CN114095768A - Infrared remote controller learning method and system based on machine learning algorithm - Google Patents
Infrared remote controller learning method and system based on machine learning algorithm Download PDFInfo
- Publication number
- CN114095768A CN114095768A CN202111432065.XA CN202111432065A CN114095768A CN 114095768 A CN114095768 A CN 114095768A CN 202111432065 A CN202111432065 A CN 202111432065A CN 114095768 A CN114095768 A CN 114095768A
- Authority
- CN
- China
- Prior art keywords
- remote controller
- infrared remote
- external equipment
- model
- infrared
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/41—Structure of client; Structure of client peripherals
- H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
- H04N21/42204—User interfaces specially adapted for controlling a client device through a remote control device; Remote control devices therefor
- H04N21/42206—User interfaces specially adapted for controlling a client device through a remote control device; Remote control devices therefor characterized by hardware details
- H04N21/42221—Transmission circuitry, e.g. infrared [IR] or radio frequency [RF]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses an infrared remote controller learning method and system based on a machine learning algorithm, wherein the method comprises the following steps: collecting the use behavior data of infrared remote controllers of a large number of users and the data of external equipment; constructing an infrared remote controller model library and an infrared remote control protocol library; carrying out data characteristic engineering processing to construct a sample data set; constructing a multi-classification deep neural network for remote controller identification; training and verifying the infrared remote controller multi-classification algorithm network by using the Tensorflow and the sample data set, and generating an infrared remote controller model identification model; deploying a prediction service of an infrared remote controller model identification model by using TFServing and docker; the intelligent television terminal collects sample characteristic information and requests an infrared remote controller model identification model of an online Tenschlowserving service. The invention enables a user to automatically learn the key codes and the corresponding functions of the infrared remote controller of the external equipment of the intelligent television without a complicated remote controller code matching learning process.
Description
Technical Field
The invention relates to the technical field of infrared remote control learning, in particular to an infrared remote controller learning method and system based on a machine learning algorithm.
Background
At present, televisions in families are usually externally connected with other devices such as a television set top box, a wireless television set top box, a satellite television set top box, an OTT box, an IPTV, a video recorder, a VCD/DVD and the like to watch television programs or video and audio contents. The common household television is an intelligent television, and can watch network videos, games and the like, and the television is provided with a special remote controller, usually a Bluetooth remote controller, and has a voice function and the like. The television external equipment (peripheral for short) also has a special remote controller, which is usually an infrared remote controller. In the process of remote control operation, a user needs to use two different remote controllers to respectively control a television or a peripheral, so that the situation that the remote controllers and equipment are not corresponding to each other and cannot be controlled easily occurs, and the problem that the peripheral remote controllers cannot be found or cannot be remotely controlled after being damaged easily exists.
In the modern times of popularization of smart televisions, televisions gradually become smart home control centers, and interaction by utilizing a television remote controller and external infrared equipment becomes a strong demand of users. I.e. the television remote control is a universal remote control for infrared devices. But the process of learning the infrared remote controller is needed before the television remote controller controls other infrared devices.
At present, if a learning remote controller needs to have partial key functions of a television remote controller or a peripheral remote controller, a user is required to learn codes through a complicated remote controller, the learning process of the infrared remote controller is time-consuming and labor-consuming, and therefore the infrared remote controller capable of automatically learning and identifying television external equipment is needed.
Disclosure of Invention
The invention provides an infrared remote controller learning method and system based on a machine learning algorithm, which adopts a machine learning multi-classification algorithm technology based on artificial intelligence to solve the problem of automatically identifying an infrared remote controller of a television external device.
The technical scheme adopted by the invention is as follows: the infrared remote controller learning method based on the machine learning algorithm comprises the following steps:
s1, data collection and ETL: collecting the use behavior data of infrared remote controllers of a large number of users and the data of external equipment; constructing an infrared remote controller model library and an infrared remote control protocol library; carrying out data characteristic engineering processing to construct a sample data set;
s2, model training: constructing a multi-classification deep neural network for remote controller identification; training and verifying the infrared remote controller multi-classification algorithm network by using the Tensorflow and the sample data set, and generating an infrared remote controller model identification model;
s3, model deployment: deploying a prediction service of an infrared remote controller model identification model by using TF Serving and docker;
s4, recognizing by an infrared remote controller of external equipment: the intelligent television terminal collects sample characteristic information and requests an infrared remote controller model identification model of an online Tensorflow Serving service.
As a preferable mode of the infrared remote controller learning method based on the machine learning algorithm, the infrared remote controller usage behavior data in S1 includes:
the type of the infrared remote controller, the key information, the infrared remote controller signal corresponding to the key, the protocol information used by the infrared remote controller, and the appearance image of the infrared remote controller.
As a preferable mode of the infrared remote controller learning method based on the machine learning algorithm, the external device data in S1 includes:
the method comprises the steps of starting up pictures of the external equipment, menus of the external equipment, key signals of a remote controller of the external equipment, the type of an output interface of the external equipment, the use duration of the external equipment, the information acquisition of the use time period of the external equipment, the geographic position information and the ASN attribution information.
As a preferable mode of the infrared remote controller learning method based on the machine learning algorithm, in S1, an infrared remote controller model library and an infrared remote control protocol library are constructed; performing data characteristic engineering processing, and specifically constructing a sample data set comprises:
s1.1, establishing an infrared remote controller model base, an infrared remote control protocol base and scanning configuration information at a cloud end according to the infrared remote controller model, the protocol information used by the infrared remote controller and the infrared remote controller key signal data;
s1.2, under an external equipment source, according to scanning configuration of a cloud, an infrared receiving module of the intelligent television terminal tries different protocols and detects whether infrared signals of different keys exist or not; meanwhile, signals of the infrared remote controller keys are collected and uploaded to a cloud end, and the infrared remote controller model index is obtained through an infrared remote controller model library;
s1.3, performing data characteristic engineering processing by using a Hadoop big data platform to form a sample data set, and dividing the sample data set into a model training set and a verification set.
As a preferable mode of the infrared remote controller learning method based on the machine learning algorithm, the S2 includes:
s2.1, converting the training sample data set into a data set in a TFRecord format;
s2.2, training a VGG16 network by using the collected data sets of the startup picture, the appearance image and the infrared remote controller appearance image of the external equipment of the intelligent television;
and S2.3, training and generating an infrared remote controller model identification model by combining the geographical position information of the sample data set, the ASN attribution information, the type of an output interface of the external equipment, the use duration of the external equipment and the use time period of the external equipment with the characteristics of S2.2 through a multi-classification algorithm network structure of the infrared remote controller.
As a preferable mode of the infrared remote controller learning method based on the machine learning algorithm, the S3 includes:
s3.1, periodically synchronizing an infrared remote controller model identification model generated by a tensoflow platform on an algorithm server for model training to a docker server;
and S3.2, creating a container on the Docker server through an open-source application container engine Docker, and operating Tensflow Serving service in the container, so that the trained infrared remote controller model identification model is directly on line and provides service.
As a preferable mode of the infrared remote controller learning method based on the machine learning algorithm, the S4 includes:
s4.1, acquiring local MAC (media access control) information, an external equipment input interface, an external equipment input type, a geographic position, an ASN (access network) attribution, the weekly use duration of the external equipment, the common time period of the external equipment, a starting image of the external equipment, an appearance image of the external equipment and a remote controller image of the external equipment by the intelligent television terminal;
s4.2, acquiring image number information of the external equipment startup image, the external equipment appearance image and the external equipment remote controller image which are acquired in the S4.1 through a corresponding VGG16 network;
s4.3, transmitting the characteristic information of the S4.1 and the S4.2 to an infrared remote controller model identification model of a Tensflow Serving service of the docker server, and acquiring the serial number of the infrared remote controller model;
s4.4, acquiring the corresponding infrared remote controller information from the serial number of the infrared remote controller model acquired in the S4.3 through an infrared remote controller model library of a far-end server;
and S4.5, the Bluetooth remote controller of the intelligent television terminal acquires the infrared remote controller information through S4.4 and controls the external infrared equipment of the television through the information.
The invention also provides an infrared remote controller learning system based on the machine learning algorithm, which comprises an artificial intelligence server, an intelligent television with a camera, a television remote controller, an intelligent television external device and an external device remote controller;
the television remote control is a Bluetooth remote controller, and an infrared signal coding module, an infrared signal modulation module and an infrared signal transmitting module are installed on the television remote control;
an infrared receiving connector is mounted on the intelligent television;
the artificial intelligence server comprises a hadoop big data platform, a Tensorflow end-to-end open source machine learning platform training server and a docker model prediction server;
the system realizes the rapid automatic learning of the Bluetooth remote controller of the intelligent television to the external infrared remote controller of the intelligent television through the infrared remote controller learning method based on the machine learning algorithm.
The invention has the beneficial effects that: according to the infrared remote controller intelligent automatic learning system, the intelligent television and the television remote controller are matched to construct the infrared remote controller intelligent automatic learning system through the artificial intelligent server (algorithms such as image recognition, multi-classification and scene recognition) on the cloud, a user does not need to perform a complicated remote controller code matching learning process, the system automatically learns the key codes and the corresponding functions of the infrared remote controller of the external equipment of the intelligent television, and therefore the television and the external equipment are not required to be controlled in a distributed mode through two different remote controllers, and the television terminal and the external equipment connected with the television terminal can be controlled and managed in a unified mode through the television remote controller.
Drawings
Fig. 1 is a flow chart of the infrared remote controller identification of the external device disclosed by the invention.
FIG. 2 is a schematic diagram of a sample data set disclosed herein.
Fig. 3 is a network structure block diagram of the infrared remote controller recognition multi-classification algorithm disclosed by the invention.
Fig. 4 is a block diagram of the network structure of the VGG16 disclosed in the present invention.
Fig. 5 is a block diagram of an intelligent television module disclosed by the invention.
Fig. 6 is a system block diagram of an infrared remote controller learning system based on a machine learning algorithm disclosed by the present invention.
Fig. 7 is a block diagram of a bluetooth remote controller module of the smart television disclosed in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail below with reference to the accompanying drawings, but embodiments of the present invention are not limited thereto.
Example 1:
referring to fig. 1, the present embodiment provides a learning method for an infrared remote controller based on a machine learning algorithm, including the following steps:
s1, data collection and ETL: collecting the use behavior data of infrared remote controllers of a large number of users and the data of external equipment; constructing an infrared remote controller model library and an infrared remote control protocol library; and carrying out data characteristic engineering processing to construct a sample data set.
Wherein the infrared remote controller uses the behavioral data to include: the type of the infrared remote controller, the key information, the infrared remote controller signal corresponding to the key, the protocol information used by the infrared remote controller, and the appearance image of the infrared remote controller.
The information of various external devices can be collected and collected manually, mainly including information of STB/IPTV set-top boxes of broadcasting and TV of various cities or IPTV boxes of various large telecom operators and OTT boxes of various large manufacturers. The external device data specifically includes: the method comprises the steps of starting up pictures of the external equipment, menus of the external equipment, key signals of a remote controller of the external equipment, the type of an output interface of the external equipment, the use duration of the external equipment, the information acquisition of the use time period of the external equipment, the geographic position information and the ASN attribution information.
In the S1, an infrared remote controller model library and an infrared remote control protocol library are constructed; performing data characteristic engineering processing, and specifically constructing a sample data set comprises:
s1.1, an infrared remote controller model base, an infrared remote control protocol base and scanning configuration information are constructed at the cloud according to the infrared remote controller model, the protocol information used by the infrared remote controller and the infrared remote controller key signal data.
S1.2, under an external equipment source, according to scanning configuration of a cloud, an infrared receiving module of the intelligent television terminal tries different protocols and detects whether infrared signals of different keys exist or not; and meanwhile, signals of the infrared remote controller keys are collected and uploaded to a cloud end, and the infrared remote controller model index is obtained through an infrared remote controller model library.
S1.3, performing data characteristic engineering processing by using a Hadoop big data platform to form a sample data set (an example of the data set is shown in figure 2), and dividing the sample data set into a model training set and a verification set.
S2, model training: constructing a multi-classification deep neural network for remote controller identification; and training and verifying the infrared remote controller multi-classification algorithm network by using Tensorflow (an end-to-end open source machine learning platform) and the sample data set, and generating an infrared remote controller model identification model. The network structure of the infrared remote controller multi-classification algorithm is shown in fig. 3, wherein V in fig. 3 represents weight, and X represents vector.
The S2 specifically includes:
and S2.1, converting the training sample data set into a data set in a TFRecord format.
S2.2, training the VGG16 network by using the collected data sets of the startup picture, the appearance image and the infrared remote controller appearance image of the external equipment of the intelligent television. The network structure block diagram of the VGG16 is shown in FIG. 4.
And S2.3, training and generating an infrared remote controller model identification model by combining the geographical position information of the sample data set, the ASN attribution information, the type of an output interface of the external equipment, the use duration of the external equipment and the use time period of the external equipment with the characteristics of S2.2 through a multi-classification algorithm network structure of the infrared remote controller.
S3, model deployment: and deploying the prediction service of the model identification model of the infrared remote controller by using TF Serving and docker.
The S3 specifically includes:
s3.1, regularly synchronizing an infrared remote controller model identification model generated by a tensoflow platform on an algorithm server for model training to a docker server.
And S3.2, creating a container on the Docker server through an open-source application container engine Docker, and operating Tensflow Serving service in the container, so that the trained infrared remote controller model identification model is directly on line and provides service.
S4, recognizing by an infrared remote controller of external equipment: the intelligent television terminal collects sample characteristic information and requests an infrared remote controller model identification model of an online Tensorflow Serving service.
The S4 specifically includes:
s4.1, acquiring local MAC (media access control) acquired by the intelligent television terminal (comprising a main module shown in figure 5), an external device input interface, an external device input type, a geographic position, an ASN (access service network) attribution, the weekly use duration of the external device, the common time period of the external device, a starting image of the external device, an appearance image of the external device and a remote controller image of the external device.
And S4.2, acquiring image number information of the external equipment startup image, the external equipment appearance image and the external equipment remote controller image which are acquired in the S4.1 through a corresponding VGG16 network.
And S4.3, transmitting the characteristic information of the S4.1 and the S4.2 to an infrared remote controller model identification model of a Tensflow Serving service of the docker server, and acquiring the serial number of the infrared remote controller model.
And S4.4, acquiring the corresponding infrared remote controller information from the serial number of the infrared remote controller acquired in the S4.3 through an infrared remote controller model library of the remote server.
And S4.5, the Bluetooth remote controller of the intelligent television terminal acquires the infrared remote controller information through S4.4 and controls the external infrared equipment of the television through the information.
Example 2
The embodiment discloses an infrared remote controller learning system based on a machine learning algorithm, as shown in fig. 6, which includes an artificial intelligence server, an intelligent television with a camera, a television remote controller, an external device of the intelligent television (IPTV/OTT/STB, etc.), and an external device remote controller (infrared remote controller).
The television remote control is a Bluetooth remote controller, and an infrared signal coding module, an infrared signal modulation module and an infrared signal transmitting module are installed on the television remote control. The block diagram of the smart television Bluetooth remote controller module is shown in FIG. 7.
An infrared receiving connector is installed on the smart television, and a block diagram of a smart television module is shown in fig. 5.
The artificial intelligence server comprises a hadoop big data platform, a Tensorflow end-to-end open source machine learning platform training server and a docker model prediction server.
An infrared remote controller is generally used by an external device of the smart television, such as an IPTV/OTT/STB, and a specific process of learning the external infrared remote controller by a bluetooth remote controller of the smart television is shown in fig. 1.
The system realizes the rapid and automatic learning of the external infrared remote controller of the intelligent television by the Bluetooth remote controller of the intelligent television through the infrared remote controller learning method based on the machine learning algorithm in the embodiment 1.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. The infrared remote controller learning method based on the machine learning algorithm is characterized by comprising the following steps:
s1, data collection and ETL: collecting the use behavior data of infrared remote controllers of a large number of users and the data of external equipment; constructing an infrared remote controller model library and an infrared remote control protocol library; carrying out data characteristic engineering processing to construct a sample data set;
s2, model training: constructing a multi-classification deep neural network for remote controller identification; training and verifying the infrared remote controller multi-classification algorithm network by using the Tensorflow and the sample data set, and generating an infrared remote controller model identification model;
s3, model deployment: deploying a prediction service of an infrared remote controller model identification model by using TF Serving and docker;
s4, recognizing by an infrared remote controller of external equipment: the intelligent television terminal collects sample characteristic information and requests an infrared remote controller model identification model of an online Tensorflow Serving service.
2. The infrared remote control learning method based on machine learning algorithm as claimed in claim 1, wherein the infrared remote control usage behavior data in S1 includes:
the type of the infrared remote controller, the key information, the infrared remote controller signal corresponding to the key, the protocol information used by the infrared remote controller, and the appearance image of the infrared remote controller.
3. The infrared remote control learning method based on machine learning algorithm as claimed in claim 2, wherein the external device data in S1 includes:
the method comprises the steps of starting up pictures of the external equipment, menus of the external equipment, key signals of a remote controller of the external equipment, the type of an output interface of the external equipment, the use duration of the external equipment, the information acquisition of the use time period of the external equipment, the geographic position information and the ASN attribution information.
4. The infrared remote control learning method based on machine learning algorithm of claim 3, wherein in S1, an infrared remote control model library and an infrared remote control protocol library are constructed; performing data characteristic engineering processing, and specifically constructing a sample data set comprises:
s1.1, establishing an infrared remote controller model base, an infrared remote control protocol base and scanning configuration information at a cloud end according to the infrared remote controller model, the protocol information used by the infrared remote controller and the infrared remote controller key signal data;
s1.2, under an external equipment source, according to scanning configuration of a cloud, an infrared receiving module of the intelligent television terminal tries different protocols and detects whether infrared signals of different keys exist or not; meanwhile, signals of the infrared remote controller keys are collected and uploaded to a cloud end, and the infrared remote controller model index is obtained through an infrared remote controller model library;
s1.3, performing data characteristic engineering processing by using a Hadoop big data platform to form a sample data set, and dividing the sample data set into a model training set and a verification set.
5. The infrared remote control learning method based on machine learning algorithm as claimed in claim 4, wherein the S2 includes:
s2.1, converting the training sample data set into a data set in a TFRecord format;
s2.2, training a VGG16 network by using the collected data sets of the startup picture, the appearance image and the infrared remote controller appearance image of the external equipment of the intelligent television;
and S2.3, training and generating an infrared remote controller model identification model by combining the geographical position information of the sample data set, the ASN attribution information, the type of an output interface of the external equipment, the use duration of the external equipment and the use time period of the external equipment with the characteristics of S2.2 through a multi-classification algorithm network structure of the infrared remote controller.
6. The infrared remote control learning method based on machine learning algorithm as claimed in claim 5, wherein the S3 includes:
s3.1, periodically synchronizing an infrared remote controller model identification model generated by a tensoflow platform on an algorithm server for model training to a docker server;
and S3.2, creating a container on the Docker server through an open-source application container engine Docker, and operating Tensflow Serving service in the container, so that the trained infrared remote controller model identification model is directly on line and provides service.
7. The infrared remote control learning method based on machine learning algorithm as claimed in claim 6, wherein the S4 includes:
s4.1, acquiring local MAC (media access control) information, an external equipment input interface, an external equipment input type, a geographic position, an ASN (access network) attribution, the weekly use duration of the external equipment, the common time period of the external equipment, a starting image of the external equipment, an appearance image of the external equipment and a remote controller image of the external equipment by the intelligent television terminal;
s4.2, acquiring image number information of the external equipment startup image, the external equipment appearance image and the external equipment remote controller image which are acquired in the S4.1 through a corresponding VGG16 network;
s4.3, transmitting the characteristic information of the S4.1 and the S4.2 to an infrared remote controller model identification model of a Tensflow Serving service of the docker server, and acquiring the serial number of the infrared remote controller model;
s4.4, acquiring the corresponding infrared remote controller information from the serial number of the infrared remote controller model acquired in the S4.3 through an infrared remote controller model library of a far-end server;
and S4.5, the Bluetooth remote controller of the intelligent television terminal acquires the infrared remote controller information through S4.4 and controls the external infrared equipment of the television through the information.
8. An infrared remote controller learning system based on a machine learning algorithm is characterized by comprising an artificial intelligence server, an intelligent television with a camera, a television remote controller, an intelligent television external device and an external device remote controller;
the television remote control is a Bluetooth remote controller, and an infrared signal coding module, an infrared signal modulation module and an infrared signal transmitting module are installed on the television remote control;
an infrared receiving connector is mounted on the intelligent television;
the artificial intelligence server comprises a hadoop big data platform, a Tensorflow end-to-end open source machine learning platform training server and a docker model prediction server;
the system realizes the rapid automatic learning of the external infrared remote controller of the intelligent television by the Bluetooth remote controller of the intelligent television through the infrared remote controller learning method based on the machine learning algorithm in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111432065.XA CN114095768B (en) | 2021-11-29 | 2021-11-29 | Infrared remote controller learning method and system based on machine learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111432065.XA CN114095768B (en) | 2021-11-29 | 2021-11-29 | Infrared remote controller learning method and system based on machine learning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114095768A true CN114095768A (en) | 2022-02-25 |
| CN114095768B CN114095768B (en) | 2023-06-13 |
Family
ID=80305475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111432065.XA Active CN114095768B (en) | 2021-11-29 | 2021-11-29 | Infrared remote controller learning method and system based on machine learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114095768B (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102346643A (en) * | 2011-09-14 | 2012-02-08 | 华为终端有限公司 | Realization method and device for learnable type remoter |
| EP2645728A1 (en) * | 2012-03-29 | 2013-10-02 | LG Electronics Inc. | A multimedia device connected to at least one electronic device and controlling method thereof |
| CN103426292A (en) * | 2013-09-03 | 2013-12-04 | 湖南工业大学 | Infrared remote control, infrared code learning method and infrared code emission method |
| CN103458283A (en) * | 2013-08-07 | 2013-12-18 | 四川长虹电器股份有限公司 | Remote control learning method based on smart television application |
| CN103546791A (en) * | 2013-10-15 | 2014-01-29 | 华为技术有限公司 | Method and equipment for recognizing various remote control units |
| CN103544830A (en) * | 2012-07-11 | 2014-01-29 | 上海曜铂信息科技有限公司 | Intelligent pairing method of infrared remote control device |
| CN103680118A (en) * | 2013-12-04 | 2014-03-26 | 康佳集团股份有限公司 | An intelligent remote control system and a control method thereof |
| CN104320684A (en) * | 2014-10-13 | 2015-01-28 | 四川长虹电器股份有限公司 | Method for controlling set top box, television and system |
| CN105825659A (en) * | 2015-01-04 | 2016-08-03 | 中兴通讯股份有限公司 | Terminal and infrared remote control method |
| CN105992039A (en) * | 2015-02-28 | 2016-10-05 | Tcl集团股份有限公司 | Television media device control device, system and method |
| CN106781378A (en) * | 2016-12-12 | 2017-05-31 | 广州视源电子科技股份有限公司 | The information configuring methods and related device of information matching method, remote control |
| CN107170228A (en) * | 2017-07-03 | 2017-09-15 | 杭州古北电子科技有限公司 | Remote control system based on infrared code |
| CN107770589A (en) * | 2017-08-31 | 2018-03-06 | 成都市斯达鑫辉视讯科技有限公司 | A kind of top box of digital machine remotely controlled and memory system |
| CN107798852A (en) * | 2017-11-08 | 2018-03-13 | 东莞市康茂电子有限公司 | A kind of control method of Universal infrared remote controller system |
| CN108197633A (en) * | 2017-11-24 | 2018-06-22 | 百年金海科技有限公司 | Deep learning image classification based on TensorFlow is with applying dispositions method |
| JP2019016960A (en) * | 2017-07-07 | 2019-01-31 | 国立大学法人 奈良先端科学技術大学院大学 | Signal identification method and device of infrared remote control |
| CN111432022A (en) * | 2020-04-07 | 2020-07-17 | 深圳中兴网信科技有限公司 | Model deployment method, server, and computer-readable storage medium |
| CN112085942A (en) * | 2020-09-25 | 2020-12-15 | 汉桑（南京）科技有限公司 | Method and system for configuring remote control function data according to remote control equipment image |
| CN113516840A (en) * | 2021-09-13 | 2021-10-19 | 北京创米智汇物联科技有限公司 | Electric appliance control method, camera device, electronic equipment and storage medium |
-
2021
- 2021-11-29 CN CN202111432065.XA patent/CN114095768B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102346643A (en) * | 2011-09-14 | 2012-02-08 | 华为终端有限公司 | Realization method and device for learnable type remoter |
| EP2645728A1 (en) * | 2012-03-29 | 2013-10-02 | LG Electronics Inc. | A multimedia device connected to at least one electronic device and controlling method thereof |
| CN103544830A (en) * | 2012-07-11 | 2014-01-29 | 上海曜铂信息科技有限公司 | Intelligent pairing method of infrared remote control device |
| CN103458283A (en) * | 2013-08-07 | 2013-12-18 | 四川长虹电器股份有限公司 | Remote control learning method based on smart television application |
| CN103426292A (en) * | 2013-09-03 | 2013-12-04 | 湖南工业大学 | Infrared remote control, infrared code learning method and infrared code emission method |
| CN103546791A (en) * | 2013-10-15 | 2014-01-29 | 华为技术有限公司 | Method and equipment for recognizing various remote control units |
| CN103680118A (en) * | 2013-12-04 | 2014-03-26 | 康佳集团股份有限公司 | An intelligent remote control system and a control method thereof |
| CN104320684A (en) * | 2014-10-13 | 2015-01-28 | 四川长虹电器股份有限公司 | Method for controlling set top box, television and system |
| CN105825659A (en) * | 2015-01-04 | 2016-08-03 | 中兴通讯股份有限公司 | Terminal and infrared remote control method |
| CN105992039A (en) * | 2015-02-28 | 2016-10-05 | Tcl集团股份有限公司 | Television media device control device, system and method |
| CN106781378A (en) * | 2016-12-12 | 2017-05-31 | 广州视源电子科技股份有限公司 | The information configuring methods and related device of information matching method, remote control |
| CN107170228A (en) * | 2017-07-03 | 2017-09-15 | 杭州古北电子科技有限公司 | Remote control system based on infrared code |
| JP2019016960A (en) * | 2017-07-07 | 2019-01-31 | 国立大学法人 奈良先端科学技術大学院大学 | Signal identification method and device of infrared remote control |
| CN107770589A (en) * | 2017-08-31 | 2018-03-06 | 成都市斯达鑫辉视讯科技有限公司 | A kind of top box of digital machine remotely controlled and memory system |
| CN107798852A (en) * | 2017-11-08 | 2018-03-13 | 东莞市康茂电子有限公司 | A kind of control method of Universal infrared remote controller system |
| CN108197633A (en) * | 2017-11-24 | 2018-06-22 | 百年金海科技有限公司 | Deep learning image classification based on TensorFlow is with applying dispositions method |
| CN111432022A (en) * | 2020-04-07 | 2020-07-17 | 深圳中兴网信科技有限公司 | Model deployment method, server, and computer-readable storage medium |
| CN112085942A (en) * | 2020-09-25 | 2020-12-15 | 汉桑（南京）科技有限公司 | Method and system for configuring remote control function data according to remote control equipment image |
| CN113516840A (en) * | 2021-09-13 | 2021-10-19 | 北京创米智汇物联科技有限公司 | Electric appliance control method, camera device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 杨连池;林春婷;: "自动适配多种设备的智能遥控器设计与实现", 物联网技术, no. 12 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114095768B (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101321268B (en) | Personal media broadcasting system | |
| CN103780970A (en) | Media playing method, device and system | |
| CN102842213A (en) | Remote control terminal and information processing apparatus | |
| WO2014082353A1 (en) | Method and device for identifying frequency channel | |
| CN101426125A (en) | Personal video recorder functionality for placeshifting systems | |
| CN104184923A (en) | System and method used for retrieving figure information in video | |
| CN103581705A (en) | Method and system for recognizing video program | |
| CN102118639A (en) | Information processing apparatus, information processing method, and program | |
| CN1703910A (en) | Control device in a home network environment | |
| CN103475856A (en) | Video monitoring system applied to broadcast and TV network | |
| CN103974125A (en) | Method and system for previewing and playing video streaming | |
| CN102346643A (en) | Realization method and device for learnable type remoter | |
| CN104754422A (en) | Control method for realizing smart home equipments based on STB (Set Top Box) | |
| CN109587536A (en) | A kind of long-distance remote-control method, equipment, server and system | |
| CN107948737A (en) | The recommendation method and device of TV programme | |
| CN104410898A (en) | Intelligent home cloud box system and control method thereof | |
| CN102316386A (en) | Double-screen interaction method based on digital television receiving device, and device and system | |
| CN102685567A (en) | Digital television terminal, hot channel control method and server | |
| CN103368925B (en) | A kind of method of device authentication | |
| CN101335849A (en) | TV set and its program information obtaining method, TV broadcasting receiving system | |
| CN114095768B (en) | Infrared remote controller learning method and system based on machine learning algorithm | |
| CN110430383B (en) | Terminal, signaling server, audio and video communication method and computer storage medium | |
| CN104378681A (en) | Self-adaptive control method of smart television | |
| CN104284212A (en) | Method, device and system for acquiring program information | |
| CN106165436B (en) | Double-direction control is carried out to set-top box using optical character identification |
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 |