Chamber temperature control system

Abstract

The invention provides a compartment temperature control system, and relates to the technical field of computer processing, and the system comprises an information obtaining module which is used for obtaining historical temperature control data of a target building, and extracting temperature change characteristics from the historical temperature control data, and the temperature change characteristics comprise temperature fluctuation characteristics caused by room functions, orientation and personnel activities; constructing a temperature control database based on the historical temperature control data; the data acquisition module is in communication connection with the temperature control database and is used for acquiring real-time temperature data characteristics from the database; the thermal dynamic analysis module is used for analyzing the dynamic temperature change rule of the building under the different thermal load contextual models; and an efficiency verification subunit. According to the method, the differentiated temperature control strategy is intelligently formulated by sensing the position of the person and the working condition of the room, so that the heat energy consumption is remarkably reduced while the personalized comfort degree is improved.

Description

Technical Field

[0001] This invention relates to the field of computer processing technology, and in particular to a compartment temperature control system. Background Technology

[0002] Currently, traditional heating systems typically employ centralized temperature control, which struggles to meet users' personalized temperature needs for different rooms, leading to energy waste and decreased comfort. As people's demands for comfortable and energy-efficient living environments increase, existing heating systems show significant shortcomings in independent room-by-room temperature control. This is particularly true for rooms with different functions, such as living rooms, bedrooms, and rooms facing different directions; current technology cannot achieve precise control or efficient utilization of free heat. Furthermore, existing systems lack intelligent learning and remote control capabilities, preventing users from flexibly adjusting temperature settings based on actual usage and hindering seamless integration with smart home systems. While room-by-room temperature control systems exist both domestically and internationally, improvements are still needed in terms of intelligence, networking, and system compatibility, particularly in adapting to multiple communication protocols, environmental tolerance, remote diagnostics, and configuration management. Summary of the Invention

[0003] To address the aforementioned technical problems, the present invention provides a compartmentalized temperature control system, comprising: The information acquisition module is used to acquire historical temperature control data of the target building and extract temperature change features from the historical temperature control data, including temperature fluctuation features caused by room function, orientation and human activities; and to construct a temperature control database based on the historical temperature control data. The data acquisition module is communicatively connected to the temperature control database and is used to acquire real-time temperature data characteristics from the database; The thermal dynamics analysis module is used to analyze the dynamic temperature change patterns of the building under the different heat load scenarios. The intelligent monitoring terminal is used to bind the identification information of each room and its associated users, receive the uploaded real-time environmental data and update the backend; when the evaluation result is abnormal performance, it sends a prompt message about the operating status to the associated users.

[0004] Preferably, the data acquisition unit includes: The data area molecular unit, based on the characteristics of the collected temperature data, is used to classify the data according to the dominant factors affecting temperature fluctuations. The classification method includes distinguishing the temperature data characteristics into human activity-dominated temperature characteristics and environmental factor-dominated temperature characteristics; wherein, the human activity-dominated temperature characteristics are related to the presence and activity intensity of people in a specific room; The scenario segmentation subunit, in response to the classification results of the data differentiation module, is used to combine the temperature characteristics dominated by human activities and the temperature characteristics dominated by environmental factors to segment different building heat load scenario modes.

[0005] Preferably, the thermal dynamic analysis module includes: The data sampling subunit is used to collect temperature data of each room at a preset cycle under a specific scenario mode; its sampling method includes collecting at least one set of data containing 24-36 temperature sampling points at a cycle of 5-6 minutes. The pattern recognition subunit, based on the temperature data set within each sampling period, is used to identify temperature fluctuation patterns and classify the patterns into stable patterns, adjustable patterns, and intervention patterns according to the fluctuation amplitude. The temperature control strategy formulation subunit, based on the identified temperature fluctuation patterns, formulates differentiated temperature regulation strategies, including: In stable mode, maintain the existing heat energy distribution; In adjustable mode, small, fine adjustments can be made, with an adjustment range of 1–2°C. In intervention mode, large-scale adjustment or directional shutdown is performed, with an adjustment range of 3-5°C, or the heat energy transfer to the area is suspended; The performance verification subunit is used to monitor the temperature stability of each room after the temperature control strategy is executed, and to evaluate the regulation performance, classifying the evaluation results into performance meeting the standard and performance abnormal.

[0006] Preferably, during the execution of the data sampling subunit, for the temperature data set under the intervention mode, the data of the first 5 consecutive sampling points are extracted, and the difference between adjacent points is calculated to form a difference sequence Δ=[Δ1,Δ2,...,Δ5]; Based on the difference between the first two of at least three sets of historical data, a fluctuation judgment threshold is set. When the real-time collected data difference sequence matches the judgment threshold, it is confirmed that the current intervention mode is in effect, and an early warning mechanism is triggered, while the heat energy supply to the target room is cut off; otherwise, the current state is maintained. After the heat energy supply to the target room is cut off, the system switches to high-frequency monitoring mode, collecting temperature fluctuation data every 10 seconds; it analyzes the time interval between adjacent temperature data and compares it with the benchmark time interval in the historical intervention mode; if the real-time time interval is longer than the benchmark time interval, it is determined that the intervention mode is showing a mitigation trend, and at this time, the heat energy supply can be restored to a limited extent according to the range set by the temperature control strategy formulation module for the intervention mode; otherwise, the heat energy supply interruption continues. When the range recovers to a limited extent of heat energy transfer, a stability assessment window is initiated for at least 6 sampling cycles. Within this window, if the continuously collected temperature difference values ​​are all less than the fluctuation judgment threshold, it is determined that the stable recovery state has been entered; otherwise, it is determined that the unstable recovery state has been entered.

[0007] Preferably, when in an unstable recovery state, the correlation between the current temperature control strategy and the state is analyzed; a tentative fixed heat transfer value is set, and the probability weight of this transfer value leading to an unstable state is calculated according to the following formula: ; Where, d t This represents the temperature difference collected at time t under a fixed delivery value; M is the maximum temperature value collected within the evaluation window, T is the statistical duration, and m is the minimum temperature value collected during the same period. If the weight is greater than the preset risk threshold, the fixed transmission value is adjusted downward; if the weight does not exceed the risk threshold, the heat energy transmission interruption is maintained until it returns to a stable recovery state.

[0008] Preferably, when adjusting the fixed conveying value downward, a step adjustment is adopted with a step size of 1 to 2 degrees. The adjusted temperature data were sampled using the Min-Max normalization method, and the correlation between the new transport values ​​and the trend towards stability was evaluated. The results were estimated using the following formula: ; Where S is the duration of the new delivery value; θ j τ represents the temperature data sampled for the j-th time during this period; τ is the predicted time required for the temperature to stabilize. If the temperature data stabilizes within the predicted time, the new delivery value is deemed valid; otherwise, the heat energy delivery is interrupted again.

[0009] Preferably, once the temperature data stabilizes, evidence-based analysis and the Delphi method are used to identify the key sampling point that causes the largest temperature difference and analyze its trend. If the trend shows a continuous convergence, the stable state is determined to be persistent; otherwise, it is determined to be persistent, and the input value is further fine-tuned until a persistent stable state is reached.

[0010] Preferably, after fine-tuning the delivery value, a large-scale sampling simulation of the temperature data is performed using the Monte Carlo method, and the sampling results are decomposed into multiple stability evaluation indicators. If the simulation data shows that the temperature difference is converging, the effective delivery value at this time is recorded and stored, and its weight in the historical optimal solution is calculated. When entering the intervention mode again, this delivery value is used for regulation first. If the simulation data does not show convergence, the delivery interruption strategy will be executed when encountering a similar intervention mode in the future.

[0011] The present invention has at least the following beneficial effects: 1. By accurately identifying and distinguishing temperature fluctuations dominated by human activities and environmental factors, it can achieve customized temperature control for different functional areas such as living rooms and bedrooms, as well as rooms with different orientations, effectively solving the problems of energy waste and insufficient comfort caused by the one-size-fits-all approach of traditional central air conditioning systems.

[0012] 2. By establishing three scenario modes—stable, adjustable, and interventional—the system can dynamically formulate and execute gradient strategies ranging from maintenance and fine-tuning to mandatory intervention, ensuring the timeliness and accuracy of temperature control. This significantly improves energy efficiency while guaranteeing a personalized and comfortable experience.

[0013] 3. Once the system enters intervention mode, its subsequent mitigation trend determination, stability assessment, and delivery value optimization mechanism constitute a complete closed-loop control loop, which can actively guide the system out of the abnormal state and restore stability, significantly enhancing the robustness and reliability of the system.

[0014] 4. The system not only provides users with a seamless and comfortable indoor environment, but also reduces long-term energy consumption and equipment wear through preventive thermal energy scheduling and strategic interruption, providing reliable technical support for realizing green and low-carbon smart buildings. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the modules provided in Embodiment 1 of the present invention; Figure 2 This is a unit diagram of the data acquisition module provided in Embodiment 1 of the present invention; Figure 3 This is a unit diagram of the thermal dynamic analysis module provided in Embodiment 1 of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "including," "having," and any variations are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0019] Example 1 This embodiment provides a compartmentalized temperature control system, such as Figure 1 As shown, it includes: The information acquisition module is used to acquire historical temperature control data of the target building and extract temperature change characteristics from the historical temperature control data. Temperature change characteristics include temperature fluctuation characteristics caused by room function, orientation and human activities; and to build a temperature control database based on the historical temperature control data. Specifically, the system utilizes time-series data recorded by sensors deployed in various rooms of the building, including temperature, humidity, and occupancy data, while also integrating architectural drawings and energy management system logs. This data is used to determine room functions and orientations from diverse data sources. In the data preprocessing stage, the system cleans and aligns the raw data to eliminate outliers and recording errors. Subsequently, feature engineering algorithms extract key temperature change features from the structured historical data. For example, by analyzing temperature curves over different time periods, such as weekday daytime and nighttime, the system identifies short-term rapid temperature rise characteristics unique to living rooms as activity areas and highly correlated with occupancy. By comparing the different temperature rise rates and fluctuation patterns of east- and west-facing bedrooms receiving solar radiation in summer and winter, the system identifies long-term heat load characteristics related to orientation. Cluster analysis is then used to separate typical temperature fluctuation patterns corresponding to occupancy activities, such as cooking in the kitchen and sleeping in the bedroom, from the overall data. Finally, these extracted and labeled feature data, along with their corresponding scenario labels (e.g., west-facing living rooms - summer weekday afternoons), are structured and stored in the temperature control database, forming a knowledge base that can be quickly queried by subsequent modules and used to train machine learning models.

[0020] The data acquisition module communicates with the temperature control database and is used to acquire real-time temperature data characteristics from the database. The aforementioned data acquisition units include, for example, Figure 2 As shown: The data area molecular unit, based on the characteristics of the collected temperature data, is used to classify the data according to the dominant factors affecting temperature fluctuations. The classification method includes distinguishing temperature data characteristics into human activity-dominated temperature characteristics and environmental factor-dominated temperature characteristics; among them, human activity-dominated temperature characteristics are related to the presence and activity intensity of people in a specific room; The scenario segmentation subunit, responding to the classification results of the data differentiation module, is used to combine human activity-driven temperature characteristics and environmental factor-driven temperature characteristics to segment different building heat load scenario patterns.

[0021] Specifically, the core task of the data acquisition module is not simply to collect raw temperature readings, but to perform intelligent feature extraction and classification. The data unit acts as the brain of this process. Its implementation relies on a pre-trained classification model, such as a decision tree-based or support vector machine-based classifier. This model receives real-time temperature data streams and analyzes their fluctuation patterns, such as whether the temperature rises rapidly and then remains stable (e.g., due to multiple people entering the living room) or rises slowly and steadily (e.g., due to afternoon afternoon sun). Simultaneously, it integrates sensor signals from people, the time of day, and inherent room attributes, such as the kitchen during dinner time. By matching these real-time patterns with the knowledge base established by the information acquisition module, the model can determine with a high probability whether the main driving factor of the current temperature fluctuation is human activity (e.g., evening gatherings in the living room) or environmental factors (e.g., afternoon sun exposure in the master bedroom), thus completing the dynamic classification of data features.

[0022] Following this classification, the scenario segmentation subunit makes higher-level decisions. Acting as a rule engine or scenario aggregator, it combines the output of the data segmentation subunit with additional system state parameters, such as outdoor weather forecasts and overall building energy consumption targets. For example, when it simultaneously receives data showing both occupant activity dominance (living room) and environmental factors dominance (high outdoor temperature), it doesn't treat them in isolation but merges them to generate a composite high-load-occupant-activity scenario pattern. Conversely, if only environmental factors dominance and low room temperature are identified in the bedroom at night, it might be classified as a low-load-insulation scenario pattern. This segmentation process provides a clear and actionable contextual framework for the subsequent control strategies adopted by the system. The thermal dynamics analysis module is used to analyze the dynamic temperature change patterns of a building under different heat load scenarios. Furthermore, the aforementioned thermal dynamics analysis module, such as Figure 3 The following are included: The data sampling subunit is used to collect temperature data of each room at a preset cycle under a specific scenario mode; its sampling method includes collecting at least one set of data containing 24-36 temperature sampling points at a cycle of 5-6 minutes. The pattern recognition subunit, based on the temperature data set within each sampling period, is used to identify temperature fluctuation patterns and classify the patterns into stable patterns, adjustable patterns, and intervention patterns according to the fluctuation amplitude. The temperature control strategy formulation subunit, based on the identified temperature fluctuation patterns, formulates differentiated temperature regulation strategies, including: In stable mode, maintain the existing heat energy distribution; In adjustable mode, small, fine adjustments can be made, with an adjustment range of 1–2°C. In intervention mode, large-scale adjustment or directional shutdown is performed, with an adjustment range of 3-5°C, or the heat energy transfer to the area is suspended; The performance verification subunit is used to monitor the temperature stability of each room after the temperature control strategy is executed, and to evaluate the regulation performance, classifying the evaluation results into performance meeting the standard and performance abnormal.

[0023] Specifically, the thermal dynamics analysis module serves as the intelligent decision-making center of the entire system, its functions implemented through a tightly collaborative pipeline of sub-units. The data sampling sub-unit acts first, not through simple random sampling, but by intelligently adjusting its sampling strategy based on the scenario patterns set by the previous module. For example, in an afternoon afternoon afternoon with afternoon sun exposure, it will densely collect 24-36 temperature sampling points in the affected room every 5-6 minutes, forming a high-resolution temperature snapshot. This short-cycle, high-density sampling strategy aims to capture the instantaneous details and micro-trends of temperature changes, laying the data foundation for accurate analysis.

[0024] Subsequently, the pattern recognition subunit begins operation. It receives the aforementioned dataset and applies a series of algorithms, such as calculating the standard deviation, slope, or good fit to a baseline curve within a sliding window, to quantify the amplitude and severity of temperature fluctuations. Based on preset thresholds, this subunit abstracts continuous, complex temperature fluctuations into three distinct operating modes: a stable mode (minor fluctuations within a comfortable range), an adjustable mode (controllable deviation trends), and an intervention mode (severe or persistent uncontrolled fluctuations). This classification transforms continuous physical signals into discrete, executable instructions.

[0025] Next, the temperature control strategy formulation subunit acts as a rule engine, mapping specific control commands to each mode. It is a typical IF-THEN logic actuator: if the mode is stable, it outputs a maintain command; if it is adjustable, it calculates a precise adjustment within the 1-2℃ range; if it requires intervention, it decisively triggers a large adjustment (3-5℃) or executes a strong intervention command for directional shutdown. Finally, the performance verification subunit shuts down the entire control loop. For a specific period after strategy execution, it continuously monitors temperature data to assess whether the system has quickly and smoothly achieved the expected goals. It binary-codes the result as performance met or performance abnormal, providing the system with the most direct action feedback.

[0026] The intelligent monitoring terminal is used to bind the identification information of each room and its associated users, receive the uploaded real-time environmental data and update the backend; when the evaluation result is abnormal performance, it sends a prompt message about the operating status to the associated users.

[0027] Specifically, during the initialization phase, system administrators or users need to use this interface to bind room identification information to their associated users. For example, binding the master bedroom to user A's mobile phone number, and the living room to the family WeChat group. This process establishes a precise information transmission path. The terminal continuously receives real-time environmental data uploaded from sensors and processing units in each room via IoT communication protocols such as MQTT and HTTP. This includes data on temperature, humidity, equipment status, and evaluation results generated by the performance verification subunit. This data is structured and updated to the backend database, forming a queryable historical record and a real-time operation dashboard. The core logic lies in its built-in alarm engine: this engine continuously monitors the performance evaluation results, and once it determines that the performance is abnormal—for example, if the temperature cannot be stabilized after multiple attempts to adjust the system, or if the energy consumption far exceeds the predicted value for that scenario—the engine will automatically trigger a notification process, sending a prompt message to the associated user via SMS, APP push, or email based on the preset binding relationship. This message is not obscure data, but a processed and easy-to-understand alarm, such as "The temperature adjustment in the master bedroom is abnormal, possibly due to the window being open; please check."

[0028] Example 2 Based on the above embodiment one, in the execution of the above data sampling subunit, for the temperature data set under the intervention mode, the data of the first 5 consecutive sampling points are extracted, and the difference between adjacent points is calculated to form a difference sequence Δ=[Δ1,Δ2,...,Δ5]; Based on the difference between the first two of at least three sets of historical data, a fluctuation judgment threshold is set. When the real-time collected data difference sequence matches the judgment threshold, it is confirmed that the current intervention mode is in effect, and an early warning mechanism is triggered, while the heat energy supply to the target room is cut off; otherwise, the current state is maintained. After the heat energy supply to the target room is cut off, the system switches to high-frequency monitoring mode, collecting temperature fluctuation data every 10 seconds. The system analyzes the time interval between adjacent temperature data and compares it with the baseline time interval in the historical intervention mode. If the real-time time interval is longer than the baseline time interval, it is determined that the intervention mode is showing a mitigation trend. At this time, the heat energy supply can be restored to a limited extent according to the range set by the temperature control strategy module for the intervention mode. Otherwise, the heat energy supply interruption continues. When the range recovers limited heat energy transfer, a stability assessment window is initiated for at least 6 sampling cycles. Within this window, if the continuously collected temperature difference values ​​are all less than the fluctuation judgment threshold, it is determined that the stable recovery state has been entered; otherwise, it is determined that the unstable recovery state has been entered.

[0029] Specifically, when a temperature anomaly is detected, the system does not rely on a single instantaneous reading. Instead, it extracts data from five consecutive sampling points and calculates the differences between adjacent points to form a difference sequence Δ. This sequence reflects the rate and direction of temperature change, capturing the essence of the runaway situation more effectively than a single temperature value. The system then compares this real-time sequence with a fluctuation judgment threshold derived from at least three sets of historical intervention data. This threshold represents the initial characteristics of typical runaway events in history. When the real-time sequence matches this threshold, the system can confirm the intervention mode with high confidence and immediately execute the ultimate protective command to cut off heat transfer.

[0030] After the heating supply was cut off, the system did not passively wait but instead switched to a high-frequency monitoring state with a cycle of 10 seconds. At this time, the focus of its analysis shifted from the amplitude of temperature changes to the inertia of temperature changes—that is, evaluating the system's dynamic response by analyzing the time interval between the generation of adjacent temperature data. If it was found that the time interval between temperature changes was longer, that is, the real-time time interval was longer than the historical benchmark, it indicated that the system's violent fluctuations were losing momentum and the thermal inertia was decreasing, thus indicating a mitigation trend. This is a more advanced intelligent judgment. Based on this judgment, the system attempted to restore a limited amount of heat energy transfer within the preset intervention mode range and immediately initiated a stability assessment window that lasted for at least 6 sampling cycles to verify whether the restoration action was truly effective and to ensure that the system would not become unstable again due to premature or excessive energy input.

[0031] Furthermore, when in an unstable recovery state, the correlation between the current temperature control strategy and the state is analyzed; a tentative fixed heat transfer value is set, and the probability weight of this transfer value leading to an unstable state is calculated according to the following formula: ; Where, d t This represents the temperature difference collected at time t under a fixed delivery value; M is the maximum temperature value collected within the evaluation window, T is the statistical duration, and m is the minimum temperature value collected during the same period. If the weight is greater than the preset risk threshold, the fixed transmission value is adjusted downward; if the weight does not exceed the risk threshold, the heat energy transmission interruption is maintained until it returns to a stable recovery state.

[0032] Secondly, when adjusting the fixed conveying value downward in the above embodiments, a step adjustment is adopted with a step size of 1 to 2 degrees Celsius. The adjusted temperature data were sampled using the Min-Max normalization method, and the correlation between the new transport values ​​and the trend towards stability was evaluated. The results were estimated using the following formula: ; Where S is the duration of the new delivery value; θ jτ represents the temperature data sampled for the j-th time during this period; τ is the predicted time required for the temperature to stabilize. If the temperature data stabilizes within the predicted time, the new delivery value is deemed valid; otherwise, the heat energy delivery is interrupted again.

[0033] Furthermore, once the temperature data stabilizes, evidence-based analysis and the Delphi method are used to identify the key sampling points that cause the largest temperature difference and analyze their changing trends. If the trend shows a continuous convergence, the stable state is determined to be persistent; otherwise, it is determined to be unsustainable, and the input value is further fine-tuned until a persistent stable state is reached.

[0034] After fine-tuning the delivery value, the Monte Carlo method is used to perform large-scale sampling simulation of the temperature data, and the sampling results are decomposed into multiple stability evaluation indicators. If the simulation data shows that the temperature difference is converging, the effective delivery value at this time is recorded and stored, and its weight in the historical optimal solution is calculated. When entering the intervention mode again, this delivery value is used first for regulation. If the simulation data does not show convergence, the delivery interruption strategy will be executed when encountering a similar intervention mode in the future.

[0035] Specifically, after the temperature data appears to stabilize, the analysis doesn't immediately stop. Instead, it initiates a more refined retrospective and predictive diagnostic process. It first employs evidence-based analysis and the Delphi method: from the fluctuating data before stabilization, it identifies several key sampling points that cause the largest temperature differences, much like a doctor focusing on indicators during the most critical moments of a patient's condition. Subsequently, the system analyzes the changing trends of the largest fluctuations represented by these key points after stabilization. This process is similar to organizing multiple experts. Different analytical models within the system consult, reaching a consensus through iterative analysis: if all key fluctuation trends show continuous convergence, the stability is deemed solid and sustainable; conversely, if they don't, the current stability is deemed fragile and temporary, and the system continues to fine-tune the input values ​​to seek a more stable equilibrium.

[0036] Once a delivery value that can pass continuous verification is found through fine-tuning, the system further employs the Monte Carlo method for stress testing. Based on current environmental conditions and the delivery value, it performs thousands of large-scale random sampling simulations of future temperature changes to predict the system's possible performance under various random disturbances. If the vast majority of simulation results show that the temperature difference is converging, it proves that the delivery value is robust, and the system will store it as a valid delivery value, along with its successful preconditions, such as the later stages of the winter-western-sunlit living room intervention mode, and its weight in all historical successful scenarios, in the knowledge base. In the future, when the system re-enters a similar intervention mode, it will prioritize calling this verified value, achieving a leap from zero-based exploration to experience reuse. If the simulation results show that the value is still unstable, such scenarios will be marked as uncontrollable, and a delivery interruption strategy will be directly adopted in the future to save energy. Example 3 This invention provides a non-transitory computer-readable storage medium storing at least one instruction or at least one program segment, which is loaded and executed by a processor to implement the following steps: Obtain historical temperature control data of the target building, extract temperature change characteristics caused by room function, orientation and human activities from the historical temperature control data, and build a temperature control database based on this; Real-time temperature data features are collected from the temperature control database. Based on these features, the current heat load scenario of the building is identified, and the dynamic temperature change pattern of the building is analyzed under this scenario. After implementing the temperature control strategy based on the dynamic temperature change pattern, monitor the temperature stability of each room, evaluate the regulation efficiency, and generate evaluation results indicating whether the efficiency meets the standard or is abnormal. Record the identification information of each room and its associated users, and receive real-time environmental data; when the evaluation result is abnormal performance, send a system operation status prompt message to the corresponding associated users.

[0037] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory, ROM, programmable ROM, PROM, electrically programmable ROM, EPROM, electrically erasable programmable ROM, EEPROM, or flash memory. Volatile memory can include random access memory, RAM, or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM, SRAM, dynamic RAM, DRAM, synchronous DRAM, SDRAM, dual data rate SDRAM, DDRSDRAM, enhanced SDRAM, ESDRAM, synchronous link, Synchlink DRAM, SLDRAM, memory bus, Rambus direct RAM, RDRAM, direct memory bus dynamic RAM, DRDRAM, and memory bus dynamic RAM. RDRAM, etc.

[0038] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0039] Example 4 This invention provides an electronic device, including a processor and a memory, wherein the memory stores at least one instruction or at least one program segment, and the at least one instruction or the at least one program segment is loaded and executed by the processor to implement the following steps: Obtain historical temperature control data of the target building, extract temperature change characteristics caused by room function, orientation and human activities from the historical temperature control data, and build a temperature control database based on this; Real-time temperature data features are collected from the temperature control database. Based on these features, the current heat load scenario of the building is identified, and the dynamic temperature change pattern of the building is analyzed under this scenario. After implementing the temperature control strategy based on the dynamic temperature change pattern, monitor the temperature stability of each room, evaluate the regulation efficiency, and generate evaluation results indicating whether the efficiency meets the standard or is abnormal. Record the identification information of each room and its associated users, and receive real-time environmental data; when the evaluation result is abnormal performance, send a system operation status prompt message to the corresponding associated users.

[0040] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A compartment temperature control system, characterized in that, include: The information acquisition module is used to acquire historical temperature control data of the target building and extract temperature change characteristics from the historical temperature control data. The temperature change characteristics include temperature fluctuation characteristics caused by room function, orientation and human activities. A temperature control database is constructed based on the historical temperature control data; The data acquisition module is communicatively connected to the temperature control database and is used to acquire real-time temperature data characteristics from the database; The thermal dynamics analysis module is used to analyze the dynamic temperature change patterns of the building under the different heat load scenarios. The intelligent monitoring terminal is used to bind the identification information of each room and its associated users, receive the uploaded real-time environmental data and update the backend; when the evaluation result is abnormal performance, it sends a prompt message about the operating status to the associated users.

2. The compartment temperature control system according to claim 1, characterized in that, The data acquisition unit includes: The data area molecular unit, based on the characteristics of the collected temperature data, is used to classify the data according to the dominant factors affecting temperature fluctuations. The classification method includes distinguishing the temperature data characteristics into human activity-dominated temperature characteristics and environmental factor-dominated temperature characteristics; wherein, the human activity-dominated temperature characteristics are related to the presence and activity intensity of people in a specific room; The scenario segmentation subunit, in response to the classification results of the data differentiation module, is used to combine the temperature characteristics dominated by human activities and the temperature characteristics dominated by environmental factors to segment different building heat load scenario modes.

3. The compartment temperature control system according to claim 1, characterized in that, The thermal dynamic analysis module includes: The data sampling subunit is used to collect temperature data of each room at a preset cycle under a specific scenario mode; its sampling method includes collecting at least one set of data containing 24-36 temperature sampling points at a cycle of 5-6 minutes. The pattern recognition subunit, based on the temperature data set within each sampling period, is used to identify temperature fluctuation patterns and classify the patterns into stable patterns, adjustable patterns, and intervention patterns according to the fluctuation amplitude. The temperature control strategy formulation subunit, based on the identified temperature fluctuation patterns, formulates differentiated temperature regulation strategies, including: In stable mode, maintain the existing heat energy distribution; In adjustable mode, small, fine adjustments can be made, with an adjustment range of 1–2°C. In intervention mode, large-scale adjustment or directional shutdown is performed, with an adjustment range of 3-5°C, or the heat energy transfer to the area is suspended; The performance verification subunit is used to monitor the temperature stability of each room after the temperature control strategy is executed, and to evaluate the regulation performance, classifying the evaluation results into performance meeting the standard and performance abnormality.

4. The compartment temperature control system according to claim 3, characterized in that, During the execution of the data sampling subunit, for the temperature data set under the intervention mode, the data of the first 5 consecutive sampling points are extracted, and the difference between adjacent points is calculated to form a difference sequence Δ=[Δ1,Δ2,...,Δ5]; Based on the difference between the first two of at least three sets of historical data, a fluctuation judgment threshold is set. When the real-time collected data difference sequence matches the judgment threshold, it is confirmed that the current intervention mode is in effect, and an early warning mechanism is triggered, while the heat energy supply to the target room is cut off; otherwise, the current state is maintained. After the heat energy supply to the target room is cut off, the system switches to high-frequency monitoring mode, collecting temperature fluctuation data every 10 seconds; the time interval between the generation of adjacent temperature data is analyzed and compared with the benchmark time interval in the historical intervention mode; If the real-time time interval is longer than the reference time interval, it is determined that the intervention mode is showing a mitigation trend. At this time, the heat energy transfer can be restored to a limited extent according to the range set by the temperature control strategy formulation module for the intervention mode; otherwise, the heat energy transfer interruption will continue. When the range recovers to a limited extent of heat energy transfer, a stability assessment window is initiated for at least 6 sampling cycles. Within this window, if the continuously collected temperature difference values ​​are all less than the fluctuation judgment threshold, it is determined that the stable recovery state has been entered; otherwise, it is determined that the unstable recovery state has been entered.

5. The compartment temperature control system according to claim 4, characterized in that, When in an unstable recovery state, analyze the correlation between the current temperature control strategy and the state; set a tentative fixed heat transfer value and calculate the probability weight of this transfer value leading to an unstable state, according to the following formula: ； Where, d t This represents the temperature difference collected at time t under a fixed delivery value; M is the maximum temperature value collected within the evaluation window, T is the statistical duration, and m is the minimum temperature value collected during the same period. If the weight is greater than the preset risk threshold, the fixed transmission value is adjusted downward; if the weight does not exceed the risk threshold, the heat energy transmission interruption is maintained until it returns to a stable recovery state.

6. The compartment temperature control system according to claim 5, characterized in that, When adjusting the fixed conveying value downward, a step adjustment is adopted with a step size of 1 to 2 degrees Celsius. The adjusted temperature data were sampled using the Min-Max normalization method, and the correlation between the new transport values ​​and the trend towards stability was evaluated. The results were estimated using the following formula: ； Where S is the duration of the new delivery value; θ j τ represents the temperature data sampled for the j-th time during this period; τ is the predicted time required for the temperature to stabilize. If the temperature data stabilizes within the predicted time, the new delivery value is deemed valid; otherwise, the heat energy delivery is interrupted again.

7. The compartment temperature control system according to claim 6, characterized in that, Once the temperature data stabilizes, evidence-based analysis and the Delphi method are used to identify the key sampling point that causes the largest temperature difference and analyze its trend. If the trend shows a continuous convergence, the stable state is determined to be persistent; otherwise, it is determined to be unsustainable, and the input value is further fine-tuned until a stable state is achieved.

8. The compartment temperature control system according to claim 7, characterized in that, After fine-tuning the delivery value, the Monte Carlo method is used to perform large-scale sampling simulation of the temperature data, and the sampling results are decomposed into multiple stability evaluation indicators. If the simulation data shows that the temperature difference is converging, the effective delivery value at this time is recorded and stored, and its weight in the historical optimal solution is calculated. When entering the intervention mode again, this delivery value is used for regulation first. If the simulation data does not show convergence, the delivery interruption strategy will be executed when encountering a similar intervention mode in the future.

9. A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores at least one instruction or at least one program segment, characterized in that, The at least one instruction or the at least one program segment is loaded and executed by the processor to implement the steps of the compartment temperature control system as described in any one of claims 1-8.

10. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the steps of the compartment temperature control system as described in any one of claims 1-8.

Images