A diffused intelligent oxygen supply device and dynamic control system

Abstract

The present application relates to oxygen supply control technical field, specifically to a kind of diffused intelligent oxygen supply equipment and dynamic control system.Equipment includes memory and processor, processor executes computer program stored in memory, to realize the following steps: the oxygen concentration and monitoring image of different monitoring points in oxygen supply space are obtained;According to the oxygen concentration and position of each monitoring point, obtain abnormal factor, determine key point and non-key point;According to the movement of target personnel in the monitoring image of the area where each key point is located, feature corner and the distance between target personnel and key point, obtain activity frequency;The reference coefficient of key point is determined by combining the stay time of each target personnel in the area where each key point is located, activity frequency and abnormal factor;According to the reference coefficient of key point, the oxygen concentration of key point and the oxygen concentration of non-key point, determine comprehensive oxygen concentration data, adjust the oxygen concentration of oxygen supply equipment.The present application improves the dynamic control precision of oxygen concentration.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oxygen supply control, in particular to a diffused intelligent oxygen supply equipment and a dynamic control system. BACKGROUND

[0002] In plateau areas, the air density is often lower due to altitude, causing partial hypoxia of the body cells, and thus causing altitude sickness. Long-term severe hypoxia can even cause pulmonary heart disease and mental and nervous symptoms, with serious consequences, especially for people from the plains who are not tolerant to the plateau, the impact is more obvious. Therefore, some residences provide oxygen supply services, for example: diffused oxygen supply system is mainly used for diffused oxygen supply in hypoxic environment. Diffused oxygen supply mainly changes the oxygen content in a certain space, and provides a stable oxygen-rich environment for a specific space (such as a residence in a plateau area) to improve the oxygen content in the air.

[0003] The measurement accuracy of the oxygen sensor is easily disturbed by static electricity, personnel activities, ventilation and the like. When monitoring the oxygen concentration in the living room, the average value of the oxygen concentration data of all monitoring points in the living room at the same time is generally obtained to reflect the overall oxygen concentration distribution in the living room. However, when multiple monitoring points simultaneously exist oxygen concentration fluctuations caused by local factors (such as ventilation, personnel activities, etc.), the oxygen concentration monitoring data will be inaccurate, resulting in incorrect oxygen regulation decisions by the equipment and reducing the accuracy of the oxygen concentration control of the oxygen supply equipment in the living room of the plateau residence. SUMMARY

[0004] In order to solve the problem of inaccurate oxygen concentration monitoring results when supplying oxygen to a certain space, resulting in incorrect oxygen regulation decisions by the equipment, the purpose of the present application is to provide a diffused intelligent oxygen supply equipment and a dynamic control system, and the technical solution adopted is as follows:

[0005] In a first aspect, the present application provides a diffused intelligent oxygen supply equipment, which comprises a memory and a processor. The processor executes a computer program stored in the memory to realize the following steps:

[0006] Obtain the oxygen concentration of different monitoring points in the oxygen supply space and the monitoring image of the area where the different monitoring points are located;

[0007] According to the fluctuation of the oxygen concentration of each monitoring point in the current time period, obtain the oxygen concentration fluctuation coefficient of each monitoring point; combine the differences in the change characteristics of the oxygen concentration of different monitoring points in the current time period, the relative distance and the oxygen concentration fluctuation coefficient, obtain the abnormal factor of the oxygen concentration of each monitoring point, and determine the key point and the non-key point;

[0008] According to the motion of the target person in the monitoring image of the area where each key point is located, the feature corner and the distance between the target person and the key point in the current time period, the activity frequency of each target person in the area where each key point is located is obtained; the reference coefficient of the key point is determined by combining the stay time, the activity frequency and the abnormal factor of each target person in the area where each key point is located; and the comprehensive oxygen concentration data is determined according to the reference coefficient of the key point, the oxygen concentration of the key point at the current time and the oxygen concentration of the non-key point.

[0009] Based on the comprehensive oxygen concentration data, the oxygen supply concentration of the oxygen supply equipment is adjusted.

[0010] The combination of the difference of the change characteristics of the oxygen concentration of different monitoring points in the current time period, the relative distance and the oxygen concentration fluctuation coefficient obtains the abnormal factor of the oxygen concentration of each monitoring point, including:

[0011] For any monitoring point:

[0012] According to the DTW distance between the second-order difference sequence of the sequence composed of the oxygen concentration of the any monitoring point in the current time period and the second-order difference sequence of the sequence composed of the oxygen concentration of each of the other monitoring points, and the difference of the oxygen concentration fluctuation coefficients of the any monitoring point and each of the other monitoring points, the oxygen concentration fluctuation consistency factor of the any monitoring point and each of the other monitoring points is obtained, and the DTW distance and the difference of the oxygen concentration fluctuation coefficients are negatively correlated with the oxygen concentration fluctuation consistency factor.

[0013] According to the oxygen concentration fluctuation consistency factor and the distance of the any monitoring point and all the other monitoring points, the abnormal factor of the oxygen concentration of the any monitoring point is obtained.

[0014] Preferably, the oxygen concentration fluctuation coefficient of each monitoring point is obtained according to the fluctuation of the oxygen concentration of each monitoring point in the current time period, including:

[0015] For any monitoring point:

[0016] The extreme points of the oxygen concentration curve of the any monitoring point are obtained, and the oxygen concentration curve is obtained by curve fitting the sequence composed of the oxygen concentration of the any monitoring point in the current time period;

[0017] The normalized result of the oxygen concentration difference between each extreme point and its previous extreme point is recorded as the first feature value of each extreme point; the normalized result of the time interval between each extreme point and its previous extreme point is recorded as the second feature value of each extreme point; and the extreme point whose first feature value is greater than a preset first threshold value and whose second feature value is less than a preset second threshold value is recorded as a candidate point.

[0018] The time period between the time instants corresponding to every two adjacent candidate points in chronological order constitutes a key time period;

[0019] The oxygen concentration fluctuation coefficient of the any monitoring point is obtained according to the average value of the time interval between all adjacent key time periods of the any monitoring point in the current time period, the length of each key time period, the average value of the change rate of the candidate points of each key time period, and the number of the candidate points of the any monitoring point in the current time period;

[0020] The change rate is the ratio of the first characteristic value to the second characteristic value.

[0021] Preferably, the abnormality factor of the oxygen concentration of the any monitoring point is obtained according to the oxygen concentration fluctuation consistency factor and the distance of the any monitoring point and all other monitoring points, and the abnormality factor of the oxygen concentration of the any monitoring point is obtained according to the oxygen concentration fluctuation consistency factor and the distance of the any monitoring point and all other monitoring points.

[0022] The ratio between the oxygen concentration fluctuation consistency factor of the any monitoring point and each other monitoring point and the distance between the any monitoring point and the same other monitoring point is recorded as the first ratio of the any monitoring point and each other monitoring point.

[0023] The abnormality factor of the oxygen concentration of the any monitoring point is obtained by synthesizing the first ratios of the any monitoring point and all other monitoring points, and the first ratio is negatively correlated with the abnormality factor.

[0024] Preferably, the key points and non-key points are determined, including: determining the monitoring points with the abnormality factor greater than a preset abnormality threshold as key points, and determining the monitoring points with the abnormality factor less than or equal to the preset abnormality threshold as non-key points.

[0025] Preferably, the activity frequency of each target person in the area where each key point is located is obtained according to the movement of the target person, the feature corner point, and the distance between the target person and the key point in the monitoring image of the area where each key point is located in the current time period.

[0026] For any key point:

[0027] The feature corner points of the same target person in adjacent two frames of monitoring images in the area where the any key point is located are matched by using a feature matching algorithm to obtain a feature corner point matching pair, and a motion characteristic value corresponding to the feature corner point matching pair is obtained based on the positions of the two feature points in the feature corner point matching pair.

[0028] The activity frequency of each target person in the area where the any key point is located is obtained by synthesizing all motion characteristic values corresponding to each target person in the area where the any key point is located, the number of feature corner points of each target person in the area where the any key point is located in each frame of monitoring images, and the distance between each target person and the any key point.

[0029] Preferably, the reference coefficient of the key point is determined by combining the stay duration, activity frequency and abnormal factor of each target person in the area where the key point is located, including:

[0030] For any key point:

[0031] The interference value of the oxygen concentration of the any key point caused by the activity of the person is obtained by combining the stay duration and activity frequency of each target person in the area where the any key point is located in the current time period, and the stay duration and the activity frequency are positively correlated with the interference value;

[0032] The reference coefficient of the any key point is obtained according to the abnormal factor of the oxygen concentration of the any monitoring point and the interference value of the oxygen concentration of the any key point caused by the activity of the person, and the abnormal factor is negatively correlated with the reference coefficient, and the interference value is positively correlated with the reference coefficient.

[0033] Preferably, the comprehensive oxygen concentration data is determined according to the reference coefficient of the key point, the oxygen concentration of the key point at the current time and the oxygen concentration of the non-key point, including:

[0034] The ratio between the reference coefficient of each monitoring point and the cumulative sum of the reference coefficients of all monitoring points is taken as the weight of each monitoring point;

[0035] The oxygen concentrations of all monitoring points at the current time are weighted and summed by using the weight to obtain the comprehensive oxygen concentration data;

[0036] The reference coefficient of the non-key point is greater than the reference coefficient of the reference point, and the reference coefficient of the non-key point is a preset value.

[0037] Preferably, the oxygen concentration of the oxygen supply device is adjusted based on the comprehensive oxygen concentration data, including:

[0038] The comprehensive oxygen concentration data is input into the PID controller, and the PID controller sends an adjustment instruction to the oxygen supply device to adjust the oxygen concentration.

[0039] In a second aspect, the present application provides a dynamic control system for diffuse intelligent oxygen supply, which is used to realize the method executed by the device, and the system comprises:

[0040] A data acquisition module is configured to acquire the oxygen concentrations of different monitoring points in the oxygen supply space and the monitoring images of the areas where the different monitoring points are located.

[0041] The classification module is used for obtaining an oxygen concentration fluctuation coefficient of each monitoring point according to fluctuation conditions of the oxygen concentration of each monitoring point in the current time period; combining the differences in the change characteristics of the oxygen concentration of different monitoring points, the relative distances and the oxygen concentration fluctuation coefficient, obtaining an abnormal factor of the oxygen concentration of each monitoring point, and determining key points and non-key points;

[0042] The determination module is used for obtaining the activity frequency of each target person in the area where each key point is located according to the movement conditions of the target person, the feature corner and the distance between the target person and the key point in the monitoring image of the area where each key point is located in the current time period; combining the stay duration, the activity frequency and the abnormal factor of each target person in the area where each key point is located, determining the reference coefficient of the key point; and determining the comprehensive oxygen concentration data according to the reference coefficient of the key point, the oxygen concentration of the key point at the current moment and the oxygen concentration of the non-key point.

[0043] The regulation and control module is used for adjusting the oxygen supply concentration of the oxygen supply equipment based on the comprehensive oxygen concentration data.

[0044] The present application has at least the following beneficial effects:

[0045] The present application firstly analyzes the fluctuation conditions of the oxygen concentration collected by a single monitoring point in the oxygen supply space in the current time period, obtains the oxygen concentration fluctuation coefficient, then combines the differences in the change characteristics of the oxygen concentration of different monitoring points and the relative distances, determines the abnormal factor of the oxygen concentration of the single monitoring point, and divides the monitoring points into key points and non-key points based on the size of the abnormal factor, then combines the movement characteristics of the target person in the monitoring image of the area where each key point is located to evaluate the activity frequency of the target person, combines the stay duration and the abnormal factor of each target person in the area where each key point is located to determine the reference coefficient of the key point, reduces the reference degree of the monitoring data of the position with high abnormal degree, and improves the reference degree of the monitoring data of the normal position, so as to obtain the comprehensive oxygen concentration data which can more accurately reflect the real oxygen concentration of the oxygen supply space, and improve the oxygen concentration dynamic control precision. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0047] Figure 1 The flow chart of the method executed by the dispersion type intelligent oxygen supply equipment provided by the embodiments of the present application. DETAILED DESCRIPTION

[0048] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined object of the application, a kind of diffuse intelligent oxygen supply equipment and dynamic control system according to the present application are described in detail as follows by combining with the preferred embodiments and the drawings.

[0049] 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 to which this application belongs.

[0050] The specific scheme of the diffuse intelligent oxygen supply equipment and dynamic control system provided by the present application is described in detail below in combination with the drawings.

[0051] An embodiment of a diffuse intelligent oxygen supply equipment:

[0052] The specific scenario to which the present embodiment is directed is that in the process of diffuse oxygen supply to a space, the oxygen supply strategy of the oxygen supply equipment needs to be adjusted in real time in combination with the oxygen concentration in the space, so it is necessary to ensure that the collected oxygen concentration data is as close as possible to the real oxygen concentration in the air. Oxygen concentration is often measured by oxygen sensors, and the measurement accuracy of oxygen sensors is easily affected by static electricity, ventilation and other interference, resulting in that the oxygen concentration data collected by oxygen sensors in areas with large interference is not reliable. Therefore, the present embodiment will combine the interference received by the oxygen sensor to assign different adjustment weights to sensors with different interference degrees, to obtain oxygen concentration data that can reflect the real oxygen concentration of the space, and then accurately regulate and control the oxygen supply strategy of the oxygen supply equipment.

[0053] The diffuse intelligent oxygen supply equipment of the present embodiment includes a memory and a processor. The processor executes the computer program stored in the memory to realize the steps as shown in Figure 1 The specific steps are as follows:

[0054] Step S1, obtain the oxygen concentration of different monitoring points in the oxygen supply space and the monitoring image of the area where the different monitoring points are located.

[0055] Diffuse oxygen supply includes diffuse oxygen supply of the whole space and diffuse oxygen supply of the local space. The whole space diffuse oxygen supply is to deliver oxygen through the oxygen supply end like the whole building space, increase the oxygen concentration in the whole building, and achieve the oxygen supply effect. Since the living room is the main space for family gathering and social interaction in highland residence, it is usually affected by multiple environmental factors, such as air flow, ventilation equipment, opening and closing of windows, personnel activities, etc. The interference factors received by the oxygen sensor are more, and the oxygen concentration changes more obviously. Therefore, the present embodiment takes the living room area in highland residence as an example to dynamically control the oxygen supply amount of the oxygen supply equipment, i.e. the living room is the oxygen supply space.

[0056] Firstly, a plurality of monitoring points are uniformly arranged in the oxygen supply space, and an optical oxygen sensor is used to collect the oxygen concentration in the current time period. In this embodiment, the collection frequency of the oxygen concentration is one time per second. In specific applications, the implementer can set the collection frequency of the oxygen concentration and the number of monitoring points according to the specific circumstances, and this will not be described in more detail here. At the same time, a high-definition camera is installed at each monitoring point to continuously collect monitoring images of the area where each monitoring point is located in the current time period. Each collected frame of monitoring image is preprocessed, including grayscale, mean filter denoising and other operations. Image preprocessing is prior art, and will not be described in more detail here. It should be noted that the monitoring images mentioned later are all preprocessed monitoring images. The current time period is a set of all historical moments and the current moment, and the time interval between the current moment and the current moment is less than or equal to the preset time length. In this embodiment, the preset time length is 20 minutes, which can be set by the implementer according to the specific circumstances in specific applications.

[0057] At this point, the oxygen concentration of each monitoring point at each moment in the current time period and the monitoring image of the area where each monitoring point is located have been collected.

[0058] In step S2, the oxygen concentration fluctuation coefficient of each monitoring point is obtained according to the fluctuation of the oxygen concentration of each monitoring point in the current time period; the abnormal factor of the oxygen concentration of each monitoring point is obtained in combination with the difference in the change characteristics of the oxygen concentration of different monitoring points in the current time period, the relative distance and the oxygen concentration fluctuation coefficient; and the key point and the non-key point are determined.

[0059] In a short period of time, if the oxygen concentration of a certain monitoring point suddenly and greatly jumps, and such rapid change is unlikely to occur under normal circumstances, it indicates that the sensor itself has failed or has been disturbed by the external environment.

[0060] Next, this embodiment will be described taking one monitoring point as an example. The method provided in this embodiment can be used to process other monitoring points.

[0061] Specifically, for any monitoring point:

[0062] The oxygen concentrations of the monitoring point at all moments in the current time period are arranged in chronological order to obtain an oxygen concentration sequence of the monitoring point. The least squares method is used to curve fit the data in the oxygen concentration sequence to obtain an oxygen concentration curve of the monitoring point. The abscissa of the oxygen concentration curve is the collection moment, and the ordinate is the oxygen concentration.

[0063] An extreme point of the oxygen concentration curve of the monitoring point is obtained. A normalized result of an oxygen concentration difference between each extreme point and its previous extreme point is recorded as a first characteristic value of each extreme point; a normalized result of a time interval between each extreme point and its previous extreme point is recorded as a second characteristic value of each extreme point; and a ratio between the first characteristic value and the second characteristic value of each extreme point is taken as a change rate of each extreme point. The oxygen concentration difference between two extreme points is obtained by calculating an absolute value of a difference between the oxygen concentrations of the two extreme points, and taking the absolute value as the oxygen concentration difference between the two extreme points. There are many methods for normalizing the oxygen concentration difference and the time interval, for example, a maximum-minimum value normalization method can be selected for processing, or other data normalization methods can be selected for processing, which will not be described in detail here. Since the monitoring point with a suddenly increased fluctuation amplitude is more likely to be a key point, an extreme point with a first characteristic value greater than a preset first threshold value and a second characteristic value less than a preset second threshold value is recorded as a candidate point; in this embodiment, the preset first threshold value is 0.6, and the preset second threshold value is 0.4, which can be set according to specific conditions in specific applications.

[0064] In chronological order, a time period between time points corresponding to every two adjacent candidate points constitutes a key time period, that is, a time period with the first candidate point as a starting point and the second candidate point as a terminal point belongs to a key time period; a time period with the third candidate point as a starting point and the fourth candidate point as a terminal point belongs to a key time period; a time period with the fifth candidate point as a starting point and the sixth candidate point as a terminal point belongs to a key time period; and so on, to obtain a plurality of key time periods. It should be noted that if the number of candidate points is odd, the last candidate point is not analyzed.

[0065] The time interval between every two adjacent key time periods of the monitoring point in the current time period is obtained respectively, and there is a time interval between every two adjacent key time periods. The average value of the time intervals between all adjacent key time periods of the monitoring point in the current time period is calculated. According to the average value of the time intervals between all adjacent key time periods of the monitoring point in the current time period, the length of each key time period, the average value of the change rates of the candidate points of each key time period, and the number of the candidate points of the monitoring point in the current time period, the oxygen concentration fluctuation coefficient of the monitoring point is obtained.

[0066] In this embodiment, a specific calculation formula of the oxygen concentration fluctuation coefficient is given. The oxygen concentration fluctuation coefficient of the vth monitoring point can be expressed as:

[0067]

[0068] wherein, the oxygen concentration fluctuation coefficient of the vth monitoring point, an average value of time intervals between all adjacent key time periods of the vth monitoring point in the current time period, an average value of time intervals between all adjacent key time periods of the vth monitoring point in the current time period, a number of key time periods of the vth monitoring point in the current time period, a time length of the nth key time period of the vth monitoring point in the current time period, an average value of variation rates of all candidate points of the nth key time period of the vth monitoring point in the current time period, a normalization function.

[0069] For characterizing the attention factor of the vth monitoring point in the oxygen-provided environment, the smaller the average value of time intervals between all adjacent key time periods of the vth monitoring point in the current time period is, the more frequently the abnormal fluctuation of oxygen concentration occurs, and the more attention is needed. The longer the time length of the key time period is, the more time of abnormal fluctuation is, and the more analysis is needed. The larger the oxygen concentration fluctuation coefficient is, the more likely the oxygen concentration at the position of the vth monitoring point suddenly and greatly jumps, and the more attention is needed.

[0070] When the living room is ventilated, due to the large air pressure difference between the inside and outside, air convection is generated between the inside and outside of the living room during ventilation, thereby affecting the oxygen concentration changes of each oxygen concentration monitoring point inside the living room. The oxygen concentration at each position will fluctuate, and therefore the more consistent the oxygen concentration fluctuations at each position are, the more likely the oxygen concentration fluctuations are caused by ventilation.

[0071] Next, still taking one monitoring point as an example for description.

[0072] Specifically, for any monitoring point:

[0073] According to the time sequence, the oxygen concentrations of all collection time points of each monitoring point in the current time period are arranged to obtain an oxygen concentration sequence of each monitoring point, and each monitoring point has a corresponding oxygen concentration sequence. The second-order difference sequence of each oxygen concentration sequence is calculated.

[0074] According to the DTW distance between the second-order difference sequence of the oxygen concentration sequence of the monitoring point and the second-order difference sequences of the oxygen concentration sequences of other monitoring points, and the difference between the oxygen concentration fluctuation coefficients of the monitoring point and other monitoring points, an oxygen concentration fluctuation consistency factor of the monitoring point and other monitoring points is obtained, and the DTW distance and the difference between the oxygen concentration fluctuation coefficients are both negatively correlated with the oxygen concentration fluctuation consistency factor.

[0075] The ratio between the consistency factor of the oxygen concentration fluctuation of the monitoring point and each other monitoring point and the distance between the monitoring point and the same other monitoring point is recorded as the first ratio of the monitoring point and each other monitoring point, and there is a first ratio between the monitoring point and each other monitoring point. The first ratio of the monitoring point and all other monitoring points is integrated to obtain the abnormal factor of the oxygen concentration of the monitoring point, and the first ratio is negatively correlated with the abnormal factor.

[0076] In the embodiment, the calculation formula of the abnormal factor is given, and the abnormal factor of the oxygen concentration of the vth monitoring point can be expressed as:

[0077]

[0078] The abnormal factor of the oxygen concentration of the vth monitoring point is represented as The number of monitoring points is represented as The difference between the oxygen concentration fluctuation coefficient of the vth monitoring point and the wth monitoring point other than the vth monitoring point is represented as The DTW distance between the second-order difference sequence of the oxygen concentration sequence of the vth monitoring point and the second-order difference sequence of the oxygen concentration sequence of the wth monitoring point other than the vth monitoring point is represented as The distance between the vth monitoring point and the wth monitoring point other than the vth monitoring point is represented as The exponential function with a natural constant as the base number is represented as

[0079] In the embodiment, the difference between the oxygen concentration fluctuation coefficient of the vth monitoring point and the wth monitoring point other than the vth monitoring point is obtained by taking the absolute value of the difference between the oxygen concentration fluctuation coefficient of the vth monitoring point and the wth monitoring point other than the vth monitoring point as the difference between the oxygen concentration fluctuation coefficient of the vth monitoring point and the wth monitoring point other than the vth monitoring point.

[0080] The smaller the difference between the oxygen concentration fluctuation coefficient of the vth monitoring point and the wth monitoring point other than the vth monitoring point, the more similar the oxygen concentration fluctuation intensity of the two monitoring points, and the less the difference in fluctuation law and amplitude, and the higher the consistency. The greater the DTW distance between the second-order difference sequence of the oxygen concentration sequence of the vth monitoring point and the second-order difference sequence of the oxygen concentration sequence of the wth monitoring point other than the vth monitoring point, the more significant the difference between the change trends of the oxygen concentrations of the two monitoring points, and the worse the consistency of the oxygen concentration fluctuation. It should be noted that the calculation method of the DTW distance is a prior art, which will not be described in detail here.

[0081] The closer the distance between the vth monitoring point and the wth monitoring point, the greater the possibility that the two monitoring points are affected by similar environmental factors.​ represents a consistency factor of oxygen concentration fluctuation of the vth monitoring point and the wth monitoring point, the greater the value, the more similar the oxygen concentration fluctuation trend of the two monitoring point positions, the more likely it is that the fluctuation is caused by ventilation, and the smaller the abnormal factor of oxygen concentration. represents the first ratio of the vth monitoring point and the wth monitoring point.

[0082] By using the above method, the abnormal factor of the oxygen concentration of each monitoring point can be obtained, the monitoring points with an abnormal factor greater than a preset abnormal threshold are determined as key points, and the monitoring points with an abnormal factor less than or equal to the preset abnormal threshold are determined as non-key points. In this embodiment, the preset abnormal threshold is 0.7, and in specific applications, the implementer can set it according to the specific situation.

[0083] So far, all the monitoring points in the oxygen supply area in this embodiment are divided into two categories, namely key points and non-key points.

[0084] In step S3, the activity frequency of each target person in the area where each key point is located is obtained according to the movement of the target person, the feature corner and the distance between the target person and the key point in the monitoring image of the area where the key point is located in the current time period; the reference coefficient of the key point is determined in combination with the stay duration, the activity frequency and the abnormal factor of each target person in the area where the key point is located; and the comprehensive oxygen concentration data is determined according to the reference coefficient of the key point, the oxygen concentration of the key point at the current time and the oxygen concentration of the non-key point.

[0085] In step S2 of this embodiment, a plurality of key points are screened out, and the consistency of the oxygen concentration fluctuation of the key points with the oxygen concentration fluctuation of other positions is low, which indicates that the fluctuation of the oxygen concentration of the key points is not caused by ventilation, and therefore it is possible that the oxygen sensor is malfunctioning or is disturbed by the activities of the personnel.

[0086] The plateau environment is usually dry, and the risk of static electricity increases in a low-humidity environment. Static electricity can interfere with the sensitivity of the components in the oxygen sensor, and the living room is a public area where personnel activities are frequent. When the personnel are active in the living room (such as walking, resting, talking, etc.), they will directly consume the surrounding oxygen, causing the local oxygen concentration to drop. For example, when a person sits on the sofa for a long time, the oxygen concentration at that position may fluctuate due to continuous oxygen consumption; if the person suddenly gets up and walks, the body movement will drive the air flow, which may temporarily change the distribution of the surrounding oxygen concentration.

[0087] The trained YOLO target detection algorithm is used to monitor each frame of the monitoring image, and a plurality of dynamic regions of each key point in each frame of the video image are obtained. Each dynamic region is recorded as a region where a target person is located. The pixel points that need to be segmented are divided into two categories, i.e., the label annotation process of the training set is: a single-channel semantic label, the annotation of the pixel points belonging to the background region is 0, and the annotation of the pixel points belonging to the dynamic region is 1. The loss function used is the cross-entropy loss function. The input is a video grayscale image, and the output is a dynamic region. The specific training process is known, and will not be described in detail in this embodiment.

[0088] The target tracking algorithm is used to track the target person in all continuous frames of video images in the region of each key point, and the region of the same target person in a plurality of frames of monitoring images is obtained.

[0089] Next, still taking one key point as an example for description.

[0090] Specifically, for any key point:

[0091] The feature point detection algorithm is used to detect each frame of the monitoring image in the region of the key point, and the feature corner points in each frame of the monitoring image are obtained.

[0092] The feature matching algorithm is used to match the feature corner points of the same target person in adjacent two frames of monitoring images in the region of the key point, and a feature corner point matching pair is obtained. The two feature corner points in the same feature corner point matching pair have similar feature expressions, i.e., a plurality of feature corner point matching pairs are obtained. Each feature corner point matching pair is composed of two feature corner points, and the two feature corner points come from adjacent two frames of monitoring images.

[0093] For any feature corner point matching pair, the Euclidean distance between the position coordinates of the two feature corner points in the matching pair is taken as the motion feature value corresponding to the feature corner point matching pair.

[0094] The activity frequency of each target person in the region of the key point is obtained by comprehensively considering all motion feature values corresponding to each target person in the region of the key point, the number of feature corner points of each target person in the region of the key point in each frame of the monitoring image, and the distance between each target person and the key point.

[0095] In this embodiment, a specific calculation formula of the activity frequency is given, and the activity frequency of the dth target person in the region of the gth key point can be expressed as:

[0096]

[0097] wherein, indicates the activity frequency of the dth target person in the region of the gth key point, a frame number of the monitoring image in which the dth target person appears in the region where the gth key point is located, a maximum value of all motion feature values corresponding to the tth frame of the monitoring image in which the dth target person appears in the region where the gth key point is located, a number of feature corner points of the dth target person in the tth frame of the monitoring image in which the dth target person appears in the region where the gth key point is located, a distance between the gth key point and the dth target person in the tth frame of the monitoring image in which the dth target person appears in the region where the gth key point is located, a normalization function.

[0098] In the determination of the distance between the key point and the target person, the embodiment takes the distance between the key point and the center point of the body region of the target person as the distance between the key point and the target person.

[0099] It should be noted that, since the motion feature value is obtained based on two adjacent frames of monitoring images, the motion feature value obtained based on the tth frame of the monitoring image and the (t+1)th frame of the monitoring image is recorded as the motion feature value corresponding to the tth frame of the monitoring image, and in addition, the motion feature value corresponding to the last but one frame of the monitoring image is taken as the motion feature value corresponding to the last frame of the monitoring image, that is, each frame of the monitoring image has its corresponding motion feature value.

[0100] The greater the maximum value of all motion feature values corresponding to the tth frame of the monitoring image in which the dth target person appears in the region where the gth key point is located, the greater the activity amount of the target person, the greater the activity degree, and the greater the oxygen consumption. The distance between the gth key point and the dth target person in the tth frame of the monitoring image in which the dth target person appears in the region where the gth key point is located, the greater the activity of the target person, the more direct the influence of the activity on the air around the sensor, the more obvious the influence on the oxygen concentration at the position of the gth key point, and the more likely to cause fluctuations in the collected oxygen concentration data.

[0101] Further, for any key point: in combination with the stay duration and the activity frequency of each target person in the region of the key point in the current time period, an interference value of the oxygen concentration of the key point caused by the activity of the person is obtained, and the stay duration and the activity frequency are in positive correlation with the interference value.

[0102] In the embodiment, a specific calculation formula of the interference value of the oxygen concentration of the key point caused by the activity of the person is given, and the interference value of the oxygen concentration of the gth key point caused by the activity of the person can be represented as:

[0103]

[0104] wherein, represents the interference value of the oxygen concentration of the gth key point by personnel activity, D represents the number of target personnel in the area where the gth key point is located in the current time period, represents the activity frequency of the dth target personnel in the area where the gth key point is located in the current time period, represents the stay duration of the dth target personnel in the area where the gth key point is located in the current time period, represents a normalization function.

[0105] The longer the stay duration of the target personnel in the area where the gth key point is located, and the more frequent the activity, the more likely it is that the fluctuation of the oxygen concentration at the position is caused by personnel activity, that is, the greater the interference value of the oxygen concentration of the gth key point by personnel activity.

[0106] The greater the interference possibility of the oxygen concentration of the gth key point position by personnel activity, the more likely it is that the abnormal fluctuation of the oxygen concentration of the gth key point position is caused by frequent personnel activity, and the more the oxygen concentration data collected at the position can reflect the actual change of the oxygen concentration in the living room; the smaller the interference possibility of the oxygen concentration of the gth key point position by personnel activity, the more likely it is that the abnormal fluctuation of the oxygen concentration of the gth key point position is caused by sensor faults such as static electricity, and the less the oxygen concentration data collected is reliable. When predicting future oxygen concentration data, the representativeness of the position should be reduced, the accuracy of dynamic adjustment of the oxygen supply amount of the oxygen supply equipment should be improved, and the comfort of the personnel in the space should be ensured.

[0107] Based on the above characteristics, the reference coefficient of the key point is obtained according to the abnormal factor of the oxygen concentration of the monitoring point and the interference value of the oxygen concentration of the key point by personnel activity, the abnormal factor and the reference coefficient are in a negative correlation relationship, and the interference value and the reference coefficient are in a positive correlation relationship.

[0108] In the embodiment, a specific calculation formula of the reference coefficient of the key point is given, and the reference coefficient of the gth key point can be represented as:

[0109]

[0110] wherein, represents the reference coefficient of the gth key point, represents the abnormal factor of the oxygen concentration of the gth key point, represents the interference value of the oxygen concentration of the gth key point by personnel activity, represents an exponential function with a natural constant as the base number.

[0111] The greater the interference value of the gth key point oxygen concentration by personnel activity, the more likely the abnormal fluctuation of the oxygen concentration at the gth key point position is caused by personnel activity, and the smaller the abnormality degree of the position should be, that is, the greater the reference coefficient of the gth key point position is, the more the oxygen concentration at the gth key point position can reflect the actual oxygen concentration change of the oxygen supply space, and the greater the representativeness is, that is, the greater the reference coefficient of the gth key point is.

[0112] The reference coefficient of each key point can be obtained by using the above method. For a non-key point, the reference coefficient of the non-key point is a preset value; wherein the reference coefficient of the non-key point is greater than the reference coefficient of the reference point, and in the embodiment, the preset value is 1, that is, the reference coefficient of the non-key point is 1. By using the above method, the reference coefficients of the monitoring points in the oxygen supply space are obtained.

[0113] The greater the reference coefficient of any monitoring point position is, the greater weight should be given to the oxygen concentration data of the position at the current time, so as to ensure that the final comprehensive oxygen concentration data can better reflect the change trend of the overall oxygen concentration in the living room, instead of only relying on the oxygen concentration data of a specific position.

[0114] Specifically, the cumulative sum of the reference coefficients of all the monitoring points in the oxygen supply space is calculated; then, the ratio between the reference coefficient of each monitoring point and the cumulative sum is taken as the weight of each monitoring point; and then, the oxygen concentrations of all the monitoring points at the current time are weighted and summed by using the weights of the monitoring points, to obtain the comprehensive oxygen concentration data.

[0115] In the embodiment, the calculation formula of the comprehensive oxygen concentration data is given, and the comprehensive oxygen concentration data can be represented as:

[0116]

[0117] wherein, represents the comprehensive oxygen concentration data, V represents the number of monitoring points in the oxygen supply space, represents the reference coefficient of the vth monitoring point, represents the cumulative sum of the reference coefficients of all the monitoring points in the oxygen supply space, represents the oxygen concentration of the vth monitoring point at the current time.

[0118] represents the weight of the vth monitoring point, and the oxygen concentration is weighted by using the weight of each monitoring point, so as to reduce the large oxygen concentration fluctuation of individual monitoring point caused by local factors, and reduce the influence of measurement error or device failure of a single monitoring point, thereby obtaining a more smooth comprehensive oxygen concentration data which can more accurately reflect the real oxygen concentration of the oxygen supply space, and improving the accuracy of the oxygen concentration control in the living room.

[0119] Step S4, based on the comprehensive oxygen concentration data, adjusting the oxygen supply concentration of the oxygen supply device.

[0120] After obtaining the comprehensive oxygen concentration data, the oxygen supply of the oxygen supply device is regulated by using a PID controller.

[0121] Specifically, the comprehensive oxygen concentration data is input into the PID controller, and the PID controller first calculates the deviation between the comprehensive oxygen concentration data and the target oxygen concentration value, i.e. , wherein, represents the target oxygen concentration value, represents the comprehensive oxygen concentration data, represents the deviation between the comprehensive oxygen concentration data at the current time and the target oxygen concentration value. The target oxygen concentration value is set by the implementer according to the specific situation.

[0122] Then, three components of the PID controller are calculated, specifically:

[0123]

[0124] , wherein, is a proportional term, which is directly proportional to the deviation, and aims to quickly respond to the deviation; is a proportional gain, which determines the strength of proportional control.

[0125] , wherein, represents the integral term corresponding to the current time, is the integral term corresponding to the last time; the integral term accumulates the past deviation, aiming to eliminate long-term deviation; is an integral gain.

[0126]

[0127] , wherein, is a differential term, which predicts the trend of the deviation and aims to correct the upcoming deviation in advance; is a differential gain, is a time interval, is the deviation between the comprehensive oxygen concentration data at the last time and the target oxygen concentration value.

[0128] According to the three components of the PID algorithm, the controller will calculate the control amount, i.e. the output signal. According to the output signal, the PID controller sends an adjustment instruction to the oxygen supply device to adjust the oxygen concentration. This process is prior art, and will not be described in detail here.

[0129] Thus, by using the method provided in this embodiment, intelligent control of the diffuse oxygen supply device is achieved.

[0130] The embodiment first analyzes the fluctuation of the oxygen concentration collected by a single monitoring point in the oxygen supply space in the current time period, obtains the oxygen concentration fluctuation coefficient, then determines the abnormal factor of the oxygen concentration of the single monitoring point in combination with the difference and relative distance of the change characteristics of the oxygen concentration of different monitoring points, and divides the monitoring points into key points and non-key points based on the size of the abnormal factor, then evaluates the activity frequency of the target person in combination with the motion characteristics of the target person in the monitoring image of the area where the key point is located, and determines the reference coefficient of the key point in combination with the stay duration and abnormal factor of each target person in the area where the key point is located, reduces the reference degree of the monitoring data of the position with high abnormal degree, and improves the reference degree of the monitoring data of the normal position, so that more comprehensive oxygen concentration data which can accurately reflect the real oxygen concentration in the oxygen supply space is obtained, and the oxygen concentration dynamic control precision is improved.

[0131] An embodiment of a diffuse intelligent oxygen supply dynamic control system:

[0132] The diffuse intelligent oxygen supply dynamic control system provided by an embodiment of the present application can include a data acquisition module, a classification module, a determination module and a regulation and control module.

[0133] The data acquisition module is configured to acquire the oxygen concentration of different monitoring points in the oxygen supply space and the monitoring image of the area where the different monitoring points are located.

[0134] The classification module is configured to obtain the oxygen concentration fluctuation coefficient of each monitoring point according to the fluctuation of the oxygen concentration of each monitoring point in the current time period, and obtain the abnormal factor of the oxygen concentration of each monitoring point in combination with the difference, relative distance and oxygen concentration fluctuation coefficient of the change characteristics of the oxygen concentration of different monitoring points in the current time period, and determine the key points and non-key points.

[0135] The determination module is configured to obtain the activity frequency of each target person in the area where each key point is located according to the motion of the target person, the feature corner and the distance between the target person and the key point in the monitoring image of the area where each key point is located in the current time period, determine the reference coefficient of each key point in combination with the stay duration, activity frequency and abnormal factor of each target person in the area where each key point is located, and determine the comprehensive oxygen concentration data according to the reference coefficient of the key point, the oxygen concentration of the key point at the current moment and the oxygen concentration of the non-key point.

[0136] The regulation and control module is configured to adjust the oxygen supply concentration of the oxygen supply equipment based on the comprehensive oxygen concentration data.

[0137] It should be appreciated that the modules of the dynamic control system for diffuse smart oxygen supply can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented in hardware, software, or a combination of software and hardware. The hardware portion can be implemented with special logic, while the software portion can be stored in memory and executed by a suitable instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art can understand that the above-mentioned method and system can be implemented using computer executable instructions and / or included in processor control code, such as provided on a carrier medium, such as a disk, CD or DVD-ROM, programmable memory, such as read-only memory (firmware), or data carrier, such as optical or electronic signal carrier. The system and its modules of the present specification can not only be implemented in hardware circuit, such as very large scale integrated circuit or gate array, semiconductor, such as logic chip, transistor, or programmable hardware device, such as field programmable gate array, programmable logic device, but also in software, for example, executed by various types of processors, and also by the combination of the above-mentioned hardware circuit and software (for example, firmware).

[0138] More details about the above-mentioned modules can be referred to other places in the present specification, which will not be described here.

[0139] It should be noted that the above-mentioned only for the preferred embodiments of the present application, and not to limit the present application, any modification, equivalent replacement, improvement, etc. made within the principles of the present application, should be included in the scope of protection of the present application.

Claims

1. A diffusion-type intelligent oxygen supply device, characterized in that, The device includes a memory and a processor, the processor executing a computer program stored in the memory to perform the following steps: Acquire oxygen concentrations at different monitoring points within the oxygen supply space and monitoring images of the areas where these monitoring points are located; Based on the fluctuation of oxygen concentration at each monitoring point within the current time period, the oxygen concentration fluctuation coefficient of each monitoring point is obtained; combined with the differences in the characteristics of oxygen concentration change at different monitoring points within the current time period, the relative distance, and the oxygen concentration fluctuation coefficient, the abnormal factors of oxygen concentration at each monitoring point are obtained, and key points and non-key points are determined. Based on the movement of target personnel, characteristic corner points, and distance between target personnel and key points in the monitoring images of the areas where each key point is located within the current time period, the activity frequency of each target personnel in the area where each key point is located is obtained; combined with the dwell time, activity frequency, and abnormal factors of each target personnel in the area where each key point is located, the reference coefficient of the key point is determined; based on the reference coefficient of the key point, the oxygen concentration of the key point at the current time, and the oxygen concentration of non-key points, the comprehensive oxygen concentration data is determined. Based on the comprehensive oxygen concentration data, adjust the oxygen supply concentration of the oxygen supply equipment; The abnormal factors of oxygen concentration at each monitoring point are obtained by combining the differences in oxygen concentration variation characteristics, relative distances, and oxygen concentration fluctuation coefficients at different monitoring points within the current time period, including: For any monitoring point: Based on the DTW distance between the second difference sequence of the oxygen concentration sequence of any monitoring point and the second difference sequence of the oxygen concentration sequence of other monitoring points within the current time period, and the difference in the oxygen concentration fluctuation coefficient of any monitoring point and other monitoring points, the oxygen concentration fluctuation consistency factor of any monitoring point and other monitoring points is obtained. The difference in the DTW distance and the oxygen concentration fluctuation coefficient are both negatively correlated with the oxygen concentration fluctuation consistency factor. Based on the consistency factor of oxygen concentration fluctuations at any given monitoring point with all other monitoring points and the distance therefrom, the abnormal factor of oxygen concentration at any given monitoring point is obtained.

2. The diffusion-type intelligent oxygen supply device according to claim 1, characterized in that, The process of obtaining the oxygen concentration fluctuation coefficient for each monitoring point based on the fluctuation of oxygen concentration at each monitoring point within the current time period includes: For any monitoring point: Obtain the extreme point of the oxygen concentration curve of any of the monitoring points, wherein the oxygen concentration curve is obtained by curve fitting of the sequence of oxygen concentrations of any of the monitoring points in the current time period. The normalized result of the difference in oxygen concentration between each extreme point and its previous extreme point is recorded as the first characteristic value of each extreme point; the normalized result of the time interval between each extreme point and its previous extreme point is recorded as the second characteristic value of each extreme point; extreme points whose first characteristic value is greater than a preset first threshold and whose second characteristic value is less than a preset second threshold are recorded as candidate points. According to the chronological order, the time interval between the times corresponding to two adjacent candidate points constitutes a key time interval; The oxygen concentration fluctuation coefficient of any monitoring point is obtained based on the average time interval between all adjacent key time periods of any monitoring point in the current time period, the duration of each key time period, the average rate of change of candidate points in each key time period, and the number of candidate points of any monitoring point in the current time period. The rate of change is the ratio of the first characteristic value to the second characteristic value.

3. The diffusion-type intelligent oxygen supply device according to claim 1, characterized in that, The step of obtaining the anomalous factor of oxygen concentration at any monitoring point based on the consistency factor and distance of oxygen concentration fluctuation at any monitoring point with all other monitoring points includes: The ratio between the oxygen concentration fluctuation consistency factor of any monitoring point and that of each other monitoring point and the distance between any monitoring point and the same other monitoring point is recorded as the first ratio of any monitoring point to each other monitoring point. By combining the first ratio of any monitoring point with all other monitoring points, an anomalous factor of oxygen concentration at any monitoring point is obtained, and the first ratio is negatively correlated with the anomalous factor.

4. The diffusion-type intelligent oxygen supply device according to claim 1, characterized in that, Determining critical and non-critical points includes: identifying monitoring points with abnormal factors greater than a preset abnormal threshold as critical points, and identifying monitoring points with abnormal factors less than or equal to a preset abnormal threshold as non-critical points.

5. The diffusion-type intelligent oxygen supply device according to claim 1, characterized in that, The process of determining the activity frequency of each target person in the area of ​​each key point based on the movement of the target person in the monitoring images of the area where each key point is located within the current time period, the characteristic corner points, and the distance between the target person and the key point includes: For any key point: A feature matching algorithm is used to match the feature corner points of the same target person in two adjacent frames of monitoring images in the area where any key point is located, to obtain feature corner point matching pairs; based on the positions of the two feature points in the feature corner point matching pair, the motion feature value corresponding to the feature corner point matching pair is obtained; By combining all motion feature values ​​corresponding to each target person in the area where any key point is located, the number of feature corner points of each target person in the area where any key point is located in each frame of the monitoring image, and the distance between each target person and any key point, the activity frequency of each target person in the area where any key point is located can be obtained.

6. The diffusion-type intelligent oxygen supply device according to claim 1, characterized in that, The reference coefficients for each key point are determined by combining the dwell time, activity frequency, and abnormal factors of each target person in the area where each key point is located. For any key point: By combining the dwell time and activity frequency of each target person in the area where any key point is located within the current time period, the interference value of the oxygen concentration at any key point due to the activity of the person is obtained. The dwell time and the activity frequency are both positively correlated with the interference value. Based on the abnormal factor of oxygen concentration at any monitoring point and the interference value of oxygen concentration at any key point due to human activity, a reference coefficient for any key point is obtained. The abnormal factor is negatively correlated with the reference coefficient, and the interference value is positively correlated with the reference coefficient.

7. A diffusion-type intelligent oxygen supply device according to claim 4, characterized in that, The process of determining comprehensive oxygen concentration data based on the reference coefficients of key points, the current oxygen concentration at key points, and the oxygen concentration at non-key points includes: The ratio between the reference coefficient of each monitoring point and the sum of the reference coefficients of all monitoring points is used as the weight of each monitoring point. The oxygen concentration data of all monitoring points at the current time is obtained by weighting and summing the oxygen concentrations using the aforementioned weights. Among them, the reference coefficient of non-critical points is greater than the reference coefficient of reference points, and the reference coefficient of non-critical points is a preset value.

8. A diffusion-type intelligent oxygen supply device according to claim 1, characterized in that, The adjustment of the oxygen supply concentration of the oxygen supply equipment based on the comprehensive oxygen concentration data includes: The comprehensive oxygen concentration data is input into the PID controller, which then sends an adjustment command to the oxygen supply equipment to adjust the oxygen concentration.

9. A dynamic control system for diffused intelligent oxygen supply, the system being used to implement the steps performed by the device according to claim 1, characterized in that, The system includes: The data acquisition module is used to acquire oxygen concentrations at different monitoring points within the oxygen supply space and monitoring images of the areas where different monitoring points are located; The classification module is used to obtain the oxygen concentration fluctuation coefficient of each monitoring point based on the fluctuation of oxygen concentration at each monitoring point within the current time period; and to obtain the abnormal factors of oxygen concentration at each monitoring point by combining the differences in the change characteristics of oxygen concentration at different monitoring points within the current time period, the relative distance, and the oxygen concentration fluctuation coefficient, and to determine the key points and non-key points. The determination module is used to determine the activity frequency of each target person in the area of ​​each key point based on the movement of the target person in the monitoring images of the area where each key point is located within the current time period, the characteristic corner points, and the distance between the target person and the key point; combined with the dwell time, activity frequency, and abnormal factors of each target person in the area where each key point is located, the reference coefficient of the key point is determined; and based on the reference coefficient of the key point, the oxygen concentration of the key point and the oxygen concentration of non-key points at the current time, the comprehensive oxygen concentration data is determined. The control module is used to adjust the oxygen supply concentration of the oxygen supply equipment based on the comprehensive oxygen concentration data.

Images