A Communication Scheduling Method for Intelligent Mining Helmets Based on Multimodal Data Analysis

Abstract

This invention relates to the field of communication scheduling technology, specifically to a communication scheduling method for smart mining helmets based on multimodal data analysis. The method includes: dividing all smart mining helmets in the target scheduling area at the current monitoring time into a set of helmets to be relayed and a relay set, based on the difference between the individual protective monitoring data and normal data corresponding to the helmets to be relayed, the future communication status characterization value, the bandwidth utilization rate of the relay helmets, and the positional distance between the relay helmets and the helmets to be relayed; determining the relay link priority of the helmets to be relayed and the degree to which a link can be established between the relay helmets; and scheduling the communication of the smart mining helmets based on the relay link priority and the degree to which a link can be established. This invention can improve the effectiveness of communication scheduling for smart mining helmets, thereby ensuring or improving emergency response efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication scheduling, in particular to an intelligent mining helmet communication scheduling method based on multi-modal data analysis. BACKGROUND

[0002] In mining operations, the intelligent mining helmet worn by the miner can sense the wearer's vital sign data and the surrounding environmental parameters in real time, and since the wearer's vital sign data and the surrounding environmental parameters can reflect whether an emergency or an emergency occurs during the operation, in order to ensure the safety of the miners and the efficiency of the emergency response, it is necessary to ensure the stability and timeliness of the data transmission sensed or collected by the intelligent mining helmet, or to ensure the timeliness and stability of the communication between the helmet terminal and the ground system, and since the environment in the mine is complex, it can affect the stability and timeliness of the communication, that is, it can affect the stability and timeliness between the helmet terminal and the ground system, and when the stability and timeliness between the helmet terminal and the ground system are poor, it will directly affect the efficiency of the emergency response, and the efficiency of the emergency response is closely related to the safety of the miners, so in order to ensure the stability and timeliness between the helmet terminal and the ground system, it is necessary to schedule the communication of the intelligent mining helmet, that is, it is crucial to schedule the communication of the intelligent mining helmet.

[0003] And the existing communication scheduling mode is single and fixed, which can cause poor effect of communication scheduling of the intelligent mining helmet, that is, the existing communication scheduling generally does not consider the communication state of the helmet, only considers the importance of data, and transmits according to a fixed communication path, only considers the importance of data, such as the existing method of sensing that the gas concentration exceeds the standard, which generally selects to transmit the gas concentration according to a preset fixed path, but when some miners are in the deep or curved part of the roadway, the signal attenuation is serious, at this time, the data transmission stability according to the original fixed path, if the system still transmits data according to the fixed path at this time, it will cause that the key data cannot be transmitted to the receiving end of the ground system in time and reliably, and affect the efficiency of the emergency response, that is, when the effect of communication scheduling is poor, it will cause poor efficiency of the emergency response, and thus it will aggravate the safety risk, therefore, how to adaptively schedule the communication of the intelligent mining helmet to improve the scheduling effect and ensure the efficiency of the emergency response becomes a problem to be solved. SUMMARY

[0004] In order to solve the above problems, the present application provides an intelligent mining helmet communication scheduling method based on multi-modal data analysis, and the technical scheme adopted is as follows:

[0005] An embodiment of the present application provides an intelligent mining helmet communication scheduling method based on multi-modal data analysis, comprising the following steps:

[0006] obtain positive correlation communication data, negative correlation communication data and individual protection monitoring data corresponding to each intelligent mining helmet in the target scheduling area at different monitoring moments;

[0007] According to the positive correlation communication data and the negative correlation communication data, a predicted communication quality index value of the intelligent mining helmet at a future monitoring moment is obtained, and according to the predicted communication quality index value, a future communication state representation value of the intelligent mining helmet at the current monitoring moment is obtained.

[0008] According to the future communication state representation value, all intelligent mining helmets in the target scheduling area at the current monitoring moment are divided to obtain a to-be-relayed link set and a relay set.

[0009] According to the difference between the individual protection monitoring data and normal data corresponding to the to-be-relayed link helmet, the future communication state representation value, the bandwidth utilization rate of the relay helmet and the position distance between the relay helmet and the to-be-relayed link helmet, a relay link priority of the to-be-relayed link helmet and an establishable link degree between the relay helmet and the to-be-relayed link helmet are obtained, and the to-be-relayed link helmet belongs to the to-be-relayed link set and the relay helmet belongs to the relay set.

[0010] According to the relay link priority and the establishable link degree, the intelligent mining helmets are communicated and scheduled.

[0011] Beneficial effects: the present application firstly obtains positive correlation communication data, negative correlation communication data and individual protection monitoring data corresponding to each intelligent mining helmet in the target scheduling area at different monitoring moments; then according to the positive correlation communication data and the negative correlation communication data, a predicted communication quality index value of the intelligent mining helmet at a future monitoring moment is obtained, and according to the predicted communication quality index value, a future communication state representation value of the intelligent mining helmet at the current monitoring moment is obtained; then according to the future communication state representation value, all intelligent mining helmets in the target scheduling area at the current monitoring moment are divided to obtain a to-be-relayed link set and a relay set, and according to the difference between the individual protection monitoring data and normal data corresponding to the to-be-relayed link helmet, the future communication state representation value, the bandwidth utilization rate of the relay helmet and the position distance between the relay helmet and the to-be-relayed link helmet, a relay link priority of the to-be-relayed link helmet and an establishable link degree between the relay helmet and the to-be-relayed link helmet are obtained; finally, according to the relay link priority and the establishable link degree, the intelligent mining helmets are communicated and scheduled. And the present application communicates and schedules the intelligent mining helmets according to the relay link priority and the establishable link degree, which can improve the effect of communication scheduling, so as to improve the timeliness and reliability of data transmission, so as to ensure or improve the efficiency of emergency response. BRIEF DESCRIPTION OF DRAWINGS

[0012] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a smart mining helmet communication scheduling method based on multimodal data analysis according to the present invention. Detailed Implementation

[0014] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the protection scope of the embodiments of the present invention.

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art.

[0016] This embodiment provides a communication scheduling method for intelligent mining helmets based on multimodal data analysis, which is described in detail below:

[0017] like Figure 1 As shown, the intelligent mining helmet communication scheduling method based on multimodal data analysis includes the following steps:

[0018] Step S001: Obtain the positive correlation communication data, negative correlation communication data, and personal protective equipment monitoring data corresponding to each smart mining helmet in the target scheduling area at different monitoring times.

[0019] The purpose of this embodiment is to improve the communication scheduling effect of smart mining helmets by analyzing the relay link priority and the degree of link establishment in the helmets, thereby improving emergency response efficiency. For example, improving the communication scheduling effect can enhance the timeliness and reliability of transmitting important data such as excessive gas concentration and abnormal personal protective equipment monitoring data, or improve the timeliness and reliability of data transmission, thus improving emergency response efficiency. For ease of understanding and analysis, this embodiment will subsequently describe the communication scheduling process of a smart mining helmet in any mine or mining area as an example, and this mine or mining area will be designated as the target scheduling area.

[0020] Since the data support obtained by the subsequent analysis of the embodiment for relay link priority and the degree of link establishment and communication scheduling is the multi-modal communication data reflecting the communication status of the intelligent mining helmet and the multi-modal individual protection monitoring data reflecting the wearer status and the environment status, the embodiment next obtains the multi-modal communication data and the multi-modal individual protection monitoring data corresponding to each intelligent mining helmet in the target scheduling area at different monitoring moments. The multi-modal communication data corresponding to any intelligent mining helmet at any monitoring moment refers to all types of communication data of the intelligent mining helmet collected at the monitoring moment. The multi-modal individual protection monitoring data corresponding to any intelligent mining helmet at any monitoring moment refers to all types of individual protection monitoring data of the intelligent mining helmet collected at the monitoring moment. The individual protection monitoring data is collected by various sensing modules of the intelligent mining helmet. In the communication scheduling process of the intelligent mining helmet, the system of the receiving end needs to monitor and record the communication status and transmission content of the helmet in real time. Therefore, the multi-modal communication data of the helmet is periodically collected by the network monitoring module arranged at the receiving end when the helmet communicates, which can reflect the communication status of the helmet. The types or modes of the communication data in the embodiment include but are not limited to packet loss rate, delay, jitter, throughput rate, received signal strength, signal-to-noise ratio, etc. The types or modes of the individual protection monitoring data include but are not limited to the heart rate of the helmet wearer, the body temperature of the helmet wearer, the environmental humidity, the gas concentration, etc. The intelligent mining helmet integrates various sensing modules such as voice communication, positioning and navigation, environmental monitoring, and physiological monitoring, which can sense the working environment and vital signs of the miner in real time. That is, the various sensing modules integrated in the intelligent mining helmet can sense and collect the vital sign data and environmental parameter data of the wearer. The vital sign data and the environmental parameter data are collectively referred to as individual protection monitoring data. The vital sign data includes the heart rate and body temperature of the wearer. The environmental parameter data includes the gas concentration, humidity, and temperature in the environment. The individual protection monitoring data is the key data to ensure the safety of the miner or the operation safety. The monitoring moment is the moment of data sensing and data collection. The time interval between the monitoring moments needs to be set by the implementer according to the actual situation.

[0021] After obtaining the multi-modal communication data of each intelligent mining helmet in the target scheduling area at different monitoring moments, the communication data and the communication quality are related to each other to obtain positively correlated communication data and negatively correlated communication data. The positively correlated communication data and the negatively correlated communication data are the data support for obtaining the future communication status representation value in the subsequent process. The future communication status representation value is the key data for obtaining the relay link priority and the degree of link establishment. The specific process of obtaining the positively correlated communication data and the negatively correlated communication data is as follows:

[0022] For any communication data of any intelligent mining helmet, if the communication data is positively correlated with the communication quality of the intelligent mining helmet, the communication data is recorded as a positive correlation communication data corresponding to the intelligent mining helmet, if the communication data is negatively correlated with the communication quality of the intelligent mining helmet, the communication data is recorded as a negative correlation communication data corresponding to the intelligent mining helmet, the communication data is positively correlated with the communication quality of the intelligent mining helmet means that the larger the communication data is, the better the communication quality of the intelligent mining helmet is, and the communication data is negatively correlated with the communication quality of the intelligent mining helmet means that the larger the communication data is, the worse the communication quality of the intelligent mining helmet is.

[0023] Therefore, the embodiment can obtain the positive correlation communication data, the negative correlation communication data and the individual protection monitoring data of each intelligent mining helmet in the target scheduling area at different monitoring moments through the above process.

[0024] Step S002, obtaining a predicted communication quality index value of the intelligent mining helmet at a future monitoring moment according to the positive correlation communication data and the negative correlation communication data, and obtaining a future communication state representation value of the intelligent mining helmet at the current monitoring moment according to the predicted communication quality index value.

[0025] After obtaining the positive correlation communication data and the negative correlation communication data, the embodiment predicts the future communication quality based on the obtained positive correlation communication data and the negative correlation communication data, and obtains the future communication state representation value of the intelligent mining helmet at the current monitoring moment by fusing and analyzing the prediction result. The future communication state representation value obtained based on the predicted future communication quality is an important parameter for improving the communication scheduling effect, or the future communication state representation value obtained based on the predicted future communication quality is an important parameter for ensuring that the important data is still quickly and stably sent to the receiving end of the ground system in a harsh environment, and is also an important parameter for improving the bandwidth utilization, improving the overall communication reliability, and providing a powerful guarantee for mine safety production and emergency response.

[0026] Based on the above, before obtaining the future communication state representation value of the intelligent mining helmet at the current monitoring moment, the embodiment needs to predict the future communication quality based on the obtained positive correlation communication data and the negative correlation communication data, and obtain a predicted communication quality index value of the intelligent mining helmet at a future monitoring moment. The predicted communication quality index value is the basis for obtaining the future communication state representation value subsequently; and the specific obtaining process of the predicted communication quality index value of the intelligent mining helmet at the future monitoring moment is as follows:

[0027] Firstly, according to the positive correlation communication data and the negative correlation communication data corresponding to each intelligent mining helmet in the target scheduling area at different monitoring moments, actual communication quality index values of each intelligent mining helmet in the target scheduling area at different monitoring moments are obtained, and at this time, actual communication quality index values of each intelligent mining helmet in the target scheduling area at the current monitoring moment and at the historical monitoring moment are obtained; then, according to the actual communication quality index values of the intelligent mining helmet at the current monitoring moment and at the historical monitoring moment, a prediction model is used to predict the communication quality of the intelligent mining helmet at each future monitoring moment in the preset future time period of the current monitoring moment, and prediction communication quality index values of the intelligent mining helmet at each future monitoring moment in the preset future time period of the current monitoring moment are obtained; for any intelligent mining helmet, under the premise that the actual communication quality index values of the intelligent mining helmet at the current monitoring moment and at the historical monitoring moment are known, the prediction model is used to predict the communication quality index values of the intelligent mining helmet at each future monitoring moment in the preset future time period of the current monitoring moment, and a process of obtaining the prediction communication quality index values is a known process, so this embodiment will not be described in detail; in specific application, the implementer can select a prediction model according to actual conditions, for example, the GRU (Gated Recurrent Unit) prediction model can be selected for prediction in this embodiment, and the GRU prediction model is an improved recurrent neural network (RNN); in specific application, the implementer can flexibly adjust the length of the preset future time period according to the response speed and real-time requirement of the scheduling system, for example, when the scheduling system switching delay is large, a longer time period should be predicted, so as to leave sufficient reaction time for the scheduling system, otherwise, a shorter time can be selected, for example, the sensitivity of the system reaction, in this embodiment, the preset future time period of the current monitoring moment is set to 1 second after the current monitoring moment.

[0028] In this embodiment, the specific process of obtaining the actual communication quality index values of each intelligent mining helmet in the target scheduling area at different monitoring moments according to the positive correlation communication data and the negative correlation communication data of each intelligent mining helmet in the target scheduling area at different monitoring moments is as follows:

[0029] For any intelligent mining helmet A in the target scheduling area at any monitoring moment t: after normalization processing and then weighted accumulation of all positive correlation communication data corresponding to the intelligent mining helmet A at the monitoring moment t, the weighted accumulation result is recorded as a first accumulation value, after negative correlation mapping and then weighted accumulation of the normalization result of all negative correlation communication data corresponding to the intelligent mining helmet A at the monitoring moment t, the weighted accumulation result is recorded as a second accumulation value, and the sum of the first accumulation value and the second accumulation value is taken as the actual communication quality index value of the intelligent mining helmet A at the monitoring moment t; and the specific calculation expression for obtaining the actual communication quality index value of the intelligent mining helmet A at the monitoring moment t is as follows:

[0030]

[0031] wherein, is an actual communication quality index value of the intelligent mining helmet A at a monitoring time t, is a number of positive correlation communication data corresponding to the intelligent mining helmet A at the monitoring time t or is a category number of positive correlation communication data in all communication data corresponding to the intelligent mining helmet A collected at the monitoring time t, is a number of negative correlation communication data corresponding to the intelligent mining helmet A at the monitoring time t or is a category number of negative correlation communication data in all communication data corresponding to the intelligent mining helmet A collected at the monitoring time t, Norm() is a normalization function, is the ith positive correlation communication data corresponding to the intelligent mining helmet A at the monitoring time t, is a weight value of the ith positive correlation communication data corresponding to the intelligent mining helmet A at the monitoring time t, is the jth negative correlation communication data corresponding to the intelligent mining helmet A at the monitoring time t, is a weight value of the jth negative correlation communication data corresponding to the intelligent mining helmet A at the monitoring time t; the constant 1 minus is to perform negative correlation mapping on ; an accumulated result of weight values of all positive correlation communication data corresponding to the intelligent mining helmet A at the monitoring time t is 1, and an accumulated result of weight values of all negative correlation communication data corresponding to the intelligent mining helmet A at the monitoring time t is 1, and in specific application, an implementer can set the weight values according to actual situations such as correlation with the communication quality, if the positive correlation communication data corresponding to the intelligent mining helmet A at the monitoring time t are respectively data 1, data 2 and data 3, and the correlation between data 1 and the communication quality of the intelligent mining helmet A is greater than the correlation between data 2 and the communication quality of the intelligent mining helmet A, and the correlation between data 2 and the communication quality of the intelligent mining helmet A is greater than the correlation between data 3 and the communication quality of the intelligent mining helmet A, then the weight value of data 1 can be required to be greater than the weight value of data 2, the weight value of data 2 is greater than the weight value of data 3, and the sum of the weight value of data 1, the weight value of data 2 and the weight value of data 3 is 1, and the greater the correlation is, the higher the credibility of the communication quality situation reflected or represented by the corresponding data is.

[0032] In addition, the greater the value of is, and the smaller the value of is, the better the communication quality of the intelligent mining helmet A at the monitoring time t is, the greater the value of The greater the value, the better the communication quality of the intelligent mining helmet A at the monitoring time t, and vice versa The smaller the value, the worse the communication quality of the intelligent mining helmet A at the monitoring time t; and the multi-modal communication data in this embodiment can reflect data integrity, real-time, stability, bandwidth utilization and physical link quality, that is, it can comprehensively reflect the communication state, so the above multi-modal data can more accurately represent the communication quality of the helmet than the single-modal data, and can provide more accurate comprehensive score basis for subsequent scheduling.

[0033] After obtaining the predicted communication quality index value, the future communication state representation value of the intelligent mining helmet at the current monitoring time is obtained according to the predicted communication quality index value of the intelligent mining helmet at each future monitoring time in the preset future time period of the current monitoring time, and the specific obtaining process of the future communication state representation value of the intelligent mining helmet at the current monitoring time is as follows:

[0034] For any intelligent mining helmet A in the target scheduling area at any monitoring time t: first, calculate the mean value of the predicted communication quality index value of the intelligent mining helmet A at all future monitoring times in the preset future time period of the current monitoring time, and mark it as the predicted mean value corresponding to the intelligent mining helmet A at the current monitoring time; then, the predicted communication quality index value of the intelligent mining helmet A at each historical monitoring time in the preset historical time period before the current monitoring time is obtained by using the prediction model, the method for obtaining the predicted communication quality index value of the intelligent mining helmet A at the historical monitoring time is the same as the method for obtaining the predicted communication quality index value of the intelligent mining helmet A at the future monitoring time, and the mean square error between the predicted communication quality index value of the intelligent mining helmet A at the historical monitoring time and the actual communication quality index value of the intelligent mining helmet A at the corresponding historical monitoring time in the preset historical time period before the current monitoring time is calculated, and is marked as the mean square error corresponding to the intelligent mining helmet A at the current monitoring time. The mean square error corresponding to the intelligent mining helmet A at the current monitoring time is negatively correlated and mapped, and the mapping result is marked as the prediction credibility representation value corresponding to the intelligent mining helmet A at the current monitoring time; then, the product of the predicted mean value corresponding to the intelligent mining helmet A at the current monitoring time and the prediction credibility representation value is calculated after normalization, and is marked as the future communication state representation value of the intelligent mining helmet A at the current monitoring time; in specific application, the implementer needs to set the length of the preset historical time period according to the actual situation, such as setting the preset historical time period to 1 second before the monitoring time in this embodiment. The specific expression of the future communication state representation value of the intelligent mining helmet A at the current monitoring time is as follows:

[0035]

[0036] Wherein, Let W be the future communication state representation value of the smart mining helmet A at the current monitoring time, W be the predicted mean value of the smart mining helmet A at the current monitoring time, exp() be an exponential function with a base of constant e (used for negative correlation mapping), and M be the mean square error of the smart mining helmet A at the current monitoring time. R represents the number of historical monitoring times in the preset historical time period preceding the current monitoring time. This represents the actual communication quality index value of the smart mining helmet A at the r-th historical monitoring moment within a preset historical time period prior to the current monitoring moment. Let W be the predicted communication quality index value of the smart mining helmet A at the r-th historical monitoring time within a preset historical time period before the current monitoring time. The smaller the mean square error M, the more regular the change in the helmet's communication quality at this time. Therefore, the change in its communication quality in the future time period is likely to be relatively regular as well, indicating that the prediction result is more reliable, that is, W is more reliable. When it is larger or A larger value indicates a better communication performance for the smart mining helmet A within a preset future timeframe, or a better communication performance for the smart mining helmet A within a recent timeframe; conversely, a smaller value indicates a better communication performance for the helmet A within a recent timeframe. The smaller the value, the worse the communication status of the smart mining helmet A is within the preset future time period. The value range is from 0 to 1.

[0037] Therefore, this embodiment obtains the future communication status representation value of the smart mining helmet at the current monitoring time through the above process. Subsequently, it will determine whether communication scheduling is required and the specific scheduling mode based on the future communication status representation value of the smart mining helmet at the current monitoring time.

[0038] Step S003: Based on the future communication status characterization value, all smart mining helmets in the target scheduling area at the current monitoring time are divided into a set of helmets to be relayed and a relay set. Based on the difference between the individual protection monitoring data and normal data corresponding to the helmets to be relayed, the future communication status characterization value, the bandwidth utilization rate of the relay helmets, and the positional distance between the relay helmets and the helmets to be relayed, the relay link priority of the helmets to be relayed and the degree to which a link can be established between the relay helmets and the helmets to be relayed are obtained. The helmets to be relayed belong to the set of helmets to be relayed, and the relay helmets belong to the relay set.

[0039] After obtaining the future communication state representation value, all smart mining helmets in the target scheduling area at the current monitoring time are divided according to the future communication state representation value to obtain the set of links to be relayed and the relay set. The division is a key step for subsequent effective scheduling. The process of obtaining the set of links to be relayed and the relay set is as follows:

[0040] In all smart mining helmets in the target scheduling area at the current monitoring moment, the smart mining helmets with future communication state representation values less than the preset communication state threshold are obtained, and a set of all smart mining helmets with future communication state representation values less than the preset communication state threshold is recorded as a set of to-be-relayed link sets, a set of all smart mining helmets with future communication state representation values not less than the preset communication state threshold is recorded as a relay set, all helmets in the to-be-relayed link set are recorded as to-be-relayed link helmets, and all helmets in the relay set are recorded as relay helmets; since the future communication state representation values of the smart mining helmets in the to-be-relayed link set are small, and the communication states of the smart mining helmets in the to-be-relayed link set are poor in the near stage, when the to-be-relayed link set is not empty, it indicates that communication scheduling needs to be performed, that is, the helmets in the relay set are used as relay nodes for transmission, that is, the communication link needs to be adjusted to ensure the emergency response efficiency, and the scheduling mode of using the helmets in the relay set as relay nodes for transmission can make the helmets with poor communication states in the near stage also transmit and timely report key data such as gas concentration exceeding the standard and individual protection monitoring data, or can improve the timeliness and reliability of helmet data transmission as much as possible, thereby ensuring the emergency response efficiency, that is, the communication scheduling mode of using the helmets in the relay set as relay nodes for transmission in the embodiment can make the helmets transmit and report key data such as gas concentration exceeding the standard and individual protection monitoring data as much as possible when the communication quality of the helmets is poor, or can improve the timeliness and stability of helmet data transmission as much as possible, and direct connection means direct forwarding or transmission to the ground system receiving end without relay nodes or direct connection of the helmet with the ground system receiving end; since the future communication state representation values of the smart mining helmets in the relay set are large, and the communication states of the helmets in the set are good in the near stage, the communication link of the helmets in the set does not need to be adjusted at this time. In addition, if the to-be-relayed link set is empty, it indicates that the communication states of all smart mining helmets in the target scheduling area are good at this time, and the emergency response efficiency can be ensured without communication scheduling, that is, when the to-be-relayed link set is empty, the helmets transmit data according to the original transmission mode or path, and if the relay set is empty, it indicates that the communication states of all helmets in the near stage are poor, and there is no helmet that can be used as a relay node at this time, and in order to ensure the timeliness and stability of key data or data transmission, troubleshooting needs to be performed at this time to improve the communication quality. In specific applications, the implementer needs to set the preset communication state threshold according to the actual situation such as the value range and experimental statistics, for example, the preset communication state threshold can be set to 0.65 in the embodiment.

[0041] After the obtained relay link set and relay set, in order to ensure the timeliness of transmission of important data such as gas concentration exceeding standard, abnormal individual protection monitoring data, or the timeliness and stability of data transmission, it is necessary to analyze the relay link priority of the to-be-relayed link helmet and the degree of link establishment between the relay helmet and the to-be-relayed link helmet, that is, according to the difference between the individual protection monitoring data and the normal data corresponding to the to-be-relayed link helmet, the future communication state representation value, the bandwidth utilization rate of the relay helmet, and the position distance between the relay helmet and the to-be-relayed link helmet, the relay link priority of the to-be-relayed link helmet and the degree of link establishment between the relay helmet and the to-be-relayed link helmet are obtained, and the relay link priority and the degree of link establishment are the key basis for communication scheduling, and are also the key to ensure that important data is transmitted to the receiving end in time and stably, or to ensure the timeliness and stability of data transmission, and are also the key data to ensure the efficiency of emergency response, that is, the relay link priority and the degree of link establishment are the key to improve or ensure the effect of communication scheduling.

[0042] In the embodiment, the specific obtaining process of the relay link priority of the to-be-relayed link helmet and the degree of link establishment between the relay helmet and the to-be-relayed link helmet is as follows:

[0043] First, the normal data of each individual protection monitoring data corresponding to the to-be-relayed link helmet at the current monitoring time, the bandwidth utilization rate of the relay helmet in a preset historical time period before the current monitoring time, and the position distance between the relay helmet and the to-be-relayed link helmet at the current monitoring time are obtained. The process of obtaining the bandwidth utilization rate of the helmet in a certain time period is known. The specific process of obtaining the normal data of the hth individual protection monitoring data corresponding to any to-be-relayed link helmet at the current monitoring time is as follows: among all the individual protection monitoring data corresponding to the to-be-relayed link helmet at all historical monitoring times, the median of all individual protection monitoring data of the same type as the hth individual protection monitoring data is obtained, and is recorded as the normal data of the hth individual protection monitoring data corresponding to the to-be-relayed link helmet at the current monitoring time. The median in the historical data can indicate the normal level.

[0044] Then, according to the difference between the individual protection monitoring data corresponding to the relay link helmet and the normal data of the corresponding individual protection monitoring data at the current monitoring moment and the future communication state representation value of the relay link helmet at the current monitoring moment, the relay link priority of the relay link helmet at the current monitoring moment is obtained, and according to the future communication state representation value of the relay helmet at the current monitoring moment, the bandwidth utilization rate of the relay helmet in the preset historical time period before the current monitoring moment and the position distance between the relay helmet and the relay link helmet at the current monitoring moment, the establishment degree of the link between the relay helmet and the relay link helmet at the current monitoring moment is obtained. The bandwidth utilization rate of any relay helmet in the preset historical time period before the current monitoring moment refers to the ratio of the actual bandwidth occupation to the total available bandwidth of the data transmission channel of the relay helmet in the preset historical time period before the current monitoring moment.

[0045] In the embodiment, the specific process of obtaining the relay link priority of the relay link helmet at the current monitoring moment according to the difference between the individual protection monitoring data corresponding to the relay link helmet and the normal data of the corresponding individual protection monitoring data at the current monitoring moment and the future communication state representation value of the relay link helmet at the current monitoring moment is as follows: for any relay link helmet b, first, according to the difference between the individual protection monitoring data corresponding to the relay link helmet and the normal data of the corresponding individual protection monitoring data at the current monitoring moment and the future communication state representation value of the relay link helmet at the current monitoring moment, the importance of the relay link helmet b at the current monitoring moment is obtained. The higher the importance, the more important or critical the individual protection monitoring data corresponding to the relay link helmet b is, and the relay should be performed in priority to ensure the timeliness of data transmission or the efficiency of emergency response; then, according to the future communication state representation value of the relay link helmet b at the current monitoring moment and the importance of the relay link helmet b at the current monitoring moment, the relay link priority of the relay link helmet b at the current monitoring moment is obtained, and the smaller the future communication state representation value of the relay link helmet b, the worse the communication condition of the relay link helmet b in the near future, and the more likely it is to cause the problem of low emergency response efficiency, so the relay should be performed in priority to ensure the timeliness and stability of data transmission.

[0046] In the embodiment, the specific process of obtaining the importance degree of the to-be-relayed link helmet b at the current monitoring moment is that: the absolute value difference between the individual protection monitoring data corresponding to the to-be-relayed link helmet b at the current monitoring moment and the normal data of the corresponding individual protection monitoring data is normalized, and all are recorded as the deviation characteristic value corresponding to the to-be-relayed link helmet b at the current monitoring moment, that is, the kth deviation characteristic value corresponding to the to-be-relayed link helmet b at the current monitoring moment is the result of normalizing the absolute value difference between the kth individual protection monitoring data corresponding to the to-be-relayed link helmet b at the current monitoring moment and the normal data of the kth individual protection monitoring data by using the normalization function Norm ( ); a set composed of all the deviation characteristic values corresponding to the to-be-relayed link helmet b at the current monitoring moment is recorded as the first set of the to-be-relayed link helmet b at the current monitoring moment, and the product of the cumulative result of all data in the first set and the maximum value in the first set is normalized to obtain the importance degree of the to-be-relayed link helmet at the current monitoring moment, which is also normalized by using the normalization function Norm ( ); the greater the deviation characteristic value or the greater the cumulative result, or the greater the cumulative result of all data in the first set and the maximum value in the first set, the more it indicates that the individual protection monitoring data corresponding to the to-be-relayed link helmet b at this time carries important data representing a sudden event or an emergency, and therefore the to-be-relayed link helmet b is more important and needs to be relayed and linked first.

[0047] In the embodiment, according to the future communication state characteristic value of the to-be-relayed link helmet b at the current monitoring moment and the importance degree of the to-be-relayed link helmet b at the current monitoring moment, the specific process of obtaining the relay link priority of the to-be-relayed link helmet b at the current monitoring moment is that: the result of negatively correlating the future communication state characteristic value of the to-be-relayed link helmet b at the current monitoring moment and the importance degree of the to-be-relayed link helmet b at the current monitoring moment is weighted and summed, and is recorded as the relay link priority of the to-be-relayed link helmet b at the current monitoring moment, and the specific expression of the relay link priority of the to-be-relayed link helmet b at the current monitoring moment is:

[0048]

[0049] wherein, is the relay link priority of the to-be-relayed link helmet b at the current monitoring moment, is the future communication state characteristic value of the to-be-relayed link helmet b at the current monitoring moment, and the constant 1 is subtracted from is to negatively correlate , is the weight value of the future communication state characteristic value of the to-be-relayed link helmet b at the current monitoring moment, The importance of the helmet b to be relayed at the current monitoring time; and The smaller When it is larger, The larger, and The larger the value, the greater the probability that the personal protective equipment (PPE) monitoring data corresponding to helmet b to be relayed contains important data indicating a sudden event or emergency, and the worse the communication status of helmet b to be relayed in the near future. Therefore, in order to ensure that important data can be transmitted in a timely and reliable manner, the priority of helmet b to be relayed should be higher at the current monitoring time, or helmet b to be relayed should be prioritized earlier at the current monitoring time, and vice versa. The smaller the value, the lower the priority of helmet b waiting to relay a connection at the current monitoring time, or the later helmet b will relay. Furthermore, in practical applications, implementers need to configure the settings according to the degree of relevance to sudden or emergency events. The value of the importance is usually highly correlated with sudden or emergency events, so this embodiment assigns a higher weight to the importance, such as... Set it to 0.35.

[0050] In this embodiment, the specific process of determining the degree to which a link can be established between the relay helmet and the helmet to be relayed at the current monitoring time is as follows, based on the future communication status representation value of the relay helmet at the current monitoring time, the bandwidth utilization rate of the relay helmet in the preset historical time period before the current monitoring time, and the location distance between the relay helmet and the helmet to be relayed at the current monitoring time:

[0051] For any relay helmet 'a' and any helmet 'b' to be relayed: the distance between relay helmet 'a' and helmet 'b' at the current monitoring time is denoted as the distance index value. The negative correlation mapping result of the bandwidth utilization rate of relay helmet 'a' in the preset historical time period before the current monitoring time is denoted as the additional bandwidth characterization value. The product of the distance index value, the additional bandwidth characterization value, and the future communication state characterization value of relay helmet 'a' at the current monitoring time is calculated and used as the degree to which a link can be established between relay helmet 'a' and helmet 'b' at the current monitoring time. The specific expression for the degree to which a link can be established between relay helmet 'a' and helmet 'b' at the current monitoring time is:

[0052]

[0053] in, This represents the degree to which a link can be established between relay helmet a and helmet b, which is to be relayed, at the current monitoring time. This represents the distance between relay helmet a and helmet b, which is to be relayed, at the current monitoring time. This refers to the bandwidth utilization rate of relay helmet a during a preset historical time period prior to the current monitoring time. The value representing the future communication state of relay helmet a at the current monitoring time is a constant 1 minus In order to achieve The purpose of performing negative correlation mapping is to use a negative exponential function with base e to... Mapping is also for the purpose of achieving... The purpose of performing negative correlation mapping; and A larger value indicates a better communication status for relay helmet a at the current monitoring time. Therefore, prioritizing relay helmet a as the relay node would improve the timeliness and reliability of transmission. Consequently, the likelihood of establishing a link between relay helmet a and the helmet b to be relayed should be greater. The larger the value, the more likely the relay helmet a will be selected as the relay node, ensuring that the helmet's data can be transmitted in a timely and stable manner. The smaller the value, the better the signal stability and communication quality are likely to be after the relay helmet a and the helmet b to be relayed establish a link. Therefore, the degree to which the link can be established between the two should be greater. The smaller the value, the higher the bandwidth available for additional transmission in relay helmet a. This means relay helmet a has redundant bandwidth to serve as a relay node for other helmets to be relayed. Therefore, the likelihood of establishing a connection between relay helmet a and helmet b to be relayed should be greater in this case. The value range is from 0 to 1; based on the above description, it can be known that... The bigger, smaller and The smaller, The larger, and The larger the value, the greater the likelihood of establishing a link between relay helmet a and helmet b to be relayed. A higher likelihood of establishing a link indicates a greater probability that relay helmet a will subsequently be matched as a relay node for helmet b to be relayed. In other words, the probability that relay helmet a will subsequently be matched as a matching relay helmet for helmet b to be relayed is higher. Conversely, a lower likelihood indicates a lower likelihood of establishing a link. The smaller the value, the lower the likelihood of establishing a link between relay helmet a and helmet b (the one to be relayed). A lower likelihood of establishing a link indicates a lower probability that relay helmet a will subsequently be matched as a relay node for helmet b. In other words, the probability of relay helmet a being subsequently matched as a matching relay helmet for helmet b is lower. Furthermore, this embodiment calculates the likelihood of establishing a link to ensure that short-term relaying does not affect the communication quality and data transmission of the relay helmets.

[0054] Therefore, this embodiment can obtain the relay link priority of the helmet to be relayed and the degree to which a link can be established between the relay helmet and the helmet to be relayed through the above process.

[0055] Step S004: Based on the relay link priority and the degree of link establishment, perform communication scheduling for the smart mining helmet.

[0056] This embodiment, after obtaining the relay link priority of the helmet to be relayed and the degree to which a link can be established between the relay helmets, performs communication scheduling on the smart mining helmets in the target scheduling area at the current monitoring time based on the relay link priority of the helmet to be relayed and the degree to which a link can be established between the relay helmets. The specific process is as follows:

[0057] The maximum load capacity of the relay helmet is obtained. This refers to the maximum amount of data or processing capacity the helmet can handle during data transmission; it is essentially a system-set safety threshold. Specifically, the maximum load capacity of the smart mining helmet refers to the upper limit of power its hardware system can withstand during continuous operation or the limit of collaborative operation of its functional modules. Considering the maximum load capacity of the relay helmet aims to ensure that its load does not exceed the limit when acting as a relay node. After obtaining the relay link priority of the helmet to be relayed, the degree of connection that can be established between the relay helmets, and the maximum load capacity of the relay helmet, a matching algorithm is used... The algorithm matches the set of helmets to be relayed with the smart mining helmets in the relay set to obtain matching relay helmets for each helmet in the set to be relayed. The matching algorithm follows matching rules based on relay link priority (high to low), the degree of link establishment between relay helmets and helmets to be relayed (high to low), and the maximum load capacity of the relay helmet after connection. Data from the helmets to be relayed will pass through the corresponding relay helmet... The data from the relay helmet, or the data received by the relay helmet acting as a relay node, is forwarded to the receiving end according to the original link path. That is, the data from the relay helmet, or the data received by the relay helmet acting as a relay node, is forwarded to the receiving end using the original direct connection mode. Direct connection mode means forwarding or transmitting data directly to the receiving end without going through a relay node. Furthermore, this embodiment can choose a greedy algorithm or a Hungarian algorithm for matching. Moreover, the process of using a greedy algorithm or a Hungarian algorithm for matching is known, provided the matching rules are known, i.e., the relay link priority of the helmet to be relayed is known. Given the degree of link establishment between the relay helmet and the helmet to be relayed, the maximum load capacity of the relay helmet, and the matching rules, the process of matching using a greedy algorithm or the Hungarian algorithm is well-known. An example illustrating that the linking process will not exceed the maximum load capacity of the relay helmet is as follows: For relay helmet a and helmet b to be relayed, if the amount of data that helmet b needs to transmit plus the amount of data that relay helmet a needs to transmit exceeds the maximum load capacity of relay helmet a, then relay helmet a will not be selected as a relay node for helmet b or will not be selected as a matching relay helmet for helmet b.

[0058] Thus, this embodiment completes the communication scheduling of the smart mining helmet, and the scheduling method for future moments in this embodiment is the same as the scheduling method for the current monitoring moment. Furthermore, the communication scheduling effect of this embodiment is good; that is, the scheduling method of this embodiment can transmit important data such as excessive gas concentration and abnormal personal protective equipment monitoring data in a timely and reliable manner even when the helmet's communication quality is poor, or can maximize the timeliness and stability of helmet data transmission, thus ensuring emergency response efficiency. Therefore, the scheduling effect is good.

[0059] In summary, this embodiment first acquires the positively correlated communication data, negatively correlated communication data, and personal protective equipment (PPE) monitoring data corresponding to each smart mining helmet in the target scheduling area at different monitoring times. Then, based on the positively and negatively correlated communication data, it obtains the predicted communication quality index value of the smart mining helmet at future monitoring times. Based on the predicted communication quality index value, it obtains the future communication status characterization value of the smart mining helmet at the current monitoring time. Next, based on the future communication status characterization value, it divides all smart mining helmets in the target scheduling area at the current monitoring time into a set to be relayed and a relay set. Based on the difference between the PPE monitoring data and normal data corresponding to the helmets to be relayed, the future communication status characterization value, the bandwidth utilization rate of the relay helmets, and the positional distance between the relay helmets and the helmets to be relayed, it obtains the relay link priority of the helmets to be relayed and the degree to which a link can be established between the relay helmets and the helmets to be relayed. Finally, it performs communication scheduling for the smart mining helmets based on the relay link priority and the degree to which a link can be established. Furthermore, this embodiment uses relay link priority and the degree of link establishment to schedule communication for the smart mining helmet, which can improve the effectiveness of communication scheduling, thereby improving the timeliness and reliability of data transmission, and thus ensuring or improving the efficiency of emergency response.

[0060] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. An intelligent mining helmet communication dispatching method based on multi-modal data analysis, characterized in that, The method comprises the following steps: Obtaining positive correlation communication data, negative correlation communication data and individual protection monitoring data corresponding to each intelligent mining helmet in the target scheduling area at different monitoring moments; the positive correlation communication data is positively correlated with the communication quality of the intelligent mining helmet, and the negative correlation communication data is negatively correlated with the communication quality of the intelligent mining helmet; According to the positive correlation communication data and the negative correlation communication data, a predicted communication quality index value of the intelligent mining helmet at a future monitoring moment is obtained, and according to the predicted communication quality index value, a future communication state representation value of the intelligent mining helmet at a current monitoring moment is obtained; According to the future communication state representation value, all intelligent mining helmets in the target scheduling area at the current monitoring moment are divided to obtain a relay link set and a relay set; According to the difference between the individual protection monitoring data and normal data corresponding to the relay link helmet, the future communication state representation value, the bandwidth usage rate of the relay helmet and the position distance between the relay helmet and the relay link helmet, a relay link priority of the relay link helmet and an establishable link degree between the relay helmet and the relay link helmet are obtained, the relay link helmet belongs to the relay link set, and the relay helmet belongs to the relay set; According to the relay link priority and the establishable link degree, the intelligent mining helmets are communicated and scheduled; The method for obtaining the relay link priority of the relay link helmet and the establishable link degree between the relay helmet and the relay link helmet comprises the following steps: According to the difference between the individual protection monitoring data and normal data corresponding to the relay link helmet at the current monitoring moment and the future communication state representation value of the relay link helmet, the relay link priority of the relay link helmet at the current monitoring moment is obtained; According to the future communication state representation value of the relay helmet, the bandwidth usage rate of the relay helmet in a preset historical time period before the current monitoring moment and the position distance between the relay helmet and the relay link helmet, the establishable link degree between the relay helmet and the relay link helmet at the current monitoring moment is obtained; The method for obtaining the relay link priority of the relay link helmet at the current monitoring moment comprises the following steps: The absolute value of the difference between each individual protection monitoring data corresponding to the relay link helmet at the current monitoring moment and the normal data corresponding to the individual protection monitoring data is normalized, and the normalized result is recorded as a deviation representation value corresponding to the relay link helmet at the current monitoring moment; a set composed of all deviation representation values corresponding to the relay link helmet at the current monitoring moment is recorded as a first set of the relay link helmet, and the product of the cumulative result of all data in the first set and the maximum value in the first set is normalized to obtain the importance degree of the relay link helmet at the current monitoring moment. A result of negatively correlating the future communication state representation value of the to-be-relayed link helmet at the current monitoring moment is weighted and summed with the importance of the to-be-relayed link helmet, and the result is recorded as a relay link priority of the to-be-relayed link helmet at the current monitoring moment. The method for determining the link establishment degree between the relay helmet and the to-be-relayed link helmet comprises: For any relay helmet a and any to-be-relayed link helmet b, the distance between the relay helmet a and the to-be-relayed link helmet b at the current monitoring moment is recorded as a distance index value, a negatively correlated mapping result of the bandwidth usage rate of the relay helmet a in a preset historical time period before the current monitoring moment is recorded as an additional bandwidth representation value, and a product of the distance index value, the additional bandwidth representation value and a future communication state representation value of the relay helmet a at the current monitoring moment is taken as the link establishment degree between the relay helmet a and the to-be-relayed link helmet b.

2. The intelligent mining helmet communication dispatching method based on multi-modal data analysis of claim 1, wherein, The method for obtaining the predicted communication quality index value of the intelligent mining helmet at the future monitoring moment comprises: According to the positively correlated communication data and the negatively correlated communication data, actual communication quality index values of the intelligent mining helmet at different monitoring moments are obtained; For any intelligent mining helmet in the target scheduling area at any monitoring moment, according to the actual communication quality index values of the intelligent mining helmet at the current monitoring moment and the historical monitoring moments, a prediction model is used to predict the communication quality index value of the intelligent mining helmet at the future monitoring moment, so as to obtain the predicted communication quality index value of the intelligent mining helmet at the future monitoring moment.

3. The intelligent mining helmet communication dispatching method based on multi-modal data analysis of claim 2, wherein, The method for obtaining the actual communication quality index value of the intelligent mining helmet at different monitoring moments comprises: A result of weighting and accumulating normalized results of all the positively correlated communication data corresponding to the intelligent mining helmet at the monitoring moment is recorded as a first accumulated value, a result of weighting and accumulating normalized results of all the negatively correlated communication data corresponding to the intelligent mining helmet at the monitoring moment after negatively correlating the normalized results is recorded as a second accumulated value, and a sum of the first accumulated value and the second accumulated value is taken as the actual communication quality index value of the intelligent mining helmet at the monitoring moment.

4. The intelligent mining helmet communication dispatching method based on multi-modal data analysis of claim 1, wherein, The method for obtaining the future communication state representation value of the intelligent mining helmet at the current monitoring moment comprises: For any intelligent mining helmet in the target scheduling area at the current monitoring moment, a mean value of the predicted communication quality index values of the intelligent mining helmet at all the future monitoring moments in a preset future time period is recorded as a predicted mean value, a negatively correlated mapping result of a mean square error between the actual communication quality index value of the intelligent mining helmet at the historical monitoring moment in a preset historical time period before the current monitoring moment and the predicted communication quality index value of the intelligent mining helmet at the corresponding historical monitoring moment is recorded as a prediction reliability representation value, and a result of normalizing a product of the predicted mean value and the prediction reliability representation value is recorded as the future communication state representation value of the intelligent mining helmet at the current monitoring moment.

5. The intelligent mining helmet communication dispatching method based on multi-modal data analysis of claim 1, wherein, The method for obtaining the to-be-relayed link set and the relay set comprises: In all smart mining helmets in the target scheduling area at the current monitoring moment, a set of smart mining helmets with future communication state representation values less than a preset communication state threshold is denoted as a to-be-relayed link set, and a set of remaining smart mining helmets is denoted as a relay set.

6. The intelligent mining helmet communication dispatching method based on multi-modal data analysis of claim 1, wherein, According to the relay link priority and the link establishment degree, a method for performing communication scheduling on the smart mining helmets includes: According to the relay link priority, the link establishment degree, and the maximum load capacity of the relay helmet, the smart mining helmets in the to-be-relayed link set and the relay set are matched to obtain the matching relay helmet of the to-be-relayed link helmet in the to-be-relayed link set, and the to-be-relayed link helmet is linked in communication with the matching relay helmet corresponding to the to-be-relayed link helmet, and the relay helmet belongs to a relay node. The matching relay helmet of the to-be-relayed link helmet in the to-be-relayed link set is obtained by a matching algorithm according to the rules that the relay link priority in the to-be-relayed link helmet set is from high to low, the link establishment degree between the relay helmet and the to-be-relayed link helmet is from high to low, and the data amount carried by the relay helmet does not exceed the maximum load capacity of the relay helmet.

Images