Distributed intelligent equipment integrated conversion system and control method thereof

Abstract

The invention relates to the technical field of distributed intelligent equipment, in particular to a distributed intelligent equipment integrated conversion system and a control method thereof.The distributed intelligent equipment integrated conversion system comprises a distributed architecture composed of a plurality of child nodes and one or more master control nodes, and the distributed architecture is integrated in each child node; the device integration module is used for connecting and managing intelligent devices in a region, the data conversion module is integrated in each child node and used for converting various data formats of the intelligent devices into standard data formats recognized by a system, and the data conversion module is communicated with the master control node. The distributed intelligent device integration conversion system comprises a central control system, a plurality of sub-nodes used for receiving data, an intelligent control module used for according to a preset rule or a user instruction, an edge calculation module integrated in the sub-nodes and responsible for locally processing part of data, and a central control system integrated in the central control system. The problems of data compatibility, delay and heat dissipation management in the prior art are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed intelligent devices, and in particular to a distributed intelligent device integrated conversion system and a control method thereof. Background Art

[0002] With the rapid development of Internet of Things technology, a variety of smart devices are integrated into smart home systems, such as smart bulbs, smart sockets, smart thermostats, security cameras, and smart door locks. Although these devices have improved user convenience, unified device management and control still face challenges due to differences in data formats, communication protocols, and control logic among different devices.

[0003] Although the traditional centralized control architecture can achieve a certain degree of intelligent device integration, there is a risk of single point failure. When multiple devices send control signals at the same time, the processing load of the central control system increases significantly, which may cause system response delays or performance degradation. In addition, the heat dissipation management problem under high-load work has gradually become prominent, especially when processing multiple signals. The central control system needs a more efficient heat dissipation solution. Therefore, a distributed intelligent device integrated conversion system and its control method are proposed to address the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a distributed intelligent device integrated conversion system and a control method thereof, so as to solve the problem that although the traditional centralized control architecture can achieve a certain degree of intelligent device integration, there is a risk of single point failure, and when multiple devices send control signals at the same time, the processing load of the central control system increases significantly, which may cause system response delays or performance degradation.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A distributed intelligent device integrated conversion system and control method thereof, comprising a distributed architecture consisting of a plurality of sub-nodes and one or more master control nodes, a device integration module integrated in each sub-node for connecting and managing intelligent devices in a region, a data conversion module integrated in each sub-node for converting a plurality of data formats of intelligent devices into a standard data format recognized by the system, an intelligent control module communicating with the master control node for processing according to preset rules or user instructions, an edge computing module integrated in the sub-node for processing part of the data locally, and a heat dissipation management module integrated in the central control system for dynamically determining whether a heat dissipation fan needs to intervene by predicting the number of future signal receptions in real time;

[0007] The heat dissipation management module predicts the signal quantity by capturing the time dependency and correlation of the signal reception data. The time dependency is used to generate a hidden state vector and a memory unit. The calculation formula of the hidden state vector is:

[0008] i t =σ(W i ·[h t-1 , X t ]+b i )

[0009] f t =σ(W f ·[h t-1 , X t ]+b f )

[0010] o t =σ(W o ·[h t-1 , X t ]+b o )

[0011]

[0012] h t =o t tanh(C t )

[0013] Where: i t 、f t , o t are the state vectors of the input gate, forget gate, and output gate, respectively. is a candidate memory unit, C t is the memory cell state at the current time step, h t is the hidden state vector of the current time step, X t Receive data for input historical signals;

[0014] The generated hidden state h t The hidden state of the previous step focuses on the relevant time step. The specific algorithm is:

[0015]

[0016] Where: Score the attention weights for the time step, is the normalized attention weight, c t is the attention context vector, h j is the hidden state of the previous step;

[0017] The signal quantity is predicted by the hidden state h t and the attention context vector c t Combined to calculate:

[0018] y t =W y ·[ht ;c t ]+b y

[0019] In the formula, y t is the predicted number of future signal receptions, W y is the weight matrix of the output layer, b y is the bias vector.

[0020] As further optimized content of the present invention, the distributed architecture sub-nodes are responsible for managing the smart devices in their respective areas, and interacting with the main control node for data and executing instructions, the device integration module supports multiple communication protocols and provides a unified data interface, the data conversion module transmits standard data to the main control node or other sub-nodes, the intelligent control module coordinates the control of multiple smart devices, and the heat dissipation management module dynamically determines whether the cooling fan needs to intervene.

[0021] As a further optimized content of the present invention, the data conversion module adopts an adaptive prediction algorithm to adjust the signal conversion logic in real time to improve the conversion efficiency.

[0022] As a further optimized content of the present invention, the data conversion algorithm of the data conversion module is defined as follows:

[0023] Y=f(X)=W2·ρ(W1·X+b1)+b2

[0024] Where: X represents the input data formats, Y is the standard data format after conversion, W1 and W2 are weight matrices, b1 and b2 are bias vectors, and ρ is the activation function.

[0025] As a further optimization of the present invention, the edge computing module pre-processes high-frequency data and dynamically adjusts the heat dissipation strategy in combination with the signal prediction of the heat dissipation management module.

[0026] As a further optimization content of the present invention, the data exchange between the edge computing module and the main control node adopts a distributed cache mechanism.

[0027] As further optimized content of the present invention, the following steps are included: S1: device registration and initialization: the device integration module automatically scans and registers the smart devices in the area, initializes them, and connects to the corresponding sub-nodes;

[0028] S2: Data collection and conversion: The sub-node collects data from the smart device through the data conversion module, converts it into a standard format, and transmits it to the master node;

[0029] S3: Signal prediction and heat dissipation management: The heat dissipation management module analyzes historical data in real time, predicts the number of signals by capturing the time dependency and correlation of signal reception data, and dynamically determines whether the cooling fan is turned on or not.

[0030] As a further optimization of the present invention, the data conversion module uses a distributed cache mechanism and parallel processing technology to distribute frequently occurring signal conversion tasks to different computing nodes.

[0031] As a further optimization of the present invention, the intelligent control module performs collaborative control of multiple smart devices according to preset rules or user instructions, and supports scene control based on time, daylight, environmental sensor data or voice commands.

[0032] As a further optimization of the present invention, the system continuously monitors the operating status of the equipment through a remote management module, and automatically triggers an alarm when a device failure or data abnormality is detected, and attempts to restore the normal state.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. In the present invention, the distributed intelligent device integrated conversion system and control method thereof effectively solve the data compatibility, delay and heat dissipation management problems in the prior art through distributed architecture and multi-level data processing, and can predict the number of signal receptions in the future, and judge whether the cooling fan needs to be intervened, thereby improving the efficiency and effect of the central control system, helping to optimize resource utilization, reduce energy consumption, and ensure that the smart home system can run stably under various conditions. The system can optimize signal processing efficiency and improve the collaborative working ability between devices;

[0035] 2. In the present invention, through the adaptive prediction algorithm, the data conversion module can adjust the signal conversion logic in real time, improve the conversion efficiency, and ensure the accuracy and real-time performance of the data. In addition, the use of distributed caching mechanism and parallel processing technology enables the system to effectively allocate computing resources and process a large number of data conversion tasks, further improving the performance and reliability of the system;

[0036] 3. In the present invention, the intelligent control module can coordinately control multiple smart devices according to preset rules or user instructions, and supports scene control based on time, daylight, environmental sensor data or voice commands, which greatly improves the convenience and comfort of users. The remote management module of the system provides users with continuous equipment status monitoring, and can promptly alarm and attempt to recover when equipment fails or data is abnormal, thereby enhancing the self-diagnosis and self-repair capabilities of the system, optimizing the overall intelligence level of the equipment, and providing users with a more intelligent and automated living environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a control flow chart of a distributed intelligent device integrated conversion system of the present invention. DETAILED DESCRIPTION

[0038] See also Figure 1 , the present invention provides a technical solution:

[0039] A distributed intelligent device integrated conversion system and control method thereof, comprising a distributed architecture consisting of a plurality of sub-nodes and one or more master control nodes, a device integration module integrated in each sub-node for connecting and managing intelligent devices in a region, a data conversion module integrated in each sub-node for converting a plurality of data formats of intelligent devices into a standard data format recognized by the system, an intelligent control module communicating with the master control node for processing according to preset rules or user instructions, an edge computing module integrated in the sub-node for processing part of the data locally, and a heat dissipation management module integrated in the central control system for dynamically determining whether a heat dissipation fan needs to intervene by predicting the number of future signal receptions in real time;

[0040] The heat dissipation management module predicts the signal quantity by capturing the time dependency and correlation of the signal reception data. The time dependency is used to generate the hidden state vector and memory unit. The calculation formula of the hidden state vector is:

[0041] i t =σ(W i ·[h t-1 , X t ]+b i )

[0042] f t =σ(W f ·[h t-1 , X t ]+b f )

[0043] o t =σ(W o ·[h t-1 , X t ]+b o )

[0044]

[0045] h t =o t tanh(C t )

[0046] Where: i t 、f t , o tare the state vectors of the input gate, forget gate, and output gate, respectively. is a candidate memory unit, C t is the memory cell state at the current time step, h t is the hidden state vector of the current time step, X t Receive data for input historical signals;

[0047] Generate hidden state h t The hidden state of the previous step focuses on the relevant time step. The specific algorithm is:

[0048]

[0049] Where: Score the attention weights for the time step, is the normalized attention weight, c t is the attention context vector, h j is the hidden state of the previous step;

[0050] The number of signals is predicted by the hidden state h t and the attention context vector c t Combined to calculate:

[0051] y t =W y ·[h t ;c t ]+b y

[0052] In the formula, y t is the predicted number of future signal receptions, W y is the weight matrix of the output layer, b y is the bias vector.

[0053] As a technical solution for further implementation of this solution, the distributed architecture sub-nodes are responsible for managing the smart devices in their respective areas, and interact with the master node for data and command execution. The device integration module supports multiple communication protocols and provides a unified data interface. The data conversion module transmits standard data to the master node or other sub-nodes. The intelligent control module performs collaborative control of multiple smart devices. The heat dissipation management module dynamically determines whether the heat dissipation fan needs to intervene. Through the above settings, the overall stability of the integrated conversion system during operation can be further improved.

[0054] As a technical solution for further implementation of this solution, the data conversion module adopts an adaptive prediction algorithm to adjust the signal conversion logic in real time to improve the conversion efficiency. The data conversion algorithm of the data conversion module is defined as follows:

[0055] Y=f(X)=W2·ρ(W1·X+b1)+b2In the formula: X represents multiple data formats of input, Y is the standard data format after conversion, W1 and W2 are weight matrices, b1 and b2 are bias vectors, and ρ is the activation function. The above adaptive prediction algorithm can improve the conversion efficiency;

[0056] As a technical solution for further implementation of this solution, the edge computing module pre-processes high-frequency data and dynamically adjusts the heat dissipation strategy in combination with the signal prediction of the heat dissipation management module. Through the above settings, the load of the central control system can be reduced;

[0057] As a technical solution for further implementation of this solution, the data exchange between the edge computing module and the master control node adopts a distributed cache mechanism. Through the above settings, the data processing efficiency is further improved;

[0058] As a technical solution for further implementation of this solution, the following steps are included: S1: Device registration and initialization: the device integration module automatically scans and registers the smart devices in the area, initializes them, and connects to the corresponding sub-nodes;

[0059] S2: Data collection and conversion: The sub-node collects data from the smart device through the data conversion module, converts it into a standard format, and transmits it to the master node;

[0060] S3: Signal prediction and heat dissipation management: The heat dissipation management module analyzes historical data in real time, predicts the number of signals by capturing the time dependency and correlation of signal reception data, and dynamically determines whether the cooling fan is turned on or not.

[0061] As a technical solution for further implementation of this solution, the data conversion module uses a distributed cache mechanism and parallel processing technology to allocate frequently occurring signal conversion tasks to different computing nodes. The above settings can reduce the computing pressure of the central control system;

[0062] As a technical solution for further implementation of this solution, the intelligent control module performs collaborative control of multiple intelligent devices according to preset rules or user instructions, and supports scene control based on time, daylight, environmental sensor data or voice commands. Through the above settings, the overall applicability of the device can be improved;

[0063] As a technical solution for further implementation of this plan, the system continuously monitors the operating status of the equipment through the remote management module. When equipment failure or data abnormality is detected, it automatically triggers an alarm and attempts to restore to normal status, further optimizing the overall intelligence level of the equipment.

[0064] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. The above is only a preferred implementation of the present invention. It should be pointed out that due to the limitations of textual expression and the objective existence of infinite specific structures, ordinary technicians in this technical field can make several improvements, modifications or changes without departing from the principles of the present invention, and can also combine the above technical features in an appropriate manner; these improvements, modifications, changes or combinations, or the direct application of the inventive concept and technical solution to other occasions without improvement, should be regarded as the protection scope of the present invention.

Claims

1. A distributed intelligent device integrated conversion system, characterized in that: It includes a distributed architecture consisting of multiple sub-nodes and one or more master control nodes, a device integration module integrated in each sub-node for connecting and managing smart devices in the area, a data conversion module integrated in each sub-node for converting multiple data formats of smart devices into a standard data format recognized by the system, an intelligent control module that communicates with the master control node and is used according to preset rules or user instructions, an edge computing module integrated in the sub-node responsible for locally processing part of the data, and a heat dissipation management module integrated in the central control system to dynamically determine whether a heat dissipation fan needs to intervene by predicting the number of future signal receptions in real time; The heat dissipation management module predicts the signal quantity by capturing the time dependency and correlation of the signal reception data. The time dependency is used to generate a hidden state vector and a memory unit. The calculation formula of the hidden state vector is: i t =σ(W i ·[h t-1 ,X t ]+b i ) f t =σ(W f ·[h t-1 ,X t ]+b f ) the t =σ(W o ·[h t-1 ,X t ]+b o ) h t =o t ·tanh(C t ) Where: i t 、f t , o t are the state vectors of the input gate, forget gate, and output gate, respectively. is a candidate memory unit, C t is the memory cell state at the current time step, h t is the hidden state vector of the current time step, X t Receive data for input historical signals; The generated hidden state h t The hidden state of the previous step focuses on the relevant time step. The specific algorithm is: Where: Score the attention weights for the time step, is the normalized attention weight, c t is the attention context vector, h j is the hidden state of the previous step; The signal quantity is predicted by the hidden state h t and the attention context vector c t Combined to calculate: y t =W y ·[h t ;c t ]+b y In the formula, y t is the predicted number of future signal receptions, W y is the weight matrix of the output layer, b y is the bias vector.

2. A distributed intelligent device integrated conversion system according to claim 1, characterized in that: The distributed architecture sub-nodes are responsible for managing the smart devices in their respective areas, and interacting with the main control node for data and executing instructions. The device integration module supports multiple communication protocols and provides a unified data interface. The data conversion module transmits standard data to the main control node or other sub-nodes. The intelligent control module coordinates the control of multiple smart devices. The heat dissipation management module dynamically determines whether the cooling fan needs to intervene.

3. A distributed intelligent device integrated conversion system according to claim 1, characterized in that: The data conversion module adopts an adaptive prediction algorithm to adjust the signal conversion logic in real time to improve the conversion efficiency.

4. A distributed intelligent device integrated conversion system according to claim 3, characterized in that: The data conversion algorithm of the data conversion module is defined as follows: Y=f(X)=W2·ρ(W1·X+b1)+b2 Where: X represents the input data formats, Y is the standard data format after conversion, W1 and W2 are weight matrices, b1 and b2 are bias vectors, and ρ is the activation function.

5. A distributed intelligent device integrated conversion system according to claim 1, characterized in that: The edge computing module pre-processes high-frequency data and dynamically adjusts the heat dissipation strategy in combination with the signal prediction of the heat dissipation management module.

6. A distributed intelligent device integrated conversion system according to claim 1, characterized in that: The data exchange between the edge computing module and the master control node adopts a distributed cache mechanism.

7. A control method for a distributed intelligent device integrated conversion system according to any one of claims 1 to 6, characterized in that: The following steps are involved: S1: Device registration and initialization: The device integration module automatically scans and registers the smart devices in the area, initializes them, and connects them to the corresponding sub-nodes; S2: Data collection and conversion: The sub-node collects data from the smart device through the data conversion module, converts it into a standard format, and transmits it to the master node; S3: Signal prediction and heat dissipation management: The heat dissipation management module analyzes historical data in real time, predicts the number of signals by capturing the time dependency and correlation of signal reception data, and dynamically determines whether the cooling fan is turned on or not.

8. The control method of a distributed intelligent device integrated conversion system according to claim 7, characterized in that: The data conversion module uses a distributed cache mechanism and parallel processing technology to distribute frequently occurring signal conversion tasks to different computing nodes.

9. The control method of a distributed intelligent device integrated conversion system according to claim 7, characterized in that: The intelligent control module performs collaborative control of multiple smart devices according to preset rules or user instructions, and supports scene control based on time, daylight, environmental sensor data or voice commands.

10. The control method of a distributed intelligent device integrated conversion system according to claim 7, characterized in that: The system continuously monitors the operating status of the equipment through the remote management module. When a device failure or data anomaly is detected, it automatically triggers an alarm and attempts to restore normal status.

Images