Indoor environment data analysis method and related device

Abstract

The embodiment of the invention provides an indoor environment data analysis method and a related device, and belongs to the technical field of data analysis. The method comprises the following steps: acquiring first monitoring data of a target object at a first moment and second monitoring data of the target object at a second moment under the monitoring of a plurality of Lora sensors; obtaining a first association relationship between any two Lora sensors in the plurality of Lora sensors according to the first monitoring data, and obtaining a second association relationship between any two Lora sensors in the plurality of Lora sensors according to the second monitoring data; determining a first analysis result of the target object according to the first association relationship and the second association relationship; determining a first data change according to the first monitoring data and the second monitoring data, and determining a second analysis result of the target object according to the first data change and a data threshold; and fusing the first analysis result and the second analysis result to determine a target analysis result. The problem that the analysis effect is poor due to the fact that correlation between Lora sensors is not utilized in the related technology is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to an indoor environment data analysis method and related devices. Background Art

[0002] The analysis of indoor monitoring data can be realized by using complex algorithms and models after collecting data using Lora sensors. For example, by using recurrent neural networks to process Lora sensor data, these technologies have greatly improved the intelligence level of indoor monitoring data analysis. However, the existing technology lacks the association between Lora sensors, so more data may need to be analyzed to achieve the same analysis effect, which may increase the consumption of time and computing resources. And if the association between Lora sensors is not used, the synergy effect of Lora sensors cannot be exerted, resulting in poor analysis results, further increasing security risks. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide an indoor environment data analysis method and related devices, aiming to solve the problem in the related technology that there is a lack of association between Lora sensors, the synergistic effect of Lora sensors cannot be exerted, resulting in poor analysis results, further increasing the safety risks.

[0004] In a first aspect, an embodiment of the present invention provides an indoor environment data analysis method, comprising:

[0005] Obtaining first monitoring data corresponding to a first moment and second monitoring data corresponding to a second moment of a target object under monitoring by multiple Lora sensors;

[0006] Obtaining a first association relationship between any two Lora sensors among the plurality of Lora sensors according to the first monitoring data, and obtaining a second association relationship between any two Lora sensors among the plurality of Lora sensors according to the second monitoring data;

[0007] Determine a first analysis result corresponding to the target object according to the first association relationship and the second association relationship;

[0008] Determine a first data change corresponding to the target object according to the first monitoring data and the second monitoring data, and determine a second analysis result corresponding to the target object according to the first data change and a data threshold;

[0009] The first analysis result and the second analysis result are integrated to determine a target analysis result corresponding to the target object.

[0010] In a second aspect, an embodiment of the present invention provides an indoor environment data analysis device, comprising:

[0011] A data acquisition module, used to obtain first monitoring data corresponding to a first moment and second monitoring data corresponding to a second moment of a target object under monitoring by multiple Lora sensors;

[0012] an association analysis module, configured to obtain a first association relationship between any two Lora sensors among the plurality of Lora sensors according to the first monitoring data, and to obtain a second association relationship between any two Lora sensors among the plurality of Lora sensors according to the second monitoring data;

[0013] A first analysis module, configured to determine a first analysis result corresponding to the target object according to the first association relationship and the second association relationship;

[0014] A second analysis module, configured to determine a first data change corresponding to the target object according to the first monitoring data and the second monitoring data, and to determine a second analysis result corresponding to the target object according to the first data change and a data threshold;

[0015] A target analysis module is used to fuse the first analysis result and the second analysis result to determine a target analysis result corresponding to the target object.

[0016] In a third aspect, an embodiment of the present invention further provides a terminal device, comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the steps of any indoor environment data analysis method provided in the specification of the present invention are implemented.

[0017] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any indoor environment data analysis method provided in the specification of the present invention.

[0018] The embodiment of the present invention provides an indoor environment data analysis method and a related device. The method includes: obtaining first monitoring data corresponding to the first moment and second monitoring data corresponding to the second moment of a target object under the monitoring of multiple Lora sensors, and then determining the first association relationship between any two Lora sensors by analyzing the first monitoring data, and determining the second association relationship between any two Lora sensors by analyzing the second monitoring data, so as to help reveal the relationship and role between different sensors, help understand the influence and dependence between sensors in the monitoring network, and then determine the first analysis result of the target object based on the first association relationship and the second association relationship. This can help detect important changes or abnormal conditions of the target object, and then by analyzing the first monitoring data and the second monitoring data, the data change of the target object can be calculated, and the second analysis result of the target object can be determined according to the data threshold, which helps to timely discover data changes and identify potential problems or risks. Therefore, the first analysis result and the second analysis result are integrated to determine the target analysis result of the target object, and then the state of the target object can be more comprehensively understood, providing support for subsequent decision makers to make accurate judgments and decisions. And enhance the monitoring and analysis capabilities of the state changes of the target object, which helps to timely warn potential problems and take targeted measures, thereby improving the corresponding security of the target object. And it solves the problem that the related technology lacks the connection between Lora sensors, so that the synergistic effect of Lora sensors cannot be exerted, resulting in poor analysis results, further increasing the safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A schematic diagram of a flow chart of an indoor environment data analysis method provided by an embodiment of the present invention;

[0021] Figure 2 A schematic diagram of the module structure of an indoor environment data analysis device provided by an embodiment of the present invention;

[0022] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0025] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0026] The embodiment of the present invention provides an indoor environment data analysis method and related devices. The indoor environment data analysis method can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0027] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0028] Please refer to Figure 1 , Figure 1 A schematic diagram of a flow chart of an indoor environment data analysis method provided by an embodiment of the present invention.

[0029] like Figure 1 As shown, the indoor environment data analysis method includes steps S101 to S105.

[0030] Step S101: obtaining first monitoring data corresponding to a first moment and second monitoring data corresponding to a second moment of a target object under monitoring by multiple Lora sensors.

[0031] For example, Lora sensors usually use low-power wide area network (LPWAN) technology for data transmission to ensure that data can be stably transmitted to a centralized storage or processing unit. The target object is the indoor environment that needs to be monitored, which can be a scene room corresponding to cultural relics protection, or an ecological environment corresponding to ecological protection, etc.

[0032] Exemplarily, a plurality of LoRa sensors are used to monitor the target object, and the plurality of LoRa sensors include but are not limited to temperature sensors, humidity sensors, light intensity sensors and other LoRa sensors.

[0033] Exemplarily, the second moment can be the current moment, and the first moment is the previous moment adjacent to the current moment, and then multiple Lora sensors are used to monitor the target object to obtain first monitoring data corresponding to the first moment, and multiple Lora sensors are used to monitor the target object to obtain second monitoring data corresponding to the second moment.

[0034] Step S102: obtaining a first association relationship between any two Lora sensors among the plurality of Lora sensors according to the first monitoring data, and obtaining a second association relationship between any two Lora sensors among the plurality of Lora sensors according to the second monitoring data.

[0035] Exemplarily, the multiple Lora sensors include a temperature sensor, a humidity sensor, and a light intensity sensor, and then first temperature data corresponding to the temperature sensor, first humidity data corresponding to the humidity sensor, and first light data corresponding to the light intensity sensor are obtained from the first monitoring data.

[0036] Exemplarily, the first temperature data and the first humidity data are used to evaluate the first temperature-humidity correlation between the temperature sensor and the humidity sensor using the Pearson correlation coefficient, or the covariance between the first temperature data and the first humidity data is used to measure the overall directional correlation between the temperature sensor and the humidity sensor. For example, a positive covariance indicates that the correlation between the two sensors is positively correlated, and a negative covariance indicates that the correlation between the two sensors is negatively correlated. Similarly, the first temperature data and the first illumination data are used to determine the first temperature-light correlation between the temperature sensor and the light intensity sensor, and the first illumination data and the first illumination data are used to determine the first humidity-light correlation between the humidity sensor and the light intensity sensor, thereby obtaining the first correlation according to the first temperature-humidity correlation, the first temperature-light correlation, and the first humidity-light correlation.

[0037] Exemplarily, second temperature data corresponding to the temperature sensor, second humidity data corresponding to the humidity sensor, and second illumination data corresponding to the illumination intensity sensor are obtained from the second monitoring data.

[0038] Exemplarily, the second temperature data and the second humidity data are used to evaluate the second temperature-humidity correlation between the temperature sensor and the humidity sensor using the Pearson correlation coefficient, or the covariance between the second temperature data and the second humidity data is used to measure the overall directional correlation between the temperature sensor and the humidity sensor. For example, a positive covariance indicates that the correlation between the two sensors is positively correlated, and a negative covariance indicates that the correlation between the two sensors is negatively correlated. Similarly, the second temperature data and the second illumination data are used to determine the second temperature-illumination correlation between the temperature sensor and the illumination intensity sensor, and the second illumination data and the second illumination data are used to determine the second humidity-illumination correlation between the humidity sensor and the illumination intensity sensor, thereby obtaining the second correlation according to the second temperature-humidity correlation, the second temperature-illumination correlation, and the second humidity-illumination correlation.

[0039] In some embodiments, the first monitoring data includes at least first sensor data corresponding to the first Lora sensor and second sensor data corresponding to the second Lora sensor, and obtaining a first association relationship between any two Lora sensors among the multiple Lora sensors based on the first monitoring data includes: performing data clustering on the first sensor data and the second sensor data to obtain a first multidimensional data set; performing data association analysis based on the first multidimensional data set to obtain an association matrix between the first Lora sensor and the second Lora sensor; and determining the first association relationship between the first Lora sensor and the second Lora sensor based on the association matrix.

[0040] Exemplarily, the first monitoring data includes at least first sensing data corresponding to the first Lora sensor and second sensing data corresponding to the second Lora sensor, such as the first Lora sensor is a temperature sensor and the second Lora sensor is a humidity sensor.

[0041] Exemplarily, a clustering algorithm (such as K-means clustering, hierarchical clustering, etc.) is used to cluster the first sensor data and the second sensor data into different clusters. The goal of clustering is to classify data points between the first sensor data and the second sensor data with similar features into the same cluster. Thus, the clustered data points are combined into a first multidimensional data set. Each data point can be regarded as a vector, representing features in different dimensions.

[0042] Exemplarily, an association analysis method (such as association rule mining, collaborative filtering, etc.) is used to explore the relationship between the first Lora sensor and the second Lora sensor in the first multidimensional data set. Association analysis can help discover patterns or rules that frequently co-occur between sensors, thereby identifying the association between them.

[0043] Exemplarily, a correlation matrix is ​​constructed according to the results of the correlation analysis, and each element of the matrix represents the degree of correlation or the strength of the relationship between two Lora sensors, so that relationship classification is performed based on the correlation matrix to obtain the first correlation relationship corresponding to the first Lora sensor and the second Lora sensor at the first moment.

[0044] Specifically, the clustering process helps to discover potential patterns and clusters in the data between different sensors. These patterns may reveal common features or change patterns between different sensor data at the same time, providing a basis for subsequent association analysis. Then, association analysis based on the first multidimensional data set can deeply explore the association patterns between sensors, and then find out which sensors are close to each other in multidimensional space, or have a tendency to change together in certain specific features, thereby providing good support for subsequent data analysis.

[0045] In some embodiments, performing data association analysis according to the first multidimensional data set to obtain an association matrix between the first Lora sensor and the second Lora sensor includes: obtaining first data corresponding to the first Lora sensor and second data corresponding to the second Lora sensor from the first multidimensional data set; calculating a data distance between the first data and the second data at the same time, and establishing an adjacent matrix according to the data distance; arbitrarily combining the first data and the second data to obtain combined data, and obtaining a first probability corresponding to the combined data; obtaining a second probability corresponding to the first data in the combined data and a third probability corresponding to the second data in the combined data; determining the association matrix between the first Lora sensor and the second Lora sensor according to the adjacent matrix, the first probability, the second probability, and the third probability; wherein the association matrix is ​​obtained according to the following formula:

[0046] ;

[0047] represents the matrix value corresponding to the incidence matrix in row i and column j, The first probability of the combined data obtained by combining the i-th data in the first data and the j-th data in the second data; represents the second probability corresponding to the i-th data in the first data; represents the third probability corresponding to the j-th data in the second data; represents the matrix value corresponding to the adjacent matrix in the i-th row and j-th column; Represents weight information between the i-th data in the first data and the j-th data in the second data.

[0048] Exemplarily, first data corresponding to the first Lora sensor and second data corresponding to the second Lora sensor are extracted from the first multidimensional data set. These data may be features determined in the clustering process or other data representations. Then, for the first data and the second data at the same time, the data distance between them is calculated. The distance metric may select a suitable method according to the data type, such as Euclidean distance, Manhattan distance, etc.

[0049] Exemplarily, an adjacency matrix is ​​established based on the calculated data distance. The adjacency matrix is ​​used to represent the proximity or distance between two sensors. Generally, the smaller the distance, the closer the sensor pair is or the higher the correlation is. Thus, the first data and the second data are arbitrarily combined to form combined data.

[0050] Exemplarily, a first probability is calculated for each combination of data based on statistical analysis, model output or other prior knowledge, and a first frequency corresponding to the first data in the combination of data in the first multidimensional data set is obtained, and then a second probability is obtained according to the first frequency, and a second frequency corresponding to the second data in the combination of data in the first multidimensional data set is obtained, and then a third probability is obtained according to the second frequency.

[0051] Exemplarily, a correlation matrix between the first Lora sensor and the second Lora sensor is determined according to the adjacent matrix, the first probability, the second probability, and the third probability, the correlation between the data of the first Lora sensor and the second Lora sensor is determined by the correlation matrix, and the correlation matrix is ​​obtained according to the following formula:

[0052] ;

[0053] represents the matrix value corresponding to the i-th row and j-th column of the association matrix, represents a first probability of combined data obtained by combining the i-th data in the first data and the j-th data in the second data; represents the second probability corresponding to the i-th data in the first data; represents the third probability corresponding to the j-th data in the second data; Represents the matrix value corresponding to the adjacent matrix of the i-th row and j-th column; Represents the weight information between the i-th data in the first data and the j-th data in the second data.

[0054] Specifically, by calculating the data distance between two Lora sensors at the same time and establishing an adjacent matrix, the relationship between these sensors can be identified and modeled. The adjacent matrix can help understand which sensors are close to each other in space or data, so that more refined analysis and optimization can be performed. Then, by arbitrarily combining the first data and the second data and calculating the probability corresponding to the combined data, the relationship between the data and its impact can be more comprehensively understood. This method helps to discover potential patterns and laws in data combinations, and then by constructing an association matrix, it provides support for a better understanding of the association between sensors in the future, and more accurately understands the interactions and dependencies between data, thereby improving the accuracy of data processing and analysis.

[0055] Similarly, according to the above steps, the second monitoring data is used to obtain a second association relationship between any two Lora sensors in the plurality of Lora sensors, which will not be described in detail here.

[0056] Step S103: Determine a first analysis result corresponding to the target object according to the first association relationship and the second association relationship.

[0057] Exemplarily, the first association relationship represents the association degree or similarity between any two Lora sensors at a first moment, and the second association relationship represents the association degree or similarity between any two Lora sensors at a second moment.

[0058] Exemplarily, when the first correlation between the first Lora sensor and the second Lora sensor at the first moment is a positive correlation, and the second correlation between the first Lora sensor and the second Lora sensor at the second moment is also a positive correlation, the first analysis result is that the test result of the target object between the first Lora sensor and the second Lora sensor is normal; when the first correlation between the first Lora sensor and the second Lora sensor at the first moment is a positive correlation, and the second correlation between the first Lora sensor and the second Lora sensor at the second moment is a negative correlation, the first analysis result is that the test result of the target object between the first Lora sensor and the second Lora sensor is abnormal.

[0059] In some embodiments, determining the first analysis result corresponding to the target object based on the first association relationship and the second association relationship includes: determining a mapping table, obtaining a first numerical value corresponding to the first association relationship based on the mapping table, and obtaining a second numerical value corresponding to the second association relationship based on the mapping table; determining a second data change between the first association relationship and the second association relationship based on the first numerical value and the second numerical value; and determining the first analysis result corresponding to the target object based on the second data change.

[0060] Exemplarily, a mapping table is created to map the first association relationship and the second association relationship to specific values. These mappings may be based on pre-set rules or data analysis results.

[0061] Exemplarily, a mapping table is used to obtain the first and second values ​​corresponding to the first and second association relationships, respectively, according to the first and second association relationships. These values ​​can be any measure for describing the strength or similarity of the relationship. Thus, based on the obtained first and second values, the second data change between them is calculated or inferred. This can be a difference value, ratio, or other related measure to indicate the change or trend of the relationship.

[0062] Exemplarily, a statistical analysis or machine learning method is used to determine the first analysis result corresponding to the target object according to the second data change.

[0063] Specifically, by determining a mapping table and obtaining the values ​​corresponding to the first association relationship and the second association relationship according to the mapping table, complex relationship data can be quantified into standardized values ​​that can be compared and analyzed. This helps to eliminate subjectivity and uncertainty, making subsequent analysis more objective and reliable. Then, based on the first value and the second value, the data changes between the association relationships are calculated. This analysis can reveal the evolution trend of the relationship, such as whether it tends to strengthen, weaken, or remain stable. Thus, by determining the first analysis result of the target object through the second data change, the impact of the relationship change on the target object can be more deeply understood.

[0064] Step S104: determine a first data change corresponding to the target object according to the first monitoring data and the second monitoring data, and determine a second analysis result corresponding to the target object according to the first data change and a data threshold.

[0065] Exemplarily, the difference (such as difference, ratio change, etc.) between the first monitoring data and the second monitoring data is calculated to obtain the first data change. And one or more data thresholds are set according to business needs or historical data. These thresholds are used to determine whether the data change has reached a level that requires attention, and may include a safety range, a performance degradation warning line, a fault warning line, etc.

[0066] Exemplarily, the calculated first data change is compared with a set data threshold. According to the comparison result, the second analysis result corresponding to the target object is determined. For example, if the data change exceeds a certain data threshold, it may indicate that the state of the target object has changed significantly and corresponding measures need to be taken.

[0067] In some embodiments, the first monitoring data includes third sensor data corresponding to a third Lora sensor, and the second monitoring data includes fourth sensor data corresponding to the third Lora sensor, and determining the first data change corresponding to the target object based on the first monitoring data and the second monitoring data includes: splicing the third sensor data and the fourth sensor data to obtain spliced ​​sensor data; determining a sliding window, and obtaining window sensor data corresponding to the spliced ​​sensor data based on the sliding window; calculating a first mean value and a first variance corresponding to the window sensor data; determining a window representation value corresponding to the target object based on the first mean value and the first variance, and determining the first data change based on the window representation value.

[0068] Exemplarily, the first monitoring data includes at least third sensor data corresponding to the third Lora sensor, and the second monitoring data includes at least fourth sensor data corresponding to the third Lora sensor, and then the third sensor data and the fourth sensor data are spliced ​​in the order of collection to form spliced ​​sensor data.

[0069] Exemplarily, a sliding window is set to extract window sensor data from the spliced ​​sensor data. The size and step size of the sliding window can be set according to specific needs, such as the time span of the window or the number of data points. Then, the window sensor data in each sliding window is statistically analyzed to calculate the first mean and first variance of the window sensor data. These statistics help to understand the central tendency and distribution range of the data in the window.

[0070] Exemplarily, data fusion is performed based on the calculated first mean value and first variance to determine the window characterization value, which is then used for subsequent analysis and comparison. The window characterization value is then used to calculate the first data change corresponding to the target object. This may involve comparison with previous window characterization values, or use other mathematical models or rules to analyze the change trend between windows.

[0071] Specifically, setting a sliding window and extracting window sensor data can make the analysis more refined and dynamic. By moving the window over time or data series, the instantaneous changes and long-term trends of the data can be captured, providing a more accurate basis for analysis. Calculating the mean and variance of the window sensor data helps to extract the statistical features of the window. These features can not only summarize the central tendency and distribution range of the data within the window, but also provide a quantitative basis for subsequent data change analysis. Based on the window characterization value, the data changes of the target object can be calculated. This analysis can help identify and understand the change patterns of the target object in time or space, thereby providing deeper insights and basis for prediction, optimization, and decision-making.

[0072] In some embodiments, determining the window representation value corresponding to the target object based on the first mean and the first variance includes: obtaining the second mean and the second variance corresponding to the previous sliding window; determining the sliding factor corresponding to the sliding window, and determining the target mean by fusing the first mean and the second mean based on the sliding factor; determining the target variance by fusing the first variance and the second variance based on the sliding factor; and determining the window representation value corresponding to the target object by fusing the target mean and the target variance using an adjustment factor.

[0073] For example, during the window sliding process, the second mean value and the second variance of the previous sliding window are saved and recorded, and then a sliding factor is set, which can be a fixed value or dynamically adjusted according to specific circumstances. The sliding factor determines how to fuse the statistical features of the previous window and the statistical features of the current window.

[0074] Exemplarily, a sliding factor is used to linearly or nonlinearly fuse the first average value of the previous window and the first average value of the current window to determine the target average value. This fusion can select a suitable method according to business requirements and data characteristics, such as weighted average or other mathematical models.

[0075] Similarly, the sliding factor is used to fuse the first variance of the previous window and the first variance of the current window to determine the target variance. This step is similar to the fusion of the average value, and a suitable fusion method can be selected as needed.

[0076] For example, an adjustment factor is used to combine the fused target mean and target variance to form a final window representation value. This adjustment factor can be adjusted according to the specific application scenario to achieve the best balance or accuracy requirement.

[0077] Specifically, the comprehensive analysis and feature extraction of the window sensor data corresponding to the sliding window is realized, so as to understand the dynamic characteristics and change trends of the target object in the time series. This method can not only improve the accuracy and practicality of data analysis, but also provide an important reference for subsequent decision-making and optimization.

[0078] Step S105: Fusing the first analysis result and the second analysis result to determine a target analysis result corresponding to the target object.

[0079] Exemplarily, a logical operation (such as logical AND, logical OR) or a decision tree fusion algorithm is used to merge or operate the first analysis result and the second analysis result according to the selected fusion method to obtain a comprehensive target analysis result.

[0080] In some embodiments, the fusion of the first analysis result and the second analysis result to determine the target analysis result corresponding to the target object includes: obtaining a first analysis probability corresponding to the first analysis result and a second analysis probability corresponding to the second analysis result; fusing the first analysis probability and the second analysis probability to obtain a target analysis probability; and determining the target analysis result corresponding to the target object based on the target analysis probability.

[0081] Exemplarily, for the first analysis result, according to the analysis method or model used, a first analysis probability corresponding to the result is obtained or calculated. This probability may represent the possibility or accuracy of the occurrence of the result. Similarly, for the second analysis result, a corresponding second analysis probability is calculated.

[0082] Exemplarily, a suitable probability fusion method is selected. Common methods include weighted average, product rule, maximum rule or more complex fusion algorithms, such as Dempster-Shafer theory, etc., and then the first analysis probability and the second analysis probability are fused according to the probability fusion method to obtain the target analysis probability.

[0083] Exemplarily, a decision threshold is set, which is used to determine whether the target analysis probability reaches the standard for taking a certain action or drawing a conclusion. The target analysis probability is then compared with the decision threshold. If the target analysis probability exceeds the threshold, the target analysis result of the target object is determined according to a preset rule or logic. The target analysis result may be a classification label, a predicted value, a decision suggestion, etc., depending on the application scenario and the purpose of the analysis.

[0084] Specifically, fusing the first analysis probability and the second analysis probability can reduce the possibility of misjudgment of a single analysis result. By comprehensively considering information from different sources, the target analysis probability obtained is more reliable and robust, which helps to make more reliable decisions or inferences. Therefore, the target analysis result of the target object is determined according to the fused target analysis probability, which can provide an important reference for subsequent decision-making. This method makes decisions more based on data and probability, reduces the influence of subjective judgment, and helps to improve the accuracy and effectiveness of decisions.

[0085] The embodiment of the present invention provides an indoor environment data analysis method and a related device. The method includes: obtaining first monitoring data corresponding to the first moment and second monitoring data corresponding to the second moment of a target object under the monitoring of multiple Lora sensors, and then determining the first association relationship between any two Lora sensors by analyzing the first monitoring data, and determining the second association relationship between any two Lora sensors by analyzing the second monitoring data, so as to help reveal the relationship and role between different sensors, help understand the influence and dependence between sensors in the monitoring network, and then determine the first analysis result of the target object based on the first association relationship and the second association relationship. This can help detect important changes or abnormal conditions of the target object, and then by analyzing the first monitoring data and the second monitoring data, the data change of the target object can be calculated, and the second analysis result of the target object can be determined according to the data threshold, which helps to timely discover data changes and identify potential problems or risks. Therefore, the first analysis result and the second analysis result are integrated to determine the target analysis result of the target object, and then the state of the target object can be more comprehensively understood, providing support for subsequent decision makers to make accurate judgments and decisions. And enhance the monitoring and analysis capabilities of the state changes of the target object, which helps to timely warn potential problems and take targeted measures, thereby improving the corresponding security of the target object. And it solves the problem that the related technology lacks the connection between Lora sensors, so that the synergistic effect of Lora sensors cannot be exerted, resulting in poor analysis results, further increasing the safety risks.

[0086] See also Figure 2 , Figure 2An indoor environment data analysis device 200 provided in an embodiment of the present application includes a data acquisition module 201, an association analysis module 202, a first analysis module 203, a second analysis module 204, and a target analysis module 205, wherein the data acquisition module 201 is used to obtain first monitoring data corresponding to a target object at a first moment and second monitoring data corresponding to a second moment under the monitoring of multiple Lora sensors; the association analysis module 202 is used to obtain a first association relationship between any two Lora sensors in the multiple Lora sensors according to the first monitoring data, and to obtain a second association relationship between any two Lora sensors in the multiple Lora sensors according to the second monitoring data; the first analysis module 203 is used to determine a first analysis result corresponding to the target object according to the first association relationship and the second association relationship; the second analysis module 204 is used to determine a first data change corresponding to the target object according to the first monitoring data and the second monitoring data, and determine a second analysis result corresponding to the target object according to the first data change and a data threshold; the target analysis module 205 is used to fuse the first analysis result and the second analysis result to determine the target analysis result corresponding to the target object.

[0087] In some embodiments, the first monitoring data includes at least first sensor data corresponding to the first Lora sensor and second sensor data corresponding to the second Lora sensor. In the process of obtaining a first association relationship between any two Lora sensors among the plurality of Lora sensors according to the first monitoring data, the association analysis module 202 executes:

[0088] Performing data clustering on the first sensor data and the second sensor data to obtain a first multidimensional data set;

[0089] Performing data association analysis according to the first multidimensional data set to obtain an association matrix between the first Lora sensor and the second Lora sensor;

[0090] A first association relationship between the first Lora sensor and the second Lora sensor is determined according to the association matrix.

[0091] In some implementations, the association analysis module 202, during the process of performing data association analysis according to the first multidimensional data set to obtain an association matrix between the first Lora sensor and the second Lora sensor, performs:

[0092] Obtaining first data corresponding to the first Lora sensor and second data corresponding to the second Lora sensor from the first multidimensional data set;

[0093] Calculating the data distance between the first data and the second data at the same time, and establishing an adjacent matrix according to the data distance;

[0094] Combining the first data and the second data arbitrarily to obtain combined data, and obtaining a first probability corresponding to the combined data;

[0095] Obtaining a second probability corresponding to the first data in the combined data and a third probability corresponding to the second data in the combined data;

[0096] Determine the association matrix between the first Lora sensor and the second Lora sensor according to the adjacent matrix, the first probability, the second probability and the third probability;

[0097] The correlation matrix is ​​obtained according to the following formula:

[0098] ;

[0099] represents the matrix value corresponding to the incidence matrix in row i and column j, The first probability of the combined data obtained by combining the i-th data in the first data and the j-th data in the second data; represents the second probability corresponding to the i-th data in the first data; represents the third probability corresponding to the j-th data in the second data; represents the matrix value corresponding to the adjacent matrix in the i-th row and j-th column; Represents weight information between the i-th data in the first data and the j-th data in the second data.

[0100] In some implementations, during the process of determining the first analysis result corresponding to the target object according to the first association relationship and the second association relationship, the first analysis module 203 executes:

[0101] Determine a mapping table, obtain a first value corresponding to the first association relationship according to the mapping table, and obtain a second value corresponding to the second association relationship according to the mapping table;

[0102] Determine a second data change between the first association relationship and the second association relationship according to the first value and the second value;

[0103] The first analysis result corresponding to the target object is determined according to the second data change.

[0104] In some implementations, the first monitoring data includes third sensing data corresponding to a third Lora sensor, and the second monitoring data includes fourth sensing data corresponding to the third Lora sensor. In the process of determining the first data change corresponding to the target object according to the first monitoring data and the second monitoring data, the second analysis module 204 executes:

[0105] Splicing the third sensor data and the fourth sensor data to obtain spliced ​​sensor data;

[0106] Determine a sliding window, and obtain window sensor data corresponding to the spliced ​​sensor data according to the sliding window;

[0107] Calculating a first average value and a first variance corresponding to the window sensing data;

[0108] A window characterization value corresponding to the target object is determined according to the first mean value and the first variance, and the first data change is determined according to the window characterization value.

[0109] In some implementations, during the process of determining the window representation value corresponding to the target object according to the first mean value and the first variance, the second analysis module 204 performs:

[0110] Obtain a second mean value and a second variance corresponding to the previous sliding window;

[0111] Determine a sliding factor corresponding to the sliding window, and determine a target average value by fusing the first average value and the second average value according to the sliding factor;

[0112] Determine a target variance by fusing the first variance and the second variance according to the sliding factor;

[0113] The target mean value and the target variance are fused using an adjustment factor to determine the window representation value corresponding to the target object.

[0114] In some implementations, the target analysis module 205, during the process of fusing the first analysis result and the second analysis result to determine the target analysis result corresponding to the target object, performs:

[0115] Obtaining a first analysis probability corresponding to the first analysis result and a second analysis probability corresponding to the second analysis result;

[0116] fusing the first analysis probability and the second analysis probability to obtain a target analysis probability;

[0117] The target analysis result corresponding to the target object is determined according to the target analysis probability.

[0118] In some implementations, the indoor environment data analysis apparatus 200 may be applied to a terminal device.

[0119] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the indoor environment data analysis device 200 described above can refer to the corresponding process in the aforementioned indoor environment data analysis method embodiment, and will not be repeated here.

[0120] See also Figure 3 , Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention.

[0121] like Figure 3 As shown, the terminal device 300 includes a processor 301 and a memory 302 , and the processor 301 and the memory 302 are connected via a bus 303 , such as an I2C (Inter-integrated Circuit) bus.

[0122] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0123] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0124] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the embodiment of the present invention is applied. The specific server may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] The processor is used to run the computer program stored in the memory, and implement any one of the indoor environment data analysis methods provided by the embodiments of the present invention when executing the computer program.

[0126] In one embodiment, the processor is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0127] Obtaining first monitoring data corresponding to a first moment and second monitoring data corresponding to a second moment of a target object under monitoring by multiple Lora sensors;

[0128] Obtaining a first association relationship between any two Lora sensors among the plurality of Lora sensors according to the first monitoring data, and obtaining a second association relationship between any two Lora sensors among the plurality of Lora sensors according to the second monitoring data;

[0129] Determine a first analysis result corresponding to the target object according to the first association relationship and the second association relationship;

[0130] Determine a first data change corresponding to the target object according to the first monitoring data and the second monitoring data, and determine a second analysis result corresponding to the target object according to the first data change and a data threshold;

[0131] The first analysis result and the second analysis result are integrated to determine a target analysis result corresponding to the target object.

[0132] In some embodiments, the first monitoring data includes at least first sensor data corresponding to the first Lora sensor and second sensor data corresponding to the second Lora sensor. In the process of obtaining a first association relationship between any two Lora sensors among the plurality of Lora sensors according to the first monitoring data, the processor 301 executes:

[0133] Performing data clustering on the first sensor data and the second sensor data to obtain a first multidimensional data set;

[0134] Performing data association analysis according to the first multidimensional data set to obtain an association matrix between the first Lora sensor and the second Lora sensor;

[0135] A first association relationship between the first Lora sensor and the second Lora sensor is determined according to the association matrix.

[0136] In some implementations, the processor 301, during the process of performing data association analysis according to the first multidimensional data set to obtain an association matrix between the first Lora sensor and the second Lora sensor, executes:

[0137] Obtaining first data corresponding to the first Lora sensor and second data corresponding to the second Lora sensor from the first multidimensional data set;

[0138] Calculating the data distance between the first data and the second data at the same time, and establishing an adjacent matrix according to the data distance;

[0139] Combining the first data and the second data arbitrarily to obtain combined data, and obtaining a first probability corresponding to the combined data;

[0140] Obtaining a second probability corresponding to the first data in the combined data and a third probability corresponding to the second data in the combined data;

[0141] Determine the association matrix between the first Lora sensor and the second Lora sensor according to the adjacent matrix, the first probability, the second probability and the third probability;

[0142] The correlation matrix is ​​obtained according to the following formula:

[0143] ;

[0144] represents the matrix value corresponding to the incidence matrix in row i and column j, The first probability of the combined data obtained by combining the i-th data in the first data and the j-th data in the second data; represents the second probability corresponding to the i-th data in the first data; represents the third probability corresponding to the j-th data in the second data; represents the matrix value corresponding to the adjacent matrix in the i-th row and j-th column; Represents weight information between the i-th data in the first data and the j-th data in the second data.

[0145] In some implementations, during the process of determining the first analysis result corresponding to the target object according to the first association relationship and the second association relationship, the processor 301 executes:

[0146] Determine a mapping table, obtain a first value corresponding to the first association relationship according to the mapping table, and obtain a second value corresponding to the second association relationship according to the mapping table;

[0147] Determine a second data change between the first association relationship and the second association relationship according to the first value and the second value;

[0148] The first analysis result corresponding to the target object is determined according to the second data change.

[0149] In some embodiments, the first monitoring data includes third sensing data corresponding to a third Lora sensor, and the second monitoring data includes fourth sensing data corresponding to the third Lora sensor. In the process of determining a first data change corresponding to the target object according to the first monitoring data and the second monitoring data, the processor 301 executes:

[0150] Splicing the third sensor data and the fourth sensor data to obtain spliced ​​sensor data;

[0151] Determine a sliding window, and obtain window sensor data corresponding to the spliced ​​sensor data according to the sliding window;

[0152] Calculating a first average value and a first variance corresponding to the window sensing data;

[0153] A window characterization value corresponding to the target object is determined according to the first mean value and the first variance, and the first data change is determined according to the window characterization value.

[0154] In some implementations, during the process of determining the window representation value corresponding to the target object according to the first mean value and the first variance, the processor 301 executes:

[0155] Obtain a second mean value and a second variance corresponding to the previous sliding window;

[0156] Determine a sliding factor corresponding to the sliding window, and determine a target average value by fusing the first average value and the second average value according to the sliding factor;

[0157] Determine a target variance by fusing the first variance and the second variance according to the sliding factor;

[0158] The target mean value and the target variance are fused using an adjustment factor to determine the window representation value corresponding to the target object.

[0159] In some implementations, during the process of fusing the first analysis result and the second analysis result to determine the target analysis result corresponding to the target object, the processor 301 executes:

[0160] Obtaining a first analysis probability corresponding to the first analysis result and a second analysis probability corresponding to the second analysis result;

[0161] fusing the first analysis probability and the second analysis probability to obtain a target analysis probability;

[0162] The target analysis result corresponding to the target object is determined according to the target analysis probability.

[0163] It should be noted that technicians in the relevant field can clearly understand that for the convenience and brevity of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned indoor environment data analysis method embodiment, and will not be repeated here.

[0164] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any indoor environment data analysis method provided in the description of the embodiment of the present invention.

[0165] The storage medium may be an internal storage unit of the terminal device in the aforementioned embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device.

[0166] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0167] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0168] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for analyzing indoor environment data, characterized in that: The method comprises: Obtaining first monitoring data corresponding to a first moment and second monitoring data corresponding to a second moment of a target object under monitoring by multiple Lora sensors; Obtaining a first association relationship between any two Lora sensors among the plurality of Lora sensors according to the first monitoring data, and obtaining a second association relationship between any two Lora sensors among the plurality of Lora sensors according to the second monitoring data; Determine a first analysis result corresponding to the target object according to the first association relationship and the second association relationship; Determine a first data change corresponding to the target object according to the first monitoring data and the second monitoring data, and determine a second analysis result corresponding to the target object according to the first data change and a data threshold; The first analysis result and the second analysis result are integrated to determine a target analysis result corresponding to the target object.

2. The method according to claim 1, characterized in that The first monitoring data at least includes first sensor data corresponding to the first Lora sensor and second sensor data corresponding to the second Lora sensor, and obtaining a first association relationship between any two Lora sensors among the plurality of Lora sensors according to the first monitoring data includes: Performing data clustering on the first sensor data and the second sensor data to obtain a first multidimensional data set; Performing data association analysis according to the first multidimensional data set to obtain an association matrix between the first Lora sensor and the second Lora sensor; A first association relationship between the first Lora sensor and the second Lora sensor is determined according to the association matrix.

3. The method according to claim 2, characterized in that The performing data association analysis according to the first multidimensional data set to obtain an association matrix between the first Lora sensor and the second Lora sensor includes: Obtaining first data corresponding to the first Lora sensor and second data corresponding to the second Lora sensor from the first multidimensional data set; Calculating the data distance between the first data and the second data at the same time, and establishing an adjacent matrix according to the data distance; Combining the first data and the second data arbitrarily to obtain combined data, and obtaining a first probability corresponding to the combined data; Obtaining a second probability corresponding to the first data in the combined data and a third probability corresponding to the second data in the combined data; Determine the association matrix between the first Lora sensor and the second Lora sensor according to the adjacent matrix, the first probability, the second probability and the third probability; The correlation matrix is ​​obtained according to the following formula: ; represents the matrix value corresponding to the incidence matrix in row i and column j, The first probability of the combined data obtained by combining the i-th data in the first data and the j-th data in the second data; represents the second probability corresponding to the i-th data in the first data; represents the third probability corresponding to the j-th data in the second data; represents the matrix value corresponding to the adjacent matrix in the i-th row and j-th column; Represents weight information between the i-th data in the first data and the j-th data in the second data.

4. The method according to claim 1, characterized in that: The determining a first analysis result corresponding to the target object according to the first association relationship and the second association relationship includes: Determine a mapping table, obtain a first value corresponding to the first association relationship according to the mapping table, and obtain a second value corresponding to the second association relationship according to the mapping table; Determine a second data change between the first association relationship and the second association relationship according to the first value and the second value; The first analysis result corresponding to the target object is determined according to the second data change.

5. The method according to claim 1, characterized in that The first monitoring data includes third sensing data corresponding to a third Lora sensor, the second monitoring data includes fourth sensing data corresponding to the third Lora sensor, and determining a first data change corresponding to the target object according to the first monitoring data and the second monitoring data includes: Splicing the third sensor data and the fourth sensor data to obtain spliced ​​sensor data; Determine a sliding window, and obtain window sensor data corresponding to the spliced ​​sensor data according to the sliding window; Calculating a first average value and a first variance corresponding to the window sensing data; A window characterization value corresponding to the target object is determined according to the first mean value and the first variance, and the first data change is determined according to the window characterization value.

6. The method according to claim 5, characterized in that The determining the window representation value corresponding to the target object according to the first mean value and the first variance includes: Obtain a second mean value and a second variance corresponding to the previous sliding window; Determine a sliding factor corresponding to the sliding window, and determine a target average value by fusing the first average value and the second average value according to the sliding factor; Determine a target variance by fusing the first variance and the second variance according to the sliding factor; The target mean value and the target variance are fused using an adjustment factor to determine the window representation value corresponding to the target object.

7. The method according to claim 1, characterized in that The fusing the first analysis result and the second analysis result to determine the target analysis result corresponding to the target object includes: Obtaining a first analysis probability corresponding to the first analysis result and a second analysis probability corresponding to the second analysis result; fusing the first analysis probability and the second analysis probability to obtain a target analysis probability; The target analysis result corresponding to the target object is determined according to the target analysis probability.

8. An indoor environment data analysis device, characterized in that: include: A data acquisition module, used to obtain first monitoring data corresponding to a first moment and second monitoring data corresponding to a second moment of a target object under monitoring by multiple Lora sensors; an association analysis module, configured to obtain a first association relationship between any two Lora sensors among the plurality of Lora sensors according to the first monitoring data, and to obtain a second association relationship between any two Lora sensors among the plurality of Lora sensors according to the second monitoring data; A first analysis module, configured to determine a first analysis result corresponding to the target object according to the first association relationship and the second association relationship; A second analysis module, configured to determine a first data change corresponding to the target object according to the first monitoring data and the second monitoring data, and to determine a second analysis result corresponding to the target object according to the first data change and a data threshold; A target analysis module is used to fuse the first analysis result and the second analysis result to determine a target analysis result corresponding to the target object.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the indoor environment data analysis method according to any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the indoor environment data analysis method according to any one of claims 1 to 7.

Images