A method and system for compressing and transmitting environmental data of a fire monitoring platform

Abstract

The present invention relates to the technical field of data compression, and in particular to a method and system for compressing and transmitting environmental data of a fire monitoring platform. The method comprises the steps of: performing revolving door compression on an environmental data curve, predicting subsequent data points based on previous data points during the compression process, obtaining the abnormalities of the data points and the predicted data points respectively, obtaining the dominance of the predicted data points in combination with the fitting errors of the data points and the fitting errors of the predicted data points, correcting the data points based on the dominance, continuing to perform revolving door compression based on the corrected data points, and sending the compression results to a fire monitoring platform so that the fire monitoring platform can perform fire management. The present invention realizes the correction of abnormal data points in the environmental data curve, reduces the degree of loss of environmental data, improves the compression efficiency of environmental data, and thereby improves the detection rate of fire hazards and the response speed of fire hazards.

Description

Technical Field

[0001] The present invention relates to the technical field of data compression, and in particular to a method and system for compressing and transmitting environmental data of a fire monitoring platform. Background Art

[0002] In the field of fire protection, real-time monitoring of environmental data such as smoke, temperature and gas concentration can promptly detect fire hazards, help fire departments to respond and rescue quickly, prevent accidents, reduce possible losses, and protect the safety of people and property.

[0003] Environmental data is in time series form and has a large amount of data. Compressing and transmitting environmental data can increase the transmission speed of environmental data, thereby increasing the response speed of fire hazards. For example, the patent document with publication number "CN117692011B" and titled "A monitoring data early warning method for fire rescue environmental monitoring system" and the patent document with publication number "CN117560718B" and titled "A fire IoT remote monitoring method based on crowd intelligence perception" both compress environmental data.

[0004] The revolving door compression algorithm is a relatively fast linear fitting algorithm suitable for compressing time series data. The essence of the revolving door compression algorithm is to replace a series of continuous data points with a straight line determined by the starting point and the end point to achieve compression. In the process of collecting environmental data, there may be anomalies in the collected environmental data due to noise and other reasons. If all environmental data are directly compressed by the revolving door, the abnormal data caused by noise and other factors may cause the loss of other environmental data to increase, thereby affecting the detection rate of fire hazards. At the same time, the abnormal data caused by noise will reduce the compression efficiency of environmental data, affect the transmission speed of environmental data, and thus reduce the response speed of fire hazards. Summary of the invention

[0005] In order to solve the problem that abnormal data will cause increased loss of other environmental data, reduced compression efficiency, affect the detection rate of fire hazards, and reduce the response speed of fire hazards, the present invention provides an environmental data compression and transmission method and system for a fire monitoring platform.

[0006] In a first aspect, the present invention provides a method for compressing and transmitting environmental data of a fire monitoring platform, which adopts the following technical solution:

[0007] A method for compressing and transmitting environmental data of a fire monitoring platform, comprising the steps of:

[0008] The environmental data curve is compressed using a revolving door compression algorithm, and the compression result is transmitted to a fire monitoring platform so that the fire monitoring platform can perform fire management; during the compression process, in response to the previous data point of the current data point in the environmental data curve being the starting data point of a line segment in the revolving door compression algorithm, the current data point is corrected and compressed, including: determining a smoothing coefficient based on the door opening angle difference between the previous two data points of the current data point, the smoothing coefficient being positively correlated with the angle difference; predicting the environmental data based on the smoothing coefficient and the data points in the door to obtain a predicted data point; in response to the distance between the predicted data point and the current data point being not less than a preset An error threshold is provided, wherein the abnormality of the current data point is determined according to the distribution difference between the current data point and the data points after the current data point, and the abnormality of the predicted data point is determined according to the distribution difference between the predicted data point and the data points after the current data point; the fitting error when the data points in the gate are represented by the current data point and the predicted data point is determined respectively; the dominance of the predicted data point is determined according to the difference between the abnormality of the current data point and the predicted data point and the corresponding difference in fitting errors, and the dominance is positively correlated with the difference in the abnormality and the difference in the fitting errors; in response to the dominance being greater than a preset dominance threshold, the current data point is corrected to the predicted data point.

[0009] The effect is as follows: in the process of revolving door compression of the environmental data curve by the present invention, the subsequent data points are predicted according to the previous data points, and the predicted data points that are more consistent with the distribution characteristics of the previous data points are obtained. The predicted data points are subsequently used to correct the current data points, thereby avoiding the influence of abnormal data points caused by noise on the compression effect, reducing the loss degree of other environmental data, improving the compression efficiency of environmental data, and thus improving the detection rate and response speed of fire hazards; the present invention determines the abnormality of the current data and the predicted data points according to the distribution of the data points after the current data points, and compares the fitting errors of the data points in the door when the current data points and the predicted data points are respectively used as the endpoints of the line segments, thereby selecting the data points that can bring better compression effects as the final compressed data points, so that the abnormal data points in the environmental data curve are corrected to normal values, avoiding the abnormal data points causing the loss degree of other environmental data points to increase, achieving a better compression effect, and further improving the detection rate and response speed of fire hazards.

[0010] In one embodiment, the determining of the smoothing coefficient includes: recording a data point before the current data point as a first data point, and recording a data point before the first data point as a second data point; the smoothing coefficient satisfies the expression: , represents the smoothing coefficient; It represents the internal angle of the door after opening the door according to the first data point; Indicates the inner angle of the lower door after opening the door according to the first data point; Indicates the internal angle of the door after opening the door according to the second data point; Indicates the inner angle of the lower door after opening the door according to the second data point.

[0011] The effect is that the present invention utilizes the difference in the inner angles of the upper or lower door after opening twice to reflect the distribution pattern of the data points before the current data point, and determines the smoothing coefficient based on the distribution pattern, so that the predicted data points subsequently obtained according to the smoothing coefficient are more in line with the distribution pattern of the data points before the current data point.

[0012] In one embodiment, the environmental data is predicted based on the smoothing coefficient and the data points inside the door to obtain the predicted data points, including: the data points inside the door include all data points from the data point corresponding to the fulcrum of the current door to the current data point; the data points inside the door are used as data samples, and the environmental data is predicted using the exponential smoothing method based on the data samples and the smoothing coefficient to obtain the predicted data points.

[0013] The effect is that the present invention predicts subsequent data points based on previous data points, and the obtained predicted data points are more consistent with the distribution characteristics of previous data points. The predicted data points are subsequently used to correct the current data points, avoiding the influence of abnormal data points caused by noise on the compression effect.

[0014] In one embodiment, determining the abnormality of the current data point based on the distribution difference between the current data point and the data points after the current data point includes: data points constitute the first data point sequence, where is the preset number of data points; the abnormality of the current data point is determined according to the distribution of data points in the first data point sequence: , Indicates the abnormality of the current data point; Indicates the current data point; Indicates the next data point of the current data point; Indicates the distance between the current data point and the next data point; represents a distance sequence consisting of the distances between every two adjacent data points in the first data point sequence; represents the standard deviation function; represents the mean function; Indicates the absolute value symbol; represents the hyperbolic tangent function.

[0015] The effect is that the present invention uses the distribution law of data points after the current data point to determine the abnormality of the current data point and the predicted data point, and uses the abnormality to reflect whether the current data point and the predicted data point conform to the distribution law of the data point after the current data point, thereby determining to a certain extent whether the predicted data point will be used to correct the current data point in the future, so that the abnormal data points in the environmental data curve are corrected to normal values ​​as much as possible, thereby achieving a better compression effect.

[0016] In one embodiment, determining the abnormality of the predicted data point based on the distribution difference between the predicted data point and the data points after the current data point includes: data points constitute the second data point sequence, where is the preset number of data points; the abnormality of the current data point is determined according to the distribution of data points in the second data point sequence: , Indicates the abnormality of the predicted data point; represents a predicted data point; Indicates the next data point of the current data point; Represents the distance between the predicted data point and the next data point of the current data point; represents a distance sequence formed by the distance between every two adjacent data points in the second data point sequence; represents the standard deviation function; represents the mean function; Indicates the absolute value symbol; represents the hyperbolic tangent function.

[0017] In one embodiment, the method of separately determining the fitting error when the data points in the gate are represented by the current data points and the predicted data points includes: the data point corresponding to the fulcrum of the current gate is the starting data point of the current gate, the line between the starting data point of the current gate and the current data point is used as the first fitting line segment, and the sum of the distances from the data points in the gate to the first fitting line segment is used as the fitting error corresponding to the current data point; the line between the starting data point of the current gate and the predicted data point is used as the second fitting line segment, and the sum of the distances from the data points in the gate to the second fitting line segment is used as the fitting error corresponding to the predicted data point.

[0018] In one embodiment, the dominance of the predicted data point satisfies the expression:

[0019] ;in, Indicates the dominance of the predicted data point; Indicates the abnormality of the current data point; Indicates the abnormality of the predicted data point; Indicates the fitting error corresponding to the current data point; Represents the fitting error corresponding to the predicted data point; sigmoid represents an S-shaped growth curve; Represents the absolute value symbol.

[0020] The effect is that the present invention combines the difference in abnormality between the current data point and the predicted data point, and the difference between the fitting errors to obtain the advantage of the predicted data point, and uses the advantage of the predicted data point to reflect whether the predicted data point is more in line with the changing trend of the environmental data curve than the current data point, so as to decide whether to use the predicted data point to correct the current data point, eliminate abnormal data points in the environmental data curve as much as possible, and avoid abnormal data points causing an increase in the loss of other environmental data points, thereby achieving a better compression effect.

[0021] In a second aspect, the present invention provides an environmental data compression and transmission system for a fire monitoring platform, which adopts the following technical solution:

[0022] A system for compressing and transmitting environmental data of a fire monitoring platform comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned method for compressing and transmitting environmental data of a fire monitoring platform is implemented.

[0023] By adopting the above technical solution, the environmental data compression and transmission method of the above-mentioned fire monitoring platform is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is made according to the memory and the processor for easy use.

[0024] The present invention has the following technical effects: the present invention corrects abnormal data points caused by noise and the like in an environmental data curve, thereby improving the compression efficiency of environmental data, reducing the degree of loss of environmental data, and thereby improving the detection rate and response speed of fire hazards; the present invention uses predicted data points that are more in line with the distribution law of environmental data points to correct abnormal data points, and the correction result is more accurate, avoiding the increase in the degree of loss of environmental data caused by abnormal data points, achieving a better compression effect, and further improving the detection rate and response speed of fire hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0026] Figure 1 This is a method flow chart of a method for compressing and transmitting environmental data of a fire monitoring platform according to an embodiment of the present invention;

[0027] Figure 2 It is a schematic diagram of a temperature curve in a method for compressing and transmitting environmental data of a fire monitoring platform according to an embodiment of the present invention;

[0028] Figure 3 It is a flow chart of a method for correcting a current data point in a method for compressing and transmitting environmental data of a fire monitoring platform in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0030] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0031] The embodiment of the present invention discloses a method for compressing and transmitting environmental data of a fire monitoring platform, referring to Figure 1 , comprising steps S1 to S3:

[0032] S1. Collect environmental data of the monitoring area at each moment and draw an environmental data curve based on the environmental data at each moment.

[0033] Sensors deployed in the monitoring area are used to collect environmental data at every moment, such as temperature, humidity, combustible gas concentration, smoke concentration, etc.

[0034] For any kind of environmental data collected, a rectangular coordinate system is constructed with time as the horizontal axis and the environmental data as the vertical axis. The environmental data at each moment is taken as a data point in the rectangular coordinate system, and the data points corresponding to the environmental data at all moments constitute the environmental data curve. Figure 2 is a schematic diagram of the temperature curve. Figure 2 A, B, and C are data points on the temperature curve respectively.

[0035] At this point, the construction of the environmental data curve has been achieved.

[0036] S2. Compress the environmental data curve to obtain compressed data.

[0037] The essence of the revolving door compression algorithm is to replace a series of continuous data points with multiple line segments, and only record the endpoints of the line segments to achieve compression. In the revolving door compression algorithm, two pivots are constructed with the starting data point, and two virtual doors are established with the pivots. At this time, the virtual door is a closed door, and the door is not opened, so it is called an unopened door. When a new data point is added, the virtual door will rotate and open, and it is called an open door. In the process of revolving door compression, when the sum of the internal angles of the upper door and the lower door corresponding to the data point is not less than 180°, the previous data point is recorded. The previous data point is the end data point of a line segment in the final compression result, and it is also the starting data point of the next line segment; when the sum of the internal angles of the upper door and the lower door corresponding to the data point is less than 180°, the previous data point is not recorded, and all the data points recorded in the end are the endpoints of the line segments in the revolving door compression process. In the revolving door compression algorithm, when a data point is recorded, the data point will be used as a new starting data point, and a new compression will start from this point. When a data point is not recorded, it will not be used as a new starting data point.

[0038] In the process of collecting environmental data, there may be anomalies in the collected environmental data due to noise and other reasons. Since the abnormal data deviates from the changing trend of normal environmental data, if all environmental data curves are directly compressed by a revolving door, the abnormal data may increase the loss of normal environmental data. At the same time, it may increase the number of line segments finally obtained, increase the number of endpoints of the recorded line segments, increase the amount of data, and affect the compression efficiency. Therefore, in the process of revolving door compression of environmental data, the present invention corrects possible abnormal data points according to the angle of the door and the distribution of data points in the door, thereby reducing the loss of normal data points, and reducing the number of line segments as much as possible to improve the compression efficiency. The abnormal data points in the present invention refer to data points that deviate from the actual environmental data due to factors such as noise in the collection process, rather than the corresponding data points when the actual environment is abnormal.

[0039] In one embodiment, the environmental data curve is compressed using a revolving door compression algorithm. During the compression process, before compressing each data point in the environmental data curve, the data point is judged. If the previous data point of the data point is the starting data point, the current data point is directly compressed; otherwise, the current data point is compressed after being modified.

[0040] The correction process is specifically as follows: a smoothing coefficient is determined based on the difference in door opening angles of the two data points preceding the current data point, the smoothing coefficient being positively correlated with the angle difference; environmental data is predicted based on the smoothing coefficient and the data points inside the door to obtain a predicted data point; in response to the distance between the predicted data point and the current data point being greater than a preset error threshold, the abnormality of the current data point is determined based on the distribution difference between the current data point and the data points after the current data point; the abnormality of the predicted data point is determined based on the distribution difference between the predicted data point and the data points after the current data point; the fitting error when the data points inside the door are represented by the current data point and the predicted data point is determined respectively; the dominance of the predicted data point is determined based on the difference between the abnormalities of the current data point and the predicted data point and the corresponding difference in fitting errors, the dominance is positively correlated with the difference in the abnormalities and the difference in fitting errors; in response to the dominance being greater than the preset dominance threshold, the current data point is corrected to the predicted data point.

[0041] Reference Figure 3 , correcting the current data point includes steps S21 to S24, which are as follows:

[0042] S21: Determine a smoothing coefficient based on the difference in door opening angles between the two data points before the current data point, and predict the environmental data based on the smoothing coefficient and the data points inside the door to obtain a predicted data point.

[0043] Specifically, the previous data point of the current data point is recorded as the first data point, and the previous data point of the first data point is recorded as the second data point. According to the difference in the door opening angle between the first data point and the second data point, the smoothing coefficient is obtained:

[0044]

[0045] in, represents the smoothing coefficient; It represents the internal angle of the door after opening the door according to the first data point; Indicates the inner angle of the lower door after opening the door according to the first data point; Indicates the internal angle of the door after opening the door according to the second data point; represents the inner angle of the lower door after opening the door according to the second data point; It indicates the difference in the inner angle of the door after opening it twice; It indicates the difference in the inner angle of the lower door after opening it twice; Used as a pair Normalize the data so that the smoothing coefficient is in the range of [0,1]. When the difference between the inner angles of the upper or lower door after opening the door twice is smaller, it means that the first data point has changed less than the previous data point, and the first data point is more likely to have the same change trend as the previous data point. At this time, the smoothing coefficient When the exponential smoothing method is used for prediction in the future, the predicted value can better reflect the overall change trend of the data points in the door; when the difference between the inner angles of the upper or lower door after opening the door twice is larger, it means that the first data point has changed more than the second data point, and the first data point may have brought new changes compared with the previous data point. At this time, the smoothing coefficient When the exponential smoothing method is used for subsequent prediction, more attention is paid to the new changes brought about by the first data point, so that the predicted value can better reflect the new changes.

[0046] The data points inside the gate are taken as data samples, and according to the data samples and the smoothing coefficient The exponential smoothing method is used to predict the environmental data at the time of the current data point, and the predicted value is taken as a data point in the rectangular coordinate system, recorded as the predicted data point. The time corresponding to the predicted data point is consistent with the time of the current data point.

[0047] The data points within the gate include all data points from the data point corresponding to the fulcrum of the current gate to the current data point.

[0048] S22: In response to the distance between the predicted data point and the current data point being greater than a preset error threshold, determining the abnormality of the current data point based on the distribution difference between the current data point and data points after the current data point, and determining the abnormality of the predicted data point based on the distribution difference between the predicted data point and data points after the current data point.

[0049] It should be noted that if the data point inside the gate is located before the current data point, the predicted data point is consistent with the change trend of the data point inside the gate. If the distance between the predicted data point and the current data point is very small, it means that the current data point also conforms to the change trend of the data point inside the gate. If the distance between the predicted data point and the current data point is large, it means that the current data point does not conform to the change trend of the data point inside the gate. The current data point may be an abnormal data point caused by noise in the process of environmental data collection, or it may be a data point close to the turning point after the turning point of the trend change of environmental data. For example Figure 2 The data point A is an abnormal data point, which does not match the changing trend of the data points before A, nor does it match the changing trend of the data points after A. Figure 3 Data point B is the turning point of the temperature data trend change. The data points before data point B show an overall increasing trend, and the data points after data point B show an overall decreasing trend. Figure 3 The data point C in the middle is a data point that is closer to the turning point after the turning point of the temperature data trend change. Data point C does not conform to the changing trend of the data points before C, but conforms to the changing trend of the data points after C.

[0050] In one embodiment, the distance between the predicted data point and the current data point is obtained and recorded as the prediction error. An error threshold is preset The present invention does not limit the specific value of the error threshold K, and the implementer can set it according to the actual implementation situation, for example ,in Represents the maximum value of the environmental data at all times, Indicates the minimum value of the environmental data at all times.

[0051] When the prediction error is less than the preset error threshold , it means that the difference between the predicted data point and the current data point is very small, and the current data point is not corrected at this time.

[0052] When the prediction error is not less than the preset error threshold When , the abnormality of the current data point is determined based on the distribution difference between the current data point and the data points after the current data point, and the abnormality of the predicted data point is determined based on the distribution difference between the predicted data point and the data points after the current data point.

[0053] It should be noted that if the current data point is a data point that is closer to the turning point after the turning point of the environmental data trend change, although the current data point does not conform to the change trend of the data points in the gate, it conforms to the change trend of the data points after the current data point. For example Figure 2 If the current data point is an abnormal data point, it does not conform to the change trend of the data points in the gate, nor does it conform to the change trend of the data points after the current data point. For example Figure 3 Therefore, the present invention analyzes the abnormality of the current data point and the predicted data point in combination with the distribution of the data points after the current data point.

[0054] In one embodiment, the process of determining the abnormality of the current data point based on the distribution difference between the current data point and the data points after the current data point is as follows:

[0055] Preset number of data points The present invention is There is no specific limit on the value of ,For example .

[0056] The current data point and the adjacent Data points constitute the first data point sequence, and the abnormality of the current data point is determined according to the distribution of data points in the first data point sequence:

[0057]

[0058] in, Indicates the abnormality of the current data point; Indicates the current data point; Indicates the next data point of the current data point; Indicates the distance between the current data point and the next data point; represents a distance sequence consisting of the distances between every two adjacent data points in the first data point sequence; represents the standard deviation function; represents the mean function; Indicates the absolute value symbol; represents the hyperbolic tangent function.

[0059] The standard deviation of the distance sequence formed by the distance between each two adjacent data points in the first data point sequence reflects the fluctuation range of the distance between two adjacent data points in the first data point sequence; Represents the difference between the distance between the current data point and the next data point and the mean distance between each two adjacent data points in the first data point sequence. The smaller it is, the more the current data point conforms to the trend of the subsequent data points, and the smaller the abnormality of the current data point; The larger it is, the less the current data point conforms to the trend of the subsequent data points, and the greater the abnormality of the current data point.

[0060] The process of determining the abnormality of a predicted data point based on the distribution difference between the predicted data point and the data points after the current data point is as follows:

[0061] The predicted data point and the adjacent data points constitute the second data point sequence, where It should be noted that the second data point sequence does not include the current data point.

[0062] Determine the abnormality of the predicted data point based on the distribution of data points in the second data point sequence:

[0063]

[0064] in, Indicates the abnormality of the predicted data point; represents a predicted data point; Indicates the next data point of the current data point; Represents the distance between the predicted data point and the next data point of the current data point; represents a distance sequence formed by the distance between every two adjacent data points in the second data point sequence; represents the standard deviation function; represents the mean function; Indicates the absolute value symbol; tanh represents the hyperbolic tangent function.

[0065] The standard deviation of the distance sequence formed by the distance between each two adjacent data points in the second data point sequence reflects the fluctuation range of the distance between two adjacent data points in the second data point sequence; Represents the difference between the distance between the predicted data point and the next data point of the current data point and the mean distance between each two adjacent data points in the second data point sequence. The smaller it is, the more the predicted data point conforms to the trend of the data points after the current data point, and the smaller the abnormality of the predicted data point; When the value is larger, the predicted data point does not conform to the trend of the data points after the current data point, and the predicted data point is more abnormal.

[0066] At this point, the abnormalities of the current data point and the predicted data point are obtained.

[0067] S23: respectively determining the fitting errors when the data points within the gate are represented by the current data points and the predicted data points, and determining the dominance of the predicted data points according to the difference in abnormality between the current data points and the predicted data points and the difference in the corresponding fitting errors.

[0068] It should be noted that the essence of the revolving door compression algorithm is to represent a series of continuous data points with line segments, and use the endpoints of the line segments to achieve compression. In this process, there will be a certain loss of data points. The smaller the loss of data points, the better the selected line segments. For the current data point and the predicted data point, it is very likely to be an endpoint of the line segment. Therefore, the present invention calculates the fitting error when the current data point is used as the endpoint of the line segment, and the fitting error when the predicted data point is used as the endpoint of the line segment, so as to obtain the advantage of the predicted data point by combining the abnormality of the current data point and the predicted data point, and then correct the current data point, thereby improving the compression effect of the final environmental data curve.

[0069] Specifically, the data point corresponding to the fulcrum of the current gate is the starting data point of the current gate, the line between the starting data point of the current gate and the current data point is used as the first fitting line segment, and the sum of the distances from the data points in the gate to the first fitting line segment is used as the fitting error corresponding to the current data point.

[0070] Similarly, the line between the starting data point of the current gate and the predicted data point is used as the second fitting line segment, and the sum of the distances from the data points in the gate to the second fitting line segment is used as the fitting error corresponding to the predicted data point.

[0071] According to the difference between the abnormality of the current data point and the predicted data point and the difference of the corresponding fitting error, the dominance of the predicted data point is determined:

[0072] ;

[0073] in, Indicates the dominance of the predicted data point; Indicates the abnormality of the current data point; Indicates the abnormality of the predicted data point; Indicates the fitting error corresponding to the current data point; Represents the fitting error corresponding to the predicted data point; sigmoid represents an S-shaped growth curve; Indicates the absolute value symbol; when When it is greater than 0, the abnormality of the current data point is greater than that of the predicted data point. The predicted data point is more consistent with the change trend of the data points before and after the current data point than the current data point. The current data point may be affected by noise and is relatively abnormal. At this time, if the predicted data point is used to replace the current data point, the current data point can be corrected. When it is not greater than 0, the abnormality of the current data point is not greater than the abnormality of the predicted data point, the current data point conforms to the change trend of the previous and next data points, and the current data point is a normal data point. At this time, it is less necessary to replace the current data point with the predicted data point. When is greater than or equal to 0, the fitting error caused by using the predicted data points to compress the data points in the gate is smaller than the fitting error caused by using the current data points to compress the data points in the gate. At this time, it is more appropriate to use the predicted data points instead of the current data points. Therefore, As The exponent of Make corrections so that Expand, when The bigger it is, The smaller, the The greater the expansion, the greater the advantage of the predicted data point. When it is less than 0, the fitting error caused by using the current data point to compress the data points in the gate is smaller than the fitting error caused by using the predicted data point to compress the data points in the gate. At this time, the effect of using the predicted data point to replace the current data point is poor. Therefore, As The exponent of Make corrections so that Reduce, when The more hours, The bigger, yes The greater the reduction, the less advantageous the predicted data point is.

[0074] At this point, the dominance of the predicted data points is obtained.

[0075] S24: In response to the advantage being greater than a preset advantage threshold, the current data point is corrected to be a predicted data point.

[0076] Specifically, a dominant threshold is preset. The present invention does not specifically limit the dominant threshold, and implementers can set the dominant threshold according to actual implementation conditions, for example, 0.7.

[0077] When the dominance of the predicted data point is less than or equal to the preset dominance threshold, the current data point is retained and no correction is made to the current data point; when the dominance of the predicted data point is greater than the preset dominance threshold, the predicted data point is used to replace the current data point on the environmental data curve to achieve correction of the current data point.

[0078] At this point, the correction of the current data point is achieved.

[0079] Through step S2, the environmental data is compressed to obtain compressed data.

[0080] S3. Send the compression result to the fire monitoring platform so that the fire monitoring platform can decompress the compressed data and identify fire hazards based on the decompression result.

[0081] The compressed data is transmitted to the fire monitoring platform, and the compressed data is decompressed using the decompression method in the revolving door compression algorithm to obtain environmental data. It should be noted that the decompression method in the revolving door compression algorithm is a well-known technology and will not be described in detail here.

[0082] The fire monitoring platform identifies whether there are fire hazards in the monitoring area based on environmental data and issues early warnings based on the identification results.

[0083] An embodiment of the present invention also discloses an environmental data compression and transmission system for a fire monitoring platform, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, an environmental data compression and transmission method for a fire monitoring platform according to the present invention is implemented.

[0084] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0085] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0086] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for compressing and transmitting environmental data of a fire monitoring platform, characterized in that: include: The environmental data curve is compressed using a revolving door compression algorithm, and the compression result is sent to a fire monitoring platform so that the fire monitoring platform can perform fire management; during the compression process, in response to a previous data point of a current data point in the environmental data curve being a starting data point of a line segment in the revolving door compression algorithm, the current data point is corrected and compressed, including: Determining the smoothing coefficient based on the difference in door opening angles between the two data points before the current data point includes: The previous data point of the current data point is recorded as the first data point, and the previous data point of the first data point is recorded as the second data point; the smoothing coefficient satisfies the expression: , represents the smoothing coefficient; It represents the internal angle of the door after opening the door according to the first data point; Indicates the inner angle of the lower door after opening the door according to the first data point; Indicates the internal angle of the door after opening the door according to the second data point; Indicates that the inner angle of the lower door after the door is opened according to the second data point, the smoothing coefficient is positively correlated with the angle difference; predicting the environmental data according to the smoothing coefficient and the data points inside the door, and obtaining the predicted data points includes: the data points inside the door include all data points from the data point corresponding to the fulcrum of the current door to the current data point; using the data points inside the door as data samples, predicting the environmental data using the exponential smoothing method according to the data samples and the smoothing coefficient to obtain the predicted data points; in response to the distance between the predicted data point and the current data point being not less than a preset error threshold, determining the abnormality of the current data point according to the distribution difference between the current data point and the data points after the current data point includes: comparing the current data point with the adjacent data points after the current data point data points constitute the first data point sequence, where is the preset number of data points; the abnormality of the current data point is determined according to the distribution of data points in the first data point sequence: , Indicates the abnormality of the current data point; Indicates the current data point; Indicates the next data point of the current data point; Indicates the distance between the current data point and the next data point; The distance sequence is formed by the distance between each two adjacent data points in the first data point sequence. Determining the abnormality of the predicted data point according to the distribution difference between the predicted data point and the data points after the current data point includes: data points constitute the second data point sequence; the abnormality of the current data point is determined according to the distribution of the data points in the second data point sequence: , Indicates the abnormality of the predicted data point; represents a predicted data point; Represents the distance between the predicted data point and the next data point of the current data point; Representing a distance sequence formed by the distance between each two adjacent data points in the second data point sequence; respectively determining the fitting error when the data points in the gate are represented by the current data point and the predicted data point, including: the data point corresponding to the fulcrum of the current gate is the starting data point of the current gate, the line between the starting data point of the current gate and the current data point is used as the first fitting line segment, and the sum of the distances from the data points in the gate to the first fitting line segment is used as the fitting error corresponding to the current data point; the line between the starting data point of the current gate and the predicted data point is used as the second fitting line segment, and the sum of the distances from the data points in the gate to the second fitting line segment is used as the fitting error corresponding to the predicted data point; determining the dominance of the predicted data point according to the difference in abnormality between the current data point and the predicted data point and the difference in the corresponding fitting error, wherein the dominance is positively correlated with the difference in the abnormality and the difference in the fitting error; in response to the dominance being greater than a preset dominance threshold, correcting the current data point to the predicted data point; The dominance of the predicted data point satisfies the expression: ； in, Indicates the dominance of the predicted data point; Indicates the abnormality of the predicted data point; Indicates the fitting error corresponding to the current data point; Represents the fitting error corresponding to the predicted data point; sigmoid Represents an S-shaped growth curve.

2. An environmental data compression and transmission system for a fire monitoring platform, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the environmental data compression and transmission method of a fire monitoring platform according to claim 1 is implemented.

Images