CN115268269B - Household energy consumption optimization system and method based on new energy low carbon - Google Patents
Household energy consumption optimization system and method based on new energy low carbon Download PDFInfo
- Publication number
- CN115268269B CN115268269B CN202210909751.XA CN202210909751A CN115268269B CN 115268269 B CN115268269 B CN 115268269B CN 202210909751 A CN202210909751 A CN 202210909751A CN 115268269 B CN115268269 B CN 115268269B
- Authority
- CN
- China
- Prior art keywords
- user
- data
- toilet
- unit
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a new energy low-carbon-based household energy consumption optimization system and method, and belongs to the technical field of household energy consumption optimization. The system comprises an intelligent home acquisition module, a behavior analysis module, a model construction module, a signal transmission module and a temperature monitoring module; the output end of the intelligent home collection module is connected with the input end of the behavior analysis module; the output end of the behavior analysis module is connected with the input end of the model building module; the output end of the model building module is connected with the input end of the signal transmission module; the output end of the signal transmission module is connected with the input end of the temperature monitoring module. The invention can stop the endless power consumption behavior of the intelligent closestool; meanwhile, the problem that the temperature of the toilet gasket is not timely is solved by utilizing the personalized adaptation model, the user experience is improved, the low-carbon requirement of new energy under the current large environment is met, and the energy conservation and the environmental protection are realized.
Description
Technical Field
The invention relates to the technical field of household energy consumption optimization, in particular to a household energy consumption optimization system and method based on new energy and low carbon.
Background
Smart home refers to the integration or control of electronic and electrical products or systems in the home using micro-processing electronics technology, such as: lighting lamps, coffee ovens, computer equipment, security systems, heating and cooling systems, video and audio systems, shower systems, and the like. The intelligent home is mainly characterized in that a central microprocessor receives information from related electronic and electric products (changes of external environment factors, such as light changes caused by initial rise of the sun or western fall, and the like), and then sends appropriate information to other electronic and electric products by a preset program. The central microprocessor must control the electrical products in the home through a number of interfaces, either keyboard manual or cloud platform automatic.
However, the smart home brings great convenience and great power consumption and energy consumption, and a large number of human body scanning or detecting devices are attached to the whole smart home system due to the specificity of the smart home, so that the smart home can realize high-performance intelligence; for example, in the market, a higher-level intelligent closestool generally has an infrared detection or face detection function, continuously detects the surrounding change, starts to operate when detecting that a person approaches, and adjusts the opening of the closestool cover or the temperature of the gasket so as to bring the best experience to people; as a result, the toilet also has two core problems, firstly, due to the specificity of the toilet, the toilet is usually not in the same space as other intelligent devices, but is sealed in a separate space of the toilet, so that the toilet must be provided with a voice or detection device, and most of the existing intelligent toilets in the market have voice control and detection devices, so that the intelligent toilets consume electricity at any time and have huge energy consumption; second, toilet gasket temperature is usually awakened by voice or by detection, and time is required for heating or cooling, which causes great discomfort when the user is in contact with the skin of the user at the beginning of use
Disclosure of Invention
The invention aims to provide a new energy low-carbon-based household energy consumption optimization system and method, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a home energy consumption optimization method based on new energy low carbon comprises the following steps:
s1, constructing a time period T, and acquiring self data of a user in historical data, wherein the self data of the user comprise a moving state, a body posture and time characteristics of the user in a house; acquiring the moving state, the body posture and the time characteristics of a user in a house in a time period T before the user uses the intelligent closestool;
s2, constructing a user toilet prediction model according to the historical data acquired in the step S1, and generating user toilet probability according to the moving state, the body posture and the time characteristics of the current user in the house;
s3, setting a probability threshold, judging that the user will have a toilet action if the toilet probability exceeds the probability threshold, transmitting a signal to the intelligent closestool, and starting a temperature function of a closestool gasket;
s4, acquiring indoor temperature data, adjusting the temperature data of the toilet gasket according to the history of the user, constructing a personalized adaptation model, and adjusting the temperature of the toilet gasket.
According to the above technical scheme, the constructing the user toilet prediction model includes:
s2-1, acquiring user self data by utilizing an intelligent home indoor sensor, wherein the user self data comprises a moving state, a body posture and time characteristics; constructing a time period T, and under different user self data, in the range of the time period T, recording the user self data in the range of the time period T as high-quality data when the user uses the intelligent closestool; the rest is marked as irrelevant data;
s2-2, the intelligent household indoor sensor in the step S2-1 acquires the user data and carries out combined coding, and the combination coding is recorded as [ A ] 1 、A 2 、……、A n ]Each code corresponds to a set of user's own data, wherein A 1 、A 2 、……、A n Respectively representing one of the user own data and marking as an element;
s2-3, randomly initializing a population, wherein the population comprises N groups of high-quality data, N is a settable constant value, and the initial iteration times G=1 are set;
s2-4, randomly combining elements in the codes in the group of the step S2-3, and according to the element A in the codes 1 、A 2 、A 3 、……、A n Element A 1 、A 2 、A 3 、……、A n The influence degree of the user self data corresponding to each element or element combination on the intelligent closestool used by the user is calculated respectively, and a deviation value is calculated:
wherein C is i Representing the deviation value of the user data corresponding to the code i for the user to use the intelligent closestool; n represents the set of combinations of all elements in the code i, wherein a single oneSpecies elements are also referred to as combinations of elements; x represents any one of the combinations of all elements in the code i; f (F) x Representing the coding quantity of the user self data with the combination mode of x in the population; f (F) y Representing the number of codes with the combination mode of x in the population; c (C) i Is not extracted and put back;
s2-5, obtaining deviation values of all codes in a population, taking the average value as an iteration judgment result, setting a threshold value, and if the average value is higher than the threshold value, iterating until the average value is lower than the threshold value, ending the iteration; stopping iteration when the average value is lower than the threshold value, and outputting the average value of all current coded deviation values; after finishing iteration, entering a step S2-6;
the iteration adopts a random selection mode, two codes are randomly selected each time, the deviation value is high, the iteration is continuously circulated until the number of selected individuals reaches M, wherein M is a set constant and is smaller than the number of initial individuals; counting the elements in the selected M groups of codes, deleting the element with the lowest occurrence rate, and mining the sub-elements of the rest elements to form a new code [ A ] 11 、A 21 、……、A n1 ]The element and the subelement have a containing relation, the iteration times G=G+1 are set, and the steps S2-4 are repeated;
s2-6, acquiring element information and sub-element information of user self data corresponding to the current deviation value, and generating a user toilet prediction model:
wherein P represents a predicted user's toilet probability; k (k) 1 Representing the influence coefficient of the deviation value; l (L) 0 Representing the current deviation value; k (k) 2 Representing an iteration influence coefficient; g 0 Representing the number of iterations.
According to the above technical scheme, the starting of the temperature function of the toilet gasket comprises:
the intelligent home is connected to the cloud platform through an intelligent gateway;
the signal transmission module is provided with a probability threshold, and under the condition that the toilet probability of the user exceeds the probability threshold, the signal transmission module judges that the user is about to perform toilet behavior and sends out a signal instruction;
the signal instruction is sent to the intelligent closestool, the intelligent closestool is started, the closestool cover is opened, and meanwhile the temperature of the closestool gasket is adjusted.
According to the technical scheme, the constructing the personalized adaptation model comprises
Acquiring user history manual regulation data, and under single toilet action, setting indoor temperature t 1 Number of times s of adjustment 1 Toilet gasket temperature u 1 Record as a single set of toilet behavior: [ t ] 1 、s 1 、u 1 ];
Setting a threshold s of the number of times of adjustment 0 The method comprises the steps of carrying out a first treatment on the surface of the The data meeting the adjustment times exceeding the times threshold are marked as high weight data, and the rest are marked as low weight data;
respectively constructing two linear regression equations according to the high-weight data and the low-weight data, and combining to generate a personalized adaptation model:
u comfort =(β 0 +β 1 *t 1-1 )*k 3 +k 4 *(β 01 +β 11 *t 1-2 )
wherein u is comfort The temperature data of the toilet gasket output by the personalized adaptation model is represented; beta 0 、β 1 Representing regression coefficients under high weight data; beta 01 、β 11 Representing regression coefficients under high weight data; t is t 1-1 Representing the indoor temperature at high weight data; t is t 1-2 Representing the indoor temperature at low weight data; k (k) 3 、k 4 Respectively represent weight proportion data, k 3 >k 4 ;
The more times of adjustment, the more perfect the fit of the data to the user is represented, and so the low weight data is not discarded, mainly because it reflects the lower limit level acceptable to the user;
fitting regression coefficient values by utilizing MATLAB software;
acquiring real-time indoor temperatureAccordingly, it is denoted as t j The method comprises the steps of carrying out a first treatment on the surface of the The toilet gasket temperature data output by the personalized adaptation model is:
u comfort =(β 0 +β 1 *t j )*k 3 +k 4 *(β 01 +β 11 *t j )
according to the generated u comfort Data, adjust toilet gasket temperature.
A new energy low-carbon-based household energy consumption optimization system comprises:
the intelligent household system comprises an intelligent household acquisition module, a behavior analysis module, a model construction module, a signal transmission module and a temperature monitoring module;
the intelligent home collection module is used for collecting user self data, wherein the user self data comprises the moving state, the body posture and the time characteristics of a user in a house; the behavior analysis module is used for further analyzing the user data and decomposing sub-element data of the user data; the model construction module is used for constructing a user toilet prediction model according to user self data and sub-element data of the user self data, and generating user toilet probability according to the moving state, body posture and time characteristics of the current user in a house; the signal transmission module is used for setting a probability threshold, judging that the user will have a toilet behavior if the toilet probability exceeds the probability threshold, transmitting signals to the intelligent closestool, and starting the temperature function of the closestool gasket; the temperature monitoring module is used for acquiring indoor temperature data, adjusting the temperature data of the toilet gasket according to the history of a user, constructing a personalized adaptation model and adjusting the temperature of the toilet gasket;
the output end of the intelligent home collection module is connected with the input end of the behavior analysis module; the output end of the behavior analysis module is connected with the input end of the model building module; the output end of the model building module is connected with the input end of the signal transmission module; the output end of the signal transmission module is connected with the input end of the temperature monitoring module.
According to the technical scheme, the intelligent home collection module comprises a mobile state monitoring unit, a body posture monitoring unit and a time unit;
the mobile state monitoring unit is used for collecting the mobile state of the user indoors and recording the mobile path of the user; the body posture monitoring unit is used for collecting body posture actions of a user and judging whether the user has abdomen discomfort; the time unit is used for recording the time characteristics;
the output ends of the movement state monitoring unit, the body posture monitoring unit and the time unit are all connected to the input end of the behavior analysis module.
According to the technical scheme, the behavior analysis module comprises a subelement analysis unit and an output unit;
the sub-element analysis unit is used for acquiring self data of a user, further analyzing the self data of the user and decomposing sub-element data of the self data of the user; the output unit is used for outputting the subelements to the model building module;
the output end of the subelement analysis unit is connected with the input end of the output unit.
According to the technical scheme, the model building module comprises a model building unit and a probability calculating unit;
the model construction unit is used for constructing a user toilet prediction model according to the user self data and the child element data of the user self data; the probability calculation unit is used for generating the toilet probability of the user according to the moving state, the body posture and the time characteristics of the current user in the house;
the output end of the model building unit is connected with the input end of the probability calculating unit; the output end of the probability calculation unit is connected with the input end of the signal transmission module.
According to the technical scheme, the signal transmission module comprises a probability judging unit and a signal transmission unit;
the probability judging unit is used for setting a probability threshold, judging that the user will have toilet behavior if the toilet probability of the user exceeds the probability threshold, and starting the signal transmission unit; the signal transmission unit is used for connecting the intelligent closestool with the intelligent household cloud platform, transmitting signals to the intelligent closestool and starting the temperature function of a closestool gasket;
the output end of the probability judging unit is connected with the input end of the signal transmission unit; the output end of the signal transmission unit is connected with the input end of the temperature monitoring module.
According to the technical scheme, the temperature monitoring module comprises a real-time temperature data acquisition unit and a personalized adaptation unit;
the real-time temperature data acquisition unit is used for acquiring indoor temperature data; the personalized adaptation unit is used for adjusting the temperature data of the toilet gasket according to the history of the user, constructing a personalized adaptation model and adjusting the temperature of the toilet gasket;
the output end of the real-time temperature data acquisition unit is connected with the input end of the personalized adaptation model.
Compared with the prior art, the invention has the following beneficial effects:
according to the intelligent toilet, the sensor detection device in a large space attached to the intelligent household can be utilized, based on the behavior habit of the user, the toilet-using behavior of the user is predicted and analyzed, and further the voice of the intelligent toilet or the start and stop of the detection device are controlled in a signal transmission mode, so that the endless power consumption behavior of the intelligent toilet can be stopped; meanwhile, the problem that the temperature of the toilet gasket is not timely is solved by utilizing the personalized adaptation model, the user experience is improved, the low-carbon requirement of new energy under the current large environment is met, and the energy conservation and the environmental protection are realized.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic flow chart of a new energy low-carbon-based household energy consumption optimization system and method.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, in a first embodiment:
constructing a time period T, and acquiring self data of a user in historical data, wherein the self data of the user comprise the moving state, the body posture and the time characteristics of the user in a house; acquiring the moving state, the body posture and the time characteristics of a user in a house in a time period T before the user uses the intelligent closestool;
the construction of the user toilet prediction model according to the historical data comprises the following steps:
s2-1, acquiring user self data by utilizing an intelligent home indoor sensor, wherein the user self data comprises a moving state, a body posture and time characteristics; constructing a time period T, and under different user self data, in the range of the time period T, recording the user self data in the range of the time period T as high-quality data when the user uses the intelligent closestool; the rest is marked as irrelevant data;
the moving state, the body posture and the time characteristics of the user in the house specifically comprise that the path of the user in the house moves, for example, a plurality of paths leading to the toilet from the starting point of the user exist, the intention of the user is judged step by step through different path turning points, for example, one path leads to the toilet, I turning points exist on the path, after the user passes through the first turning point, whether the path still leads to the toilet or not, and if so, iterative analysis is continued; if not, the task is directly ended.
The body posture refers to a common posture of a user, such as a hand-covered abdomen;
the time feature refers to a fixed time point, and is updated repeatedly according to the habit of the user, for example, the initially set time feature is meal time, namely, the data of the user is meal time feature, and under the detection of a period of time, the user is found to frequently go to a toilet after eating one hour of meal, and then the corresponding subelement under the time feature is one hour after meal;
s2-2, the intelligent household indoor sensor in the step S2-1 acquires the user data and carries out combined coding, and the combination coding is recorded as [ A ] 1 、A 2 、……、A n ]Each code corresponds to a set of user's own data, wherein A 1 、A 2 、……、A n Respectively representing one of the user own data and marking as an element;
s2-3, randomly initializing a population, wherein the population comprises N groups of high-quality data, N is a settable constant value, and the initial iteration times G=1 are set;
s2-4, randomly combining elements in the codes in the group of the step S2-3, and according to the element A in the codes 1 、A 2 、A 3 、……、A n Element A 1 、A 2 、A 3 、……、A n The influence degree of the user self data corresponding to each element or element combination on the intelligent closestool used by the user is calculated respectively, and a deviation value is calculated:
wherein C is i Representing the deviation value of the user data corresponding to the code i for the user to use the intelligent closestool; n represents a set of combinations of all elements in the code i, wherein a single element is also referred to as an element combination; x represents any one of the combinations of all elements in the code i; f (F) x Representing the coding quantity of the user self data with the combination mode of x in the population; f (F) y Representing the number of codes with the combination mode of x in the population; c (C) i Is not extracted and put back;
s2-5, obtaining deviation values of all codes in a population, taking the average value as an iteration judgment result, setting a threshold value, and if the average value is higher than the threshold value, iterating until the average value is lower than the threshold value, ending the iteration; stopping iteration when the average value is lower than the threshold value, and outputting the average value of all current coded deviation values; after finishing iteration, entering a step S2-6;
the iteration adopts a random selection mode, two codes are randomly selected each time, the deviation value is high, the iteration is continuously circulated until the number of selected individuals reaches M, wherein M is a set constant and is smaller than the number of initial individuals; counting the elements in the selected M groups of codes, deleting the element with the lowest occurrence rate, and mining the sub-elements of the rest elements to form a new code [ A ] 11 、A 21 、……、A n1 ]The element and the subelement have a containing relation, the iteration times G=G+1 are set, and the steps S2-4 are repeated;
s2-6, acquiring element information and sub-element information of user self data corresponding to the current deviation value, and generating a user toilet prediction model:
wherein P represents a predicted user's toilet probability; k (k) 1 Representing the influence coefficient of the deviation value; l (L) 0 Representing the current deviation value; k (k) 2 Representing an iteration influence coefficient; g 0 Representing the number of iterations.
The more iterations, the more accurate the result, and the degree of accuracy increases exponentially.
According to the above technical scheme, the starting of the temperature function of the toilet gasket comprises:
the intelligent home is connected to the cloud platform through an intelligent gateway;
the signal transmission module is provided with a probability threshold, and under the condition that the toilet probability of the user exceeds the probability threshold, the signal transmission module judges that the user is about to perform toilet behavior and sends out a signal instruction;
the signal instruction is sent to the intelligent closestool, the intelligent closestool is started, the closestool cover is opened, and meanwhile the temperature of the closestool gasket is adjusted.
According to the technical scheme, the constructing the personalized adaptation model comprises
Acquiring user history manual regulation data, and under single toilet action, setting indoor temperature t 1 Number of times s of adjustment 1 Toilet gasket temperature u 1 Record as a single set of toilet behavior: [ t ] 1 、s 1 、u 1 ];
Setting a threshold s of the number of times of adjustment 0 The method comprises the steps of carrying out a first treatment on the surface of the The data meeting the adjustment times exceeding the times threshold are marked as high weight data, and the rest are marked as low weight data;
respectively constructing two linear regression equations according to the high-weight data and the low-weight data, and combining to generate a personalized adaptation model:
u comfort =(β 0 +β 1 *t 1-1 )*k 3 +k 4 *(β 01 +β 11 *t 1-2 )
wherein u is comfort The temperature data of the toilet gasket output by the personalized adaptation model is represented; beta 0 、β 1 Representing regression coefficients under high weight data; beta 01 、β 11 Representing regression coefficients under high weight data; t is t 1-1 Representing the indoor temperature at high weight data; t is t 1-2 Representing the indoor temperature at low weight data; k (k) 3 、k 4 Respectively represent weight proportion data, k 3 >k 4 ;
Fitting regression coefficient values by utilizing MATLAB software;
acquiring real-time indoor temperature data, and recording as t j The method comprises the steps of carrying out a first treatment on the surface of the The toilet gasket temperature data output by the personalized adaptation model is:
u comfort =(β 0 +β 1 *t j )*k 3 +k 4 *(β 01 +β 11 *t j )
according to the generated u comfort Data, adjust toilet gasket temperature.
In a second embodiment, a new energy low-carbon based household energy consumption optimization system is provided, and the system includes: the intelligent household system comprises an intelligent household acquisition module, a behavior analysis module, a model construction module, a signal transmission module and a temperature monitoring module;
the intelligent home collection module is used for collecting user self data, wherein the user self data comprises the moving state, the body posture and the time characteristics of a user in a house; the behavior analysis module is used for further analyzing the user data and decomposing sub-element data of the user data; the model construction module is used for constructing a user toilet prediction model according to user self data and sub-element data of the user self data, and generating user toilet probability according to the moving state, body posture and time characteristics of the current user in a house; the signal transmission module is used for setting a probability threshold, judging that the user will have a toilet behavior if the toilet probability exceeds the probability threshold, transmitting signals to the intelligent closestool, and starting the temperature function of the closestool gasket; the temperature monitoring module is used for acquiring indoor temperature data, adjusting the temperature data of the toilet gasket according to the history of a user, constructing a personalized adaptation model and adjusting the temperature of the toilet gasket;
the output end of the intelligent home collection module is connected with the input end of the behavior analysis module; the output end of the behavior analysis module is connected with the input end of the model building module; the output end of the model building module is connected with the input end of the signal transmission module; the output end of the signal transmission module is connected with the input end of the temperature monitoring module.
The intelligent home acquisition module comprises a mobile state monitoring unit, a body posture monitoring unit and a time unit;
the mobile state monitoring unit is used for collecting the mobile state of the user indoors and recording the mobile path of the user; the body posture monitoring unit is used for collecting body posture actions of a user and judging whether the user has abdomen discomfort; the time unit is used for recording the time characteristics;
the output ends of the movement state monitoring unit, the body posture monitoring unit and the time unit are all connected to the input end of the behavior analysis module.
The behavior analysis module comprises a subelement analysis unit and an output unit;
the sub-element analysis unit is used for acquiring self data of a user, further analyzing the self data of the user and decomposing sub-element data of the self data of the user; the output unit is used for outputting the subelements to the model building module;
the output end of the subelement analysis unit is connected with the input end of the output unit.
The model building module comprises a model building unit and a probability calculating unit;
the model construction unit is used for constructing a user toilet prediction model according to the user self data and the child element data of the user self data; the probability calculation unit is used for generating the toilet probability of the user according to the moving state, the body posture and the time characteristics of the current user in the house;
the output end of the model building unit is connected with the input end of the probability calculating unit; the output end of the probability calculation unit is connected with the input end of the signal transmission module.
The signal transmission module comprises a probability judging unit and a signal transmission unit;
the probability judging unit is used for setting a probability threshold, judging that the user will have toilet behavior if the toilet probability of the user exceeds the probability threshold, and starting the signal transmission unit; the signal transmission unit is used for connecting the intelligent closestool with the intelligent household cloud platform, transmitting signals to the intelligent closestool and starting the temperature function of a closestool gasket;
the output end of the probability judging unit is connected with the input end of the signal transmission unit; the output end of the signal transmission unit is connected with the input end of the temperature monitoring module.
The temperature monitoring module comprises a real-time temperature data acquisition unit and a personalized adaptation unit;
the real-time temperature data acquisition unit is used for acquiring indoor temperature data; the personalized adaptation unit is used for adjusting the temperature data of the toilet gasket according to the history of the user, constructing a personalized adaptation model and adjusting the temperature of the toilet gasket;
the output end of the real-time temperature data acquisition unit is connected with the input end of the personalized adaptation model.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A home energy consumption optimization method based on new energy low carbon is characterized in that: the method comprises the following steps:
s1, constructing a time period T, and acquiring self data of a user in historical data, wherein the self data of the user comprise a moving state, a body posture and time characteristics of the user in a house; acquiring the moving state, the body posture and the time characteristics of a user in a house in a time period T before the user uses the intelligent closestool;
s2, constructing a user toilet prediction model according to the historical data acquired in the step S1, and generating user toilet probability according to the moving state, the body posture and the time characteristics of the current user in the house;
s3, setting a probability threshold, judging that the user will have a toilet action if the toilet probability exceeds the probability threshold, transmitting a signal to the intelligent closestool, and starting a temperature function of a closestool gasket;
s4, acquiring indoor temperature data, adjusting the temperature data of the toilet gasket according to the history of a user, constructing a personalized adaptation model, and adjusting the temperature of the toilet gasket;
the construction of the user toilet prediction model comprises the following steps:
s2-1, acquiring user self data by utilizing an intelligent home indoor sensor, wherein the user self data comprises a moving state, a body posture and time characteristics; constructing a time period T, and under different user self data, in the range of the time period T, recording the user self data in the range of the time period T as high-quality data when the user uses the intelligent closestool; the rest is marked as irrelevant data;
s2-2, the intelligent household indoor sensor in the step S2-1 acquires the user data and carries out combined coding, and the combination coding is recorded as [ A ] 1 、A 2 、……、A n ]Each code corresponds to a set of user's own data, wherein A 1 、A 2 、……、A n Respectively representing one of the user own data and marking as an element;
s2-3, randomly initializing a population, wherein the population comprises N groups of high-quality data, N is a settable constant value, and the initial iteration times G=1 are set;
s2-4, randomly combining elements in the codes in the group of the step S2-3, and according to the element A in the codes 1 、A 2 、A 3 、……、A n Element A 1 、A 2 、A 3 、……、A n The influence degree of the user self data corresponding to each element or element combination on the intelligent closestool used by the user is calculated respectively, and a deviation value is calculated:
wherein C is i Representing the deviation value of the user data corresponding to the code i for the user to use the intelligent closestool; n represents a set of combinations of all elements in the code i, wherein a single element is also referred to as an element combination; x represents any one of the combinations of all elements in the code i; f (F) x Representing the coding quantity of the user self data with the combination mode of x in the population; f (F) y Representing the number of codes with the combination mode of x in the population;
s2-5, obtaining deviation values of all codes in a population, taking the average value as an iteration judgment result, setting a threshold value, and if the average value is higher than the threshold value, iterating until the average value is lower than the threshold value, ending the iteration; stopping iteration when the average value is lower than the threshold value, and outputting the average value of all current coded deviation values; after finishing iteration, entering a step S2-6;
the iteration adopts a random selection mode, two codes are randomly selected each time, the deviation value is high, the iteration is continuously circulated until the number of selected individuals reaches M, wherein M is a set constant and is smaller than the number of initial individuals; counting the elements in the selected M groups of codes, deleting the element with the lowest occurrence rate, and mining the sub-elements of the rest elements to form a new code [ A ] 11 、A 21 、……、A n1 ]The element and the subelement have a containing relation, the iteration times G=G+1 are set, and the steps S2-4 are repeated;
s2-6, acquiring element information and sub-element information of user self data corresponding to the current deviation value, and generating a user toilet prediction model:
wherein P represents a predicted user's toilet probability; k (k) 1 Representing the influence coefficient of the deviation value; l (L) 0 Representing the current deviation value; k (k) 2 Representing an iteration influence coefficient; g 0 Representing the number of iterations.
2. The new energy low-carbon-based household energy consumption optimization method as claimed in claim 1, wherein the method is characterized by comprising the following steps: the start toilet gasket temperature function includes:
the intelligent home is connected to the cloud platform through an intelligent gateway;
the signal transmission module is provided with a probability threshold, and under the condition that the toilet probability of the user exceeds the probability threshold, the signal transmission module judges that the user is about to perform toilet behavior and sends out a signal instruction;
the signal instruction is sent to the intelligent closestool, the intelligent closestool is started, the closestool cover is opened, and meanwhile the temperature of the closestool gasket is adjusted.
3. The new energy low-carbon-based household energy consumption optimization method as claimed in claim 2, wherein the method is characterized by comprising the following steps: the construction of the personalized adaptation model comprises
Acquiring user history manual regulation data, and under single toilet action, setting indoor temperature t 1 Number of times S of adjustment 1 Toilet gasket temperature u 1 Record as a single set of toilet behavior: [ t ] 1 、s 1 、u 1 ];
Setting a threshold s of the number of times of adjustment 0 The method comprises the steps of carrying out a first treatment on the surface of the The data meeting the adjustment times exceeding the times threshold are marked as high weight data, and the rest are marked as low weight data;
respectively constructing two linear regression equations according to the high-weight data and the low-weight data, and combining to generate a personalized adaptation model:
u comfort =(β 0 +β 1 *t 1-1 )*k 3 +k 4 *(β 01 +β 11 *t 1-2 )
wherein u is comfort The temperature data of the toilet gasket output by the personalized adaptation model is represented; beta 0 、β 1 Representing regression coefficients under high weight data; beta 01 、β 11 Representing regression coefficients under high weight data; t is t 1-1 Representing the indoor temperature at high weight data; t is t 1-2 Representing the indoor temperature at low weight data; k (k) 3 、k 4 Respectively represent weightsRatio data, k 3 >k 4 ;
Fitting regression coefficient values by utilizing MATLAB software;
acquiring real-time indoor temperature data, and recording as t j The method comprises the steps of carrying out a first treatment on the surface of the The toilet gasket temperature data output by the personalized adaptation model is:
u comfort =(β 0 +β 1 *t j )*k 3 +k 4 *(β 01 +β 11 *t j )
according to the generated u comfort Data, adjust toilet gasket temperature.
4. The new energy low-carbon-based household energy consumption optimizing system applying the new energy low-carbon-based household energy consumption optimizing method as claimed in claim 1, which is characterized in that: the system comprises:
the intelligent household system comprises an intelligent household acquisition module, a behavior analysis module, a model construction module, a signal transmission module and a temperature monitoring module;
the intelligent home collection module is used for collecting user self data, wherein the user self data comprises the moving state, the body posture and the time characteristics of a user in a house; the behavior analysis module is used for further analyzing the user data and decomposing sub-element data of the user data; the model construction module is used for constructing a user toilet prediction model according to user self data and sub-element data of the user self data, and generating user toilet probability according to the moving state, body posture and time characteristics of the current user in a house; the signal transmission module is used for setting a probability threshold, judging that the user will have a toilet behavior if the toilet probability exceeds the probability threshold, transmitting signals to the intelligent closestool, and starting the temperature function of the closestool gasket; the temperature monitoring module is used for acquiring indoor temperature data, adjusting the temperature data of the toilet gasket according to the history of a user, constructing a personalized adaptation model and adjusting the temperature of the toilet gasket;
the output end of the intelligent home collection module is connected with the input end of the behavior analysis module; the output end of the behavior analysis module is connected with the input end of the model building module; the output end of the model building module is connected with the input end of the signal transmission module; the output end of the signal transmission module is connected with the input end of the temperature monitoring module.
5. The new energy low-carbon-based household energy consumption optimization system according to claim 4, wherein the system is characterized in that: the intelligent home acquisition module comprises a mobile state monitoring unit, a body posture monitoring unit and a time unit;
the mobile state monitoring unit is used for collecting the mobile state of the user indoors and recording the mobile path of the user; the body posture monitoring unit is used for collecting body posture actions of a user and judging whether the user has abdomen discomfort; the time unit is used for recording the time characteristics;
the output ends of the movement state monitoring unit, the body posture monitoring unit and the time unit are all connected to the input end of the behavior analysis module.
6. The new energy low-carbon-based household energy consumption optimization system according to claim 4, wherein the system is characterized in that: the behavior analysis module comprises a subelement analysis unit and an output unit;
the sub-element analysis unit is used for acquiring self data of a user, further analyzing the self data of the user and decomposing sub-element data of the self data of the user; the output unit is used for outputting the subelements to the model building module;
the output end of the subelement analysis unit is connected with the input end of the output unit.
7. The new energy low-carbon-based household energy consumption optimization system according to claim 4, wherein the system is characterized in that: the model building module comprises a model building unit and a probability calculating unit;
the model construction unit is used for constructing a user toilet prediction model according to the user self data and the child element data of the user self data; the probability calculation unit is used for generating the toilet probability of the user according to the moving state, the body posture and the time characteristics of the current user in the house;
the output end of the model building unit is connected with the input end of the probability calculating unit; the output end of the probability calculation unit is connected with the input end of the signal transmission module.
8. The new energy low-carbon-based household energy consumption optimization system according to claim 4, wherein the system is characterized in that: the signal transmission module comprises a probability judging unit and a signal transmission unit;
the probability judging unit is used for setting a probability threshold, judging that the user will have toilet behavior if the toilet probability of the user exceeds the probability threshold, and starting the signal transmission unit; the signal transmission unit is used for connecting the intelligent closestool with the intelligent household cloud platform, transmitting signals to the intelligent closestool and starting the temperature function of a closestool gasket;
the output end of the probability judging unit is connected with the input end of the signal transmission unit; the output end of the signal transmission unit is connected with the input end of the temperature monitoring module.
9. The new energy low-carbon-based household energy consumption optimization system according to claim 4, wherein the system is characterized in that: the temperature monitoring module comprises a real-time temperature data acquisition unit and a personalized adaptation unit;
the real-time temperature data acquisition unit is used for acquiring indoor temperature data; the personalized adaptation unit is used for adjusting the temperature data of the toilet gasket according to the history of the user, constructing a personalized adaptation model and adjusting the temperature of the toilet gasket;
the output end of the real-time temperature data acquisition unit is connected with the input end of the personalized adaptation model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210909751.XA CN115268269B (en) | 2022-07-29 | 2022-07-29 | Household energy consumption optimization system and method based on new energy low carbon |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210909751.XA CN115268269B (en) | 2022-07-29 | 2022-07-29 | Household energy consumption optimization system and method based on new energy low carbon |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115268269A CN115268269A (en) | 2022-11-01 |
CN115268269B true CN115268269B (en) | 2023-06-02 |
Family
ID=83746950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210909751.XA Active CN115268269B (en) | 2022-07-29 | 2022-07-29 | Household energy consumption optimization system and method based on new energy low carbon |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115268269B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116521340B (en) * | 2023-04-27 | 2023-10-10 | 福州慧林网络科技有限公司 | Low-delay parallel data processing system and method based on large-bandwidth network |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3599609A1 (en) * | 2005-11-26 | 2020-01-29 | Natera, Inc. | System and method for cleaning noisy genetic data and using data to make predictions |
CN104112168B (en) * | 2014-06-16 | 2017-08-29 | 国家电网公司 | A kind of smart home optimization method based on multi-agent system |
US20170051933A1 (en) * | 2015-08-21 | 2017-02-23 | Google Inc. | Persistent home thermal comfort model reusable across multiple sensor and device configurations in a smart home |
KR102586745B1 (en) * | 2015-09-01 | 2023-10-10 | 삼성전자 주식회사 | Method and apparatus of controlling energy consumption |
CN105607508A (en) * | 2016-03-24 | 2016-05-25 | 重庆邮电大学 | Smart home device control method and system based on user behavior analysis |
CN109188924A (en) * | 2018-09-18 | 2019-01-11 | 珠海格力电器股份有限公司 | Power utilization control method and device for intelligent household system |
CN111025922B (en) * | 2019-11-21 | 2023-09-12 | 维沃移动通信有限公司 | Target equipment control method and electronic equipment |
CN113110085A (en) * | 2021-04-16 | 2021-07-13 | 广州鑫泓设备设计有限公司 | Intelligent home management system based on big data |
-
2022
- 2022-07-29 CN CN202210909751.XA patent/CN115268269B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN115268269A (en) | 2022-11-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105045234B (en) | Wired home energy management method based on intelligence wearable device behavior perception | |
US20180323996A1 (en) | Automatic generation of scenes using an assistant device | |
Dong et al. | Sensor-based occupancy behavioral pattern recognition for energy and comfort management in intelligent buildings | |
Dobbs et al. | Model predictive HVAC control with online occupancy model | |
US11268713B2 (en) | Smart home air conditioner automatic control system based on artificial intelligence | |
CN115268269B (en) | Household energy consumption optimization system and method based on new energy low carbon | |
CN108413588B (en) | Personalized air conditioner control system and method based on thermal imaging and BP neural network | |
CN108401013A (en) | A kind of smart home Internet of Things communication device | |
CN112288599A (en) | Scene service implementation method for smart home, computer device and storage medium | |
CN109951363B (en) | Data processing method, device and system | |
CN107229262A (en) | A kind of intelligent domestic system | |
CN106461260B (en) | Method and apparatus for controlling temperature | |
CN104933128A (en) | Information pushing method and system | |
CN111077785A (en) | Awakening method, awakening device, terminal and storage medium | |
CN110471301A (en) | A kind of smart home service recommendation system and method based on user behavior | |
CN116384773A (en) | Public building cold load prediction method and device, equipment and storage medium | |
CN110308663A (en) | A kind of intelligent home control system and its control method | |
KR20210049769A (en) | Smart Home Airconditioner Automatic control system based on Artificial Intelligence | |
Verbruggen et al. | Inclusion of window opening habits in a window model based on activity and occupancy patterns | |
CN111797980A (en) | Self-adaptive learning method for personalized floor heating use habits | |
CN110044073B (en) | Control method and system of water heater | |
CN112286103A (en) | Intelligent household control system | |
CN116088338A (en) | Intelligent household equipment control method | |
KR102465304B1 (en) | Situation based ai smart home system using ai switch and ai living information device | |
KR102319475B1 (en) | AI human life service providing system through AI home appliances |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |