range, to form a structured event data matrix. Next, the Apriori association rule algorithm is used to calculate the co-occurrence frequency and conditional probability between different events. For example, the number of times strong electromagnetic interference, signal transmission link interruption, and device antenna failure co-occur within the same time window (e.g., within 5 minutes) is counted. If the proportion of co-occurrence to the total number of events exceeds a set threshold of 30%, a potential correlation is preliminarily determined.

[0068] Subsequently, we verify the causal relationship through time series analysis, examining the order in which events occur. If the timestamps of strong electromagnetic interference consistently precede those of signal transmission link interruptions and device antenna failures, with the time difference concentrated within 1-3 minutes, this aligns with the timeliness of electromagnetic interference's impact on devices, thus eliminating the possibility of random co-occurrence. We also calculate the coupling strength, such as the increase in the baseline probability of signal transmission link interruptions and the increase in the probability of device antenna failure after strong electromagnetic interference occurs, to quantify the mutual impact between the events.

[0069] Ultimately, the event relationships that met co-occurrence frequency, temporal causality, and coupling strength thresholds were categorized. The team identified strong electromagnetic interference as a common cause of signal transmission link disruptions and device antenna failures, with device antenna failures exacerbating the coupling relationship between signal transmission link disruptions. This led to the extraction of the associated characteristic of electromagnetic environment degradation, which was incorporated into the risk anomaly association feature set. Based on this risk anomaly association feature set, multiple traceability paths involving electromagnetic environment degradation were aggregated to generate a communication risk anomaly traceability tree with multiple main branches. Each branch clearly displays the complete causal chain from the base event to the top event.

[0070] Through top event identification, intermediate and basic event tracing, path construction and aggregation, the generated communication risk anomaly tracing tree can systematically sort out the transmission path and root cause of communication risks, providing a structured analysis tool for accurately locating the source of anomalies and formulating targeted optimization strategies.

[0071] Furthermore, step A400 in the method provided in the embodiment of the present application includes:

[0072] A410: Extracting a first communication configuration adjustment scheme according to the first communication configuration adjustment group, and performing fitting optimization on the communication-associated topology network according to the first communication configuration adjustment scheme to obtain a communication-optimized first network.

[0073] A420: Based on the communication environment scenario flow, a response risk prediction is performed on the communication optimized first network according to the communication response risk analysis model to obtain a first solution response risk sequence.

[0074] A430: If the first solution response risk sequence satisfies the communication response risk constraint, add the first communication configuration adjustment solution to the second communication configuration adjustment group.

[0075] A440: If the first scheme response risk sequence does not satisfy the communication response risk constraint, eliminate the first communication configuration adjustment scheme.

[0076] A450: Continue to perform response risk optimization on the first communication configuration adjustment group according to the communication response risk analysis model and the communication response risk constraint, and construct the second communication configuration adjustment group.

[0077] Specifically, solutions were sequentially extracted from the first group of communication configuration adjustments (Table 1, which contains 10 communication configuration adjustment solutions). For example, solutions 1 and 2 were first extracted: Device A switched to the n78 frequency band and a transmit power of 27dBm, and Device B activated its backup power supply. Based on these solutions, the communication-related topology network was optimized by adjusting the link between Device A and the core node to a direct link, removing redundant transit nodes, and updating the power supply module parameters of Device B to a dual-battery parallel mode. This ultimately resulted in the first communication-optimized network.

[0078] Based on the communication environment scenario flow, which includes dynamic parameters such as temperature (25-40°C) and interference intensity (10%-60%), a response risk prediction for the first communication optimization network was performed. First, 1,000 simulated responses were performed, each recording data related to communication quality (bit error rate, latency), security (encryption success rate), and hardware (battery consumption rate). This yielded 1,000 sets of simulated communication response data. This data was then subjected to confidence fusion, with 3% of outliers removed. The weighted mean of each parameter was then calculated to generate confidence response simulation data, such as an average bit error rate of 1.2 × 10⁻³, an encryption success rate of 98.5%, and an hourly battery consumption of 12%. This confidence data was input into the communication response risk analysis model, which output a response risk sequence for the first scenario, hypothesized to be [0.55, 0.42, 0.28].

[0079] Comparing the response risk sequence for the first solution with the communication response risk constraints (communication quality risk ≤ 0.6, communication security risk ≤ 0.5, and hardware reliability risk ≤ 0.4), all coefficients meet the constraints. Therefore, Solutions 1 and 2 are added to the second communication configuration adjustment group. Next, we extract Solution 3: Upgrading the encryption protocol of Device C to AES-256. Following the above steps to optimize the network and predict the risk, we hypothetically obtain the response risk sequence [0.48, 0.55, 0.32]. The communication security risk coefficient of 0.55 exceeds the constraint threshold of 0.5, so Solution 3 is eliminated.

[0080] The remaining solutions from the first group were processed sequentially using the same process, undergoing network optimization, 1,000 simulated responses, data fusion, risk prediction, and constraint comparison. Finally, solutions that met the constraints were integrated to form the second group of communication configuration adjustments. Each solution was annotated with the optimized network parameters and risk factors.

[0081] By extracting solutions from the first group one by one and performing optimization, risk prediction and constraint screening, a second group of communication configuration adjustments is constructed. This process ensures that all solutions in the second group meet the basic risk constraints, providing a high-quality set of candidate solutions for subsequent global risk variation optimization.

[0082] Furthermore, step A500 in the method provided in the embodiment of the present application includes:

[0083] A510: Based on the weight allocation of multiple indicators of communication response risk, a global communication risk assessment model is constructed.

[0084] A520: Performing mutation optimization on the second group of communication configuration adjustments according to the communication global risk assessment model to generate a first optimization domain for communication adjustment mutations.

[0085] A530: Performing mutation optimization on the communication regulation variation first optimization domain according to the communication global risk assessment model to generate a communication regulation variation second optimization domain.

[0086] A540: Continue to perform mutation optimization on the second optimization domain of the communication regulation variation according to the communication global risk assessment model until a P-th optimization domain of the communication regulation variation that meets the predetermined number of mutation rounds is generated, where P is a positive integer greater than 2.

[0087] A550: Perform communication global risk minimization optimization according to the communication configuration adjustment second group, the communication adjustment variation first optimization domain, the communication adjustment variation second optimization domain...the communication adjustment variation Pth optimization domain to obtain the communication configuration adjustment optimization strategy.

[0088] Specifically, the construction of the global communications risk assessment model begins with the weighting of multiple communication response risk indicators. Based on the core communication requirements for high-risk environment operations, weights are determined using the Analytic Hierarchy Process (AHP) combined with the impact of historical accidents: Communication security risk, directly related to data integrity and operational safety, is assigned a weight of 0.4; communication quality risk, impacting task execution efficiency, is assigned a weight of 0.35; and hardware reliability risk, impacting the equipment's ability to continue operating, is assigned a weight of 0.25. The sum of these three weights is 1, forming the indicator weight vector [0.35, 0.4, 0.25].

[0089] The model was trained using risk data from historical communication configuration adjustment scenarios. Data from 1,000 sets of valid scenarios from high-risk environments over the past five years were collected. Each set included communication quality risk (e.g., a 0-1 risk value derived from the bit error rate), communication security risk (e.g., a 0-1 risk value derived from the attack defense success rate), hardware reliability risk (e.g., a 0-1 risk value derived from the device's trouble-free operating time), and a corresponding manually labeled global risk score (0-1, with 1 being the highest risk). The dataset was split into training and validation sets at an 8:2 ratio. The model was trained using a random forest regression algorithm, using the three risk indicators as input features and the global risk score as the target value. By adjusting parameters such as the number of decision trees to 200 and the maximum depth to 10 layers, the model maintained a mean squared error (MSE) of less than 0.03 on the validation set, ensuring prediction accuracy.

[0090] The model inputs are the specific values ​​(normalized between 0 and 1) for the communication quality risk, communication security risk, and hardware reliability risk associated with the communication configuration adjustment scheme. For example, the input for a particular scheme is [0.55, 0.42, 0.28]. The output is a comprehensive score (0-1) for the scheme's global communication risk. Lower values ​​indicate lower global risk. This score is used to quantitatively evaluate the overall risk level of different schemes and provide a basis for subsequent variation optimization.

[0091] Next, the communication global risk assessment model is used to evaluate each scheme in the second group of communication configuration adjustment to obtain the risk set. The number of mutations is allocated based on the mutation number constraint. After the mutation, the first mutation space is obtained. After the response risk optimization, the first optimization domain of communication adjustment mutation is obtained. The specific steps are described in detail in A521-A524.

[0092] Then, based on the first optimization domain of communication regulation mutation (containing all mutation solutions that meet the risk constraints), a second optimization domain of communication regulation mutation is generated. First, these solutions are evaluated using the communication global risk assessment model to calculate a global risk score. For example, the score ranges from 0.36 to 0.48, with three solutions scoring below 0.4, six between 0.4 and 0.45, and three above 0.45. Based on the constraint on the number of mutations, assuming the total number of mutations in this round does not exceed 25, the number of mutations is allocated based on the score: solutions with a score above 0.45 are each allocated 3 mutations, those between 0.4 and 0.45 are each allocated 2 mutations, and those below 0.4 are each allocated 1 mutation, for a total of 3 × 3 + 6 × 2 + 3 × 1 = 9 + 12 + 3 = 24, which satisfies the constraint.

[0093] Next, each solution was subjected to parameter mutation according to the assigned number of variations. For example, for Solution 1 (scored 0.47 in Table 1), with device A operating at frequency band n78 and a transmit power of 27dBm, five variations were generated: power adjustment to 26dBm, 28dBm, and frequency band switching to n79. Similarly, variations were generated for the remaining solutions by fine-tuning hardware parameters and communication protocols, forming a second communication regulation variation space containing 24 solutions. Using the same response risk optimization method used to generate the first optimization domain, each variation was subjected to network optimization, 1000 response simulations, data fusion, and risk prediction. Solutions that met the communication response risk constraints were selected to form the second communication regulation variation optimization domain.

[0094] Continue mutation optimization on the second optimization domain using the same process as above to generate the third optimization domain. If the predetermined number of mutation rounds P = 5 > 2, repeat the above steps until the fifth optimization domain is generated. This domain contains multiple solutions, each with communication quality, security, and hardware risk factors consistently below the constraint threshold. The predetermined number of mutation rounds P should be determined based on the urgency of high-risk environment operations, the complexity of the communication system, and computing resource constraints. For scenarios with high emergency response requirements and the need for rapid strategy generation, P is typically set to a smaller value, such as 3-5, to reduce computational time. For scenarios with high communication risk control accuracy requirements and sufficient computing resources, P can be increased, such as 5-10, to improve strategy reliability through more rounds of mutation optimization. Furthermore, P must be a positive integer greater than 2 to ensure that multiple rounds of optimization cover a sufficient solution space, balancing optimization efficiency and risk control effectiveness.

[0095] Finally, all solutions for the second group of communication configuration adjustments and the first through fifth optimization domains are collected. A global risk score is extracted for each solution, and optimization is performed to minimize the communication global risk. The solution with the lowest score is selected and becomes the communication configuration adjustment optimization strategy.

[0096] By expanding the solution space through multiple rounds of mutation optimization and combining it with global risk minimization screening, the communication configuration adjustment optimization strategy finally obtained can minimize the global communication risk in high-risk environments while meeting various risk constraints, providing the optimal configuration solution for the stable execution of emergency communication tasks.

[0097] Furthermore, step A520 in the method provided in the embodiment of the present application includes:

[0098] A521: Perform a communication global risk evaluation on each communication configuration adjustment scheme in the second communication configuration adjustment group according to the communication global risk evaluation model to obtain a communication global risk set.

[0099] A522: Based on the mutation number constraint, allocate the number of mutation schemes for the second group of communication configuration adjustments according to the communication global risk set to obtain the number of mutations for each scheme.

[0100] A523: Mutate the second communication configuration adjustment group according to the number of variations of each scheme to obtain a first communication adjustment variation space.

[0101] A524: Perform response risk optimization on the communication regulation first variation space according to the communication response risk analytical model and the communication response risk constraint to obtain the communication regulation variation first optimization domain.

[0102] In one embodiment, each scheme in the second group of communication configuration adjustments (consisting of multiple communication configuration adjustment schemes that satisfy risk constraints) is first evaluated using a global communication risk assessment model. This model uses communication quality risk, communication security risk, and hardware reliability risk as inputs and calculates a global risk score by assigning weights (e.g., 0.35, 0.4, and 0.25). For example, the risk indicators for scheme 1 in Table 1 are [0.55, 0.42, 0.28], resulting in a global risk score of 0.43. The global risk scores for the remaining schemes are calculated similarly, forming a global communication risk set containing multiple scores.

[0103] Next, based on the constraint on the number of mutations, such as a total number of no more than 20, in high-risk communications emergency response scenarios, too many mutations would increase the computational burden and slow response speed. A number of approximately 20 ensures sufficient solutions for optimization exploration while avoiding the inefficiency caused by an excessive number of solutions, thus striking a balance between optimization effectiveness and practical operability. The number of mutations for each solution is allocated based on the global risk set. Solutions with higher risk scores require more mutations to explore the optimization space: For example, a solution with a score of 0.47 is allocated 5 mutations, 0.45 is allocated 4, 0.43 is allocated 3, 0.42 is allocated 3, 0.41 is allocated 3, and 0.39 is allocated 2. The total is 5 + 4 + 3 + 3 + 3 + 2 = 20, which satisfies the constraint.

[0104] Then, mutation operations were performed based on the number of variations for each solution. For the solution with a score of 0.47, for example, the antenna gain of device D in Table 1 was adjusted to 8dBi and the signal sensitivity to -110dBm. Five variations were generated: adjusting the antenna gain to 7dBi and 9dBi, and the sensitivity to -108dBm and -112dBm, and other parameter combinations. Similarly, variations were generated for the remaining solutions by fine-tuning parameters such as frequency band, power, and encryption protocol. Ultimately, a first variation space for communication adjustment was obtained, containing 20 variations.

[0105] Finally, a response risk optimization method similar to steps A410-A450 is used to process the first variation space: For each variation, the communication-related topology network is optimized. 1000 simulated responses are performed based on the communication environment scenario flow. After integrating the data, the response risk sequence is input into the communication response risk analysis model to obtain a response risk sequence. This sequence is compared with the constraints (communication quality ≤ 0.6, security ≤ 0.5, hardware ≤ 0.4). The corresponding solution among the 20 variations is identified as satisfying the constraints. For example, if the risk sequence of a variation is [0.52, 0.48, 0.36], it satisfies the constraints. The solutions that satisfy the constraints are then integrated to generate the first optimization domain for communication regulation variation.

[0106] By evaluating the global risk of the second group of solutions, allocating the number of mutations according to risk, screening parameter mutations and response risks, the generated first optimization domain of communication regulation mutation not only retains the optimization potential of high-quality solutions, but also ensures that the risks of the mutation solutions are controllable, providing a reliable initial domain for subsequent multiple rounds of mutation optimization.

[0107] Furthermore, step A100 in the method provided in the embodiment of the present application includes:

[0108] A110: Construct a communication device topology network based on the communication device set.

[0109] A120: Perform association identification on the communication device topology network according to the communication task, and generate the communication association topology network.

[0110] Optionally, at a high-risk environment operation site, after obtaining a communication task, the first step is to associate and sort out the communication equipment set on site based on the specific content of the task (such as data transmission, voice intercom, command issuance, etc.). This step requires analyzing the communication links involved in the task, clarifying the role of each intelligent communication device in the task, such as data acquisition end, transmission end, receiving end, etc., and identifying potential communication needs between devices. For example, if the task is to transmit sensor data from a certain area to the dispatch center in real time and support two-way voice communication, technical personnel in this field need to sort out the sensor equipment, the relay equipment responsible for data aggregation, the core equipment connected to the dispatch center, and the voice intercom equipment, clarify the data flow and signal interaction relationship between them, and ensure that all equipment associations required for task execution are covered.

[0111] After completing the association analysis, a communication device topology network is constructed based on the analysis results. Devices are used as nodes, and the communication links between devices (such as wireless connections and wired interfaces) are used as edges to form a visual network structure. This process records basic parameters such as the device's communication protocol, signal coverage, and connection stability. For example, it can be noted that devices A and B are connected via 5G signals with a transmission rate of up to 100Mbps, and that devices C and D are connected via Bluetooth with an effective range of 10 meters. This clearly presents the physical and logical connection status of all devices.

[0112] Subsequently, the constructed communication device topology network is associated and identified based on the communication task. Taking into account the task's priority and real-time requirements, the associated links that are critical to task execution are screened, strengthening the connections between key nodes and weakening or temporarily blocking non-essential links. For example, if the task requires data transmission latency to be no more than 50ms, low-latency links are identified and prioritized to ensure that communication between core devices meets timeliness requirements, ultimately generating a communication topology network that is highly compatible with the task.

[0113] By first sorting out device associations, then building a basic topology network, and finally combining tasks to identify key associations, a communication association topology network that is precisely adapted to communication tasks in high-risk environments can be formed, providing a clear and reliable infrastructure for subsequent risk prediction and network optimization.

[0114] Furthermore, step A200 in the method provided in the embodiment of the present application includes:

[0115] A240: Collect multimodal environment scene parameters of the communication task to obtain a communication environment scene dataset.

[0116] A250: Perform data cleaning on the communication environment scenario data set to generate the communication environment scenario stream.

[0117] In one embodiment, during high-risk environment operations, collecting multimodal environmental scenario parameters for communication tasks relies on various sensors and intelligent communication devices distributed throughout the work site. For example, temperature and humidity sensors are deployed to collect ambient temperature (-20°C to 80°C) and relative humidity (0 to 100% RH), with a sampling frequency of 10Hz, ensuring 10 sets of data per second. Electromagnetic spectrum monitoring equipment captures signal strength (-50dBm to -120dBm) and interference intensity (0 to 100% interference ratio) within the communication frequency band, while simultaneously recording the type of interference source. Sensors built into the intelligent communication devices collect information about their battery level (0% to 100%), operating temperature (-10°C to 60°C), and vibration frequency (0 to 50Hz). These parameters are aggregated via wireless transmission to form a communication environment scenario dataset containing timestamps, parameter types, values, and device identifiers.

[0118] After obtaining the communication environment scenario dataset, systematic data cleaning is required. First, the 3σ criterion is used to identify outliers. For example, if the temperature suddenly exceeds 80°C, which is outside the normal operating environment range, or if the signal strength momentarily jumps by more than 30dBm, such data will be marked and removed. Typically, the proportion of outliers can be kept below 2%. Missing values, such as 10 seconds of missing data caused by transmission interruptions, are filled using linear interpolation, generating continuous values ​​based on the valid data before and after the missing segment to ensure data integrity. Furthermore, parameters of different magnitudes are standardized. Physical parameters such as temperature and humidity, as well as communication parameters such as signal strength, are uniformly mapped to the 0-1 range to eliminate dimensional differences. For example, -20°C is mapped to 0 and 80°C to 1. This ensures a uniform dataset format and facilitates subsequent calculations.

[0119] The cleaned dataset is rearranged in time series to generate a communication environment scenario stream. This scenario stream retains the temporal characteristics of the parameters and continuously outputs them at a rate of 10 records per second. It includes dynamic changes in the physical state of the environment, electromagnetic interference conditions, and equipment operating parameters. For example, when simulating a leak in a chemical plant area, the scenario stream would show a continuous change in temperature from 25°C to 40°C, humidity from 60% to 30%, and signal interference intensity from 10% to 60%, fully reflecting the environmental evolution over time.

[0120] Through multimodal parameter collection, systematic data cleaning and timely integration, the generated communication environment scenario flow can accurately and continuously characterize the dynamic characteristics of high-risk environments, providing high-quality and highly reliable basic data support for subsequent communication task simulation response and risk prediction based on scenario flows.

[0121] In summary, the emergency response method for high-risk environment operations based on intelligent communication devices provided in the embodiments of the present application has the following technical effects:

[0122] This application obtains communication tasks at high-risk environment operation sites, constructs a communication association topology network, introduces a communication response risk analysis model to predict the communication response risk sequence, determines the communication optimization guidance characteristics through anomaly analysis and adjusts the network to establish the first communication configuration adjustment group, then optimizes the first group to generate the second group, and finally generates a strategy through global risk mutation optimization with a predetermined number of mutation rounds and executes the communication task, so as to accurately respond to the communication risks in high-risk environments, make the communication emergency response of high-risk environment operations more efficient and reliable, and achieve the technical effect of low-risk and efficient execution of communication tasks in high-risk environments.

[0123] Example 2, as Figure 2 As shown, based on the same inventive concept as the aforementioned embodiment 1, this embodiment of the present application provides an emergency response system for high-risk environment operations based on intelligent communication devices, the system comprising:

[0124] The communication association topology network construction module 1 is used to obtain the communication tasks of the high-risk environment operation site, and associate and sort the communication equipment set of the high-risk environment operation site according to the communication tasks to build a communication association topology network.

[0125] The communication response risk sequence acquisition module 2 is used to introduce a communication response risk analysis model, perform response risk prediction on the communication-related topology network in combination with the communication environment scenario flow, and determine a communication response risk sequence.

[0126] The communication configuration adjustment first group construction module 3 is used to perform abnormal analysis on the communication response risk sequence according to the communication response risk constraint, determine the communication optimization guidance characteristics, and adjust the communication association topology network according to the communication optimization guidance characteristics to establish the communication configuration adjustment first group.

[0127] The communication configuration adjustment second group acquisition module 4 is used to perform response risk optimization on the communication configuration adjustment first group according to the communication response risk analysis model and the communication response risk constraint to generate the communication configuration adjustment second group.

[0128] The communication task execution module 5 is used to perform communication global risk variation optimization on the second group of communication configuration adjustment according to a predetermined number of variation rounds, generate a communication configuration adjustment optimization strategy, and execute the communication task in combination with the communication association topology network.

[0129] Furthermore, the communication response risk sequence acquisition module 2 is configured to perform the following steps:

[0130] Based on the communication environment scenario flow, multiple simulated responses are performed on the communication task according to the communication association topology network to obtain multiple communication response simulation data; confidence fusion is performed on the multiple communication response simulation data to obtain confidence response simulation data; the confidence response simulation data is input into the communication response risk analysis model to obtain the communication response risk sequence, wherein the communication response risk analysis model includes multiple communication response risk indicators, and the multiple communication response risk indicators include communication quality risk, communication security risk and hardware reliability risk.

[0131] Furthermore, the communication configuration adjustment first group building module 3 is used to perform the following steps:

[0132] Anomaly detection is performed on the communication response risk sequence according to the communication response risk constraint to obtain response risk anomaly characteristics; accident tree learning is performed based on the communication risk anomaly event set to build a communication risk anomaly tracing tree; confidence response simulation data and the response risk anomaly characteristics are input into the communication risk anomaly tracing tree to obtain communication risk anomaly tracing results; communication tuning characteristics are analyzed according to the communication risk anomaly tracing results to generate the communication optimization guidance characteristics.

[0133] Furthermore, the communication configuration adjustment first group building module 3 is used to perform the following steps:

[0134] Perform top event feature identification based on the communication risk abnormal event set to obtain features of each abnormal top event; perform intermediate event tracing on the features of each abnormal top event based on the communication risk abnormal event set to obtain features of each abnormal intermediate event; perform basic event tracing on the features of each abnormal intermediate event based on the communication risk abnormal event set to obtain features of each abnormal basic event; construct multiple communication risk abnormality tracing paths based on the features of each abnormal top event, the features of each abnormal intermediate event and the features of each abnormal basic event; perform association detection based on the communication risk abnormal event set to determine a risk abnormality association feature set, and aggregate the multiple communication risk abnormality tracing paths based on the risk abnormality association feature set to generate the communication risk abnormality tracing tree.

[0135] Furthermore, the communication configuration adjusts the second group acquisition module 4 to perform the following steps:

[0136] A first communication configuration adjustment scheme is extracted according to the first communication configuration adjustment group, and the communication-associated topology network is fitted and optimized according to the first communication configuration adjustment scheme to obtain a first communication optimized network; based on the communication environment scenario flow, the response risk of the first communication optimized network is predicted according to the communication response risk analysis model to obtain a first scheme response risk sequence; if the first scheme response risk sequence meets the communication response risk constraint, the first communication configuration adjustment scheme is added to the second communication configuration adjustment group; if the first scheme response risk sequence does not meet the communication response risk constraint, the first communication configuration adjustment scheme is eliminated; according to the communication response risk analysis model and the communication response risk constraint, the response risk optimization of the first communication configuration adjustment group is continued to be performed to construct the second communication configuration adjustment group.

[0137] Furthermore, the communication task execution module 5 is configured to execute the following steps:

[0138] Based on the communication response risk multi-indicator weight allocation, a communication global risk assessment model is constructed; according to the communication global risk assessment model, the second group of communication configuration adjustments is mutated and optimized to generate a communication adjustment variation first optimization domain; according to the communication global risk assessment model, the first optimization domain of communication adjustment variations is mutated and optimized to generate a communication adjustment variation second optimization domain; according to the communication global risk assessment model, the second optimization domain of communication adjustment variations is continuously mutated and optimized until a communication adjustment variation P-th optimization domain that meets the predetermined number of mutation rounds is generated, where P is a positive integer greater than 2; according to the communication configuration adjustment second group, the communication adjustment variation first optimization domain, the communication adjustment variation second optimization domain...the communication adjustment variation P-th optimization domain, the communication configuration adjustment optimization strategy is obtained.

[0139] Furthermore, the communication task execution module 5 is configured to execute the following steps:

[0140] Perform communication global risk evaluation on each communication configuration adjustment scheme in the second communication configuration adjustment group according to the communication global risk evaluation model to obtain a communication global risk set; based on the mutation number constraint, allocate the number of mutation schemes to the second communication configuration adjustment group according to the communication global risk set to obtain the number of mutations of each scheme; mutate the second communication configuration adjustment group according to the number of mutations of each scheme to obtain a first communication adjustment mutation space; perform response risk optimization on the first communication adjustment mutation space according to the communication response risk analysis model and the communication response risk constraint to obtain the first optimization domain of communication adjustment mutation.

[0141] Furthermore, the communication association topology network construction module 1 is used to perform the following steps:

[0142] A communication device topology network is constructed based on the communication device set; and association identification is performed on the communication device topology network based on the communication task to generate the communication association topology network.

[0143] Furthermore, the communication response risk sequence acquisition module 2 is configured to perform the following steps:

[0144] The multimodal environment scene parameters of the communication task are collected to obtain a communication environment scene data set; and the communication environment scene data set is cleaned to generate the communication environment scene stream.

[0145] The high-risk environment operation emergency response system based on intelligent communication equipment provided in an embodiment of the present invention can execute the high-risk environment operation emergency response method based on intelligent communication equipment provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0146] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0147] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A high-risk environment operation emergency response method based on intelligent communication equipment, characterized in that: include: Obtaining communication tasks at a high-risk environment operation site, and correlating and sorting out a set of communication devices at the high-risk environment operation site according to the communication tasks to construct a communication correlation topology network; Introducing a communication response risk analysis model, combining the communication environment scenario flow to predict the response risk of the communication-related topology network, and determining the communication response risk sequence; performing anomaly analysis on the communication response risk sequence according to the communication response risk constraint, determining a communication optimization guidance feature, and adjusting the communication association topology network according to the communication optimization guidance feature to establish a first communication configuration adjustment group; Performing response risk optimization on the first communication configuration adjustment group according to the communication response risk analysis model and the communication response risk constraint to generate a second communication configuration adjustment group; Performing communication global risk mutation optimization on the second communication configuration adjustment group according to a predetermined number of mutation rounds, generating a communication configuration adjustment optimization strategy, and executing the communication task in combination with the communication association topology network; The step of performing response risk optimization on the first communication configuration adjustment group according to the communication response risk analysis model and the communication response risk constraint to generate the second communication configuration adjustment group includes: extracting a first communication configuration adjustment scheme according to the first communication configuration adjustment group, and performing fitting optimization on the communication-associated topology network according to the first communication configuration adjustment scheme to obtain a first communication-optimized network; Based on the communication environment scenario flow, predicting the response risk of the communication optimized first network according to the communication response risk analysis model to obtain a first solution response risk sequence; If the first scheme response risk sequence satisfies the communication response risk constraint, adding the first communication configuration adjustment scheme to the second communication configuration adjustment group; If the first scheme response risk sequence does not satisfy the communication response risk constraint, eliminating the first communication configuration adjustment scheme; The response risk optimization of the first communication configuration adjustment group is continued according to the communication response risk analysis model and the communication response risk constraint to construct the second communication configuration adjustment group.

2. The high-risk environment operation emergency response method based on intelligent communication equipment according to claim 1, characterized in that: A communication response risk analysis model is introduced to predict the response risk of the communication-related topology network in combination with the communication environment scenario flow, and a communication response risk sequence is determined, including: Based on the communication environment scenario flow, performing multiple simulated responses to the communication task according to the communication association topology network to obtain multiple communication response simulation data; Performing confidence fusion on the plurality of communication response simulation data to obtain confidence response simulation data; The confidence response simulation data is input into the communication response risk analysis model to obtain the communication response risk sequence. The communication response risk analysis model includes multiple communication response risk indicators, and the multiple communication response risk indicators include communication quality risk, communication security risk and hardware reliability risk.

3. The high-risk environment operation emergency response method based on intelligent communication equipment according to claim 1, characterized in that: Performing anomaly analysis on the communication response risk sequence according to the communication response risk constraint to determine a communication optimization guidance feature includes: performing anomaly detection on the communication response risk sequence according to the communication response risk constraint to obtain a response risk anomaly feature; Conduct accident tree learning based on the communication risk abnormal event set and build a communication risk abnormality tracing tree; Inputting the confidence response simulation data and the response risk anomaly characteristics into the communication risk anomaly tracing tree to obtain a communication risk anomaly tracing result; Communication optimization feature analysis is performed based on the communication risk anomaly tracing result to generate the communication optimization guidance feature.

4. The high-risk environment operation emergency response method based on intelligent communication equipment according to claim 3, characterized in that: Conduct accident tree learning based on the communication risk anomaly event set and build a communication risk anomaly tracing tree, including: Identify top event features based on the communication risk abnormal event set to obtain features of each abnormal top event; Performing intermediate event tracing on the features of each abnormal top event according to the communication risk abnormal event set to obtain features of each abnormal intermediate event; Perform basic event tracing on the features of each abnormal intermediate event according to the communication risk abnormal event set to obtain the features of each abnormal basic event; Constructing multiple communication risk anomaly tracing paths based on the characteristics of each abnormal top event, each abnormal intermediate event, and each abnormal basic event; An association detection is performed based on the communication risk anomaly event set to determine a risk anomaly association feature set, and the multiple communication risk anomaly tracing paths are aggregated based on the risk anomaly association feature set to generate the communication risk anomaly tracing tree.

5. The high-risk environment operation emergency response method based on intelligent communication equipment according to claim 1, characterized in that: Performing communication global risk mutation optimization on the communication configuration adjustment second group according to a predetermined number of mutation rounds to generate a communication configuration adjustment optimization strategy, including: Based on the weight allocation of multiple indicators of communication response risk, a global communication risk assessment model is constructed; Performing mutation optimization on the second group of communication configuration adjustments according to the communication global risk assessment model to generate a first optimization domain for communication adjustment mutations; Performing mutation optimization on the first optimization domain of communication regulation variation according to the communication global risk assessment model to generate a second optimization domain of communication regulation variation; Continuing to perform mutation optimization on the communication regulation mutation second optimization domain according to the communication global risk assessment model until a communication regulation mutation P-th optimization domain that satisfies the predetermined number of mutation rounds is generated, where P is a positive integer greater than 2; The communication configuration adjustment optimization strategy is obtained by performing communication global risk minimization optimization according to the communication configuration adjustment second group, the communication adjustment variation first optimization domain, the communication adjustment variation second optimization domain, and finally the communication adjustment variation Pth optimization domain.

6. The high-risk environment operation emergency response method based on intelligent communication equipment according to claim 5, characterized in that: Performing mutation optimization on the second group of communication configuration adjustments according to the communication global risk assessment model to generate a first optimization domain of communication adjustment mutations includes: Performing a communication global risk evaluation on each communication configuration adjustment scheme in the second communication configuration adjustment group according to the communication global risk evaluation model to obtain a communication global risk set; Based on the mutation number constraint, allocating the number of mutation schemes for the second group of communication configuration adjustments according to the communication global risk set to obtain the number of mutations for each scheme; mutating the second communication configuration adjustment group according to the number of variations of each scheme to obtain a first communication adjustment variation space; The communication regulation first variation space is optimized for response risk according to the communication response risk analytical model and the communication response risk constraint to obtain the communication regulation variation first optimization domain.

7. The high-risk environment operation emergency response method based on intelligent communication equipment according to claim 1, characterized in that: The communication equipment set at the high-risk environment operation site is associated and sorted according to the communication task to construct a communication association topology network, including: constructing a communication device topology network based on the communication device set; The communication device topology network is associated and identified according to the communication task to generate the communication association topology network.

8. The high-risk environment operation emergency response method based on intelligent communication equipment according to claim 1, characterized in that: The method comprises: Collecting multimodal environment scene parameters of the communication task to obtain a communication environment scene data set; The communication environment scenario data set is cleaned to generate the communication environment scenario stream.

9. The high-risk environment operation emergency response system based on intelligent communication equipment is characterized by: The system is used to implement the high-risk environment operation emergency response method based on intelligent communication equipment according to any one of claims 1 to 8, comprising: A communication association topology network construction module is used to obtain communication tasks at a high-risk environment operation site, and to associate and sort out the communication equipment set at the high-risk environment operation site according to the communication tasks to construct a communication association topology network; A communication response risk sequence acquisition module is used to introduce a communication response risk analysis model, perform response risk prediction on the communication-related topology network in combination with the communication environment scenario flow, and determine a communication response risk sequence; a communication configuration adjustment first group building module, configured to perform anomaly analysis on the communication response risk sequence according to the communication response risk constraint, determine communication optimization guidance characteristics, adjust the communication association topology network according to the communication optimization guidance characteristics, and establish a communication configuration adjustment first group; a communication configuration adjustment second group acquisition module, configured to perform response risk optimization on the communication configuration adjustment first group according to the communication response risk analysis model and the communication response risk constraint, and generate a communication configuration adjustment second group; The communication task execution module is used to perform communication global risk mutation optimization on the communication configuration adjustment second group according to a predetermined number of mutation rounds, generate a communication configuration adjustment optimization strategy, and execute the communication task in combination with the communication association topology network.

Images