Internet of Things control method and system

Abstract

The invention discloses an Internet of Things control method and system, and the method comprises the steps: monitoring and collecting temperature data in a refrigeration thermostatic bath in real time through a temperature sensor, and introducing a data processing and analysis algorithm based on artificial intelligence and deep learning at a rear end to carry out the time sequence analysis of the temperature data; feature filtering is carried out on the local time sequence features of the temperature in the refrigeration thermostatic bath through the contribution degree of the pseudo anchoring center, local time sequence information aggregation and reasoning of the temperature in the thermostatic bath are carried out through time-space transmission information of the local time sequence of the temperature, and therefore real-time temperature data are predicted and obtained. And then, the predicted real-time temperature data is transmitted to the actuator module, so that corresponding actions are executed through the actuator module based on the real-time temperature data and the control signal, and intelligent control of the Internet of Things is realized. Therefore, irrelevant noise interference influence of a temperature time sequence can be reduced through a feature filtering mode, and time sequence information aggregation and reasoning of the temperature in the thermostatic bath are performed by using a time-space transmission mode of temperature local time sequence semantics, so that real-time temperature data in the thermostatic bath can be predicted more accurately; according to the intelligent prediction mode, the generalization ability of the system is improved, so that the Internet of Things control system can better adapt to new conditions, and control actions can be more timely and effectively executed.

Description

Technical Field

[0001] The present application relates to the field of intelligent control, and more specifically, to an Internet of Things control method and system. Background Art

[0002] Refrigeration thermostatic bath is a device widely used in many research fields such as chemistry, biomedicine, and materials science. It is mainly used to provide a stable temperature environment for various experiments. The refrigeration thermostatic bath automatic control system is a system that realizes automatic adjustment and control of the refrigeration thermostatic bath, keeping the temperature in the refrigeration thermostatic bath constant within a predetermined range. However, there are some shortcomings in the traditional refrigeration thermostatic bath control system. For example, when collecting temperature data, it is easily affected by noise and other interference factors, resulting in inaccurate temperature measurement, and the control system cannot detect the actual temperature changes in time, resulting in temperature fluctuations in the thermostatic bath, and when the temperature changes dynamically, it is difficult for the system to quickly adjust the strategy according to the temperature changes.

[0003] In response to the above technical problems, Chinese patent CN117784849A proposes an artificial intelligence-based refrigeration thermostatic bath automatic control system, which can collect temperature data regularly, convert the residual signal between the predicted temperature and the measured temperature into a time series, perform EMD decomposition, extract the intrinsic mode function component, reduce noise interference, and improve the accuracy and stability of the data. In addition, the temperature prediction module uses a radial basis function neural network constructed by a Gaussian kernel function to predict the temperature, and adjusts the connection weights to minimize the error between the actual temperature and the predicted value, thereby improving the accuracy of temperature prediction. Then, the optimization system module initializes the neural network parameters, optimizes the system performance by selecting actions and adding noise, state transition storage, calculating loss functions and policy gradients, and uses a soft update mechanism to update the target network parameters to enhance the system's adaptability to temperature changes, so that decisions can be adjusted in time according to temperature changes to improve system stability.

[0004] However, in the above-mentioned refrigeration thermostatic bath automatic control system, in the process of predicting temperature data, the temperature prediction is performed by constructing a radial basis function neural network using a Gaussian kernel function, and the radial basis function neural network performs poorly when dealing with complex nonlinear relationships, and it is difficult to obtain accurate temperature prediction values. In other words, although the radial basis function neural network can handle nonlinear relationships to a certain extent, its generalization ability may be limited when dealing with complex and variable temperature data. This means that when faced with temperature changes in different environments, the model may not be able to adapt well to new situations, resulting in a decrease in the accuracy of the prediction. In addition, the above scheme reduces noise interference by EMD decomposition, but this method may not be sufficient to completely eliminate all types of noise. Especially in industrial or laboratory environments, various interference factors may cause large fluctuations in temperature data, which in turn affects the accuracy of temperature prediction and leads to subsequent control deviations.

[0005] Therefore, an optimized IoT control system is desired. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an Internet of Things control method and system, which collects the temperature data inside the refrigeration thermostatic bath in real time through a temperature sensor, and introduces a data processing and analysis algorithm based on artificial intelligence and deep learning in the back end to perform time series analysis on the temperature data, and then uses the contribution of the pseudo anchor center to perform feature filtering on the local time series characteristics of the temperature inside the refrigeration thermostatic bath, and at the same time, the local time series information aggregation and reasoning of the temperature inside the thermostatic bath are performed through the spatiotemporal transmission information of the local time series of the temperature, so as to predict the real-time temperature data. Then, the predicted real-time temperature data is transmitted to the actuator module, so that the actuator module performs the corresponding action based on the real-time temperature data and the control signal, so as to realize the intelligent control of the Internet of Things. In this way, the influence of irrelevant noise interference of the temperature time series can be reduced by feature filtering, and the time series information aggregation and reasoning of the temperature inside the thermostatic bath are performed by using the spatiotemporal transmission method of the local time series semantics of the temperature, so as to more accurately predict the real-time temperature data inside the thermostatic bath, and this intelligent prediction method improves the generalization ability of the system, so that the Internet of Things control system can better adapt to new situations, so as to perform control actions more timely and effectively.

[0007] According to one aspect of the present application, there is provided an Internet of Things control system, which includes:

[0008] A temperature acquisition prediction module is used to obtain a time queue of temperature data inside the refrigeration thermostatic bath collected by a temperature sensor, and perform time series information transmission aggregation analysis and prediction on the time queue of temperature data inside the refrigeration thermostatic bath to obtain real-time temperature data;

[0009] A user interface setting module, used to set the user interface for mode selection, parameter adjustment and fault prompt;

[0010] an actuator module, configured to receive the real-time temperature data and a control signal sent by the user interface, and to perform a control action based on the real-time temperature data and the control signal;

[0011] The system monitoring module is used to remotely monitor the Internet of Things control system and issue early warnings for faults.

[0012] According to another aspect of the present application, there is provided an Internet of Things control method, which includes:

[0013] Acquire a time queue of temperature data inside the refrigeration thermostatic bath collected by a temperature sensor, and perform time series information transmission aggregation analysis and prediction on the time queue of temperature data inside the refrigeration thermostatic bath to obtain real-time temperature data;

[0014] Set up the user interface for mode selection, parameter adjustment and fault prompts;

[0015] receiving the real-time temperature data and a control signal sent by the user interface, and performing a control action based on the real-time temperature data and the control signal;

[0016] The Internet of Things control system is remotely monitored and faults are warned.

[0017] Compared with the prior art, the present application provides an Internet of Things control method and system, which collects temperature data inside the refrigeration thermostatic bath in real time through a temperature sensor, and introduces a data processing and analysis algorithm based on artificial intelligence and deep learning in the back end to perform time series analysis on the temperature data, and then uses the contribution of the pseudo anchor center to perform feature filtering on the local time series characteristics of the temperature inside the refrigeration thermostatic bath, and at the same time, the local time series information of the temperature inside the thermostatic bath is aggregated and reasoned through the spatiotemporal transmission information of the local time series of the temperature, so as to predict the real-time temperature data. Then, the predicted real-time temperature data is transmitted to the actuator module, so that the actuator module performs the corresponding action based on the real-time temperature data and the control signal, and the intelligent control of the Internet of Things is realized. In this way, the influence of irrelevant noise interference of the temperature time series can be reduced by feature filtering, and the time series information aggregation and reasoning of the temperature inside the thermostatic bath are performed by using the spatiotemporal transmission method of the local time series semantics of the temperature, so as to more accurately predict the real-time temperature data inside the thermostatic bath. This intelligent prediction method improves the generalization ability of the system, so that the Internet of Things control system can better adapt to new situations, so as to perform control actions more timely and effectively. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0019] Figure 1 is a block diagram of an Internet of Things control system according to an embodiment of the present application;

[0020] Figure 2 A schematic diagram of data flow of an Internet of Things control system according to an embodiment of the present application;

[0021] Figure 3 It is a block diagram of a temperature acquisition prediction module in an Internet of Things control system according to an embodiment of the present application;

[0022] Figure 4 It is a block diagram of a temperature local timing information transmission aggregation representation unit in an Internet of Things control system according to an embodiment of the present application;

[0023] Figure 5 Flow chart of the Internet of Things control method according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0025] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0026] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0027] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0028] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0029] In the technical solution of the present application, an Internet of Things control system is proposed. Figure 1 4 is a block diagram of an Internet of Things control system according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the Internet of Things control system according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the Internet of Things control system 300 of the embodiment of the present application, it includes: a temperature acquisition prediction module 310, which is used to obtain the time queue of the temperature data inside the refrigeration thermostatic bath collected by the temperature sensor, and perform timing information transmission aggregation analysis and prediction on the time queue of the temperature data inside the refrigeration thermostatic bath to obtain real-time temperature data; a user interface setting module 320, which is used to set the user interface for mode selection, parameter adjustment and fault prompt; an actuator module 330, which is used to receive the real-time temperature data and the control signal sent by the user interface, and perform control actions based on the real-time temperature data and the control signal; a system monitoring module 340, which is used to remotely monitor the Internet of Things control system and warn of faults.

[0030] In particular, the temperature acquisition prediction module 310 is used to obtain the time queue of the temperature data inside the refrigeration thermostatic bath collected by the temperature sensor, and perform time series information transmission aggregation analysis and prediction on the time queue of the temperature data inside the refrigeration thermostatic bath to obtain real-time temperature data. In a specific example of the present application, Figure 3As shown, the temperature acquisition prediction module 310 includes: a temperature time series data encoding unit 311, which is used to standardize the time queue of the temperature data inside the refrigeration thermostatic bath and then perform temperature sequence encoding to obtain a sequence of local time series correlation characteristics of the temperature inside the thermostatic bath; a temperature local time series information transmission aggregation representation unit 312, which is used to perform information transmission aggregation representation on the sequence of local time series correlation characteristics of the temperature inside the thermostatic bath to obtain a time series information propagation aggregation representation of the temperature inside the thermostatic bath; a real-time temperature data prediction unit 313, which is used to determine the real-time temperature data based on the time series information propagation aggregation representation of the temperature inside the thermostatic bath.

[0031] Specifically, the temperature time series data encoding unit 311 is used to perform standardization on the time queue of the temperature data inside the refrigeration thermostatic bath and then perform temperature sequence encoding to obtain a sequence of local time series correlation features of the temperature inside the thermostatic bath. In a specific example of the present application, first, the time queue of the temperature data inside the thermostatic bath is standardized to obtain a time queue of standardized temperature data inside the thermostatic bath; it should be understood that since the temperature data collected by the temperature sensor may have different magnitudes and distributions, if it is not standardized, larger values ​​and denser data may dominate the learning process of the model, while ignoring those features with smaller values ​​and sparser data distribution but equally important. Therefore, in order to ensure data consistency in subsequent processing steps and reduce the impact caused by different data magnitudes or distributions, in the technical solution of the present application, the time queue of the temperature data inside the thermostatic bath is standardized to obtain a time queue of standardized temperature data inside the thermostatic bath. Next, the time queue of the standardized temperature data inside the thermostatic bath is input into the temperature sequence encoder based on the 1D-CNN model to obtain the sequence of the local time series correlation feature vectors of the temperature inside the thermostatic bath; the time queue of the standardized temperature data inside the thermostatic bath is input into the temperature sequence encoder based on the 1D-CNN model for feature encoding to extract the local time series feature information of the standardized temperature data inside the thermostatic bath in the time dimension, thereby obtaining the sequence of the local time series correlation feature vectors of the temperature inside the thermostatic bath. Subsequently, the sequence of the local time series correlation feature vectors of the temperature inside the thermostatic bath is subjected to feature filtering based on the central contribution degree to obtain the sequence of the filtered local time series correlation feature vectors of the temperature inside the thermostatic bath as the sequence of the local time series correlation features of the temperature inside the thermostatic bath. Here. Considering that each local time series correlation feature vector of the temperature inside the thermostatic bath in the sequence input of the local time series correlation feature vector of the temperature inside the thermostatic bath respectively contains the local time series correlation feature information about the temperature inside the thermostatic bath in each local time period in the time dimension, and the local time series features of these temperatures are not all equally important for the subsequent real-time temperature data prediction task and control execution task. At the same time, there are some irrelevant interference and noise information in these different local temperature time series characteristics. Especially in industrial or laboratory environments, various interference factors may cause large fluctuations in temperature data, thereby affecting the accuracy of temperature prediction and causing subsequent control deviations.Based on this, in order to screen out the most representative and influential temperature local time series features from numerous constant temperature bath internal temperature local time series correlation feature vectors, thereby improving the prediction performance and generalization ability of the model, in the technical solution of the present application, the sequence of the constant temperature bath internal temperature local time series correlation feature vectors is further subjected to feature filtering processing based on the central contribution degree to obtain the filtered sequence of the constant temperature bath internal temperature local time series correlation feature vectors as the sequence of the constant temperature bath internal temperature local time series correlation features.

[0032] Among them, the process of performing cluster analysis on the sequence of local time series correlation feature vectors of the internal temperature of the constant temperature bath to obtain the local time series clustering center representation vector of the internal temperature of the constant temperature bath includes: calculating the positional mean between each local time series correlation feature vector of the internal temperature of the constant temperature bath in the sequence of local time series correlation feature vectors of the internal temperature of the constant temperature bath to obtain the local time series clustering center representation vector of the internal temperature of the constant temperature bath.

[0033] More specifically, the process of taking the local time series clustering center representation vector of the internal temperature of the constant temperature bath as the pseudo anchor center and calculating the semantic contribution representation matrix of each local time series associated feature vector of the internal temperature of the constant temperature bath relative to the pseudo anchor center in the sequence of the local time series associated feature vector of the internal temperature of the constant temperature bath to obtain the sequence of local time series contribution representation matrices of the internal temperature of the constant temperature bath includes: calculating the positional division between the transposed vector of the local time series clustering center representation vector of the internal temperature of the constant temperature bath and the binary norm of the local time series clustering center representation vector of the internal temperature of the constant temperature bath to obtain the transformed local time series clustering center vector of the internal temperature of the constant temperature bath; calculating the vector multiplication between each local time series associated feature vector of the internal temperature of the constant temperature bath and the transformed local time series clustering center vector of the internal temperature of the constant temperature bath, and then using the Softmax function to perform soft maximum value normalization processing on the sequence of the obtained association matrices to obtain the sequence of local time series contribution representation matrices of the internal temperature of the constant temperature bath.

[0034] More specifically, the process of performing feature filtering based on the central contribution degree on the sequence of the local time series correlation feature vectors of the temperature inside the thermostat bath to obtain the filtered sequence of the local time series correlation feature vectors of the temperature inside the thermostat bath as the sequence of the local time series correlation features of the temperature inside the thermostat bath includes: first, clustering analysis is performed on the sequence of the local time series correlation feature vectors of the temperature inside the thermostat bath to obtain the local time series cluster center representation vector of the temperature inside the thermostat bath; through clustering analysis, the local time series cluster center representation vector of the temperature inside the thermostat bath can be extracted as a pseudo anchor center, which helps to capture the intrinsic structure and distribution of the temperature time series data. The determination of the pseudo anchor center provides a benchmark for the importance evaluation of the feature vector, so that the model can focus on the features that are most meaningful for temperature prediction. Next, the semantic contribution of each thermostat bath internal temperature local time series associated feature vector in the sequence of the thermostat bath internal temperature local time series associated feature vectors relative to the thermostat bath internal temperature local time series cluster center representation vector is calculated to obtain a sequence of masked sparse thermostat bath internal temperature local time series contribution representation matrices; the semantic contribution is calculated to quantify the contribution and importance of each thermostat bath internal temperature local time series associated feature to the overall semantics, thereby ignoring those features that are not helpful or even harmful to temperature prediction in subsequent processing. Furthermore, each masked sparse thermostat bath internal temperature local time series contribution representation matrix in the sequence of the masked sparse thermostat bath internal temperature local time series contribution representation matrix is ​​used as a modulation matrix, and the matrix product between it and each thermostat bath internal temperature local time series associated feature vector is calculated to obtain the sequence of the filtered thermostat bath internal temperature local time series associated feature vectors. Specifically, the cluster center representation vector of the local time series of the temperature inside the thermostat is first used as the pseudo anchor center, and the semantic contribution representation matrix of each local time series associated feature vector of the temperature inside the thermostat in the sequence of the local time series associated feature vector of the temperature inside the thermostat is calculated relative to the pseudo anchor center to obtain the sequence of the local time series contribution representation matrix of the temperature inside the thermostat; and then the local time series contribution representation matrix of the temperature inside the thermostat in the sequence of the local time series contribution representation matrix of the temperature inside the thermostat is subjected to random inactivation to obtain the sequence of the masked sparse local time series contribution representation matrix of the temperature inside the thermostat. That is, the local time series contribution representation matrix of the temperature inside the thermostat is subjected to sparse processing by using the random inactivation mechanism to generate a sequence of masked sparse local time series contribution representation matrices of the temperature inside the thermostat, so as to enhance the generalization ability of the model and reduce the number of parameters. The contribution pseudo-mask sparse processing strengthens the model's attention to key temperature time series features by randomly "closing" a part of unimportant local time series features of temperature, while reducing the complexity of the model and the risk of overfitting.Finally, the masked sparse thermostat internal temperature local time series contribution representation matrix is ​​used as a modulation matrix, and a matrix product operation is performed with each thermostat internal temperature local time series associated feature vector to achieve feature filtering. That is, the original feature vector is weighted by the modulation matrix to filter out unimportant or noisy temperature time series features. After feature filtering, a sequence of filtered thermostat internal temperature local time series associated feature vectors is obtained, which contains important temperature local time series semantics and features that have been evaluated and screened. These features are used for subsequent predictions, which can more accurately reflect the actual change trend of the temperature inside the thermostat, thereby improving the accuracy of temperature prediction.

[0035] In summary, in the above embodiment, the sequence of the local time series correlation feature vectors of the internal temperature of the thermostatic bath is subjected to feature filtering processing based on the central contribution to obtain the sequence of the local time series correlation feature vectors of the internal temperature of the thermostatic bath after filtering as the sequence of the local time series correlation features of the internal temperature of the thermostatic bath, including: performing feature filtering processing based on the central contribution to obtain the sequence of the local time series correlation feature vectors of the internal temperature of the thermostatic bath after filtering as the sequence of the local time series correlation features of the internal temperature of the thermostatic bath according to the following feature filtering formula; wherein the feature filtering formula is:

[0036] X={x1,x2,...,x n}

[0037]

[0038] {x i '}={WF i *x i}

[0039] Where X is the sequence of local time series correlation feature vectors of the internal temperature of the thermostatic bath, x1, x2, x n are the first, second and nth local time series correlation feature vectors of the internal temperature of the thermostatic bath in the sequence of the local time series correlation feature vectors of the internal temperature of the thermostatic bath, respectively. i is the i-th local time series correlation feature vector of the internal temperature of the thermostatic bath in the sequence of the local time series correlation feature vectors of the internal temperature of the thermostatic bath, N is the number of feature vectors in the sequence of the local time series correlation feature vectors of the internal temperature of the thermostatic bath, x c is the vector representing the local time series cluster center of the internal temperature of the thermostat, ||·||2 represents the vector binorm, Softmax(·) is the Softmax function, dropout is the random inactivation process, WF iis the masked sparse thermostatic bath internal temperature local time series contribution representation matrix corresponding to the i-th thermostatic bath internal temperature local time series associated feature vector, x i ' is the i-th filtered local time series correlation feature vector of the internal temperature of the thermostatic bath in the sequence of the filtered local time series correlation feature vectors of the internal temperature of the thermostatic bath.

[0040] Specifically, the temperature local time series information transfer aggregation representation unit 312 is used to perform information transfer aggregation representation on the sequence of the local time series correlation features of the temperature inside the thermostatic bath to obtain the aggregation representation of the time series information propagation of the temperature inside the thermostatic bath. It should be understood that since the sequence of the filtered local time series correlation feature vectors of the temperature inside the thermostatic bath respectively contains the local time series correlation features of the temperature inside the thermostatic bath after feature filtering and purification, these local time series features of the temperature after feature filtering have a time series transfer characteristic, which exists not only in the attenuation of the time series correlation in time, but also in the span information of the features of the two in space. Based on this, in order to better capture and utilize the dynamic changes of temperature data in time and space, thereby improving the prediction accuracy and response speed of the system, in the technical solution of the present application, the sequence of the local time series correlation features of the temperature inside the thermostatic bath is further performed information transfer aggregation representation to obtain the aggregation representation of the time series information propagation of the temperature inside the thermostatic bath. In a specific example of the present application, Figure 4 As shown, the temperature local time series information transmission aggregation representation unit 312 includes: a thermostatic bath internal temperature local time series correlation feature extraction subunit 3121, which is used to extract the current thermostatic bath internal temperature local time series correlation feature and the sequence of historical thermostatic bath internal temperature local time series correlation feature from the sequence of the thermostatic bath internal temperature local time series correlation feature; a thermostatic bath internal temperature dynamic energy spatiotemporal transfer weight calculation subunit 3122, which is used to calculate the sequence of the thermostatic bath internal temperature dynamic energy spatiotemporal transfer weights of the sequence of the historical thermostatic bath internal temperature local time series correlation feature relative to the current thermostatic bath internal temperature local time series correlation feature; a node feature transmission fusion subunit 3123, which is used to perform node feature transmission fusion on the sequence of the thermostatic bath internal temperature local time series correlation feature based on the sequence of the thermostatic bath internal temperature dynamic energy spatiotemporal transfer weights to obtain the thermostatic bath internal temperature time series information propagation aggregation representation.

[0041] More specifically, the thermostatic bath internal temperature local time series correlation feature extraction subunit 3121 is used to extract the current thermostatic bath internal temperature local time series correlation feature and the historical thermostatic bath internal temperature local time series correlation feature sequence from the thermostatic bath internal temperature local time series correlation feature sequence. In the technical solution of the present application, the current filtered thermostatic bath internal temperature local time series correlation feature vector is extracted from the sequence of filtered thermostatic bath internal temperature local time series correlation feature vectors as the current thermostatic bath internal temperature local time series correlation feature, and other filtered thermostatic bath internal temperature local time series correlation feature vectors in the sequence of filtered thermostatic bath internal temperature local time series correlation feature vectors are defined as historical filtered thermostatic bath internal temperature local time series correlation feature vectors to obtain a sequence of historical filtered thermostatic bath internal temperature local time series correlation feature vectors as the sequence of historical thermostatic bath internal temperature local time series correlation features.

[0042] More specifically, the thermostatic bath internal temperature dynamic energy spatiotemporal transfer weight calculation subunit 3122 is used to calculate the sequence of the thermostatic bath internal temperature dynamic energy spatiotemporal transfer weights of the sequence of the historical thermostatic bath internal temperature local time series correlation features relative to the current thermostatic bath internal temperature local time series correlation features. In a specific example of the present application, first, the thermostatic bath internal temperature local time series static energy value of each historical filtered thermostatic bath internal temperature local time series correlation feature vector in the sequence of the historical filtered thermostatic bath internal temperature local time series correlation feature vectors is calculated; then, based on the spatial span coefficient between each historical filtered thermostatic bath internal temperature local time series correlation feature vector and the current filtered thermostatic bath internal temperature local time series correlation feature vector, the spatial attenuation factor of the thermostatic bath internal temperature local time series energy is determined; then, based on the time span coefficient between each historical filtered thermostatic bath internal temperature local time series correlation feature vector and the current filtered thermostatic bath internal temperature local time series correlation feature vector, the time attenuation factor of the thermostatic bath internal temperature local time series energy is determined; further , based on the local time series energy spatial attenuation factor of the thermostatic bath internal temperature and the local time series energy time attenuation factor of the thermostatic bath internal temperature, the local time series static energy value of the thermostatic bath internal temperature of each historical filtered thermostatic bath internal temperature local time series associated feature vector is temporally modulated to obtain the local time series dynamic energy spatiotemporal transfer value of the thermostatic bath internal temperature of each historical filtered thermostatic bath internal temperature local time series associated feature vector relative to the current filtered thermostatic bath internal temperature local time series associated feature vector; then the local time series dynamic energy spatiotemporal transfer value of the thermostatic bath internal temperature of each historical filtered thermostatic bath internal temperature local time series associated feature vector is input into the energy transfer gating module based on the mask function to obtain the sequence of the spatiotemporal transfer weights of the local time series dynamic energy of the thermostatic bath internal temperature. Here, by calculating the static energy value of each historical filtered thermostatic bath internal temperature local time series associated feature vector, and combining the spatial span coefficient and the time span coefficient of the current filtered thermostatic bath internal temperature local time series associated feature vector, the historical information and the current state can be integrated to form an aggregate representation vector. This vector contains the dynamic change information of the local time series characteristics of temperature in time and space span, which helps the model to understand the trend of temperature change more comprehensively. In particular, the static energy value is related to the maximum eigenvalue, mean and variance of the local time series associated eigenvectors of the internal temperature of the thermostatic bath after each historical filtering. The static energy value provides a quantitative measure of the inherent properties of the eigenvector in space, provides a benchmark for the spatiotemporal attenuation of potential energy, and helps the model understand the static importance of each node in the spatial and temporal dimensions.The spatial span coefficient and the temporal span coefficient respectively reflect the spatial distance and temporal distance between nodes. The static energy value of the local time series associated feature vector of the temperature in each thermostatic bath after historical filtering is modulated by the energy spatial decay factor and the energy temporal decay factor, so as to adjust the static energy value by combining the spatial decay factor and the temporal decay factor through spatiotemporal modulation, so as to reflect the dynamic changes of node features in space and time, so that the model can adjust the weight and intensity of information transfer according to the distance between the space and time of the nodes, and enhance the sensitivity of the model to the locality and timeliness of the temperature time series. In this way, the dynamic changes and information transfer effects of the local time series feature data of the temperature can be more accurately captured between different nodes in the full time domain. Furthermore, through the energy transfer gating module, important spatiotemporal transfer information about the local time series of the temperature can be screened out, and this information can be strengthened through the mask function. This mechanism can help the model identify which historical local time series information of the temperature is crucial to the current state prediction, thereby improving the accuracy and effectiveness of the transmission of the local time series feature information of the temperature. By adaptively adjusting the information flow, the model can pay more attention to the features that contribute to the task.

[0043] The process of calculating the local time series static energy value of the internal temperature of the thermostatic bath for each local time series associated characteristic vector of the internal temperature of the thermostatic bath after historical filtering in the sequence of the local time series associated characteristic vector of the internal temperature of the thermostatic bath after historical filtering comprises: respectively calculating the mean and standard deviation of the local time series associated characteristic vector of the internal temperature of the thermostatic bath after historical filtering to obtain the local time series characteristic mean of the internal temperature of the thermostatic bath after historical filtering and the local time series standard deviation of the internal temperature of the thermostatic bath after historical filtering; calculating the local time series associated characteristic vector of the internal temperature of the thermostatic bath after historical filtering and the local time series associated characteristic vector of the internal temperature of the thermostatic bath after historical filtering After calculating the fourth power of the position difference between the mean values ​​of the local temperature time series characteristics, the expected value of the local time series offset vector of the internal temperature of the thermostatic bath after the fourth power modulation history filtering is calculated to obtain the expected factor of the local time series characteristic offset of the internal temperature of the thermostatic bath after the filtering; after calculating the division between the expected factor of the local time series characteristic offset of the internal temperature of the thermostatic bath after the filtering and the fourth power of the standard deviation of the local time series of the internal temperature of the thermostatic bath after the historical filtering, the expected factor is added to the maximum eigenvalue in the associated eigenvalue vector of the local time series of the internal temperature of the thermostatic bath after the historical filtering to obtain the static energy value of the local time series of the internal temperature of the thermostatic bath.

[0044] More specifically, based on the spatial span coefficient between the local time series correlation feature vectors of the internal temperature of the thermostatic bath after each historical filtering and the local time series correlation feature vector of the internal temperature of the thermostatic bath after the current filtering, the process of determining the spatial attenuation factor of the local time series energy of the internal temperature of the thermostatic bath includes: calculating the spatial distance span between the local time series correlation feature vectors of the internal temperature of the thermostatic bath after the historical filtering and the local time series correlation feature vectors of the internal temperature of the thermostatic bath after the current filtering to obtain the local time series spatial span coefficient of the internal temperature of the thermostatic bath after the historical filtering; calculating the division between the local time series static energy value of the internal temperature of the thermostatic bath corresponding to the local time series correlation feature vector of the internal temperature of the thermostatic bath after the historical filtering and the local time series spatial span coefficient of the internal temperature of the thermostatic bath after the historical filtering to obtain the local time series spatial attenuation factor of the internal temperature of the thermostatic bath.

[0045] More specifically, based on the time span coefficient between the local time series associated characteristic vectors of the internal temperature of the thermostatic bath after each historical filtering and the local time series associated characteristic vectors of the internal temperature of the thermostatic bath after the current filtering, the process of determining the time decay factor of the local time series energy of the internal temperature of the thermostatic bath includes: calculating the subtraction between the timestamp of the local time series associated characteristic vectors of the internal temperature of the thermostatic bath after the current filtering and the timestamp of the local time series associated characteristic vectors of the internal temperature of the thermostatic bath after the historical filtering, rounding down the obtained timestamp value to obtain the filtered local time series time span coefficient of the internal temperature of the thermostatic bath; dividing the filtered local time series time span coefficient of the internal temperature of the thermostatic bath by the inverse scaling parameter of the control time decay period, taking the obtained time span decay representation coefficient as the exponential power, calculating the natural exponential function value with the natural constant e as the base to obtain the time span decay class support representation coefficient; calculating the division between the local time series static energy value of the internal temperature of the thermostatic bath and the time span decay class support representation coefficient to obtain the local time series energy time decay factor of the internal temperature of the thermostatic bath.

[0046] More specifically, the process of inputting the local temporal dynamic energy spatiotemporal transfer values ​​of the local temporal dynamic energy of the thermostatic bath after each historical filtering of the local temporal dynamic energy associated feature vectors of the thermostatic bath to an energy transfer gating module based on a mask function to obtain a sequence of local temporal dynamic energy spatiotemporal transfer weights of the thermostatic bath includes: in the energy transfer gating module based on a mask function, in response to the local temporal dynamic energy spatiotemporal transfer value of the thermostatic bath being greater than a threshold hyperparameter, the local temporal dynamic energy spatiotemporal transfer value of the thermostatic bath that is greater than the threshold hyperparameter is normalized by a sigmoid function to obtain the local temporal dynamic energy spatiotemporal transfer weight of the thermostatic bath.

[0047] More specifically, the node feature transfer fusion subunit 3123 is used to perform node feature transfer fusion on the sequence of local time series associated features of the internal temperature of the thermostat based on the sequence of dynamic energy spatiotemporal transfer weights of the internal temperature of the thermostat to obtain the aggregated representation of the internal temperature time series information propagation of the thermostat. In a specific example of the present application, first, based on the sequence of dynamic energy spatiotemporal transfer weights of the local time series of the internal temperature of the thermostat, the weighted sum of the sequence of local time series associated feature vectors of the internal temperature of the thermostat after historical filtering is calculated to obtain the local time series node feature transfer aggregate modulation vector of the internal temperature of the thermostat after historical filtering; that is, by weighted summing the dynamic energy spatiotemporal transfer values ​​of the historical node feature vectors to synthesize information from different historical nodes, the model is provided with rich local time series feature context information of temperature, which is crucial for understanding the dynamics and development trends of temperature changes, and helps to improve the model's processing capabilities for complex temperature time series information transmission and prediction tasks. Furthermore, the positional sum of the local time series node feature transfer aggregation modulation vector of the internal temperature of the thermostatic bath after historical filtering and the local time series correlation feature vector of the internal temperature of the thermostatic bath after current filtering is calculated to obtain the spatiotemporal significant propagation aggregation representation vector of the internal temperature of the thermostatic bath as the aggregation representation of the time series information propagation of the internal temperature of the thermostatic bath. Here, the local time series node feature transfer aggregation modulation vector of the internal temperature of the thermostatic bath after historical filtering and the local time series correlation feature vector of the internal temperature of the thermostatic bath after current filtering are positionally summed to generate an aggregation representation of the time series information propagation of the internal temperature of the thermostatic bath that integrates the local time series historical information of the temperature and the current state, providing rich features for subsequent tasks such as temperature prediction. Such a representation not only contains the local time series feature information of the temperature at the current moment, but also integrates the temperature change trend over the past period of time, so that the model can more accurately infer and predict future temperature changes, and enhance the model's ability to handle complex tasks.

[0048] In summary, in the above embodiment, the sequence of the local time series correlation characteristics of the internal temperature of the thermostatic bath is subjected to information transmission aggregation representation to obtain the time series information propagation aggregation representation of the internal temperature of the thermostatic bath, including: the sequence of the local time series correlation characteristics of the internal temperature of the thermostatic bath is subjected to information transmission aggregation representation using the following characteristic message propagation formula to obtain the time series information propagation aggregation representation of the internal temperature of the thermostatic bath; wherein the characteristic message propagation formula is:

[0049] X'={x1',x2',...,x i ',...,x p '}

[0050]

[0051] Among them, X' is the sequence of the local time series correlation feature vectors of the internal temperature of the thermostatic bath after filtering, x1', x2', x i ',x p ' is the first, second, i-th and p-th filtered local time series correlation feature vectors of the internal temperature of the thermostatic bath in the sequence of the filtered local time series correlation feature vectors, x i '(j) is the eigenvalue of the jth position in the local time series correlation eigenvector of the internal temperature of the thermostatic bath after the ith filtering, μ i and σ i are the characteristic mean and standard deviation of the local time series correlation characteristic vector of the internal temperature of the thermostatic bath after the i-th filtering, E is the calculated expected value, max(·) represents the maximum value in the vector, is the local time series static energy value of the temperature inside the constant temperature bath, Count(x i '→x p ') represents x i ' and x p 'The space span coefficient between For x i ' and x p 'The energy space attenuation factor between t p and t i Represents x p ' and x i 'Timestamp, represents the rounding down operation, L is the inverse scaling parameter that controls the time decay period, exp(·) is the value of the natural exponential function, For x i and x p ' is the energy time decay factor between α and β, which are trainable hyperparameters. (i→p) For x i 'Relative to x p ', mask(·) is the mask operation, p is the number of vectors in the sequence of the local time series correlation feature vectors of the internal temperature of the thermostatic bath after filtering, θ is the threshold hyperparameter, sigmoid(·) is the sigmoid function, x p+1 ' is the temporal and spatial significant propagation aggregation vector of the temperature inside the thermostatic bath.

[0052] It is worth mentioning that in other specific examples of the present application, the sequence of local time series correlation features of the internal temperature of the constant temperature bath can also be aggregated by information transfer to obtain an aggregated representation of the time series information propagation of the internal temperature of the constant temperature bath, for example: input a sequence of local time series correlation features of the internal temperature of the constant temperature bath; select a suitable model, such as a recursive neural network such as LSTM (long short-term memory network), GRU (gated recurrent unit), or a model based on an attention mechanism such as Transformer; use the extracted features to train the model so that it can learn the pattern of temperature data changing over time; define in the model how to transfer information from one time point to another, for example, through connections between recursive layers; perform aggregation operations at different levels of the model, such as average pooling, maximum pooling, etc., to integrate information at different time points; to obtain an aggregated representation of the time series information propagation of the internal temperature of the constant temperature bath.

[0053] Specifically, the real-time temperature data prediction unit 313 is used to determine the real-time temperature data based on the aggregate representation of the time series information propagation inside the thermostatic bath. In a specific example of the present application, the spatiotemporal significant propagation aggregate representation vector of the temperature inside the thermostatic bath is input into a decoder-based temperature predictor to obtain a decoded value of the real-time temperature data. That is, the spatiotemporal information transmission aggregate representation characteristics of the temperature inside the thermostatic bath are used to perform decoding regression, so as to predict the real-time temperature data inside the thermostatic bath. In this way, the influence of irrelevant noise interference of the temperature time series can be reduced, and the real-time temperature data inside the thermostatic bath can be predicted more accurately. This intelligent prediction method improves the generalization ability of the system, so that the Internet of Things control system can better adapt to new situations, so as to perform control actions more timely and effectively.

[0054] In a preferred example, inputting the spatiotemporal significant propagation aggregation representation vector of the internal temperature of the thermostatic bath into a decoder-based temperature predictor to obtain a decoded value of the real-time temperature data includes:

[0055] Determine the maximum eigenvalue of the spatiotemporal significant propagation aggregation of the temperature inside the thermostat bath and the minimum eigenvalue of the spatiotemporal significant propagation aggregation of the temperature inside the thermostat bath of the spatiotemporal significant propagation aggregation representation vector, and calculate the spatiotemporal significant propagation aggregation mean and spatiotemporal significant propagation aggregation standard deviation of the feature set of the spatiotemporal significant propagation aggregation representation vector of the temperature inside the thermostat bath;

[0056] Calculate the quotient of the temporal and spatial significant propagation aggregate mean of the temperature inside the thermostatic bath and the temporal and spatial significant propagation aggregate standard deviation of the temperature inside the thermostatic bath to obtain a statistical normalized value of the temporal and spatial significant propagation aggregate of the temperature inside the thermostatic bath;

[0057] Calculate the inverse of each eigenvalue of the temporal and spatial significant propagation aggregation representation vector of the thermostatic bath internal temperature, multiply it by the difference between the maximum eigenvalue of the temporal and spatial significant propagation aggregation of the thermostatic bath internal temperature and the minimum eigenvalue of the temporal and spatial significant propagation aggregation of the thermostatic bath internal temperature, and then subtract it from the temporal and spatial significant propagation aggregation statistical normalized value of the thermostatic bath internal temperature to obtain the temporal and spatial significant propagation aggregation distribution approximation vector of the thermostatic bath internal temperature;

[0058] Calculate an exponential function with a natural constant as the base, with each eigenvalue of the approximate vector of the temporal and spatial significant propagation aggregate distribution of the temperature inside the thermostatic bath being an exponent, to obtain an approximate vector of the temporal and spatial significant propagation aggregate distribution of the temperature inside the thermostatic bath;

[0059] Performing point addition of the thermostatic bath internal temperature spatiotemporal significant propagation aggregate distribution class approximation vector and the thermostatic bath internal temperature spatiotemporal significant propagation aggregate statistical normalized value, and calculating the base-two logarithm of the absolute value of each eigenvalue of the point addition vector to obtain an optimized thermostatic bath internal temperature spatiotemporal significant propagation aggregate representation vector; and

[0060] The optimized spatiotemporal significant propagation aggregation representation vector of the internal temperature of the thermostatic bath is input into a temperature predictor based on a decoder to obtain a decoded value of the real-time temperature data.

[0061] Among them, the optimization representation vector of the temporal and spatial significant propagation aggregation of the temperature inside the thermostatic bath, denoted as V, is:

[0062]

[0063]

[0064] δ=v max -v min

[0065] Among them, V is the temporal and spatial significant propagation aggregation vector of the temperature inside the thermostat, V ⊙-1 is the inverse of each eigenvalue of the temporal and spatial significant spread aggregation representation vector of the internal temperature of the thermostat, v max and v min is the maximum eigenvalue of the spatiotemporal significant propagation aggregation of the temperature inside the thermostat and the minimum eigenvalue of the spatiotemporal significant propagation aggregation of the temperature inside the thermostat, and δ is the difference between the maximum eigenvalue of the spatiotemporal significant propagation aggregation of the temperature inside the thermostat and the minimum eigenvalue of the spatiotemporal significant propagation aggregation of the temperature inside the thermostat, μ is the mean of the spatiotemporal significant propagation aggregation of the temperature inside the thermostat, σ is the standard deviation of the spatiotemporal significant propagation aggregation of the temperature inside the thermostat, η is the statistical standardization value of the spatiotemporal significant propagation aggregation of the temperature inside the thermostat, V e is the approximate vector of the spatial and temporal significant propagation of the temperature inside the thermostatic bath, is the dot addition, ⊙ is the dot product, is point subtraction, exp() is exponential operation, log is logarithm with base 2, and V′ is the optimized spatiotemporal significant propagation aggregation representation vector of the internal temperature of the thermostatic bath.

[0066] Here, in the preferred example, since the sequence of filtered thermostatic bath internal temperature local time series correlation feature vectors respectively represent the filtering query semantic features of the thermostatic bath internal temperature local time series correlation under each local time domain based on the pseudo-anchor center contribution semantic query, when it is input into the feature message propagation network based on the node potential energy spatiotemporal transfer characteristics, the node semantic filtering query difference will have different semantic propagation weights based on the potential energy spatiotemporal transfer characteristics, so that the thermostatic bath internal temperature spatiotemporal significant propagation aggregation representation vector will also have a diversified set expression distribution of time series aggregation features. Therefore, it is expected to improve the balance between the regression mapping accuracy and completeness when the thermostatic bath internal temperature spatiotemporal significant propagation aggregation representation vector is input based on the temperature predictor of the decoder for decoding regression, thereby improving the accuracy of the decoded value of the obtained real-time temperature data.

[0067] Therefore, by performing random statistical normalization on the diversified feature set of the spatiotemporal significant propagation aggregate representation vector of the temperature inside the thermostat, the confidence space constructed based on the overall eigenvalue of the spatiotemporal significant propagation aggregate representation vector of the temperature inside the thermostat is approximated by the standardized continuous probability density distribution relative to the response hypothesis test of each eigenvalue of the spatiotemporal significant propagation aggregate representation vector of the temperature inside the thermostat, thereby establishing the target reachability of the diversified feature distribution of the spatiotemporal significant propagation aggregate representation vector of the temperature inside the thermostat to the unified regression target, so as to achieve the balanced executableness between mapping accuracy and mapping completeness in the decoding regression process based on the diversified feature distribution of the spatiotemporal significant propagation aggregate representation vector of the temperature inside the thermostat, and improve the accuracy of the decoded value of the real-time temperature data obtained by the temperature predictor based on the decoder of the spatiotemporal significant propagation aggregate representation vector of the temperature inside the thermostat. In this way, the real-time temperature data inside the thermostat can be predicted more accurately, the generalization ability of the system is improved, and the Internet of Things control system can better adapt to new situations so as to perform control actions more timely and effectively.

[0068] It is worth mentioning that in other specific examples of the present application, the time queue of the temperature data inside the refrigeration thermostatic bath collected by the temperature sensor can also be obtained by other means, and the time queue of the temperature data inside the refrigeration thermostatic bath is subjected to time series information transmission aggregation analysis and prediction to obtain real-time temperature data, for example: input the time queue of the temperature data inside the refrigeration thermostatic bath; select a model suitable for time series data analysis, such as LSTM (long short-term memory network), GRU (gated recurrent unit), Transformer, etc.; use the extracted features and label data to train the model to ensure that the model can learn the pattern of temperature data changing over time; define an information transfer mechanism in the model, such as realizing information transfer through connections between recursive layers; perform aggregation operations at different levels of the model, such as average pooling, maximum pooling, etc., to integrate information at different time points; continuously collect real-time temperature data from the temperature sensor and add it to the time queue; perform the same preprocessing steps on the real-time collected data to ensure the consistency and accuracy of the data; perform feature extraction on the real-time data to form the same feature representation as the training data; input the features of the real-time data into the trained model, and output the temperature prediction value at a certain time point in the future to obtain the real-time temperature data.

[0069] In particular, the user interface setting module 320 is used to set the user interface for mode selection, parameter adjustment and fault prompt. The user interface setting module plays a vital role in the refrigeration thermostatic bath control system. It not only provides an entry for users to interact with the system, but also enhances the system's usability and user experience. In one example, the user interface setting module allows the user to select different operating modes and adjust various control parameters, such as set temperature, temperature fluctuation range, heating / cooling rate, etc. In addition, it monitors the system status in real time, and when a fault or abnormality is detected, it promptly issues a warning or prompt to the user. In this way, the user's operating experience and the reliability of the system are significantly improved, ensuring that the refrigeration thermostatic bath operates efficiently and stably in various application scenarios.

[0070] In particular, the actuator module 330 is used to receive the real-time temperature data and the control signal sent by the user interface, and to perform control actions based on the real-time temperature data and the control signal. In one example, the actuator module performs corresponding control actions according to the real-time temperature data and the control signal set by the user. For example: when the real-time temperature is lower than the set temperature, the actuator module increases the heating speed by adjusting the current or voltage of the heater to increase the power of the heater; when the real-time temperature is higher than the set temperature, the actuator module increases the cooling speed by adjusting the fan speed or refrigerant flow of the cooler to increase the power of the cooler; when a temperature abnormality or equipment failure is detected, the heater is turned off by the actuator module, the cooler is started, a fault alarm signal is issued, and the fault information is recorded. Through the effective operation of the actuator module, it can be ensured that the refrigeration thermostatic bath operates stably and efficiently under various working conditions to meet the user's temperature control needs.

[0071] In particular, the system monitoring module 340 is used to remotely monitor the IoT control system and issue early warnings for faults. That is, through the Internet or a local area network, the user can remotely monitor the system at any location. In one example, a threshold is set to monitor the system status in real time. When the parameter exceeds the threshold, it is displayed that an abnormality or potential fault is detected, and an early warning is issued immediately, which can improve the flexibility and efficiency of management.

[0072] As described above, the Internet of Things control system 300 according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with an Internet of Things control algorithm. In a possible implementation, the Internet of Things control system 300 according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the Internet of Things control system 300 can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the Internet of Things control system 300 can also be one of the many hardware modules of the wireless terminal.

[0073] Alternatively, in another example, the Internet of Things control system 300 and the wireless terminal may also be separate devices, and the Internet of Things control system 300 may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0074] Furthermore, a method for controlling an Internet of Things is also provided.

[0075] Figure 5 FIG. 1 is a flow chart of an Internet of Things control method according to an embodiment of the present application. Figure 5As shown, the Internet of Things control method according to the embodiment of the present application includes the following steps: S1, obtaining a time queue of the temperature data inside the refrigeration thermostatic bath collected by a temperature sensor, and performing timing information transmission aggregation analysis and prediction on the time queue of the temperature data inside the refrigeration thermostatic bath to obtain real-time temperature data; S2, setting a user interface for mode selection, parameter adjustment and fault prompt; S3, receiving the real-time temperature data and the control signal sent by the user interface, and performing control actions based on the real-time temperature data and the control signal; S4, remotely monitoring the Internet of Things control system and issuing early warnings for faults.

[0076] In summary, the Internet of Things control method according to the embodiment of the present application is explained, which collects the temperature data inside the refrigeration thermostatic bath in real time through the temperature sensor, and introduces the data processing and analysis algorithm based on artificial intelligence and deep learning in the back end to perform time series analysis on the temperature data, and then uses the contribution of the pseudo anchor center to perform feature filtering on the local time series characteristics of the temperature inside the refrigeration thermostatic bath, and at the same time, the local time series information aggregation and reasoning of the temperature inside the thermostatic bath are performed through the spatiotemporal transmission information of the local time series of the temperature, so as to predict the real-time temperature data. Then, by transmitting the predicted real-time temperature data to the actuator module, the actuator module performs the corresponding action based on the real-time temperature data and the control signal, and realizes the intelligent control of the Internet of Things. In this way, the influence of irrelevant noise interference of the temperature time series can be reduced by feature filtering, and the time series information aggregation and reasoning of the temperature inside the thermostatic bath are performed by the spatiotemporal transmission method of the local time series semantics of the temperature, so as to more accurately predict the real-time temperature data inside the thermostatic bath. This intelligent prediction method improves the generalization ability of the system, so that the Internet of Things control system can better adapt to new situations, so as to perform control actions more timely and effectively.

[0077] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An Internet of Things control system, characterized in that: include: A temperature acquisition prediction module is used to obtain a time queue of temperature data inside the refrigeration thermostatic bath collected by a temperature sensor, and perform time series information transmission aggregation analysis and prediction on the time queue of temperature data inside the refrigeration thermostatic bath to obtain real-time temperature data; A user interface setting module, used to set the user interface for mode selection, parameter adjustment and fault prompt; an actuator module, configured to receive the real-time temperature data and a control signal sent by the user interface, and to perform a control action based on the real-time temperature data and the control signal; A system monitoring module, used to remotely monitor the IoT control system and issue early warnings for faults; Among them, the temperature acquisition prediction module includes: a temperature time series data encoding unit, which is used to standardize the time queue of the temperature data inside the refrigeration thermostatic bath and then perform temperature sequence encoding to obtain a sequence of local time series correlation characteristics of the temperature inside the thermostatic bath; a temperature local time series information transmission aggregation representation unit, which is used to perform information transmission aggregation representation on the sequence of local time series correlation characteristics of the temperature inside the thermostatic bath to obtain a time series information propagation aggregation representation of the temperature inside the thermostatic bath; a real-time temperature data prediction unit, which is used to determine the real-time temperature data based on the time series information propagation aggregation representation of the temperature inside the thermostatic bath.

2. The Internet of Things control system according to claim 1, characterized in that: The temperature local time series information transmission aggregation representation unit includes: A thermostatic bath internal temperature local time series correlation feature extraction subunit, used to extract a sequence of current thermostatic bath internal temperature local time series correlation features and a sequence of historical thermostatic bath internal temperature local time series correlation features from the sequence of the thermostatic bath internal temperature local time series correlation features; The thermostatic bath internal temperature dynamic energy spatiotemporal transfer weight calculation subunit is used to calculate the sequence of the thermostatic bath internal temperature dynamic energy spatiotemporal transfer weights of the sequence of the historical thermostatic bath internal temperature local time series correlation characteristics relative to the sequence of the current thermostatic bath internal temperature local time series correlation characteristics; The node feature transfer fusion subunit is used to perform node feature transfer fusion on the sequence of local time series correlation features of the internal temperature of the thermostatic bath based on the sequence of dynamic energy spatiotemporal transfer weights of the internal temperature of the thermostatic bath to obtain an aggregated representation of the internal temperature time series information propagation of the thermostatic bath.

3. The Internet of Things control system according to claim 2, characterized in that: The temperature time series data encoding unit comprises: A standardization subunit, used for standardizing the time queue of the temperature data inside the thermostatic bath to obtain a time queue of standardized temperature data inside the thermostatic bath; A temperature sequence encoding subunit, used for inputting the time queue of the standardized temperature data inside the thermostatic bath into a temperature sequence encoder based on a 1D-CNN model to obtain a sequence of local time series correlation feature vectors of the temperature inside the thermostatic bath; The feature filtering subunit is used to perform feature filtering processing on the sequence of the local time series correlation feature vectors of the internal temperature of the thermostatic bath based on the central contribution to obtain a sequence of filtered local time series correlation feature vectors of the internal temperature of the thermostatic bath as the sequence of local time series correlation features of the internal temperature of the thermostatic bath.

4. The Internet of Things control system according to claim 3, characterized in that: The feature filtering subunit comprises: A cluster analysis secondary subunit, used for performing cluster analysis on the sequence of the local time series associated feature vectors of the internal temperature of the thermostatic bath to obtain a cluster center representation vector of the local time series of the internal temperature of the thermostatic bath; The semantic contribution calculation secondary subunit is used to calculate the semantic contribution of each thermostat internal temperature local time series associated feature vector in the sequence of the thermostat internal temperature local time series associated feature vector relative to the thermostat internal temperature local time series cluster center representation vector to obtain a sequence of masked sparse thermostat internal temperature local time series contribution representation matrices; The feature modulation secondary subunit is used to use each masked sparse thermostatic bath internal temperature local timing contribution degree representation matrix in the sequence of the masked sparse thermostatic bath internal temperature local timing contribution degree representation matrix as a modulation matrix, and calculate the matrix product between it and each thermostatic bath internal temperature local timing associated feature vector to obtain the sequence of filtered thermostatic bath internal temperature local timing associated feature vectors.

5. The Internet of Things control system according to claim 4, characterized in that: The semantic contribution calculation secondary subunit is used to: The cluster center representation vector of the local time series of the temperature inside the thermostat is used as a pseudo anchor center, and the semantic contribution representation matrix of each local time series associated feature vector of the temperature inside the thermostat in the sequence of the local time series associated feature vector of the temperature inside the thermostat is calculated relative to the pseudo anchor center to obtain a sequence of the local time series contribution representation matrices of the temperature inside the thermostat; A random deactivation process is performed on each thermostatic bath internal temperature local time series contribution degree representation matrix in the sequence of the thermostatic bath internal temperature local time series contribution degree representation matrix to obtain the sequence of the mask sparse thermostatic bath internal temperature local time series contribution degree representation matrix.

6. The Internet of Things control system according to claim 5, characterized in that: The thermostatic bath internal temperature local time series association feature extraction subunit is used to: extract the current filtered thermostatic bath internal temperature local time series association feature vector from the sequence of filtered thermostatic bath internal temperature local time series association feature vectors as the current thermostatic bath internal temperature local time series association feature, and define other filtered thermostatic bath internal temperature local time series association feature vectors in the sequence of filtered thermostatic bath internal temperature local time series association feature vectors as historical filtered thermostatic bath internal temperature local time series association feature vectors to obtain a sequence of historical filtered thermostatic bath internal temperature local time series association feature vectors as the sequence of historical thermostatic bath internal temperature local time series association features.

7. The Internet of Things control system according to claim 6, characterized in that: The thermostatic bath internal temperature dynamic energy spatiotemporal transfer weight calculation subunit is used to: Calculating the static energy value of the local time series of the internal temperature of the thermostatic bath of each historical filtered local time series associated feature vector in the sequence of the local time series associated feature vectors of the internal temperature of the thermostatic bath after historical filtering; Determine the spatial attenuation factor of the local time series energy of the internal temperature of the thermostatic bath based on the spatial span coefficient between the local time series correlation feature vectors of the internal temperature of the thermostatic bath after each historical filtering and the local time series correlation feature vector of the internal temperature of the thermostatic bath after the current filtering; Determine the energy time decay factor of the local time series of the internal temperature of the thermostatic bath based on the time span coefficient between the local time series correlation feature vectors of the internal temperature of the thermostatic bath after each historical filtering and the local time series correlation feature vector of the internal temperature of the thermostatic bath after the current filtering; Based on the spatial attenuation factor of the local time series energy of the constant temperature bath internal temperature and the temporal attenuation factor of the local time series energy of the constant temperature bath internal temperature, the local time series static energy value of the constant temperature bath internal temperature of each of the historical filtered local time series associated feature vectors of the constant temperature bath internal temperature is subjected to spatiotemporal modulation to obtain the spatiotemporal transfer value of the local time series dynamic energy of the constant temperature bath internal temperature of each of the historical filtered local time series associated feature vectors of the constant temperature bath internal temperature relative to the currently filtered local time series associated feature vector of the constant temperature bath internal temperature; The local temporal dynamic energy spatiotemporal transfer value of the internal temperature of the constant temperature bath of the local temporal correlation feature vector after each historical filtering is input into the energy transfer gating module based on the mask function to obtain a sequence of the local temporal dynamic energy spatiotemporal transfer weights of the internal temperature of the constant temperature bath.

8. The Internet of Things control system according to claim 7, characterized in that: The node feature transfer fusion subunit is used to: Based on the sequence of the spatiotemporal transfer weights of the local time series dynamic energy of the internal temperature of the thermostatic bath, the weighted sum of the sequence of the local time series associated feature vectors of the internal temperature of the thermostatic bath after historical filtering is calculated to obtain the node feature transfer aggregation modulation vector of the local time series node feature transfer of the internal temperature of the thermostatic bath after historical filtering; Calculate the positional sum of the local time series node feature transfer aggregation modulation vector of the internal temperature of the thermostatic bath after historical filtering and the local time series associated feature vector of the internal temperature of the thermostatic bath after current filtering to obtain the spatiotemporal significant propagation aggregation representation vector of the internal temperature of the thermostatic bath as the aggregation representation of the internal temperature time series information propagation of the thermostatic bath.

9. The Internet of Things control system according to claim 8, characterized in that: The real-time temperature data prediction unit is used to input the spatiotemporal significant propagation aggregation representation vector of the internal temperature of the thermostatic bath into a decoder-based temperature predictor to obtain a decoded value of the real-time temperature data.

10. A method for controlling the Internet of Things, characterized in that: include: Acquire a time queue of temperature data inside the refrigeration thermostatic bath collected by a temperature sensor, and perform time series information transmission aggregation analysis and prediction on the time queue of temperature data inside the refrigeration thermostatic bath to obtain real-time temperature data; Set up the user interface for mode selection, parameter adjustment and fault prompts; receiving the real-time temperature data and a control signal sent by the user interface, and performing a control action based on the real-time temperature data and the control signal; Remotely monitor the Internet of Things control system and provide early warning of faults.

Images