Energy consumption data early warning method, system, equipment and medium based on smart home

Abstract

The present invention relates to the field of energy consumption early warning technology, and in particular to a method, system, device and medium for early warning of energy consumption data based on smart home, including using quantum particle swarm optimization algorithm to construct an optimal smart home system knowledge map based on smart home system information to extract device node characteristics and associated information of the smart home system, and construct a three-dimensional real-scene dynamic model of the smart home system in combination with meteorological information; by inputting indoor environmental parameters, device operating status and user habits in the current use scenario into the three-dimensional real-scene dynamic model, and using quantum response equilibrium game theory to simulate the collaborative game operation between different smart home devices, the optimal energy consumption distribution is obtained; and the actual energy consumption data is warned according to the optimal energy consumption distribution. The smart home energy consumption early warning method proposed by the present invention can better adapt to the dynamic changes of the smart home system, optimize resources and energy consumption, reduce unnecessary energy consumption, and improve the accuracy of early warning.

Description

Technical Field

[0001] The present invention relates to the field of energy consumption early warning technology, and in particular to an energy consumption data early warning method, system, device and medium based on smart home. Background Art

[0002] With the rapid development of science and technology, smart home systems have become an indispensable part of modern life. These smart home systems include various smart devices, such as smart bulbs, smart air conditioners, smart refrigerators, smart TVs, etc. However, with the popularization of smart home devices, smart home systems are becoming more and more complex and need to solve more complex problems. In addition, energy consumption issues are becoming increasingly prominent. Traditional energy consumption warning methods are usually based on statistics, mathematical models and other methods. These methods have problems such as high computational complexity and low efficiency when processing large-scale, high-dimensional data. In addition, traditional warning methods lack consideration of the relationship between smart home devices and cannot fully utilize the synergy between devices for warning. Therefore, in the face of the continuous expansion of the scale of smart home systems and the increasing complexity of data structures, there is an urgent need to provide an early warning method that can effectively warn smart home energy consumption data. Summary of the invention

[0003] The present invention provides an energy consumption data early warning method, system, device and medium based on smart home, and solves the technical problem that the existing smart home early warning method has the problems of high computational complexity and low efficiency, and cannot fully utilize the synergy between devices for early warning.

[0004] In order to solve the above technical problems, the present invention provides an energy consumption data early warning method, system, device and medium based on smart home.

[0005] In a first aspect, the present invention provides an energy consumption data early warning method based on a smart home, the method comprising the following steps:

[0006] Based on the pre-acquired smart home system information, the optimal smart home system knowledge graph is constructed using the quantum particle swarm optimization algorithm, and the device node characteristics and associated information of the smart home system are extracted based on the optimal smart home system knowledge graph;

[0007] According to the device node characteristics and related information of the smart home system, the meteorological information is integrated to build a three-dimensional real-scene dynamic model of the smart home system;

[0008] By inputting indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model, and using quantum response equilibrium game theory to simulate the collaborative game operation process between different smart home devices, the optimal energy consumption distribution is obtained;

[0009] According to the optimal energy consumption distribution, a pre-established energy consumption early warning mechanism is used to warn the actual energy consumption data and generate early warning information.

[0010] In a further embodiment, the step of constructing an optimal smart home system knowledge graph using a quantum particle swarm optimization algorithm based on pre-acquired smart home system information includes:

[0011] According to the pre-acquired smart home system information, determine each node in the smart home system knowledge graph and the relationship between the nodes, and determine the node state parameter of each node; wherein the node includes a concept node and an instance node;

[0012] A group of particles is randomly generated to obtain a quantum particle swarm, and a multi-particle state is initialized for the quantum particle swarm according to the node and node state parameters;

[0013] In each iteration of the quantum particle swarm optimization algorithm, by tracking the individual optimal solution and the global optimal solution, the quantum entanglement degree between quantum particles is calculated, and the quantum entanglement degree between quantum particles is introduced into the quantum revolving gate to update the quantum state of each quantum particle. The weights between each node and the relationship between nodes in the knowledge graph of the smart home system are gradually optimized and adjusted according to the updated quantum state.

[0014] After each iteration, the fitness function is used to evaluate the fitness of each quantum particle, and based on the fitness, the best quantum particle is selected for the next round of iteration. Through multiple iterations, the quantum algorithm is used to evolve the multi-particle state of the search space, and the optimal solution is found by optimizing the objective function. The optimal solution is used as the optimal smart home system knowledge graph.

[0015] In a further embodiment, the calculation process of the quantum entanglement degree between quantum particles is specifically as follows:

[0016] Calculate the quantum state product between any two quantum particles and obtain several product states;

[0017] Calculating density matrix eigenvalues ​​of the product state, and sorting the density matrix eigenvalues ​​to obtain density matrix eigenvalue sorting results, and selecting the largest preset number of density matrix eigenvalues ​​from the density matrix eigenvalue sorting results as target density matrix eigenvalues;

[0018] The target density matrix eigenvalues ​​are used to reconstruct the approximate quantum state of the density matrix, and the entanglement entropy of the approximate quantum state is calculated to obtain the quantum entanglement degree between quantum particles.

[0019] In a further embodiment, the fitness function is specifically:

[0020]

[0021]

[0022] In the formula, Indicates the number of all concept nodes; Indicates the number of all concept nodes used in the smart home system; Indicates the number of all instance nodes; Indicates the number of all instance nodes used by the smart home system; Indicates the number of all relationship nodes; Indicates the number of all relationship nodes used in the smart home system; Indicates the number of all current nodes; Indicates the number of all nodes; Indicates adding The number of nodes that need to be created and updated when a device is installed; Indicates the number of newly created and updated nodes; , , , , Both represent weight parameters.

[0023] In a further implementation scheme, the step of integrating meteorological information into constructing a three-dimensional real-scene dynamic model of the smart home system according to the device node characteristics and associated information of the smart home system includes:

[0024] Use machine learning algorithms to analyze the device node characteristics and associated information of the smart home system to obtain the key feature patterns of the devices;

[0025] Obtain real-time meteorological information and use statistical methods to establish a relationship model between meteorological information and key characteristic patterns of equipment;

[0026] According to the relationship model, a discrete event simulation algorithm is used to simulate the operation behavior of the equipment under different meteorological environments to obtain the equipment operation behavior data;

[0027] A three-dimensional real-life dynamic model of the smart home system is constructed based on the device operation behavior data.

[0028] In a further implementation scheme, the step of obtaining the optimal energy consumption distribution by inputting indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model and simulating the collaborative game operation process between different smart home devices using quantum response equilibrium game theory includes:

[0029] Define the state space, action space and reward function of smart home devices based on the indoor environment parameters, device operation status and user habits in the 3D real-life dynamic model;

[0030] Constructing an A2C network model, wherein the A2C network model includes a policy network and a value function network, wherein the policy network is used to output a probability distribution of actions, and the value function network is used to estimate a state value;

[0031] The three-dimensional real-scene dynamic model is used to simulate the interaction between the smart home device and the environment in the current usage scenario. After the smart home device performs an action, the state change data of the smart home device is obtained, and the A2C network model is updated using the state change data of the smart home device. By continuously iteratively updating the network parameters, the individual energy consumption of each smart home device in the current usage scenario is learned;

[0032] Map the individual energy consumption of each smart home device to the state space of qubits and initialize a preset number of qubits for each smart home device;

[0033] According to the quantum response equilibrium game theory, quantum gates are used to simulate the collaborative game process between different smart home devices between quantum bits, and the optimal game strategy and energy consumption distribution between each smart home device are calculated. The optimal game strategy and energy consumption distribution between each smart home device are fed back to the A2C network model, so that the A2C network model optimizes the individual energy consumption of each smart home device according to the optimal game strategy and energy consumption distribution between each smart home device to obtain the optimal energy consumption distribution.

[0034] In a further implementation scheme, the energy consumption early warning mechanism is specifically:

[0035] The optimal energy consumption distribution within a preset time period is analyzed using a time series analysis algorithm to obtain the optimal energy consumption distribution change trend;

[0036] According to the changing trend of the optimal energy consumption distribution, the preset difference threshold is dynamically adjusted using the adaptive threshold algorithm to obtain a dynamic difference threshold, and the actual energy consumption data obtained is compared with the optimal energy consumption distribution to obtain the energy consumption difference;

[0037] The energy consumption difference is compared with the dynamic difference threshold, and if the energy consumption difference is higher than the dynamic difference threshold, a warning message is generated.

[0038] In a second aspect, the present invention provides an energy consumption data early warning system based on a smart home, the system comprising:

[0039] A knowledge graph construction module is used to construct an optimal smart home system knowledge graph based on pre-acquired smart home system information using a quantum particle swarm optimization algorithm, and extract device node characteristics and associated information of the smart home system based on the optimal smart home system knowledge graph;

[0040] A three-dimensional model building module is used to build a three-dimensional real-scene dynamic model of the smart home system based on the device node characteristics and associated information of the smart home system and integrate meteorological information;

[0041] The optimal energy consumption analysis module is used to obtain the optimal energy consumption distribution by inputting indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model, and simulating the collaborative game operation process between different smart home devices using quantum response equilibrium game theory;

[0042] The energy consumption early warning module is used to warn the actual energy consumption data according to the optimal energy consumption distribution using a pre-established energy consumption early warning mechanism to generate early warning information.

[0043] In a third aspect, the present invention further provides a computer device, comprising a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the computer device performs the steps of implementing the above method.

[0044] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0045] The present invention provides a smart home-based energy consumption data early warning method, system, device and medium. The method solves the smart home knowledge graph through a quantum particle swarm optimization algorithm, constructs a three-dimensional real-scene dynamic model of the smart home system according to the device node characteristics and associated information of the smart home knowledge graph, and uses quantum response equilibrium game theory to simulate the collaborative game operation process between different smart home devices to obtain the optimal energy consumption distribution, and warns the actual energy consumption data according to the optimal energy consumption distribution to generate early warning information. Compared with the existing technology, in the face of the continuous expansion of the scale of smart home systems and the increasingly complex data structures, this method uses the quantum particle swarm optimization algorithm to construct the optimal smart home system knowledge graph. It can not only make full use of quantum parallelism to efficiently process the construction and optimization of large-scale knowledge graphs and improve the efficiency of knowledge graph construction, but also can combine the characteristics of the quantum particle swarm optimization algorithm that can quickly adapt to system changes, so that the smart home system knowledge graph optimized by the quantum particle swarm optimization can more comprehensively consider and adapt to the equipment and relationships in the dynamically changing smart home system. By adaptively learning and optimizing the knowledge graph, it can more accurately reflect the association between smart home devices, and convert the association between devices in the smart home knowledge graph and weather information into dynamic association information in the three-dimensional real-life model, so that the subsequent three-dimensional real-life dynamic model can more accurately simulate the operation and energy consumption of smart home devices. At the same time, through the optimization of quantum response equilibrium game theory, the collaborative operation process between different smart home devices is simulated, and resource optimization and energy consumption optimization are further realized, unnecessary energy consumption is reduced, and the accuracy and practicality of early warning are improved, which can more efficiently handle the complexity and real-time requirements of smart home systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic flow chart of an energy consumption data early warning method based on smart home provided by an embodiment of the present invention;

[0047] Figure 2 It is a block diagram of an energy consumption data early warning system based on smart home provided by an embodiment of the present invention;

[0048] Figure 3 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following specifically illustrates the implementation mode of the present invention in conjunction with the accompanying drawings. The embodiments are provided for illustrative purposes only and cannot be understood as limiting the present invention. The accompanying drawings are provided for reference and illustration only and do not constitute a limitation on the scope of patent protection of the present invention, because many changes can be made to the present invention without departing from the spirit and scope of the present invention.

[0050] refer to Figure 1The embodiment of the present invention provides an energy consumption data early warning method based on smart home, such as Figure 1 As shown, the method comprises the following steps:

[0051] S1. Based on the pre-acquired smart home system information, the quantum particle swarm optimization algorithm is used to construct the optimal smart home system knowledge graph, and based on the optimal smart home system knowledge graph, the device node characteristics and related information of the smart home system are extracted.

[0052] In this embodiment, the smart home system information can be collected through sensors or user input, and the smart home system information includes but is not limited to data such as device attributes, functions, usage patterns and historical energy consumption. In order to ensure the accuracy and completeness of the data, the smart home system information can be cleaned and standardized to remove invalid or erroneous data. Since the association relationship between devices in the smart home system is often very complex, including the dependency relationship, control relationship and user needs between different devices, and the devices and user habits in the smart home system will change over time, the quantum particle swarm optimization algorithm (Quantum Particle Swarm Optimization, QPSO) can find the optimal association relationship by searching the solution space, and show more outstanding performance advantages in large-scale and complex data structures. Therefore, in the face of the continuous expansion of the scale of the smart home system and the more complex data structure, in order to improve the real-time and accuracy of the knowledge graph, this embodiment uses the quantum particle swarm optimization algorithm to optimize and update the attributes and relationship strength of each device node in the knowledge graph to adapt to the characteristics of the actual system operation and better ensure the efficiency and accuracy of data processing.

[0053] In this embodiment, the step of constructing an optimal smart home system knowledge graph using a quantum particle swarm optimization algorithm based on pre-acquired smart home system information includes:

[0054] According to the pre-acquired smart home system information, determine each node in the smart home system knowledge graph and the relationship between the nodes, and determine the node state parameter of each node; wherein the node includes a concept node and an instance node;

[0055] A group of particles is randomly generated to obtain a quantum particle swarm, and a multi-particle state is initialized for the quantum particle swarm according to the node and node state parameters;

[0056] In each iteration of the quantum particle swarm optimization algorithm, by tracking the individual optimal solution and the global optimal solution, the quantum entanglement degree between quantum particles is calculated, and the quantum entanglement degree between quantum particles is introduced into the quantum revolving gate to update the quantum state of each quantum particle. The weights between each node and the relationship between nodes in the knowledge graph of the smart home system are gradually optimized and adjusted according to the updated quantum state.

[0057] After each iteration, the fitness function is used to evaluate the fitness of each quantum particle, and based on the fitness, the best quantum particle is selected for the next round of iteration. Through multiple iterations, the quantum algorithm is used to evolve the multi-particle state of the search space, and the optimal solution is found by optimizing the objective function. The optimal solution is used as the optimal smart home system knowledge graph.

[0058] The knowledge graph optimized by the quantum particle swarm optimization algorithm in this embodiment can better adapt to the characteristics that the devices and relationships in the smart home system will change with time and environment. It not only provides a more complete and accurate knowledge representation, but also enhances the dynamic applicability of the system. It can optimize and adjust the characteristics of devices or relationships without changing the entire knowledge graph structure, so that the knowledge graph can quickly respond to changes in the smart home system, better reflect the working principles of the smart home system and the interaction between devices, provide more accurate basic data for the subsequent construction of three-dimensional real-scene models, more accurately simulate the operation of smart home devices and changes in the home environment, and better meet user needs.

[0059] Compared with the traditional quantum particle swarm algorithm which usually uses a single quantum particle state to represent a solution in the search space, this embodiment introduces multi-particle states and entanglement between particles when constructing the smart home knowledge graph using the quantum particle swarm optimization algorithm. This embodiment encodes and updates multiple particle states simultaneously according to the complexity and scale of the system information, which can increase the exploration capability of the search space and improve the global search capability of the algorithm. At the same time, in each quantum state update step, by introducing the quantum entanglement degree between particles and then updating the quantum particles according to the quantum entanglement degree parameter, the information transmission between particles is made more efficient and accurate, thereby improving the search efficiency and accuracy of the algorithm. In this embodiment, the calculation process of the quantum entanglement degree between quantum particles is specifically as follows:

[0060] Calculate the quantum state product between any two quantum particles and obtain several product states;

[0061] Calculating density matrix eigenvalues ​​of the product state, and sorting the density matrix eigenvalues ​​to obtain density matrix eigenvalue sorting results, and selecting the largest preset number of density matrix eigenvalues ​​from the density matrix eigenvalue sorting results as target density matrix eigenvalues;

[0062] The target density matrix eigenvalues ​​are used to reconstruct the approximate quantum state of the density matrix, and the entanglement entropy of the approximate quantum state is calculated to obtain the quantum entanglement degree between quantum particles.

[0063] As a complex intelligent system, the smart home system includes multiple device nodes and a large amount of related information. As the scale of the smart home system continues to expand, a large amount of data and information needs to be processed when constructing the knowledge graph of the smart home system. The quantum particle swarm optimization algorithm mainly uses the collaborative search ability between particles to solve the optimal solution to the problem, and the search ability between particles is limited by the information transmission and influence between each other. Therefore, this embodiment introduces quantum entanglement to adjust and optimize the search behavior between particles, and can better describe and quantify the information transmission and influence between particles, so as to better discover and optimize the related information in the smart home system, and combine the iterative process of the quantum particle swarm optimization algorithm. ,Using quantum revolving gates to update the quantum states of particles can better utilize the advantages of quantum computing, gradually optimize the weights between nodes and the relationships between nodes in the knowledge graph of the smart home system, and ,accelerate the search process and the convergence of the global optimal solution, so as to more effectively construct the optimal ,knowledge graph of the smart home system. ,Compared with the traditional particle swarm algorithm, the quantum particle swarm optimization algorithm can converge to the optimal ,solution faster, therefore, it can more accurately describe the location, function and performance of the device nodes, and ,extract more accurate device node characteristics and associated information in the smart home system. ,These accurate device node characteristics and associated information of the smart home system can ,help build a more accurate three-dimensional real-life dynamic model, making the smart home system more realistic.

[0064] In addition, according to the dynamic change characteristics of the knowledge graph of the smart home system, this embodiment adopts a fitness function to evaluate the quality of each particle state. Through the evaluation of the fitness function, the movement and update process of the particles are guided, the update process of the particle swarm is monitored, and it is determined whether the quantum particle swarm optimization algorithm has converged or reached the preset iteration stop condition. When the quantum particle swarm optimization algorithm converges, the optimal particle state is output as the optimal solution of the knowledge graph of the smart home system. In this embodiment, the fitness function is specifically:

[0065]

[0066]

[0067] In the formula, Indicates the number of all concept nodes; Indicates the number of all concept nodes used in the smart home system; Indicates the number of all instance nodes; Indicates the number of all instance nodes used by the smart home system; Indicates the number of all relationship nodes; Indicates the number of all relationship nodes used in the smart home system; Indicates the number of all current nodes; Indicates the number of all nodes; Indicates adding The number of nodes that need to be created and updated when a device is installed; Indicates the number of newly created and updated nodes; , , , , Both represent weight parameters; Represents the concept coverage contained in the knowledge graph of the smart home system; Indicates the coverage of instance nodes contained in the knowledge graph of the smart home system; Indicates the coverage of the relationship nodes contained in the knowledge graph of the smart home system; Indicates the dynamic nature of the smart home system knowledge graph, that is, the degree to which the smart home system knowledge graph reflects the current usage environment. Since the smart home environment changes frequently, only by updating and adjusting the knowledge graph in a timely manner can it better adapt to the actual situation. Reflecting the real-time and adaptability of the knowledge graph is very important for the smart home system. It should be noted that the current node is defined as:

[0068] For any node v, define Indicates the update time of the node v, Indicates the current time. Indicates the preset time threshold. If , then it means that the node v is in The node v is updated within the time period, and the node v belongs to the current node. In this embodiment, the time threshold can be adjusted according to the update frequency of the smart home system. For example, if the update frequency of the system is low, the time threshold can be set to be larger.

[0069] Taking into account the demand for expansion of the number of devices, this embodiment evaluates the scalability and flexibility of the knowledge graph by evaluating the number of nodes that need to be created and updated when adding devices. This can make the fitness function knowledge graph scalable and adaptable to the smart home system, providing support for the growth and change of the smart home system.

[0070] In summary, the quantum particle swarm optimization algorithm can accurately capture and describe the static association relationship between device nodes, and mine the data similarity and correlation between device nodes in the topological space between smart home devices. In order to enable quantum particles to autonomously adjust their behavior according to the actual environment and needs, this embodiment introduces concept coverage, instance coverage, relationship coverage, dynamics and extended contribution into the fitness function during the execution of the quantum particle swarm optimization algorithm according to the dynamic changes of the actual smart home system information to adaptively adjust the behavior of the quantum particle swarm, which can comprehensively evaluate the quality and performance of the smart home system knowledge graph. At the same time, it enables the smart home early warning method to adapt to the addition of new devices, introduce new particle states or update particle states through extended contributions, adjust the parameters of existing particle states, and timely update and adjust the knowledge graph to better adapt to and respond to changes in the real environment.

[0071] S2. According to the device node characteristics and related information of the smart home system, the meteorological information is integrated to build a three-dimensional real-scene dynamic model of the smart home system.

[0072] In this embodiment, the step of integrating meteorological information into building a three-dimensional real-scene dynamic model of the smart home system according to the device node characteristics and associated information of the smart home system includes:

[0073] Use machine learning algorithms to analyze the device node characteristics and associated information of the smart home system to obtain the key feature patterns of the devices;

[0074] Obtain real-time meteorological information and use statistical methods to establish a relationship model between meteorological information and key characteristic patterns of equipment;

[0075] According to the relationship model, a discrete event simulation algorithm is used to simulate the operation behavior of the equipment under different meteorological environments to obtain the equipment operation behavior data;

[0076] A three-dimensional real-life dynamic model of the smart home system is constructed based on the device operation behavior data.

[0077] This embodiment correlates the device node characteristics and associated information with meteorological information and establishes a model to predict the operating behavior of the device. It can capture the impact of different meteorological environments on device behavior and provide data-driven predictions, thereby creating a highly realistic and practical three-dimensional real-scene model.

[0078] S3. By inputting the indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model, and using quantum response equilibrium game theory to simulate the collaborative game operation process between different smart home devices, the optimal energy consumption distribution is obtained.

[0079] Advantage Actor-Critic (A2C) is a reinforcement learning algorithm that combines advantage function and policy gradient. Quantum response equilibrium game theory is based on the concept of quantum mechanics. By encoding the strategies of participants into the form of quantum bits and using quantum gate operations to realize the interaction between participants, this embodiment combines the A2C algorithm with the quantum response equilibrium game theory to realize the coordinated optimization of energy consumption distribution of smart home devices. In this embodiment, the indoor environmental parameters, device operation status and user habits in the current usage scenario are input into the three-dimensional real-scene dynamic model, and then the A2C algorithm is used to optimize the individual energy consumption of smart home devices, so that the smart home devices can dynamically adjust the energy consumption according to the current environmental conditions. The obtained individual energy consumption of the smart home devices is then used as the strategy in the quantum response equilibrium game theory and encoded into quantum bits. Then, the interaction between devices is realized by quantum gate operations. Through the operation of the quantum response equilibrium game theory, the optimal game strategy and energy consumption distribution between the smart home devices are obtained, and they are fed back to the A2C algorithm for more accurate optimization of the individual energy consumption of smart home devices. In this way, while maximizing the efficiency of the device, energy waste is minimized.

[0080] In this embodiment, the step of obtaining the optimal energy consumption distribution by inputting indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model and simulating the collaborative game operation process between different smart home devices using quantum response equilibrium game theory includes:

[0081] According to the indoor environmental parameters, equipment operation status and user habits in the three-dimensional real-life dynamic model, the state space, action space and reward function of the smart home equipment are defined; the state space can include indoor environmental parameters such as temperature, humidity, and light, as well as the current operation status of the equipment, such as: light switch status, electrical power, etc.; the action space defines the operations that the equipment can take, such as: adjusting the brightness of the light, adjusting the temperature of the air conditioner and other equipment energy consumption adjustment operations; the reward function can be designed according to the energy consumption goals and user needs of the smart home equipment to guide the intelligent agent to optimize energy consumption; the indoor environmental parameters can be used to make corresponding adjustments to different temperatures in different rooms, and the indoor environmental parameters can include data such as the number of people in the room and the indoor temperature;

[0082] Constructing an A2C network model, wherein the A2C network model includes a policy network and a value function network, wherein the policy network is used to output a probability distribution of actions, and the value function network is used to estimate a state value;

[0083] The three-dimensional real-scene dynamic model is used to simulate the interaction between the smart home device and the environment in the current usage scenario. After the smart home device performs an action, the state change data of the smart home device is obtained, and the A2C network model is updated by using the state change data of the smart home device. The network parameters are continuously updated iteratively to optimize the policy network and the value function network, and the individual energy consumption of each smart home device in the current usage scenario is learned;

[0084] The individual energy consumption of each smart home device is mapped to the state space of the quantum bit, and a preset number of quantum bits are initialized for each smart home device. In this embodiment, the individual energy consumption of each smart home device can be represented as a quantum bit state or a probability distribution vector, and these quantum bit states or probability distribution vectors are encoded in the form of quantum bits, and mapped to the state space of the quantum bit through a conversion algorithm to ensure that the information represented by the energy consumption can be represented in quantum computing, and then a corresponding number of quantum bits are initialized for each device and set to an initial state.

[0085] According to the quantum response equilibrium game theory, quantum gates are used to simulate the collaborative game process between different smart home devices between quantum bits, and the optimal game strategy and energy consumption distribution between each smart home device are calculated. The optimal game strategy and energy consumption distribution between each smart home device are fed back to the A2C network model, so that the A2C network model optimizes the individual energy consumption of each smart home device according to the optimal game strategy and energy consumption distribution between each smart home device, thereby achieving the optimal allocation of the overall energy consumption and obtaining the optimal energy consumption distribution.

[0086] Since the A2C network model has relatively good performance when the environmental model is unknown or complex, the present embodiment adopts the A2C algorithm to learn the optimal strategy through interaction with the environment, and can adaptively adjust individual energy consumption in an unknown or complex environment, so as to better adapt to the actual situation. At the same time, the present embodiment uses the individual energy consumption of smart home devices as the strategy in the quantum response equilibrium game theory, and calculates and computes the game process through the quantum response equilibrium game theory to obtain the optimal game strategy and energy consumption distribution between each smart home device. The obtained optimal game strategy and energy consumption distribution can be fed back to the A2C algorithm by using optimization methods such as gradient descent, and the energy consumption is further optimized by updating the parameters of the A2C network, so as to realize the coordinated optimization of energy consumption distribution between smart home devices, so that the overall energy consumption of the system is optimized and energy utilization is more efficient. Moreover, the nature of quantum computing can better cope with the complex interaction and optimization problems between smart home devices, so that the smart home energy consumption warning method can provide better performance and adaptability in an unknown or complex environment, and bring a more energy-saving life experience to users.

[0087] It should be noted that the quantum particle swarm optimization algorithm is used to analyze the linear relationship between static devices and cannot handle the collaborative operation process involved in real-time interaction between devices. However, in the smart home system, there are complex interactions and influences between devices. Therefore, this embodiment adopts quantum response equilibrium game theory to describe the nonlinear relationship in the dynamic system. The combination of static and dynamic can better optimize the efficiency and performance of the entire smart home system. In this embodiment, the quantum response equilibrium game theory can help better coordinate the operation of different smart home devices by considering the interactions and influences between smart home device nodes to minimize the cost function of the overall system.

[0088] S4. Based on the optimal energy consumption distribution, use the pre-established energy consumption warning mechanism to warn the actual energy consumption data and generate warning information.

[0089] Since the energy consumption distribution will change with the change of time and environmental factors, this embodiment adopts an adaptive adjustment algorithm to dynamically adjust the warning threshold according to the current energy consumption distribution. The energy consumption warning mechanism is specifically as follows:

[0090] The optimal energy consumption distribution within a preset time period is analyzed using a time series analysis algorithm to obtain the optimal energy consumption distribution change trend;

[0091] According to the changing trend of the optimal energy consumption distribution, the preset difference threshold is dynamically adjusted using the adaptive threshold algorithm to obtain a dynamic difference threshold, and the actual energy consumption data obtained is compared with the optimal energy consumption distribution to obtain the energy consumption difference;

[0092] The energy consumption difference is compared with the dynamic difference threshold, and if the energy consumption difference is higher than the dynamic difference threshold, a warning message is generated.

[0093] Compared with traditional energy consumption warning methods that are usually based on fixed thresholds and cannot be dynamically adjusted according to the user's actual energy consumption and habits, resulting in low warning accuracy, this embodiment adopts an adaptive adjustment algorithm to dynamically adjust the warning threshold according to the current energy consumption distribution, so that the warning mechanism has autonomous learning capabilities and can better adapt to real-time energy consumption distribution changes to improve the accuracy, adaptability and timeliness of the warning, avoiding the risks of inaccuracy and false alarms brought about by a single fixed threshold, so that the system can maintain high accuracy while avoiding the risk of missing abnormal situations due to excessively high thresholds, reducing false alarm rates and improving user experience.

[0094] An embodiment of the present invention provides an energy consumption data warning method based on smart home. The method solves the smart home knowledge graph through a quantum particle swarm optimization algorithm, extracts the device node characteristics and related information of the smart home system, and constructs a three-dimensional real-scene dynamic model of the smart home system. By inputting indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model, and using quantum response equilibrium game theory to simulate the collaborative game operation process between different smart home devices, the optimal energy consumption distribution is obtained, and the energy consumption warning mechanism is used to warn the actual energy consumption data to generate warning information. Compared with the existing early warning methods, this embodiment adopts the quantum particle swarm optimization algorithm to construct and update the knowledge graph, which can quickly adapt to system changes and can efficiently handle larger-scale knowledge graph construction; at the same time, the quantum particle swarm optimization algorithm introduces multi-particle state representation and quantum entanglement and other mechanisms, which can more efficiently handle the complexity and real-time requirements of the smart home system. Moreover, when solving the optimal energy consumption distribution, this embodiment combines the A2C algorithm with the quantum response equilibrium game theory to coordinately optimize the energy consumption distribution among smart home devices, which maximizes the performance of the equipment while minimizing energy waste, thereby improving the efficient energy consumption management of the smart home system, and has a good application prospect in the field of smart home.

[0095] It should be noted that the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0096] In one embodiment, Figure 2 As shown, an embodiment of the present invention provides an energy consumption data early warning system based on a smart home, the system comprising:

[0097] The knowledge graph construction module 101 is used to construct an optimal smart home system knowledge graph based on the pre-acquired smart home system information using a quantum particle swarm optimization algorithm, and extract device node characteristics and associated information of the smart home system based on the optimal smart home system knowledge graph;

[0098] A three-dimensional model building module 102 is used to build a three-dimensional real-scene dynamic model of the smart home system based on the device node characteristics and associated information of the smart home system and integrate meteorological information;

[0099] The optimal energy consumption analysis module 103 is used to obtain the optimal energy consumption distribution by inputting indoor environmental parameters, device operation status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model, and simulating the collaborative game operation process between different smart home devices using quantum response equilibrium game theory;

[0100] The energy consumption warning module 104 is used to warn the actual energy consumption data according to the optimal energy consumption distribution using a pre-established energy consumption warning mechanism to generate warning information.

[0101] For the specific definition of an energy consumption data early warning system based on smart home, please refer to the above-mentioned definition of an energy consumption data early warning method based on smart home, which will not be repeated here. A person of ordinary skill in the art can appreciate that the various modules and steps described in conjunction with the embodiments disclosed in this application can be implemented in hardware, software, or a combination of both. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0102] The embodiment of the present invention provides an energy consumption data early warning system based on smart home, the system adopts a knowledge graph construction module to use a quantum particle swarm optimization algorithm to construct an optimal smart home system knowledge graph; adopts a three-dimensional model construction module to construct a three-dimensional real-life dynamic model of the smart home system; adopts an optimal energy consumption analysis module to combine the A2C algorithm and the quantum response equilibrium game theory, and apply them to the collaborative game process between smart home devices to obtain the optimal energy consumption distribution; and adopts an energy consumption early warning module to warn the actual energy consumption data and generate early warning information. Compared with the prior art, the present application makes full use of the parallelism and global optimization characteristics of the quantum particle swarm optimization algorithm to adaptively learn and optimize the knowledge graph, quickly adapt to the changes of smart home devices, and at the same time applies the quantum response equilibrium game theory to the collaborative game between smart home devices, and feeds back the obtained optimal game strategy and energy consumption distribution to the A2C algorithm, so as to realize the collaborative optimization of energy consumption distribution between smart home devices, and improve the efficient energy consumption management and optimization of the smart home system.

[0103] Figure 3 A computer device provided by an embodiment of the present invention includes a memory, a processor and a transceiver, which are connected via a bus; the memory is used to store a set of computer program instructions and data, and can transmit the stored data to the processor, and the processor can execute the program instructions stored in the memory to perform the steps of the above method.

[0104] The memory may include a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories; the processor may be a central processing unit, a microprocessor, an application-specific integrated circuit, a programmable logic device, or a combination thereof. By way of example but not limitation, the programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0105] Additionally, the memory may be a physically separate unit or may be integrated with the processor.

[0106] It can be understood by those skilled in the art that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.

[0107] In one embodiment, the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0108] The embodiment of the present invention provides an energy consumption data early warning method, system, device and medium based on smart home. The energy consumption data early warning method based on smart home adopts quantum particle swarm optimization algorithm to construct an optimal smart home system knowledge graph that can adapt to the dynamically changing system environment and needs, so that quantum particles can autonomously adjust their behavior according to the actual environment and needs; at the same time, quantum response equilibrium game theory is adopted to simulate the collaborative game operation process between different smart home devices in a three-dimensional real-scene dynamic model, and the optimal game strategy and energy consumption distribution between each smart home device are obtained, and the optimal energy consumption distribution is fed back to the A2C algorithm to further optimize the individual energy consumption of the smart home device to obtain the optimal energy consumption distribution, thereby realizing the energy consumption data analysis and early warning functions of the smart home system, which can help smart home users better manage energy consumption, thereby achieving the purpose of energy saving and emission reduction.

[0109] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., an SSD), etc.

[0110] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0111] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A method for early warning of energy consumption data based on smart home, characterized in that: The following steps are involved: Based on the pre-acquired smart home system information, the optimal smart home system knowledge graph is constructed using the quantum particle swarm optimization algorithm, and the device node characteristics and associated information of the smart home system are extracted based on the optimal smart home system knowledge graph; According to the device node characteristics and related information of the smart home system, the meteorological information is integrated to build a three-dimensional real-scene dynamic model of the smart home system; By inputting indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model, and using quantum response equilibrium game theory to simulate the collaborative game operation process between different smart home devices, the optimal energy consumption distribution is obtained; According to the optimal energy consumption distribution, a pre-established energy consumption early warning mechanism is used to warn the actual energy consumption data and generate early warning information; The step of constructing an optimal smart home system knowledge graph using a quantum particle swarm optimization algorithm based on pre-acquired smart home system information includes: According to the pre-acquired smart home system information, determine each node in the smart home system knowledge graph and the relationship between the nodes, and determine the node state parameter of each node; wherein the node includes a concept node and an instance node; A group of particles is randomly generated to obtain a quantum particle swarm, and a multi-particle state is initialized for the quantum particle swarm according to the node and node state parameters; In each iteration of the quantum particle swarm optimization algorithm, by tracking the individual optimal solution and the global optimal solution, the quantum entanglement degree between quantum particles is calculated, and the quantum entanglement degree between quantum particles is introduced into the quantum revolving gate to update the quantum state of each quantum particle. The weights between each node and the relationship between nodes in the knowledge graph of the smart home system are gradually optimized and adjusted according to the updated quantum state. After each iteration, the fitness function is used to evaluate the fitness of each quantum particle, and the best quantum particle is selected for the next round of iteration based on the fitness. Through multiple iterations, the multi-particle state of the search space is evolved using the quantum algorithm, and the optimal solution is found by optimizing the objective function. The optimal solution is used as the optimal smart home system knowledge graph. The step of obtaining the optimal energy consumption distribution by inputting indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model and simulating the collaborative game operation process between different smart home devices using quantum response equilibrium game theory includes: According to the indoor environment parameters, device operation status and user habits in the three-dimensional real-life dynamic model, the state space, action space and reward function of the smart home device are defined; wherein the state space includes the indoor environment parameters and the current operation status of the device; the action space includes the operations taken by the device; the reward function is used to guide the intelligent agent to optimize energy consumption by combining the energy consumption target of the smart home device and the user needs; Constructing an A2C network model, wherein the A2C network model includes a policy network and a value function network, wherein the policy network is used to output a probability distribution of actions, and the value function network is used to estimate a state value; The three-dimensional real-scene dynamic model is used to simulate the interaction between the smart home device and the environment in the current usage scenario. After the smart home device performs an action, the state change data of the smart home device is obtained, and the A2C network model is updated using the state change data of the smart home device. By continuously iteratively updating the network parameters, the individual energy consumption of each smart home device in the current usage scenario is learned; Map the individual energy consumption of each smart home device to the state space of qubits and initialize a preset number of qubits for each smart home device; According to the quantum response equilibrium game theory, quantum gates are used to simulate the collaborative game process between different smart home devices between quantum bits, and the optimal game strategy and energy consumption distribution between each smart home device are calculated. The optimal game strategy and energy consumption distribution between each smart home device are fed back to the A2C network model, so that the A2C network model optimizes the individual energy consumption of each smart home device according to the optimal game strategy and energy consumption distribution between each smart home device to obtain the optimal energy consumption distribution.

2. The energy consumption data early warning method based on smart home as claimed in claim 1 is characterized in that the quantum The calculation process of the quantum entanglement between particles is as follows: Calculate the quantum state product between any two quantum particles and obtain several product states; Calculating density matrix eigenvalues ​​of the product state, and sorting the density matrix eigenvalues ​​to obtain density matrix eigenvalue sorting results, and selecting the largest preset number of density matrix eigenvalues ​​from the density matrix eigenvalue sorting results as target density matrix eigenvalues; The target density matrix eigenvalues ​​are used to reconstruct the approximate quantum state of the density matrix, and the entanglement entropy of the approximate quantum state is calculated to obtain the quantum entanglement degree between quantum particles.

3. The energy consumption data early warning method based on smart home as claimed in claim 1, characterized in that: The fitness function is specifically: In the formula, Indicates the number of all concept nodes; Indicates the number of all concept nodes used in the smart home system; Indicates the number of all instance nodes; Indicates the number of all instance nodes used by the smart home system; Indicates the number of all relationship nodes; Indicates the number of all relationship nodes used in the smart home system; Indicates the number of all current nodes; Indicates the number of all nodes; Indicates adding The number of nodes that need to be created and updated when a device is installed; Indicates the number of newly created and updated nodes; , , , , Both represent weight parameters; The current node is defined as follows: For any node v, define Indicates the update time of the node v, Indicates the current time. Indicates the preset time threshold. If , then it means that the node v is in The node v has been updated within the time, and it belongs to the current node.

4. The energy consumption data early warning method based on smart home according to claim 1, characterized in that: The step of integrating meteorological information into constructing a three-dimensional real-scene dynamic model of the smart home system according to the device node characteristics and associated information of the smart home system comprises: Use machine learning algorithms to analyze the device node characteristics and associated information of the smart home system to obtain the key feature patterns of the devices; Obtain real-time meteorological information and use statistical methods to establish a relationship model between meteorological information and key characteristic patterns of equipment; According to the relationship model, a discrete event simulation algorithm is used to simulate the operation behavior of the equipment under different meteorological environments to obtain the equipment operation behavior data; A three-dimensional real-life dynamic model of the smart home system is constructed based on the device operation behavior data.

5. The energy consumption data early warning method based on smart home according to claim 1, characterized in that: The energy consumption early warning mechanism is specifically as follows: The optimal energy consumption distribution within a preset time period is analyzed using a time series analysis algorithm to obtain the optimal energy consumption distribution change trend; According to the changing trend of the optimal energy consumption distribution, the preset difference threshold is dynamically adjusted using the adaptive threshold algorithm to obtain a dynamic difference threshold, and the actual energy consumption data obtained is compared with the optimal energy consumption distribution to obtain the energy consumption difference; The energy consumption difference is compared with the dynamic difference threshold, and if the energy consumption difference is higher than the dynamic difference threshold, a warning message is generated.

6. An energy consumption data early warning system based on smart home, characterized in that: The system comprises: A knowledge graph construction module is used to construct an optimal smart home system knowledge graph based on pre-acquired smart home system information using a quantum particle swarm optimization algorithm, and extract device node characteristics and associated information of the smart home system based on the optimal smart home system knowledge graph; A three-dimensional model building module is used to build a three-dimensional real-scene dynamic model of the smart home system based on the device node characteristics and associated information of the smart home system and integrate meteorological information; The optimal energy consumption analysis module is used to obtain the optimal energy consumption distribution by inputting indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model, and simulating the collaborative game operation process between different smart home devices using quantum response equilibrium game theory; An energy consumption early warning module is used to warn the actual energy consumption data according to the optimal energy consumption distribution using a pre-established energy consumption early warning mechanism to generate early warning information; The method of constructing an optimal smart home system knowledge graph using a quantum particle swarm optimization algorithm based on the pre-acquired smart home system information specifically includes: According to the pre-acquired smart home system information, determine each node in the smart home system knowledge graph and the relationship between the nodes, and determine the node state parameter of each node; wherein the node includes a concept node and an instance node; A group of particles is randomly generated to obtain a quantum particle swarm, and a multi-particle state is initialized for the quantum particle swarm according to the node and node state parameters; In each iteration of the quantum particle swarm optimization algorithm, by tracking the individual optimal solution and the global optimal solution, the quantum entanglement degree between quantum particles is calculated, and the quantum entanglement degree between quantum particles is introduced into the quantum revolving gate to update the quantum state of each quantum particle. The weights between each node and the relationship between nodes in the knowledge graph of the smart home system are gradually optimized and adjusted according to the updated quantum state. After each iteration, the fitness function is used to evaluate the fitness of each quantum particle, and the best quantum particle is selected for the next round of iteration based on the fitness. Through multiple iterations, the multi-particle state of the search space is evolved using the quantum algorithm, and the optimal solution is found by optimizing the objective function. The optimal solution is used as the optimal smart home system knowledge graph. The optimal energy consumption distribution is obtained by inputting indoor environmental parameters, device operating status and user habits in the current usage scenario into the three-dimensional real-scene dynamic model, and using quantum response equilibrium game theory to simulate the collaborative game operation process between different smart home devices, specifically including: According to the indoor environment parameters, device operation status and user habits in the three-dimensional real-life dynamic model, the state space, action space and reward function of the smart home device are defined; wherein the state space includes the indoor environment parameters and the current operation status of the device; the action space includes the operations taken by the device; the reward function is used to guide the intelligent agent to optimize energy consumption by combining the energy consumption target of the smart home device and the user needs; Constructing an A2C network model, wherein the A2C network model includes a policy network and a value function network, wherein the policy network is used to output a probability distribution of actions, and the value function network is used to estimate a state value; The three-dimensional real-scene dynamic model is used to simulate the interaction between the smart home device and the environment in the current usage scenario. After the smart home device performs an action, the state change data of the smart home device is obtained, and the A2C network model is updated using the state change data of the smart home device. By continuously iteratively updating the network parameters, the individual energy consumption of each smart home device in the current usage scenario is learned; Map the individual energy consumption of each smart home device to the state space of qubits and initialize a preset number of qubits for each smart home device; According to the quantum response equilibrium game theory, quantum gates are used to simulate the collaborative game process between different smart home devices between quantum bits, and the optimal game strategy and energy consumption distribution between each smart home device are calculated. The optimal game strategy and energy consumption distribution between each smart home device are fed back to the A2C network model, so that the A2C network model optimizes the individual energy consumption of each smart home device according to the optimal game strategy and energy consumption distribution between each smart home device to obtain the optimal energy consumption distribution.

7. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the computer device executes the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 5 is implemented.

Images