Humidity detection method, system, humidifier and storage medium

Abstract

The present application provides a humidity detection method, system, humidifier and storage medium. Multiple sensors in a humidifier are used to collect current environmental humidity data of a target space. Feature constraints are performed on the current environmental humidity data to obtain environmental humidity constraint data. The environmental humidity constraint data is converted into multiple modal humidity data segments according to the difference characteristics of the sensors. The sampling mutual support of each modal humidity data segment is determined by the confidence distance between the sensors. The local fusion humidity of the corresponding modal humidity data segment is determined according to the sampling mutual support. The ambient temperature data within a specified time period is obtained. The temperature distribution characteristic entropy of the current environment of the target space is extracted through the discrete characteristics of the ambient temperature data and the current ambient humidity data. The global fusion humidity of the current ambient humidity data is determined according to all the local fusion humidity and the temperature distribution characteristic entropy. The global fusion humidity is used as the humidity of the current environment of the target space, so that multi-source heterogeneous ambient humidity detection can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of humidifiers, and more specifically, to a humidity detection method, system, humidifier and storage medium. Background Art

[0002] A humidifier is a device that improves the indoor environment by adjusting the humidity in the air. It is particularly useful in dry environments, especially in winter or when using a humidifier in an air-conditioned room. It can effectively relieve symptoms such as dry throat, cough and nasal congestion caused by dry air.

[0003] In a humidifier, humidity detection is generally used to measure the water vapor content in the air, and the ambient humidity is adjusted according to the detection results to ensure the comfort and health of the indoor environment. Since the scale of indoor spaces is usually large, there are significant differences in ambient humidity parameters at different locations. For example, the humidity in areas near doorways or vents is different from that in areas far away from these locations. The existing technology based on a single sensor detection system cannot accurately reflect the indoor ambient humidity state. If multiple sensors are used to collect humidity data at different locations for fused humidity estimation, the accuracy of indoor space humidity detection can be improved and the uncertainty of humidity environment information can be reduced. However, how to evaluate the ambient humidity in a humidifier through multi-source heterogeneous humidity detection data to achieve multi-source heterogeneous environmental humidity detection has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a humidity detection method, system, humidifier and storage medium, which can realize humidity detection in multi-source heterogeneous environments.

[0005] In a first aspect, the present application provides a humidity detection method, comprising the following steps:

[0006] Use multiple sensors in the humidifier to collect current ambient humidity data of the target space;

[0007] Performing feature constraints on current environmental humidity data to obtain environmental humidity constraint data, and then converting the environmental humidity constraint data into multiple modal humidity data segments according to differential characteristics of sensors;

[0008] The sampling mutual support of each modal humidity data segment is determined by the confidence distance between each sensor, and the local fusion humidity of the corresponding modal humidity data segment is determined according to each sampling mutual support;

[0009] Acquire the ambient temperature data within a specified time period, and extract the temperature distribution characteristic entropy of the current environment of the target space through the discrete characteristics of the ambient temperature data and the current ambient humidity data;

[0010] The global fused humidity of the current environmental humidity data is determined according to all the local fused humidity and the temperature distribution characteristic entropy, and the global fused humidity is used as the humidity of the current environment of the target space.

[0011] In some embodiments, the feature constraints are applied to the current environmental humidity data to obtain environmental humidity constraint data, specifically including:

[0012] Eliminate abnormal data in the current environmental humidity data to obtain environmental humidity cleaning data;

[0013] Then, the environmental humidity cleaning data is scale-constrained to obtain environmental humidity constraint data.

[0014] In some embodiments, determining the sampling mutual support of each modal humidity data segment through the confidence distance between each sensor specifically includes:

[0015] Get the distance between each sensor;

[0016] Determine the confidence distance between each sensor through all the distances;

[0017] Determine the confidence distance matrix of each sensor based on all confidence distances;

[0018] Determine the sampling variance matrix of each modal humidity data segment;

[0019] The sampling mutual support of each modal humidity data segment is determined based on all confidence distance matrices and all sampling variance matrices.

[0020] In some embodiments, determining the local fusion humidity of the corresponding modal humidity data segment according to the mutual support of each sample specifically includes:

[0021] Select a modal humidity data segment;

[0022] Determine the similarity between the humidity data collected by the sensor corresponding to the modal humidity data segment;

[0023] Determine the similarity matrix of the modal humidity data segment based on all similarities;

[0024] Determining the local fusion humidity of the modal humidity data segment through the sampling mutual support of the modal humidity data segment and the similarity matrix;

[0025] Continue to determine the local fused humidity for the remaining modal humidity data segments.

[0026] In some embodiments, determining the global fusion humidity of the current environmental humidity data according to all the local fusion humidity and the temperature distribution characteristic entropy specifically includes:

[0027] Determine the temperature compensation coefficient of the external environment;

[0028] Determine the humidity credible interval for each modal humidity data segment;

[0029] Determine the heterogeneous fusion humidity characteristic value of each modal humidity data segment according to all local fusion humidity and all humidity credible intervals;

[0030] The global fused humidity of the current environmental humidity data is determined by the temperature compensation coefficient, all heterogeneous fused humidity characteristic values ​​and the temperature distribution characteristic entropy.

[0031] In some embodiments, converting the environmental humidity constraint data into a plurality of modal humidity data segments according to the difference characteristics of the sensor specifically includes:

[0032] Get the category information of the sensor;

[0033] Determining the difference characteristics of the sensor through the category information;

[0034] Classifying the environmental humidity constraint data according to the difference characteristics to obtain different humidity data classes;

[0035] A plurality of modal humidity data segments are determined according to different humidity data categories.

[0036] In some embodiments, the sensor includes: a resistive humidity sensor, a capacitive humidity sensor, and a thermal conductivity humidity sensor.

[0037] In a second aspect, the present application provides a humidity detection system, comprising:

[0038] An acquisition module is used to collect current environmental humidity data of the target space using multiple sensors in the humidifier;

[0039] A processing module, used for performing feature constraints on current environmental humidity data to obtain environmental humidity constraint data, and then converting the environmental humidity constraint data into multiple modal humidity data segments according to the difference characteristics of the sensor;

[0040] The processing module is further used to determine the sampling mutual support of each modal humidity data segment through the confidence distance between each sensor, and determine the local fusion humidity of the corresponding modal humidity data segment according to each sampling mutual support;

[0041] The processing module is further used to obtain the ambient temperature data within a specified time period, and extract the temperature distribution characteristic entropy of the current environment of the target space through the discrete characteristics of the ambient temperature data and the current ambient humidity data;

[0042] The execution module is used to determine the global fusion humidity of the current environmental humidity data according to all the local fusion humidity and the temperature distribution characteristic entropy, and use the global fusion humidity as the humidity of the current environment of the target space.

[0043] In a third aspect, the present application provides a humidifier, wherein the humidifier includes the above-mentioned humidity detection system.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above-mentioned humidity detection method when executed by a processor.

[0045] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0046] In an embodiment of the present application, multiple sensors in a humidifier are used to collect current ambient humidity data of a target space; feature constraints are performed on the current ambient humidity data to obtain ambient humidity constraint data, and then the ambient humidity constraint data is converted into multiple modal humidity data segments according to the difference characteristics of the sensors, and the sampling mutual support of each modal humidity data segment is determined by the confidence distance between each sensor, wherein the sampling mutual support represents the average degree of mutual correlation between sensors of the same type, and is used to evaluate the consistency between humidity data collected by different sensors in the same space, and the local fusion humidity of the corresponding modal humidity data segment is determined according to each sampling mutual support, that is, a fusion humidity value obtained by local fusion of humidity data collected by sensors of the same type is obtained, and then the ambient temperature data within a specified time period is obtained, and the temperature distribution characteristic entropy of the current environment of the target space is extracted through the discrete characteristics of the ambient temperature data and the current ambient humidity data, and the global fusion humidity of the current ambient humidity data is determined according to all the local fusion humidity and the temperature distribution characteristic entropy, and the global fusion humidity is used as the humidity of the current environment of the target space.

[0047] It can be seen that in this application, the global fusion humidity of the current environmental humidity data is determined according to all the local fusion humidity and the temperature distribution characteristic entropy, and the global fusion humidity is used as the humidity of the current environment of the target space. First, the average degree of correlation between sensors of the same type is determined by the confidence distance between sensors to evaluate the similarity between the humidity data corresponding to each sensor, and then the humidity data corresponding to sensors of the same type are locally fused according to all similarities to obtain a fused humidity value. The local feature fusion process considers the correlation between data collected by different sensors of the same type, thereby improving the accuracy of local humidity data fusion. Secondly, the temperature distribution characteristic entropy determined in this application can measure the uncertainty of temperature distribution in the target space, thereby reducing the influence of ambient temperature on the ambient humidity detection result of the indoor space. Then, the current ambient humidity data is globally fused by local fusion humidity and temperature distribution characteristic entropy, and the ambient humidity of the target space is comprehensively evaluated, which is conducive to providing a more comprehensive ambient humidity estimation result, thereby improving the reliability of the humidity detection result. In summary, this scheme can complete the feature fusion of multi-source heterogeneous humidity detection data, thereby realizing multi-source heterogeneous environmental humidity detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is an exemplary flow chart of a humidity detection method according to some embodiments of the present application;

[0049] Figure 2 is a distribution structure diagram of sensors according to some embodiments of the present application;

[0050] Figure 3 is a schematic diagram of a process for determining local fusion humidity according to some embodiments of the present application;

[0051] Figure 4 is a schematic diagram of exemplary hardware and / or software of a humidity detection system according to some embodiments of the present application;

[0052] Figure 5 It is a structural schematic diagram of a computer device for implementing a humidity detection method according to some embodiments of the present application. DETAILED DESCRIPTION

[0053] The core of this application is to use multiple sensors in a humidifier to collect the current ambient humidity data of the target space, perform feature constraints on the current ambient humidity data, obtain ambient humidity constraint data, convert the ambient humidity constraint data into multiple modal humidity data segments according to the difference characteristics of the sensors, determine the sampling mutual support of each modal humidity data segment through the confidence distance between the sensors, determine the local fusion humidity of the corresponding modal humidity data segment according to the sampling mutual support, obtain the ambient temperature data within a specified time period, extract the temperature distribution characteristic entropy of the current environment of the target space through the discrete characteristics of the ambient temperature data and the current ambient humidity data, determine the global fusion humidity of the current ambient humidity data according to all the local fusion humidity and temperature distribution characteristic entropy, use the global fusion humidity as the humidity of the current environment of the target space, and realize multi-source heterogeneous ambient humidity detection.

[0054] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a humidity detection method according to some embodiments of the present application. The humidity detection method 100 mainly includes the following steps:

[0055] In step 101, multiple sensors in a humidifier are used to collect current environmental humidity data of a target space.

[0056] In the specific implementation, after the humidity detection of the humidifier is started, multiple different types of sensors are used to collect the current environmental humidity data of the target space (i.e., indoor space) according to the specified sampling frequency. Among them, the sensor types include resistive humidity sensors, capacitive humidity sensors and thermal conductivity humidity sensors. The distribution positions of the sensors can be referred to, for example Figure 2 As shown, this figure is a distribution structure diagram of sensors in some embodiments of the present application. In other embodiments, other types of sensors for humidity detection can also be used, which is not limited here. The current environmental humidity data represents a set of humidity data collected by all sensors at the current moment, and the value range of the specified sampling frequency can be set between 1000-5000Hz.

[0057] It should be noted that, due to the delay effect when the sensor collects humidity data, the current environmental humidity data defaults to the humidity data collected by all sensors within a short period of time, and the short period of time can be set between 10 seconds and 30 seconds.

[0058] In addition, it should be noted that the humidity detection method in the present application is suitable for indoor humidity detection in a closed building. The closed building refers to a building with a high degree of sealing in the building structure and restricted indoor and outdoor gas exchange, such as: commercial office buildings, hotels, hospitals, schools, etc. In some embodiments, the humidity detection method provided in the present application can be used in the indoor humidity detection of a central humidifier.

[0059] In step 102, feature constraints are performed on current environmental humidity data to obtain environmental humidity constraint data, and then the environmental humidity constraint data is converted into a plurality of modal humidity data segments according to differential features of the sensor.

[0060] In some embodiments, the characteristic constraints are applied to the current ambient humidity data to obtain ambient humidity constraint data, which can be achieved by using the following steps:

[0061] Eliminate abnormal data in the current environmental humidity data to obtain environmental humidity cleaning data;

[0062] Then, the environmental humidity cleaning data is scale-constrained to obtain environmental humidity constraint data.

[0063] In specific implementation, in some embodiments, the abnormal data in the current environmental humidity data is removed to obtain environmental humidity cleaning data, which can be achieved by the following steps:

[0064] Determine the average value of current ambient humidity data;

[0065] Determine the standard deviation of the current ambient humidity data;

[0066] Select an ambient humidity value from the current ambient humidity data, and mark the absolute value of the difference between the ambient humidity value and the average value as the absolute difference. When the absolute difference is greater than 3 times the standard deviation, mark the ambient humidity value as an abnormal value and clear the ambient humidity value. Otherwise, retain the ambient humidity value. Repeat the above steps to obtain all retained ambient humidity values, and use the collection of all ambient humidity values ​​as ambient humidity cleaning data.

[0067] It should be noted that in the present application, the scale constraint on the ambient humidity cleaning data refers to limiting the various ambient humidity values ​​in the ambient humidity cleaning data to the same scale range to ensure the rationality and reliability of the ambient humidity data. As a preferred embodiment, the minimum-maximum standardization technology in the prior art can be used to standardize all ambient humidity in the ambient humidity cleaning data, so as to limit each ambient humidity to the same scale range, and then all the values ​​obtained after the standardization process constitute the ambient humidity constraint data. In other embodiments, other existing standardization technologies can also be used to limit the same scale range, which is not limited here.

[0068] In some embodiments, converting the ambient humidity constraint data into multiple modal humidity data segments according to the difference characteristics of the sensor can be achieved by using the following steps:

[0069] Get the category information of the sensor;

[0070] Determining the difference characteristics of the sensor through the category information;

[0071] Classifying the environmental humidity constraint data according to the difference characteristics to obtain different humidity data classes;

[0072] A plurality of modal humidity data segments are determined according to different humidity data categories.

[0073] In the specific implementation, it should be noted that the sensor types in this application include resistive humidity sensors, capacitive humidity sensors and thermal conductivity humidity sensors, that is, the sensor category is 3. In other embodiments, other types of humidity detection sensors can be used for humidity detection, and the category information of the sensor will change accordingly. There is no limitation here. The category of the sensor is used as the difference feature of the sensor, that is, the difference feature in this application is 3. The various ambient humidity values ​​in the ambient humidity constraint data are classified according to the corresponding collection source, which can be divided into 3 humidity data categories, and different humidity data categories are used as different modal humidity data segments.

[0074] In step 103, the sampling mutual support of each modal humidity data segment is determined by the confidence distance between each sensor, and the local fusion humidity of the corresponding modal humidity data segment is determined according to each sampling mutual support.

[0075] In some embodiments, determining the sampling mutual support of each modal humidity data segment through the confidence distance between each sensor can be implemented by the following steps:

[0076] Get the distance between each sensor;

[0077] Determine the confidence distance between each sensor through all the distances;

[0078] Determine the confidence distance matrix of each sensor based on all confidence distances;

[0079] Determine the sampling variance matrix of each modal humidity data segment;

[0080] The sampling mutual support of each modal humidity data segment is determined based on all confidence distance matrices and all sampling variance matrices.

[0081] In specific implementation, the confidence distance between each sensor is determined by all distances. The confidence distance is used to measure the similarity between the probability distributions of the data collected by the two sensors. As a preferred embodiment, the reciprocal of the natural logarithm of the distance between the two sensors can be used as the confidence distance between the two sensors, that is, ,in, represents the confidence distance between two sensors, Represents the distance between two sensors; determine the confidence distance matrix of each sensor based on all the confidence distances, that is, select a sensor, obtain the confidence distance between the sensor and other sensors of the same type, arrange all the confidence distances according to the distribution position of the sensor, and use the arranged matrix as the confidence distance matrix of the sensor, and continue to determine the confidence distance matrix of the remaining sensors. It should be noted that the confidence distance between the sensor and its own sensor in this application is 1; determine the sampling variance matrix of each modal humidity data segment, that is, obtain a modal humidity data segment, divide the modal humidity data segment into multiple clusters according to the data source, where one cluster corresponds to the data collected by one sensor, calculate the variance of the ambient humidity data in each cluster respectively, and then distribute all the variances according to the distribution position of the corresponding sensor. Arrange, use the matrix obtained by arrangement as the sampling variance matrix of the modal humidity data segment, and continue to determine the sampling variance matrix of the remaining modal humidity data segments; determine the sampling mutual support of each modal humidity data segment according to all confidence distance matrices and all sampling variance matrices, that is, select a modal humidity data segment, obtain the sampling variance matrix of the modal humidity data segment, multiply the inverse matrix of the sampling variance matrix by the confidence distance matrix of each sensor corresponding to the modal humidity data segment, through this step, the random error of the sensor caused by environmental factors can be reduced, and then all the matrices obtained by multiplication are added to obtain a new matrix, and finally the average value of all elements on the diagonal of the new matrix is ​​used as the sampling mutual support of the modal humidity data segment, and continue to determine the sampling mutual support of the remaining modal humidity data segments.

[0082] It should be noted that the sampling mutual support in the present application represents the average degree of correlation between sensors of the same type, and is used to evaluate the consistency between humidity data collected by different sensors in the same space. The value range of the sampling mutual support is between 0 and 1. The larger the value, the higher the support degree of the corresponding sensor for other sensors. It should also be noted that the mutual support degree in the present application represents a kind of correlation, that is, it expresses the similarity of humidity data collected by the same type of sensors in the same environment.

[0083] In some embodiments, reference Figure 3As shown, this figure is a schematic diagram of the process of determining the local fusion humidity in some embodiments of the present application. In this embodiment, the local fusion humidity of the corresponding modal humidity data segment is determined according to the mutual support of each sample, which can be achieved by the following steps:

[0084] First, in step 1031, a modal humidity data segment is selected;

[0085] Secondly, in step 1032, the similarity between the humidity data collected by the sensor corresponding to the modal humidity data segment is determined;

[0086] Again in step 1033, the similarity matrix of the modal humidity data segment is determined from all the similarities;

[0087] Then in step 1034, the local fusion humidity of the modal humidity data segment is determined through the sampling mutual support of the modal humidity data segment and the similarity matrix;

[0088] Finally, in step 1035, the local fused humidity of the remaining modal humidity data segments continues to be determined.

[0089] In a specific implementation, the similarity between the humidity data collected by the sensor corresponding to the modal humidity data segment is determined, that is, the modal humidity data segment is divided into multiple clusters according to the data source, wherein one cluster corresponds to the data collected by one sensor, and the Euclidean distance calculation in the prior art can be used to respectively calculate the similarity between clusters. In other embodiments, other existing similarity calculation formulas can also be used to calculate the similarity between clusters, which is not limited here; the similarity matrix of the modal humidity data segment is determined by all the similarities, that is, a sensor is selected from all the sensors corresponding to the modal humidity data segment, and the average value of the similarity between the humidity data collected by the sensor and the humidity data collected by all other sensors is recorded as the similarity of the sensor, and the similarity of the remaining sensors is continued to be determined, and then all the similarities are arranged into a matrix according to the distribution positions of the corresponding sensors. The matrix is ​​used as the similarity matrix of the modal humidity data segment; the local fusion humidity of the modal humidity data segment is determined by the sampling mutual support of the modal humidity data segment and the similarity matrix, that is, first, the sampling mutual support of the modal humidity data segment is used as the adjustment weight to adjust the similarity matrix, that is, the sampling mutual support is multiplied with the similarity matrix to obtain a new similarity matrix, and the humidity weights of each sensor corresponding to the modal humidity data segment are determined by the new similarity matrix. As a preferred embodiment, the ratio of each element in the new similarity matrix to the sum of all elements can be used as the humidity weight of the corresponding sensor. Secondly, the humidity weight of each sensor is multiplied by the average of the humidity data collected by the corresponding sensor, and then the sum of all the multiplied humidity values ​​is used as the local fusion humidity of the modal humidity data segment.

[0090] It should be noted that the local fused humidity in the present application refers to the fused humidity value obtained by locally fusing the humidity data collected by sensors of the same type. The local fusion process takes into account the correlation between the data collected by different sensors of the same type to reduce the random errors caused by the external environment.

[0091] In addition, it should be noted that in this application, by calculating the confidence distance and sampling support, the credibility between the data of each sensor can be evaluated, so as to more accurately perform local fusion of humidity data, thereby improving the reliability and accuracy of the data.

[0092] In step 104, the ambient temperature data within a specified time period is acquired, and the temperature distribution characteristic entropy of the current environment of the target space is extracted through the discrete characteristics of the ambient temperature data and the current ambient humidity data.

[0093] In the specific implementation, the ambient temperature data within the specified time period is obtained, that is, the ambient temperature data within the specified time period is collected by the temperature sensor according to the preset sampling frequency, and the specified time period is the time period corresponding to the current moment to the past 30 days. It should be noted that the preset sampling frequency in this application has a value range of 1000-5000Hz.

[0094] In some embodiments, the following steps may be used to extract the temperature distribution characteristic entropy of the current environment of the target space through the discrete characteristics of the ambient temperature data and the current ambient humidity data:

[0095] Get the ambient humidity data within the specified time period;

[0096] Determine a correlation coefficient between humidity and temperature according to the ambient humidity data and the ambient temperature data;

[0097] Converting the ambient temperature data into a temperature sequence, and then determining discrete features of the temperature sequence;

[0098] Extracting temperature distribution characteristic values ​​of the ambient temperature data through the discrete features;

[0099] The temperature distribution characteristic entropy of the current environment of the target space is determined by the current environment humidity data, the correlation coefficient and the temperature distribution characteristic value.

[0100] It should be noted that in the present application, in order to obtain the ambient humidity data within a specified time period, multiple temperature sensors can be used to collect the ambient humidity data of the target space within a specified time period according to a specified sampling frequency, wherein the value range of the specified sampling frequency can be set between 1000-5000Hz, and the specified time period is the time period corresponding to the current moment to the past 30 days.

[0101] In specific implementation, the correlation coefficient between humidity and temperature is determined according to the ambient humidity data and the ambient temperature data, that is, the correlation coefficient represents the changing relationship between temperature and humidity. In some embodiments, the correlation coefficient between humidity and temperature can be determined by using the covariance in the prior art, which will not be described in detail here; the ambient temperature data is converted into a temperature sequence, and then the discrete characteristics of the temperature sequence are determined, that is, the sequence obtained by sorting the ambient humidity data in chronological order according to the collection time is used as the temperature sequence. As a preferred embodiment, the discrete characteristics of the temperature sequence can be calculated by the standard deviation in the prior art, and in other embodiments, the discrete characteristics of the temperature sequence can also be calculated by using the variance in the prior art; the temperature distribution characteristic value of the ambient temperature data is extracted by the discrete characteristics, that is, the temperature distribution characteristic value represents an indicator of the temperature distribution law in the target space, and the temperature distribution characteristic value is composed of the ratio of the average degree of the ambient temperature sequence to the discrete degree, which is used to reflect the distribution of the ambient temperature in the target space. The larger the value, the more dispersed the ambient temperature distribution in the target space is; the temperature distribution characteristic entropy of the current environment of the target space is determined by the current ambient humidity data, the correlation coefficient and the temperature distribution characteristic value, that is, first, the average value of the current ambient humidity data is calculated; secondly, the current ambient temperature margin is calculated by the correlation coefficient and the average value, that is, the current ambient temperature margin is obtained by multiplying the correlation coefficient with the inverse of the average value; thirdly, the current ambient temperature margin is used as an adjustment coefficient to adjust the temperature distribution characteristic value to obtain a temperature adjustment distribution characteristic value; then, the temperature information entropy of the current environment of the target space can be calculated by the information entropy in the prior art; finally, the temperature information entropy is compensated by the temperature adjustment distribution characteristic value to obtain the temperature distribution characteristic entropy of the current environment of the target space; in some embodiments, the natural logarithm of the inverse of the temperature adjustment distribution characteristic value can be used as a compensation coefficient, and the product of the compensation coefficient and the temperature information entropy is used as the temperature distribution characteristic entropy of the current environment of the target space.

[0102] It should be noted that the temperature distribution characteristic entropy in this application refers to a measurement value used to describe the uncertainty of the temperature distribution in the target space. The larger the value of the temperature distribution characteristic entropy, the higher the uncertainty of the temperature distribution, and vice versa.

[0103] In step 105, the global fusion humidity of the current environmental humidity data is determined according to all the local fusion humidity and the temperature distribution characteristic entropy, and the global fusion humidity is used as the humidity of the current environment of the target space.

[0104] In some embodiments, determining the global fusion humidity of the current environmental humidity data according to all the local fusion humidity and the temperature distribution characteristic entropy can be implemented by the following steps:

[0105] Determine the temperature compensation coefficient of the external environment;

[0106] Determine the humidity credible interval for each modal humidity data segment;

[0107] Determine the heterogeneous fusion humidity characteristic value of each modal humidity data segment according to all local fusion humidity and all humidity credible intervals;

[0108] The global fused humidity of the current environmental humidity data is determined by the temperature compensation coefficient, all heterogeneous fused humidity characteristic values ​​and the temperature distribution characteristic entropy.

[0109] In specific implementation, the temperature compensation coefficient of the external environment is determined, that is, the temperature value of the current detection environment is obtained, the average temperature value of the detection environment is calculated through the temperature values ​​of the historical detection environments, and the temperature fluctuation value of the detection environment is determined through the temperature value of the current detection environment and the average temperature value. In some embodiments, the temperature fluctuation value may be the absolute value of the difference between the temperature value of the current detection environment and the average temperature value, and then the natural logarithm of the reciprocal of the temperature fluctuation value is used as the temperature compensation coefficient of the external environment. The temperature compensation coefficient represents a parameter used when considering the influence of temperature changes on the detection results during the humidity detection process, and is used to reduce the error caused by temperature fluctuations on the environmental humidity detection results; determine the humidity of each modal humidity data segment. The humidity credible interval is determined by calculating the humidity credible interval of the modal humidity data segment, that is, selecting a modal humidity data segment, obtaining the maximum and minimum ambient humidity values ​​in the modal humidity data segment, and taking the interval formed by the maximum and minimum ambient humidity values ​​(maximum ambient humidity value - minimum ambient humidity value) as the humidity credible interval of the modal humidity data segment, and continuing to determine the humidity credible intervals of the remaining modal humidity data segments; the heterogeneous fusion humidity feature values ​​of each modal humidity data segment are determined according to all the local fusion humidity and all the humidity credible intervals, that is, selecting a modal humidity data segment, firstly, selecting an ambient humidity value from the modal humidity data segment, and comparing the ambient humidity value with the local fusion humidity of the modal humidity data segment. The rows are subtracted and then squared to obtain the square of the difference of the ambient humidity value, and the square of the difference of the remaining ambient humidity values ​​is continued to be determined, and then all the squares of the difference are summed, and the sum obtained by the sum is multiplied by the inverse of the humidity credible interval of the modal humidity data segment to obtain the heterogeneous fusion humidity eigenvalue of the modal humidity data segment, and the heterogeneous fusion humidity eigenvalues ​​of the remaining modal humidity data segments are continued to be determined; the global fusion humidity of the current ambient humidity data is determined by the temperature compensation coefficient, all the heterogeneous fusion humidity eigenvalues ​​and the temperature distribution characteristic entropy, that is, first, the compensation coefficient of the heterogeneous fusion humidity eigenvalue can be determined by the temperature compensation coefficient and the temperature distribution characteristic entropy. As a preferred embodiment, The product of the temperature compensation coefficient and the temperature distribution characteristic entropy is used as the compensation coefficient of the heterogeneous fusion humidity characteristic value, and then each heterogeneous fusion humidity characteristic value is compensated to reduce the error caused by temperature fluctuation to the ambient humidity detection result. The compensation coefficient can be multiplied by each heterogeneous fusion humidity characteristic value respectively. Secondly, the central trend feature of the compensated heterogeneous fusion humidity characteristic value is used as the global fusion humidity of the current ambient humidity data. The central trend feature represents a parameter for quantifying the average degree of all heterogeneous fusion humidity characteristic values. In some embodiments, the mean in the prior art can be used as the central trend feature, or the mode in the prior art can be used as the central trend feature, which is not limited here.

[0110] It should be noted that the global fused humidity in the present application represents a comprehensive evaluation index of the ambient humidity in the target space. It is beneficial to provide a more comprehensive ambient humidity estimation result by fusing multi-source heterogeneous data, thereby improving the reliability of the humidity detection results. Therefore, the global fused humidity can be used as the humidity of the current environment of the target space.

[0111] In addition, in another aspect of the present application, in some embodiments, the present application provides a humidity detection system, referring to Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a humidity detection system according to some embodiments of the present application, the humidity detection system 400 includes: an acquisition module 401, a processing module 402 and an execution module 403, which are described as follows:

[0112] Acquisition module 401, in this application, acquisition module 401 is mainly used to collect current environmental humidity data of the target space using multiple sensors in the humidifier;

[0113] Processing module 402, in the present application, the processing module 402 is used to perform feature constraints on the current environmental humidity data to obtain environmental humidity constraint data, and then convert the environmental humidity constraint data into multiple modal humidity data segments according to the difference characteristics of the sensor;

[0114] The processing module 402 in the present application is also used to determine the sampling mutual support of each modal humidity data segment through the confidence distance between each sensor, and determine the local fusion humidity of the corresponding modal humidity data segment according to each sampling mutual support;

[0115] The processing module 402 in the present application is also used to obtain the ambient temperature data within a specified time period, and extract the temperature distribution characteristic entropy of the current environment of the target space through the discrete characteristics of the ambient temperature data and the current ambient humidity data;

[0116] Execution module 403, in this application, execution module 403 is mainly used to determine the global fusion humidity of the current environmental humidity data according to all local fusion humidity and the temperature distribution characteristic entropy, and use the global fusion humidity as the humidity of the current environment of the target space.

[0117] In other aspects of the present application, a humidifier is also provided, which includes the above-mentioned humidity detection system. The humidifier can perform feature fusion on multi-source heterogeneous humidity data according to the humidity detection system to provide a more comprehensive environmental humidity estimation result, thereby improving the reliability of the humidity detection result of the humidifier.

[0118] In addition, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned humidity detection method.

[0119] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing a humidity detection method according to some embodiments of the present application. The humidity detection method in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0120] The processor 501 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more processors for controlling the execution of the humidity detection method in the present application.

[0121] Communication bus 502 may include a pathway for transmitting information between the above-mentioned components.

[0122] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0123] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The humidity detection method in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0124] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0125] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0126] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0127] In addition, the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned humidity detection method is implemented.

[0128] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0129] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A humidity detection method, characterized in that: The steps include: Use multiple sensors in the humidifier to collect current ambient humidity data of the target space; Performing feature constraints on current environmental humidity data to obtain environmental humidity constraint data, and then converting the environmental humidity constraint data into multiple modal humidity data segments according to differential characteristics of sensors; The sampling mutual support of each modal humidity data segment is determined by the confidence distance between each sensor, and the local fusion humidity of the corresponding modal humidity data segment is determined according to each sampling mutual support; Acquire the ambient temperature data within a specified time period, and extract the temperature distribution characteristic entropy of the current environment of the target space through the discrete characteristics of the ambient temperature data and the current ambient humidity data; The global fused humidity of the current environmental humidity data is determined according to all the local fused humidity and the temperature distribution characteristic entropy, and the global fused humidity is used as the humidity of the current environment of the target space.

2. The method according to claim 1, characterized in that The current environmental humidity data is subjected to feature constraints, and the obtained environmental humidity constraint data specifically includes: Eliminate abnormal data in the current environmental humidity data to obtain environmental humidity cleaning data; Then, the environmental humidity cleaning data is scale-constrained to obtain environmental humidity constraint data.

3. The method according to claim 1, characterized in that The mutual support of sampling of each modal humidity data segment is determined by the confidence distance between each sensor, specifically including: Get the distance between each sensor; Determine the confidence distance between each sensor through all the distances; Determine the confidence distance matrix of each sensor based on all confidence distances; Determine the sampling variance matrix of each modal humidity data segment; The sampling mutual support of each modal humidity data segment is determined based on all confidence distance matrices and all sampling variance matrices.

4. The method according to claim 1, characterized in that The local fusion humidity of the corresponding modal humidity data segment is determined according to the mutual support of each sample, specifically including: Select a modal humidity data segment; Determine the similarity between the humidity data collected by the sensor corresponding to the modal humidity data segment; Determine the similarity matrix of the modal humidity data segment based on all similarities; Determining the local fusion humidity of the modal humidity data segment through the sampling mutual support of the modal humidity data segment and the similarity matrix; Continue to determine the local fused humidity for the remaining modal humidity data segments.

5. The method according to claim 1, characterized in that Determining the global fusion humidity of the current environmental humidity data based on all the local fusion humidity and the temperature distribution characteristic entropy specifically includes: Determine the temperature compensation coefficient of the external environment; Determine the humidity credible interval for each modal humidity data segment; Determine the heterogeneous fusion humidity characteristic value of each modal humidity data segment according to all local fusion humidity and all humidity credible intervals; The global fused humidity of the current environmental humidity data is determined by the temperature compensation coefficient, all heterogeneous fused humidity characteristic values ​​and the temperature distribution characteristic entropy.

6. The method according to claim 1, characterized in that Converting the environmental humidity constraint data into a plurality of modal humidity data segments according to the difference characteristics of the sensor specifically includes: Get the category information of the sensor; Determining the difference characteristics of the sensor through the category information; Classifying the environmental humidity constraint data according to the difference characteristics to obtain different humidity data classes; A plurality of modal humidity data segments are determined according to different humidity data categories.

7. The method according to claim 1, characterized in that The sensors include: a resistive humidity sensor, a capacitive humidity sensor and a thermal conductivity humidity sensor.

8. A humidity detection system, characterized in that: include: An acquisition module is used to collect current environmental humidity data of the target space using multiple sensors in the humidifier; A processing module, used for performing feature constraints on current environmental humidity data to obtain environmental humidity constraint data, and then converting the environmental humidity constraint data into multiple modal humidity data segments according to the difference characteristics of the sensor; The processing module is further used to determine the sampling mutual support of each modal humidity data segment through the confidence distance between each sensor, and determine the local fusion humidity of the corresponding modal humidity data segment according to each sampling mutual support; The processing module is further used to obtain the ambient temperature data within a specified time period, and extract the temperature distribution characteristic entropy of the current environment of the target space through the discrete characteristics of the ambient temperature data and the current ambient humidity data; The execution module is used to determine the global fusion humidity of the current environmental humidity data according to all the local fusion humidity and the temperature distribution characteristic entropy, and use the global fusion humidity as the humidity of the current environment of the target space.

9. A humidifier, characterized in that: The humidifier includes the humidity detection system described in claim 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the humidity detection method according to any one of claims 1 to 7 is implemented.

Images