Distributed building self-organization decision-making method and system based on block chain

Abstract

The invention discloses a distributed building self-organization decision-making method and system based on a block chain, and the method comprises the steps: collecting multi-dimensional operation data and distributed node state data of a building system, generating a decision-making task through an intelligent contract, achieving the collaborative decision-making between nodes through a consensus algorithm, and extracting a target optimization parameter in combination with artificial intelligence. And generating and broadcasting an encrypted self-organizing decision instruction, and performing simulation verification to complete building system optimization. According to the invention, the intelligence, collaboration and safety of building system decision making are improved, and the method has the beneficial effects of fast real-time response, accurate processing and credible data.

Description

Technical Field

[0001] The present invention relates to the field of building intelligent control and blockchain technology, and specifically to a distributed building self-organizing decision-making method and system based on blockchain, which is suitable for decision-making and optimization control in smart building systems. Background Art

[0002] With the development of smart and green buildings, the automation and intelligence levels of building systems are constantly improving. Traditional building control systems typically rely on centralized data processing and decision-making mechanisms, which suffer from uneven distribution of computing resources, low data reliability, and untimely responses. These systems struggle to cope with complex operating environments with multiple scenarios and variables.

[0003] In recent years, blockchain technology, due to its decentralized, tamper-resistant, and traceable characteristics, has been gradually introduced into building information management to improve data security and collaborative efficiency. Simultaneously, the development of artificial intelligence and edge computing technologies has also provided building systems with more powerful data processing and decision-making capabilities. However, existing technologies have yet to develop a self-organizing decision-making mechanism that effectively combines blockchain, artificial intelligence, and distributed node resources, resulting in a lack of scalable and highly reliable building system optimization solutions.

[0004] Therefore, there is an urgent need to provide a technical solution that integrates multi-source data processing, intelligent task allocation, consensus collaboration mechanism and self-organizing optimization control to improve the intelligence level and system autonomy of building system operation. Summary of the Invention

[0005] The purpose of this invention is to provide a distributed building self-organizing decision-making method and system based on blockchain to solve the problems of decision-making centralization, low response efficiency, poor data credibility and insufficient optimization capabilities in existing building systems, realize intelligent task generation, node collaborative consensus, self-organizing optimization control and result feedback driven by multi-source data, and improve the intelligence, coordination and security of building system operation.

[0006] Specifically, according to the present invention, a distributed building self-organization decision-making method based on blockchain is provided, the method comprising:

[0007] When it is detected that the building system initiates a decision request, the multi-dimensional operation data of the building system and the status data of the distributed nodes are obtained; based on the multi-dimensional operation data and the status data, a target decision task is generated through the smart contract in the blockchain network; when it is determined that the distributed nodes reach a decision consensus based on the target decision task and the preset consensus algorithm, the target optimization parameters are extracted according to the multi-dimensional operation data; a self-organizing decision instruction is generated according to the target optimization parameters; the self-organizing decision instruction is simulated and verified according to the multi-dimensional operation data to predict the operating status of the building system after the execution of the self-organizing decision instruction; if the simulation result meets the preset optimization target, the self-organizing decision instruction is broadcast through the blockchain network to execute the building system optimization; otherwise, the self-organizing decision instruction is adjusted and the simulation verification is repeated.

[0008] Furthermore, the step of generating a target decision task through a smart contract in a blockchain network based on the multi-dimensional operation data and the status data includes:

[0009] The multidimensional operation data is standardized to generate a target operation data set in a unified format; the target operation data set is cleaned according to a target noise reduction algorithm, and the cleaned data is feature enhanced to obtain optimized operation data; based on the optimized operation data and the status data, a target decision task is generated through the task allocation logic in the smart contract, wherein the target decision task includes prediction parameters required to support the simulation verification of the self-organizing decision instruction.

[0010] Furthermore, the step of generating a target decision task through task allocation logic in a smart contract based on the optimization operation data and the status data includes:

[0011] Based on the target clustering algorithm, the optimized operation data is classified into scenarios to obtain multiple building operation scenario characteristics; the computing power and trust level of each distributed node are determined according to the status data; and according to the building operation scenario characteristics, the computing power and the trust level, the target decision-making task is generated through the task allocation logic of the smart contract.

[0012] Furthermore, before the step of performing data cleaning on the target running data set according to the target noise reduction algorithm, the step further includes:

[0013] Acquire historical multidimensional operation data and corresponding historical decision result data; generate a data cleaning training sample set based on the historical multidimensional operation data and the historical decision result data; train a target denoising model based on the target machine learning algorithm and the data cleaning training sample set; calculate the loss value between the predicted value and the true value of the target denoising model based on the target loss function, and adjust the parameters of the target denoising model through an optimization algorithm so that the loss value is less than a preset threshold.

[0014] Furthermore, when it is determined that the distributed nodes have reached a decision consensus based on the target decision task and the preset consensus algorithm, the step of extracting target optimization parameters based on the multidimensional operation data includes: according to the target decision task, the task execution results of the distributed nodes are verified for consistency through the preset consensus algorithm; when the verification passes, the multidimensional operation data is semantically analyzed according to the target parameter extraction model in the artificial intelligence module; and the target optimization parameters related to the target decision task are extracted according to the semantic analysis results.

[0015] Furthermore, the step of generating a self-organizing decision instruction based on the target optimization parameters and broadcasting the self-organizing decision instruction through the blockchain network to execute building system optimization includes: generating identification information of the self-organizing decision instruction based on the target optimization parameters; encrypting the self-organizing decision instruction through a smart contract to generate an encrypted decision instruction; broadcasting the encrypted decision instruction through the blockchain network, and executing building system optimization based on the decryption verification results of the distributed nodes.

[0016] Furthermore, after the step of generating a self-organizing decision instruction according to the target optimization parameters and broadcasting the self-organizing decision instruction through the blockchain network to execute the building system optimization, it also includes: obtaining the execution result data of the self-organizing decision instruction; generating a building system optimization effect evaluation report according to the execution result data, the multi-dimensional operation data and the simulation verification results; storing the optimization effect evaluation report in the blockchain network, and opening access rights to distributed nodes according to preset sharing rules.

[0017] Furthermore, after the step of generating a self-organizing decision instruction according to the target optimization parameters and broadcasting the self-organizing decision instruction through the blockchain network to execute the building system optimization, it also includes: when an abnormal operation of the building system is detected, obtaining multi-dimensional operation data under the abnormal scenario; generating an exception handling suggestion based on the multi-dimensional operation data under the abnormal scenario and the historical decision data in the blockchain network; broadcasting the exception handling suggestion to the distributed nodes through the smart contract, and executing the exception handling operation according to the consensus result of the distributed nodes.

[0018] The present invention also provides a distributed building self-organizing decision-making system based on blockchain, the system comprising:

[0019] a data acquisition module configured to acquire multi-dimensional operation data of the building system and status data of the distributed nodes through the data acquisition units of the distributed nodes when detecting a decision request initiated by the building system;

[0020] A task generation module is configured to generate the target decision task through a smart contract in the blockchain network based on the multi-dimensional operation data and the status data;

[0021] a parameter extraction module configured to extract target optimization parameters from the multidimensional operation data through the artificial intelligence module when it is determined that the distributed nodes reach a decision consensus based on the target decision task and the preset consensus algorithm;

[0022] A decision execution module is configured to generate a self-organizing decision instruction based on the target optimization parameters, and simulate and verify the self-organizing decision instruction based on the multi-dimensional operation data to predict the operating state of the building system after executing the self-organizing decision instruction; if the simulation result meets the preset optimization target, the self-organizing decision instruction is broadcast through the blockchain network to execute the building system optimization; otherwise, the self-organizing decision instruction is adjusted and the simulation verification is repeated.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. A self-organizing decision-making mechanism that integrates multi-dimensional operational data and distributed node status data is proposed. Combined with smart contracts to generate target decision-making tasks, this mechanism breaks through the limitations of traditional building systems that rely on centralized scheduling at central nodes. It achieves data-driven autonomous generation of distributed tasks, effectively improving the system's decentralized processing and intelligent perception capabilities.

[0025] 2. By building task allocation logic for distributed nodes and comprehensively considering the computing power and trust level of nodes, dynamic classification and precise dispatch of tasks are achieved. This solves the problems of low resource utilization efficiency and poor node coordination in existing systems, and improves the computing efficiency and trusted coordination level of the entire system.

[0026] 3. Based on the blockchain network and the preset consensus algorithm, the consistency of the execution results of each node is verified, and after consensus is reached, the encrypted self-organizing decision instructions are automatically broadcast, ensuring the transparency and non-tamperability of instruction execution, and improving the security and reliability of decision-making release and execution;

[0027] 4. Supports anomaly detection and intelligent processing mechanisms. When a building system operates abnormally, it can generate exception handling suggestions and achieve consensus responses based on historical decision-making data, enhancing the system's self-recovery and resilience in emergency scenarios, breaking through the limitations of traditional systems' delayed response.

[0028] 5. A decision-making feedback closed-loop mechanism and simulation verification have been established. Simulation verification is carried out before decision execution, and the result data is extracted and an optimization effect evaluation report is generated after the decision execution. Storage and permission opening are carried out based on blockchain to enhance the system's continuous optimization capabilities and process traceability, and promote the evolution of building systems towards high autonomy, high transparency, and high security. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The present invention provides a flowchart of a distributed building self-organizing decision-making method based on blockchain;

[0030] Figure 2 A flowchart of a method for evaluating and sharing building system optimization effects is provided for the present invention;

[0031] Figure 3 The present invention provides a flow chart of a distributed response method for building system exception handling;

[0032] Figure 4 A framework diagram of a distributed building self-organizing decision-making system based on blockchain provided by the present invention.

[0033] Reference numerals:

[0034] A distributed building self-organizing decision-making system based on blockchain 101, a data acquisition module 1011, a task generation module 1012, a parameter extraction module 1013, and a decision execution module 1014. DETAILED DESCRIPTION

[0035] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0036] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the technical features indicated. Thus, features specified as "first" or "second" may explicitly or implicitly include one or more of such features; and in the description of this application, unless otherwise specified, "plurality" means two or more.

[0037] In order to more clearly illustrate the technical solution of the present invention, the present invention is described in detail below in conjunction with specific embodiments, but this should not be construed as limiting the scope of protection of the present invention.

[0038] In this embodiment, if Figure 1 As shown, a distributed building self-organizing decision-making method based on blockchain is provided, which can be implemented through the following steps to ensure that the building system achieves efficient, transparent and trustworthy optimization decision-making in a distributed environment.

[0039] Specifically, step S01: upon detecting a decision request from the building system, multidimensional operational data of the building system and status data of distributed nodes are acquired. The building system may be an intelligent building management system, such as one used to manage energy consumption, environmental control, or equipment operation in an office building. When the system detects a triggering event requiring a decision (e.g., excessive indoor temperature or abnormal energy consumption), relevant data is collected through the data acquisition units of the distributed nodes. Multidimensional operational data includes, but is not limited to, real-time data such as temperature, humidity, energy consumption, equipment operating status, and occupancy density within the building. This data is acquired in the form of time series or structured data via sensors, IoT devices, or building management systems. For example, a temperature sensor records the indoor temperature once a minute, generating a multidimensional data point containing a timestamp and temperature value. The status data of the distributed nodes includes information such as the computing power, storage capacity, online status, and network connection quality of each node. For example, a distributed node may be an edge computing device deployed in a building. Its status data may indicate that its current CPU utilization is 30%, its available memory space is 2GB, and its network latency is 10ms. This data is acquired using standardized data acquisition protocols (such as MQTT or HTTP) to ensure real-time and accurate data. Those skilled in the art will appreciate that the frequency and range of data collection can be adjusted according to the specific needs of the building system, for example, high-frequency collection can be used for dynamic environmental control, and low-frequency collection can be used for long-term trend analysis.

[0040] Furthermore, step S02 involves generating a target decision task via a smart contract within the blockchain network based on the multi-dimensional operating data and status data. The blockchain network consists of multiple distributed nodes, each running a blockchain client and jointly maintaining a decentralized ledger. Smart contracts are pre-deployed automated executable programs within the blockchain network that contain the logical rules for generating decision tasks. In specific implementations, the smart contract first performs preliminary processing on the multi-dimensional operating data and status data, for example, calculating the average building energy consumption or detecting node availability using a data aggregation function. The smart contract then converts the data into a specific decision task based on predefined task generation logic. For example, if the multi-dimensional operating data indicates that the air conditioning energy consumption on a certain floor exceeds a threshold, and the status data indicates that multiple nodes have sufficient computing power, the smart contract will generate a target decision task, such as "Optimize the air conditioning operating parameters on this floor to reduce energy consumption." This task generation logic can be based on a rules engine or simple conditional judgments, such as "If energy consumption > 100 kWh and node computing power > 50%, then generate an optimization task." The execution of smart contracts ensures that the task generation process is transparent and cannot be tampered with. Technical personnel in the relevant technical field can understand that the logic of smart contracts can be customized according to actual application scenarios (such as energy-saving optimization or equipment maintenance), but does not involve complex data cleaning or feature enhancement operations.

[0041] Furthermore, step S03: When it is determined that the distributed nodes have reached a decision consensus based on the target decision task and the preset consensus algorithm, target optimization parameters are extracted based on the multi-dimensional operating data. After the target decision task is generated, the distributed nodes perform corresponding calculations or analyses based on the task content, such as calculating the optimal air conditioner temperature set point or equipment operation schedule. The preset consensus algorithm is used to ensure that all nodes reach consensus on the task execution results. Common consensus algorithms include proof-of-work (PoW), proof-of-stake (PoS), or practical Byzantine fault tolerance (PBFT). Taking PBFT as an example, each node votes on the task execution results. Decision consensus is only considered reached when more than two-thirds of the nodes agree on the result. For example, if the target decision task is to optimize air conditioner operating parameters, the nodes may calculate the set temperature as 24°C, 25°C, and 24°C respectively. The consensus algorithm compares these results and confirms 24°C as the consensus result. After reaching consensus, the system extracts the target optimization parameters based on the multi-dimensional operating data. For example, the optimization parameters of "set temperature = 24°C, run time = 8 hours" are extracted from the temperature, energy consumption, and occupancy density data. The extraction process can be implemented through simple statistical analysis (such as mean or weighted average) or predefined rules, such as "select the temperature value that minimizes energy consumption and meets comfort requirements." Those skilled in the art will appreciate that the parameter extraction rules can be adjusted based on the building system's optimization goal (such as energy conservation or comfort), but do not involve complex semantic analysis or feature decomposition.

[0042] Furthermore, step S04: generating a self-organizing decision instruction according to the target optimization parameters, and performing simulation verification on the self-organizing decision instruction according to the multi-dimensional operation data to predict the operation state of the building system after executing the self-organizing decision instruction; if the simulation result meets the preset optimization target, broadcasting the self-organizing decision instruction through the blockchain network to execute the building system optimization; otherwise, adjusting the self-organizing decision instruction and repeating the simulation verification.

[0043] It is understood that before issuing a command, the system will simulate and verify the decision-making instructions in a platform such as a digital twin simulation. By simulating the building system's response after executing the command, it can evaluate whether the preset optimization goals, such as improved energy savings, shorter elevator wait times, or increased user satisfaction, have been achieved.

[0044] If the simulation results meet the optimization goals, the smart contract will call the blockchain network for network-wide broadcast, triggering the actual building system to respond. If the results do not meet expectations, the system will adjust the optimization parameters based on the deviation analysis results and repeat the simulation verification process until the requirements are met.

[0045] Furthermore, the simulation verification is based on a digital twin model of the building system. This model uses real-time synchronization to construct a virtual building environment, integrating multiple physical environment and control system simulation modules, including temperature and humidity sensors, power load models, equipment response characteristics, and human behavior patterns. The simulation platform captures the latest multi-dimensional operational data to reconstruct the current state of the building system with high fidelity, which serves as the basis for verification.

[0046] In practice, the system inputs the self-organizing decision-making instructions to be executed into the simulation platform's control module, which then drives the virtual building's operational logic to simulate the actual response process. For example, if the instruction involves adjusting the air conditioning system's operating strategy, the system simulates the compressor's start-stop frequency, outlet temperature fluctuations, and heat transfer interactions with the external environment to predict the temperature and humidity trends within the building after the instruction is executed.

[0047] The system also sets multiple evaluation metrics to quantify the effectiveness of command execution, including but not limited to energy consumption change rate (kWh), per capita comfort index (PMV / PPD), system stability (such as current fluctuation amplitude), response latency, and task completion rate. During the simulation, these metrics are compared and analyzed with preset optimization targets to determine whether the decision-making command meets the optimization threshold.

[0048] Furthermore, the self-organizing decision-making instructions are control commands generated based on target optimization parameters, such as "adjust the air conditioning setpoint temperature on a certain floor to 24°C and the operating time to 8 hours." The instruction generation process can be accomplished using instruction templates within a smart contract, for example, by populating a predefined instruction format with optimization parameters. The generated self-organizing decision-making instructions are sent to all relevant nodes via the blockchain network's broadcast protocol (e.g., a P2P network), ensuring transparency and consistency. Nodes receiving the instructions (e.g., building management systems or equipment controllers) perform optimization operations based on the instructions, such as adjusting the operating parameters of air conditioners through API calls. During execution, the blockchain network records the broadcast and execution status of the instructions to ensure traceability. For example, the execution results of the instructions can be recorded as transactions on the blockchain, containing information such as a timestamp, the executing node ID, and the execution status. Those skilled in the art will appreciate that the format and broadcast method of the instructions can be adjusted based on the specific implementation of the blockchain network (e.g., Ethereum or Hyperledger Fabric), but encryption processing or performance evaluation is not involved.

[0049] In summary, this method acquires multidimensional operational and status data, along with simulation verification results, and leverages smart contracts within a blockchain network to generate target decision tasks. After reaching consensus, it extracts optimization parameters and generates and broadcasts self-organizing decision instructions, ultimately achieving building system optimization. This process ensures decentralized, transparent, and trustworthy decision-making, making it suitable for scenarios such as smart building management and energy optimization. Those skilled in the art can adapt the data collection method, consensus algorithm, or instruction format to specific application scenarios without the need for complex model training or semantic analysis.

[0050] In some embodiments, based on the multi-dimensional operating data and the status data, the step of generating a target decision task through a smart contract in a blockchain network can be implemented in the following manner to ensure that the generated target decision task accurately reflects the operating requirements of the building system and the processing capabilities of the distributed nodes.

[0051] Specifically, the multidimensional operational data is normalized to generate a target operational dataset in a unified format. Multidimensional operational data is typically collected by various sensors and devices within a building system and may be in heterogeneous formats. For example, temperature data may be expressed in degrees Celsius as a floating-point number (e.g., 25.5°C), while energy consumption data may be expressed in kilowatt-hours as an integer (e.g., 100 kWh). Normalization aims to convert this heterogeneous data into a unified format for easier processing. For example, all numerical data can be converted to floating-point format, and a unified timestamp and data source identifier can be added to each data entry. In practice, normalization can be accomplished using a data conversion script. For example, a Python script can be used to map temperature and energy consumption data into a unified JSON structure, such as {"timestamp":"2025-05-20T10:00:00","type":"temperature","value":25.5,"unit":"C"}. Furthermore, normalization includes handling missing values, such as using interpolation to fill in missing time series data (e.g., linear interpolation to calculate missing temperature values). Those skilled in the art will appreciate that the details of the normalization process can be adjusted according to the source and type of the data. For example, non-numeric data (such as the on / off status of a device) can be converted into Boolean values ​​or enumeration values, but does not involve complex feature extraction or clustering analysis.

[0052] Furthermore, the target operating dataset is cleaned according to a targeted noise reduction algorithm, and feature enhancement is performed on the cleaned data to obtain optimized operating data. The targeted noise reduction algorithm aims to remove noise and outliers from the target operating dataset to improve data quality. For example, the targeted noise reduction algorithm can be a statistical anomaly detection method, such as the Z-score method, which detects and removes data points that deviate from the mean by three standard deviations. Suppose the target operating dataset contains a set of temperature data [25.0, 25.2, 30.0, 25.1], where 30.0 is an outlier. The Z-score method calculates its degree of deviation and removes it. Data cleaning also includes processing duplicate data, such as removing duplicate records through timestamp checking. The cleaned data is then subjected to feature enhancement to extract more meaningful features to support decision-making tasks. Feature enhancement can include calculating derived features, such as aggregating hourly energy consumption data into daily average energy consumption or calculating the rate of change of temperature data (e.g., a temperature change of 0.1°C per minute). In specific implementations, feature enhancement can be achieved through simple mathematical operations, such as using a sliding window to calculate the moving average of energy consumption. Optimizing operational data is the result of cleaning and enhancement, such as a dataset containing daily average energy consumption and temperature change rates. Those skilled in the art will appreciate that the choice of noise reduction algorithm and feature enhancement method can be adjusted based on data characteristics, such as using median filtering instead of the Z-score method. However, this does not involve training machine learning models or scene classification.

[0053] Furthermore, based on the optimized operation data and the status data, a target decision task is generated through the task allocation logic in the smart contract, wherein the target decision task includes the prediction parameters required to support the simulation verification of the self-organizing decision instructions. The optimized operation data provides a reliable representation of the operating status of the building system, such as the average daily energy consumption and the temperature change rate, while the status data reflects the available resources of the distributed nodes, such as CPU usage and memory capacity. The task allocation logic in the smart contract is a set of predefined rules for generating target decision tasks based on these data. For example, the task allocation logic can be a conditional statement: if the optimized operation data shows that the average daily energy consumption of a certain floor exceeds 100kWh, and the status data shows that the CPU usage of at least 3 nodes is less than 50%, then an energy consumption optimization task is generated, such as "reduce the operating power of the air conditioner on this floor." In a specific implementation, the smart contract can be written as Solidity code and run on an Ethereum-compatible blockchain network. The code example is:

[0054]

[0055] This smart contract receives optimized operation data (avgEnergy) and status data (nodeCpuUsage) and generates a task description based on the conditions. After the task is generated, it is stored on the blockchain to ensure transparency and immutability. Those skilled in the art will understand that the specific rules of the task allocation logic can be customized according to the building system's optimization goals (such as energy conservation or equipment maintenance), but do not involve complex operations such as node computing power classification or semantic analysis. In addition, the target decision task includes not only scheduling goals and execution requirements, but also key prediction parameters required to support subsequent simulation verification. For example, in a building air conditioning energy-saving optimization task, the prediction parameters included in the target decision task may include: expected changes in occupancy density in different areas of the building, short-term prediction curves for external temperature, air conditioning system response delay models, regional heat capacity estimates, and equipment start-up and shutdown power consumption models. These parameters can be directly used as input items in the simulation model to accurately reproduce the dynamic response process of the building environment under instruction execution.

[0056] Furthermore, the system supports modeling the uncertainty of prediction parameters. The target decision task will be annotated with a credible interval or range of variation for each prediction parameter, ensuring that the simulation system can evaluate the robustness of instructions under certain disturbance conditions. For example, if the external temperature forecast fluctuates within a ±2°C range, the simulation system can simulate the impact of this change on the building's internal temperature control system, thereby improving the actual credibility and engineering usability of the simulation verification.

[0057] In summary, this step transforms multidimensional operational data into optimized operational data through standardization, data cleaning, and feature enhancement. This data is then combined with the smart contract's task allocation logic to generate target decision tasks. These target decision tasks also include the prediction parameters required to support the simulation and verification of the self-organizing decision instructions. This process ensures efficient data processing and reliable task generation, making it suitable for distributed building management scenarios. Those skilled in the art can adjust the standardized format, noise reduction algorithm, or task allocation logic based on specific application scenarios, without the need for complex model training or scenario classification.

[0058] In some embodiments, based on the optimized operation data and the status data, the step of generating a target decision task through the task allocation logic in the smart contract can be implemented in the following manner to ensure that the task allocation fully considers the performance differences of the building operation scenario and distributed nodes, thereby generating efficient and adaptive target decision tasks.

[0059] Specifically, based on the target clustering algorithm, the optimized operation data is subjected to scenario classification to obtain a plurality of building operation scenario features. The optimized operation data is a standardized and feature-enhanced data set, for example, including features such as average daily energy consumption, temperature change rate, and personnel density. The target clustering algorithm is used to group these data into different building operation scenarios, such as "peak energy consumption scenario", "low-load comfort scenario" or "equipment intensive operation scenario". A feasible target clustering algorithm is K-means clustering (K-means), which divides the optimized operation data into K clusters by minimizing the distance from the data point to the cluster center. For example, assume that the optimized operation data contains the following feature vectors: [average daily energy consumption = 120kWh, temperature change rate = 0.1℃ / min, personnel density = 0.5 people / m 2 ], the K-means algorithm can assign it to the "peak energy consumption scenario" based on feature similarity. In implementation, the K value can be preset according to the data distribution (for example, K=3), and the cluster center is iteratively calculated to assign the data points to the nearest cluster to obtain the scene features, such as "peak energy consumption scenario: energy consumption>100kWh, temperature change rate<0.2℃ / min". The clustering results are stored in the form of structured data, such as JSON format: {"scene":"high_energy","features":{"avg_energy":120,"temp_rate":0.1,"density":0.5}}. Those skilled in the art will understand that the choice of clustering algorithm (such as K-means or DBSCAN) and the determination of the K value can be adjusted according to the data scale and scenario requirements, but do not involve complex semantic analysis or model training.

[0060] Furthermore, the computing power and trust level of each distributed node are determined based on the status data. Status data includes the operating status of distributed nodes, such as CPU usage, available memory, network latency, and other metrics, as well as historical performance data for assessing trust levels. Computing power can be determined by quantifying the node's hardware performance and current load. For example, nodes with a CPU usage below 50% and available memory greater than 1GB are labeled as "high computing power." In a specific implementation, a computing power scoring formula can be defined, such as: computing power score = (1 - CPU usage) × 0.5 + (available memory / total memory) × 0.5. Trust levels are based on the node's historical behavior, such as task completion rate and data consistency records. Assuming a node successfully completed 95 of the past 100 tasks with no record of data tampering, its trust level can be assigned a value of 0.95 (on a scale of 0 to 1). In implementation, trust levels can be calculated using historical transaction logs stored on the blockchain, such as by counting the node's consensus voting success rate. After status data processing, a node status table is generated, for example: {"node_id":"Node1","compute_score":0.8,"trust_level":0.95}. Those skilled in the art will appreciate that the evaluation methods for computing power and trust level can be adjusted based on node type and application scenario, such as adding network bandwidth as a computing power indicator, without involving complex machine learning models.

[0061] It can be understood that the target decision-making task is generated by the task allocation logic of the smart contract based on the building operation scenario characteristics, the computing power and the trust level. The building operation scenario characteristics provide the context of the task. For example, the "peak energy consumption scenario" requires energy consumption optimization, while the computing power and trust level determine which nodes are suitable for performing the task. The task allocation logic in the smart contract is a set of rules for matching scenario characteristics and node capabilities. For example, the logical rule can be: if the scenario is a "peak energy consumption scenario" and the node computing power score is >0.7 and the trust level is >0.9, then the task of "optimizing air conditioning operating parameters" is assigned. In the specific implementation, the smart contract can be written in Solidity and run on the blockchain network. The code example is:

[0062]

[0063]

[0064] This smart contract receives scenario characteristics (scene), a compute capability score (computeScore), and a trust level (trustLevel) and generates a target decision task based on these conditions. Once generated, the task is recorded on the blockchain, ensuring a transparent and tamper-proof allocation process. Those skilled in the art will appreciate that the specific rules of the task allocation logic can be adjusted based on scenario characteristics and node capability priorities, such as prioritizing allocation to nodes with higher trust levels. However, this does not involve cryptographic processing or semantic analysis.

[0065] In summary, this step uses a target clustering algorithm to classify optimized operational data into scenarios, evaluates node computing capabilities and trust levels based on status data, and generates target decision tasks through the smart contract's task allocation logic. This process ensures that task allocation is highly aligned with building operational scenarios and node capabilities, making it suitable for distributed building management scenarios. Those skilled in the art can adjust the clustering algorithm, scoring formula, or allocation logic based on specific scenarios without the need for complex data cleaning models or performance evaluation.

[0066] In some embodiments, before performing data cleaning on the target operating dataset according to the target noise reduction algorithm, the target noise reduction model is trained through the following steps to ensure that the data cleaning process can effectively remove noise and improve the quality of the target operating dataset.

[0067] Specifically, historical multi-dimensional operation data and corresponding historical decision result data are obtained. Historical multi-dimensional operation data includes long-term operation records of building systems, such as time series data such as temperature, energy consumption and humidity, which are stored in a building management database or blockchain ledger. For example, the data may include hourly energy consumption (such as 100kWh) and temperature (such as 25.0℃). Historical decision result data is the optimization decision record associated with this data, such as "adjust the air conditioner to 24℃". The data is obtained through database query or blockchain API in the form of structured records, such as {"time":"2024-05-20T10:00:00","energy":100,"temperature":25.0,"decision":"SetAC to 24C"}. Those skilled in the art will understand that the data acquisition method can be adjusted according to the system architecture, such as using distributed storage, but it does not involve scene classification.

[0068] Furthermore, a data cleaning training sample set is generated based on the historical multidimensional operation data and the historical decision result data. The training sample set provides labeled data for the target noise reduction model, wherein the historical multidimensional operation data is used as input and the labels are derived based on the decision results. For example, if a certain energy consumption data (such as 1000kWh) is far beyond the normal range (50-200kWh) and is not used for effective decision-making, it is marked as "noise". Label generation can use statistical methods, such as the Z-score method, to mark data that deviates from the mean by 3 times the standard deviation. The sample set format is: {"input":{"energy":1000,"temperature":25.0},"label":"noise"}. The sample size can be adjusted according to historical data, for example, 100,000 records are extracted. Those skilled in the art can understand that labeling rules can be optimized according to data characteristics, but do not involve semantic analysis.

[0069] It can be understood that the target denoising model is trained according to the target machine learning algorithm and the data cleaning training sample set. The target machine learning algorithm can select random forest, which is suitable for processing classification tasks of multi-dimensional operating data. The training samples are divided into training set and validation set (80% training, 20% validation), and the features include numerical values ​​such as energy consumption and temperature. Random forest learns the relationship between features and labels by constructing decision trees, for example, to determine whether high energy consumption data is noise. It can be understood by technicians in the relevant technical field that the algorithm and parameters (such as the number of trees) can be adjusted according to the data scale, but complex deep learning models should be avoided.

[0070] Furthermore, the loss value between the predicted value and the true value of the target denoising model is calculated according to the target loss function, and the parameters of the target denoising model are adjusted through the optimization algorithm so that the loss value is less than a preset threshold. The target loss function uses cross entropy loss to measure the difference between the predicted label and the true label. For example, the predicted noise probability is 0.9, the true label is "noise", and the loss value is -log(0.9). The optimization algorithm uses gradient descent to adjust the model parameters (such as feature weights). The training is iterated until the loss of the validation set is less than a preset threshold (such as 0.1). The optimized model can accurately identify noise data, for example, marking 1000kWh as noise. Those skilled in the art can understand that the loss function and threshold can be adjusted according to the scenario, but consensus verification is not involved.

[0071] In summary, this step supports data cleaning by acquiring historical data, generating training samples, training the target noise reduction model, and optimizing parameters, ensuring accurate noise identification and suitable for distributed building management scenarios. While those skilled in the art can adjust the data format, algorithm, or threshold, this approach can be implemented without complex analysis.

[0072] In some embodiments, when it is determined that the distributed nodes reach a decision consensus based on the target decision task and the preset consensus algorithm, the step of extracting the target optimization parameters based on the multi-dimensional operation data can be implemented in the following way to ensure that the parameter extraction process is efficient and accurate, and is suitable for distributed building self-organizing decision-making scenarios.

[0073] Based on the target decision task, the consistency of the task execution results of distributed nodes is verified using a pre-set consensus algorithm. A target decision task is generated by a smart contract within the blockchain network, such as "Optimize air conditioning operating parameters on a specific floor to reduce energy consumption." Distributed nodes independently perform calculations or analyses based on the task content, such as calculating the optimal air conditioning temperature set point. A pre-set consensus algorithm is used to verify the consistency of the execution results of each node. Common algorithms include Practical Byzantine Fault Tolerance (PBFT). In PBFT, each node submits the task execution result (e.g., setting the temperature to 24°C) to the blockchain network. The master node in the network collects the results and votes. Verification passes only when more than two-thirds of the nodes agree. For example, if five nodes submit the results [24°C, 24°C, 25°C, 24°C, 24°C], the PBFT algorithm confirms 24°C as the consensus result. In specific implementations, the consensus process is completed through the blockchain client's protocol stack, and the verification results are recorded as blockchain transactions to ensure transparency and immutability. Those skilled in the art will appreciate that the choice of consensus algorithm (such as PBFT or PoS) and voting threshold can be adjusted based on the network scale, but does not involve feature decomposition or semantic scoring.

[0074] Furthermore, upon passing verification, semantic analysis is performed on the multidimensional operating data based on the target parameter extraction model in the artificial intelligence module. The target parameter extraction model is a pre-trained artificial intelligence model used to extract optimization parameters relevant to the target decision task from the multidimensional operating data. The multidimensional operating data includes real-time data such as temperature, energy consumption, and humidity, for example, [temperature = 25.0°C, energy consumption = 120 kWh, humidity = 60%]. Semantic analysis aims to identify patterns or features in the data that are relevant to the task objective (such as energy saving or comfort). For example, for the task "Optimize air conditioning operating parameters," the model analyzes the data to determine which parameters (such as the temperature set point) have the greatest impact on energy consumption. In implementation, the target parameter extraction model can be a simple regression model (such as linear regression), which predicts optimal parameters by analyzing the correlation between historical data and decision outcomes. For example, the model may learn the relationship that "a temperature reduction of 1°C reduces energy consumption by 5 kWh." The semantic analysis process is implemented through model inference, taking the multidimensional operating data as input and outputting parameter recommendations relevant to the task. Those skilled in the art will appreciate that the choice of model can be adjusted based on the complexity of the data, such as using a decision tree instead of a regression model, but without involving complex multi-dimensional feature decomposition.

[0075] As can be understood, the target optimization parameters relevant to the target decision task are extracted based on the semantic analysis results. The semantic analysis results are the output of the target parameter extraction model, for example, a set of parameter recommendations: {"temperature set point": 24°C, "run time": 8 hours}. The process of extracting target optimization parameters aligns these recommendations with the objectives of the target decision task. For example, if the task objective is "reducing energy consumption while maintaining comfort," parameters that meet the requirements are selected from the analysis results, such as a temperature of 24°C (which is both energy-efficient and within the comfort range of 20-26°C). In a specific implementation, the extraction process can be implemented through rule-based filtering, such as setting a threshold rule: "Select parameters that reduce energy consumption by >10% and have a temperature between 20-26°C." The extracted parameters are stored in a structured format, such as JSON: {"parameter":"temperature","value":24,"unit":"C"}, and recorded on the blockchain for traceability. Those skilled in the art will appreciate that the parameter extraction rules can be adjusted based on the task objective, such as prioritizing comfort or energy conservation, but do not involve semantic relevance scoring or broadcast encryption.

[0076] In summary, this step verifies the consistency of task execution results across distributed nodes using a pre-set consensus algorithm, performs semantic analysis on multidimensional operational data using a target parameter extraction model, and extracts target optimization parameters based on the analysis results. This process ensures that parameter extraction is highly relevant to the decision-making task and is suitable for distributed building management scenarios. Those skilled in the art can adjust the consensus algorithm or model selection based on the task type and data characteristics, without the need for complex eigenvalue decomposition or encryption processing.

[0077] In some embodiments, the step of performing semantic analysis on the multidimensional operation data according to the target parameter extraction model in the artificial intelligence module can be implemented in the following manner to ensure accurate extraction of optimization parameters related to the target decision-making task from the multidimensional operation data, which is suitable for distributed building self-organizing decision-making scenarios.

[0078] Specifically, the multi-dimensional operational data is subjected to multi-dimensional feature decomposition to obtain multiple feature subsets. Multi-dimensional operational data is data collected from building systems in real time, covering dimensions such as temperature, energy consumption, humidity, and occupant density. For example, a set of data may include temperature 25.0°C, energy consumption 120kWh, humidity 60%, and occupant density 0.5 people / m 2. These data are stored in time series or structured formats and may come from sensors or building management systems. The purpose of multidimensional feature decomposition is to split these data into independent subsets by feature type for subsequent analysis. For example, the decomposition process can divide the data into temperature subsets (such as 25.0℃, 25.2℃, 24.8℃), energy consumption subsets (such as 120kWh, 115kWh, 122kWh), humidity subsets (such as 60%, 58%, 61%) and personnel density subsets (such as 0.5, 0.4, 0.6 people / m 2 In practice, decomposition can be accomplished using data processing tools, such as grouping data by field and storing it as a separate list or table. The decomposed feature subsets retain the characteristics of the original data, ensuring that subsequent analysis can be targeted at specific features. Those skilled in the art will appreciate that the decomposition method can be adjusted based on the data structure, such as grouping by time period or device type, but does not involve encryption processing or consensus verification.

[0079] Furthermore, based on a target semantic analysis algorithm, semantic relevance scores are assigned to the multiple feature subsets. The target semantic analysis algorithm aims to assess the relevance of each feature subset to the target decision-making task. For example, if the task is "optimize air conditioning operating parameters to reduce energy consumption," it is necessary to determine which features have the greatest impact on energy consumption. Semantic relevance scoring can be achieved through statistical methods, such as calculating the Pearson correlation coefficient between the feature subsets and the task objective. Assuming the task objective is to reduce total energy consumption, the algorithm analyzes the correlation between the energy consumption subset and historical energy consumption data and obtains a high score (e.g., 0.9, indicating a strong correlation), while the humidity subset may receive a lower score (e.g., 0.2). In a specific implementation, the scoring process includes the following steps: first, determining a quantitative indicator of the task objective, such as total energy consumption; then, calculating the correlation between each feature subset and the indicator; and finally, normalizing the scores to a range of 0 to 1. For example, the temperature subset may receive a score of 0.8, the energy consumption subset 0.9, the humidity subset 0.2, and the occupancy density subset 0.5. The scoring results are stored in a structured format, such as a table or key-value pairs, recording the correlation scores for each feature subset. Those skilled in the art will appreciate that the scoring method can be adjusted to meet task requirements, such as using the Spearman correlation coefficient instead of the Pearson coefficient, but no encryption or broadcasting operations are involved.

[0080] It can be understood that, based on the semantic relevance score, the target optimization parameters with the highest relevance to the target decision task are extracted from the multiple feature subsets. The semantic relevance score provides the degree of relevance between each feature subset and the task objective. For example, the energy consumption subset has the highest score of 0.9, indicating that it has the greatest impact on the "reducing energy consumption" task. The process of extracting the target optimization parameters is to select parameters consistent with the task objective from the high-scoring subsets. For example, if the task requires reducing energy consumption, the target optimization parameters are extracted from the energy consumption subset (120kWh, 115kWh, 122kWh), such as "target energy consumption = 115kWh" (the average is taken as the recommended value). The extraction process is implemented through predefined rules, such as "select feature subsets with a score greater than 0.7 and extract their average or recommended value as the optimization parameter." If the temperature subset also has a high score (such as 0.8), "temperature set point = 24°C" may be additionally extracted as a parameter to take comfort into consideration. The extracted parameters are stored in a structured format, such as a key-value pair: {"parameter":"energy consumption","value":115,"unit":"kWh"}, and recorded on the blockchain to ensure traceability. Those skilled in the art will appreciate that the extraction rules can be optimized based on task objectives, such as prioritizing energy-saving parameters, but do not involve instruction generation or effectiveness evaluation.

[0081] In summary, this step, through multi-dimensional feature decomposition, semantic relevance scoring, and parameter extraction, extracts optimization parameters highly relevant to the target decision-making task from multi-dimensional operational data. This process ensures accurate and efficient analysis results, making it suitable for distributed building management scenarios. Those skilled in the art can adjust the decomposition method, scoring approach, or extraction rules based on the data type and task objectives, without the need for encryption or consensus algorithms to implement the above method steps.

[0082] In some embodiments, the steps of generating self-organizing decision instructions based on the target optimization parameters and broadcasting the self-organizing decision instructions through the blockchain network to perform building system optimization can be achieved in the following manner to ensure that the decision instructions are generated and distributed securely and transparently, which is suitable for distributed building self-organizing decision scenarios.

[0083] Specifically, identification information for a self-organizing decision instruction is generated based on the target optimization parameters. Target optimization parameters are parameters extracted from multidimensional operational data related to the decision-making task, such as "temperature setpoint = 24°C" or "air conditioning operating power = 80%." They are used to optimize building system operations, such as reducing energy consumption or improving comfort. Self-organizing decision instructions are control commands generated based on these parameters, directing building systems to perform specific operations. The purpose of generating identification information is to assign a unique identifier to each decision instruction for easy tracking and verification. For example, the identification information may include the instruction's unique ID, generation timestamp, and task objective, in a format such as: {"Instruction ID":"CMD202505201023", "Timestamp":"2025-05-20T22:23:00", "Objective":"Reduce energy consumption"}. This generation process is accomplished through a template within the smart contract. For example, the target optimization parameter "temperature = 24°C" is entered into the instruction template "Adjust air conditioning to {temperature}," generating the instruction "Adjust air conditioning to 24°C" and appending the aforementioned identification information. Identification information is stored as structured data to ensure the traceability of instructions within the blockchain network. Those skilled in the art will appreciate that the format and content of identification information can be adjusted based on system requirements, such as adding a device ID or priority, but this does not involve data cleaning or semantic analysis.

[0084] Furthermore, the self-organizing decision-making instruction is encrypted by the smart contract to generate an encrypted decision-making instruction. Encryption is intended to protect the security and integrity of the instruction during transmission over the blockchain network, preventing unauthorized tampering or access. Encryption logic is embedded in the smart contract, using a symmetric encryption algorithm (such as AES) or an asymmetric encryption algorithm (such as RSA) to encrypt the instruction content. For example, for the instruction "adjust the air conditioner to 24°C," the encryption process may generate a ciphertext string, such as a hexadecimal string, ensuring that only nodes with the correct key can decrypt it. The specific implementation of the encryption process includes the following steps: First, the smart contract obtains the encryption key from a preconfigured keystore; then, the instruction content (including identification information) is encrypted with the key; finally, an encrypted decision-making instruction is generated in the format of {"Command ID":"CMD202505201023","Ciphertext":"0x7a8b9c..."}. The encrypted instruction is recorded as a blockchain transaction to ensure its immutability. Those skilled in the art will appreciate that the choice of encryption algorithm can be adjusted according to security requirements, such as using more efficient symmetric encryption, but this does not involve effect evaluation or exception handling.

[0085] As can be understood, the encrypted decision instruction is broadcast via the blockchain network, and building system optimization is executed based on the decryption verification results of distributed nodes. The blockchain network uses a peer-to-peer (P2P) protocol to broadcast the encrypted decision instruction to all distributed nodes, such as edge devices or controllers deployed in the building management system. This broadcast process ensures that each node receives the same copy of the instruction, maintaining system consistency. After receiving the instruction, each node decrypts it using a pre-shared decryption key, for example, using the AES decryption algorithm to restore the ciphertext to the original instruction "adjust the air conditioner to 24°C." Decryption verification includes checking the integrity and legitimacy of the instruction, such as verifying that the timestamp in the identification information is within a valid range or confirming that the instruction originates from a trusted smart contract. If verification passes, the node passes the instruction to the building management system for execution of the optimization action, such as adjusting the temperature setpoint of the air conditioner through an API call. The execution result is recorded as a blockchain transaction, for example: {"Command ID":"CMD202505201023","Execution Status":"Success","Time":"2025-05-20T22:24:00"}. Those skilled in the art will appreciate that the details of the broadcast protocol and decryption verification can be adjusted according to the blockchain platform (such as Ethereum or Hyperledger Fabric), but do not involve optimization effect evaluation or exception handling.

[0086] In summary, this step ensures the security and transparency of instruction generation and distribution by generating identification information for self-organizing decision instructions, encrypting the instructions, and broadcasting and executing optimization operations via the blockchain network. This approach is suitable for distributed building management scenarios. Those skilled in the art can adjust the identification format, encryption algorithm, or broadcast mechanism based on system requirements; however, the above method steps can be implemented without the need for data analysis or performance evaluation.

[0087] In some embodiments, as Figure 2 As shown, after generating a self-organizing decision instruction according to the target optimization parameters and broadcasting the self-organizing decision instruction through the blockchain network to perform building system optimization, the following steps are performed to realize the evaluation and sharing of the optimization effect to ensure that the results of the building system optimization can be verified and accessed, which is suitable for distributed building system self-organizing decision-making scenarios.

[0088] Specifically, the execution result data of the self-organizing decision-making instructions is obtained. Self-organizing decision-making instructions are control commands generated based on target optimization parameters, such as "adjust the air conditioner set temperature to 24°C" or "reduce fan operating power to 80%." They are broadcast over the blockchain network and executed by the building management system or equipment. Execution result data is feedback data collected from execution nodes (such as edge devices or controllers) that reflects the actual effect of the instruction execution. For example, if the instruction is "adjust the air conditioner to 24°C," the execution result data may include the actual temperature after execution (such as 24.1°C), the change in energy consumption (such as from 120kWh to 110kWh), and the execution status (such as "success" or "failure"). This data is collected by sensors or the monitoring module of the building management system in the form of structured records, for example: {"Command ID":"CMD202505201023", "Actual Temperature":24.1, "Energy Consumption":110, "Status":"Success"}. The data collection process is implemented through standard protocols (such as MQTT) to ensure real-time and accuracy. Those skilled in the art will appreciate that the type and collection frequency of execution result data may be adjusted according to the instruction objective, such as adding humidity or personnel density data, but this does not involve exception handling or consensus verification.

[0089] Furthermore, step S11: Execution result data for the self-organizing decision-making instruction is obtained, and a building system optimization effect evaluation report is generated based on the execution result data, the multi-dimensional operational data, and the simulation verification results. The execution result data provides direct feedback on instruction execution, while the multi-dimensional operational data includes building operational status before and after instruction execution, such as temperature, energy consumption, and humidity. The optimization effect evaluation report evaluates the effectiveness of the instruction by comparing the execution results with the expected target. For example, if the goal is to reduce energy consumption by 10%, and the execution results show a decrease from 120 kWh to 110 kWh, the report will record "Energy consumption reduced by 8.3%, approaching the target." The report generation process includes the following steps: first, extracting key indicators (such as energy consumption and temperature) from the execution result data; then, comparing these indicators with historical or expected values ​​in the multi-dimensional operational data to calculate the optimization effect (such as the percentage of energy consumption reduction); then, invoking the simulation verification results generated in the previous simulation phase to simulate the consistency and deviation between the prediction and actual execution; and finally, compiling the report into a structured report containing the instruction ID, execution time, optimization indicators, and evaluation conclusions. The report format can be either table or text, for example: {"Command ID":"CMD202505201023","Execution Time":"2025-05-20T22:24:00","Energy Consumption Reduction":"8.3%","Conclusion":"Good Optimization Results"}. Those skilled in the art will appreciate that the report content and evaluation metrics can be adjusted based on the optimization objectives, such as including a comfort assessment, but without exception handling suggestions.

[0090] Furthermore, step S12 involves storing the optimization effect evaluation report on the blockchain network and granting access rights to distributed nodes according to pre-set sharing rules. The blockchain network provides decentralized storage, ensuring the transparency and immutability of the report. The storage process uploads the evaluation report to the blockchain as a transaction record, for example, by invoking a storage function in a smart contract to write the report content to the distributed ledger. After the report is stored, it is assigned a unique transaction hash (e.g., "0x9a8b7c...") to facilitate subsequent queries. Pre-set sharing rules define which distributed nodes can access the report, such as "only nodes with a trust level above 0.9" or "open to all consensus-participating nodes." In practice, sharing rules are implemented through the smart contract's access control logic, for example, by validating access rights based on node address or role. Access is completed through a blockchain query interface, and nodes submit requests to obtain decrypted report content. Those skilled in the art will appreciate that storage methods and sharing rules can be tailored to the blockchain platform, such as using IPFS (InterPlanetary File System, a decentralized distributed file storage and sharing protocol) to store large files or setting more granular access rights. However, this does not involve analysis of abnormal scenarios.

[0091] In summary, this step ensures transparency and verifiability of optimization results by acquiring execution result data, generating an optimization effect evaluation report, and storing it on the blockchain network. This step also provides access rights according to sharing rules, making it suitable for distributed building management scenarios. Those skilled in the art can adjust the data collection method, evaluation metrics, or sharing rules based on system requirements, but the functionality of the above method steps can be achieved without introducing exception handling or semantic analysis.

[0092] In some embodiments, as Figure 3 As shown, after the self-organizing decision-making instructions are broadcasted through the blockchain network to execute building system optimization, the processing under abnormal scenarios is implemented through the following steps to ensure that the building system can quickly resume normal operation under abnormal circumstances, which is applicable to distributed building system self-organizing decision-making scenarios.

[0093] Specifically, in step S21, when an abnormal building system operation is detected, multi-dimensional operating data for the abnormal scenario is acquired. Building system abnormalities may include equipment failure, abnormal energy consumption, or environmental parameter excursions, such as a failure in air conditioning system temperature regulation or a sudden surge in energy consumption. Anomaly detection is implemented by the building management system's monitoring module. For example, an abnormality alert is triggered when the temperature exceeds the normal range (e.g., 20-26°C) for 10 consecutive minutes or when energy consumption exceeds three standard deviations of the historical mean. Multi-dimensional operating data for abnormal scenarios is real-time data collected from sensors or devices, covering dimensions such as temperature, energy consumption, humidity, and device status. For example, if the temperature on a floor is detected to have reached 30°C (abnormally high), the multi-dimensional operating data may include: {"time":"2025-05-20T22:30:00","temperature":30.0","energy consumption":150kWh","humidity":65%,"device status":"operating"}. Data collection is accomplished via IoT protocols (e.g., CoAP) to ensure real-time and accuracy. Those skilled in the art will appreciate that the anomaly detection threshold and data collection dimensions can be adjusted according to system requirements, such as adding air quality data, but this does not involve data cleaning or feature enhancement.

[0094] Furthermore, in step S21, an exception handling recommendation is generated based on the multi-dimensional operational data for the abnormal scenario and historical decision data in the blockchain network. The multi-dimensional operational data for the abnormal scenario provides a snapshot of the current system state, while the historical decision data is a record of past decisions extracted from the blockchain network, such as "adjust the air conditioner to 24°C" or "shut down the faulty device." The process of generating an exception handling recommendation includes the following steps: first, analyzing the abnormal scenario data to identify key characteristics of the abnormality, such as a temperature of 30°C indicating overheating; then, querying the historical decision data on the blockchain to find records of similar abnormal scenarios, such as past actions to "increase ventilation power" when the temperature exceeded the standard; finally, generating a recommendation based on rules or pattern matching, such as "recommend increasing ventilation power to 90% and inspecting the air conditioning equipment." The recommendation is generated in a structured format, for example: {"Exception ID":"ERR202505201030","Exception Type":"Temperature Too High","Recommendation":"Increase ventilation power to 90%"}. Rules can be based on a predefined exception handling knowledge base, such as "If the temperature is >28°C, prioritize increasing ventilation." Those skilled in the art will appreciate that the suggestion generation rules may be adjusted according to the anomaly type, such as recommending reducing device power for energy consumption anomalies, but this does not involve semantic analysis or optimization parameter extraction.

[0095] It can be understood that step S22: broadcast the exception handling suggestion to the distributed nodes through the smart contract, and perform the exception handling operation according to the consensus result of the distributed nodes. The exception handling suggestion is broadcast through the smart contract of the blockchain network to ensure that all distributed nodes (such as edge devices or management nodes) receive consistent suggestions. The broadcast process uses a peer-to-peer (P2P) protocol to distribute the suggestions as transaction records, such as transactions containing an exception ID and the content of the suggestion. The distributed nodes perform consensus verification on the suggestions using a preset consensus algorithm (such as Practical Byzantine Fault Tolerance, PBFT). In PBFT, nodes vote to confirm the rationality of the suggestions, such as checking whether the suggestions match the current exception data. Consensus is reached only when more than 2 / 3 of the nodes agree. After reaching consensus, the exception handling operation is performed, such as adjusting the ventilation power to 90% through a building management system API call. The execution results are recorded on the blockchain, for example: {"Exception ID":"ERR202505201030","Execution Status":"Success","Time":"2025-05-20T22:32:00"}. Those skilled in the art will appreciate that the consensus algorithm and execution method can be adjusted based on the blockchain platform, such as using Proof of Stake (PoS) instead of PBFT, but this does not involve cryptographic processing or performance evaluation.

[0096] In summary, this step ensures rapid recovery of building systems in the event of an anomaly by acquiring multidimensional operational data under abnormal circumstances, generating anomaly handling recommendations, and broadcasting and executing them through smart contracts. This approach is suitable for distributed building management scenarios. Those skilled in the art can adjust the data collection method, recommendation generation rules, or consensus mechanism based on the anomaly type and system architecture, but the functionality of the above method steps can be achieved without the need for data cleaning or optimized parameter extraction.

[0097] Another embodiment of the present invention further provides a distributed building self-organizing decision-making system 101 based on blockchain, such as Figure 4 As shown, the system 101 implements decentralized decision-making and optimization functions through the following modules, which is suitable for smart building management scenarios, such as energy optimization or environmental control of commercial buildings.

[0098] Specifically, the data acquisition module 1011 is configured to acquire multi-dimensional operating data of the building system and status data of the distributed nodes via the data acquisition units of the distributed nodes when a decision request is detected by the building system. Data acquisition module 1011 is deployed on distributed nodes, such as edge computing devices or IoT gateways, and is responsible for collecting building system operating data and node status in real time. Multi-dimensional operating data includes temperature, energy consumption, humidity, occupancy density, and other data, and is sourced from sensors or management systems within the building. For example, when the system detects a decision request (such as an optimization request triggered by excessive energy consumption), the module collects data via an IoT protocol (such as MQTT) and generates a structured record, such as: {"time":"2025-05-20T22:32:00","temperature":25.0","energy consumption":120kWh","humidity":60%}. Status data of the distributed nodes includes CPU usage, available memory, and network connection status, such as: {"node ID":"Node1","CPU usage":30%,"memory":2GB}. The data acquisition unit communicates with sensors or devices via standardized interfaces, ensuring real-time and accurate data. Those skilled in the art will appreciate that the frequency and dimensions of data acquisition can be adjusted based on the building type. For example, high-frequency acquisition can be used for dynamic control, but does not involve data cleaning or feature enhancement.

[0099] Furthermore, the task generation module 1012 is configured to generate the target decision task based on the multi-dimensional operating data and the status data through a smart contract in the blockchain network. Task generation module 1012 operates in the smart contract layer of the blockchain network and uses the multi-dimensional operating data and status data to generate decision tasks. For example, if the multi-dimensional operating data shows that the energy consumption of a certain floor is 120kWh (above the threshold of 100kWh), and the status data indicates that multiple nodes have sufficient computing power, the module generates a task "Optimize the air conditioning operating parameters on this floor" through a smart contract. The smart contract contains predefined task generation rules, such as "If energy consumption > 100kWh and node CPU utilization < 50%, then generate an energy-saving task." The generated tasks are stored in a structured format, for example: {"Task ID":"TASK202505201032", "Goal":"Reduce energy consumption", "Area":"Floor A"}, and recorded on the blockchain to ensure transparency. The task generation process is completed through the automated execution of the smart contract, without the need for human intervention. Those skilled in the art will appreciate that the task generation rules can be adjusted according to the optimization objectives, such as optimizing for comfort, but do not involve scene classification or trust level assessment.

[0100] It is understood that the parameter extraction module 1013 is configured to extract target optimization parameters from the multi-dimensional operating data through the artificial intelligence module when it is determined that the distributed nodes have reached a decision consensus based on the target decision task and the preset consensus algorithm. The parameter extraction module 1013 operates in conjunction with the consensus mechanism of the blockchain network and the artificial intelligence module. Once a task is generated, the distributed nodes execute the task and submit the results, such as calculating the optimal air conditioning temperature. A preset consensus algorithm (such as Practical Byzantine Fault Tolerance (PBFT)) verifies the consistency of the results, for example, confirming that a majority of nodes recommend a temperature of 24°C. After consensus is reached, the artificial intelligence module (such as a pre-trained regression model) analyzes the multi-dimensional operating data and extracts optimization parameters, such as "temperature setpoint = 24°C." This analysis is based on rules or simple models, such as comparing the historical relationship between energy consumption and temperature to determine energy-saving parameters. The extracted parameters are stored in a structured format, for example: {"parameter":"temperature","value":24","unit":"°C"}, and recorded on the blockchain. Those skilled in the art will appreciate that the consensus algorithm and artificial intelligence model can be adjusted according to system requirements, such as using a decision tree model, but without involving feature decomposition or encryption processing.

[0101] Furthermore, the decision execution module 1014 is configured to generate a self-organizing decision instruction based on the target optimization parameters and perform simulation verification on the self-organizing decision instruction based on the multi-dimensional operating data to predict the building system operating state after executing the self-organizing decision instruction. If the simulation results meet the preset optimization target, the self-organizing decision instruction is broadcasted via the blockchain network to execute the building system optimization. Otherwise, the self-organizing decision instruction is adjusted and the simulation verification is repeated. After the simulation verification, the decision execution module 1014 generates an instruction based on the extracted parameters, for example, converting "temperature = 24°C" into the instruction "adjust air conditioning to 24°C." Once generated, the instruction is distributed to all relevant nodes, such as building management systems or device controllers, via the blockchain network's peer-to-peer (P2P) broadcast protocol. The broadcast instruction is recorded as a transaction, for example: {"Command ID": "CMD202505201033", "Content": "Adjust air conditioning to 24°C"}. The receiving node executes the instruction, for example, by adjusting device parameters through an API call, completing the optimization operation. The execution results are recorded on the blockchain to ensure traceability. Those skilled in the art will appreciate that the instruction format and broadcast protocol can be adjusted according to the blockchain platform, such as using Ethereum's transaction mechanism, but without involving encryption or effect evaluation.

[0102] In summary, system 101, through the data acquisition module 1011, task generation module 1012, parameter extraction module 1013, and decision execution module 1014, implements a complete process from data collection to decision execution, ensuring decentralized, transparent, and efficient building system optimization, making it suitable for distributed building management scenarios. Those skilled in the art can adjust module functions based on building requirements, such as optimizing data collection frequency or consensus algorithms, without the need for data cleaning or exception handling to achieve the system's functionality.

[0103] The above description is merely an exemplary embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformation made by utilizing the contents of the present invention's description and drawings under the technical concept of the present invention, or directly / indirectly applied in other related technical fields, is included in the patent protection scope of the present invention.

Claims

1. A distributed building self-organizing decision-making method based on blockchain, characterized in that: The method comprises: When a decision request is detected from the building system, the multi-dimensional operation data of the building system and the status data of the distributed nodes are obtained; generating a target decision task through a smart contract in a blockchain network based on the multidimensional operation data and the status data; extracting target optimization parameters based on the multidimensional operation data when it is determined that the distributed nodes reach a decision consensus based on the target decision task and a preset consensus algorithm; A self-organizing decision instruction is generated according to the target optimization parameters, and the self-organizing decision instruction is simulated and verified according to the multi-dimensional operation data to predict the operating status of the building system after the execution of the self-organizing decision instruction; if the simulation result meets the preset optimization target, the self-organizing decision instruction is broadcast through the blockchain network to execute the building system optimization; otherwise, the self-organizing decision instruction is adjusted and the simulation verification is repeated.

2. The method according to claim 1, wherein The step of generating a target decision task through a smart contract in a blockchain network based on the multi-dimensional operation data and the status data includes: Standardizing the multidimensional operation data to generate a target operation data set in a unified format; Cleaning the target operating data set according to a target noise reduction algorithm, and enhancing features of the cleaned data to obtain optimized operating data; Based on the optimized operation data and the status data, a target decision task is generated through the task allocation logic in the smart contract, wherein the target decision task includes prediction parameters required to support the simulation verification of the self-organizing decision instruction.

3. The method according to claim 2, wherein The step of generating a target decision task through task allocation logic in a smart contract based on the optimized operation data and the status data includes: Based on the target clustering algorithm, the optimized operation data is classified into scenarios to obtain multiple building operation scenario features; the computing power and trust level of each distributed node are determined according to the status data; According to the building operation scenario characteristics, the computing power and the trust level, a target decision task is generated through the task allocation logic of the smart contract.

4. The method according to claim 2, wherein Before the step of performing data cleaning on the target running data set according to the target noise reduction algorithm, the method further includes: Obtain historical multi-dimensional operation data and corresponding historical decision result data; Generate a data cleaning training sample set based on the historical multi-dimensional operation data and the historical decision result data; Training a target denoising model based on a target machine learning algorithm and the data cleaning training sample set; The loss value between the predicted value and the true value of the target denoising model is calculated according to the target loss function, and the parameters of the target denoising model are adjusted through an optimization algorithm so that the loss value is less than a preset threshold.

5. The method according to claim 1, wherein The step of extracting target optimization parameters based on the multi-dimensional operation data when determining that the distributed nodes reach a decision consensus based on the target decision task and the preset consensus algorithm includes: According to the target decision-making task, the consistency of the task execution results of the distributed nodes is verified through a preset consensus algorithm; When the verification is passed, semantic analysis is performed on the multi-dimensional operation data according to the target parameter extraction model in the artificial intelligence module; The target optimization parameters related to the target decision task are extracted according to the semantic analysis results.

6. The method according to claim 5, wherein The step of performing semantic analysis on the multi-dimensional operation data according to the target parameter extraction model in the artificial intelligence module includes: Performing multi-dimensional feature decomposition on the multi-dimensional operation data to obtain multiple feature subsets; Based on a target semantic analysis algorithm, performing semantic relevance scoring on the plurality of feature subsets; According to the semantic relevance score, the target optimization parameter with the highest relevance to the target decision task is extracted from the multiple feature subsets.

7. The method according to claim 1, wherein The step of generating a self-organizing decision instruction according to the target optimization parameter and broadcasting the self-organizing decision instruction through the blockchain network to perform building system optimization includes: Generate identification information of a self-organizing decision instruction according to the target optimization parameter; Encrypting the self-organizing decision instruction through a smart contract to generate an encrypted decision instruction; The encrypted decision instructions are broadcasted through the blockchain network, and building system optimization is performed based on the decryption verification results of the distributed nodes.

8. The method according to claim 1, wherein After the step of generating a self-organizing decision instruction according to the target optimization parameter and broadcasting the self-organizing decision instruction through the blockchain network to perform building system optimization, the method further includes: Obtaining execution result data of the self-organizing decision instruction; generating a building system optimization effect evaluation report based on the execution result data, the multi-dimensional operation data and the simulation verification result; The optimization effect evaluation report is stored in the blockchain network, and access rights are opened to distributed nodes according to preset sharing rules.

9. The method according to claim 1, wherein After the step of generating a self-organizing decision instruction according to the target optimization parameter and broadcasting the self-organizing decision instruction through the blockchain network to perform building system optimization, the method further includes: When an abnormal operation of the building system is detected, multi-dimensional operation data under the abnormal scenario is obtained; based on the multi-dimensional operation data under the abnormal scenario and the historical decision data in the blockchain network, an abnormal handling suggestion is generated; The exception handling suggestions are broadcast to distributed nodes through smart contracts, and exception handling operations are performed based on the consensus results of the distributed nodes.

10. A distributed building self-organizing decision-making system based on blockchain, characterized in that: The system is used to perform the method according to any one of claims 1 to 9, and the system comprises: a data acquisition module configured to acquire multi-dimensional operation data of the building system and status data of the distributed nodes through the data acquisition units of the distributed nodes when detecting a decision request initiated by the building system; A task generation module is configured to generate the target decision task through a smart contract in the blockchain network based on the multi-dimensional operation data and the status data; a parameter extraction module configured to extract target optimization parameters from the multidimensional operation data through the artificial intelligence module when it is determined that the distributed nodes reach a decision consensus based on the target decision task and the preset consensus algorithm; a decision execution module configured to generate a self-organizing decision instruction according to the target optimization parameter, and simulate and verify the self-organizing decision instruction according to the multi-dimensional operation data to predict the operation state of the building system after executing the self-organizing decision instruction; If the simulation result meets the preset optimization target, the self-organizing decision instruction is broadcast through the blockchain network to execute the building system optimization; otherwise, the self-organizing decision instruction is adjusted and the simulation verification is repeated.

Images