WO2017012321A1 - 显示状态的调节方法、显示状态调节装置及显示装置 - Google Patents

显示状态的调节方法、显示状态调节装置及显示装置 Download PDF

Info

Publication number
WO2017012321A1
WO2017012321A1 PCT/CN2016/071713 CN2016071713W WO2017012321A1 WO 2017012321 A1 WO2017012321 A1 WO 2017012321A1 CN 2016071713 W CN2016071713 W CN 2016071713W WO 2017012321 A1 WO2017012321 A1 WO 2017012321A1
Authority
WO
WIPO (PCT)
Prior art keywords
neural network
network model
display state
wavelet neural
wavelet
Prior art date
Application number
PCT/CN2016/071713
Other languages
English (en)
French (fr)
Inventor
王笛
张�浩
时凌云
董学
Original Assignee
京东方科技集团股份有限公司
北京京东方光电科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司, 北京京东方光电科技有限公司 filed Critical 京东方科技集团股份有限公司
Priority to US15/107,384 priority Critical patent/US10565955B2/en
Publication of WO2017012321A1 publication Critical patent/WO2017012321A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G5/00—Control arrangements or circuits for visual indicators common to cathode-ray tube indicators and other visual indicators
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G5/00—Control arrangements or circuits for visual indicators common to cathode-ray tube indicators and other visual indicators
    • G09G5/003—Details of a display terminal, the details relating to the control arrangement of the display terminal and to the interfaces thereto
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
    • G06F3/147—Digital output to display device ; Cooperation and interconnection of the display device with other functional units using display panels
    • 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
    • G06N3/048—Activation functions
    • 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
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2320/00—Control of display operating conditions
    • G09G2320/06—Adjustment of display parameters
    • G09G2320/0626—Adjustment of display parameters for control of overall brightness
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2320/00—Control of display operating conditions
    • G09G2320/08—Arrangements within a display terminal for setting, manually or automatically, display parameters of the display terminal
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2340/00—Aspects of display data processing
    • G09G2340/04—Changes in size, position or resolution of an image
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2340/00—Aspects of display data processing
    • G09G2340/04—Changes in size, position or resolution of an image
    • G09G2340/0407—Resolution change, inclusive of the use of different resolutions for different screen areas
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2360/00—Aspects of the architecture of display systems
    • G09G2360/14—Detecting light within display terminals, e.g. using a single or a plurality of photosensors
    • G09G2360/144—Detecting light within display terminals, e.g. using a single or a plurality of photosensors the light being ambient light
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G2360/00—Aspects of the architecture of display systems
    • G09G2360/16—Calculation or use of calculated indices related to luminance levels in display data

Definitions

  • the invention belongs to the technical field of display, and particularly relates to a method for adjusting a display state, a display state adjusting device and a display device.
  • the screen brightness of the display device needs to be increased to meet the viewing requirements; in dim ambient light conditions, The brightness of the screen of the display device is lowered to maintain proper brightness to avoid damage to the eyes.
  • the current method for adjusting the display state of a mobile phone screen includes:
  • the inventor has found that at least the following problems exist in the prior art: when the screen of the mobile phone is adjusted by the method 1), only the brightness of the screen of the mobile phone can be adjusted, and the function is single; and when the screen of the mobile phone is adjusted by the method 2), There are relatively many setting parameters, but manual setting of each parameter is required, so it is energy-intensive and less accurate.
  • the present invention provides a method for adjusting a display state, a display state adjusting device, and a display device, which can adjust the display state more intelligently and conveniently, and have high precision. , applicability is strong.
  • a method for adjusting a display state including: collecting information parameters of an environment in which the display is located; inputting the collected information parameters into a pre-established wavelet neural network model for analysis, and obtaining a display The display state to be displayed; and adjust the display state of the display based on the analysis result.
  • the information parameter includes at least one of a gravity acceleration parameter, a light parameter, a position parameter, a temperature parameter, and an angle parameter.
  • the adjustment target of the display state includes at least one of brightness, standby, resolution, and refresh rate.
  • the wavelet neural network model is updated once for each information parameter of the environment in which the display is located 100 times.
  • the wavelet neural network model is generated using a wavelet basis function.
  • the output of the hidden layer is h n (j), Where i is the i-th node of the input layer, j is the j-th node of the hidden layer; ⁇ ij is the connection weight between the i-th node of the input layer and the j-th node of the hidden layer; h j is a wavelet basis function; b j is a translation factor of the wavelet basis function h j ; a j is a scaling factor of the wavelet basis function h j ; n is a positive integer.
  • the value of the output layer is y n (k), Where ⁇ jk is the connection weight between the jth node of the hidden layer and the kth node of the output layer.
  • the method before collecting the information parameters of the environment in which the environment is located, the method further includes: a step of establishing a wavelet neural network model; a step of training the established wavelet neural network model; and a step of testing the wavelet neural network model.
  • the wavelet neural network model is generated using a wavelet basis function
  • the step of training the wavelet neural network model includes the steps of initializing the wavelet neural network model, wherein the scaling factor, the translation factor, and the connection weight of the wavelet neural network are randomly initialized in the wavelet basis function, and the wavelet neural network is set.
  • the learning speed of the network model; the step of classifying the samples is used to divide the samples into training samples and test samples, wherein the training samples are used to train the wavelet neural network model, and the test samples are used to test the test accuracy of the wavelet neural network model.
  • the calculation analysis step is used to input the training sample into the wavelet neural network model, calculate the predicted output value of the wavelet neural network model, and calculate the error between the predicted output value and the expected output value of the wavelet neural network model, and analyze the number of training times. If the error is less than or equal to 0.0001, the prediction output step is performed, or the analysis obtains the training number to reach the preset value, and then the prediction output step is performed; otherwise, the following steps are performed: the correction step is used for the scaling factor, the translation factor, and the wavelet in the wavelet basis function Neural network Then the weight is corrected so that the output value of the error prediction value and the desired output wavelet neural network model is 0.0001 or less; and a prediction output step outputs the predicted value output.
  • a display state adjustment apparatus includes: an acquisition unit for collecting information parameters of an environment in which the display is located; and an analysis unit for inputting the collected information parameters to a pre-established The analysis is performed in the wavelet neural network model to obtain the display state in which the display is to be displayed, and an adjustment unit for adjusting the display state of the display according to the analysis result.
  • the collecting unit comprises at least one of a gravity acceleration sensor, a light sensor, a temperature sensor, a positioning module, and an electronic compass.
  • the adjustment target of the display state includes at least one of brightness, standby, resolution, and refresh rate.
  • the display state adjusting device further comprises: a modeling unit for establishing a wavelet neural network model; a training unit for training the established wavelet neural network model; and a testing unit for the wavelet neural network The model is tested.
  • the training unit comprises: an initialization module, configured to randomly initialize a scaling factor, a translation factor, and a wavelet neural network in the wavelet basis function The connection weight, and set the learning speed of the wavelet neural network model; the sample classification module is used to divide the sample into training samples and test samples, wherein the training samples are used to train the wavelet neural network model, and the test samples are used to test the wavelet The test accuracy of the neural network model; and the computational analysis module for inputting the training samples into the wavelet neural network model, calculating the predicted output values of the wavelet neural network model, and calculating the predicted output values and expected output values of the wavelet neural network model The error between the two is analyzed, and the number of trainings is obtained.
  • an initialization module configured to randomly initialize a scaling factor, a translation factor, and a wavelet neural network in the wavelet basis function The connection weight, and set the learning speed of the wavelet neural network model
  • the sample classification module is used to divide the sample into training samples and test samples, wherein the training samples are used to
  • the error is less than or equal to 0.0001, the predicted output is performed, or if the training reaches the preset value, the predicted output is performed; and the correction module is used for the error greater than 0.0001 and the training number does not reach the pre-predicted
  • the scaling factor, the translation factor and the connection weight of the wavelet neural network in the wavelet basis function are modified so that the error between the predicted output value of the wavelet neural network model and the expected output value is less than or equal to 0.0001.
  • the analyzing unit is further configured to analyze the number of acquisitions of the collecting unit, and update the wavelet neural network model once every 100 times of information parameters of the environment in which the display is located.
  • the wavelet neural network model is generated using a wavelet basis function.
  • the output of the hidden layer is h n (j), Where i is the i-th node of the input layer, j is the j-th node of the hidden layer; ⁇ ij is the connection weight between the i-th node of the input layer and the j-th node of the hidden layer; h j is a wavelet basis function; b j is a translation factor of the wavelet basis function h j ; a j is a scaling factor of the wavelet basis function h j ; n is a positive integer.
  • the value of the output layer is y n (k), Where ⁇ jk is the connection weight between the jth node of the hidden layer and the kth node of the output layer.
  • a display comprising the above display state adjusting device.
  • the information parameter of the environment where the collected display (or user) is located is analyzed by the wavelet neural network, and information about the environment where the display is located is obtained, and the information corresponds to one of the displays.
  • the display state is adjusted to adjust the display state of the display based on the information.
  • the information parameters of the environment in which the gravity acceleration sensor, the light sensor, the temperature sensor, the positioning module, and the electronic compass are detected are integrated and analyzed by the wavelet neural network, and according to the analysis result
  • the display state of the display is adjusted to achieve higher recognition accuracy and a wider range of applications than a conventional single-function sensor (for example, a light sensor).
  • the embodiment of the present invention provides a display including the above display state adjusting device, which achieves higher recognition accuracy and a wider application range than when the configuration is not provided.
  • FIG. 1 is a flow chart showing a method of adjusting a display state according to Embodiment 1 of the present invention.
  • FIG. 2 is a flow chart showing the modeling of an intelligent algorithm in a method of adjusting a display state according to Embodiment 2 of the present invention.
  • FIG. 3 is a schematic diagram of a wavelet neural network model of Embodiment 2 of the present invention.
  • FIG. 4 is a flow chart showing training of a wavelet neural network model in a method of adjusting a display state according to Embodiment 2 of the present invention.
  • Fig. 5 is a schematic diagram of a display state adjusting device of a third embodiment of the present invention.
  • Fig. 6 is another schematic view of the display state adjusting device of the third embodiment of the present invention.
  • Fig. 7 is a schematic diagram of a training unit in the display state adjusting device of the third embodiment of the present invention.
  • the embodiment provides a method for adjusting a display state for adjusting a display state of a display (for example, a display screen of a mobile phone), for example, adjusting brightness, resolution, refresh rate, and the like.
  • FIG. 1 is a flow chart of a method for adjusting a display state according to the embodiment. As shown in FIG. 1 , the adjustment method includes: collecting information parameters of an environment in which the display is located; inputting the collected information parameters into a pre-established wavelet neural network model, and analyzing the display state that the display is to be displayed; The result of the analysis adjusts the display state of the display.
  • the information parameter of the environment in which the collected display (or user) is located is analyzed by the wavelet neural network to obtain information about the environment in which the display is located, and the information corresponds to a display state of the display, thereby The information adjusts the display state of the display.
  • the adjustment method is very intelligent and has strong applicability, and the specific implementation method is described in detail in conjunction with the following embodiments.
  • This embodiment provides a method for adjusting a display state.
  • the method for adjusting the display state provided by the embodiment will be described in detail below with reference to FIGS.
  • the method specifically includes the following steps S1 to S4.
  • step S1 the intelligent algorithm is modeled.
  • Figure 2 is a flow chart of intelligent algorithm modeling. As shown in FIG. 2, the process of intelligent algorithm modeling specifically includes the following steps S101 to S103.
  • step S101 a wavelet neural network model is established, which is generated by using a wavelet basis function.
  • the mathematical formula of the wavelet basis function is:
  • FIG. 3 is a schematic diagram of a wavelet neural network model of the present embodiment.
  • the wavelet neural network model includes an input layer, an implicit layer, and an output layer.
  • the output of the hidden layer is h n (j)
  • i is the i-th node of the input layer
  • j is the j-th node of the hidden layer
  • ⁇ ij is the connection weight between the i-th node of the input layer and the j-th node of the hidden layer
  • h j is a wavelet basis function
  • b j is a translation factor of the wavelet basis function h j
  • a j is a scaling factor of the wavelet basis function h j
  • n is a positive integer.
  • the value of the output layer is y n (k),
  • ⁇ jk is the connection weight between the jth node of the hidden layer and the kth node of the output layer.
  • the small neural network model is updated every time the information parameters of the environment in which the display is located are updated, wherein h n (j) represents the jth of the hidden layer after the wavelet neural network model is updated n times.
  • the output of the node, h n-1 (j), represents the output of the jth node of the hidden layer after the wavelet neural network model is updated n-1 times.
  • step S102 After completing the establishment of the wavelet neural network model, the wavelet neural network model is trained in step S102.
  • FIG. 4 is a flow chart of training the wavelet neural network model in the embodiment. As shown in FIG. 4, the process of training the wavelet neural network model specifically includes the following steps S1021 to S1025.
  • step S1021 the wavelet neural network model is initialized, specifically, the scaling factor, the translation factor, and the connection weight of the wavelet neural network in the wavelet basis function are randomly initialized, and the learning speed of the wavelet neural network model is set; the learning speed is usually Is 0.1.
  • step S1022 the samples are classified. Specifically, the samples are divided into training samples and test samples, wherein the training samples are used to train the wavelet neural network model, and the test samples are used to test the test accuracy of the wavelet neural network model.
  • step S1023 calculation and analysis are performed. Specifically, the training sample is input into the wavelet neural network model, the predicted output value of the wavelet neural network model is calculated, and the predicted output value of the wavelet neural network model is calculated and the expected output value is calculated. The error is analyzed and the number of trainings is obtained. If the error is less than or equal to 0.0001, the prediction output step S1025 is performed, or if the number of training times reaches the preset value, the prediction output step S1025 is performed; otherwise, the following step S1024 is performed.
  • step S1024 the factor and the weight are modified, specifically, the scaling factor, the translation factor, and the connection weight of the wavelet neural network in the wavelet basis function are modified to make the predicted output value and expectation of the wavelet neural network model.
  • the error of the output value is less than or equal to 0.0001.
  • step S1025 the predicted output value is output. So far, the training of the wavelet neural network model is completed.
  • step S103 the wavelet neural network model is tested in step S103.
  • the wavelet neural network model obtained by the training in step S102 is applied to the adjustment of the display state of the display, and the wavelet neural network model is tested by using the collected environmental information parameters to obtain a desired wavelet neural network model. So far, the process of intelligent algorithm (ie, wavelet neural network) modeling is completed.
  • the information parameter of the environment in which the display is located is updated 100 times, and the wavelet neural network model is updated once.
  • step S2 the information parameters of the environment in which the display is located are collected.
  • the collected information parameters may include at least one of a gravity acceleration parameter, a light parameter, a position parameter, a temperature parameter, and an angle parameter.
  • a gravity acceleration parameter For example, multiple information parameters are collected to make the analysis of the next step more accurate.
  • the collected environmental information parameters are current or voltage signals
  • these digital signals can be used as training inputs of the wavelet neural network model.
  • the training of wavelet neural network models is known in the field of wavelet neural network technology and will not be discussed in detail herein.
  • the parameter weights of the wavelet neural network can be obtained.
  • step S3 the collected information parameters are input to the wavelet neural network model established in step S1 for analysis, and the display state in which the display is to be displayed is obtained.
  • the positional parameters for example, GPS coordinates
  • the angle parameter is 90°
  • the gravity acceleration parameter is, for example, 2 minutes without change
  • the parameters are obtained by the wavelet neural network model.
  • the analysis is performed to obtain that the user state is a sleep state, and thus, the display state that the mobile phone is to display is obtained as a standby state corresponding to the user's sleep state.
  • step S4 the display state of the display is adjusted according to the analysis result described above so that the display state satisfies the needs of the user. For example, when the analysis indicates that the display state to be displayed should be in the standby state, the display is made to stand by.
  • the adjustment target of the display state described above may include at least one of brightness, standby, resolution, and refresh rate.
  • At least one of a gravity acceleration parameter, a light parameter, a position parameter, a temperature parameter, and an angle parameter is preferably a plurality of types, and the parameters are analyzed by a wavelet neural network. According to the analysis result, the display state of the display is adjusted, so that the adjustment of the display state is more accurate, and the method is more intelligent and applicable than the prior art. At the same time, this method can achieve higher fault tolerance, which can be more accurate than the traditional threshold setting method.
  • FIG. 5 is a schematic view of the display state adjusting device.
  • the display state adjustment device may include: an acquisition unit configured to collect information parameters of an environment in which the display is located; and an analysis unit configured to input the collected information parameters into a pre-established wavelet neural network model. Analysis, the display state of the display to be displayed; and the adjustment unit, It is used to adjust the display status of the display according to the analysis result.
  • the analyzing unit analyzes the information parameters of the environment in which the display (or the user) collected by the collecting unit is located through the wavelet neural network, and obtains information about the environment in which the display is located, and the information corresponds to one of the displays.
  • the display state is adjusted to adjust the display state of the display by the adjustment unit according to the information.
  • the adjustment device is very intelligent and adaptable.
  • the above-mentioned collecting unit may include at least one of a gravity acceleration sensor, a light sensor, a temperature sensor, a positioning module, and an electronic compass.
  • the gravity acceleration sensor is used to detect the motion information parameter of the display;
  • the light sensor is used to detect the brightness information parameter of the light in the environment where the display is located;
  • the temperature sensor is used to detect the temperature information parameter of the environment in which the display is located; and
  • the positioning module for example, GPS
  • the position parameter (indoor/outdoor) of the environment in which the display is located is detected;
  • the electronic compass is used to detect the inclination parameter of the display.
  • the adjustment target of the display state may include at least one of brightness, standby, resolution, and refresh rate.
  • Fig. 6 is another schematic view of the display state adjusting device of the embodiment.
  • the display state adjusting apparatus of this embodiment may further include: a modeling unit for establishing a wavelet neural network model; a training unit for training the wavelet neural network model; and a testing unit for The wavelet neural network model was tested.
  • Fig. 7 is a schematic diagram of a training unit in the display state adjusting device of the embodiment.
  • the training unit may include: an initialization module, configured to randomly initialize a scaling factor, a translation factor, and a connection weight of the wavelet neural network in the wavelet basis function, and set a learning speed of the wavelet neural network model; the sample classification module For dividing the sample into training samples and test samples, wherein the training samples are used to train the wavelet neural network model, and the test samples are used to test the test accuracy of the wavelet neural network model; the calculation analysis module is used to input the training samples to In the wavelet neural network model, the predicted output value of the wavelet neural network model is calculated, and the error between the predicted output value and the expected output value of the wavelet neural network model is calculated, and the training times are analyzed.
  • an initialization module configured to randomly initialize a scaling factor, a translation factor, and a connection weight of the wavelet neural network in the wavelet basis function, and set a learning speed of the wavelet neural network model
  • the predicted output is performed. Or, if the analysis reaches the preset number of times, the predicted output is performed; and the correction module is used to make the error larger than 0.0001 and the number of trainings does not reach the preset value, the scaling factor in the wavelet basis function, the translation factor and the connection weight of the wavelet neural network are modified so that the error between the predicted output value of the wavelet neural network model and the expected output value is less than Is equal to 0.0001.
  • the wavelet neural network model established by the modeling module of the display state adjustment device is generated by using a wavelet basis function.
  • the analysis unit in this embodiment is further configured to analyze the number of acquisitions of the collection unit, and update the wavelet neural network model every time the information parameters of the environment in which the display is located are collected 100 times. .
  • i is the i-th node of the input layer
  • j is the j-th node of the hidden layer
  • ⁇ ij is the connection weight between the i-th node of the input layer and the j-th node of the hidden layer
  • h j is a wavelet basis function
  • b j is a translation factor of the wavelet basis function h j
  • a j is a scaling factor of the wavelet basis function h j
  • n is a positive integer.
  • ⁇ jk is the connection weight between the jth node of the hidden layer and the kth node of the output layer.
  • the information parameters of the environment in which the gravity acceleration sensor, the light sensor, the temperature sensor, the positioning module, and the electronic compass are detected are integrated and analyzed by the wavelet neural network, and according to the analysis result. Adjusting the display state of the display, achieving higher recognition accuracy than a traditional single-function sensor (for example, a light sensor) And the scope of application.
  • the embodiment provides a display including the display state adjusting device described in Embodiment 3.
  • the display of this embodiment is preferably a display of a mobile device (e.g., a mobile phone), or may be another display.
  • the display also includes other known components.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computer Hardware Design (AREA)
  • Human Computer Interaction (AREA)
  • User Interface Of Digital Computer (AREA)
  • Controls And Circuits For Display Device (AREA)

Abstract

一种显示状态的调节方法、显示状态调节装置及显示装置。显示状态的调节方法包括：采集显示器所处环境的信息参数；将所采集的信息参数输入至预先建立的小波神经网络模型中进行分析，得出显示器将要进行显示的显示状态；以及根据分析结果调整显示器的显示状态。显示状态的调节方法可解决现有的显示器的显示状态调整方法单一且精确度低的问题。

Description

显示状态的调节方法、显示状态调节装置及显示装置 技术领域
本发明属于显示技术领域，具体涉及显示状态的调节方法、显示状态调节装置及显示装置。
背景技术
显示装置最终展现在用户面前的是屏幕的输出、外形的设计以及产品的性能。适宜的亮度和分辨率可以提高用户的体验。
用户在不同的使用场景下对屏幕的显示状态有着不同的需求，例如，在明亮环境光条件下，需要将显示装置的屏幕亮度调高以满足观看的需求；在昏暗环境光条件下，需要将显示装置的屏幕的亮度调低，从而保持合适的亮度，以避免对眼睛的损害。
以手机为例，目前通用的手机屏幕显示状态的调整方法包括：
1)通过手机内建的光线传感器检测环境光亮度，从而根据检测到的环境光亮度自动调节手机屏幕的亮度；2)通过手机系统的个性化设置功能，人工调节手机屏幕的亮度、分辨率和刷新率等，例如，通过调整设置菜单中的各相应参数来调节屏幕的亮度、分辨率和刷新率等。
发明人发现现有技术中至少存在如下问题：当通过方法1)对手机屏幕进行调整时，只能够调节手机屏幕的亮度，功能单一；而当通过方法2)对手机屏幕进行调整时，虽然可设置参数相对较多，但是需要对各参数执行人工设置，因此耗费精力且精确度较低。
发明内容
针对现有的显示器屏幕的调节方法存在的上述问题，本发明实施例提供显示状态的调节方法、显示状态调节装置及显示装置，其能够更加智能且便捷地对显示状态进行调节，并且精确度高，适用性强。
根据本发明的实施例，提供了一种显示状态的调节方法，包括：采集显示器所处环境的信息参数；将所采集的信息参数输入至预先建立的小波神经网络模型中进行分析，得出显示器将要进行显示的显示状态；以及根据分析结果调整显示器的显示状态。
优选的是，所述信息参数包括：重力加速度参数、光线参数、位置参数、温度参数、角度参数中的至少一种。
优选的是，所述显示状态的调整对象包括：亮度、待机、分辨率、刷新率中的至少一种。
优选的是，每采集100次显示器所处环境的信息参数，更新一次小波神经网络模型。
优选的是，所述小波神经网络模型采用小波基函数生成。
进一步优选的是，所述小波神经网络模型包括输入层、隐含层和输出层；其中，向输入层输入的信息参数为Xi，i＝1、2、3……k，k为正整数；所述隐含层的输出为hn(j)，
Figure PCTCN2016071713-appb-000001
式中，i为输入层的第i个节点，j为隐含层的第j个节点；ωij为输入层的第i个节点和隐含层的第j个节点之间的连接权值；hj为小波基函数；bj为小波基函数hj的平移因子；aj为小波基函数hj的伸缩因子；n为正整数。
进一步优选的是，所述输出层的值为yn(k)，
Figure PCTCN2016071713-appb-000002
式中，ωjk为隐含层第j个节点到输出层第k个节点之间的连接权值。
优选的是，在采集显示所处环境的信息参数之前还包括：建立小波神经网络模型的步骤；对建立的小波神经网络模型进行训练的步骤；以及对小波神经网络模型进行测试的步骤。
优选的是，所述小波神经网络模型采用小波基函数生成，其 中，对小波神经网络模型进行训练的步骤包括：对小波神经网络模型进行初始化的步骤，其中，随机初始化小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值，并设置小波神经网络模型的学习速度；对样本进行分类的步骤，用于将样本分为训练样本和测试样本，其中，训练样本用于训练小波神经网络模型，而测试样本用于测试小波神经网络模型的测试精度；计算分析步骤，用于将训练样本输入至小波神经网络模型中，计算小波神经网络模型的预测输出值，以及计算小波神经网络模型的预测输出值与期望输出值的误差，并分析得到训练次数，若误差小于等于0.0001则进行预测输出步骤，或者分析得到训练次数达到预设值则进行预测输出步骤，否则进行以下步骤：修正步骤，用于对小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值进行修正，以使小波神经网络模型的预测输出值与期望输出值的误差小于等于0.0001；以及预测输出步骤，对预测输出值进行输出。
根据本发明的另一实施例，提供了一种显示状态调节装置，包括：采集单元，用于采集显示器所处环境的信息参数；分析单元，用于将所采集的信息参数输入至预先建立的小波神经网络模型中进行分析，得出显示器将要进行显示的显示状态；以及调整单元，用于根据分析结果调整显示器的显示状态。
优选的是，所述采集单元包括：重力加速度传感器、光线传感器、温度传感器、定位模块、电子罗盘中的至少一种。
优选的是，所述显示状态的调整对象包括：亮度、待机、分辨率、刷新率中的至少一种。
优选的是，所述显示状态调节装置还包括：建模单元，用于建立小波神经网络模型；训练单元，用于对建立的小波神经网络模型进行训练；以及测试单元，用于对小波神经网络模型进行测试。
进一步优选的是，所述训练单元包括：初始化模块，用于随机初始化小波基函数中的伸缩因子、平移因子以及小波神经网络 的连接权值，并设置小波神经网络模型的学习速度；样本分类模块，用于把样本分为训练样本和测试样本，其中，训练样本用于训练小波神经网络模型，而测试样本用于测试小波神经网络模型的测试精度；以及计算分析模块，用于把训练样本输入至小波神经网络模型中，计算小波神经网络模型的预测输出值，以及计算小波神经网络模型的预测输出值与期望输出值之间的误差，并分析得到训练次数，若误差小于等于0.0001则进行预测输出，或者分析得到训练次数达到预设值则进行预测输出；以及修正模块，用于在误差大于0.0001且训练次数未达到预设值时，对小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值进行修正，以使小波神经网络模型的预测输出值与期望输出值的误差小于等于0.0001。
优选的是，所述分析单元还用于分析所述采集单元的采集次数，且每采集100次显示器所处环境的信息参数，更新一次小波神经网络模型。
优选的是，所述小波神经网络模型采用小波基函数生成。
进一步优选的是，所述小波神经网络模型包括输入层、隐含层和输出层；向输入层输入的信息参数为Xi，i＝1、2、3……k，k为正整数；所述隐含层的输出为hn(j)，
Figure PCTCN2016071713-appb-000003
式中，i为输入层的第i个节点，j为隐含层的第j个节点；ωij为输入层的第i个节点和隐含层的第j个节点之间的连接权值；hj为小波基函数；bj为小波基函数hj的平移因子；aj为小波基函数hj的伸缩因子；n为正整数。
进一步优选的是，所述输出层的值为yn(k)，
Figure PCTCN2016071713-appb-000004
式中，ωjk为隐含层第j个节点到输出层第k个节点之间的连接权 值。
根据本发明的另一实施例，提供了一种显示器，包括上述的显示状态调节装置。
根据本发明实施例提供的显示状态的调节方法，通过小波神经网络对所采集的显示器(或者用户)所处环境的信息参数进行分析，得到显示器所处环境的信息，该信息对应于显示器的一种显示状态，从而根据该信息对显示器的显示状态进行调整。该调节方法非常智能，且适用性强。
根据本发明实施例提供的显示状态调节装置，通过小波神经网络将重力加速度传感器、光线传感器、温度传感器、定位模块、电子罗盘所检测的显示器所处环境的信息参数进行融合分析并根据分析结果来对显示器的显示状态进行调整，相对传统的单一单功能传感器(例如，光线传感器)而言，获得了更高的识别精度和更广的应用范围。
本发明实施例提供显示器包括上述显示状态调节装置，与不提供该构造的情况相比，获得了更高的识别精度和更广的应用范围。
附图说明
图1为本发明的实施例1的显示状态的调节方法的流程图。
图2为本发明的实施例2的显示状态的调节方法中智能算法建模的流程图。
图3为本发明的实施例2的小波神经网络模型的示意图。
图4为本发明的实施例2的显示状态的调节方法中对小波神经网络模型进行训练的流程图。
图5为本发明的实施例3的显示状态调节装置的示意图。
图6为本发明的实施例3的显示状态调节装置的另一示意图。
图7为本发明的实施例3的显示状态调节装置中训练单元的示意图。
具体实施方式
为使本领域技术人员更好地理解本发明的技术方案，下面结合附图和具体实施方式对本发明作进一步详细描述。
[实施例1]
本实施例提供一种显示状态的调节方法，用于调整显示器(例如，手机的显示屏幕)的显示状态，例如，对亮度、分辨率、刷新率等进行调整。图1为本实施例的显示状态的调节方法的流程图。如图1所示，该调节方法包括：采集显示器所处环境的信息参数；将所采集的信息参数输入至预先建立的小波神经网络模型中，分析得出显示器将要进行显示的显示状态；以及根据分析结果调整显示器的显示状态。
在本实施例中，通过小波神经网络对所采集的显示器(或者用户)所处环境的信息参数进行分析，得到显示器所处环境的信息，该信息对应于显示器的一种显示状态，从而根据该信息对显示器的显示状态进行调整。该调节方法非常智能，且适用性强，其具体实现方法结合下述实施例进行详细说明。
[实施例2]
本实施例提供一种显示状态的调节方法。下面结合图1-图4对本实施例提供的显示状态的调节方法进行详细说明。所述方法具体包括如下步骤S1至S4。
在步骤S1，对智能算法进行建模。
图2为智能算法建模的流程图。如图2所示，智能算法建模的流程具体包括如下步骤S101至S103。
在步骤S101，建立小波神经网络模型，该小波神经网络模型是采用小波基函数生成的。其中，小波基函数的数学公式为：
Figure PCTCN2016071713-appb-000005
图3为本实施例的小波神经网络模型的示意图。如图3所示， 小波神经网络模型包括输入层、隐含层和输出层。当向输入层输入的信息参数为Xi(i＝1、2、3……k；k为正整数)时，所述隐含层的输出为hn(j)，
Figure PCTCN2016071713-appb-000006
式中，i为输入层的第i个节点，j为隐含层的第j个节点；ωij为输入层的第i个节点和隐含层的第j个节点之间的连接权值；hj为小波基函数；bj为小波基函数hj的平移因子；aj为小波基函数hj的伸缩因子；n为正整数。
所述输出层的值为yn(k)，
Figure PCTCN2016071713-appb-000007
式中，ωjk为隐含层第j个节点到输出层第k个节点之间的连接权值。在此需要说明的是，每采集多次显示器所处环境的信息参数之后，都会更新一次小神经网络模型，其中hn(j)表示小波神经网络模型更新n次后的隐含层第j个节点的输出，hn-1(j)则表示在小波神经网络模型更新n-1次后的隐含层第j个节点的输出。
接下来，返回参考图2，在完成小波神经网络模型的建立之后，在步骤S102，对该小波神经网络模型进行训练。
图4为本实施例中对小波神经网络模型进行训练的流程图。如图4所示，对小波神经网络模型进行训练的流程具体包括如下步骤S1021至S1025。
在步骤S1021中，对小波神经网络模型进行初始化，具体地，随机初始化小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值，并设置小波神经网络模型的学习速度；学习速度通常为0.1。
在步骤S1022中，对样本进行分类，具体地，将样本分为训练样本和测试样本，其中，训练样本用于训练小波神经网络模型，而测试样本用于测试小波神经网络模型的测试精度。
在步骤S1023中，进行计算和分析，具体地，将训练样本输入至小波神经网络模型中，计算小波神经网络模型的预测输出值，以及计算小波神经网络模型的预测输出值与期望输出值之间的误差，并分析得到训练次数。若误差小于等于0.0001则进行预测输出步骤S1025，或者分析得到训练次数达到预设值则进行预测输出步骤S1025，否则进行以下步骤S1024。
在步骤S1024中，对因子和权值进行修正，具体地，对小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值进行修正，以使小波神经网络模型的预测输出值与期望输出值的误差小于等于0.0001。
在步骤S1025中，输出预测输出值。至此，完成小波神经网络模型的训练。
接下来，返回参考图2，在完成小波神经网络模型的训练之后，在步骤S103，对小波神经网络模型进行测试。
在该步骤中，将步骤S102中通过训练获得的小波神经网络模型应用至显示器显示状态的调节当中，利用所采集的环境信息参数对小波神经网络模型进行测试，以获得期望的小波神经网络模型。至此，智能算法(即，小波神经网络)建模的流程完成。
附带提及，在本实施例中，为了提高对所处环境分析的精确度，例如，每采集100次显示器所处环境的信息参数，更新一次小波神经网络模型。
接下来，在完成智能算法的建模之后，在步骤S2，采集显示器所处环境的信息参数。
在该步骤中，具体地，所采集的信息参数可以包括重力加速度参数、光线参数、位置参数、温度参数、角度参数中的至少一种。例如，采集多种信息参数，以使下一步骤的分析更加准确。
在此，需要说明的是，在本实施例中无论采集的环境信息参数为电流还是电压信号，因为传到显示器都是数字信号，这些数字信号可以作为小波神经网络模型的训练输入。小波神经网络模型的训练在小波神经网络技术领域是已知的，这里不再详细讨论。 此外，通过获得样本数据，可以得到小波神经网络的参数权值。
接下来，在完成步骤S2之后，在步骤S3，将所采集的信息参数输入至步骤S1所建立的小波神经网络模型中进行分析，得出显示器将要进行显示的显示状态。
在该步骤中，具体的以判断夜间使用手机(显示器)的用户已经睡着为例进行说明。
当采集到的光线参数为亮度较低，位置参数(例如，GPS坐标)为用户的家中，角度参数为90°，重力加速度参数为例如2分钟未发生变化时，通过小波神经网络模型对这些参数进行分析，得出用户状态为睡眠状态，由此，得出手机将要显示的显示状态为与用户睡眠状态对应的待机状态。
接下来，在步骤S4，根据上述的分析结果调整显示器的显示状态，以使显示状态满足用户的需要。例如，在分析得出将要进行显示的显示状态应该为待机状态时，使显示器待机。
上述显示状态的调整对象可以包括亮度、待机、分辨率、刷新率中的至少一种。
本实施例所提供的显示状态的调整方法，将重力加速度参数、光线参数、位置参数、温度参数、角度参数中的至少一种，最好为多种，通过小波神经网络对这些参数进行融合分析并根据分析结果来对显示器的显示状态进行调整，使得对显示状态的调整更加准确，而且该方法较现有技术而言更加智能，适用性强。同时，该种方法可以获得更高的容错性，相对传统的阈值设定方式，可以更加准确。
[实施例3]
本实施例提供一种显示状态调节装置，图5为该显示状态调节装置的示意图。如图5所示，该显示状态调节装置可以包括：采集单元，用于采集显示器所处环境的信息参数；分析单元，用于将所采集的信息参数输入至预先建立的小波神经网络模型中进行分析，得出显示器将要进行显示的显示状态；以及调整单元， 用于根据分析结果调整显示器的显示状态。
根据本实施例的显示状态调节装置，分析单元通过小波神经网络对采集单元所采集的显示器(或者用户)所处环境的信息参数进行分析，得到显示器所处环境的信息，该信息对应显示器的一种显示状态，从而根据该信息通过调整单元对显示器的显示状态进行调整。该调节装置非常智能，且适用性强。
例如，上述采集单元可以包括：重力加速度传感器、光线传感器、温度传感器、定位模块、电子罗盘中的至少一种。重力加速度传感器用于检测显示器的运动信息参数；光线传感器用于检测显示器所处环境中光线的亮度信息参数；温度传感器用于检测显示器所处环境的温度信息参数；定位模块(例如，GPS)用于检测显示器所处环境的位置参数(室内/室外)；电子罗盘用于检测显示器的倾角参数。
例如，上述显示状态的调整对象可以包括：亮度、待机、分辨率、刷新率中的至少一种。
图6为本实施例的显示状态调节装置的另一示意图。如图6所示，本实施例的显示状态调节装置还可以包括：建模单元，用于建立小波神经网络模型；训练单元，用于对小波神经网络模型进行训练；以及测试单元，用于对小波神经网络模型进行测试。
图7为本实施例的显示状态调节装置中训练单元的示意图。如图7所示，训练单元可以包括：初始化模块，用于随机初始化小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值，并设置小波神经网络模型的学习速度；样本分类模块，用于将样本分为训练样本和测试样本，其中，训练样本用于训练小波神经网络模型，而测试样本用于测试小波神经网络模型的测试精度；计算分析模块，用于将训练样本输入至小波神经网络模型中，计算小波神经网络模型的预测输出值，以及计算小波神经网络模型的预测输出值与期望输出值之间的误差，并分析得到训练次数，若误差小于等于0.0001则进行预测输出，或者分析得到训练次数达到预设值则进行预测输出；以及修正模块，用于在误差大于 0.0001且训练次数未达到预设值时，对小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值进行修正，以使小波神经网络模型的预测输出值与期望输出值的误差小于等于0.0001。
本实施例中，显示状态调节装置的建模模块所建立的小波神经网络模型是采用小波基函数生成的。
为了使得更加准确的调整显示器屏幕的显示状态，本实施例中的分析单元还用于分析所述采集单元的采集次数，且每采集100次显示器所处环境的信息参数，更新一次小波神经网络模型。
具体的，小波神经网络模型包括输入层、隐含层和输出层；当向输入层输入的信息参数为Xi(i＝1、2、3……k，k为正整数)时，所述隐含层的输出为hn(j)，
Figure PCTCN2016071713-appb-000008
式中，i为输入层的第i个节点，j为隐含层的第j个节点；ωij为输入层的第i个节点和隐含层的第j个节点之间的连接权值；hj为小波基函数；bj为小波基函数hj的平移因子；aj为小波基函数hj的伸缩因子；n为正整数。
其中，所述输出层的值为yn(k)，
Figure PCTCN2016071713-appb-000009
式中，ωjk为隐含层第j个节点到输出层第k个节点之间的连接权值。
根据本实施例所提供的显示状态调节装置，通过小波神经网络将重力加速度传感器、光线传感器、温度传感器、定位模块、电子罗盘所检测的显示器所处环境的信息参数进行融合分析并根据分析结果来对显示器的显示状态进行调整，相对传统的单一单功能传感器(例如，光线传感器)而言，获得了更高的识别精度 和应用范围。
[实施例4]
本实施例提供一种显示器，包括实施例3中所述的显示状态调节装置。
本实施例的显示器优选为移动装置(例如，手机)的显示器，也可以是其它显示器。该显示器还包括其它已知的元件。
可以理解的是，以上实施方式仅仅是为了说明本发明的原理而采用的示例性实施方式，然而本发明并不局限于此。对于本领域内的普通技术人员而言，在不脱离本发明的精神和实质的情况下，可以做出各种变型和改进，这些变型和改进也视为本发明的保护范围。

Claims (19)

  1. 一种显示状态的调节方法，包括：
    采集显示器所处环境的信息参数；
    将所采集的信息参数输入至预先建立的小波神经网络模型中进行分析，得出显示器将要进行显示的显示状态；以及
    根据分析结果调整显示器的显示状态。
  2. 根据权利要求1所述的显示状态的调节方法，其中，所述信息参数包括：重力加速度参数、光线参数、位置参数、温度参数、角度参数中的至少一种。
  3. 根据权利要求1所述的显示状态的调节方法，其中，所述显示状态的调整对象包括：亮度、待机、分辨率、刷新率中的至少一种。
  4. 根据权利要求1所述的显示状态的调节方法，其中，每采集100次所述信息参数，更新一次小波神经网络模型。
  5. 根据权利要求1所述的显示状态的调节方法，其中，所述小波神经网络模型采用小波基函数生成。
  6. 根据权利要求5所述的显示状态的调节方法，其中，所述小波神经网络模型包括输入层、隐含层和输出层，其中
    向所述输入层输入的信息参数为Xi，i＝1、2、3……k，k为正整数；
    所述隐含层的输出为hn(j)，
    Figure PCTCN2016071713-appb-100001
    式中，i为所 述输入层的第i个节点，j为所述隐含层的第j个节点；ωij为所述输入层的第i个节点和所述隐含层的第j个节点之间的连接权值；hj为小波基函数；bj为小波基函数hj的平移因子；aj为小波基函数hj的伸缩因子；n为正整数。
  7. 根据权利要求6所述的显示状态的调节方法，其中，所述输出层的值为yn(k)，
    Figure PCTCN2016071713-appb-100002
    式中，ωjk为所述隐含层第j个节点到所述输出层第k个节点之间的连接权值。
  8. 根据权利要求1-7中任一项所述的显示状态的调节方法，其中，在采集显示所处环境的信息参数之前还包括：
    建立小波神经网络模型的步骤；
    对建立的小波神经网络模型进行训练的步骤；以及
    对小波神经网络模型进行测试的步骤。
  9. 根据权利要求8所述的显示状态的调节方法，其中，所述小波神经网络模型采用小波基函数生成，并且其中，对小波神经网络模型进行训练的步骤包括：
    对小波神经网络模型进行初始化的步骤，其中，随机初始化小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值，并设置小波神经网络模型的学习速度；
    对样本进行分类的步骤，用于将样本分为训练样本和测试样本，其中，训练样本用于训练小波神经网络模型，而测试样本用于测试小波神经网络模型的测试精度；
    计算分析步骤，用于将训练样本输入至小波神经网络模型中，计算小波神经网络模型的预测输出值，以及计算小波神经网络模型的预测输出值与期望输出值的误差，并分析得到训练次数，若误差小于等于0.0001则进行预测输出步骤，或者分析得到训练次 数达到预设值则进行预测输出步骤，否则进行以下步骤：
    修正步骤，用于对小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值进行修正，以使小波神经网络模型的预测输出值与期望输出值的误差小于等于0.0001；以及
    预测输出步骤，对预测输出值进行输出。
  10. 一种显示状态调节装置，包括：
    采集单元，用于采集显示器所处环境的信息参数；
    分析单元，用于将所采集的信息参数输入至预先建立的小波神经网络模型中进行分析，得出显示器将要进行显示的显示状态；以及
    调整单元，用于根据分析结果调整显示器的显示状态。
  11. 根据权利要求10所述的显示状态调节装置，其中，所述采集单元包括：重力加速度传感器、光线传感器、温度传感器、定位模块、电子罗盘中的至少一种。
  12. 根据权利要求10所述的显示状态调节装置，其中，所述显示状态的调整对象包括：亮度、待机、分辨率、刷新率中的至少一种。
  13. 根据权利要求10所述的显示状态调节装置，还包括：
    建模单元，用于建立小波神经网络模型；
    训练单元，用于对建立的小波神经网络模型进行训练；以及
    测试单元，用于对小波神经网络模型进行测试。
  14. 根据权利要求13所述的显示状态调节装置，其中，所述训练单元包括：
    初始化模块，用于随机初始化小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值，并设置小波神经网络模型 的学习速度；
    样本分类模块，用于把样本分为训练样本和测试样本，其中，训练样本用于训练小波神经网络模型，而测试样本用于测试小波神经网络模型的测试精度；
    计算分析模块，用于把训练样本输入至小波神经网络模型中，计算小波神经网络模型的预测输出，以及计算小波神经网络模型的预测输出值与期望输出值之间的误差，并分析得到训练次数，若误差小于等于0.0001则进行预测输出，或者分析得到训练次数达到预设值则进行预测输出；以及
    修正模块，用于在误差大于0.0001且训练次数未达到预设值时，对小波基函数中的伸缩因子、平移因子以及小波神经网络的连接权值进行修正，以使小波神经网络模型的预测输出值与期望输出值的误差小于等于0.0001。
  15. 根据权利要求10所述的显示状态调节装置，其中，所述分析单元还用于分析所述采集单元的采集次数，且每采集100次显示器所处环境的信息参数，更新一次小波神经网络模型。
  16. 根据权利要求10所述的显示状态调节装置，其中，所述小波神经网络模型采用小波基函数生成。
  17. 根据权利要求16所述的显示状态调节装置，其中，所述小波神经网络模型包括输入层、隐含层和输出层，其中，
    向所述输入层输入的信息参数为Xi，i＝1、2、3……k，k为正整数；
    所述隐含层的输出为hn(j)，
    Figure PCTCN2016071713-appb-100003
    式中，i为所述输入层的第i个节点，j为所述隐含层的第j个节点；ωij为所述 输入层的第i个节点和所述隐含层的第j个节点之间的连接权值；hj为小波基函数；bj为小波基函数hj的平移因子；aj为小波基函数hj的伸缩因子；n为正整数。
  18. 根据权利要求17所述的显示状态调节装置，其中，所述输出层的值为yn(k)，
    Figure PCTCN2016071713-appb-100004
    式中，ωjk为所述隐含层第j个节点到所述输出层第k个节点之间的连接权值。
  19. 一种显示器，包括权利要求10-18中任一项所述的显示状态调节装置。
PCT/CN2016/071713 2015-07-17 2016-01-22 显示状态的调节方法、显示状态调节装置及显示装置 WO2017012321A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/107,384 US10565955B2 (en) 2015-07-17 2016-01-22 Display status adjustment method, display status adjustment device and display device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510425488.7 2015-07-17
CN201510425488.7A CN104978947B (zh) 2015-07-17 2015-07-17 显示状态的调节方法、显示状态调节装置及显示装置

Publications (1)

Publication Number Publication Date
WO2017012321A1 true WO2017012321A1 (zh) 2017-01-26

Family

ID=54275407

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/071713 WO2017012321A1 (zh) 2015-07-17 2016-01-22 显示状态的调节方法、显示状态调节装置及显示装置

Country Status (3)

Country Link
US (1) US10565955B2 (zh)
CN (1) CN104978947B (zh)
WO (1) WO2017012321A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019117942A1 (en) * 2017-12-15 2019-06-20 Google Llc Adaptive display brightness adjustment
CN114333736A (zh) * 2021-12-29 2022-04-12 深圳市华星光电半导体显示技术有限公司 显示装置和显示装置的亮度调节方法

Families Citing this family (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104978947B (zh) 2015-07-17 2018-06-05 京东方科技集团股份有限公司 显示状态的调节方法、显示状态调节装置及显示装置
CN105869580B (zh) * 2016-06-15 2018-05-22 京东方科技集团股份有限公司 色温调节方法及装置、背光源、显示设备
US10733946B2 (en) 2016-08-26 2020-08-04 Semiconductor Energy Laboratory Co., Ltd. Display device and electronic device
CN106528024A (zh) * 2016-11-20 2017-03-22 滁州职业技术学院 一种显示屏分辨率调整的方法及显示终端
CN106951054B (zh) * 2017-03-10 2020-03-10 Oppo广东移动通信有限公司 一种应用程序的控制方法、装置及移动终端
CN108154853A (zh) * 2017-11-27 2018-06-12 国网北京市电力公司 硅基液晶显示设备的控制方法
CN107835324B (zh) * 2017-12-13 2021-05-25 维沃移动通信有限公司 一种背光亮度调节方法及移动终端
US10445401B2 (en) * 2018-02-08 2019-10-15 Deep Labs Inc. Systems and methods for converting discrete wavelets to tensor fields and using neural networks to process tensor fields
US10692467B2 (en) 2018-05-04 2020-06-23 Microsoft Technology Licensing, Llc Automatic application of mapping functions to video signals based on inferred parameters
CN110188886B (zh) * 2018-08-17 2021-08-20 第四范式（北京）技术有限公司 对机器学习过程的数据处理步骤进行可视化的方法和系统
CN109147715A (zh) * 2018-08-28 2019-01-04 武汉华星光电技术有限公司 用于降低显示面板功耗的方法及低功耗的显示装置
CN109471803B (zh) * 2018-11-05 2021-10-01 湖南工学院 基于人因可靠性的复杂工业系统数字化人机界面画面配置方法
CN110598488B (zh) * 2019-09-17 2022-12-27 山东大学 半导体单元器件、半导体芯片系统及puf信息处理系统
CN111341286B (zh) * 2020-02-25 2022-06-10 惠州Tcl移动通信有限公司 屏幕显示控制方法、装置、存储介质及终端
CN111460617B (zh) * 2020-03-03 2022-10-14 华中科技大学 一种基于神经网络的igbt结温预测方法
US11637920B2 (en) 2020-07-27 2023-04-25 Samsung Electronics Co., Ltd. Providing situational device settings for consumer electronics and discovering user-preferred device settings for consumer electronics
CN112530352B (zh) * 2020-12-24 2023-07-25 武汉天马微电子有限公司 一种显示装置的驱动方法及驱动装置
CN114974056A (zh) * 2021-02-24 2022-08-30 广州三星通信技术研究有限公司 屏幕刷新率的调整方法及其装置
CN113947008B (zh) * 2021-08-30 2023-08-15 西安电子科技大学 一种基于bp神经网络模型的半导体器件温度分布预测方法
GB2611817A (en) * 2021-10-18 2023-04-19 Samsung Electronics Co Ltd Mobile device and method
CN115051864B (zh) * 2022-06-21 2024-02-27 郑州轻工业大学 基于pca-mf-wnn的网络安全态势要素提取方法及系统
CN115083337B (zh) * 2022-07-08 2023-05-16 深圳市安信泰科技有限公司 一种led显示驱动系统及方法
CN115984889B (zh) * 2023-03-22 2023-06-09 中国人民解放军总医院 基于人工智能的医疗文书完整性分析方法及系统
CN116363997B (zh) * 2023-03-29 2024-08-13 江苏磐鼎科技有限公司 一种基于深度学习的led显示屏配色及节能方法

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101521973A (zh) * 2009-03-19 2009-09-02 浙江大学 舞台彩幕亮度的自适应控制系统和方法
CN102122133A (zh) * 2011-01-21 2011-07-13 北京工业大学 自适应小波神经网络异常检测故障诊断分类系统及方法
CN102663976A (zh) * 2010-11-15 2012-09-12 伊格尼斯创新公司 用于发光器件显示器中的不均匀性的补偿的系统和方法
US20130124847A1 (en) * 2011-11-15 2013-05-16 International Business Machines Corporation External evironment sensitive predictive application and memory initiation
CN103707769A (zh) * 2014-01-02 2014-04-09 上海理工大学 透明车载数字式仪表控制器及其显示亮度控制方法
CN104036474A (zh) * 2014-06-12 2014-09-10 厦门美图之家科技有限公司 一种图像亮度和对比度的自动调节方法
CN104094287A (zh) * 2011-12-21 2014-10-08 诺基亚公司 用于情境识别的方法、装置以及计算机软件
CN104320881A (zh) * 2014-10-28 2015-01-28 江苏天语雅思医疗设备有限公司 一种led无影灯照明系统中的智能调光控制器
CN104978947A (zh) * 2015-07-17 2015-10-14 京东方科技集团股份有限公司 显示状态的调节方法、显示状态调节装置及显示装置
US20150313529A1 (en) * 2014-05-01 2015-11-05 Ramot At Tel-Aviv University Ltd. Method and system for behavioral monitoring

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5760760A (en) * 1995-07-17 1998-06-02 Dell Usa, L.P. Intelligent LCD brightness control system
US6550320B1 (en) * 2000-05-31 2003-04-22 Continental Ag System and method for predicting tire forces using tire deformation sensors
US7389432B2 (en) * 2004-11-10 2008-06-17 Microsoft Corporation Advanced power management for computer displays
CN101404150B (zh) * 2008-11-14 2011-03-09 深圳市凯立德欣软件技术有限公司 亮度调整装置及亮度调整方法和导航装置及导航方法
CN201409246Y (zh) * 2009-03-19 2010-02-17 杭州剧院 一种舞台彩幕亮度的自适应控制系统
WO2011103377A1 (en) * 2010-02-22 2011-08-25 Dolby Laboratories Licensing Corporation System and method for adjusting display based on detected environment
US8370283B2 (en) * 2010-12-15 2013-02-05 Scienergy, Inc. Predicting energy consumption
CN104240674B (zh) * 2013-06-14 2016-10-05 联想(北京)有限公司 一种调节显示单元的方法及一种电子设备
US9379546B2 (en) * 2013-06-07 2016-06-28 The Board Of Trustees Of The University Of Alabama Vector control of grid-connected power electronic converter using artificial neural networks
US9248789B2 (en) * 2014-01-08 2016-02-02 Verizon Patent And Licensing Inc. Method and apparatus for detecting key-on and key-off states using time-to-frequency transforms
US10375344B2 (en) * 2014-10-24 2019-08-06 Dish Ukraine L.L.C. Display device viewing angle compensation
CN104596957A (zh) * 2015-01-12 2015-05-06 西安科技大学 基于可见光近红外光谱技术的土壤铜含量估算方法

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101521973A (zh) * 2009-03-19 2009-09-02 浙江大学 舞台彩幕亮度的自适应控制系统和方法
CN102663976A (zh) * 2010-11-15 2012-09-12 伊格尼斯创新公司 用于发光器件显示器中的不均匀性的补偿的系统和方法
CN102122133A (zh) * 2011-01-21 2011-07-13 北京工业大学 自适应小波神经网络异常检测故障诊断分类系统及方法
US20130124847A1 (en) * 2011-11-15 2013-05-16 International Business Machines Corporation External evironment sensitive predictive application and memory initiation
CN104094287A (zh) * 2011-12-21 2014-10-08 诺基亚公司 用于情境识别的方法、装置以及计算机软件
CN103707769A (zh) * 2014-01-02 2014-04-09 上海理工大学 透明车载数字式仪表控制器及其显示亮度控制方法
US20150313529A1 (en) * 2014-05-01 2015-11-05 Ramot At Tel-Aviv University Ltd. Method and system for behavioral monitoring
CN104036474A (zh) * 2014-06-12 2014-09-10 厦门美图之家科技有限公司 一种图像亮度和对比度的自动调节方法
CN104320881A (zh) * 2014-10-28 2015-01-28 江苏天语雅思医疗设备有限公司 一种led无影灯照明系统中的智能调光控制器
CN104978947A (zh) * 2015-07-17 2015-10-14 京东方科技集团股份有限公司 显示状态的调节方法、显示状态调节装置及显示装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LI, XINWU: "Monitor Color Management Model Based on Wavelet Neural Network", JOURNAL OF DATA ACQUISITION & PROCESSING, vol. 23, no. 4, 31 July 2008 (2008-07-31), pages 441 - 443, ISSN: 1004-9037 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019117942A1 (en) * 2017-12-15 2019-06-20 Google Llc Adaptive display brightness adjustment
US11096259B2 (en) 2017-12-15 2021-08-17 Google Llc Adaptive display brightness adjustment
US11419197B2 (en) 2017-12-15 2022-08-16 Google Llc Adaptive display brightness adjustment
CN114333736A (zh) * 2021-12-29 2022-04-12 深圳市华星光电半导体显示技术有限公司 显示装置和显示装置的亮度调节方法
CN114333736B (zh) * 2021-12-29 2023-06-02 深圳市华星光电半导体显示技术有限公司 显示装置和显示装置的亮度调节方法

Also Published As

Publication number Publication date
CN104978947A (zh) 2015-10-14
CN104978947B (zh) 2018-06-05
US10565955B2 (en) 2020-02-18
US20180197499A1 (en) 2018-07-12

Similar Documents

Publication Publication Date Title
WO2017012321A1 (zh) 显示状态的调节方法、显示状态调节装置及显示装置
US20210042666A1 (en) Localized Learning From A Global Model
KR102173610B1 (ko) 딥 러닝에 기반한 차량번호판 분류 방법, 시스템, 전자장치 및 매체
US10219129B2 (en) Autonomous semantic labeling of physical locations
CN109919251A (zh) 一种基于图像的目标检测方法、模型训练的方法及装置
CN109508671A (zh) 一种基于弱监督学习的视频异常事件检测系统及其方法
CN110826453A (zh) 一种通过提取人体关节点坐标的行为识别方法
CN103747240B (zh) 融合颜色和运动信息的视觉显著性滤波方法
CN110264495A (zh) 一种目标跟踪方法及装置
CN110276235A (zh) 通过感测瞬态事件和连续事件的智能装置的情境感知
Zhou et al. Classroom learning status assessment based on deep learning
WO2015018780A4 (en) Method, device and system for annotated capture of sensor data and crowd modelling of activities
CN110059611A (zh) 一种智能化教室空余座位识别方法
CN110222925A (zh) 绩效量化考核方法、装置及计算机可读存储介质
CN111126220B (zh) 一种视频监控目标实时定位方法
CN112532746A (zh) 一种云边协同感知的方法及系统
WO2020012738A1 (ja) 断熱性能診断装置、断熱性能診断プログラムおよび断熱性能診断方法
CN109684302A (zh) 数据预测方法、装置、设备及计算机可读存储介质
CN114566277B (zh) 一种基于联邦元学习的罕见疾病分类方法
CN117854156B (zh) 一种特征提取模型的训练方法和相关装置
CN104639714A (zh) 手机反应时间的测试方法
CN109086690A (zh) 图像特征提取方法、目标识别方法及对应装置
CN107610224A (zh) 一种基于弱监督与明确闭塞建模的3d汽车对象类表示算法
CN111601418B (zh) 色温调节方法、装置、存储介质和处理器
CN106778558B (zh) 一种基于深度分类网络的面部年龄估计方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16827014

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16827014

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16827014

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 23/08/2018)

122 Ep: pct application non-entry in european phase

Ref document number: 16827014

Country of ref document: EP

Kind code of ref document: A1