16 results about "Predictive display" patented technology

Machine Learning (ML)-based systems and methods are described for predicting cardiovascular disease of users of specific geographic regions. In various aspects, user- specific cardiovascular data of a user may be input into an ML model trained with data of a plurality of cardiovascular risk factors specific to a population of given geographic region. The plurality of cardiovascular risk factors is subdivided into a first training data subset (preselected factors) and a second training data subset (remaining factors). The user-specific cardiovascular data of the user as input into the ML model is data of the user corresponding to the preselected subset of cardiovascular risk factors and the remaining subset of cardiovascular risk factors. The ML model outputs a user-specific cardiovascular prediction of the user. The user-specific cardiovascular prediction comprises a cardiovascular risk score of the user. The cardiovascular prediction is displayed on a graphical user interface (GUI).

According to an embodiment of the disclosure, a display device includes a display unit including a plurality of areas, a driver integrated circuit including a plurality of integrated circuits driving the display unit, and a storage medium configured to store temperature information of the display unit. Each of the temperature information includes data for temperature increment values for each area of the display unit when the driver integrated circuit is driven.

While operating a display device at a predetermined voltage, a fitting function is determined based on respective greyscale images output by the display device. For respective color images output by the display device, respective actual power consumptions of the display device are determined. For the respective color images, respective power consumptions of the display device are predicted based on the fitting function. A best fit line is determined based on the respective actual power consumptions and the respective predicted power consumptions. While outputting an image via the display device, a total power consumption of the display device is predicted based on the best fit line and the fitting function.

A camera located behind a partially transparent display allows for a participant in a video conference to appear to be looking directly at other participants, creating a natural eye-to-eye setting similar to an in-person meeting. However, the camera picks up moiré patterns and other distortion from the display. A machine learning model is trained to predict the interference from a frame of video on the display. The predicted interference is then subtracted from a corresponding video frame from the camera, resulting in a clean image. The clean image is then used in place of the camera's video frame in output video, resulting in high quality video useful for a video conference.

To realize a demand forecasting display device that can provide users with information to make more accurate product demand forecasts. [Solution] The demand forecasting display device comprises: a consumption forecasting unit that uses purchase data showing the actual purchase history of the product by consumers to forecast consumer demand for the product for each unit period during the forecast period; a wholesale shipment forecasting unit that uses wholesale shipment data showing the actual shipment history of the product by wholesalers to forecast wholesale shipment demand for each unit period during the forecast period; a manufacturer shipment forecasting unit that uses manufacturer shipment data showing the actual shipment history of the product by manufacturers to forecast manufacturer shipment demand for each unit period during the forecast period; and a display control unit that displays the forecast results for consumer demand, the forecast results for wholesale shipment demand, and the forecast results for manufacturer shipment demand on a common time axis.

The invention provides a test method and a substrate, and the method comprises the steps: providing a first substrate which is provided with a first pixel circuit comprising a transistor; an input signal is provided for the first pixel circuit, the current of a target branch in the first pixel circuit is tested, and the target branch comprises two power supplies providing different voltage values; and determining whether the first pixel circuit is qualified or not according to the current. According to the scheme provided by the invention, the low-gray-scale brightness uniformity condition of the display panel can be predicted in advance, so that the development cost can be reduced.

The application discloses a charging pile platform, which comprises a multi-region power consumption load data acquisition module, a regional power consumption peak period grading dynamic monitoring module, a multi-period regional charging pile operation data correlation module, a charging pile intelligent execution control module, a charging pile user interaction prediction display module and a central processing server, aims to be divided into multiple independent monitoring regions according to a charging pile group power distribution structure, to realize real-time sensing of power consumption loads in different regions in a cell, to analyze the real-time load state of each region, to take intervention measures before a transformer overload, to intelligently determine the working mode of the charging piles in the region, to dynamically regulate the operation state and the rate of the charging piles in different regions, to avoid the situation that some charging piles are idle and some charging piles are overloaded, and to realize spatial balance of charging resources and power resources in the cell.

The application discloses a compaction equipment with edge pressing function and an operation method. It relates to the technical field of compaction machinery and comprises a rack, a steel wheel, a damping assembly and a compaction detection device. The rack comprises a horizontal support, a vertical support and a semicircular support. A driving assembly is arranged on the horizontal support, and a shock absorber is arranged between the driving assembly and the horizontal support. The inner ring of the semicircular support is provided with a groove. The right end of the steel wheel is connected with the driving assembly, and the left end of the steel wheel is rotatably arranged in the semicircular support. The left end of the steel wheel extends out of the semicircular support and beyond the left end of the vehicle body. The damping assembly is arranged in the groove and in contact with the steel wheel. The compaction detection device comprises an image acquisition camera, an image data processor and a route trajectory prediction display. The left end of the steel wheel extends out of the semicircular support and beyond the left end of the vehicle body, so that the edge pressing of the transition section can be realized. The left and right ends of the steel wheel are damped by the shock absorber and the damping assembly. The compaction detection device can avoid the collision between the compaction equipment and the structure of the transition section.

The invention discloses a white balance correction method, device and equipment and a storage medium, and belongs to the technical field of display, and the method comprises the steps: obtaining the chromaticity coordinate of a first white point displayed by a display system, the chromaticity coordinate being determined by the proportion of the output brightness of red, green and blue channels corresponding to the first white point; predicting a characteristic curve of a red channel, a green channel and a blue channel of the display system, wherein the characteristic curve indicates a mapping relation between the input gray level and the output brightness; based on the color coordinates of the first white point, the target color coordinates and the characteristic curve, first gain values corresponding to the red channel, the green channel and the blue channel respectively are obtained; and adjusting the output brightness of the red, green and blue channels according to the first gain values respectively corresponding to the red, green and blue channels so as to correct the white balance of the display system. The method can improve the white balance correction efficiency.

This invention discloses an energy-saving display method and system for LED displays, relating to the field of energy saving in LED displays. The method includes: acquiring intermediate data of the current display content through a video decoder interface to generate a predicted display content feature vector set for at least one future display frame; constructing a feature and response database based on a clustering algorithm; updating and optimizing the feature and response database based on the content feature vectors of the current display frame acquired in real time; calculating the current compensation coefficient for each pixel area of ​​the display screen based on the temperature drift characteristic curve of the LED device; outputting the optimal driving parameter combination based on a deep reinforcement learning model; generating multi-level control instructions based on the optimal driving parameter combination, and dynamically optimizing and updating the model parameters based on actual results. The advantages of this invention are: effectively achieving significant reduction in LED display power consumption and extending device lifespan while ensuring display quality and temperature balance.

A driving method for a display device and a display device, the driving method including: predicting a grayscale change value of a data line inside a display panel; obtaining an original voltage waveform of a pre-output of a zero-potential reference point to a trace of a glass substrate; generating a compensation voltage waveform of the zero-potential reference point based on the original voltage waveform of the zero-potential reference point, the grayscale change value, and a first grayscale compensation table; synthesizing the original voltage waveform and the compensation voltage waveform of the zero-potential reference point to output to the trace of the glass substrate.

The invention discloses an energy storage charging and discharging monitoring and auxiliary decision-making method and system under multiple time scales, and the method comprises the steps: carrying out the collection and verification of the operation state of an energy storage station group, and forming a chargeable / dischargeable capability surface based on the province-based and whole-network aggregation; a suggested target curve is generated on multiple time scales; when it is predicted that new energy peak regulation blocking occurs in the noon, the system calculates the needed charging power; when a peak segment balance gap is predicted and displayed, the system calculates a discharge strategy; after the strategy is generated, checking the cross-section tidal current and the climbing rate, and reserving the peak electric quantity of the next day in a cross-day scene; and the suggested curve lands according to the hierarchy of whole network-provincial-zoning-station. According to the method, energy storage resources can be arranged in a unified manner in multiple time scales, multi-level landing can be oriented in a master station platform, online rolling check is supported, and new energy consumption, peak section guarantee supply and section safety are considered at the same time.

The invention provides "display device power consumption". When operating the display device at a predetermined voltage, a fitting function is determined based on a corresponding grayscale image output by the display device. A respective actual power consumption of the display device is determined for a respective color image output by the display device. For respective color images, respective power consumption of the display device is predicted based on the fitting function. A best fit line is determined based on the respective actual power consumption and the respective predicted power consumption. When outputting an image via the display device, a total power consumption of the display device is predicted based on the best fit line and the fit function.

While a display device is operated at a predetermined voltage, an adaptation function is determined based on the respective grayscale images output by the display device. For each color image output by the display device, the respective actual power consumption of the display device is determined. For each color image, the respective power consumption of the display device is predicted based on the adaptation function. A regression line is determined based on the respective actual power consumption and the respective predicted power consumption. During the output of an image by the display device, a total power consumption of the display device is predicted based on the regression line and the adaptation function.

The application discloses a nuclear power safety radiation dose rate predictor based on an attention decomposition mechanism, which comprises a database, a host computer and a sensor, and the database, the host computer and the sensor are sequentially connected. The database contains the radiation dose rate data of the nuclear power safety historical monitoring. The host computer comprises a supervised training module, a data prediction module and a prediction display module, the supervised training module uses the nuclear power safety historical monitoring data to train a deep prediction network model and transmits the data into the data prediction module. The sensor acquires the nuclear power safety monitoring data in real time and transmits the data into the data prediction module of the host computer for prediction and estimation, and the prediction result is displayed on the prediction display module of the host computer. The application innovatively uses the attention decomposition mechanism, obtains the seasonal and trend characteristics of the data, better grasps the inherent characteristics and rules of the data, and realizes the nuclear power safety radiation dose rate predictor based on the attention decomposition mechanism with high accuracy and online prediction.