Home system switch intelligent monitoring control system based on multi-source data fusion

Abstract

The application belongs to the technical field of home switch control, and specifically discloses a home system switch intelligent monitoring control system based on multi-source data fusion, which comprises an environment sensing identification module, a centralized switch determination module, a task priority decision module and a hierarchical centralized execution module. The application makes a control task triggering judgment from two dimensions of an over-limit amplitude and an over-limit time window number based on a continuous time window average value, makes up for the deficiency of frequent start-stop of a switch caused by instantaneous over-limit, generates a corresponding task execution priority or a task group execution priority based on an enabled switch level, solves the problem that a fixed flow or a simple condition judgment is relied on in the current multi-task concurrency, and a coupling influence between devices cannot be coordinated, thereby realizing dynamic adaptation of task scheduling from independent execution to cooperative control, avoiding control effect conflict or energy consumption increase caused by improper execution sequence, and improving energy saving effect.

Description

Technical Field

[0001] This invention belongs to the field of home switch control technology, and more specifically, relates to a smart monitoring and control system for home system switches based on multi-source data fusion. Background Technology

[0002] In existing smart home environments, control terminals and controlled terminals are typically arranged independently and in a distributed manner. To overcome the inconvenience of operating multiple independent points, integrated switches have been introduced into smart home control, enabling centralized management and control of multiple similar controlled terminals. To ensure the control efficiency and user experience of this integrated switch, its operation process needs to be monitored and controlled.

[0003] Existing technologies, such as the intelligent home environment sensing switch control system disclosed in Chinese invention patent application No. 2019102131503, dynamically sense environmental status and user behavior by integrating an environmental sensing module and a human activity recognition module, thereby automatically triggering preset scene responses, realizing adaptive adjustment of the device and improving comfort and energy saving.

[0004] Existing technologies, such as the smart home electronic switch disclosed in Chinese invention patent application number 201510172627X, achieve precise monitoring and remote control of the switch status through the collaboration of a local detection module and a business logic module, thereby improving the convenience and security of control.

[0005] However, the aforementioned existing technologies still have the following shortcomings when facing specific application scenarios of integrated switches: First, the triggering of environmental control basically depends on whether the parameters exceed a fixed threshold. If the parameters only momentarily exceed the threshold, it will cause frequent switching actions of the device, leading to increased energy consumption.

[0006] Secondly, when faced with complex situations where multiple tasks are triggered concurrently at the same time, existing solutions usually rely on fixed preset processes or simple condition judgments to execute tasks, lacking consideration of the dynamic correlation between environmental factors between tasks, making it difficult to guarantee the task scheduling effect and thus failing to quickly achieve the control target.

[0007] Meanwhile, different controlled terminals in the home environment are not independent; their control commands are strongly coupled and mutually influential. For example, starting a fresh air system will change the indoor temperature. If this is done concurrently with a temperature control command, the difference in their execution order will lead to completely different environmental results and energy consumption levels. Currently, their control priority is not considered, making it difficult to achieve the expected energy-saving effect and coordinated control effect, resulting in insufficient overall control coordination. Summary of the Invention

[0008] In view of this, in order to solve the above problems, a smart monitoring and control system for home system switches based on multi-source data fusion is proposed.

[0009] The objective of this invention can be achieved through the following technical solution: This invention provides a smart monitoring and control system for home system switches based on multi-source data fusion. The system includes: an environmental perception and identification module, which determines task triggering based on the average value of environmental parameters within a continuous time window, and constructs a task list containing target environmental parameter identifiers and controlled terminals.

[0010] The centralized control switch determination module enables the corresponding level of integrated control switch according to the type of controlled terminal. The level includes a secondary switch for controlling a single type of controlled terminal and a primary switch for controlling multiple secondary switches.

[0011] The task priority decision module, if the secondary switch is enabled, calculates the urgency of each control task based on the task list and generates the task execution priority accordingly. If the primary switch is enabled, it quantifies the coupling effect between task groups based on historical operation logs through multiple linear regression analysis to obtain the synergistic correlation strength, and generates the task group execution priority based on the control urgency and synergistic correlation strength.

[0012] The hierarchical centralized control execution module generates and sends corresponding integrated control switch execution and control commands based on the execution priority.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention makes the control task triggering judgment based on the average value of the continuous time window from two dimensions: the over-limit amplitude and the number of over-limit time windows. This makes up for the shortcomings of the frequent start-stop switching caused by the instantaneous over-limit, effectively filters out the interference of short-term environmental fluctuations, thereby avoiding the frequent start-stop action of the controlled terminal due to the instantaneous parameter over-limit, and reducing unnecessary energy consumption and equipment wear.

[0014] (2) This invention enables the corresponding level of integrated control switch according to the type of controlled terminal, and generates task execution priority or task group execution priority based on the enabled switch level. This solves the problem that currently, when multiple tasks are concurrent, only fixed processes or simple condition judgments are relied upon, and the coupling effects between devices cannot be coordinated. This realizes the dynamic adaptation of task scheduling from independent execution to collaborative control, avoids the conflict of control effects or increased energy consumption caused by improper execution order, and improves the overall coordination and control efficiency of multi-device collaborative operation.

[0015] (3) When generating priorities, this invention fully considers the dynamic correlation between environmental parameters by performing urgency analysis and synergy correlation strength analysis. Thus, it can assess the urgency of a single task based on the real-time status and changing trend of environmental parameters, and quantitatively assess the synergy or conflict relationship between different task combinations. At the same time, while ensuring the speed of critical response, it greatly improves the energy-saving effect and control effect.

[0016] (4) This invention quantifies the coupling effect by performing multivariate regression analysis based on historical operating data, and dynamically corrects the initial synergy strength value according to the distribution ratio of direct and indirect association markers, so that the calculation results of synergy association strength can more accurately reflect the real and verifiable degree of mutual influence between devices, solve the problem of inaccuracy and inconsistency caused by subjective experience judgment, and thus provide reliable quantitative input of synergy relationship for priority decision-making, ensuring the stability of the final control results. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the 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.

[0018] Figure 1 This is a schematic diagram of the system module connections of the present invention.

[0019] Figure 2 This is a schematic diagram of the overall implementation process of the present invention.

[0020] Figure 3 This is a schematic diagram of the switch level structure of the present invention. Detailed Implementation

[0021] 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.

[0022] Please see Figure 1 and Figure 2 As shown, the present invention provides a smart monitoring and control system for home system switches based on multi-source data fusion. The system includes: an environmental perception and identification module, a centralized control switch determination module, a task priority decision module, and a hierarchical centralized control execution module.

[0023] In the above, the centralized control switch determination module is connected to the environmental perception and identification module and the task priority decision module, respectively, and the task priority decision module is connected to the hierarchical centralized control execution module.

[0024] The environmental perception and recognition module determines task triggering based on the average value of environmental parameters within a continuous time window and constructs a task list that includes target environmental parameter identifiers and controlled terminals.

[0025] The environmental parameters include, but are not limited to, at least one of temperature, humidity, light intensity, and air quality parameters, such as carbon dioxide concentration and PM2.5 concentration.

[0026] In smart home systems, if adjustments are triggered solely based on whether instantaneous environmental parameters exceed fixed thresholds, it is highly susceptible to generating numerous unnecessary control commands due to the pervasive, transient, and random fluctuations in the environment. This not only wastes energy but also accelerates equipment wear and tear, thereby negatively impacting the user experience.

[0027] Based on this, the present invention constructs a task triggering determination based on two dimensions: the over-limit magnitude and the number of over-limit time windows, using the average value of continuous time windows, and constructs a task list that includes at least the target environment parameter identifier and the controlled terminal.

[0028] Preferably, in a specific embodiment of the present invention, the environmental perception and recognition module specifically executes the following process: A1, real-time collection of at least one of the following parameters: temperature, humidity, light intensity, and air quality parameters of each functional area.

[0029] A2. Compare the real-time collected environmental parameters with their preset reference range.

[0030] A3. When an environmental parameter exceeds its preset reference range, a continuous time window is divided and extracted according to a preset fixed duration, wherein the fixed duration can preferably be set to 5 minutes.

[0031] A4. Calculate the average value of the environmental parameter within each time window and determine whether it meets any of the following conditions: the average value of N consecutive time windows exceeds its preset reference range, where N is an integer greater than 1.

[0032] The average value of a certain time window exceeds its preset reference range by a certain amount, which reaches the preset intervention deviation range.

[0033] A5. If any of the above conditions are met, the environmental parameter shall be recorded as the target environmental parameter.

[0034] A6. Generate a control task that includes the target environment parameter identifier, the controlled terminal corresponding to the target environment parameter, the functional area where it is located, the control direction, and the target control value.

[0035] A7. Summarize all control tasks and build a task list. If the task list is empty, no integrated control switches will be enabled, and the system will maintain its current state.

[0036] During the execution of steps A1-A7 by the aforementioned environmental perception and recognition module, the following supplementary explanations are required: The preset reference range is primarily based on human health and comfort standards, building environment codes, or the user's personalized needs. For example, the preset temperature reference range can be set to 22℃-28℃ in summer and 16℃-24℃ in winter, based on indoor air quality standards. The preset humidity reference range can be set to a relative humidity of 40%-60% that is comfortable for humans.

[0037] The target control value is the difference between the environmental parameter and the upper or lower limit of the preset reference range. Specifically, when the target environmental parameter exceeds the upper limit of its preset reference range, the target control value is the upper limit of the preset reference range minus the current target environmental parameter value; when the target environmental parameter exceeds the lower limit of its preset reference range, the target control value is the lower limit of the preset reference range minus the current target environmental parameter value.

[0038] The direction of regulation is determined by the sign of the target regulation value. When the target regulation value is negative, the direction of regulation is to lower or reduce it. When the target regulation value is positive, the direction of regulation is to raise or increase it.

[0039] Before a smart home system is put into use, control relationships are set in advance. Specifically, one or more target environmental parameters that can be adjusted are set for each type of controlled terminal, as well as the preset parameter range for automatic adjustment triggering of the corresponding target environmental parameters, and a control relationship between the controlled terminal and the target environmental parameters is established.

[0040] The controlled terminals include air conditioners, fresh air systems, humidifiers, etc. An example process for predefining one or more adjustable environmental parameters for each type of controlled terminal is as follows: temperature is defined as the target environmental parameter controlled by the air conditioner; humidity is defined as the target environmental parameter controlled by the humidifier or dehumidifier; and air quality parameters such as carbon dioxide concentration and PM2.5 concentration are defined as the target environmental parameters controlled by the fresh air system.

[0041] This invention, through its embodiment, determines the triggering of control tasks based on two dimensions: the magnitude of the exceedance and the number of exceedance time windows, using the average value of continuous time windows. This compensates for the shortcomings of frequent start-stop switching caused by instantaneous exceedances, effectively filters out brief environmental fluctuations, and thus avoids frequent start-stop actions of the controlled terminal due to instantaneous parameter exceedances, reducing unnecessary energy consumption and equipment wear.

[0042] The centralized control switch determination module enables the corresponding level of integrated control switch according to the type of controlled terminal. The level includes a secondary switch for controlling a single type of controlled terminal and a primary switch for controlling multiple secondary switches.

[0043] In smart home systems, when multiple environmental parameters simultaneously malfunction, triggering multiple concurrent control tasks, the controlled terminals may belong to different types. If all control commands are directly sent to each individual device switch, it becomes impossible to distinguish between independent single-point tasks and related collaborative tasks, making centralized coordinated control difficult and reducing the overall efficiency of control.

[0044] Based on this, such as Figure 3 As shown, this invention activates corresponding level integrated control switches based on the controlled terminal category. Specifically, it receives a task list from the environmental perception and recognition module. If all controlled terminals involved in the control tasks in the task list belong to the same category, a secondary switch controlling that category of controlled terminals is activated. This secondary switch directly associates with and controls all individuals of that category of controlled terminals. If all controlled terminals involved in the control tasks do not belong to the same category, a primary switch capable of synchronously and coordinately controlling these categories of controlled terminals is activated. The control commands issued by this primary switch can be simultaneously sent to multiple subordinate secondary switches.

[0045] It should be noted that, Figure 3 In this context, n represents the total number of controlled terminals, and m represents the total number of secondary switches associated with the corresponding primary switch.

[0046] This invention enables differentiated control for simple independent tasks and complex collaborative tasks by selecting to enable single-point secondary switch control or one-to-many primary switch collaborative control, providing targeted control solutions for scenarios of varying complexity.

[0047] If the secondary switch is enabled, the task priority decision module calculates the urgency of each control task based on the task list and generates the task execution priority accordingly. If the primary switch is enabled, it quantifies the coupling effect between task groups based on historical operation logs through multiple linear regression analysis to obtain the synergistic correlation strength, and generates the task group execution priority based on the control urgency and synergistic correlation strength.

[0048] Considering the concurrent triggering of multiple tasks, current fixed rules based on a single dimension, such as sorting based solely on the degree to which sensor readings deviate from a threshold, or executing tasks sequentially according to a preset fixed process, may lead to mutual interference between device actions, thereby reducing overall energy efficiency. Furthermore, fixed processes cannot adapt to dynamically changing task combinations and relationships. Therefore, this invention provides a priority generation rule that can dynamically adjust according to the control scenario while taking into account both task urgency and inter-device coordination.

[0049] Preferably, when the current control scenario is that the secondary switch is enabled, since the secondary switch only controls a single type of controlled terminal, it indicates that the control tasks in the current task list are relatively independent or weakly coupled. At this time, the control focus is on quickly responding to the most urgent environmental anomalies, that is, it is only necessary to calculate the control urgency of each control task and sort the control tasks in descending order according to their control urgency. This sorting result is the task execution priority.

[0050] As a preferred example, calculating the urgency of each control task includes: B1, calculating the degree of deviation between the target environmental parameters and the preset reference range, and using the degree of deviation as the benchmark control urgency.

[0051] It should be noted that the degree of deviation is quantified by calculating the absolute value of the relative deviation between the target environmental parameters and the upper or lower limit of the preset reference range.

[0052] B2. Perform linear fitting on the target environmental parameters within a preset time period to obtain the slope of the fitted line. Based on the slope and the deviation direction of the target environmental parameters relative to a preset reference range, determine whether to trigger dynamic compensation.

[0053] It should be noted that, in the process of calculating the urgency of regulation, in order to overcome the inability to predict the future trend of parameter changes based solely on the current deviation, this application introduces a step of linearly fitting the target environmental parameters within a preset time period to obtain their slope of change. This linear fitting process can specifically utilize existing linear fitting algorithms such as the least squares method.

[0054] By analyzing the sign and magnitude of the slope value corresponding to the fitted straight line, it is possible to quantify whether environmental parameters are continuously deteriorating. This provides a reliable basis for subsequent benchmark control urgency dynamic compensation and dynamic compensation trigger judgment, making subsequent control decisions more forward-looking and improving the timeliness of response and the effectiveness of intervention.

[0055] The determination of whether dynamic compensation is triggered includes: if the current target environmental parameter is higher than its preset upper limit and the slope of its fitted line is positive, or the current target environmental parameter is lower than the preset lower limit and the slope is negative, then dynamic compensation is triggered.

[0056] B3. If triggered, the baseline control urgency is dynamically compensated to generate the final control urgency; otherwise, the baseline control urgency is directly output as the final control urgency.

[0057] Specifically, the implementation process of dynamically compensating for the urgency of the benchmark regulation includes: first, dividing the preset time period evenly into multiple sub-time periods on the time axis, and linearly fitting the environmental parameter values ​​in each sub-time period to obtain the local slope reflecting the rate of change of that segment.

[0058] Subsequently, each local slope is compared with the slope of the fitted line for the entire preset time period. Sub-time periods with the same sign as the slope of the fitted line are recorded as sub-time periods in the same direction, indicating that the direction of change in these time periods is consistent with the overall trend.

[0059] Within the same-direction sub-periods, the absolute values ​​of the local slope and the absolute values ​​of the fitted line slope are further compared. Sub-periods with local slope absolute values ​​greater than or equal to the absolute values ​​of the fitted line slope are classified as enhanced sub-periods, indicating that the changes in this sub-period are more drastic than the overall changes. Sub-periods with local slope absolute values ​​less than the absolute values ​​of the fitted line slope are classified as weakened sub-periods, indicating that the changes in this sub-period are more gradual than the overall changes.

[0060] The number of strengthening and weakening sub-periods is counted and compared. If the number of strengthening sub-periods is greater than the number of weakening sub-periods, it indicates that there are multiple periods of accelerated change in the overall trend. The trend may be underestimated by the overall fitting smoothing. Therefore, the local slope with the largest absolute value is selected from the sub-periods in the same direction as the target slope to reflect the most dramatic change. If the number of strengthening sub-periods is less than or equal to the number of weakening sub-periods, it can be determined that the slope of the current overall fitting can truly reflect the current change. That is, the slope of the fitted line is directly used as the target slope.

[0061] Next, based on the absolute value of the target slope, the length of the preset time period, and the difference between the upper and lower limits of the preset reference range corresponding to the target environmental parameters, a normalized trend intensity value is calculated. The benchmark control urgency is numerically corrected using the normalized trend intensity value, and the corrected control urgency is output as the final control urgency.

[0062] The formula for calculating the normalized trend strength value is as follows: ,in, Indicates the strength of the normalization trend. Represents the absolute value of the target slope. Indicates the length of the preset time period. and These are the upper and lower limits of the preset reference range corresponding to the target environment parameters, respectively. This indicates that the Sigmoid function normalization calculation is performed. The Sigmoid function formula is an existing formula and will not be shown again.

[0063] The specific correction formula for the normalized trend strength value to numerically correct the baseline regulatory urgency is as follows: , Adjust the urgency level based on the benchmark. This is the revised level of urgency for regulation.

[0064] This invention avoids the smoothing and underestimation of drastic fluctuations by selecting representative target slopes, and enhances the sensitivity to continuously and rapidly deteriorating operating conditions by calculating the normalized trend strength, making subsequent regulation more forward-looking.

[0065] In another preferred embodiment, when the current control scenario involves activating a primary switch, since the primary switch controls multiple types of controlled terminals, there may be potential correlations between tasks. In this case, the control focus is on two aspects: the most urgent environmental anomalies and how to coordinate control commands to achieve the best overall effect. Therefore, this invention groups control tasks according to their controlled terminal categories and quantifies the coupling effect between task groups based on historical operation logs using multiple linear regression analysis to obtain the strength of synergistic correlation. Based on the urgency of control and the strength of synergistic correlation, the final execution priority of the task groups is determined, thereby ensuring the effectiveness of subsequent control.

[0066] It's important to note that when a smart home system is put into use, it continuously collects and records two types of timestamped data sequences. One type is the controlled terminal status sequence, recording the operating status of all controlled terminals, such as air conditioners, fresh air systems, and humidifiers, at various times, including their on / off status, speed settings, and mode settings. The other type is the environmental parameter sequence, recording the values ​​of various environmental parameters monitored at the same time and in the same space, such as temperature, humidity, carbon dioxide concentration, TVOC concentration, and PM2.5 concentration. These two sets of data together constitute the operation log, and combining the operation logs from various times yields the historical operation log.

[0067] In smart home systems, there is often a physical coupling effect between different controlled terminals. For example, the start and stop of a fresh air system can affect the indoor temperature, while the temperature control operation of an air conditioner may change airflow and humidity distribution. Currently, when scheduling multiple tasks, most systems ignore or rely on experience to roughly estimate the mutual influence between devices. This can lead to control commands potentially canceling each other out due to conflicts, or failing to achieve the optimal overall effect due to a lack of coordination.

[0068] Based on this, as a preferred embodiment, the present invention quantifies the coupling effect between task groups through multiple linear regression analysis. The specific analysis process includes: Step 1, extracting the working status of all controlled terminals and various environmental parameter values ​​recorded at the same time point from the historical operation log, constructing the controlled terminal status vector sequence and the environmental parameter vector sequence, and performing multiple linear regression analysis on the two to output the regression coefficients.

[0069] For example, the specific analysis process for performing multiple linear regression analysis on the above two sequences includes: taking the environmental parameter vector at each sampling time as the dependent variable and the state vectors of all controlled terminals at the same time as the independent variables, and then importing them into the least squares function to directly output a set of regression coefficients through the least squares method. Each regression coefficient represents the average expected change in a specific environmental parameter when the control parameter of a specific controlled terminal changes by one unit, while keeping the states of other controlled terminals constant.

[0070] It should be noted that the least squares method in the multiple linear regression analysis step is merely an exemplary algorithm. This invention does not limit the specific regression algorithm used; implementers can select other multiple linear regression algorithms according to specific practical needs, including but not limited to ridge regression, Lasso regression, and elastic networks. All the listed algorithms are prior art, and their specific implementation processes will not be elaborated in this application.

[0071] Step 2: Label the two task groups currently being analyzed as Group 1 and Group 2, and obtain the controlled terminals, target environmental parameters, and control directions (such as increasing temperature or decreasing humidity) marked in their control tasks.

[0072] Step 3: From the constructed task influence matrix, query the regression coefficients of the controlled terminals in the first group on the environmental parameters of the second group's tasks, and the regression coefficients of the controlled terminals in the second group on the environmental parameters of the first group's tasks. Then, convert the control directions of the two groups into cross coefficients, where the cross coefficient corresponding to an increase is +1 and the quantitative cross coefficient corresponding to a decrease is -1. Multiply the quantitative cross coefficient of the first group by the regression coefficients of the controlled terminals in the first group on the environmental parameters of the second group's tasks to obtain the cross-influence coefficient of the controlled terminals in the first group on the second group. Similarly, calculate the cross-influence coefficient of the controlled terminals in the second group on the first group using the same method. These are denoted as follows: and .

[0073] Step 4: Considering that the inhibitory effects of either party would directly offset the control effect and increase energy consumption, this is a conflict situation that must be avoided first. Therefore, if or If both conditions are met, a negative coupling effect is considered to exist. After excluding the influence of negative coupling, to maximize the synergistic potential, a positive coupling effect is defined as the presence of at least one-way promotion without any inhibition. That is, if... and Simultaneously established, or and Or and If so, then a positive coupling effect is determined to exist. And when... and If both are equal to 0, then it is determined that there is no coupling effect.

[0074] It should be noted that if the system is in the initial operation phase, or if the amount of historical operation log data does not reach the amount of data required for regression analysis, for example, if the amount of data does not reach 1,000 records and the cumulative number of operation days does not exceed one month, then there is no coupling effect by default. In this case, if the number of direct positive association markers is zero, then the collaborative association strength is directly set to 0.

[0075] As another preferred example, the specific process of obtaining the collaborative association strength includes: C1, randomly selecting a task group as the analysis object, and traversing other task groups.

[0076] C2. If there are two entities with the same target environmental parameter identifiers, they are marked as directly positive or directly negatively correlated depending on whether the control directions are consistent. If the control directions are consistent, they are marked as directly positively correlated; if the control directions are inconsistent, they are marked as directly negatively correlated.

[0077] C3. If there are no identical environmental parameter identifiers, when there is a positive coupling effect, it is marked as an indirect positive association; when there is a negative coupling effect, it is marked as an indirect negative association; and when there is no coupling effect, it is marked as no association.

[0078] C4. After completing the association marking between all groups, for each task group, count the number of other groups that have a positive association with it, and record it as the number of positively associated groups. Divide the number of positively associated groups by the total number of remaining task groups other than the task group to obtain the initial collaborative association strength of the task group.

[0079] C5. If the task group only has direct positive association markers, then the initial collaborative association strength shall be taken as its final collaborative association strength.

[0080] C6. Otherwise, adjust the initial cooperative association strength according to the distribution of its associated markers, and use the adjustment result as its final cooperative association strength.

[0081] In generating priorities, this invention fully considers the dynamic correlation between environmental parameters by performing urgency analysis and synergy strength analysis. This allows for the assessment of the urgency of a single control task based on the real-time status and changing trends of environmental parameters, as well as the quantitative assessment of the synergistic or conflicting relationships between different task combinations. At the same time, it significantly improves energy-saving and control effects while ensuring critical response speed.

[0082] To clearly illustrate the calculation process of the collaborative association strength, the following will use the analysis steps between two task groups as an example. Assume that in a smart home system, there are two task groups that need to be analyzed, denoted as task group 1 and task group 2. Also assume that the total number of task groups is 5.

[0083] Task group 1 contains one control task, with the controlled terminal being the air conditioner, the target environmental parameter being temperature, and the control direction being to decrease it. Task group 2 contains one control task, with the controlled terminal being the fresh air system, the target environmental parameter being carbon dioxide concentration, and the control direction being to decrease it. After comparison, there are no identical target environmental parameter identifiers in task group 1 and task group 2, so the historical operation logs of the air conditioner and fresh air system are extracted.

[0084] Based on the historical operation logs and the historical coupling effect judgment method described above, the cross-influence coefficients of both tasks are calculated to be -1, indicating that there is a negative coupling effect between task group 1 and task group 2.

[0085] The negative coupling effect is specifically manifested in the fact that the fresh air system reduces When outdoor air is introduced at a certain concentration, it may also introduce air at a higher temperature, thus interfering with the air conditioner's cooling objective. Conversely, when the air conditioner is set to lower the temperature, it may indirectly affect air circulation and... Distribution. Executing both simultaneously will cause them to interfere with each other.

[0086] Based on this judgment, indirect negative association labels are applied to these two groups. After completing the inter-group association analysis, the association labels for task group 1 are summarized. Assume the distribution of its association labels is as follows: indirect negative association with task group 2, direct positive association with task groups 3 and 4, and no association with task group 5.

[0087] According to statistics, the other groups that have a positive correlation with task group 1 are group 3 and group 4, totaling 2 groups. The collaborative correlation strength of task group 1 is calculated to be 0.5 according to the above-mentioned initial collaborative correlation strength calculation method.

[0088] Since there is a negative association marker in the association marker distribution of task group 1, the initial collaborative association strength needs to be adjusted according to the distribution of its association markers. That is, the proportion of direct positive associations of task group 1 is calculated. In this embodiment, the proportion of direct positive associations of task group 1 is 1. Next, the negative compensation coefficient of task group 1 is calculated to be 0.5, and then the final collaborative association strength of task group 1 is calculated to be 0.25.

[0089] As shown in the example above, although task group 1 has a positive correlation with other groups, its negative coupling with task group 2 weakens its final collaborative correlation strength to 0.25 after adjustment. This ensures that when generating execution priorities later, it effectively avoids mistakenly classifying fundamentally conflicting task groups as having high synergy and prioritizing their execution, preventing the resulting cancellation of control effects and increased energy consumption. This, in turn, effectively guarantees the overall efficiency, stability, and energy-saving effect of multi-device collaborative control.

[0090] In a smart home environment, the interactions between devices are uncertain. Direct connections typically imply strong coupling and predictable interactions, while indirect connections have relatively weaker and more uncertain effects. Treating both equally would lead to severely distorted assessments.

[0091] Based on this, the present invention adjusts the initial collaborative strength based on the distribution of association markers, and the adjustment process described in step C6 includes: if there are no negative association markers for the task group, then count the number of other groups with direct positive association markers with it, and calculate the ratio of it to the total number of all other groups with positive associations, as the direct positive association ratio.

[0092] The product of the initial collaborative association strength and the proportion of direct positive association is taken as the collaborative association strength of the task group.

[0093] If there is a negative correlation marker in the task group, calculate the ratio of the number of negative correlation markers to the number of direct positive correlation markers, and subtract the ratio from 1 to obtain the negative compensation coefficient.

[0094] The final synergistic association strength is the product of the initial synergistic association strength, the proportion of direct positive associations, and the negative compensation coefficient.

[0095] If there are multiple negative association markers in the task group, the final collaborative association strength will be 0.

[0096] This invention quantifies the coupling effect by performing multivariate regression analysis based on historical operating data, and dynamically corrects the initial synergy strength value according to the distribution ratio of direct and indirect association markers. This allows the calculation results of synergy association strength to more accurately reflect the real and verifiable degree of mutual influence between devices, solving the inaccuracy and inconsistency problems caused by subjective experience judgment. This provides a reliable quantitative input of synergy relationship for priority decision-making and ensures the stability of the final control results.

[0097] As another preferred example, the execution priority of the generated task groups includes: calculating the sum of the control urgency of each control task within each task group, and sorting them in descending order according to the sum of their control urgency.

[0098] For task groups with the same total urgency, they are sorted in descending order according to their synergistic correlation strength to obtain the final descending order.

[0099] The task group execution priority is generated based on the final descending sort.

[0100] This invention combines the strength of collaborative association to calculate the urgency of collaboration and the overall urgency weight, reflecting both the overall urgency of anomalies within each task group and their collaborative relationship with other groups. This ensures the rationality of task group execution priorities, significantly improving overall control efficiency when coordinating multi-device control, reducing energy waste caused by action conflicts, and ultimately enhancing the stability of the smart home system.

[0101] The hierarchical centralized control execution module generates and sends a sequence of control commands to the corresponding level of integrated control switches according to the execution priority in order to perform regulation.

[0102] Specifically, the sequence of sending control commands includes: when the secondary switch is activated, processing each control task sequentially based on the task execution priority order. For each control task, querying its associated secondary switch according to the calibrated controlled terminal and its functional area, and converting the control direction and target control value of the control task into control commands recognizable by the secondary switch, and then sending the generated control commands for a single control task sequentially to the corresponding secondary switch.

[0103] When a primary switch is activated, each task group is processed sequentially according to its priority. For each group, the controlled terminals, control directions, functional areas, and target control values ​​of all control tasks within that group are summarized and encapsulated into combined control commands according to the primary switch's protocol format. These combined control commands are then sent to the primary switches controlling all controlled terminals in that group. Upon receiving the combined control commands, the primary switches synchronously issue corresponding sub-commands to their subordinate secondary switches based on the command content. This achieves centralized and coordinated control of all devices within a task group.

[0104] This invention addresses the problem of relying solely on fixed processes or simple conditional judgments when multiple tasks are running concurrently, and failing to coordinate the coupling effects between devices. By enabling integrated control switches at corresponding levels according to the category of the controlled terminal, and generating task execution priorities or task group execution priorities based on the enabled switch levels, this invention achieves dynamic adaptation of task scheduling from independent execution to collaborative control. This avoids conflicts in control effects or increased energy consumption caused by improper execution order, and improves the overall coordination and control efficiency of multi-device collaborative operation.

[0105] In summary, this invention effectively avoids frequent device start-ups and shutdowns caused by instantaneous fluctuations by determining task triggers based on the average value of environmental parameters within a continuous time window; it achieves dynamic priority scheduling under multi-task concurrency by comprehensively adjusting the execution priority of integrated control switches at different levels based on urgency and collaborative correlation strength; and it effectively improves the overall efficiency and energy-saving effect of multi-device collaborative control through historical operation log coupling effect analysis.

[0106] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A smart monitoring and control system for home system switches based on multi-source data fusion, characterized in that, The system includes: The environmental perception and recognition module determines task triggering based on the average value of environmental parameters within a continuous time window and constructs a task list that includes target environmental parameter identifiers and controlled terminals. The centralized control switch determination module enables the corresponding level of integrated control switch according to the type of controlled terminal. The level includes a secondary switch for controlling a single type of controlled terminal and a primary switch for controlling multiple secondary switches. The task priority decision module, if the second-level switch is enabled, calculates the urgency of each control task based on the task list and generates the task execution priority accordingly. If the first-level switch is enabled, it quantifies the coupling effect between task groups based on historical operation logs through multiple linear regression analysis to obtain the synergistic correlation strength, and generates the task group execution priority based on the control urgency and synergistic correlation strength. The quantification of the coupling effect between task groups through multiple linear regression analysis includes: Extract the working status of all controlled terminals and the values ​​of various environmental parameters recorded at the same time point from the historical operation logs, and construct the controlled terminal status vector sequence and the environmental parameter vector sequence. Perform multiple linear regression analysis on the vector sequence, output regression coefficients, and construct a task influence matrix based on the regression coefficients; The two task groups currently being analyzed are designated as Group 1 and Group 2, respectively, and the controlled terminals, target environmental parameters, and control directions marked in their control tasks are obtained. From the influence matrix, query the regression coefficients of the controlled terminals of the first group to the environmental parameters of the second group tasks, and the regression coefficients of the controlled terminals of the second group to the environmental parameters of the first group tasks; Based on the control directions of the first and second groups, the cross-regression coefficients of the controlled terminals in the first group with respect to the second group and the cross-regression coefficients of the controlled terminals in the second group with respect to the first group are calculated and denoted as follows: and ; like or If both conditions are met, then a negative coupling effect is determined to exist; like and Simultaneously established, or and If one is greater than 0 and the other is equal to 0, then a positive coupling effect is determined to exist; like and If both are equal to 0, then it can be determined that there is no coupling effect; The process of obtaining the collaborative association strength includes: Randomly select one task group as the analysis object, and traverse the other task groups; If the two have the same target environmental parameter identifier, they are marked as directly positive or directly negatively correlated, depending on whether the control direction is consistent. If there are no identical environmental parameter identifiers, when there is a positive coupling effect, it is marked as an indirect positive correlation; when there is a negative coupling effect, it is marked as an indirect negative correlation; and when there is no coupling effect, it is marked as no correlation. After completing the association labeling between all groups, for each task group, count the number of other groups that have a positive association with it, divide by the total number of remaining task groups, and obtain the initial collaborative association strength of that task group; If the task group only has direct positive association markers, then the initial collaborative association strength will be used as its final collaborative association strength. Otherwise, the initial cooperative association strength is adjusted according to the distribution of its associated tags, and the adjustment result is used as its final cooperative association strength; The hierarchical centralized control execution module generates and sends corresponding integrated control switch execution and control commands based on the execution priority.

2. The intelligent monitoring and control system for home system switches based on multi-source data fusion as described in claim 1, characterized in that: The specific execution process of the environmental perception and recognition module includes: The real-time collected environmental parameters are compared with their preset reference range; When an environmental parameter exceeds its preset reference range, a continuous time window is divided and extracted according to a preset fixed duration. Calculate the average value of the environmental parameter within each time window, and determine whether any of the following conditions are met: The average value of N consecutive time windows exceeds its preset reference range, where N is an integer greater than 1; The deviation of the average value of a certain time window from its preset reference range reaches the preset intervention deviation range; If any of the above conditions are met, the environmental parameter shall be recorded as the target environmental parameter. Generate a control task that includes the target environmental parameter identifier, the controlled terminal corresponding to the target environmental parameter, the functional area where it is located, the control direction, and the target control value. The control direction is determined according to the sign of the target control value. Summarize all control tasks and build a task list.

3. The intelligent monitoring and control system for home system switches based on multi-source data fusion as described in claim 1, characterized in that: The calculation process for the urgency of the regulation includes: Calculate the degree of deviation between the target environmental parameters and the preset reference range, and use the degree of deviation as a benchmark to adjust the urgency level; Linear fitting is performed on the target environmental parameters within a preset time period to obtain the slope of the fitted line. Based on the slope and the deviation direction of the target environmental parameters relative to a preset reference range, it is determined whether dynamic compensation is triggered. If triggered, the baseline control urgency is dynamically compensated to generate the final control urgency; otherwise, the baseline control urgency is directly output as the final control urgency.

4. The intelligent monitoring and control system for home system switches based on multi-source data fusion as described in claim 3, characterized in that: The determination of whether dynamic compensation is triggered includes: If the current target environmental parameter is higher than its preset upper limit and the slope of its fitted line is positive, or if the current target environmental parameter is lower than the preset lower limit and the slope is negative, then dynamic compensation is triggered.

5. The intelligent monitoring and control system for home system switches based on multi-source data fusion as described in claim 3, characterized in that: The dynamic compensation includes: The preset time period is evenly divided into multiple sub-time periods. The target environmental parameters in each sub-time period are linearly fitted to obtain the corresponding local slope. Sub-time periods whose local slope has the same sign as the slope of the fitted line are recorded as sub-time periods in the same direction. Sub-periods with local slope absolute values ​​greater than or equal to the absolute value of the slope of the fitted line are denoted as strengthening sub-periods, and sub-periods with local slope absolute values ​​less than the absolute value of the slope of the fitted line are denoted as weakening sub-periods. If the number of strengthening sub-time periods is greater than the number of weakening sub-time periods, the maximum local slope is extracted from the same-direction sub-time periods and used as the target slope; otherwise, the slope of the fitted line is used as the target slope. The normalized trend strength value is calculated based on the absolute value of the target slope, the length of the preset time period, and the difference between the upper and lower limits of the preset reference range corresponding to the target environmental parameters. The baseline regulatory urgency is numerically corrected based on the normalized trend strength value, and the output is the final regulatory urgency.

6. The intelligent monitoring and control system for home system switches based on multi-source data fusion as described in claim 1, characterized in that: The adjustment process for the initial collaborative association strength includes: If there are no negative association markers for the task group, count the number of other groups that have direct positive association markers with it, and count the percentage of direct positive associations. The product of the initial collaborative association strength and the proportion of direct positive association is taken as the collaborative association strength of the task group. If there is a negative association marker in the task group, calculate the ratio of the number of negative association markers to the number of direct positive association markers, and set a negative compensation coefficient based on the ratio; The final synergistic association strength is the product of the initial synergistic association strength, the proportion of direct positive associations, and the negative compensation coefficient. If there are multiple negative association markers in the task group, the final collaborative association strength will be 0.

7. The intelligent monitoring and control system for home system switches based on multi-source data fusion as described in claim 1, characterized in that: The execution priority of the generated task group includes: Calculate the total urgency of each control task within each task group, and sort them in descending order based on the total urgency. For task groups with the same total urgency, sort them in descending order according to their synergistic correlation strength to obtain the final descending order; The task group execution priority is generated based on the final descending sort.

8. The intelligent monitoring and control system for home system switches based on multi-source data fusion as described in claim 1, characterized in that: The process of generating and sending integrated control switch commands at the corresponding level includes: When the secondary switch is activated, each control task is converted into a control command associated with the corresponding secondary switch of the controlled terminal according to the task execution priority, and sent sequentially. When a primary switch is activated, all control tasks of each group are packaged into a combined control command according to the priority order of task groups and sent to the primary switch associated with the corresponding controlled terminal.

Images