A Walkie-Talkie-Assisted Rescue Method and System Based on Fall Detection in Rescue Scenarios

Abstract

The present invention discloses an intercom-assisted rescue method and system based on fall detection in a rescue scenario, including: acquiring rescue status collection information and performing preprocessing, and constructing an operating environment data sequence, a communication status data sequence, and a motion status data sequence; constructing an anomaly detection model, inputting the motion status data sequence to analyze abnormal motion status data in real-time rescue tasks; performing fall detection on the target intercom user to determine whether there is a fall condition; if there is a fall condition, then combining the fall warning information to perform a fall risk assessment to determine whether collaborative rescue is required; if collaborative rescue is required, then search for the intercoms of other rescuers in the current communication environment for collaborative rescue, and perform communication optimization in combination with the operating environment data sequence and the communication status data sequence to expand the communication range. Thereby avoiding safety accidents caused by rescue personnel being unable to carry out independent rescue in case of emergencies during rescue operations.

Description

Technical Field

[0001] The present invention relates to the technical field of walkie - talkie assisted rescue, and particularly to a walkie - talkie assisted rescue method and system based on fall detection in a rescue scenario. Background Art

[0002] In outdoor rescue, industrial operations, and high - risk environments, the frequency of practitioners and individuals using walkie - talkies has gradually increased, relying on their convenient voice communication function to transmit important information in a timely manner. However, in these scenarios, the possibility of personnel accidentally falling or losing their ability to move is relatively high, especially in complex terrains or extreme environments. When a fall occurs, if help cannot be requested in a timely manner, it may lead to danger for rescue personnel and thus cause serious consequences. When the user is in a fallen state and the ability to seek help is limited, traditional communication devices cannot efficiently locate and identify risks for autonomous help - seeking. This problem of communication isolation is widespread in practical applications and poses a potential threat to the safety of rescue personnel. Therefore, how to improve the safety and searchability of rescue personnel during rescue operations is an urgent problem to be solved. Summary of the Invention

[0003] The present invention overcomes the defects of the prior art and provides a walkie - talkie assisted rescue method and system based on fall detection in a rescue scenario, and its important purpose is to improve the safety and searchability of rescue personnel during rescue operations.

[0004] To achieve the above object, the first aspect of the present invention provides a walkie - talkie assisted rescue method based on fall detection in a rescue scenario, including:

[0005] Collect rescue status data for real - time rescue tasks to obtain rescue status collection information and perform pre - processing, time - series the pre - processed data, and construct an operating environment data sequence, a communication status data sequence, and a motion status data sequence;

[0006] Construct an anomaly detection model based on a generative adversarial network, input the motion status data sequence to analyze abnormal motion status data in real - time rescue tasks, and obtain abnormal motion status analysis information;

[0007] Based on the abnormal motion status analysis information, perform fall detection on the target walkie - talkie user, judge whether there is a fall condition, and generate a fall warning information;

[0008] If it is detected that the current walkie - talkie user has a fall condition, then combine the fall warning information to perform a fall risk assessment and judge whether collaborative rescue is required;

[0009] If collaborative rescue is required, search for the walkie-talkies of other rescuers in the current communication environment for collaborative rescue, and optimize communication by combining the running environment data sequence and the communication status data sequence to expand the communication range.

[0010] In this solution, the rescue status data of the real-time rescue task is collected to obtain the rescue status collection information and preprocessed. The preprocessed data is sequenced to construct a running environment data sequence, a communication status data sequence, and a motion status data sequence, specifically including:

[0011] Collect the rescue status data of the real-time rescue task based on the sensor array set by the target walkie-talkie to obtain the rescue status collection information, where the rescue status collection information includes the walkie-talkie running environment data, the walkie-talkie communication status data, and the walkie-talkie motion status data;

[0012] Preprocess the rescue status collection information, calculate the data standard deviation of the rescue status collection information, and judge the calculated data standard deviation with the preset standard deviation range;

[0013] Define the rescue status collection data corresponding to the data standard deviation outside the preset standard deviation range as abnormal data, perform outlier removal and introduce the linear interpolation method for difference supplementation to obtain the preprocessing result information;

[0014] Extract the time series features based on the preprocessing result information, and perform time series processing on the preprocessing result information according to the extracted time series features to generate a running environment data sequence, a communication status data sequence, and a motion status data sequence.

[0015] In this solution, an anomaly detection model is constructed based on the generative adversarial network, and the motion status data sequence is input to analyze the abnormal motion status data in the real-time rescue task to obtain the abnormal motion status analysis information, specifically including:

[0016] Construct an anomaly detection model based on the generative adversarial network, obtain the motion status data sequence, use the motion status data sequence as the original sequence, and input it into the anomaly detection model for analysis;

[0017] The generator extracts the features of the input motion status data sequence, reconstructs the sequence according to the extracted real-time walkie-talkie motion status features to generate a reconstructed motion status sequence, and inputs the reconstructed motion status sequence into the discriminator for judgment;

[0018] The discriminator judges whether it can structure the current reconstructed motion status sequence. If the discriminator's discrimination result for the current reconstructed motion status sequence is not accepted, mark the current reconstructed motion status sequence as an incorrect reconstructed motion status sequence, and obtain the next reconstructed motion status sequence for judgment;

[0019] Iteratively repeat the discriminator to generate a reconstructed motion state sequence, and select a reconstructed motion state sequence that meets the preset acceptance criteria to obtain the final reconstructed motion state sequence;

[0020] Calculate the reconstruction error between the final reconstructed motion state sequence and the original sequence, and compare the calculated reconstruction error with a preset threshold. If it is greater than the preset threshold, it means that the current real-time motion condition is abnormal;

[0021] Perform temporal alignment on the final reconstructed motion state sequence and the original sequence, analyze the matching differences between the reconstructed motion state sequence and the original sequence, and determine abnormal motion state data and time nodes through the matching differences to obtain abnormal motion state analysis information.

[0022] In this solution, based on the abnormal motion state analysis information, perform fall detection on the target walkie-talkie user to determine whether there is a fall condition, specifically including:

[0023] Obtain the abnormal motion state analysis information, extract features from the abnormal motion state analysis information, extract the time features of the abnormal motion state, and mark them in the running state data sequence through the extracted time features of the abnormal motion state;

[0024] Intercept a motion state data sequence of a preset time length according to the marked motion state data sequence to obtain a number of motion state data subsequences, and introduce the sliding window method for fall detection;

[0025] Slide the window on the motion state data subsequence according to the preset sliding window size, extract the motion state data features in each window to obtain the first feature extraction information;

[0026] Preset a fall determination rule, and compare the first feature extraction information with the fall determination rule. If the features extracted in the current window meet the fall determination rule, the current window is determined as a potential fall event window;

[0027] Analyze whether the motion state features in the next window of the potential fall event window meet the fall determination rule. If they also meet, mark the corresponding window as a potential fall event window;

[0028] Perform iterative sliding analysis and fall determination until all motion state data subsequences are detected, and output all potential fall event windows and their time positions in the current motion state subsequence to obtain potential fall event window detection information;

[0029] Analyze whether there are consecutive potential fall event windows based on the detected information of potential fall event windows. If there are consecutive fall event windows and the number is greater than the preset quantity threshold, mark the potential fall event window with the earliest time feature as the starting point of the fall, and generate a fall warning message.

[0030] In this solution, if it is detected that the current walkie-talkie user has fallen, combine the fall warning message to conduct a fall risk assessment to determine whether collaborative rescue is needed. Specifically, it includes:

[0031] Obtain the operating environment data sequence and the fall warning message, use the fall warning message to extract the sub-sequence of motion state data when the fall occurs, and determine the time node when the walkie-talkie user falls according to the fall warning message, and intercept the sub-sequence of operating environment data after the corresponding time node from the obtained operating environment data sequence;

[0032] Extract features from the sub-sequence of motion state data to obtain the motion state features of the walkie-talkie after the fall occurs. Calculate the impact intensity and the amplitude of posture change based on the extracted operating state features, and generate the first analysis information;

[0033] Construct a three-dimensional coordinate system, extract features based on the intercepted sub-sequence of operating environment data, obtain the change features of the operating environment of the walkie-talkie after the fall occurs, and conduct a fall condition analysis;

[0034] Represent the obtained change features of the operating environment using the constructed three-dimensional coordinate system to generate a three-dimensional coordinate change diagram of the walkie-talkie user after the fall occurs. Analyze the fall direction, fall distance, and fall position of the walkie-talkie user based on the three-dimensional coordinate change diagram to obtain the second analysis information;

[0035] Construct a risk assessment model, input the first analysis information and the second analysis information into the model for analysis, judge the real-time fall risk of the walkie-talkie user, and obtain the fall risk assessment information;

[0036] Preset a risk rescue threshold, judge the fall risk assessment information and the risk rescue threshold. If it is greater than the preset threshold, it means that the current walkie-talkie user needs collaborative rescue.

[0037] In this solution, if collaborative rescue is needed, search for the walkie-talkies of other rescuers in the current communication environment for collaborative rescue, and combine the operating environment data sequence and the communication status data sequence to optimize communication to expand the communication range. Specifically, it includes:

[0038] Obtain the walkie-talkie operating environment data sequence and the walkie-talkie communication status data sequence, and extract the spatial position features of the walkie-talkie before the time node when the target person falls based on the walkie-talkie operating environment data sequence;

[0039] Perform three-dimensional coordinate transformation on the extracted spatial location features of the walkie-talkie and associate them with the corresponding time features; perform redundancy removal on the associated three-dimensional coordinates and generate the movement trajectory data of the target walkie-talkie user according to the time change features;

[0040] Generate cooperative rescue information based on the movement trajectory data of the target walkie-talkie user, search for the walkie-talkies of other rescuers in the current communication environment for cooperative rescue, and if no other rescuers can be found in the current environment, perform communication optimization to expand the autonomous search range;

[0041] Obtain the specification information of the target walkie-talkie, extract the communication status features of the target walkie-talkie based on the communication status data sequence of the walkie-talkie, and calculate the current communication frequency of the target walkie-talkie according to the extracted communication status features;

[0042] Extract the maximum communication frequency feature through the specification information of the target walkie-talkie, generate a limit interval in combination with the current communication frequency, introduce an improved sparrow algorithm for communication frequency optimization, perform population initialization and construct constraint conditions through the limit interval;

[0043] Calculate the fitness of the sparrow individuals in the initial population, select the corresponding number of sparrow individuals as discoverers according to the discoverer ratio based on the fitness ranking, and use the remaining sparrow individuals as joiners for position update;

[0044] Randomly select guards from the sparrow individuals according to the guard ratio and perform position update, calculate the fitness of each updated sparrow individual, introduce the golden sine algorithm in the position update to guide the sparrow individuals to update to new positions, and output the optimized control parameters by repeatedly iterating to update the optimal position of the sparrows;

[0045] Generate a control command based on the optimized control parameter to regulate the communication frequency of the target walkie-talkie to expand the communication range.

[0046] The second aspect of the present invention provides a walkie-talkie-assisted rescue system based on fall detection in a rescue scenario. The system includes: a memory and a processor. The memory contains a program for the walkie-talkie-assisted rescue method based on fall detection in a rescue scenario. When the program for the walkie-talkie-assisted rescue method based on fall detection in a rescue scenario is executed by the processor, the following steps are implemented:

[0047] Collect rescue status data for real-time rescue tasks to obtain rescue status collection information and perform preprocessing. Temporalize the preprocessed data to construct a running environment data sequence, a communication status data sequence, and a motion status data sequence;

[0048] Construct an anomaly detection model based on a generative adversarial network, input the motion state data sequence to analyze the abnormal motion state data in the real-time rescue task, and obtain the abnormal motion state analysis information;

[0049] Based on the abnormal motion state analysis information, perform a fall detection on the target walkie-talkie user, determine whether there is a fall condition, and generate a fall warning information;

[0050] If it is detected that the current walkie-talkie user has a fall condition, then combine the fall warning information to perform a fall risk assessment to determine whether collaborative rescue is required;

[0051] If collaborative rescue is required, search for the walkie-talkies of other rescuers in the current communication environment for collaborative rescue, and combine the operation environment data sequence and the communication status data sequence to optimize communication to expand the communication range.

[0052] The present invention discloses a walkie-talkie-assisted rescue method and system based on fall detection in a rescue scenario, including: obtaining rescue status collection information and performing preprocessing, and constructing an operation environment data sequence, a communication status data sequence, and a motion state data sequence; constructing an anomaly detection model, inputting the motion state data sequence to analyze the abnormal motion state data in the real-time rescue task; performing a fall detection on the target walkie-talkie user to determine whether there is a fall condition; if there is a fall condition, then combine the fall warning information to perform a fall risk assessment to determine whether collaborative rescue is required; if collaborative rescue is required, search for the walkie-talkies of other rescuers in the current communication environment for collaborative rescue, and combine the operation environment data sequence and the communication status data sequence to optimize communication to expand the communication range. Thereby, it is possible to avoid safety accidents caused by the inability of rescue personnel to seek help autonomously in case of emergencies during rescue operations, and improve the safety and searchability of rescue personnel during rescue tasks. Description of the Drawings

[0053] In order to more clearly illustrate the technical solutions in the embodiments or exemplary examples of the present invention, the following will briefly introduce the drawings required for use in the embodiments or exemplary descriptions. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the drawings shown.

[0054] Figure 1 It is a flowchart of a walkie-talkie-assisted rescue method based on fall detection in a rescue scenario provided by an embodiment of the present invention;

[0055] Figure 2 It is a flowchart of a walkie-talkie autonomous rescue method provided by an embodiment of the present invention;

[0056] Figure 3 Block diagram of an intercom-assisted rescue system based on fall detection in a rescue scenario provided by an embodiment of the present invention;

[0057] The realization, functional characteristics, and advantages of the objectives of the present invention will be further described in conjunction with the embodiments and with reference to the accompanying drawings. Specific embodiments

[0058] In order to more clearly understand the above objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.

[0059] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention may be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0060] Figure 1 Flowchart of an intercom-assisted rescue method based on fall detection in a rescue scenario provided by an embodiment of the present invention;

[0061] As Figure 1 shown, the present invention provides a flowchart of an intercom-assisted rescue method based on fall detection in a rescue scenario, including:

[0062] S102, collect rescue status data for the real-time rescue task to obtain rescue status collection information and perform preprocessing, sequence the preprocessed data, and construct an operating environment data sequence, a communication status data sequence, and a motion status data sequence;

[0063] S104, construct an anomaly detection model based on a generative adversarial network, input the motion status data sequence to analyze abnormal motion status data in the real-time rescue task, and obtain abnormal motion status analysis information;

[0064] S106, perform fall detection on the target intercom user based on the abnormal motion status analysis information, determine whether there is a fall condition, and generate a fall warning information;

[0065] S108, if it is detected that the current intercom user has a fall condition, then perform a fall risk assessment in combination with the fall warning information to determine whether collaborative rescue is required;

[0066] S110, if collaborative rescue is required, search for the intercoms of other rescuers in the current communication environment for collaborative rescue, and perform communication optimization in combination with the operating environment data sequence and the communication status data sequence to expand the communication range.

[0067] It should be noted that a walkie-talkie-assisted rescue method and system based on fall detection in a rescue scenario are mainly applied to the detection of abnormal motion states, fall risk assessment, and implementation of collaborative rescue in real-time rescue tasks, aiming to improve rescue efficiency and reliability through data collection and analysis techniques. First, various state data during the rescue process are collected, including the operating environment, communication status, and the motion state of the user, forming multi-dimensional data available for subsequent analysis. Then, three key time-series data sequences are constructed, namely the operating environment data sequence, the communication status data sequence, and the motion state data sequence, laying the foundation for subsequent analysis. In the anomaly detection stage, a generative adversarial network (GAN) model is used to process the motion state data sequence. Through the adversarial training of the generator and discriminator, GAN can model the latent distribution of the input data and efficiently identify abnormal data. The motion state of the walkie-talkie user in the rescue task is analyzed in real-time, capturing abnormal motion patterns that may be related to falls, and generating abnormal motion state analysis information. Based on the abnormal motion state analysis information, a sliding window method is introduced to detect whether the walkie-talkie user has fallen. Once it is determined that a fall has occurred, a risk assessment is further carried out based on the fall warning information, comprehensively analyzing the severity of the fall, the impact of the surrounding environment, and the rescue time requirement to determine whether to initiate the collaborative rescue mode. If it is determined that collaborative rescue is required, the walkie-talkie devices of other rescuers are actively searched in the current communication environment, and a communication link is automatically established. At the same time, combined with the operating environment data sequence and the communication status data sequence, the communication process is optimized to expand the communication range and improve communication stability, thereby improving the efficiency and effectiveness of collaborative rescue and enhancing the safety of rescuers in the event of a fall accident.

[0068] Further, in a preferred embodiment of the present invention, the rescue state data of the real-time rescue task is collected to obtain rescue state collection information and preprocessed, and the preprocessed data is time-seriesized to construct an operating environment data sequence, a communication state data sequence, and a motion state data sequence, which specifically includes:

[0069] The rescue state data of the real-time rescue task is collected based on the sensor array set by the target walkie-talkie to obtain rescue state collection information, and the rescue state collection information includes walkie-talkie operating environment data, walkie-talkie communication status data, and walkie-talkie motion state data;

[0070] The rescue state collection information is preprocessed, the standard deviation of the data of the rescue state collection information is calculated, and the calculated standard deviation of the data is judged against a preset standard deviation range;

[0071] Define the data standard deviation corresponding to the rescue status acquisition data outside the preset standard deviation range as abnormal data, perform outlier removal and introduce linear interpolation method for difference supplementation to obtain the preprocessing result information;

[0072] Extract temporal features based on the preprocessing result information, and perform temporal processing on the preprocessing result information according to the extracted temporal features to generate an operating environment data sequence, a communication status data sequence, and a motion status data sequence.

[0073] It should be noted that the collected information covers three main aspects: the operating environment data, communication status data, and motion status data of the walkie-talkie. These data reflect the physical state of the environment where the walkie-talkie is currently located, the communication quality with other devices, and the motion state of the walkie-talkie itself, providing a basis for subsequent intelligent analysis. After completing the preliminary data collection, a data preprocessing stage is carried out on the rescue status acquisition information to improve the effectiveness and consistency of the data, thereby enhancing the accuracy and robustness of the analysis. After completing the preprocessing, temporal features are further extracted. Identify potential patterns in the data that change over time, capture important information that can reflect the dynamic change law, and perform temporalization to generate an operating environment data sequence, a communication status data sequence, and a motion status data sequence respectively. It reflects the change law of data in different dimensions over time, providing a more organized and logical infrastructure for subsequent in-depth analysis.

[0074] Furthermore, in a preferred embodiment of the present invention, the anomaly detection model is constructed based on a generative adversarial network, and the motion status data sequence is input to analyze the abnormal motion status data in the real-time rescue task to obtain abnormal motion status analysis information, specifically including:

[0075] Construct an anomaly detection model based on a generative adversarial network, obtain the motion status data sequence, take the motion status data sequence as the original sequence, and input it into the anomaly detection model for analysis;

[0076] The generator extracts features from the input motion status data sequence, reconstructs the sequence according to the extracted real-time walkie-talkie motion status features to generate a reconstructed motion status sequence, and inputs the reconstructed motion status sequence into the discriminator for judgment;

[0077] Judge whether the current reconstructed motion status sequence can be structured through the discriminator. If the discriminator's discrimination result for the current reconstructed motion status sequence is not accepted, mark the current reconstructed motion status sequence as an incorrect reconstructed motion status sequence, and obtain the next reconstructed motion status sequence for judgment;

[0078] Select the reconstructed motion status sequence that meets the preset acceptance standard by iteratively repeating the reconstructed motion status sequence generated by the discriminator-generator to obtain the final reconstructed motion status sequence;

[0079] Calculate the reconstruction error between the final reconstructed motion state sequence and the original sequence, and compare the calculated reconstruction error with a preset threshold. If it is greater than the preset threshold, it indicates that there is an abnormality in the current real-time motion condition;

[0080] Perform temporal alignment on the final reconstructed motion state sequence and the original sequence, analyze the matching differences between the reconstructed motion state sequence and the original sequence, and determine abnormal motion state data and time nodes through the matching differences to obtain abnormal motion state analysis information.

[0081] It should be noted that an anomaly detection model is constructed using a generative adversarial network (GAN). Through the analysis of the motion state data sequence, accurate identification of abnormal motion states is achieved. First, the collected motion state data sequence is used as the original sequence and input into the anomaly detection model for processing. During the operation of the generative adversarial network, the generator reconstructs the sequence based on the real-time walkie-talkie motion state characteristics to generate a reconstructed motion state sequence. Subsequently, it will be sent to the discriminator to receive its judgment and evaluation of the reconstruction result. In the discrimination stage, the role of the discriminator is to analyze the reconstructed sequence generated by the generator and determine whether the sequence meets the structural expectations. If the discriminator's evaluation result for the current reconstructed sequence is "not accepted", this indicates that the output of the generator does not meet the established standard. Therefore, the reconstructed sequence is marked as an incorrect reconstructed motion state sequence and enters the next generation-discrimination cycle until a reconstructed motion state sequence that meets the preset acceptance standard is selected. Through the adversarial training of the generator and the discriminator, the accuracy and reliability of the reconstructed sequence are continuously improved. After obtaining the final reconstructed motion state sequence, calculate the reconstruction error between this reconstructed sequence and the original sequence to evaluate the degree to which the generator restores the original data features. If the reconstruction error value exceeds the preset threshold range, it indicates that there is an abnormality in the current motion state. Perform temporal alignment on the final reconstructed motion state sequence and the original sequence, and analyze the matching differences between the reconstructed sequence and the original sequence. Further locate the abnormal data points and their corresponding time nodes, thereby realizing the precise analysis of abnormal motion states. Finally, output the abnormal motion state analysis information, providing important data support for subsequent fall detection and rescue decisions.

[0082] Furthermore, in a preferred embodiment of the present invention, the fall detection is performed on the target walkie-talkie user based on the abnormal motion state analysis information to determine whether there is a fall condition, specifically including:

[0083] Obtain the abnormal motion state analysis information, extract features from the abnormal motion state analysis information, extract the time features of the abnormal motion state, and mark them in the operation state data sequence through the extracted time features of the abnormal motion state;

[0084] Intercept the motion state data sequence with a preset time length according to the marked motion state data sequence to obtain several motion state data subsequences, and introduce the sliding window method for fall detection;

[0085] Slide the window on the motion state data subsequence according to the preset sliding window size, extract the motion state data features in each window, and obtain the first feature extraction information;

[0086] Preset the fall determination rule, and judge the first feature extraction information and the fall determination rule. If the features extracted in the current window meet the fall determination rule, the current window is judged as a potential fall event window;

[0087] Analyze whether the motion state features in the next window of the potential fall event window meet the fall determination rule. If they also meet, mark the corresponding window as a potential fall event window;

[0088] Perform iterative sliding analysis and fall determination until all motion state data subsequences are detected, and output all potential fall event windows and their time positions in the current motion state subsequence to obtain the potential fall event window detection information;

[0089] Analyze whether there are continuous potential fall event windows according to the potential fall event window detection information. If there are continuous fall event windows and the number is greater than the preset quantity threshold, mark the potential fall event window with the earliest time feature as the fall starting point and generate a fall warning information.

[0090] It should be noted that, first, key features are extracted from the abnormal motion state analysis information, especially the time features of the abnormal motion state, to clarify the time points related to the abnormality. According to the marked motion state data sequence, the sequence is divided into several motion state data subsequences with a preset time length. The sliding window method is introduced to gradually slide on each motion state data subsequence according to the preset sliding window size, and the features of the motion state data extracted in each window are analyzed. The extracted features include various motion parameters such as speed, acceleration, and attitude change, so as to comprehensively reflect the motion state during this time period. Subsequently, the preset fall determination rule is used to judge the features extracted from each window. If the features in the window meet the fall determination rule, the window is marked as a potential fall event window, indicating that a fall may have occurred during this time period. For each potential fall event window, the motion state features in its subsequent windows are further analyzed. If the features of the subsequent windows also meet the fall determination rule, the window is also marked as a potential fall event window. The iteration sliding method is used to expand within the entire subsequence range until all windows are detected. The output is all potential fall event windows and their corresponding time positions in the current subsequence, forming the potential fall event window detection information. Finally, based on the potential fall event window detection information, it is analyzed whether there are consecutive potential fall event windows. If the number of consecutive windows exceeds the preset threshold, this abnormality may be a fall event. At this time, the potential fall event window with the earliest time feature is marked as the fall starting point, and a fall warning information is generated.

[0091] It should be noted that the setting of the fall judgment rule includes the peak acceleration, attitude angle change, acceleration change rate, etc. By setting the corresponding thresholds, it is judged whether there is a fall condition.

[0092] Furthermore, in a preferred embodiment of the present invention, if it is detected that the current walkie-talkie user is in a fall condition, the fall risk assessment is combined with the fall warning information to judge whether collaborative rescue is needed, specifically including:

[0093] Obtain the operating environment data sequence and the fall warning information, use the fall warning information to extract the motion state data subsequence when the fall condition occurs, and intercept the operating environment data subsequence after the corresponding time node from the obtained operating environment data sequence according to the fall warning information to determine the time node when the walkie-talkie user falls;

[0094] Extract the features of the motion state data subsequence to obtain the motion state features of the walkie-talkie after the fall condition occurs, calculate the impact intensity and the attitude change amplitude based on the extracted operating state features, and generate the first analysis information;

[0095] Construct a three-dimensional coordinate system, extract features based on the intercepted subsequence of the operating environment data, obtain the characteristics of the change in the operating environment of the walkie-talkie after a fall occurs, and conduct a fall condition analysis;

[0096] Represent the obtained characteristics of the change in the operating environment using the constructed three-dimensional coordinate system, generate a three-dimensional coordinate change diagram of the walkie-talkie user after a fall occurs, and analyze the fall direction, fall distance, and fall position of the walkie-talkie user based on the three-dimensional coordinate change diagram to obtain the second analysis information;

[0097] Construct a risk assessment model, input the first analysis information and the second analysis information into the model for analysis, judge the real-time fall risk of the walkie-talkie user, and obtain the fall risk assessment information;

[0098] Preset a risk rescue threshold, judge the fall risk assessment information against the risk rescue threshold. If it is greater than the preset threshold, it means that the current walkie-talkie user needs to be rescued collaboratively.

[0099] It should be noted that first, locate the time node when the walkie-talkie user falls through the fall warning information, and extract the corresponding subsequence of the motion state data from it. These subsequences comprehensively display the detailed motion characteristics of the user during the fall. At the same time, intercept the subsequence of the environmental data corresponding to the fall time node from the obtained operating environment data sequence. This part of the data reflects the dynamic changes in the environment where the user is located after the fall. Extract features from the extracted subsequence of the motion state data, calculate the impact intensity and the amplitude of the posture change during the user's fall based on the extracted features, and generate the first analysis information related to the motion state. These data are important parameters for measuring the severity of the fall. The measurement of the impact intensity can reflect the force when the user falls, and the amplitude of the posture change can provide the posture change during the fall. Furthermore, extract features from the subsequence of the operating environment data, and construct a three-dimensional coordinate system to represent the characteristics of the change in the operating environment after the user falls. By visualizing these environmental change characteristics in the three-dimensional coordinate system, generate a three-dimensional coordinate change diagram of the fall condition of the walkie-talkie user. The three-dimensional change diagram provides information in the spatial dimension, including the fall direction, distance, and specific position. Generate the second analysis information related to the environmental change through these indicators. Input the first analysis information and the second analysis information into the risk assessment model for calculation. Accurately assess the real-time fall risk of the user to obtain the fall risk assessment information. Compare it with the preset risk rescue threshold. If the risk assessment result exceeds the threshold, it indicates that the situation of the user needs to be taken seriously and may require timely collaborative rescue. This ensures that in a real rescue scenario, the severity of the fall event can be quickly and accurately judged, providing a basis for timely ensuring the safety of rescue personnel.

[0100] Further, in a preferred embodiment of the present invention, if collaborative rescue is required, search for the walkie-talkies of other rescuers in the current communication environment for collaborative rescue, and optimize communication by combining the operating environment data sequence and the communication status data sequence to expand the communication range. Specifically, it includes:

[0101] Obtain the walkie-talkie operating environment data sequence and the walkie-talkie communication status data sequence, and extract the walkie-talkie spatial position characteristics before the time node when the target person falls based on the walkie-talkie operating environment data sequence;

[0102] Perform three-dimensional coordinate transformation on the extracted walkie-talkie spatial position characteristics and associate them with the corresponding time characteristics; perform redundancy removal on the associated three-dimensional coordinates and generate the movement trajectory data of the target walkie-talkie user according to the time change characteristics;

[0103] Generate collaborative rescue information based on the movement trajectory data of the target walkie-talkie user, search for the walkie-talkies of other rescuers in the current communication environment for collaborative rescue. If no other rescuers can be found in the current environment, perform communication optimization to expand the autonomous search range;

[0104] Obtain the specification information of the target walkie-talkie, extract the communication status characteristics of the target walkie-talkie based on the walkie-talkie communication status data sequence, and calculate the current communication frequency of the target walkie-talkie according to the extracted communication status characteristics;

[0105] Extract the maximum communication frequency characteristics through the specification information of the target walkie-talkie, generate a limit interval in combination with the current communication frequency, introduce an improved sparrow algorithm for communication frequency optimization, perform population initialization and construct constraint conditions through the limit interval;

[0106] Calculate the fitness of the sparrow individuals in the initial population, select the corresponding number of sparrow individuals as discoverers according to the discoverer ratio based on the fitness ranking, and use the remaining sparrow individuals as joiners for position update;

[0107] Randomly select guardians from the sparrow individuals according to the guardian ratio and perform position update. Calculate the fitness of each updated sparrow individual, introduce the golden sine algorithm in the position update to guide the sparrow individuals to update to new positions, and output the optimized control parameters by repeatedly iterating to update the optimal position of the sparrows;

[0108] Generate a control command based on the optimized control parameters to regulate the communication frequency of the target walkie-talkie to expand the communication range.

[0109] It should be noted that based on the operating environment data sequence of the target walkie-talkie, the spatial position characteristics of the target person before falling are extracted, and the dynamic behavior of the walkie-talkie in space is characterized by the position characteristics. Subsequently, the spatial position characteristics are converted into three-dimensional coordinates, and correlated with time characteristics to form three-dimensional coordinate data with a time dimension. Redundancy removal is performed on the correlated three-dimensional coordinates, and the movement trajectory data of the target walkie-talkie user is generated based on the time change characteristics. These trajectory data can clearly display the movement path of the walkie-talkie, providing an important reference for rescue operations. In the current communication environment, the system will attempt to search for the walkie-talkies of other rescuers to achieve coordinated rescue. If other rescue devices cannot be successfully searched for in the current communication environment, communication optimization will be automatically performed to expand the search range to ensure the effectiveness of the coordinated rescue operation. Further, using the specification information and communication status data sequence of the walkie-talkie, the communication status characteristics of the target walkie-talkie are extracted, and its current communication frequency is calculated based on this. On this basis, the maximum communication frequency characteristics are extracted through the specification information, and a restricted interval is defined in combination with the current communication frequency. The communication frequency is optimized by an improved sparrow algorithm. During the population initialization process, constraint conditions are constructed based on the restricted interval to ensure that the optimization process is always within the feasible range. In the sparrow algorithm optimization stage, the fitness of the sparrow individuals in the initial population is calculated, and the best-performing part of the individuals is selected as discoverers according to the fitness ranking, and the remaining individuals are classified as joiners. The discoverers are responsible for exploring the global optimal solution, and the joiners conduct refined searches in a more local range. In addition, a certain proportion of the individuals are selected as vigilant individuals, and the vigilant individuals enhance the global search ability of the algorithm by introducing a special update mechanism. To improve the convergence effect and accuracy, the golden sine algorithm is used to guide the migration behavior of the sparrow individuals during the position update process, and the optimal position is continuously searched for through iterative optimization. Finally, the optimized control parameters are output, and a regulation instruction is generated to perform real-time regulation on the communication frequency of the target walkie-talkie, so as to effectively expand the communication range. It can not only improve the safety of the fallen rescuer, but also improve the communication effect in a complex environment, providing guarantee for the execution of rescue tasks.

[0110] It should be noted that the position update calculation process is as follows:

[0111] ;

[0112] Among them, represents the position of the th sparrow individual on the th and th iterations in the th dimension, represents a random number, which determines the moving distance and direction of the sparrow individual, represents the global optimal position at the th iteration, Indicates the position update parameter combined with the golden ratio coefficient, where the golden ratio coefficient is taken as The search space is reduced by the position update parameter combined with the golden ratio coefficient, guiding the sparrow individuals to move towards the optimal position.

[0113] Figure 2 It is the flow chart of the walkie-talkie autonomous rescue method provided by an embodiment of the present invention;

[0114] As Figure 2 shown, the present invention provides a flow chart of a walkie-talkie autonomous rescue method, including:

[0115] S202, obtaining the walkie-talkie operating environment data sequence and the walkie-talkie communication status data sequence, and extracting the walkie-talkie spatial position characteristics before the time node when the target person falls based on the walkie-talkie operating environment data sequence;

[0116] S204, performing three-dimensional coordinate conversion on the extracted walkie-talkie spatial position characteristics and associating them with the corresponding time characteristics, performing redundancy removal on the associated three-dimensional coordinates, and generating the movement trajectory data of the target walkie-talkie user according to the time change characteristics;

[0117] S206, generating cooperative rescue information according to the movement trajectory data of the target walkie-talkie user, searching for the walkie-talkies of other rescuers in the current communication environment for cooperative rescue, and if no other rescuers can be found in the current environment, performing communication optimization to expand the autonomous search range;

[0118] S208, extracting the communication status characteristics of the target walkie-talkie through the walkie-talkie communication status data sequence, calculating the current communication frequency of the target walkie-talkie, and generating a limit interval by combining the maximum communication frequency characteristics extracted from the target walkie-talkie;

[0119] S210, introducing an improved sparrow algorithm for communication frequency optimization, repeatedly iterating to update the optimal position of the sparrow, outputting an optimized control parameter to generate a regulation instruction to regulate the communication frequency of the target walkie-talkie to expand the communication range.

[0120] Furthermore, in a walkie-talkie assisted rescue method based on fall detection in a rescue scenario provided by the present invention, the following steps are further included:

[0121] Based on data retrieval, obtaining a number of historical cooperative rescue instances of historical fall scenarios, extracting features from the historical cooperative rescue instances, and obtaining the communication environment characteristics and communication optimization scheme characteristics of each historical cooperative rescue instance;

[0122] Construct a communication environment portrait corresponding to each historical collaborative rescue instance based on the communication environment characteristics of each historical collaborative rescue instance as a representation of the corresponding historical rescue instance, and calculate the similarity value between the communication environment portraits of each historical rescue instance;

[0123] Use the calculated similarity value to classify each historical collaborative rescue instance by a clustering algorithm, and associate the extracted communication optimization scheme features with the corresponding categories to construct a historical collaborative rescue database;

[0124] When, after fall detection and determination, the current user of the walkie-talkie needs to perform collaborative rescue, match and analyze the rescue status collection information at the current moment with the communication environment portraits stored in the historical collaborative database;

[0125] If there is a matching communication environment portrait, extract the communication optimization scheme associated with the corresponding collaborative rescue category of the target communication environment portrait, generate a corresponding control instruction based on the extracted communication optimization scheme for communication optimization, so as to expand the communication distress range;

[0126] If there is no matching communication environment portrait, formulate an optimization scheme based on the current communication frequency and the maximum communication frequency of the walkie-talkie.

[0127] It should be noted that for the fall scenario of rescue personnel, if there is a relatively serious situation, that is, the rescue personnel fall from a high place and lose the ability of self-rescue, it is necessary to find personnel who can carry out collaborative rescue in a short time, so as to ensure the safety of the rescue personnel. Through historical data analysis, the communication optimization scheme in a similar environment is adopted to further improve the autonomous rescue ability of the walkie-talkie, ensure the safety of the fallen rescue personnel, improve the searchability, and thus avoid safety problems of rescue personnel caused by carrying out rescue tasks in a harsh environment.

[0128] Figure 3 A walkie-talkie assisted rescue system 3 based on fall detection in a rescue scenario provided by an embodiment of the present invention, the system includes: a memory 31 and a processor 32. The memory 31 contains a walkie-talkie assisted rescue method program based on fall detection in a rescue scenario. When the walkie-talkie assisted rescue method program based on fall detection in a rescue scenario is executed by the processor 32, the following steps are implemented:

[0129] Collect rescue status data for real-time rescue tasks to obtain rescue status collection information and perform preprocessing, and temporalize the preprocessed data to construct a running environment data sequence, a communication status data sequence, and a motion status data sequence;

[0130] Construct an anomaly detection model based on a generative adversarial network, input the motion status data sequence to analyze the abnormal motion status data in the real-time rescue task, and obtain abnormal motion status analysis information;

[0131] Perform fall detection on the target walkie-talkie user based on the abnormal motion state analysis information to determine whether a fall condition exists;

[0132] If it is detected that the current walkie-talkie user is in a fall condition, then perform a fall risk assessment in combination with the fall warning information to determine whether collaborative rescue is required;

[0133] If collaborative rescue is required, search for the walkie-talkies of other rescuers in the current communication environment for collaborative rescue, and optimize communication by combining the operation environment data sequence and the communication status data sequence to expand the communication range.

[0134] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the couplings, direct couplings, or communication connections between the various components shown or discussed can be through some interfaces, indirect couplings or communication connections of devices or units, and can be electrical, mechanical, or other forms.

[0135] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, in each embodiment of the present invention, the various functional units can all be integrated in one processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit; the above-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0137] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage media include: mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks, etc., which can store program codes.

[0138] Alternatively, if the above integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, may be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0139] The above are only the specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A walkie-talkie assisted rescue method based on fall detection in rescue scenarios, characterized in that: include: Collect rescue status data for real-time rescue tasks to obtain rescue status collection information and preprocess it, time-sequence the preprocessed data, and construct operating environment data sequence, communication status data sequence and motion status data sequence; Building an anomaly detection model based on a generative adversarial network, inputting the motion state data sequence to analyze abnormal motion state data in real-time rescue missions, and obtaining abnormal motion state analysis information; Based on the abnormal motion state analysis information, a fall detection is performed on the target intercom user to determine whether there is a fall condition, and a fall warning information is generated; If it is detected that the current intercom user has fallen, a fall risk assessment is performed in combination with the fall warning information to determine whether collaborative rescue is required; If collaborative rescue is required, the intercoms of other rescuers are searched for in the current communication environment for collaborative rescue, and communication optimization is performed in combination with the operating environment data sequence and the communication status data sequence to expand the communication range; If collaborative rescue is required, the intercoms of other rescuers are searched for in the current communication environment for collaborative rescue, and communication optimization is performed in combination with the operating environment data sequence and the communication status data sequence to expand the communication range, specifically including: Acquire a walkie-talkie operating environment data sequence and a walkie-talkie communication status data sequence, and extract the walkie-talkie spatial position features before the time node when the target person falls based on the walkie-talkie operating environment data sequence; The extracted spatial position features of the walkie-talkie are converted into three-dimensional coordinates and associated with the corresponding time features; the associated three-dimensional coordinates are de-redundant and the movement trajectory data of the target walkie-talkie user is generated according to the time change characteristics; Generate collaborative rescue information based on the target walkie-talkie user's movement trajectory data, search for other rescuers' walkie-talkies in the current communication environment for collaborative rescue, and if other rescuers cannot be found in the current environment, optimize communication to expand the autonomous search range; Acquire specification information of the target intercom, extract communication status features of the target intercom based on the intercom communication status data sequence, and calculate the current communication frequency of the target intercom according to the extracted communication status features; The maximum communication frequency feature is extracted through the specification information of the target walkie-talkie, and the restricted interval is generated in combination with the current communication frequency. The improved sparrow algorithm is introduced to optimize the communication frequency, the population is initialized, and the constraint conditions are constructed through the restricted interval. Calculate the fitness of the sparrow individuals in the initial population, select the corresponding number of sparrow individuals as discoverers based on the fitness ranking and the proportion of discoverers, and take the remaining sparrow individuals as joiners to update their positions; Randomly select alerters from individual sparrows according to the alerter ratio, and update the position. Calculate and update the fitness of each individual sparrow. In the position update, introduce the golden sine algorithm to guide the individual sparrow to update to the new position. Update the optimal position of the sparrow through repeated iterations and output the optimized control parameters. Based on the optimized control parameters, a control instruction is generated to control the communication frequency of the target walkie-talkie to expand the communication range.

2. According to claim 1, a walkie-talkie assisted rescue method based on fall detection in rescue scenarios is characterized in that: The rescue status data collection for the real-time rescue task obtains the rescue status collection information and performs preprocessing, performs time series processing on the preprocessed data, and constructs the operation environment data sequence, the communication status data sequence and the motion status data sequence, specifically including: Based on the sensor array set by the target walkie-talkie, rescue status data collection is performed on the real-time rescue task to obtain rescue status collection information, wherein the rescue status collection information includes walkie-talkie operating environment data, walkie-talkie communication status data and walkie-talkie motion status data; Performing data preprocessing on the rescue status collected information, calculating the data standard deviation of the rescue status collected information, and comparing the calculated data standard deviation with a preset standard deviation range; Define the rescue state collected data corresponding to the data standard deviation that is not within the preset standard deviation range as abnormal data, remove the abnormal values ​​and introduce the linear interpolation method to supplement the difference to obtain the preprocessing result information; Based on the preprocessing result information, time series features are extracted, and time series processing is performed on the preprocessing result information according to the extracted time series features to generate an operating environment data sequence, a communication status data sequence, and a motion status data sequence.

3. According to claim 1, a walkie-talkie assisted rescue method based on fall detection in rescue scenarios is characterized in that: The abnormality detection model is constructed based on the generative adversarial network, and the motion state data sequence is input to analyze the abnormal motion state data in the real-time rescue mission to obtain abnormal motion state analysis information, which specifically includes: Building an anomaly detection model based on a generative adversarial network, obtaining a motion state data sequence, and inputting the motion state data sequence as an original sequence into the anomaly detection model for analysis; The generator extracts features from the input motion state data sequence, reconstructs the sequence according to the extracted real-time intercom motion state features, generates a reconstructed motion state sequence, and inputs the reconstructed motion state sequence into the discriminator for judgment; The discriminator determines whether the current reconstructed motion state sequence can be constructed. If the discriminator determines that the current reconstructed motion state sequence is unacceptable, the current reconstructed motion state sequence is marked as an erroneous reconstructed motion state sequence, and the next reconstructed motion state sequence is obtained for judgment; The reconstructed motion state sequence generated by the iteratively repeated discriminant generator is selected to meet the preset acceptance criteria to obtain a final reconstructed motion state sequence; Calculating the reconstruction error between the final reconstructed motion state sequence and the original sequence, and comparing the calculated reconstruction error with a preset threshold. If the error is greater than the preset threshold, it indicates that the current real-time motion state is abnormal. The final reconstructed motion state sequence and the original sequence are time-ordered, the matching difference between the reconstructed motion state sequence and the original sequence is analyzed, and the abnormal motion state data and time nodes are determined through the matching difference to obtain abnormal motion state analysis information.

4. The walkie-talkie assisted rescue method based on fall detection in rescue scenarios according to claim 1, characterized in that: The step of performing fall detection on the target intercom user based on the abnormal motion state analysis information to determine whether there is a fall condition specifically includes: Acquire abnormal motion state analysis information, perform feature extraction on the abnormal motion state analysis information, extract abnormal motion state time features, and mark the running state data sequence with the extracted abnormal motion state time features; According to the marked motion state data sequence, a motion state data sequence of a preset time length is intercepted to obtain several motion state data subsequences, and a sliding window method is introduced to perform fall detection; Performing window sliding on the motion state data subsequence according to a preset sliding window size, extracting motion state data features in each window, and obtaining first feature extraction information; Preset a fall determination rule, and judge the first feature extraction information against the fall determination rule. If the feature extracted in the current window meets the fall determination rule, the current window is judged as a potential fall event window; Analyze whether the motion state characteristics in the next window of the potential fall event window meet the fall determination rule. If they also meet the rule, mark the corresponding window as a potential fall event window. Perform iterative sliding analysis and fall determination until all motion state data subsequences are detected, output all potential fall event windows and their time positions of the current motion state subsequence, and obtain potential fall event window detection information; Whether there are continuous potential fall event windows is analyzed according to the potential fall event window detection information. If there are continuous fall event windows and the number is greater than a preset threshold, the potential fall event window with the earliest time feature is marked as the fall starting point, and fall warning information is generated.

5. The walkie-talkie assisted rescue method based on fall detection in rescue scenarios according to claim 1, characterized in that: If it is detected that the current intercom user has fallen, a fall risk assessment is performed in combination with the fall warning information to determine whether collaborative rescue is required, specifically including: Acquire an operating environment data sequence and fall warning information, extract a motion state data subsequence when a fall occurs using the fall warning information, and determine the time node when the intercom user falls according to the fall warning information, and intercept the operating environment data subsequence after the corresponding time node from the acquired operating environment data sequence; Extracting features from the motion state data subsequence, obtaining motion state features of the intercom after the fall occurs, calculating the impact intensity and posture change amplitude based on the extracted motion state features, and generating first analysis information; Construct a three-dimensional coordinate system, perform feature extraction based on the intercepted operating environment data subsequence, obtain the operating environment change characteristics of the intercom after the fall occurs, and perform fall analysis; The acquired operating environment change characteristics are represented by using the constructed three-dimensional coordinate system, and a three-dimensional coordinate change graph after the walkie-talkie user falls is generated; and the fall direction, fall distance and fall position of the walkie-talkie user are analyzed based on the three-dimensional coordinate change graph to obtain second analysis information; Constructing a risk assessment model, inputting the first analysis information and the second analysis information into the model for analysis, determining the real-time fall risk of the intercom user, and obtaining fall risk assessment information; A risk rescue threshold is preset, and the fall risk assessment information is compared with the risk rescue threshold. If it is greater than the preset threshold, it means that the current intercom user needs collaborative rescue.

6. The walkie-talkie assisted rescue method based on fall detection in rescue scenarios according to claim 1, characterized in that: If collaborative rescue is required, the intercoms of other rescuers are searched for in the current communication environment for collaborative rescue, and communication optimization is performed in combination with the operating environment data sequence and the communication status data sequence to expand the communication range, specifically including: Acquire a walkie-talkie operating environment data sequence and a walkie-talkie communication status data sequence, and extract the walkie-talkie spatial position features before the time node when the target person falls based on the walkie-talkie operating environment data sequence; The extracted spatial position features of the walkie-talkie are converted into three-dimensional coordinates and associated with the corresponding time features; the associated three-dimensional coordinates are de-redundant and the movement trajectory data of the target walkie-talkie user is generated according to the time change characteristics; Generate collaborative rescue information based on the target walkie-talkie user's movement trajectory data, search for other rescuers' walkie-talkies in the current communication environment for collaborative rescue, and if other rescuers cannot be found in the current environment, optimize communication to expand the autonomous search range; Acquire specification information of the target intercom, extract communication status features of the target intercom based on the intercom communication status data sequence, and calculate the current communication frequency of the target intercom according to the extracted communication status features; The maximum communication frequency feature is extracted through the specification information of the target walkie-talkie, and the restricted interval is generated in combination with the current communication frequency. The improved sparrow algorithm is introduced to optimize the communication frequency, the population is initialized, and the constraint conditions are constructed through the restricted interval. Calculate the fitness of the sparrow individuals in the initial population, select the corresponding number of sparrow individuals as discoverers based on the fitness ranking and the proportion of discoverers, and take the remaining sparrow individuals as joiners to update their positions; Randomly select alerters from individual sparrows according to the alerter ratio, and update the position. Calculate and update the fitness of each individual sparrow. In the position update, introduce the golden sine algorithm to guide the individual sparrow to update to the new position. Update the optimal position of the sparrow through repeated iterations and output the optimized control parameters. Based on the optimized control parameters, a control instruction is generated to control the communication frequency of the target walkie-talkie to expand the communication range.

7. A walkie-talkie assisted rescue system based on fall detection in rescue scenarios, characterized in that: The system includes: a memory and a processor, wherein the memory contains a walkie-talkie assisted rescue method program based on rescue scenario fall detection, and when the walkie-talkie assisted rescue method program based on rescue scenario fall detection is executed by the processor, the walkie-talkie assisted rescue method steps based on rescue scenario fall detection as described in any one of claims 1-5 are implemented.

Images