Data display method and device, electronic equipment, storage medium and chip

Abstract

The data display method, device, electronic equipment, storage medium and chip provided by the present disclosure include: obtaining prediction point data corresponding to a target trajectory output by a prediction point prediction model; wherein the prediction point prediction model is used to perform data prediction from at least one of a device direction dimension, a data integrity dimension, a trajectory bending dimension, a trajectory position dimension and a trajectory repetition dimension; filtering the prediction point data according to attribute information of a display screen and a prediction period to obtain target point data; and drawing the target point data along the target trajectory. In the present disclosure, the prediction point prediction model performs prediction point data prediction from the device direction dimension, the data integrity dimension, the trajectory bending dimension, the trajectory position dimension and the trajectory repetition dimension, thereby improving the accuracy of trajectory prediction. In addition, in combination with the screen attribute information, the prediction period and the filtering of the prediction point data are dynamically adjusted, thereby improving the smoothness and continuity of the trajectory and improving the overall hand-following experience.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of data processing, and particularly relates to a data display method and device, electronic equipment, storage medium and chip. BACKGROUND

[0002] With the popularity of intelligent terminal equipment and the development of the field of data processing, users have higher requirements for the quality of terminal data display content. As an important direction in the field of display technology, the touch input processing of the terminal can enhance the display effect by predicting handwriting when the terminal outputs touch content to the user. However, in related technologies, the prediction error of the predicted handwriting is large, the prediction cycle number estimation is inaccurate, and the writing scene adaptation is insufficient, which will cause a large deviation between the predicted trajectory and the real trajectory, resulting in poor hand following performance of writing. SUMMARY

[0003] The present disclosure provides a data display method and device, electronic equipment, storage medium and chip to solve the problems in related technologies, which can improve the accuracy of trajectory prediction, dynamically adjust the prediction cycle number combined with screen attribute information, improve the smoothness and continuity of the trajectory, and improve the overall hand following experience.

[0004] A first aspect embodiment of the present disclosure provides a data display method, which comprises:

[0005] Obtaining predicted point data corresponding to a target trajectory output by a point reporting prediction model; wherein the point reporting prediction model is used for data prediction from at least one of the following dimensions: device direction dimension, data integrity dimension, trajectory bending dimension, trajectory position dimension, and trajectory repetition dimension;

[0006] Filtering the predicted point data according to the attribute information of the display screen and the prediction cycle to obtain target point data;

[0007] Drawing the target point data along the target trajectory.

[0008] In some embodiments of the present disclosure, the obtaining of the predicted point data corresponding to the target trajectory output by the point reporting prediction model comprises:

[0009] First adjusting the direction of the coordinate system of the target trajectory to be consistent with the direction of the coordinate system of the device screen;

[0010] According to the preset sampling interval and the attribute information of the predicted trajectory point, performing interpolation calculation on the predicted trajectory point to obtain first data;

[0011] According to the first trajectory point at the current time and the second trajectory point at the historical time within the preset sampling interval, calculating the curvature of the target trajectory;

[0012] differentially processing the first data to obtain second data;

[0013] filtering the second data to obtain the predicted point data.

[0014] In some embodiments of the present disclosure, the filtering the predicted point data according to the attribute information of the display screen and the prediction period to obtain target point data comprises:

[0015] converting the direction of the coordinate system of the target trajectory and the coordinates of the predicted trajectory point to obtain converted data;

[0016] filtering the converted data according to the attribute information of the display screen and the prediction period to obtain target point data.

[0017] In some embodiments of the present disclosure, the converting the direction of the coordinate system of the target trajectory and the coordinates of the trajectory point to obtain converted data comprises:

[0018] secondly adjusting the direction of the coordinate system of the target trajectory to the direction before the first adjustment, the second adjustment being reverse processing of the first adjustment;

[0019] determining the coordinates corresponding to the target point data according to the nearest visible coordinates of the target trajectory and the coordinates of the predicted trajectory point to obtain the converted data.

[0020] In some embodiments of the present disclosure, the filtering the converted data according to the attribute information of the display screen and the prediction period to obtain target point data comprises:

[0021] calculating a deviation between the attribute information of the predicted trajectory point and the latest point of the target trajectory;

[0022] inputting the deviation into a preset recognition model and outputting the predicted trajectory point that is unavailable in the prediction period;

[0023] filtering the number of the predicted trajectory points according to the attribute information of the display screen to obtain the target point data.

[0024] In some embodiments of the present disclosure, the first adjusting the direction of the coordinate system of the target trajectory to be consistent with the direction of the coordinate system of the device screen comprises:

[0025] judging whether the direction of the coordinate system of the target trajectory is consistent with the direction of the coordinate system of the device screen;

[0026] If not, the direction of the coordinate system of the target trajectory is adjusted according to the direction of the coordinate system of the device screen.

[0027] In some embodiments of the present disclosure, the training method of the report point prediction model comprises:

[0028] Obtaining trajectory features for training, and obtaining a preset number of prediction deviation sequences in each training prediction period;

[0029] Dividing the deviation labels of the prediction deviation sequences;

[0030] Generating feature values based on the trajectory features for training and the prediction deviation sequences carrying deviation categories according to a preset algorithm;

[0031] Inputting the feature values into a report point prediction model for training to obtain a trained report point prediction model.

[0032] A second aspect of the present disclosure provides a data display device, which comprises:

[0033] An obtaining unit is configured to obtain prediction report point data corresponding to a target trajectory output by a report point prediction model; wherein the report point prediction model is configured to perform data prediction from at least one of a device direction dimension, a data integrity dimension, a trajectory bending dimension, a trajectory position dimension, and a trajectory repetition dimension;

[0034] A screening unit is configured to screen the prediction report point data according to attribute information of a display screen and a prediction period to obtain target report point data;

[0035] A drawing unit is configured to draw the target report point data along the target trajectory.

[0036] In some embodiments of the present disclosure, the obtaining unit comprises:

[0037] An adjusting module is configured to perform first adjustment on the direction of the coordinate system of the target trajectory to make it consistent with the direction of the coordinate system of the device screen;

[0038] A first calculation module is configured to perform interpolation calculation on a prediction trajectory point according to a preset sampling interval and attribute information of the prediction trajectory point to obtain first data;

[0039] A second calculation module is configured to calculate the curvature of the target trajectory according to a first trajectory point at a current time and a second trajectory point at a historical time within the preset sampling interval;

[0040] A first processing module is configured to perform differential processing on the first data to obtain second data;

[0041] The second processing module is configured to perform filtering processing on the second data to obtain the predicted report point data.

[0042] In some embodiments of the present disclosure, the screening unit comprises:

[0043] The conversion module is configured to convert a direction of a coordinate system of the target trajectory and a coordinate of the predicted trajectory point to obtain converted data.

[0044] The screening module is configured to screen the converted data according to attribute information of the display screen and the prediction period to obtain target report point data.

[0045] In some embodiments of the present disclosure, the conversion module is further configured to:

[0046] perform a second adjustment on the direction of the coordinate system of the target trajectory to the direction before the first adjustment, the second adjustment being reverse processing of the first adjustment.

[0047] determine a coordinate corresponding to the target report point data according to the latest visible coordinate of the target trajectory and the coordinate of the predicted trajectory point to obtain the converted data.

[0048] In some embodiments of the present disclosure, the screening module is further configured to:

[0049] calculate a deviation between the attribute information of the predicted trajectory point and the latest report point of the target trajectory;

[0050] input the deviation into a preset recognition model of historical trajectories to output a predicted trajectory point that is unavailable in the prediction period;

[0051] screen the number of the predicted trajectory points according to attribute information of the display screen to obtain the target report point data.

[0052] In some embodiments of the present disclosure, the adjustment module is further configured to:

[0053] determine whether the direction of the coordinate system of the target trajectory is consistent with a direction of a coordinate system of the device screen;

[0054] if not, adjust the direction of the coordinate system of the target trajectory according to the direction of the coordinate system of the device screen.

[0055] In some embodiments of the present disclosure, further comprising a training unit.

[0056] The training unit is configured to:

[0057] obtain a trajectory feature for training and a preset number of prediction deviation sequences in each prediction period for training;

[0058] dividing the deviation labels of the predicted deviation sequence;

[0059] generating a feature value according to the training trajectory feature and the predicted deviation sequence carrying the deviation category based on a preset algorithm;

[0060] inputting the feature value into a point prediction model for training to obtain a trained point prediction model.

[0061] A third aspect embodiment of the present disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect embodiment of the present disclosure.

[0062] A fourth aspect embodiment of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to perform the method described in the first aspect embodiment of the present disclosure.

[0063] A fifth aspect embodiment of the present disclosure provides a chip, comprising one or more interfaces and one or more processors; the interface is used to receive a signal from a memory of an electronic device and send a signal to the processor, the signal includes computer instructions stored in the memory, and when the processor executes the computer instructions, the electronic device performs the method described in the first aspect embodiment of the present disclosure.

[0064] In summary, according to the data display method provided by the present disclosure, the method comprises: obtaining predicted point data corresponding to a target trajectory output by a point prediction model; wherein the point prediction model is used to perform data prediction from at least one of the following dimensions: device direction dimension, data integrity dimension, trajectory bending dimension, trajectory position dimension, and trajectory repetition dimension; filtering the predicted point data according to attribute information of a display screen and a prediction period to obtain target point data; and drawing the target point data along the target trajectory. In the present disclosure, the point prediction model performs point data prediction from the device direction dimension, the data integrity dimension, the trajectory bending dimension, the trajectory position dimension, and the trajectory repetition dimension, which improves the accuracy of trajectory prediction. In addition, in combination with the screen attribute information, the prediction period and the filtering of the predicted point data are dynamically adjusted, which can improve the smoothness and continuity of the trajectory and improve the overall followability experience.

[0065] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0066] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, function to explain the principles of the disclosure, but do not limit the disclosure.

[0067] Figure 1 A flowchart of a data display method provided for an embodiment of the present disclosure;

[0068] Figure 2 A flowchart of a data display method provided for an embodiment of the present disclosure;

[0069] Figure 3 A flowchart of a data display method provided for an embodiment of the present disclosure;

[0070] Figure 4 A flowchart of a data display method provided for an embodiment of the present disclosure;

[0071] Figure 5 A structural schematic diagram of a data display device provided for an embodiment of the present disclosure;

[0072] Figure 6 A structural schematic diagram of another data display device provided for an embodiment of the present disclosure;

[0073] Figure 7 A structural schematic diagram of an electronic device provided for an embodiment of the present disclosure;

[0074] Figure 8 A structural schematic diagram of a chip provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0075] Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present disclosure, and cannot be understood as limiting the present disclosure.

[0076] With the popularity of intelligent terminal devices and the development of data processing field, users have higher requirements for the quality of terminal data display content. As an important direction in the field of display technology, the touch input processing of the terminal can enhance the display effect by predicting the handwriting when the terminal outputs touch content to the user. However, in related technologies, the prediction error of predicting handwriting is large, the prediction cycle number estimation is not accurate, and the writing scene adaptation is insufficient, which will cause a large deviation between the predicted trajectory and the real trajectory, resulting in poor hand following performance of writing. Therefore, a data display method with strong hand following experience is needed.

[0077] Therefore, in order to solve the problems in the related art, the present disclosure provides a data display method, which comprises: acquiring predicted report point data corresponding to a target trajectory output by a report point prediction model; wherein the report point prediction model is used for data prediction from at least one of the following dimensions: device direction dimension, data integrity dimension, trajectory bending dimension, trajectory position dimension, and trajectory repetition dimension; filtering the predicted report point data according to attribute information of a display screen and a prediction period to obtain target report point data; and drawing the target report point data along the target trajectory.

[0078] The scheme can improve the accuracy of trajectory prediction, dynamically adjust the number of prediction periods in combination with the attribute information of the screen, improve the smoothness and continuity of the trajectory, and improve the overall hand-following experience.

[0079] The embodiments of the present disclosure are not exhaustive, but only illustrate some embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the scheme after removing some steps in an embodiment can also be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation manners in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, some or all steps of different embodiments can be combined arbitrarily, an embodiment can be combined with optional implementation manners of other embodiments.

[0080] In the embodiments of the present disclosure, the terms and / or descriptions of the embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0081] The terms used in the embodiments of the present disclosure are only for the purpose of describing the specific embodiments, and not as a limitation on the present disclosure.

[0082] In the embodiments of the present disclosure, unless otherwise specified, the elements expressed in singular form, such as "one", "a", "the", "above", "said", "preceding", "this" and the like, can represent "one and only one", or "one or more", "at least one" and the like. For example, in the case of using articles such as "a", "an", "the" and the like in English, the noun after the article can be understood as singular expression, or can be understood as plural expression.

[0083] In some embodiments, the terms “in response to,” “in response to determining,” “in the case of,” “when,” “if,” “if,” and the like can be replaced with each other.

[0084] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” “above,” and the like can be replaced with each other, and the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” “below,” and the like can be replaced with each other.

[0085] In the embodiments of the present disclosure, the prefix words “first,” “second,” and the like are only used to distinguish different description objects, and do not constitute limitations on the position, order, priority, quantity, or content of the description objects. The description of the description objects should refer to the description in the context of the claims or embodiments, and should not constitute redundant limitations because of the use of the prefix words.

[0086] In the embodiments of the present disclosure, “a plurality of” means two or more.

[0087] In the embodiments of the present disclosure, the terms “import,” “input,” “read in,” and the like can be replaced with each other.

[0088] In some embodiments, the apparatus and the like can be interpreted as entities, and can also be interpreted as virtual, and the name thereof is not limited to the name recorded in the embodiments. The terms “apparatus,” “equipment,” “device,” “circuit,” “network element,” “node,” “function,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” “subject,” and the like can be replaced with each other.

[0089] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, and the like can be used interchangeably.

[0090] Figure 1 A flowchart of a data display method is provided for embodiments of the present disclosure. The method can be applied to application scenarios such as smart terminals supporting touch functions, which can input by a stylus, a finger, or even gaze. The present disclosure is not limited thereto. As shown in Figure 1 The data display method includes steps 101-104.

[0091] In step 101, target trajectory corresponding prediction report point data output by a report point prediction model is obtained. The report point prediction model is used to perform data prediction from at least one of device direction dimension, data integrity dimension, trajectory bending dimension, trajectory position dimension, and trajectory repetition dimension.

[0092] Embodiments of the present application can be applied to smart devices supporting touch functions. The device can be a touch screen device with different sampling rates, including but not limited to 500Hz, 360Hz, 240Hz, etc. The present disclosure is not limited thereto.

[0093] The device supports different input methods, including but not limited to finger, active pen, passive pen, resistive, capacitive, and the like.

[0094] Different auxiliary sensing devices, including but not limited to watches, bracelets, etc., different scenarios (including but not limited to Chinese, English, architectural drawings, illustrations, etc.), do not limit the gender of the user, the right or left handedness of the user, etc. when using the above-mentioned devices to draw.

[0095] The method described in the present disclosure is applied to the prediction of drawing trajectories during the drawing process in the device, so as to realize the hand following property of the drawing process. The target trajectory is the trajectory that the user is currently drawing.

[0096] The target trajectory is composed of a plurality of trajectory points, each of which contains corresponding attribute information, which includes a timestamp, touch coordinates, the orientation of the input device relative to the screen (MotionEventOrientation), the angle of the input device relative to the screen (MotionEventTilt), the pressure of the input device (pressure), the orientation of the screen (ScreenOrientation). Due to the different types of input devices, some of the attribute information of these trajectory points comes from the touch screen, and some comes from the sensor of the input device. The subsequent processing does not distinguish the data sources. Some attribute information comes from the sensor data of the auxiliary sensing device, such as acceleration, temperature, capacitance, impedance, sweat rate, etc.

[0097] During the drawing process of the target trajectory, the report point prediction model predicts the trajectory points (report points) displayed subsequently, and realizes the hand following property of the trajectory according to the predicted report point data.

[0098] In some embodiments, the report point prediction model performs output of the predicted report point data according to the above-mentioned attribute information of the trajectory points, and the report point prediction model is used to perform data prediction from at least one of the device orientation dimension, the data integrity dimension, the trajectory bending dimension, the trajectory position dimension, and the trajectory repetition dimension. As a realizable manner of the embodiments of the present disclosure, in order to realize the accuracy of the predicted report point data, when predicting the report points, the report point prediction model performs prediction of the report points from the five dimensions of the device orientation dimension, the data integrity dimension, the trajectory bending dimension, the trajectory position dimension, and the trajectory repetition dimension. However, the determination of the dimensions can select at least one or a combination of any multiple dimensions in the five dimensions according to the business needs or the hardware conditions of the device, and the embodiments of the present disclosure are not limited.

[0099] Step 102: filtering the predicted report point data according to the attribute information of the display screen and the prediction period to obtain target report point data.

[0100] The purpose of step 102 is to limit the number of predicted report point data output in the report point prediction model, so as to improve the accuracy of the predicted report point data.

[0101] In step 101, the prediction value (predicted point data) of the next N prediction periods is output by the point prediction model. According to the attribute information of the screen, such as the sampling rate and the refresh rate, the number of predicted points is further controlled. For example, when the screen refresh rate is 120 Hz and the expected number of predicted frames is 3, the number of points is not more than 3*1000ms / 120Hz*500Hz=12.5 when the sampling rate is 500 Hz, and the number of points is not more than 3 / 120Hz*240Hz=6 when the sampling rate is 240 Hz. The above examples are only illustrative and are not limited to specific values.

[0102] In order to avoid the advance or lag of the predicted point data, the embodiment of the present disclosure allows the model to be independent of the specific time interval size according to the predicted point of the specified period (prediction period).

[0103] In step 103, the target point data is plotted along the target trajectory.

[0104] The target point data obtained by filtering in step 102 is plotted on the display screen of the device to achieve the hand-following property of the plot. The plotting implementation can use any implementation in the related art, but is not limited thereto, and the embodiment of the present disclosure will not be described here.

[0105] According to the data display method proposed in the present disclosure, the method comprises obtaining predicted point data corresponding to a target trajectory output by a point prediction model; wherein the point prediction model is used to perform data prediction from at least one of the device direction dimension, the data integrity dimension, the trajectory bending dimension, the trajectory position dimension, and the trajectory repetition dimension; the predicted point data is filtered according to the attribute information of the display screen and the prediction period to obtain target point data; and the target point data is plotted along the target trajectory. In the present disclosure, the point prediction model performs point data prediction from the device direction dimension, the data integrity dimension, the trajectory bending dimension, the trajectory position dimension, and the trajectory repetition dimension, which improves the accuracy of trajectory prediction. In addition, in combination with the screen attribute information, the prediction period is dynamically adjusted and the predicted point data is filtered, which can improve the smoothness and continuity of the trajectory and improve the overall hand-following experience.

[0106] Figure 2 Further, a flowchart of a data display method proposed in the present disclosure is shown. Based on the embodiment shown in Figure 1 The step 101 is further explained, Figure 2 may comprise the following steps:

[0107] In step 201, the direction of the coordinate system of the target trajectory is first adjusted to be consistent with the direction of the coordinate system of the device screen.

[0108] This step corresponds to the device direction dimension of the report point prediction model.

[0109] The x and y axis coordinates are adjusted according to the screen direction, aligned with the user's writing, so as to distinguish the horizontal and vertical stroke features,

[0110] In some embodiments of the present disclosure, it is first determined whether the direction of the coordinate system of the target trajectory is consistent with the direction of the coordinate system of the device screen, and in the case of inconsistency, the direction of the coordinate system of the target trajectory is adjusted according to the direction of the coordinate system of the device screen. In the case of consistency, this step is not performed.

[0111] Adjusting the direction of the coordinate system includes the following scenarios:

[0112] If the device screen direction is ORIENTATION_PORTRAIT (portrait screen), this step is not performed.

[0113] If the device screen direction is Orientation_PortraitUpsideDown (portrait screen, upside down), the x and y coordinates of all trajectories are rotated by 180 degrees around the screen center point.

[0114] If the device screen direction is Orientation_LandscapeLeft (screen placed horizontally to the left), the x and y coordinates of all trajectories are rotated counterclockwise by 90 degrees around the screen center point.

[0115] If the device screen direction is Orientation_LandscapeRight (screen placed horizontally to the right), the x and y coordinates of all trajectories are rotated clockwise by 90 degrees around the screen center point.

[0116] In other cases (unknown direction, screen lying flat upwards or downwards), the most recent known direction is processed.

[0117] In the feature collection, except for the x and y coordinates, the remaining attribute information and the device screen direction are irrelevant and do not need to be processed. For example, the attribute information orientation is rotated with the screen orientation; the attribute information tilt is only related to the screen vertical axis and is irrelevant to rotation; the attribute information pressure is also irrelevant to the screen direction; and the auxiliary sensor input is also irrelevant to the screen.

[0118] Step 202: interpolating and calculating the predicted trajectory points according to the preset sampling interval and the attribute information of the predicted trajectory points to obtain first data.

[0119] This step corresponds to the data integrity dimension of the report point prediction model.

[0120] The interpolation calculation makes the time interval of the historical trajectory more stable, and the report point at a specified time in the related technology is changed into the report point of the prediction period (preset sampling interval) of the embodiment of the disclosure, so that the model is independent of the specific time interval size, and the advance and lag of the prediction result are avoided.

[0121] In some embodiments, the average sampling interval T is estimated according to the sampling rate, and if the prediction trajectory point timestamp interval D satisfies mT <= D < nT (m and n are positive integers, and m > 1, for example, m = 2 and n = 5), interpolation calculation is performed; the interpolation number is D / / T-1, where / / represents integer division (for example, when m = 2 and n = 5, the interpolation number is 1-3); when the interpolation number is small, linear interpolation can be used, and when the interpolation number is large, Lagrange interpolation, Taylor expansion fitting interpolation and the like can be used; the attribute information of the interpolation includes all model input features.

[0122] It should be noted that the part of D >= nT will not be interpolated to avoid excessive continuous interpolation data affecting the model output effect.

[0123] In step 203, the curvature of the target trajectory is calculated according to the first trajectory point at the current time and the second trajectory point at the historical time within the preset sampling interval.

[0124] This step corresponds to the trajectory bending dimension of the report point prediction model.

[0125] In the embodiment of the disclosure, the curvature of the target trajectory is used to measure the bending degree of the historical curve, and the smaller the curvature, the smoother the historical trajectory; the larger the curvature, the more tortuous the historical trajectory. The curvature improvement model is more obvious in optimizing the scene with high curvature of curves and broken lines.

[0126] Suppose the current time is T, and the first trajectory points at times T-2, T-1 and T are A, B and C respectively. The curvature is the reciprocal of the circumradius R of triangle ABC, and according to the curvature definition and the trigonometric function formula, that is,

[0127] curv = 1 / R

[0128] 1 / R = 2sinA / (|BC|) = 2sinB / (|AC|) = 2sinC / (|AB|)

[0129] nsinB = (BA x BC) / (|BA||BC|)

[0130] curv = 1 / R = 2sinB / (|AC|) = (2BA x BC) / (n|BA||BC||AC|)

[0131] In the above formula, BA, BC, and AC are all vectors, n is a unit vector perpendicular to vectors BA and BC, and BA × BC is the cross product of vectors BA and BC. Because the cross product has direction, the calculated curvature also has direction, corresponding to clockwise and counterclockwise. For example, a circle and an S-curve may have the same magnitude of curvature, but the sign of curvature changes at the inflection points of the S-curve. If two of the three points coincide, the curvature is recorded as 0.

[0132] Step 204: Perform differential processing on the first data to obtain the second data.

[0133] This step corresponds to the trajectory location dimension of the reporting point prediction model.

[0134] To ensure that the point trajectories in the target trajectory are independent of the screen rendering area, the first set of data is subtracted to extract position-independent features. The features used to calculate the difference include x, y, orientation, tilt, pressure, and curvature.

[0135] In some embodiments, since the timestamps have already been interpolated (step 202) and the time interval is fixed, no further differential interpolation is performed.

[0136] In this embodiment of the disclosure, rotation invariant processing is not performed for two reasons: first, to distinguish the differences in writing the x and y axes; and second, orientation invariant processing has already been performed in step 201.

[0137] In this embodiment of the disclosure, the second data is not standardized after differencing; instead, the original difference value is used. After standardization, the distributions of the x and y axis data are similar, making it impossible to distinguish their differences.

[0138] Step 205: Filter the second data to obtain the predicted reporting data.

[0139] This step corresponds to the trajectory repetition dimension of the reporting point prediction model.

[0140] In practical applications, when many repeated coordinate points appear in the adjacent historical trajectory during plotting, the trajectory becomes discontinuous and jumps, making it difficult to predict. Therefore, a threshold is set (e.g., the proportion of repeated points > 20%) to filter the second data, deleting the trajectory points with repeated coordinate points so that they are not used for prediction.

[0141] In passing Figure 2 After performing data preprocessing as shown, input all preprocessed attribute parameters into the reporting point prediction model to obtain predicted reporting point data.

[0142] In some embodiments, after data preprocessing, a tensor of [None, seqLen, featureSize] dimensions is obtained, where None corresponds to the batch size, the amount of data for training a batch, according to the GPU memory capacity and training effect, for example, 1024, seqLen is the number of historical points, for example, 19 points, and featureSize is the number of features, including screen and input device sensor parameter features (such as x, y, orientation, tilt, pressure, etc.), auxiliary sensor input features (such as x, y, z components of acceleration, skin humidity, impedance, etc.), and high-order features (such as curvature). It should be noted that the input parameters can be adjusted according to the actual needs to select the features, and the specific embodiments of the present disclosure do not limit this.

[0143] The output of the point prediction model is a tensor of [None, predLen, 2], where None is the batch size, predLen is the number of predicted point data, and 2 is the x coordinate and y coordinate. For example, if predLen is 12, the last dimension 2 corresponds to the x coordinate and y coordinate, and other features are not predicted.

[0144] In some embodiments, the point prediction model can be regarded as a seq2seq model combined with an encoder and a decoder, where:

[0145] The encoder part: single-layer GRU, the result after the encoder is [None, seqLen, gruDim], and gruDim is the dimension of the GRU cell, which can be 64, and the dimension size is not limited in the embodiments of the present disclosure.

[0146] The decoder part: using a multi-layer perceptron (MLP) to complete multi-step prediction at one time, instead of passing the result of the previous step to the next step as in the traditional LSTM decoder, to avoid error propagation. Specifically:

[0147] The MLP directly completes multi-step prediction, instead of one Dense per time, and does not pass the previous prediction value to the next one, causing bias accumulation.

[0148] The hidden vector is converted to a [None, dim, seqLen] vector by transpose.

[0149] Convert to a vector of [None, dim, predLen] by Dense(predLen), and then transpose back to [None, pred Len, dim], which corresponds to the state of the future predLen prediction points

[0150] Convert the state to the corresponding x coordinate and y coordinate by Dense(2), and since the difference is made before, it is actually the difference between the prediction point and the last visible historical point.

[0151] Figure 3 Further show the flow chart of the data display method proposed by the present disclosure. Based on Figure 1 The step 102 is further explained, Figure 3 May include the following steps:

[0152] Step 301, the direction of the coordinate system of the target trajectory and the coordinates of the predicted trajectory point are converted to obtain the converted data.

[0153] Figure 2 When predicting the point data, data preprocessing is done, so before finally determining the target point data, the data needs to be reversed to obtain the target point data.

[0154] In some embodiments, the direction of the coordinate system of the target trajectory is adjusted to the direction before the first adjustment is performed, and the second adjustment is the reverse processing of the first adjustment. According to the latest visible coordinates of the target trajectory and the coordinates of the predicted trajectory point, the coordinates corresponding to the target point data are determined, and the converted data is obtained.

[0155] Position-independent reverse processing: add the last visible x coordinate and y coordinate of the historical trajectory (the latest visible coordinate of the target trajectory) to the predicted trajectory point to obtain the dx and dy of the predicted trajectory point.

[0156] Direction-independent reverse processing: according to the current device screen direction, rotate in the opposite direction when data preprocessing.

[0157] For example, when the operation during preprocessing is to rotate 90 degrees clockwise around the screen center point, then when performing conversion, it needs to rotate 90 degrees counterclockwise around the screen center point; the above is an example, and the embodiments of the present disclosure are not limited.

[0158] Step 302, according to the attribute information of the display screen and the prediction period, the converted data is filtered to obtain the target point data.

[0159] The purpose of this step is to limit the number of predicted point data.

[0160] In the step of performing, the following methods can be used, but are not limited to, for example: calculating the deviation between the attribute information of the predicted trajectory point and the latest report point of the target trajectory, inputting the deviation into a historical trajectory recognition model, and outputting the predicted trajectory points that are unavailable in the prediction period, screening the number of predicted trajectory points according to the attribute information of the display screen, and obtaining the target report point data.

[0161] In some embodiments, according to the attribute information of the latest predicted trajectory point, the deviation between the latest report point of the target trajectory is calculated, that is, the prediction deviation of the previous time is updated, the calculated deviation and the historical trajectory feature are input into a discrimination model to determine which period of predicted trajectory points is not used, and the number of predicted trajectory points is further controlled according to the sampling rate and refresh rate (attribute information of the display screen). For example, the screen refresh rate is 120 Hz, and the expected number of predicted frames is 3 frames. When the sampling rate is 500 Hz, the number of points is not more than 3*1000ms / 120Hz*500Hz=12.5; when the sampling rate is 240 Hz, the number of points is not more than 3 / 120Hz*240Hz=6.

[0162] Figure 4 Further, a flowchart of a data display method according to the present disclosure is shown. Based on the report point prediction model shown in the figure, the training process of the report point prediction model is as shown in the figure Figure 1 As shown, the method comprises the following steps: Figure 4 As shown, the method comprises the following steps:

[0163] Step 401: Obtain a training trajectory feature, and obtain a preset number of prediction deviation sequences in each training prediction period.

[0164] Before predicting N prediction report point data each time, a training trajectory feature at the current time is obtained, which can be a historical trajectory feature.

[0165] A prediction period (such as N periods) is obtained, and a preset number (such as 10 times) of prediction deviation sequences in each period are obtained, which are measured by two indicators: prediction lead distance and prediction direction deviation.

[0166] In some embodiments, the last visible trajectory point is denoted as LP, the predicted trajectory point is denoted as PP, and the true trajectory point is denoted as TP.

[0167] Prediction lead distance: distance(PP, LP) - distance(TP, LP), which is positive if the predicted point is farther than the true point, and negative if the predicted point is closer than the true point;

[0168] Prediction direction deviation: the angle between LP and PP and TP.

[0169] In the calculation of the weighted prediction lead distance deviation and the prediction direction deviation, the prediction lead distance deviation can be in the form of, but not limited to, the Euclidean distance, and the prediction direction deviation is not limited to 1-cos(A). Since both the prediction value and the true value are differentiated, it is actually the vector from the prediction point and the true point to the last visible point, which can be brought into the vector angle cosine formula.

[0170] It should be noted that the longer the prediction period is, the greater the deviation is. Optionally, in order to avoid the model sacrificing the prediction accuracy of the short period and improving the average prediction accuracy, different weights are added to different prediction periods, and the closer the period is, the higher the weight is.

[0171] Step 402, dividing the deviation label of the prediction deviation sequence.

[0172] Based on the prediction deviation sequence obtained in step 401, the labeling processing is performed. When the prediction lead distance is greater than the distance threshold, the prediction trajectory is ahead of the true trajectory, the experience is not good, and the prediction should not be performed, and the deviation label is configured as 0. When the prediction direction deviation is greater than the angle threshold, the direction of the prediction trajectory is different from that of the true trajectory (the angle deviation is large), that is, the prediction should not be performed, and the deviation label is configured as 0. Except for the above two scenarios, the prediction is needed in other cases, and the deviation label is configured as 1.

[0173] Step 403, generating a feature value based on a preset algorithm according to the training trajectory feature and the prediction deviation sequence carrying the deviation category.

[0174] In some embodiments, through a feature engineering framework, the training trajectory feature and the prediction deviation sequence carrying the deviation category (including the lead distance and the direction) generate a large number of feature values.

[0175] In some embodiments, topK feature values can also be selected according to the correlation coefficient.

[0176] Step 404, inputting the feature value into a report point prediction model for training to obtain a trained report point prediction model.

[0177] In the training process, a classification model such as a decision tree, a random forest, a gbdt, and an svm can be used for binary classification. As a realizable scheme, the model based on the decision tree has an advantage in the conditional judgment logic converted into code, but in order to facilitate conversion, the maximum tree depth needs to be limited, for example, to 5. From the trained decision tree node, the corresponding key features and the discrimination conditions are obtained, which are converted into if-else code discrimination conditions in use. The specific discrimination conditions include but are not limited to:

[0178] a. Trajectory linearity

[0179] b. Historical maximum prediction deviation, quartile, mean square and other distribution characteristics of the 1st, 2nd, 3rd and 4th points

[0180] c. Linearity, rate of change, covariance and other distribution characteristics of pressure

[0181] d. Quartile and other distribution characteristics of curvature

[0182] In some embodiments, a discriminant model can be established for each prediction period in theory, but the farther the actual prediction time is, the greater the deviation is, so a discriminant model is established for a maximum number of periods.

[0183] In summary, the method described in the present disclosure can achieve the following beneficial effects:

[0184] 1. Improve the accuracy of trajectory prediction.

[0185] Through data processing and feature expansion: the deviations of T3 (6 ms), T7 (14 ms) and T10 (20 ms) are as follows, in pixels

[0186] Table 1

[0187] Prediction period T3 T7 T10 Ours 0.49 1.35 2.31 No data integrity processing, directly use difference 0.55 1.48 2.47 No high-order features 0.52 1.44 2.41 No screen direction independence processing 0.52 1.43 2.45

[0188] As can be seen from Table 1, using data completeness, high-order features and screen direction-independent processing, each is improved by about 8.8%, 6.2% and 5.6%.

[0189] 2. Fine modeling of prediction deviation, combined with screen refresh rate and sampling rate, dynamic adjustment of prediction period number, improvement of trajectory smoothness and continuity.

[0190] 3. Only when the prediction is particularly far or the direction is not accurate, the number of prediction points is reduced, and the false error is reduced.

[0191] 4. Improve the overall hand tracking experience.

[0192] Figure 5 A structural schematic diagram of a data display device 500 provided for an embodiment of the present disclosure, the data display device comprising:

[0193] An acquisition unit 51 is configured to acquire prediction point data corresponding to a target trajectory output by a prediction point prediction model; wherein the prediction point prediction model is configured to perform data prediction from at least one of a device direction dimension, a data completeness dimension, a trajectory bending dimension, a trajectory position dimension and a trajectory repetition dimension;

[0194] A screening unit 52 is configured to screen the prediction point data according to attribute information of a display screen and a prediction period, to obtain target prediction point data;

[0195] The drawing unit 53 is configured to draw the target report point data along the target trajectory.

[0196] According to the data display device provided in the present disclosure, the target report point data is obtained by acquiring the predicted report point data corresponding to the target trajectory of the report point prediction model; wherein the report point prediction model is used to perform data prediction from at least one of the device direction dimension, the data integrity dimension, the trajectory bending dimension, the trajectory position dimension, and the trajectory repetition dimension; the target report point data is obtained by screening the predicted report point data according to the attribute information of the display screen and the prediction period; and the target report point data is drawn along the target trajectory. In the present disclosure, the report point prediction model is used to perform report point data prediction from the device direction dimension, the data integrity dimension, the trajectory bending dimension, the trajectory position dimension, and the trajectory repetition dimension, so as to improve the accuracy of trajectory prediction. In addition, the prediction period and the screening of the predicted report point data are dynamically adjusted in combination with the screen attribute information, so as to improve the smoothness and continuity of the trajectory and improve the overall hand tracking experience.

[0197] Further, in a possible implementation manner of the present embodiment, as shown in Figure 6 the acquisition unit 51 comprises:

[0198] The adjustment module 511 is configured to perform first adjustment on the direction of the coordinate system of the target trajectory, and adjust the direction to be consistent with the direction of the coordinate system of the device screen.

[0199] The first calculation module 512 is configured to perform interpolation calculation on the predicted trajectory point according to a preset sampling interval and attribute information of the predicted trajectory point, to obtain first data.

[0200] The second calculation module 513 is configured to calculate the curvature of the target trajectory according to the first trajectory point at the current time and the second trajectory point at the historical time within the preset sampling interval.

[0201] The first processing module 514 is configured to perform differential processing on the first data, to obtain second data.

[0202] The second processing module 515 is configured to perform filtering processing on the second data, to obtain the predicted report point data.

[0203] Further, in a possible implementation manner of the present embodiment, as shown in Figure 6 the screening unit 52 comprises:

[0204] The conversion module 521 is configured to convert the direction of the coordinate system of the target trajectory and the coordinates of the predicted trajectory point, to obtain converted data.

[0205] The screening module 522 is configured to screen the converted data according to the attribute information of the display screen and the prediction period, to obtain target report point data.

[0206] Further, in a possible implementation of the embodiment, as shown in Figure 6 The conversion module 521 is further configured to:

[0207] perform a second adjustment on the direction of the coordinate system of the target trajectory, to the direction before the first adjustment, the second adjustment being reverse processing of the first adjustment;

[0208] According to the latest visible coordinate of the target trajectory and the coordinate of the prediction trajectory point, determine the coordinate corresponding to the target report point data, to obtain the converted data.

[0209] Further, in a possible implementation of the embodiment, as shown in Figure 6 The screening module 522 is further configured to:

[0210] According to the attribute information of the prediction trajectory point, calculate the deviation between the latest report point of the target trajectory and the prediction trajectory point;

[0211] input the deviation into a preset recognition model of historical trajectory, and output the prediction trajectory point that is unavailable in the prediction period;

[0212] According to the attribute information of the display screen, screen the number of prediction trajectory points, to obtain the target report point data.

[0213] Further, in a possible implementation of the embodiment, as shown in Figure 6 The adjustment module 511 is further configured to:

[0214] determine whether the direction of the coordinate system of the target trajectory is consistent with the direction of the coordinate system of the device screen;

[0215] If not, adjust the direction of the coordinate system of the target trajectory according to the direction of the coordinate system of the device screen.

[0216] Further, in a possible implementation of the embodiment, as shown in Figure 6 Further, the training unit 54 is further configured to:

[0217] The training unit 54 is configured to:

[0218] obtain a training trajectory feature, and obtain a preset number of prediction deviation sequences in each training prediction period;

[0219] divide the deviation label of the prediction deviation sequence;

[0220] generate a feature value based on the preset algorithm according to the training track feature and the predicted deviation sequence carrying the deviation category;

[0221] input the feature value into a report point prediction model for training to obtain a trained report point prediction model.

[0222] Since the apparatus provided by the embodiments of the present disclosure corresponds to the methods provided by the above several embodiments, the implementation of the methods is also applicable to the apparatus provided by the embodiments of the present disclosure, which will not be described in detail in the present embodiment.

[0223] In the embodiments provided in the present application, the method and apparatus provided by the embodiments of the present application are introduced. In order to realize the functions of the above-mentioned method provided by the embodiments of the present application, the electronic device can include hardware structure, software module, and the above-mentioned functions can be executed in the form of hardware structure, software module, or hardware structure plus software module.

[0224] Figure 7 is a block diagram of an electronic device 1000 for implementing the above-mentioned data display method according to an exemplary embodiment. For example, the electronic device 700 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0225] Referring to Figure 7 , the electronic device 700 can include one or more of the following components: a processing component 702, a memory 704, a power supply component 706, a multimedia component 708, an audio component 710, an input / output (I / O) interface 712, a sensor component 714, and a communication component 716.

[0226] The processing component 702 usually controls the overall operation of the electronic device 700, such as operations associated with displaying, making phone calls, data communications, camera operations, and recording operations. The processing component 702 can include one or more processors 720 to execute instructions to complete all or part of the steps of the above-mentioned methods. In addition, the processing component 702 can include one or more modules to facilitate interaction between the processing component 702 and other components. For example, the processing component 702 can include a multimedia module to facilitate interaction between the multimedia component 708 and the processing component 702.

[0227] The memory 704 is configured to store various types of data to support the operation of the electronic device 700. Examples of such data include instructions for any application or method operating on the electronic device 700, contact data, phonebook data, messages, pictures, videos, and the like. The memory 704 can be implemented by any type of volatile or nonvolatile memory, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disc, or optical disc.

[0228] The power supply component 706 supplies power to the various components of the electronic device 700. The power supply component 706 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 700.

[0229] The multimedia component 708 includes a screen providing an output interface between the electronic device 700 and a user. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swiping, and gestures on the touch panel. The touch sensor can not only sense a boundary of a touching or swiping action, but also detect duration and pressure related to the touching or swiping action. In some embodiments, the multimedia component 708 includes a front camera and / or a rear camera. The front and / or rear camera can receive external multimedia data when the electronic device 700 is in an operation mode, such as a photographing mode or a video mode. Each of the front and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0230] The audio component 710 is configured to output and / or input audio signals. For example, the audio component 710 includes a microphone (MIC) configured to receive external audio signals when the electronic device 700 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 704 or transmitted via the communication component 716. In some embodiments, the audio component 710 also includes a speaker for outputting audio signals.

[0231] The I / O interface 712 provides an interface between the processing component 702 and peripheral interface modules, which can be a keyboard, a click wheel, a button, and the like. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0232] The sensor component 714 includes one or more sensors for providing status assessments for various aspects of the electronic device 700. For example, the sensor component 714 can detect an open / closed position of the electronic device 700, relative positioning of components, such as a display and a keypad of the electronic device 700, a change in position of the electronic device 700 or a component of the electronic device 700, presence or absence of user contact with the electronic device 700, orientation or acceleration / deceleration / g-force and temperature of the electronic device 700. The sensor component 714 can include an optical sensor for detecting ambient light, a proximity sensor configured to detect proximity of an object, a motion sensor, a temperature sensor, a magnetic sensor, an acceleration sensor, a gyroscope sensor, a pressure sensor, or the like.

[0233] The communication component 716 is configured to facilitate wired or wireless communication between the electronic device 700 and other devices. The electronic device 700 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G LTE, 5G NR (New Radio), or a combination thereof. In an example embodiment, the communication component 716 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an example embodiment, the communication component 716 can further include a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technology.

[0234] In an example embodiment, the electronic device 700 can be implemented using one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements to perform the above-described methods.

[0235] In an example embodiment, a non-transitory computer-readable storage medium including instructions, such as the memory 704 including instructions, is also provided, which can be executed by the processor 720 of the electronic device 700 to implement the above-described methods for image processing. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disc, and an optical data storage device, etc.

[0236] Embodiments of the present disclosure further provide a non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method described in the above embodiments of the present disclosure.

[0237] For the case that the electronic device can be a chip or a chip system, refer to Figure 8 The chip shown in the structural schematic diagram. Figure 8 The chip shown in the structural schematic diagram includes a processor 801 and an interface 802. The number of the processor 801 can be one or more, and the number of the interface 802 can be multiple.

[0238] Optionally, the chip further includes a memory 803, and the memory 803 is used to store necessary computer programs and data.

[0239] Those skilled in the art can also understand that the various illustrative logical blocks and steps listed in the embodiments of the present application can be implemented by electronic hardware, computer software, or a combination of the two. Whether the function is implemented by hardware or software depends on the specific application and design requirements of the whole system. Those skilled in the art can use various methods to implement the function for each specific application, but such implementation should not be understood as beyond the scope of the embodiments of the present application.

[0240] It should be noted that the terms "first", "second", and the like in the description of the present disclosure and the claims and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0241] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "illustrative embodiment", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0242] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0243] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0244] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0245] Those skilled in the art can understand that all or part of the steps of the method carried out by the above-mentioned embodiments can be instructed by a program to the relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiments or a combination thereof.

[0246] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically independently, or two or more units can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. If the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0247] Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A data display method, characterized in that, The method includes: Obtain the predicted reporting data corresponding to the target trajectory output by the reporting prediction model; wherein, the reporting prediction model is used to predict data from at least one of the following dimensions: device direction dimension, data integrity dimension, trajectory bend dimension, trajectory position dimension, and trajectory repetition dimension; The predicted reporting data is filtered based on the attribute information of the display screen and the prediction period to obtain the target reporting data; The target reporting data is plotted along the target trajectory; The predicted reporting data corresponding to the target trajectory output by the reporting prediction model includes: The direction of the coordinate system of the target trajectory is first adjusted to be consistent with the direction of the coordinate system of the device screen; The first data is obtained by interpolating the predicted trajectory points based on the preset sampling interval and the attribute information of the predicted trajectory points. The curvature of the target trajectory is calculated based on the first trajectory point at the current moment and the second trajectory point at a historical moment within the preset sampling interval. The first data is differentially processed to obtain the second data; The second data is filtered to obtain the predicted reporting data.

2. The method according to claim 1, characterized in that, The step of filtering the predicted reporting data based on the display screen's attribute information and prediction period to obtain the target reporting data includes: The coordinate system of the target trajectory and the coordinates of the predicted trajectory points are transformed to obtain the transformed data; The converted data is filtered based on the attribute information of the display screen and the prediction period to obtain the target reporting data.

3. The method according to claim 2, characterized in that, The transformation of the coordinate system of the target trajectory and the coordinates of the trajectory points to obtain the transformed data includes: The direction of the coordinate system of the target trajectory is adjusted a second time to the direction before the first adjustment was performed. The second adjustment is the reverse of the first adjustment. Based on the nearest visible coordinates of the target trajectory and the coordinates of the predicted trajectory points, the coordinates corresponding to the target reporting data are determined, and the transformed data is obtained.

4. The method according to claim 2, characterized in that, The step of filtering the converted data based on the attribute information of the display screen and the prediction period to obtain the target reporting data includes: Calculate the deviation between the predicted trajectory points and the latest reported points of the target trajectory based on the attribute information of the predicted trajectory points; Input the deviation and historical trajectory into a preset recognition model, and output the unusable predicted trajectory points within the prediction period; The number of predicted trajectory points is filtered based on the attribute information of the display screen to obtain the target reporting point data.

5. The method according to claim 1, characterized in that, The first adjustment of the direction of the coordinate system of the target trajectory to be consistent with the direction of the coordinate system of the device screen includes: Determine whether the direction of the coordinate system of the target trajectory is consistent with the direction of the coordinate system of the device screen; If they are inconsistent, the orientation of the target trajectory's coordinate system is adjusted according to the orientation of the device screen's coordinate system.

6. The method according to any one of claims 1-5, characterized in that, The training method for the reporting prediction model includes: Acquire the trajectory features used for training, and acquire a preset number of prediction bias sequences within each training prediction period; Defining the deviation labels of the predicted deviation sequence; Feature values ​​are generated based on the training trajectory features and the predicted deviation sequence carrying the deviation category, according to a preset algorithm. The feature values ​​are input into the reporting prediction model for training to obtain a trained reporting prediction model.

7. A data display device, characterized in that, The device includes: The acquisition unit is used to acquire the predicted reporting data corresponding to the target trajectory output by the reporting prediction model; wherein, the reporting prediction model is used to predict data from at least one of the following dimensions: device direction dimension, data integrity dimension, trajectory bend dimension, trajectory position dimension, and trajectory repetition dimension. The filtering unit is used to filter the predicted reporting data according to the attribute information of the display screen and the prediction period to obtain the target reporting data. A drawing unit is used to draw the target reporting data along the target trajectory; The acquisition unit is further configured to: The direction of the coordinate system of the target trajectory is first adjusted to be consistent with the direction of the coordinate system of the device screen; The first data is obtained by interpolating the predicted trajectory points based on the preset sampling interval and the attribute information of the predicted trajectory points. The curvature of the target trajectory is calculated based on the first trajectory point at the current moment and the second trajectory point at a historical moment within the preset sampling interval. The first data is differentially processed to obtain the second data; The second data is filtered to obtain the predicted reporting data.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A chip, characterized in that, It includes one or more interfaces and one or more processors; the interfaces are used to receive signals from the memory of an electronic device and send the signals to the processors, the signals including computer instructions stored in the memory, which, when executed by the processors, cause the electronic device to perform the method of any one of claims 1-6.

Images