Power distribution switch control method and system

Abstract

The invention provides a power distribution switch control method and system, and relates to the technical field of power distribution control, and the method comprises the steps: obtaining an abnormal use judgment device; obtaining historical accompanying state data; pre-constructing an adjoint state verification model; real-time state features are obtained and synchronized to an abnormal use judgment device to execute use abnormal judgment, and if the first judgment result is abnormal, an accompanying state verification model is activated; carrying out accompanying state backtracking to obtain real-time accompanying state information, synchronizing the real-time accompanying state information to an accompanying state verification model to execute use abnormity verification, and correcting the first judgment result; and executing power distribution switch control on the power distribution control target according to the second judgment result. According to the invention, the technical problems of energy waste and shortened equipment life caused by neglect of home energy consumption due to emphasis on the living comfort of the user in the intelligent home system in the prior art can be solved, the technical purposes of considering the living comfort of the user and reducing the home energy consumption are achieved, and the technical effects of prolonging the equipment life and reducing the energy waste are achieved.

Description

Technical Field

[0001] This application relates to the technical field of power distribution control, and particularly to a power distribution switch control method and system. Background Art

[0002] Smart home systems can enhance the comfort, convenience, and security of living. However, over time, the importance of energy consumption and environmental protection has been increasingly recognized.

[0003] Currently, existing smart home systems have the problem of overemphasizing the improvement of user experience while neglecting energy efficiency. If the smart home system does not effectively consider energy management, it will lead to unnecessary high energy consumption. For example, air conditioners and lighting are still running when not necessary, or devices consume a large amount of electric energy in standby mode. Unreasonable energy consumption increases the impact on the environment, including increased carbon emissions, overexploitation of natural resources, etc. Long-term high-load operation will accelerate the aging of equipment, reduce the service life of equipment, and thus increase the frequency and cost of equipment replacement.

[0004] In summary, the smart home systems in the prior art have the problem of emphasizing the user's living comfort while neglecting home energy consumption, resulting in energy waste and shortened equipment life, further affecting the technical problem of environmental sustainable development. Summary of the Invention

[0005] The purpose of this application is to provide a power distribution switch control method and system to solve the technical problem that the smart home systems in the prior art emphasize the user's living comfort while neglecting home energy consumption, resulting in energy waste and shortened equipment life, further affecting environmental sustainable development.

[0006] In view of the above problems, this application provides a power distribution switch control method and system.

[0007] In a first aspect, the present application provides a method for controlling a distribution switch, which is implemented through a distribution switch control system. The method includes: interactively obtaining the historical operation log of the distribution control target, and performing usage feature analysis based on the historical operation log to obtain an abnormal usage judge; presetting a set of accompanying state indicators, and invoking accompanying state data based on the set of accompanying state indicators and the historical operation log to obtain historical accompanying state data; pre-constructing an accompanying state verification model, where the accompanying state verification model is a judgment model trained using the historical accompanying state data; interactively obtaining the real-time state information of the distribution control target, and performing feature extraction based on the real-time state information to obtain real-time state features; synchronizing the real-time state features to the abnormal usage judge to execute abnormal usage judgment. If the first judgment result is abnormal, activate the accompanying state verification model; perform accompanying state backtracking with the acquisition time of the real-time state information as a constraint to obtain real-time accompanying state information, synchronize the real-time accompanying state information to the accompanying state verification model to execute abnormal usage verification, correct the first judgment result, and obtain a second judgment result; perform distribution switch control on the distribution control target according to the second judgment result.

[0008] In a second aspect, the present application also provides a power distribution switch control system for implementing a power distribution switch control method as described in the first aspect. The system includes: an abnormal usage discriminator acquisition module for interactively acquiring the historical operation log of the power distribution control target and performing usage feature analysis based on the historical operation log to obtain an abnormal usage discriminator; a historical associated state data acquisition module for presetting an associated state index set and invoking associated state data based on the associated state index set and the historical operation log to obtain historical associated state data; an associated state verification model construction module for pre-constructing an associated state verification model, where the associated state verification model is a judgment model trained using the historical associated state data; a real-time state feature acquisition module for interactively acquiring the real-time state information of the power distribution control target and performing feature extraction based on the real-time state information to obtain real-time state features; an associated state verification model activation module for synchronizing the real-time state features to the abnormal usage discriminator to perform usage abnormality judgment. If the first judgment result is abnormal, the associated state verification model is activated; a second judgment result acquisition module for performing associated state backtracking with the acquisition time of the real-time state information as a constraint to obtain real-time associated state information, synchronizing the real-time associated state information to the associated state verification model to perform usage abnormality verification, and correcting the first judgment result to obtain a second judgment result; and a power distribution switch control module for performing power distribution switch control on the power distribution control target according to the second judgment result.

[0009] One or more technical solutions provided in the present application have at least the following technical effects or advantages: Obtain the historical operation log of the distribution control target through interaction, and perform usage feature analysis based on the historical operation log to obtain an abnormal usage discriminator; preset an adjoint state index set, and perform adjoint state data invocation based on the adjoint state index set and the historical operation log to obtain historical adjoint state data; pre-construct an adjoint state verification model, where the adjoint state verification model is a judgment model trained using the historical adjoint state data; interactively obtain the real-time state information of the distribution control target, and perform feature extraction based on the real-time state information to obtain real-time state features; synchronize the real-time state features to the abnormal usage discriminator to perform abnormal usage judgment. If the first judgment result is abnormal, activate the adjoint state verification model; perform adjoint state backtracking with the acquisition time of the real-time state information as a constraint to obtain real-time adjoint state information, synchronize the real-time adjoint state information to the adjoint state verification model to perform abnormal usage verification, and correct the first judgment result to obtain a second judgment result; perform distribution switch control on the distribution control target according to the second judgment result. That is, based on the usage information of multiple household appliances in the historical smart home, perform household appliance usage feature analysis, and construct a household energy consumption abnormal judgment model based on the summary of the feature analysis. When it is determined based on the household energy consumption abnormal judgment model that the household is in an abnormal power consumption state exceeding the normal usage feature analysis, verify whether the abnormal state is a real abnormality based on the household usage adjoint state features, achieving the technical goal of taking into account the user's living comfort and reducing household energy consumption, and achieving the technical effect of extending the equipment life and reducing energy waste.

[0010] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically given below. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of this application, nor is it used to limit the scope of this application. Other features of this application will become easily understood through the following description. Brief Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0012] Figure 1 It is a schematic flowchart of a distribution switch control method of this application; Figure 2This is a schematic structural diagram of a power distribution switch control system of the present application.

[0013] Description of reference numerals: Abnormal usage judgement acquisition module 11, historical accompanying state data acquisition module 12, accompanying state verification model construction module 13, real-time state feature acquisition module 14, accompanying state verification model activation module 15, second judgment result acquisition module 16, distribution switch control module 17. DETAILED DESCRIPTION

[0014] This application provides a power distribution switch control method and system to solve the problem that the existing smart home system focuses on user living comfort while ignoring home energy consumption, resulting in energy waste and shortened equipment life, further affecting environmental sustainable development. The technical goal of taking into account user living comfort and reducing home energy consumption is achieved, and the technical effect of extending equipment life and reducing energy waste is achieved.

[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0016] Embodiment 1 Please refer to the attached Figure 1 The present application provides a power distribution switch control method, wherein the method is applied to a power distribution switch control system, and the method specifically comprises the following steps: Step 1: interactively obtain the historical operation log of the power distribution control target, and perform usage feature analysis based on the historical operation log to obtain an abnormal usage determiner.

[0017] Specifically, the historical operation log of the power distribution control target is obtained by interacting with the smart home system, including operation records of the power distribution switch, power consumption data, device status and other information. The usage characteristics of the historical operation log of the smart home system are analyzed to identify normal and abnormal usage patterns, including analysis of parameters such as usage time, frequency, and duration, so as to establish an abnormal usage judgement. The abnormal usage judgement is used to identify behaviors that are inconsistent with normal usage patterns.

[0018] Step 2: preset an accompanying state indicator set, and call the accompanying state data based on the accompanying state indicator set and the historical operation log to obtain the historical accompanying state data.

[0019] Specifically, the preset adjoint state index set is used to measure the indicators of the operation state of the power distribution system, such as temperature, humidity, voltage, current, etc., to obtain the operation environment and conditions of the power distribution system. Based on the preset adjoint state index set and historical operation logs, adjoint state data is called. Data points related to the adjoint state indicators are extracted from historical data to form a historical adjoint state data set, which is used to identify the operation trend, potential problem areas or parts that need improvement of the power distribution system. For example, if the temperature in some areas of the smart home is often abnormally high, it is necessary to check whether there is a risk of overheating.

[0020] Step three: Pre-build an adjoint state verification model, where the adjoint state verification model is a judgment model obtained by training with the historical adjoint state data.

[0021] Specifically, the historical adjoint state data is used to train the adjoint state verification model so as to be able to judge whether the state of the power distribution system in the smart home system is normal. The adjoint state verification model can learn the characteristics of normal and abnormal states from historical data and perform state verification by applying, such as neural networks, decision trees or support vector machines.

[0022] Step four: Interactively obtain the real-time state information of the power distribution control target, and perform feature extraction according to the real-time state information to obtain real-time state features.

[0023] Specifically, the real-time state information of the power distribution control target is obtained interactively, including parameters such as power load, temperature, humidity, voltage, current, etc., which are collected by sensors, smart meters or other monitoring devices. Feature extraction is performed according to the real-time state information. Feature extraction is the process of converting raw data into formats and parameters that can be processed by machine learning models, including conversions such as calculating the average value, standard deviation, peak value, valley value, etc. of certain parameters, such as Fourier transform, wavelet transform, etc., in order to capture the key features in the data. After feature extraction, real-time state features are obtained, reflecting the current state of the power distribution system.

[0024] Step five: Synchronize the real-time state features to the abnormal usage judge to perform abnormal usage judgment. If the first judgment result is abnormal, activate the adjoint state verification model.

[0025] Specifically, the real-time state features are synchronized to the abnormal usage judge. The abnormal usage judge is used to perform abnormal usage judgment. If the first judgment result is abnormal, it indicates that there may be an abnormal operation mode for the power distribution control target. When the first judgment result is abnormal, the adjoint state verification model is activated.

[0026] Step 6: Perform accompanying state backtracking based on the collection time of the real-time state information as a constraint to obtain real-time accompanying state information, synchronize the real-time accompanying state information to the accompanying state verification model to perform usage anomaly verification, correct the first judgment result, and obtain a second judgment result.

[0027] Specifically, with the collection time of the real-time state information as a constraint, the accompanying state backtracking is performed, that is, the accompanying state data corresponding to the real-time state information in the past period of time is searched to obtain the real-time accompanying state information. The real-time accompanying state information is synchronized to the accompanying state verification model. The accompanying state verification model is used to perform the abnormality verification, that is, the real-time accompanying state information is analyzed to verify the preliminary abnormality judgment. According to the analysis result of the accompanying state verification model, the preliminary first judgment result is corrected to obtain the second judgment result.

[0028] Step seven: Execute power distribution switch control on the power distribution control target according to the second judgment result.

[0029] Specifically, according to the second judgment result, the power distribution switch control is performed on the power distribution control target. If it is abnormal, the state of the power distribution switch needs to be adjusted to prevent potential failures or safety issues.

[0030] The distribution switch control method is applied to a distribution switch control system, which can achieve the technical goals of taking into account both user living comfort and reducing home energy consumption, and achieve the technical effects of extending equipment life and reducing energy waste.

[0031] Furthermore, the present application also includes: The historical operation log includes multiple historical usage records, and multiple usage time information and multiple usage preference settings are obtained based on the multiple historical usage records; time sequence is performed on the multiple usage time information and usage interval calculation is performed based on the time sequence sorting result to obtain multiple usage interval periods; deviation analysis is performed on the multiple usage interval periods to obtain standard usage interval thresholds; preference habit analysis is performed on the usage preference settings to obtain standard preference setting thresholds; the standard usage interval thresholds and the standard preference setting thresholds are integrated to obtain the abnormal usage determiner.

[0032] Specifically, the historical operation logs of the power distribution control target are collected, which contain multiple historical usage records, such as the time, frequency, and duration of switch operations. The historical usage records are analyzed to extract key features, such as usage time information and user usage preference settings. Usage time information can reveal the operation mode of the power distribution equipment, while usage preference settings reflect the user's habits and needs.

[0033] Then, perform chronological sorting on the usage time information to observe and analyze the usage patterns of the distribution switches. Calculate the usage interval periods to obtain multiple usage interval periods, i.e., the time differences between each usage.

[0034] Next, perform deviation analysis on the calculated usage interval periods to determine the normal usage interval range. Any interval that significantly deviates from the standard may indicate abnormal or non-normal electricity consumption behavior.

[0035] Subsequently, analyze the usage preference settings to identify the standard electricity consumption habits and preferences of users, which helps to establish standard preference setting thresholds reflecting the normal electricity consumption behavior of users.

[0036] Finally, combine the standard usage interval threshold and the standard preference setting threshold to create an abnormal usage detector for identifying electricity consumption behaviors significantly different from the normal mode, thereby triggering an alarm or automatically adjusting the distribution strategy to optimize electricity usage and enhance safety.

[0037] Through power distribution, it can respond more intelligently to actual usage demands, quickly identify and respond to any abnormal situations, and improve the reliability and efficiency of the system.

[0038] Furthermore, this application also includes: Integrate the setting indicators for the multiple usage preference settings to obtain K sets of historical setting parameters for the K setting indicators; visualize the K sets of historical setting parameters based on the multiple usage time information to obtain K parameter discrete point graphs; perform value deviation analysis based on the K parameter discrete point graphs to obtain K parameter value thresholds, and the K parameter value thresholds constitute the standard preference setting threshold.

[0039] Specifically, integrate multiple usage preference settings into K setting indicators. Each setting indicator represents an aspect of the power distribution system, such as switch frequency, peak power usage time, valley-time electricity consumption, etc., and extract parameters to form K sets of historical setting parameters.

[0040] Next, use the multiple usage time information to convert the K sets of historical setting parameters into images, i.e., K parameter discrete point graphs, for visualizing the data to more easily identify trends and patterns.

[0041] Then, calculate the difference between the actual value of each parameter and the normal or expected value, perform value deviation analysis on the K parameter discrete point graphs, and based on the results of the value deviation analysis, establish a parameter value threshold for each setting indicator to obtain a reasonable value range for each parameter. Combine the K parameter value thresholds to form a comprehensive standard preference setting threshold as a benchmark for judging whether the power distribution system is operating normally. If there are any parameter values exceeding the threshold, they are regarded as abnormal and trigger further investigation or adjustment.

[0042] By identifying and responding to abnormal electricity consumption behaviors, it can improve the reliability and efficiency of power distribution, while reducing energy waste and operating costs, help prevent potential electrical faults, and ensure the stability and safety of power supply.

[0043] Furthermore, this application also includes: The set of accompanying state indicators includes environmental noise state indicators, remote control state indicators, and volume state indicators; locate the set of accompanying state records according to the set of accompanying state indicators, and use the multiple usage time information to extract data from the set of accompanying state records to obtain the historical accompanying state data, where the historical accompanying state data includes environmental accompanying state data, remote control accompanying state data, and volume accompanying state data; the accompanying state verification model includes an environmental accompanying verification branch, a remote control accompanying verification branch, and a volume accompanying verification branch; use the environmental accompanying state data, remote control accompanying state data, and volume accompanying state data to perform the training of the environmental accompanying verification branch, remote control accompanying verification branch, and volume accompanying verification branch respectively, and complete the construction of the accompanying state verification model.

[0044] Specifically, determining the set of accompanying state indicators, including environmental noise state indicators, remote control state indicators, and volume state indicators, reflects the external conditions and internal control states of the operation of the power distribution system.

[0045] Then, according to the set of accompanying state indicators, locate the relevant set of accompanying state records, including historical operation logs, etc. Use multiple usage time information to extract data from the set of accompanying state records to obtain historical accompanying state data, including environmental accompanying state data, remote control accompanying state data, and volume accompanying state data.

[0046] Next, set up the accompanying state verification model, including an environmental accompanying verification branch, a remote control accompanying verification branch, and a volume accompanying verification branch. Each branch corresponds to an accompanying state indicator.

[0047] Next, use the historical accompanying state data to train the accompanying state verification model. Specifically, use the environmental accompanying state data to train the environmental accompanying verification branch, use the remote control accompanying state data to train the remote control accompanying verification branch, and use the volume accompanying state data to train the volume accompanying verification branch to complete the construction of the accompanying state verification model.

[0048] Through the accompanying state verification model, it can learn how to identify and respond to different accompanying state data, which is used for real-time or near-real-time accompanying state verification, detecting and diagnosing abnormal situations of the power distribution system, thereby improving the reliability and safety of the system.

[0049] Furthermore, this application also includes: The interaction operator repository makes random operator calls and constructs the environmental adjoint verification branch based on the call results; performs data identification on the environmental adjoint state data to obtain sample environmental adjoint data, and uses the sample environmental adjoint data to perform the training construction of the environmental adjoint verification branch; and so on, performs the training construction of the remote control adjoint verification branch and the volume adjoint verification branch; and connects the environmental adjoint verification branch, the remote control adjoint verification branch, and the volume adjoint verification branch in parallel to obtain the adjoint state verification model.

[0050] Specifically, a random operator is called from the interaction operator repository to process and analyze data and construct the environmental adjoint verification branch.

[0051] Then, data identification is performed on the environmental adjoint state data, which means marking or classifying the data to facilitate the understanding and processing of the machine learning model, to obtain sample environmental adjoint data. During the data identification process, it is identified whether the environmental noise adjoint is the environmental noise when the user uses the power distribution control target based on usage habits. The sample environmental adjoint data is used to train the environmental adjoint verification branch. A machine learning algorithm is selected and the data is input into the algorithm for training so as to learn and identify the patterns of the environmental adjoint state through the model.

[0052] Next, the model training is repeatedly performed for the remote control adjoint state data and the volume adjoint state data. Data identification is performed on each data set to obtain sample data, and the sample data is used to train the corresponding verification branch.

[0053] Next, when the environmental adjoint verification branch, the remote control adjoint verification branch, and the volume adjoint verification branch are all completed with training, they are connected in parallel to form a comprehensive adjoint state verification model, which can consider multiple adjoint state indicators simultaneously to more comprehensively verify the state of the power distribution system.

[0054] Through the adjoint state verification model, various states of the power distribution system can be more accurately identified and responded to, thereby improving the system's monitoring and fault detection capabilities.

[0055] Furthermore, this application also includes: Extract features from the real-time status information to obtain the real-time status features, where the real-time status features include start time information and start setting information; interactively obtain adjacent start time information, and perform start interval calculation based on the adjacent start time and the start time information to obtain the real-time start interval; perform abnormal use judgment in the abnormal use judge based on the real-time start interval and the start setting information; if the real-time start interval and the start setting information simultaneously meet the standard use interval threshold and the standard preference setting threshold, the first judgment result is normal, and no power distribution switch control is performed on the power distribution control target; if the real-time start interval does not meet the standard use interval threshold and / or the start setting information does not meet the standard preference setting threshold, the first judgment result is abnormal; when the first judgment result is abnormal, activate the associated status verification model, and perform associated status backtracking with the acquisition time of the real-time status information as a constraint to obtain the real-time associated status information.

[0056] Specifically, obtain real-time status information from the power distribution control target, and extract features to obtain real-time status features, including start time information and start setting information.

[0057] Then, interactively obtain adjacent start time information, that is, the time points of the previous and next starts. Based on the adjacent start time and the current start time information, perform start interval calculation to obtain the real-time start interval.

[0058] Next, in the abnormal use judge, use the real-time start interval and the start setting information to perform abnormal use judgment. If the real-time start interval and the start setting information simultaneously meet the standard use interval threshold and the standard preference setting threshold, it is judged as normal, and no power distribution switch control needs to be performed on the power distribution control target. If the real-time start interval does not meet the standard use interval threshold or the start setting information does not meet the standard preference setting threshold, it is judged as abnormal.

[0059] Next, when the first judgment result is abnormal, activate the associated status verification model. With the acquisition time of the real-time status information as a constraint, perform associated status backtracking, that is, review the associated status data in the past period of time to obtain the real-time associated status information.

[0060] By identifying abnormal use patterns and activating the associated status verification model when necessary to further verify abnormal situations, the monitoring ability of the power distribution system is improved to ensure operation under the premise of safety and efficiency.

[0061] Furthermore, this application also includes: Perform retrospective analysis on the associated status record set according to the collection time of the real-time status information to obtain the real-time associated status information, where the real-time associated status information includes real-time environmental associated status, real-time remote control associated status, and real-time volume associated status; map and synchronize the real-time environmental associated status, real-time remote control associated status, and real-time volume associated status to the environmental associated status verification branch, remote control associated status verification branch, and volume associated status verification branch of the associated status verification model to perform status anomaly identification; when the output results of the environmental associated status verification branch, remote control associated status verification branch, and volume associated status verification branch are all normal, correct the first judgment result to obtain the second judgment result, where the second judgment result is normal; when the output result of any branch of the environmental associated status verification branch, remote control associated status verification branch, and volume associated status verification branch is abnormal, retain the first judgment result and use the first judgment result as the second judgment result.

[0062] Specifically, according to the collection time of the real-time status information, perform retrospective analysis on the associated status record set to obtain the real-time associated status information, including real-time environmental associated status, real-time remote control associated status, and real-time volume associated status, and find the associated status data in the past period corresponding to the real-time status information for more in-depth analysis.

[0063] Then, map and synchronize the real-time environmental associated status, real-time remote control associated status, and real-time volume associated status to the environmental associated status verification branch, remote control associated status verification branch, and volume associated status verification branch of the associated status verification model. Perform status anomaly identification in each branch, that is, use each branch to analyze the real-time associated status information to determine whether there is an anomaly.

[0064] Next, if the output results of the environmental associated status verification branch, remote control associated status verification branch, and volume associated status verification branch are all normal, it indicates that no anomaly is found in the real-time associated status information. At this time, correct the preliminary first judgment result to obtain the second judgment result as normal.

[0065] Next, judge whether the environmental accompaniment during the device usage conforms to the environmental accompaniment characteristics of normal usage, and determine whether the current device startup is a normal special case, which is used as the second judgment result. For example, when the environmental accompaniment characteristics for watching TV conform to the environmental accompaniment characteristics of normal usage, if there are other sounds such as kitchen utensils as interference, it is determined as abnormal and is a special case. Abnormal startup ensures unnecessary power consumption of the device and performs user power consumption management under the condition of not affecting user usage.

[0066] By identifying the real abnormal situations and taking corresponding measures, improve the monitoring ability of the power distribution system to ensure operation under the premise of safety and efficiency. At the same time, through secondary verification, ensure that actions are taken only when there is indeed an anomaly.

[0067] In summary, the power distribution switch control method provided by this application has the following technical effects: Obtain the historical operation log of the power distribution control target through interaction, and perform usage feature analysis based on the historical operation log to obtain an abnormal usage judge; preset an accompanying status index set, and perform accompanying status data call based on the accompanying status index set and the historical operation log to obtain historical accompanying status data; pre-construct an accompanying status verification model, where the accompanying status verification model is a judgment model trained using the historical accompanying status data; interact to obtain the real-time status information of the power distribution control target, and perform feature extraction based on the real-time status information to obtain real-time status features; synchronize the real-time status features to the abnormal usage judge to execute abnormal usage judgment. If the first judgment result is abnormal, activate the accompanying status verification model; perform accompanying status backtracking with the acquisition time of the real-time status information as a constraint to obtain real-time accompanying status information, synchronize the real-time accompanying status information to the accompanying status verification model to execute abnormal usage verification, correct the first judgment result, and obtain a second judgment result; perform power distribution switch control on the power distribution control target according to the second judgment result. That is to say, based on the usage information of multiple household appliances in the historical smart home, perform household appliance usage feature analysis, and construct a household energy consumption abnormal judgment model based on the summary of the feature analysis. When it is determined based on the household energy consumption abnormal judgment model that the household is in an abnormal power consumption state exceeding the normal usage feature analysis, perform verification on whether the abnormal state is a real abnormality based on the household usage accompanying status features, achieve the technical goal of taking into account the user's living comfort and reducing household energy consumption, and achieve the technical effect of extending the equipment life and reducing energy waste.

[0068] Embodiment 2 Based on the same inventive concept as a power distribution switch control method in the foregoing embodiment, this application also provides a power distribution switch control system. Please refer to the appendix Figure 2 , the system includes: An abnormal usage judge obtaining module 11, which is used to interactively obtain the historical operation log of the power distribution control target and perform usage feature analysis based on the historical operation log to obtain an abnormal usage judge.

[0069] A historical accompanying status data obtaining module 12, which is used to preset an accompanying status index set and perform accompanying status data call based on the accompanying status index set and the historical operation log to obtain historical accompanying status data.

[0070] An associated status verification model construction module 13, where the associated status verification model construction module 13 is used to pre-construct an associated status verification model. Among them, the associated status verification model is a judgment model obtained by training with the historical associated status data.

[0071] A real-time status feature acquisition module 14, where the real-time status feature acquisition module 14 is used to interactively obtain the real-time status information of the power distribution control target and perform feature extraction based on the real-time status information to obtain real-time status features.

[0072] An associated status verification model activation module 15, where the associated status verification model activation module 15 is used to synchronize the real-time status features to the abnormal use judge to execute the abnormal use judgment. If the first judgment result is abnormal, the associated status verification model is activated.

[0073] A second judgment result acquisition module 16, where the second judgment result acquisition module 16 is used to perform associated status backtracking with the acquisition time of the real-time status information as a constraint to obtain real-time associated status information, synchronize the real-time associated status information to the associated status verification model to execute the abnormal use verification, correct the first judgment result, and obtain the second judgment result.

[0074] A power distribution switch control module 17, where the power distribution switch control module 17 is used to perform power distribution switch control on the power distribution control target according to the second judgment result.

[0075] Furthermore, the abnormal use judge acquisition module 11 in the system is further used for: The historical operation log includes multiple historical use records, and multiple use time information and multiple use preference settings are obtained by calling based on the multiple historical use records; Perform time sequence sorting on the multiple use time information and calculate the use intervals based on the time sequence sorting result to obtain multiple use interval periods; Perform deviation analysis on the multiple use interval periods to obtain a standard use interval threshold; Perform preference habit analysis on the use preference settings to obtain a standard preference setting threshold; Integrate the standard use interval threshold and the standard preference setting threshold to obtain the abnormal use judge.

[0076] Furthermore, the abnormal use judge acquisition module 11 in the system is further used for: Perform setting index integration on the multiple use preference settings to obtain K sets of historical setting parameters for K setting indexes; Graph the K sets of historical setting parameters according to the multiple use time information to obtain K parameter discrete points; Performing value deviation analysis based on the K discrete parameter points to obtain K parameter value thresholds, and the K parameter value thresholds constitute the standard preference setting threshold.

[0077] Furthermore, the adjoint state verification model construction module 13 in the system is further configured to: The adjoint state index set includes an environmental noise state index, a remote control state index, and a volume state index; Positioning the adjoint state record set according to the adjoint state index set, and using the multiple usage time information to extract data from the adjoint state record set to obtain the historical adjoint state data, where the historical adjoint state data includes environmental adjoint state data, remote control adjoint state data, and volume adjoint state data; The adjoint state verification model includes an environmental adjoint verification branch, a remote control adjoint verification branch, and a volume adjoint verification branch; Using the environmental adjoint state data, remote control adjoint state data, and volume adjoint state data to perform the training of the environmental adjoint verification branch, remote control adjoint verification branch, and volume adjoint verification branch respectively to complete the construction of the adjoint state verification model.

[0078] Furthermore, the adjoint state verification model construction module 13 in the system is further configured to: Randomly call operators in the interaction operator repository, and construct the environmental adjoint verification branch based on the call results; Perform data identification on the environmental adjoint state data to obtain sample environmental adjoint data, and use the sample environmental adjoint data to perform the training construction of the environmental adjoint verification branch; And so on, perform the training construction of the remote control adjoint verification branch and the volume adjoint verification branch; Parallel the environmental adjoint verification branch, remote control adjoint verification branch, and volume adjoint verification branch to obtain the adjoint state verification model.

[0079] Furthermore, the adjoint state verification model activation module 15 in the system is further configured to: Extract features from the real-time state information to obtain the real-time state features, where the real-time state features include start time information and start setting information; Interactively obtain adjacent start time information, and perform start interval calculation based on the adjacent start time and the start time information to obtain the real-time start interval; Perform usage anomaly judgment in the abnormal usage judge based on the real-time start interval and the start setting information; If the real-time startup interval and startup setting information simultaneously meet the standard usage interval threshold and the standard preference setting threshold, the first judgment result is normal, and no power distribution switch control is performed on the power distribution control target; If the real-time startup interval does not meet the standard usage interval threshold and / or the startup setting information does not meet the standard preference setting threshold, the first judgment result is abnormal; When the first judgment result is abnormal, activate the accompanying state verification model, and perform accompanying state backtracking with the acquisition time of the real-time state information as a constraint to obtain the real-time accompanying state information.

[0080] Furthermore, the second judgment result acquisition module 16 in the system is further configured to: Perform accompanying state backtracking on the accompanying state record set according to the acquisition time of the real-time state information to obtain the real-time accompanying state information, where the real-time accompanying state information includes a real-time environment accompanying state, a real-time remote control accompanying state, and a real-time volume accompanying state; Map and synchronize the real-time environment accompanying state, the real-time remote control accompanying state, and the real-time volume accompanying state to the environment accompanying verification branch, the remote control accompanying verification branch, and the volume accompanying verification branch of the accompanying state verification model to perform state abnormality identification; When the output results of the environment accompanying verification branch, the remote control accompanying verification branch, and the volume accompanying verification branch are all normal, correct the first judgment result to obtain the second judgment result, where the second judgment result is normal; When the output result of any branch of the environment accompanying verification branch, the remote control accompanying verification branch, and the volume accompanying verification branch is abnormal, retain the first judgment result and use the first judgment result as the second judgment result.

[0081] The various embodiments in this specification are described in a progressive manner. The key points of each embodiment are the differences from other embodiments. The power distribution switch control method and specific examples in the foregoing Embodiment 1 are equally applicable to the power distribution switch control system in this embodiment. Through the foregoing detailed description of the power distribution switch control method, those skilled in the art can clearly know the power distribution switch control system in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0082] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but rather is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0083] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and variations.

Claims

1. A power distribution switch control method, characterized in that: The method comprises: Interactively obtain a historical operation log of a power distribution control target, and perform usage feature analysis based on the historical operation log to obtain an abnormal usage determiner; Preset an accompanying state indicator set, and call accompanying state data based on the accompanying state indicator set and the historical operation log to obtain historical accompanying state data; Pre-constructing an accompanying state verification model, wherein the accompanying state verification model is a judgment model obtained by training with the historical accompanying state data; interactively obtaining real-time status information of the power distribution control target, and performing feature extraction according to the real-time status information to obtain real-time status features; Synchronizing the real-time status feature to the abnormal use judgement device to perform abnormal use judgment, and if the first judgment result is abnormal, activating the accompanying status verification model; Performing accompanying state backtracking with the acquisition time of the real-time state information as a constraint to obtain real-time accompanying state information, synchronizing the real-time accompanying state information to the accompanying state verification model to perform use anomaly verification, correcting the first judgment result, and obtaining a second judgment result; A power distribution switch control is performed on the power distribution control target according to the second judgment result.

2. The method according to claim 1, characterized in that Interactively obtaining a historical operation log of a power distribution control target, and performing a usage feature analysis based on the historical operation log to obtain an abnormal usage determiner, the method further comprising: The historical operation log includes a plurality of historical usage records, and a plurality of usage time information and a plurality of usage preference settings are obtained based on the plurality of historical usage records; Performing time sequence sorting on the plurality of usage time information and calculating the usage interval based on the time sequence sorting result to obtain a plurality of usage interval periods; performing deviation analysis on the plurality of usage interval periods to obtain a standard usage interval threshold; Performing preference habit analysis on the usage preference setting to obtain a standard preference setting threshold; The standard usage interval threshold and the standard preference setting threshold are integrated to obtain the abnormal usage determiner.

3. The method according to claim 2, characterized in that Performing a preference habit analysis on the usage preference setting to obtain a standard preference setting threshold, the method further comprising: Integrating the setting indicators of the plurality of usage preference settings to obtain K groups of historical setting parameters of the K setting indicators; Graphically representing the K groups of historical setting parameters according to the plurality of usage time information to obtain K discrete points of the parameters; Based on the K parameter discrete points, a value deviation analysis is performed to obtain K parameter value thresholds, and the K parameter value thresholds constitute the standard preference setting thresholds.

4. The method according to claim 2, characterized in that Pre-constructing an accompanying state verification model, wherein the accompanying state verification model is a judgment model obtained by training with the historical accompanying state data, and the method further includes: The accompanying status indicator set includes an environmental noise status indicator, a remote control status indicator, and a volume status indicator; Locating the accompanying state record set according to the accompanying state indicator set, and extracting data from the accompanying state record set using the plurality of usage time information to obtain the historical accompanying state data, wherein the historical accompanying state data includes environmental accompanying state data, remote control accompanying state data, and volume accompanying state data; The accompanying state verification model includes an environment accompanying verification branch, a remote control accompanying verification branch and a volume accompanying verification branch; The environment accompanying state data, the remote control accompanying state data and the volume accompanying state data are used to respectively perform the training of the environment accompanying verification branch, the remote control accompanying verification branch and the volume accompanying verification branch, so as to complete the construction of the accompanying state verification model.

5. The method according to claim 4, characterized in that The method further comprises: using the environment accompanying state data, the remote control accompanying state data and the volume accompanying state data to respectively perform the training of the environment accompanying verification branch, the remote control accompanying verification branch and the volume accompanying verification branch to complete the construction of the accompanying state verification model; The interactive operator repository performs random operator calls, and constructs and obtains the environment accompanying verification branch based on the call result; Performing data identification on the environment accompanying state data to obtain sample environment accompanying data, and using the sample environment accompanying data to perform training construction of the environment accompanying verification branch; Similarly, the training construction of the remote control accompanying verification branch and the volume accompanying verification branch is performed; The environment accompanying verification branch, the remote control accompanying verification branch and the volume accompanying verification branch are connected in parallel to obtain the accompanying state verification model.

6. The method according to claim 5, characterized in that The real-time status feature is synchronized to the abnormal use judgement device to perform abnormal use judgment, and if the first judgment result is abnormal, the accompanying status verification model is activated, and the method further includes: Extracting features from the real-time status information to obtain the real-time status features, wherein the real-time status features include start-up time information and start-up setting information; Interactively obtain adjacent start time information, and perform start interval calculation based on the adjacent start time and the start time information to obtain a real-time start interval; In the abnormal use determiner, abnormal use determination is performed based on the real-time start interval and the start setting information; If the real-time startup interval and the startup setting information simultaneously meet the standard usage interval threshold and the standard preference setting threshold, the first judgment result is normal, and the power distribution switch control is not performed on the power distribution control target; If the real-time startup interval does not meet the standard usage interval threshold and / or the startup setting information does not meet the standard preference setting threshold, the first judgment result is abnormal; When the first judgment result is abnormal, the accompanying state verification model is activated, and the accompanying state backtracking is performed with the collection time of the real-time state information as a constraint to obtain the real-time accompanying state information.

7. The method according to claim 6, characterized in that The real-time accompanying state information is synchronized to the accompanying state verification model to perform abnormal use verification, and the first judgment result is corrected to obtain a second judgment result. The method further includes: Performing accompanying state backtracking on the accompanying state record set according to the acquisition time of the real-time state information to obtain the real-time accompanying state information, wherein the real-time accompanying state information includes real-time environment accompanying state, real-time remote control accompanying state and real-time volume accompanying state; Synchronize the real-time environment accompanying state, the real-time remote control accompanying state and the real-time volume accompanying state mapping to the environment accompanying verification branch of the accompanying state verification model, and the remote control accompanying verification branch and the volume accompanying verification branch perform state abnormality identification; When the output results of the environment accompanying verification branch, the remote control accompanying verification branch and the volume accompanying verification branch are all normal, correcting the first judgment result to obtain the second judgment result, wherein the second judgment result is normal; When the output result of any of the environment accompaniment verification branch, the remote control accompaniment verification branch and the volume accompaniment verification branch is abnormal, the first judgment result is retained and the first judgment result is used as the second judgment result.

8. A power distribution switch control system, characterized in that: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: An abnormal use judgement obtaining module, the abnormal use judgement obtaining module is used to interactively obtain a historical operation log of a power distribution control target, and perform a usage feature analysis based on the historical operation log to obtain an abnormal use judgement; A historical accompanying state data acquisition module, wherein the historical accompanying state data acquisition module is used to preset an accompanying state indicator set, and perform accompanying state data call based on the accompanying state indicator set and the historical operation log to obtain historical accompanying state data; An accompanying state verification model construction module, wherein the accompanying state verification model construction module is used to pre-construct an accompanying state verification model, wherein the accompanying state verification model is a judgment model obtained by training with the historical accompanying state data; A real-time state feature acquisition module, the real-time state feature acquisition module is used to interactively obtain the real-time state information of the power distribution control target, and perform feature extraction according to the real-time state information to obtain real-time state features; An accompanying state verification model activation module, the accompanying state verification model activation module is used to synchronize the real-time state feature to the abnormal use judgement device to perform abnormal use judgment, and if the first judgment result is abnormal, activate the accompanying state verification model; A second judgment result obtaining module, the second judgment result obtaining module is used to perform accompanying state backtracking with the acquisition time of the real-time state information as a constraint, obtain the real-time accompanying state information, synchronize the real-time accompanying state information to the accompanying state verification model to perform use abnormality verification, correct the first judgment result, and obtain a second judgment result; A power distribution switch control module, wherein the power distribution switch control module is used to perform power distribution switch control on the power distribution control target according to the second judgment result.

Images