Indoor monitoring data safety early warning method based on deep learning and related device

Abstract

The embodiment of the invention provides an indoor monitoring data safety early warning method based on deep learning and a related device, and the method comprises the steps: obtaining first monitoring data of a first LoRa sensor and second monitoring data of a second LoRa sensor, and determining first fusion data; determining a first target weight and a second target weight according to the first monitoring data and the second monitoring data in combination with the first fusion data; acquiring third monitoring data of the first LoRa sensor and fourth monitoring data of the second LoRa sensor; performing feature extraction on the third monitoring data to obtain first feature information, and performing feature extraction on the fourth monitoring data to obtain second feature information; performing feature fusion according to the first target weight, the first feature information, the second target weight and the second feature information to obtain second fusion data; according to the second fusion data, using a deep learning model to perform anomaly identification to obtain an anomaly type; and determining a safety early warning result according to the abnormal type, and executing a corresponding early warning operation according to the safety early warning result.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a deep learning-based indoor monitoring data security early warning method and related devices. Background Art

[0002] With the widespread application of the Internet of Things (IoT) in indoor monitoring and other fields, LoRa communication technology has become a key technology due to its low power consumption and long-distance transmission. However, the security of the LoRa communication system faces many threats, such as interference, deception, and replay attacks, which seriously affect the security and reliability of the indoor monitoring system. Traditional security protection methods have certain limitations for the security protection of the LoRa system. In the existing technology, the indoor monitoring system based on LoRa communication mainly relies on traditional encryption and authentication methods, which cannot effectively deal with complex security threats and attacks. There is an urgent need for a fast and accurate indoor monitoring data security early warning method. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide a deep learning-based indoor monitoring data security early warning method and related devices, aiming to solve the problem in the related technology that the indoor monitoring system based on LoRa communication mainly relies on traditional encryption and authentication methods and cannot effectively deal with complex security threats and attacks.

[0004] In a first aspect, an embodiment of the present invention provides a deep learning-based indoor monitoring data security early warning method, comprising:

[0005] Obtain first monitoring data corresponding to a first LoRa sensor of a target object at a historical moment and second monitoring data corresponding to a second LoRa sensor of the target object at the historical moment, and determine first fusion data corresponding to the first LoRa sensor and the second LoRa sensor at the historical moment;

[0006] Determine a first target weight corresponding to the first LoRa sensor and a second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data in combination with the first fusion data;

[0007] Obtain third monitoring data corresponding to the first LoRa sensor of the target object at the current moment and fourth monitoring data corresponding to the second LoRa sensor of the target object at the current moment;

[0008] Performing feature extraction on the third monitoring data to obtain first feature information and performing feature extraction on the fourth monitoring data to obtain second feature information;

[0009] Perform feature fusion according to the first target weight, the first feature information, the second target weight and the second feature information to obtain second fused data;

[0010] Performing anomaly identification using a deep learning model according to the second fusion data to obtain anomaly types;

[0011] The security warning result corresponding to the target object is determined according to the abnormality type, and a corresponding warning operation is performed according to the security warning result.

[0012] In a second aspect, an embodiment of the present invention provides an indoor monitoring data security early warning device based on deep learning, comprising:

[0013] A data processing module, used to obtain first monitoring data corresponding to a first LoRa sensor of a target object at a historical moment and second monitoring data corresponding to a second LoRa sensor of the target object at the historical moment, and determine first fusion data corresponding to the first LoRa sensor and the second LoRa sensor at the historical moment;

[0014] A weight determination module, configured to determine a first target weight corresponding to the first LoRa sensor and a second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data in combination with the first fusion data;

[0015] A data acquisition module, used to obtain third monitoring data corresponding to the first LoRa sensor of the target object at the current moment and fourth monitoring data corresponding to the second LoRa sensor of the target object at the current moment;

[0016] A feature extraction module, used for performing feature extraction on the third monitoring data to obtain first feature information and performing feature extraction on the fourth monitoring data to obtain second feature information;

[0017] A data fusion module, used for performing feature fusion according to the first target weight, the first feature information, the second target weight and the second feature information to obtain second fused data;

[0018] an abnormality identification module, used to perform abnormality identification using a deep learning model according to the second fusion data to obtain an abnormality type;

[0019] The warning processing module is used to determine the security warning result corresponding to the target object according to the abnormality type, and perform a corresponding warning operation according to the security warning result.

[0020] In the 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 one of the indoor monitoring data security early warning methods based on deep learning provided in the specification of the present invention are implemented.

[0021] 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 deep learning-based indoor monitoring data security early warning method provided in the specification of the present invention.

[0022] The embodiment of the present invention provides a deep learning-based indoor monitoring data security early warning method and related devices, the method comprising: obtaining first monitoring data corresponding to a first LoRa sensor of a target object at a historical moment and second monitoring data corresponding to a second LoRa sensor of the target object at a historical moment, and determining first fusion data corresponding to the first LoRa sensor and the second LoRa sensor at a historical moment, and then determining a first target weight corresponding to the first LoRa sensor and a second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data combined with the first fusion data, so that the contribution weights of different LoRa sensors to the target object can be determined, and then the importance of different LoRa sensor data in security early warning can be quantified more accurately, and then the third monitoring data corresponding to the first LoRa sensor of the target object at the current moment is obtained. The method comprises the following steps: extracting the first characteristic information from the third monitoring data and the fourth monitoring data corresponding to the second LoRa sensor of the target object at the current moment; extracting the first characteristic information from the third monitoring data and extracting the second characteristic information from the fourth monitoring data, and then fusion-fusing the first characteristic information, the second characteristic information, the second characteristic weight and the second characteristic information to obtain the second fusion data, so that the key information corresponding to the target object can be extracted from the monitoring data, and then the abnormality type can be obtained by using the deep learning model according to the second fusion data; finally, the security warning result corresponding to the target object is determined according to the abnormality type, and the corresponding warning operation is performed according to the security warning result, so that unusual behavior patterns or security threats can be detected more quickly and accurately, so that early warning measures can be taken in time, so that potential security risks can be responded to quickly and the security of the indoor environment can be ensured. And the problem that the indoor monitoring system based on LoRa communication in the related art mainly relies on traditional encryption and authentication means and cannot effectively deal with complex security threats and attacks is solved. The present invention provides a LoRa communication data security early warning method integrating advanced deep learning technology, which can effectively protect indoor monitoring data from security threats through enhanced security detection functions. It is not only suitable for general environmental monitoring, but can also be extended to fields such as cultural relics protection and ecological protection. It has broad application prospects and significant social and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] 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.

[0024] Figure 1 A flowchart of a deep learning-based indoor monitoring data security early warning method provided by an embodiment of the present invention;

[0025] Figure 2 A schematic diagram of a process flow of an indoor monitoring data security early warning device based on deep learning provided by an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of the structure of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] 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.

[0028] 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.

[0029] 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.

[0030] The embodiment of the present invention provides a deep learning-based indoor monitoring data security early warning method and related devices. The deep learning-based indoor monitoring data security early warning 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.

[0031] 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.

[0032] Please refer to Figure 1 , Figure 1 A schematic flow chart of a deep learning-based indoor monitoring data security early warning method provided in an embodiment of the present invention.

[0033] like Figure 1 As shown, the indoor monitoring data security early warning method based on deep learning includes steps S101 to S107.

[0034] Step S101: obtain first monitoring data corresponding to a first LoRa sensor of a target object at a historical moment and second monitoring data corresponding to a second LoRa sensor of the target object at the historical moment, and determine first fusion data corresponding to the first LoRa sensor and the second LoRa sensor at the historical moment.

[0035] Exemplarily, the target object is an indoor environment that needs to be monitored, which may be a scene room corresponding to cultural relics protection, or an ecological environment corresponding to ecological protection, and so on.

[0036] Exemplarily, a plurality of LoRa sensors are used to monitor the target object, and the first LoRa sensor or the second LoRa sensor is any one of LoRa sensors such as a temperature sensor, a humidity sensor, and a light intensity sensor.

[0037] Exemplarily, the first monitoring data corresponding to the first LoRa sensor and the second monitoring data corresponding to the second LoRa sensor at the historical moment are obtained from the database. The corresponding security warning result at the historical moment is obtained from the database, and then the first fusion data corresponding to the historical moment is inferred based on the security warning result. The first fusion data is used to characterize that the security warning result corresponding to the target object can be accurately obtained at the historical moment.

[0038] Step S102: Determine a first target weight corresponding to the first LoRa sensor and a second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data in combination with the first fusion data.

[0039] Exemplarily, by training a machine learning model (such as a regression model or a neural network), the first monitoring data and the second monitoring data are taken as input, and the first fusion data is taken as output to learn the mapping relationship of the LoRa sensor weights, thereby obtaining the first target weight corresponding to the first LoRa sensor and the second target weight corresponding to the second LoRa sensor, and then reflecting the importance or contribution of different LoRa sensors in monitoring the target object according to the first target weight and the second target weight.

[0040] In some embodiments, determining the first target weight corresponding to the first LoRa sensor and the second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data in combination with the first fusion data includes: determining a first initial weight corresponding to the first LoRa sensor and a second initial weight corresponding to the second LoRa sensor; fusing the first monitoring data and the second monitoring data according to the first initial weight and the second initial weight to obtain initial fusion data; obtaining a difference between the initial fusion data and the first fusion data, and when the difference is less than a preset value, determining a first accuracy corresponding to the first LoRa sensor according to the first monitoring data, and determining a second accuracy corresponding to the second LoRa sensor according to the second monitoring data; determining a third accuracy corresponding to the target object according to the first initial weight, the second initial weight, the first accuracy, and the second accuracy; when the third accuracy meets a preset condition, determining the first target weight and the second target weight according to the first accuracy and the second accuracy.

[0041] Exemplarily, according to prior knowledge, a first initial weight corresponding to the first LoRa sensor and a second initial weight corresponding to the second LoRa sensor are set. The first initial weight and the second initial weight can be evenly distributed, based on experience, or determined by preliminary data analysis.

[0042] Exemplarily, the first monitoring data of the first LoRa sensor and the second monitoring data of the second LoRa sensor are fused by weighted averaging in combination with the first initial weight and the second initial weight to obtain initial fused data, and then the difference between the initial fused data and the first fused data is compared.

[0043] Exemplarily, a preset value is determined. When the difference is less than the preset value, it is considered that the initial fusion data is sufficiently close to the first fusion data, and then the first accuracy corresponding to the first LoRa sensor is calculated based on the first monitoring data of the first LoRa sensor, and the second accuracy corresponding to the second LoRa sensor is determined based on the second monitoring data of the second LoRa sensor.

[0044] For example, a first variance corresponding to the first monitoring data and a second variance corresponding to the second monitoring data are calculated, and then the first variance is weighted and summed to obtain a first sum, and the second variance is weighted and summed to obtain a second sum, and then the first sum is determined as the first accuracy and the second sum is determined as the second accuracy.

[0045] Exemplarily, a first product is obtained by multiplying the first initial weight and the first accuracy, and a second product is obtained by multiplying the second initial weight and the second accuracy, and then the first product and the second product are added to determine a third accuracy corresponding to the target object.

[0046] Exemplarily, the third accuracy calculated is evaluated to see whether it meets a preset condition. For example, a threshold value of accuracy may be set to determine whether the required level of accuracy is reached, and then when the third accuracy is less than the preset threshold value, the first accuracy is solved by inverse to obtain a first inverse, and the second accuracy is solved by inverse to obtain a second inverse, and then the first inverse and the second inverse are summed to obtain an inverse sum value, and then the first inverse and the inverse sum value are multiplied to obtain a third product, and then the inverse value corresponding to the third product is determined as the first target weight, and the second inverse and the inverse sum value are multiplied to obtain a fourth product, and then the inverse value corresponding to the fourth product is determined as the second target weight.

[0047] Specifically, by calculating the difference between the initial fusion data and the first fusion data, and adjusting the accuracy of the LoRa sensor according to the difference, the possible errors of the LoRa sensor during the monitoring process can be dynamically corrected to improve the stability and reliability of the monitoring method. In this way, the accurate weights corresponding to the first LoRa sensor and the second LoRa sensor during data fusion can be effectively obtained, thereby providing good support for subsequent safety warnings.

[0048] In some embodiments, the method further includes: when the difference is greater than or equal to the preset value, or the third accuracy does not meet the preset condition, adjusting the first initial weight corresponding to the first LoRa sensor to obtain the third initial weight and adjusting the second initial weight corresponding to the second LoRa sensor to obtain the fourth initial weight, until the adjusted difference is less than the preset value, or the adjusted third accuracy meets the preset condition.

[0049] Exemplarily, the difference between the initial fusion data and the first fusion data is compared, and whether the preset value is met is determined based on the difference. If the difference is greater than or equal to the preset value, or the third accuracy does not meet the preset condition, the weight adjustment stage is entered, the first initial weight is adjusted to obtain the third initial weight, and the second initial weight is adjusted to obtain the fourth initial weight, so that the above steps are repeated until the preset value and preset condition are reached.

[0050] Specifically, by achieving the goal of dynamically adjusting the initial weights of LoRa sensors, and thus ensuring that the fused data and accuracy meet the target requirements, the performance and stability of the monitoring method are optimized, thereby providing good support for subsequent safety warnings.

[0051] Step S103: Obtain third monitoring data corresponding to the first LoRa sensor of the target object at the current moment and fourth monitoring data corresponding to the second LoRa sensor of the target object at the current moment.

[0052] Exemplarily, the third monitoring data is acquired by monitoring the target object using the first LoRa sensor at the current moment. Similarly, the fourth monitoring data is acquired by monitoring the target object using the second LoRa sensor at the current moment.

[0053] Step S104: extracting features from the third monitoring data to obtain first feature information and extracting features from the fourth monitoring data to obtain second feature information.

[0054] Exemplarily, a first maximum value and a first minimum value corresponding to the third monitoring data are obtained, and then the third monitoring data is normalized according to the first maximum value and the first minimum value to obtain first processed data. A second maximum value and a second minimum value corresponding to the fourth monitoring data are obtained, and then the fourth monitoring data is normalized according to the second maximum value and the second minimum value to obtain second processed data.

[0055] For example, the first processed data is obtained according to the following formula:

[0056] ;

[0057] represents the first processed data, Indicates the third monitoring data, represents the first minimum value, Indicates the first maximum value.

[0058] Similarly, the second processed data is obtained according to the following formula:

[0059] ;

[0060] represents the second processed data, represents the fourth monitoring data, represents the second minimum value, Indicates the second largest value.

[0061] Exemplarily, after obtaining the first processed data and the second processed data, the first processed data and the second processed data are decomposed into various frequency components according to discrete wavelet transform (DWT), thereby isolating and removing noise to obtain first denoised data corresponding to the first processed data and second denoised data corresponding to the second processed data.

[0062] Exemplarily, a comprehensive feature set of time domain and frequency domain features is extracted from the first denoised data to obtain the first feature information, and a comprehensive feature set of time domain and frequency domain features is extracted from the second denoised data to obtain the second feature information.

[0063] In some embodiments, the feature extraction of the third monitoring data to obtain the first feature information and the feature extraction of the fourth monitoring data to obtain the second feature information include: filtering the third monitoring data to obtain the first filtered data and filtering the fourth monitoring data to obtain the second filtered data; determining a first feature sequence corresponding to the first filtered data and a second feature sequence corresponding to the second filtered data; setting a first abnormal frequency corresponding to the first LoRa sensor and a second abnormal frequency corresponding to the second LoRa sensor; obtaining a first numerical value corresponding to the first abnormal frequency according to the first feature sequence and obtaining a second numerical value corresponding to the second abnormal frequency according to the second feature sequence; determining the first feature information according to the first numerical value and the first feature sequence, and determining the second feature information according to the second numerical value and the second feature sequence.

[0064] Exemplarily, an appropriate filtering algorithm is selected according to the nature of the monitoring data, such as low-pass filtering, high-pass filtering or other digital filtering methods, to eliminate noise or unnecessary signal components in the data. Thus, the selected filtering algorithm is applied to process the third monitoring data obtained by the first LoRa sensor to obtain the first filtered data. Similarly, the same filtering algorithm is applied to the fourth monitoring data obtained by the second LoRa sensor to obtain the second filtered data.

[0065] Exemplarily, a feature sequence is extracted from the filtered data, which may involve a specific feature extraction method, such as time series analysis, spectrum analysis or other signal processing techniques, so as to obtain a first feature sequence and a second feature sequence by performing feature extraction from the first filtered data and the second filtered data, respectively.

[0066] Exemplarily, a first abnormal frequency corresponding to the first LoRa sensor and a second abnormal frequency corresponding to the second LoRa sensor are obtained according to historical data. The first abnormal frequency and the second abnormal frequency are used to represent the frequency of unusual events or specific abnormal patterns in different monitoring data.

[0067] Exemplarily, a first value corresponding to a first characteristic sequence at a first abnormal frequency is obtained, and a second value corresponding to a second characteristic sequence at a second abnormal frequency is obtained. The first value and the second value are used to reflect the data features corresponding to the current moment at the abnormal frequency.

[0068] Exemplarily, a first ratio of the first values ​​in the first feature sequence is obtained, and the first ratio is determined as the first feature information, and a second ratio of the second values ​​in the second feature sequence is obtained, and the second ratio is determined as the second feature information.

[0069] Specifically, filtering can effectively remove noise and unnecessary interference signals from LoRa sensor data, thereby improving the quality and reliability of the data. By extracting feature sequences from filtered data, key feature information of the target object can be captured more accurately, which is helpful for subsequent data analysis and decision making. Furthermore, by setting the first abnormal frequency and the second abnormal frequency of the first LoRa sensor and the second LoRa sensor, and determining the values ​​according to the feature sequence and the abnormal frequency, real-time detection and early warning of abnormal events or important data features can be achieved, thereby obtaining the first feature information and the second feature information, and then effectively obtaining the corresponding characterization features under different LoRa sensors, thereby providing good support for subsequent safety warnings.

[0070] In some embodiments, obtaining the first numerical value corresponding to the first abnormal frequency according to the first characteristic sequence and obtaining the second numerical value corresponding to the second abnormal frequency according to the second characteristic sequence includes: determining a first quantity corresponding to the first abnormal frequency and determining a second quantity corresponding to the second abnormal frequency; obtaining a first integer sequence corresponding to the first quantity and obtaining a second integer sequence corresponding to the second quantity; multiplying each first integer in the first integer sequence by the first abnormal frequency to obtain a first frequency, and multiplying each second integer in the second integer sequence by the second abnormal frequency to obtain a second frequency; obtaining the first numerical value corresponding to the first frequency according to the first characteristic sequence and obtaining the second numerical value corresponding to the second frequency according to the second characteristic sequence.

[0071] Exemplarily, a first number required to be collected at a first abnormal frequency and a second number required to be collected at a second abnormal frequency are determined, and then integers between 1 and the first number are determined as a first integer sequence and integers between 1 and the second number are determined as a second integer sequence.

[0072] Exemplarily, each integer in the first integer sequence is multiplied by a first abnormal frequency to obtain a first frequency, and each integer in the second integer sequence is multiplied by a second abnormal frequency to obtain a second frequency.

[0073] Exemplarily, a first numerical value corresponding to a first frequency is obtained using an existing first characteristic sequence, and a second numerical value corresponding to a second frequency is obtained using an existing second characteristic sequence.

[0074] Specifically, by accurately determining the specific values ​​corresponding to the first abnormal frequency and the second abnormal frequency, abnormal events or important data features in the monitoring data can be accurately captured, providing an important basis for subsequent analysis and decision-making. Therefore, obtaining the integer sequence corresponding to the first quantity and the second quantity is helpful for further calculation and processing, and then by multiplying each integer in the integer sequence by the abnormal frequency, the first frequency and the second frequency can be calculated. Therefore, based on the first characteristic sequence and the second characteristic sequence, the specific values ​​corresponding to the first frequency and the second frequency are determined. These values ​​may be used to evaluate data security, thereby providing detailed data support for subsequent decisions.

[0075] In some embodiments, determining the first feature information according to the first numerical value and the first feature sequence, and determining the second feature information according to the second numerical value and the second feature sequence, includes: summing the first numerical value to obtain a first sum value, and summing the second numerical value to obtain a second sum value; summing the first feature sequence to obtain a third sum value, and summing the second feature sequence to obtain a fourth sum value; determining the first feature information according to the first sum value, the third sum value, and the first quantity; determining the second feature information according to the second sum value, the fourth sum value, and the second quantity; wherein the first feature information and the second feature information are obtained according to the following formula:

[0076] ;

[0077] ;

[0078] in, represents the first characteristic information, represents the second characteristic information, X1 represents the first quantity, X2 represents the second quantity, f1 represents the first abnormal frequency, f2 represents the second abnormal frequency, i* 1 represents the first frequency, i* 2 represents the second frequency, represents the first value, represents the second value, represents the value corresponding to the jth bit in the first feature sequence, represents the value corresponding to the jth bit in the second feature sequence, represents the number corresponding to the first feature sequence, Indicates the number corresponding to the second feature sequence.

[0079] Exemplarily, all first values ​​are summed to obtain a first sum value, and all second values ​​are summed to obtain a second sum value.

[0080] Exemplarily, all features in the first feature sequence are summed to obtain a third sum value, and all features in the second feature sequence are summed to obtain a fourth sum value.

[0081] Exemplarily, the first feature information is determined using the following formula according to the first sum, the third sum, and the first quantity:

[0082] ;

[0083] in, represents the first characteristic information, X1 represents the first quantity, f1 represents the first abnormal frequency, i* 1 indicates the first frequency, represents the first value, represents the value corresponding to the jth bit in the first feature sequence, Indicates the number corresponding to the first feature sequence.

[0084] Exemplarily, the prominence of the characteristic value corresponding to the first abnormal frequency in the first characteristic sequence is measured according to the above formula, so as to obtain the first characteristic information corresponding to the first LoRa sensor.

[0085] Exemplarily, the second feature information is determined using the following formula according to the second sum, the fourth sum, and the second quantity:

[0086] ;

[0087] in, represents the second characteristic information, X2 represents the second quantity, f2 represents the second abnormal frequency, i* 2 represents the second frequency, represents the second value, represents the value corresponding to the jth bit in the second feature sequence, Indicates the number corresponding to the second feature sequence.

[0088] Exemplarily, the prominence of the characteristic value corresponding to the second abnormal frequency in the second characteristic sequence is measured according to the above formula, so as to obtain the second characteristic information corresponding to the second LoRa sensor.

[0089] Specifically, the first characteristic information is obtained by measuring the prominence of the characteristic value corresponding to the first abnormal frequency in the first characteristic sequence, and the second characteristic information is obtained by measuring the prominence of the characteristic value corresponding to the second abnormal frequency in the second characteristic sequence, to provide good support for subsequent safety warnings.

[0090] Step S105: performing feature fusion according to the first target weight, the first feature information, the second target weight and the second feature information to obtain second fused data.

[0091] Exemplarily, the first target weight and the first feature information, and the second target weight and the second feature information are combined using weighted averaging to obtain the second fused data.

[0092] Step S106: Use a deep learning model to perform anomaly identification according to the second fusion data to obtain anomaly types.

[0093] For example, according to the specific anomaly identification requirements, select a suitable deep learning model, such as a convolutional neural network (CNN), a recurrent neural network (RNN), or a Transformer model. If the existing model is not suitable, consider adjusting or retraining the model to meet the specific data and task requirements, and then use the trained deep learning model to identify anomalies on the second fusion data. The result of the model output can be the probability of anomaly or a direct anomaly type classification result.

[0094] In some embodiments, the deep learning model can use the LoRaSec deep learning framework, combined with CNN, RNN and attention mechanism to identify anomalies in the second fused data to obtain anomaly types. Exemplarily, the deep learning model includes a feature extraction layer, a feature attention layer and an autoencoder network layer, and the use of the deep learning model to identify anomalies based on the second fused data to obtain anomaly types includes: using the feature extraction layer to extract features from the third monitoring data to obtain third feature information and using the feature extraction layer to extract features from the fourth monitoring data to obtain fourth feature information; using the feature attention layer to perform feature fusion on the third feature information, the fourth feature information and the second fused data to obtain target fused data; using the autoencoder network layer to identify anomalies on the target fused data to obtain the anomaly type (for example, the anomaly type includes interference, deception or replay attack).

[0095] Exemplarily, for the third monitoring data and the fourth monitoring data, a feature extraction layer is designed and implemented. This may include using a convolutional neural network (CNN), a recurrent neural network (RNN), or other feature extraction models suitable for the task to obtain third feature information corresponding to the third monitoring data and fourth feature information corresponding to the fourth monitoring data.

[0096] Exemplarily, a layer that can dynamically focus on different input features is designed through an attention mechanism or other weighted strategies, and the third feature information, the fourth feature information and the second fusion data are combined to generate target fusion data to ensure that the target fusion data can make full use of the input information and the corresponding prominence degree under abnormal frequency.

[0097] Exemplarily, an autoencoder network layer is implemented for anomaly identification of target fusion data. The autoencoder network can learn a stable representation of the data through unsupervised learning and identify anomaly types that do not conform to normal data.

[0098] Specifically, the third feature information and the fourth feature information are obtained by extracting features from the third monitoring data and the fourth monitoring data, and then the feature fusion is performed using the attention mechanism, and then the autoencoder network is used for anomaly identification and classification. Such a process can effectively process complex monitoring data, realize efficient anomaly detection and type identification, and thus improve the intelligence and responsiveness of the monitoring method.

[0099] Step S107: determining a security warning result corresponding to the target object according to the abnormality type, and performing a corresponding warning operation according to the security warning result.

[0100] For example, a mapping table or rule set from anomaly type to security warning results is established. These mappings can be defined in advance, such as mapping different types of anomalies to different levels of security warnings (such as low, medium, and high), or directly mapping to specific warning operations (such as sending an alarm, automatically stopping operations, etc.). Then, according to each security warning result, corresponding warning rules and operations are defined. These rules can include triggering alarms to notify relevant personnel, recording abnormal events, and performing automated emergency operations. Ensure that each warning result has clear response measures.

[0101] Exemplarily, the security warning result corresponding to the target object is determined from the mapping table according to the exception type, and then the corresponding warning operation is performed according to the security warning result, thereby effectively protecting the security of the target object and reducing potential risks and losses.

[0102] The embodiment of the present invention provides a deep learning-based indoor monitoring data security early warning method and related devices, the method comprising: obtaining first monitoring data corresponding to a first LoRa sensor of a target object at a historical moment and second monitoring data corresponding to a second LoRa sensor of the target object at a historical moment, and determining first fusion data corresponding to the first LoRa sensor and the second LoRa sensor at a historical moment, and then determining a first target weight corresponding to the first LoRa sensor and a second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data combined with the first fusion data, so that the contribution weights of different LoRa sensors to the target object can be determined, and then the importance of different LoRa sensor data in security early warning can be quantified more accurately, and then the third monitoring data corresponding to the first LoRa sensor of the target object at the current moment is obtained. The method comprises the following steps: extracting the first characteristic information from the third monitoring data and the fourth monitoring data corresponding to the second LoRa sensor of the target object at the current moment; extracting the first characteristic information from the third monitoring data and extracting the second characteristic information from the fourth monitoring data, and then fusion-fusing the first characteristic information, the second characteristic information, the second characteristic weight and the second characteristic information to obtain the second fusion data, so that the key information corresponding to the target object can be extracted from the monitoring data, and then the abnormality type can be obtained by using the deep learning model according to the second fusion data; finally, the security warning result corresponding to the target object is determined according to the abnormality type, and the corresponding warning operation is performed according to the security warning result, so that unusual behavior patterns or security threats can be detected more quickly and accurately, so that early warning measures can be taken in time, so that potential security risks can be responded to quickly and the security of the indoor environment can be ensured. And the problem that the indoor monitoring system based on LoRa communication in the related art mainly relies on traditional encryption and authentication means and cannot effectively deal with complex security threats and attacks is solved. The present invention provides a LoRa communication data security early warning method integrating advanced deep learning technology, which can effectively protect indoor monitoring data from security threats through enhanced security detection functions. It is not only suitable for general environmental monitoring, but can also be extended to fields such as cultural relics protection and ecological protection. It has broad application prospects and significant social and economic benefits.

[0103] See also Figure 2 , Figure 2An indoor monitoring data security early warning device 200 based on deep learning is provided in an embodiment of the present application. The indoor monitoring data security early warning device 200 based on deep learning includes a data processing module 201, a weight determination module 202, a data acquisition module 203, a feature extraction module 204, a data fusion module 205, an abnormality recognition module 206, and an early warning processing module 207, wherein the data processing module 201 is used to obtain the first monitoring data corresponding to the first LoRa sensor of the target object at a historical moment and the second monitoring data corresponding to the second LoRa sensor of the target object at the historical moment, and determine the first fused data corresponding to the first LoRa sensor and the second LoRa sensor at the historical moment; the weight determination module 202 is used to determine the first target weight corresponding to the first LoRa sensor and the second LoRa sensor according to the first monitoring data and the second monitoring data combined with the first fused data. Ra sensor; a data acquisition module 203, used to obtain the third monitoring data corresponding to the first LoRa sensor of the target object at the current moment and the fourth monitoring data corresponding to the second LoRa sensor of the target object at the current moment; a feature extraction module 204, used to extract features from the third monitoring data to obtain first feature information and to extract features from the fourth monitoring data to obtain second feature information; a data fusion module 205, used to perform feature fusion according to the first target weight, the first feature information, the second target weight and the second feature information to obtain second fused data; an anomaly identification module 206, used to perform anomaly identification using a deep learning model according to the second fused data to obtain anomaly types; an early warning processing module 207, used to determine the security early warning result corresponding to the target object according to the anomaly type, and perform corresponding early warning operations according to the security early warning result.

[0104] In some implementations, the weight determination module 202, in the process of determining the first target weight corresponding to the first LoRa sensor and the second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data in combination with the first fusion data, performs:

[0105] Determine a first initial weight corresponding to the first LoRa sensor and a second initial weight corresponding to the second LoRa sensor;

[0106] fusing the first monitoring data and the second monitoring data according to the first initial weight and the second initial weight to obtain initial fused data;

[0107] Obtaining a difference between the initial fusion data and the first fusion data, and when the difference is less than a preset value, determining a first accuracy corresponding to the first LoRa sensor according to the first monitoring data, and determining a second accuracy corresponding to the second LoRa sensor according to the second monitoring data;

[0108] Determining a third accuracy corresponding to the target object according to the first initial weight, the second initial weight, the first accuracy, and the second accuracy;

[0109] When the third accuracy satisfies a preset condition, the first target weight and the second target weight are determined according to the first accuracy and the second accuracy.

[0110] In some implementations, the weight determination module 202 further performs:

[0111] When the difference is greater than or equal to the preset value, or the third accuracy does not meet the preset condition, the first initial weight corresponding to the first LoRa sensor is adjusted to obtain the third initial weight and the second initial weight corresponding to the second LoRa sensor is adjusted to obtain the fourth initial weight, until the adjusted difference is less than the preset value, or the adjusted third accuracy meets the preset condition.

[0112] In some implementations, the feature extraction module 204 performs, during the process of extracting features from the third monitoring data to obtain the first feature information and extracting features from the fourth monitoring data to obtain the second feature information:

[0113] Performing filtering processing on the third monitoring data to obtain first filtered data and performing filtering processing on the fourth monitoring data to obtain second filtered data;

[0114] Determine a first characteristic sequence corresponding to the first filtered data and a second characteristic sequence corresponding to the second filtered data;

[0115] Set a first abnormal frequency corresponding to the first LoRa sensor and a second abnormal frequency corresponding to the second LoRa sensor;

[0116] Obtain a first value corresponding to the first abnormal frequency according to the first characteristic sequence and obtain a second value corresponding to the second abnormal frequency according to the second characteristic sequence;

[0117] The first feature information is determined according to the first value and the first feature sequence, and the second feature information is determined according to the second value and the second feature sequence.

[0118] In some implementations, the feature extraction module 204, in the process of obtaining the first value corresponding to the first abnormal frequency according to the first feature sequence and obtaining the second value corresponding to the second abnormal frequency according to the second feature sequence, performs:

[0119] determining a first quantity corresponding to the first abnormal frequency and determining a second quantity corresponding to the second abnormal frequency;

[0120] Obtaining a first integer sequence corresponding to the first number and obtaining a second integer sequence corresponding to the second number;

[0121] multiplying each first integer in the first integer sequence by the first abnormal frequency to obtain a first frequency, and multiplying each second integer in the second integer sequence by the second abnormal frequency to obtain a second frequency;

[0122] The first value corresponding to the first frequency is obtained according to the first characteristic sequence, and the second value corresponding to the second frequency is obtained according to the second characteristic sequence.

[0123] In some implementations, the feature extraction module 204, in the process of determining the first feature information according to the first value and the first feature sequence, and determining the second feature information according to the second value and the second feature sequence, performs:

[0124] Summing the first values ​​to obtain a first sum value, and summing the second values ​​to obtain a second sum value;

[0125] Summing the first feature sequence to obtain a third sum value, and summing the second feature sequence to obtain a fourth sum value;

[0126] determining the first feature information according to the first sum, the third sum, and the first quantity;

[0127] determining the second feature information according to the second sum value, the fourth sum value, and the second quantity;

[0128] The first characteristic information and the second characteristic information are obtained according to the following formula:

[0129] ;

[0130] ;

[0131] in, represents the first characteristic information, represents the second characteristic information, X1 represents the first quantity, X2 represents the second quantity, f1 represents the first abnormal frequency, f2 represents the second abnormal frequency, i* 1 represents the first frequency, i* 2 represents the second frequency, represents the first value, represents the second value, represents the value corresponding to the jth bit in the first feature sequence, represents the value corresponding to the jth bit in the second feature sequence, represents the number corresponding to the first feature sequence, Indicates the number corresponding to the second feature sequence.

[0132] In some implementations, the deep learning model includes a feature extraction layer, a feature attention layer, and an autoencoder network layer. In the process of performing anomaly identification using the deep learning model according to the second fusion data to obtain anomaly types, the anomaly identification module 206 executes:

[0133] Using the feature extraction layer to extract features from the third monitoring data to obtain third feature information and using the feature extraction layer to extract features from the fourth monitoring data to obtain fourth feature information;

[0134] Using the feature attention layer, the third feature information, the fourth feature information and the second fused data are feature-fused to obtain target fused data;

[0135] The autoencoder network layer is used to perform anomaly identification on the target fusion data to obtain the anomaly type.

[0136] In some embodiments, the indoor monitoring data security warning device 200 based on deep learning can be applied to terminal equipment.

[0137] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the indoor monitoring data security early warning device 200 based on deep learning described above can refer to the corresponding process in the aforementioned embodiment of the indoor monitoring data security early warning method based on deep learning, and will not be repeated here.

[0138] 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.

[0139] like Figure 3As 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] Among them, the processor is used to run the computer program stored in the memory, and implement any one of the indoor monitoring data security early warning methods based on deep learning provided by the embodiments of the present invention when executing the computer program.

[0144] 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:

[0145] Obtain first monitoring data corresponding to a first LoRa sensor of a target object at a historical moment and second monitoring data corresponding to a second LoRa sensor of the target object at the historical moment, and determine first fusion data corresponding to the first LoRa sensor and the second LoRa sensor at the historical moment;

[0146] Determine a first target weight corresponding to the first LoRa sensor and a second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data in combination with the first fusion data;

[0147] Obtain third monitoring data corresponding to the first LoRa sensor of the target object at the current moment and fourth monitoring data corresponding to the second LoRa sensor of the target object at the current moment;

[0148] Performing feature extraction on the third monitoring data to obtain first feature information and performing feature extraction on the fourth monitoring data to obtain second feature information;

[0149] Perform feature fusion according to the first target weight, the first feature information, the second target weight and the second feature information to obtain second fused data;

[0150] Performing anomaly identification using a deep learning model according to the second fusion data to obtain anomaly types;

[0151] The security warning result corresponding to the target object is determined according to the abnormality type, and a corresponding warning operation is performed according to the security warning result.

[0152] In some implementations, the processor 301, in the process of determining the first target weight corresponding to the first LoRa sensor and the second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data in combination with the first fusion data, executes:

[0153] Determine a first initial weight corresponding to the first LoRa sensor and a second initial weight corresponding to the second LoRa sensor;

[0154] fusing the first monitoring data and the second monitoring data according to the first initial weight and the second initial weight to obtain initial fused data;

[0155] Obtaining a difference between the initial fusion data and the first fusion data, and when the difference is less than a preset value, determining a first accuracy corresponding to the first LoRa sensor according to the first monitoring data, and determining a second accuracy corresponding to the second LoRa sensor according to the second monitoring data;

[0156] Determining a third accuracy corresponding to the target object according to the first initial weight, the second initial weight, the first accuracy, and the second accuracy;

[0157] When the third accuracy satisfies a preset condition, the first target weight and the second target weight are determined according to the first accuracy and the second accuracy.

[0158] In some implementations, the processor 301 further executes:

[0159] When the difference is greater than or equal to the preset value, or the third accuracy does not meet the preset condition, the first initial weight corresponding to the first LoRa sensor is adjusted to obtain the third initial weight and the second initial weight corresponding to the second LoRa sensor is adjusted to obtain the fourth initial weight, until the adjusted difference is less than the preset value, or the adjusted third accuracy meets the preset condition.

[0160] In some implementations, the processor 301, during the process of extracting features from the third monitoring data to obtain the first feature information and extracting features from the fourth monitoring data to obtain the second feature information, executes:

[0161] Performing filtering processing on the third monitoring data to obtain first filtered data and performing filtering processing on the fourth monitoring data to obtain second filtered data;

[0162] Determine a first characteristic sequence corresponding to the first filtered data and a second characteristic sequence corresponding to the second filtered data;

[0163] Set a first abnormal frequency corresponding to the first LoRa sensor and a second abnormal frequency corresponding to the second LoRa sensor;

[0164] Obtain a first value corresponding to the first abnormal frequency according to the first characteristic sequence and obtain a second value corresponding to the second abnormal frequency according to the second characteristic sequence;

[0165] The first feature information is determined according to the first value and the first feature sequence, and the second feature information is determined according to the second value and the second feature sequence.

[0166] In some implementations, the processor 301, during the process of obtaining the first value corresponding to the first abnormal frequency according to the first feature sequence and obtaining the second value corresponding to the second abnormal frequency according to the second feature sequence, performs:

[0167] determining a first quantity corresponding to the first abnormal frequency and determining a second quantity corresponding to the second abnormal frequency;

[0168] Obtaining a first integer sequence corresponding to the first number and obtaining a second integer sequence corresponding to the second number;

[0169] multiplying each first integer in the first integer sequence by the first abnormal frequency to obtain a first frequency, and multiplying each second integer in the second integer sequence by the second abnormal frequency to obtain a second frequency;

[0170] The first value corresponding to the first frequency is obtained according to the first characteristic sequence, and the second value corresponding to the second frequency is obtained according to the second characteristic sequence.

[0171] In some implementations, the processor 301, in the process of determining the first feature information according to the first value and the first feature sequence, and determining the second feature information according to the second value and the second feature sequence, executes:

[0172] Summing the first values ​​to obtain a first sum value, and summing the second values ​​to obtain a second sum value;

[0173] Summing the first feature sequence to obtain a third sum value, and summing the second feature sequence to obtain a fourth sum value;

[0174] determining the first feature information according to the first sum, the third sum, and the first quantity;

[0175] determining the second feature information according to the second sum value, the fourth sum value, and the second quantity;

[0176] The first characteristic information and the second characteristic information are obtained according to the following formula:

[0177] ;

[0178] ;

[0179] in, represents the first characteristic information, represents the second characteristic information, X1 represents the first quantity, X2 represents the second quantity, f1 represents the first abnormal frequency, f2 represents the second abnormal frequency, i* 1 represents the first frequency, i* 2 represents the second frequency, represents the first value, represents the second value, represents the value corresponding to the jth bit in the first feature sequence, represents the value corresponding to the jth bit in the second feature sequence, represents the number corresponding to the first feature sequence, Indicates the number corresponding to the second feature sequence.

[0180] In some implementations, the deep learning model includes a feature extraction layer, a feature attention layer, and an autoencoder network layer. In the process of performing anomaly identification using the deep learning model according to the second fusion data to obtain anomaly types, the processor 301 executes:

[0181] Using the feature extraction layer to extract features from the third monitoring data to obtain third feature information and using the feature extraction layer to extract features from the fourth monitoring data to obtain fourth feature information;

[0182] Using the feature attention layer, the third feature information, the fourth feature information and the second fused data are feature-fused to obtain target fused data;

[0183] The autoencoder network layer is used to perform anomaly identification on the target fusion data to obtain the anomaly type.

[0184] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned indoor monitoring data security early warning method embodiment based on deep learning, and will not be repeated here.

[0185] 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 any step of the indoor monitoring data security early warning method based on deep learning as provided in the description of the embodiment of the present invention.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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 deep learning-based indoor monitoring data security early warning method, characterized in that: The method comprises: Obtain first monitoring data corresponding to a first LoRa sensor of a target object at a historical moment and second monitoring data corresponding to a second LoRa sensor of the target object at the historical moment, and determine first fusion data corresponding to the first LoRa sensor and the second LoRa sensor at the historical moment; Determine a first target weight corresponding to the first LoRa sensor and a second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data combined with the first fusion data; Obtain third monitoring data corresponding to the first LoRa sensor of the target object at the current moment and fourth monitoring data corresponding to the second LoRa sensor of the target object at the current moment; Performing feature extraction on the third monitoring data to obtain first feature information and performing feature extraction on the fourth monitoring data to obtain second feature information; Perform feature fusion according to the first target weight, the first feature information, the second target weight and the second feature information to obtain second fused data; Performing anomaly identification using a deep learning model according to the second fusion data to obtain anomaly types; Determine the security warning result corresponding to the target object according to the abnormality type, and perform a corresponding warning operation according to the security warning result.

2. The method according to claim 1, characterized in that The determining, according to the first monitoring data and the second monitoring data in combination with the first fusion data, a first target weight corresponding to the first LoRa sensor and a second target weight corresponding to the second LoRa sensor includes: Determine a first initial weight corresponding to the first LoRa sensor and a second initial weight corresponding to the second LoRa sensor; fusing the first monitoring data and the second monitoring data according to the first initial weight and the second initial weight to obtain initial fused data; Obtaining a difference between the initial fusion data and the first fusion data, and when the difference is less than a preset value, determining a first accuracy corresponding to the first LoRa sensor according to the first monitoring data, and determining a second accuracy corresponding to the second LoRa sensor according to the second monitoring data; Determining a third accuracy corresponding to the target object according to the first initial weight, the second initial weight, the first accuracy, and the second accuracy; When the third accuracy satisfies a preset condition, the first target weight and the second target weight are determined according to the first accuracy and the second accuracy.

3. The method according to claim 2, characterized in that The method further comprises: When the difference is greater than or equal to the preset value, or the third accuracy does not meet the preset condition, the first initial weight corresponding to the first LoRa sensor is adjusted to obtain the third initial weight and the second initial weight corresponding to the second LoRa sensor is adjusted to obtain the fourth initial weight, until the adjusted difference is less than the preset value, or the adjusted third accuracy meets the preset condition.

4. The method according to claim 1, characterized in that: The step of extracting features from the third monitoring data to obtain first feature information and extracting features from the fourth monitoring data to obtain second feature information includes: Performing filtering processing on the third monitoring data to obtain first filtered data and performing filtering processing on the fourth monitoring data to obtain second filtered data; Determine a first characteristic sequence corresponding to the first filtered data and a second characteristic sequence corresponding to the second filtered data; Set a first abnormal frequency corresponding to the first LoRa sensor and a second abnormal frequency corresponding to the second LoRa sensor; Obtain a first value corresponding to the first abnormal frequency according to the first characteristic sequence and obtain a second value corresponding to the second abnormal frequency according to the second characteristic sequence; The first feature information is determined according to the first value and the first feature sequence, and the second feature information is determined according to the second value and the second feature sequence.

5. The method according to claim 4, characterized in that The step of obtaining a first value corresponding to the first abnormal frequency according to the first characteristic sequence and obtaining a second value corresponding to the second abnormal frequency according to the second characteristic sequence includes: determining a first quantity corresponding to the first abnormal frequency and determining a second quantity corresponding to the second abnormal frequency; Obtaining a first integer sequence corresponding to the first number and obtaining a second integer sequence corresponding to the second number; multiplying each first integer in the first integer sequence by the first abnormal frequency to obtain a first frequency, and multiplying each second integer in the second integer sequence by the second abnormal frequency to obtain a second frequency; The first value corresponding to the first frequency is obtained according to the first characteristic sequence, and the second value corresponding to the second frequency is obtained according to the second characteristic sequence.

6. The method according to claim 5, characterized in that The determining the first feature information according to the first value and the first feature sequence, and determining the second feature information according to the second value and the second feature sequence, includes: Summing the first values ​​to obtain a first sum value, and summing the second values ​​to obtain a second sum value; Summing the first feature sequence to obtain a third sum value, and summing the second feature sequence to obtain a fourth sum value; determining the first feature information according to the first sum, the third sum, and the first quantity; determining the second feature information according to the second sum value, the fourth sum value, and the second quantity; The first characteristic information and the second characteristic information are obtained according to the following formula: ; ; in, represents the first characteristic information, represents the second characteristic information, X1 represents the first quantity, X2 represents the second quantity, f1 represents the first abnormal frequency, f2 represents the second abnormal frequency, i* 1 represents the first frequency, i* 2 represents the second frequency, represents the first value, represents the second value, represents the value corresponding to the jth bit in the first feature sequence, represents the value corresponding to the jth bit in the second feature sequence, represents the number corresponding to the first feature sequence, Indicates the number corresponding to the second feature sequence.

7. The method according to claim 1, characterized in that The deep learning model includes a feature extraction layer, a feature attention layer, and an autoencoder network layer. The method of performing abnormality identification using the deep learning model according to the second fusion data to obtain the abnormality type includes: Using the feature extraction layer to extract features from the third monitoring data to obtain third feature information and using the feature extraction layer to extract features from the fourth monitoring data to obtain fourth feature information; Using the feature attention layer, the third feature information, the fourth feature information and the second fused data are feature-fused to obtain target fused data; The autoencoder network layer is used to perform anomaly identification on the target fusion data to obtain the anomaly type.

8. A deep learning-based indoor monitoring data security early warning device, characterized in that: include: A data processing module, used to obtain first monitoring data corresponding to a first LoRa sensor of a target object at a historical moment and second monitoring data corresponding to a second LoRa sensor of the target object at the historical moment, and determine first fusion data corresponding to the first LoRa sensor and the second LoRa sensor at the historical moment; A weight determination module, configured to determine a first target weight corresponding to the first LoRa sensor and a second target weight corresponding to the second LoRa sensor according to the first monitoring data and the second monitoring data in combination with the first fusion data; A data acquisition module, used to obtain third monitoring data corresponding to the first LoRa sensor of the target object at the current moment and fourth monitoring data corresponding to the second LoRa sensor of the target object at the current moment; A feature extraction module, used for performing feature extraction on the third monitoring data to obtain first feature information and performing feature extraction on the fourth monitoring data to obtain second feature information; A data fusion module, used for performing feature fusion according to the first target weight, the first feature information, the second target weight and the second feature information to obtain second fused data; an abnormality identification module, used to perform abnormality identification using a deep learning model according to the second fusion data to obtain an abnormality type; The warning processing module is used to determine the security warning result corresponding to the target object according to the abnormality type, and perform a corresponding warning operation according to the security warning result.

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 monitoring data security early warning method based on deep learning as described in 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 monitoring data security early warning method based on deep learning as described in any one of claims 1 to 7.

Images