CN109769333B - Event-driven household intelligent lighting method and system - Google Patents
Event-driven household intelligent lighting method and system Download PDFInfo
- Publication number
- CN109769333B CN109769333B CN201910254893.5A CN201910254893A CN109769333B CN 109769333 B CN109769333 B CN 109769333B CN 201910254893 A CN201910254893 A CN 201910254893A CN 109769333 B CN109769333 B CN 109769333B
- Authority
- CN
- China
- Prior art keywords
- illumination
- event
- lighting
- model
- color temperature
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention discloses an event-driven household intelligent lighting method and system, which comprises the following steps: collecting household lighting information, marking the information, and constructing a historical database and a decision table; establishing an event identification model and a personnel illumination demand model by utilizing data in a historical database; after real-time data acquisition, the real-time data acquisition is matched with the established model, the corresponding life scene is identified, and the optimal lighting environment is given. The invention has the beneficial effects that: (1) the household lighting environment can change according to different scenes, so that the household life is more intelligent. The color temperature and the brightness of the light can be intelligently adjusted according to the personal preference and the life habit of family members, so that the lighting system is more personalized and humanized. (2) The collection of image information enables the classification of the living scenes to be more detailed, and each living scene can obtain the most appropriate lighting environment.
Description
Technical Field
The invention relates to a household intelligent lighting method, in particular to an event-driven household lighting method capable of achieving intelligent control, and belongs to the technical field of intelligent household.
Background
Domestic illumination is the most common sight among people's daily life, but in people's daily life, forgets the situation of turning off the light and takes place occasionally, has caused unnecessary energy waste, and in addition, people hope to use different light under different life scenes, but this demand is not fine to be satisfied. Therefore, an intelligent lighting method is needed to create a saving and comfortable lighting environment for people.
However, with current home lighting, there are still many difficulties in implementing intelligent lighting. In a common family, due to the fact that family members are different, family function partitions are different, personnel activities are different, optimal lights of different scenes are different, and the diversity and complexity of the scenes are high, the error rate is high during scene recognition, and further the change of lighting environment is unsatisfactory.
In terms of the current technology, on one hand, household lighting scenes are less classified, only simple classification is provided, and common scenes of daily life of people are not divided in detail, so that the lighting comfort is greatly reduced; on the other hand, at present, only the automatic control of the on and off of the lamp is performed, and factors such as illumination intensity, color temperature and the like cannot be changed according to different scenes. Therefore, it is necessary to develop a novel household intelligent lighting method to achieve intelligent control of a household lighting system, so that household power consumption can be saved, a safe and comfortable lighting environment is provided for people, and the life quality is improved.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide an event-driven household intelligent lighting method and system.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides an event-driven household intelligent lighting method, which comprises the following steps:
step 1: collecting household lighting information, marking the information, and constructing a historical database and a decision table;
step 2: establishing an event identification model and a personnel illumination demand model by utilizing data in a historical database;
and step 3: after real-time data acquisition, the real-time data acquisition is matched with the established model, the corresponding life scene is identified, and the optimal lighting environment is given.
Preferably, the step 1 comprises:
step 11: in different household lighting places, a camera is used for collecting image information, a pyroelectric infrared sensor is used for collecting common data, an illumination sensor is used for collecting the illumination of each scene, and a color temperature sensor is used for collecting the color temperature of each scene;
step 12: marking the activities of different members in different places at different times for the acquired data and images;
step 13: and establishing a historical image database and a decision table by using the information acquired and labeled.
Preferably, the event recognition model constructed in step 2 is implemented by a deep learning method, and the image recognition strategy based on deep learning is as follows: firstly, preprocessing an image; inputting the processed image into a designed neural network for training, continuously optimizing a cost function through a forward propagation algorithm and a backward propagation algorithm until a minimum value is obtained, and updating a weight to obtain a better recognition model; and finally, identifying and classifying the real-time images by using the model.
Preferably, the method for constructing the personnel illumination demand model in the step 2 adopts a rough set method, and the rule extraction strategy based on the rough set is as follows: let X be the conditional attribute set and Y be the decision attribute set, ai,biThe attributes of each element in the sets X and Y. When the collected information conforms to aiOr biIf the conditions are specified, the data are stored in the corresponding set. The decision rule is as follows: condition → decision;
for a scene adopting image recognition, a first-class illumination demand model is constructed, and the structure is as follows: user + time + activity + field → illuminance + color temperature. The resulting human illumination demand model has the following form: if a person i is in a place k to engage in an activity l in a time period j, the optimal illumination is p, the optimal color temperature is c, wherein i is a certain person, j is a certain time period of the whole day time, k is a certain place of a family, l is a certain activity, p is a certain illumination value, and c is a certain color temperature value.
For the scene identified by the pyroelectric sensor, a second type illumination demand model is constructed, and the structure is as follows: time + field → illuminance + color temperature. The resulting human illumination demand model has the following form: if the person i is located at the site in the time period j, the optimal illumination is p and the optimal color temperature is c.
The invention also provides an event-driven household intelligent lighting system, which is used for executing the event-driven household intelligent lighting method and comprises the following steps:
the information acquisition and labeling module is used for executing the method in the step 1;
a personnel illumination requirement and scene identification module for executing the method in the step 2;
and the event identification and processing module is used for executing the method in the step 3.
Due to the adoption of the technical scheme, the invention has the beneficial effects that:
(1) the household lighting environment can change according to different scenes, so that the household life is more intelligent. The color temperature and the brightness of the light can be adjusted according to personal preferences and life habits of family members, so that the lighting system is more personalized and humanized.
(2) Adopt camera, pyroelectric infrared sensor, illuminance sensor to gather data simultaneously, data are various and comprehensive, especially image information's collection, and the life scene is categorised more meticulous for every life scene can all obtain the most suitable lighting environment.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a general flowchart of the event-driven home intelligent lighting method of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
Example 1
As shown in fig. 1, an event-driven home intelligent lighting method and system.
According to the invention, the family lighting information is collected to construct the historical database, the data in the historical database is utilized to construct the event recognition model and the personnel lighting demand model, and the real-time data is collected and then matched with the established models, so that the intelligent control of the light in different scenes is realized, the accuracy of the family lighting system in recognizing complex scenes is ensured, and the life quality of people is improved.
The invention mainly comprises three core modules, namely an information acquisition and marking module, a personnel illumination requirement and scene identification module and an event identification and processing module. The information acquisition and marking module is mainly used for acquiring household lighting information, marking the information and constructing a historical database and a decision table; the personnel illumination demand and scene recognition module is mainly used for training collected images, constructing a scene recognition model, extracting by utilizing a rough set rule and constructing a personnel illumination demand model; the event recognition and processing module mainly recognizes the corresponding life scene according to the real-time information and provides the optimal lighting environment.
The specific functions of each core module are as follows:
1. information acquisition and marking module
The module consists of three parts of information acquisition, information marking and decision table construction. The module is communicated with an event recognition model building module, a personnel illumination demand model building module and a model matching and processing module.
(1) The method comprises the following steps that a camera is used for collecting image information in public occasions with large activity population of living rooms and dining rooms, and a pyroelectric infrared sensor is used for collecting common data (whether people exist indoors or not); for occasions with strong privacy and few moving population, such as bedrooms, toilets and the like, people only need to use the pyroelectric infrared sensor to acquire whether to move. And simultaneously, acquiring the illumination of each scene by using an illumination sensor, and acquiring the color temperature of each scene by using a color temperature sensor.
Specifically, the method comprises the following steps: public places such as living rooms, restaurants and the like are provided with cameras, and images, pyroelectric data, color temperature and illumination are required to be collected; private spaces, such as bedrooms, toilets, etc., are not equipped with cameras, and only pyroelectric data, color temperature and illumination need to be collected.
(2) And marking the activities of different members in different places at different times for the acquired data and images.
In the step, images, data, users, time, places and activities are artificially labeled so as to be used as training samples for deep learning of the images.
Time: the entire day was divided into different time periods, one time interval of ten minutes.
The user: different family members in the family.
The venue includes different functional partitions in the home. Such as living room, study room, master bed, kitchen, toilet, etc.
Activities include reading books, watching television, doing homework, gathering meals, etc.
(3) And establishing a historical image database and a decision table by using the information acquired and labeled.
The decision representation reflecting different lighting environments in different scenes is shown in table 1 for example:
TABLE 1 decision table
2. Personnel illumination demand and scene recognition module
The module is mainly used for establishing a personnel illumination demand model through four elements and determining the optimal lighting environment under different scenes. The module is communicated with the information acquisition and marking module, the event recognition model construction module and the model matching and processing module.
And constructing a common scene recognition model by adopting a deep learning method based on the labeled image data in the historical database.
The image recognition strategy based on deep learning is as follows: firstly, preprocessing an image; then inputting the processed image into a designed neural network (a convolutional neural network is one of machine learning methods in a depth model, has strong adaptability, is mainly used for image classification, and is provided with the technology at present) for training, continuously optimizing a cost function (the cost function is a target function for finding an optimal solution through a forward propagation algorithm and a backward propagation algorithm, wherein the purpose of continuously optimizing the cost function is to enhance the classification performance of the volume and the neural network, and the technology is provided at present) until a minimum value is obtained, and obtaining a better identification model after updating a weight (the weight is the important degree of the index in the whole analysis process); and finally, identifying and classifying the real-time images by using the model.
And constructing a personnel illumination demand model by adopting a rough set method according to the decision table.
The rule extraction strategy based on the rough set is as follows: let X be the conditional attribute set and Y be the decision attribute set, ai,biThe attributes of each element in the sets X and Y. When the collected information conforms to aiOr biIf the conditions are specified, the data are stored in the corresponding set. The decision rule is as follows: condition → decision (adjust to the color temperature value and illumination value corresponding to the condition).
For a scene adopting image recognition, a first-class illumination demand model is constructed, and the structure is as follows: user + time + activity + field → illuminance + color temperature. The resulting human illumination demand model has the following form: if a person i is in a place k to engage in an activity l in a time period j, the optimal illumination is p, the optimal color temperature is c, wherein i is a certain person, j is a certain time period of the whole day time, k is a certain place of a family, l is a certain activity, p is a certain illumination value, and c is a certain color temperature value.
For the scene identified by the pyroelectric sensor, a second type illumination demand model is constructed, and the structure is as follows: time + field → illuminance + color temperature. The resulting human illumination demand model has the following form: if the person i is located at the site in the time period j, the optimal illumination is p and the optimal color temperature is c.
3. Event recognition and processing module
The module sends an action instruction mainly by matching the real-time data with the corresponding model, so as to obtain the optimal lighting environment. The module is communicated with the information acquisition and marking module, the event recognition model building module and the personnel illumination demand model building module.
And for a room which is not provided with a camera for collecting images, a pyroelectric sensor is used for collecting information, whether personnel move in the room is judged, a second type illumination demand model is called, and the optimal illumination and color temperature value is given.
For a room provided with a camera, calling a scene recognition model according to the collected image to judge a scene, calling a first-class illumination demand model in combination with information collected by a pyroelectric sensor, and giving an optimal illumination and color temperature value.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (4)
1. An event-driven household intelligent lighting method comprises the following steps:
step 1: collecting household lighting information, marking the information, and constructing a historical database and a decision table;
step 2: establishing an event identification model and a personnel illumination demand model by utilizing data in a historical database;
and step 3: after real-time data acquisition, matching the real-time data acquisition with the established model, identifying a corresponding life scene, and giving an optimal lighting environment;
the method for constructing the personnel illumination demand model in the step 2 adopts a rough set method, and the rule extraction strategy based on the rough set is as follows: let X be the conditional attribute set and Y be the decision attribute set, ai,biThe attributes of each element in the sets X and Y respectively; when the collected information conforms to aiOr biWhen the specified conditions exist, storing the data into a corresponding set; the decision rule is as follows: deciding a decision based on the condition;
for a scene adopting image recognition, a first-class illumination demand model is constructed, and the structure is as follows: determining illumination and color temperature based on user, time, activity, and location; the resulting human illumination demand model has the following form: if a person i is located in a place k to engage in an activity l in a time period j, the optimal illumination is p, the optimal color temperature is c, wherein i is a certain position of the person, j is a certain time period of the whole day time, k is a certain position of a family place, l is a certain position of the activity, p is a certain illumination value, and c is a certain color temperature value;
for the scene identified by the pyroelectric sensor, a second type illumination demand model is constructed, and the structure is as follows: determining illumination and color temperature based on time and place; the resulting human illumination demand model has the following form: if the person i is located at the site in the time period j, the optimal illumination is p and the optimal color temperature is c.
2. The event-driven home intelligent lighting method according to claim 1, wherein the step 1 comprises:
step 11: in different household lighting places, a camera is used for collecting image information, a pyroelectric infrared sensor is used for collecting common data, an illumination sensor is used for collecting the illumination of each scene, and a color temperature sensor is used for collecting the color temperature of each scene;
step 12: marking the activities of different members in different places at different times for the acquired data and images;
step 13: and establishing a historical image database and a decision table by using the information acquired and labeled.
3. The event-driven household intelligent lighting method according to claim 1, wherein the event recognition model is built in the step 2 by adopting a deep learning method, and the image recognition strategy based on the deep learning is as follows: firstly, preprocessing an image; inputting the processed image into a designed neural network for training, continuously optimizing a cost function through a forward propagation algorithm and a backward propagation algorithm until a minimum value is obtained, and updating a weight to obtain a better recognition model; and finally, identifying and classifying the real-time images by using the model.
4. An event-driven home smart lighting system, configured to implement the event-driven home smart lighting method according to any one of claims 1 to 3 when executed, the event-driven home smart lighting system comprising:
an information acquisition and labeling module for executing the method of step 1;
a personnel illumination requirement and scene identification module, which is used for executing the method of the step 2;
and an event identification and processing module for executing the method of step 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910254893.5A CN109769333B (en) | 2019-03-29 | 2019-03-29 | Event-driven household intelligent lighting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910254893.5A CN109769333B (en) | 2019-03-29 | 2019-03-29 | Event-driven household intelligent lighting method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109769333A CN109769333A (en) | 2019-05-17 |
CN109769333B true CN109769333B (en) | 2020-02-04 |
Family
ID=66460263
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910254893.5A Active CN109769333B (en) | 2019-03-29 | 2019-03-29 | Event-driven household intelligent lighting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109769333B (en) |
Families Citing this family (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112074062A (en) * | 2019-05-21 | 2020-12-11 | 广东小天才科技有限公司 | Scene-based light adjusting method and intelligent lighting device |
CN110139449A (en) * | 2019-06-13 | 2019-08-16 | 安徽理工大学 | A kind of full room lighting system of intelligence based on human body attitude identification |
CN110673900A (en) * | 2019-08-23 | 2020-01-10 | 康佳集团股份有限公司 | Light effect adjusting method, intelligent terminal and storage medium |
CN111352349A (en) * | 2020-01-27 | 2020-06-30 | 东北石油大学 | System and method for collecting and adjusting information of old people living environment |
CN111491429A (en) * | 2020-04-30 | 2020-08-04 | 青岛亿联客信息技术有限公司 | Intelligent lighting lamp, control method thereof and intelligent lighting system |
CN111556630B (en) * | 2020-06-29 | 2021-06-01 | 东北大学 | Intelligent lamp self-adaptive scene recognition system and method based on Bayesian network |
CN113597071B (en) * | 2021-06-25 | 2024-04-05 | 北京智芯微电子科技有限公司 | Lighting method and system |
CN113420754A (en) * | 2021-07-15 | 2021-09-21 | 智谋纪(深圳)科技有限公司 | Intelligent light color control method and device, computer equipment and storage medium |
CN113483283A (en) * | 2021-08-05 | 2021-10-08 | 威强科技(北京)有限公司 | Lighting device capable of automatically adjusting posture according to use scene |
CN114992586A (en) * | 2022-04-25 | 2022-09-02 | 淮阴工学院 | Light source adjusting device and method for building |
CN114885477A (en) * | 2022-04-26 | 2022-08-09 | 山东浪潮科学研究院有限公司 | Illumination control method, device and system based on edge calculation |
CN115175415A (en) * | 2022-05-30 | 2022-10-11 | 青岛海尔科技有限公司 | Digital twinning light adjusting method, device and system |
CN116095915B (en) * | 2023-04-10 | 2023-06-30 | 南昌大学 | Dimming method and system based on human body thermal comfort |
CN117032048A (en) * | 2023-09-06 | 2023-11-10 | 东莞市粤广创照明有限公司 | Intelligent home lighting control system of Internet of things |
CN116939921B (en) * | 2023-09-15 | 2023-12-19 | 中建照明有限公司 | Intelligent household lighting control system and method based on Internet of things |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8901825B2 (en) * | 2011-04-12 | 2014-12-02 | Express Imaging Systems, Llc | Apparatus and method of energy efficient illumination using received signals |
CN109229009B (en) * | 2018-08-20 | 2021-12-07 | 深圳佑驾创新科技有限公司 | Control method and device for vehicle headlamp, vehicle and storage medium |
-
2019
- 2019-03-29 CN CN201910254893.5A patent/CN109769333B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN109769333A (en) | 2019-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109769333B (en) | Event-driven household intelligent lighting method and system | |
CN112533319B (en) | Scene type classroom intelligent lighting control device | |
CN108712809B (en) | A kind of luminous environment intelligent control method neural network based | |
CN112584572B (en) | Open Office Lighting System | |
CN106604508B (en) | Light environment control method and control system based on self study | |
CN112969254B (en) | Business hotel guest room illumination control device based on scene automatic identification | |
CN109874209A (en) | Commercial hotel guest room scene lighting system based on scene automatic identification | |
CN110035578A (en) | Open office lighting system and control method based on mixed lighting | |
CN106340071B (en) | A kind of smart classroom system based on cloud computing | |
CN116634622A (en) | LED intelligent control method, system and medium based on Internet of things | |
CN210274639U (en) | Intelligent whole-house lighting system based on human body posture recognition | |
CN110139449A (en) | A kind of full room lighting system of intelligence based on human body attitude identification | |
US10769909B1 (en) | Using sensor data to detect events | |
CN112074062A (en) | Scene-based light adjusting method and intelligent lighting device | |
CN116300507B (en) | Intelligent home management control system and method based on Internet of things technology | |
US10791607B1 (en) | Configuring and controlling light emitters | |
CN114727461A (en) | Light control system based on intelligent home | |
CN117762032A (en) | Intelligent equipment control system and method based on scene adaptation and artificial intelligence | |
CN117406613A (en) | Furniture intelligent linkage control method and control device based on environment perception | |
CN109283849B (en) | Intelligent house system | |
CN104657575B (en) | Light source and environmental analysis method based on light sensor | |
CN113537090A (en) | Intelligent household lamp control method and device and storage medium | |
Mandaric et al. | Context-based System for User-Centric Smart Environment | |
CN118102556B (en) | Full-house intelligent lamplight illumination noninductive control method and related device | |
CN116939921B (en) | Intelligent household lighting control system and method based on Internet of things |
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 |