Sensor-based LED display screen interaction detection method and system

Abstract

The invention discloses an LED display screen interaction detection method and system based on a sensor, and relates to the related field of man-machine interaction, and the method comprises the steps: collecting interaction triggering data of an LED display screen through the sensor, and the interaction triggering data comprises an interaction generation timestamp, an interaction space coordinate, an interaction intensity parameter and an interaction type parameter; after effective interaction judgment is carried out based on the interaction triggering data, display response data of the corresponding LED display screen are collected through a sensor, and the display response data comprise display starting time, a response area brightness value, a color parameter and a driving current parameter; calculating interaction response parameters of the interaction trigger data and the display response data, and constructing an interaction response difference parameter set; lED detection evaluation is carried out according to the interaction response difference parameter set, and an interaction detection result is generated. According to the invention, the technical problem of poor abnormity judgment reliability in the existing LED display screen interactive detection is solved, and the technical effects of improving the abnormity recognition accuracy and the detection result reliability are achieved.

Description

Technical Field

[0001] This application relates to the field of human-computer interaction, and in particular to a sensor-based method and system for interactive detection of LED displays. Background Technology

[0002] As the core hardware for human-computer interaction displays, the stability and accuracy of LED displays directly affect the interactive experience, equipment reliability, and scene usage effects, making it a crucial technical aspect in the interactive display field. Currently, interactive testing of LED displays mainly relies on manual sampling or single-sensor acquisition of interactive signals, followed by simple threshold comparisons to determine if the display response is normal. This type of detection method, dependent on manual labor and simple thresholds, is susceptible to sensor drift, environmental interference, and individual differences in judgment, leading to inaccurate interactive trigger data acquisition, delayed identification of display response parameters, and difficulty in accurately locating abnormal areas and types of anomalies.

[0003] Currently, LED display screen interactive detection suffers from poor reliability in anomaly detection. Summary of the Invention

[0004] This application provides a sensor-based interactive detection method and system for LED displays. It collects interactive trigger data from the LED display using sensors, including interaction timestamps, spatial coordinates, intensity, and type parameters. The system effectively determines whether the interactive trigger data is valid. Upon successful determination, it collects display response data, including display start-up time, response area brightness, color, and drive current parameters. It calculates the interactive response parameters between the interactive trigger data and the display response data, constructs an interactive response difference parameter set, and evaluates the LED display based on this parameter set, generating corresponding interactive detection results. These technical means solve the technical problem of poor reliability in anomaly detection in existing LED display interactive detection systems, achieving the technical effect of improving the accuracy of anomaly identification and the reliability of detection results.

[0005] This application provides a sensor-based interactive detection method for LED displays, comprising: collecting interactive trigger data of the LED display through sensors, including an interaction timestamp, interaction spatial coordinates, interaction intensity parameters, and interaction type parameters; determining valid interaction based on the interactive trigger data; collecting display response data of the corresponding LED display through sensors, the display response data including display start time, response area brightness value, color parameters, and drive current parameters; calculating the interactive response parameters between the interactive trigger data and the display response data to construct an interactive response difference parameter set; and performing LED detection evaluation based on the interactive response difference parameter set to generate an interactive detection result.

[0006] In a possible implementation, the interaction response parameters of the interaction trigger data and the display response data are calculated, an interaction response difference parameter set is constructed, and the following processing is performed: timing alignment processing is performed based on the interaction occurrence timestamp and the display startup time to determine the response time difference between the interaction trigger data and the display response data; based on the response time difference, deviation analysis is performed on the brightness value, color parameters, and driving current parameters of the response area to construct an interaction response difference parameter set including time difference parameters and display deviation parameters, and the interaction response difference parameter set is matched and judged based on the standard response threshold of each response parameter to locate the initial abnormal area.

[0007] In a possible implementation, LED detection and evaluation are performed based on the interactive response difference parameter set to generate interactive detection results. The following processing is then performed: each response difference parameter in the interactive response difference parameter set is compared with a preset health benchmark response model to determine the degree of deviation of each response parameter relative to the model benchmark. The degree of deviation includes the degree of time deviation and the degree of deviation of display parameters. Based on the degree of deviation and the regional neighborhood consistency parameter of the preliminary abnormal area, anomaly determination is performed on the response area. When the response parameters of the same area exceed the corresponding preset threshold for a preset number of consecutive times, the area is marked as an abnormal area. The frequency of abnormal occurrence of each abnormal area is counted, and combined with the preset abnormal weight, the health score of the corresponding LED display module is calculated. Based on the health score, the module health status and abnormal warning information are output as the interactive detection results.

[0008] In a possible implementation, before comparing with a preset health benchmark response model, the following processing is performed: based on the mapping relationship between the display screen detection target and the interactive response parameters, the target sensing parameters are analyzed; according to the response correlation between the target sensing parameters and the interactive trigger parameters, the response feature values ​​are calculated; based on the detection constraint target of the target LED display screen, the response feature values ​​are filtered and normalized to establish the preset health benchmark response model.

[0009] In a possible implementation, based on the response correlation between the target sensing parameters and the interactive triggering parameters, response feature values ​​are calculated, and the following processing is performed: based on the response correlation between the target sensing parameters and the interactive triggering parameters, the response feature values ​​are subjected to constraint analysis of feature change time window, response linkage range, and range fluctuation relationship, generating response time window features, response range features, and range fluctuation features to obtain response relationship constraint features; the response feature values ​​are constrained and marked based on the response relationship constraint features.

[0010] In a possible implementation, the response feature values ​​are constrained and labeled based on the response relationship constraint features, and the following processing is performed: based on the response relationship constraint features, the mean, variance, and change amplitude of the response feature values ​​are statistically analyzed within a preset time window to generate time stability features; based on a preset response correlation interval, the response feature values ​​are analyzed for range consistency to generate interval convergence features and fluctuation trend features; the time stability features, interval convergence features, and fluctuation trend features are quantized and standardized to obtain a response relationship constraint feature vector, and the response relationship constraint feature vector is used as a constraint label and appended to the response feature values.

[0011] In a possible implementation, after marking the response area as an abnormal area, the following processing is also performed: spatial clustering analysis is performed on the abnormal area; when multiple adjacent display areas have the same type of difference parameter anomaly within a preset time window, an abnormal cluster is established; when the number of areas in the abnormal cluster exceeds a preset coverage ratio, it is determined to be a system-level anomaly; when the abnormal cluster is limited to a single module or the number of adjacent areas is less than a preset threshold, it is determined to be a local module anomaly.

[0012] In a possible implementation, interactive trigger data from an LED display screen is collected by a sensor, and the following processing is performed: parsing the parameter sensitivity of the interactive trigger data corresponding to the interactive detection target; searching and matching the sensor-collected parameters using the parameter sensitivity as an index to identify calibration compensation conditions and compensation targets; and using the calibration compensation conditions and compensation targets to perform parameter compensation on the corresponding sensor of the interactive trigger data for calibrating the interactive trigger data.

[0013] In a possible implementation, after determining a valid interaction based on the interaction trigger data, the display response data of the corresponding LED display screen is collected by a sensor, and the following processing is performed: a preset timing response observation window corresponding to the valid interaction is determined; after determining a valid interaction, the brightness value, color parameters, and driving current parameters of the response area are continuously sampled within the preset timing response observation window to determine the display start-up anchor time and the stable arrival time of each response parameter; based on the display start-up anchor time and the stable arrival time of each response parameter, the parameter delay difference parameter and the response consistency parameter are calculated to obtain the display response data.

[0014] This application also provides a sensor-based interactive detection system for LED displays, comprising: an interactive trigger data acquisition module for acquiring interactive trigger data of the LED display through sensors, including an interactive occurrence timestamp, interactive spatial coordinates, interactive intensity parameters, and interactive type parameters; a display response data acquisition module for acquiring display response data of the corresponding LED display through sensors after determining effective interaction based on the interactive trigger data, the display response data including display start time, response area brightness value, color parameters, and driving current parameters; an interactive response difference parameter set construction module for calculating the interactive response parameters between the interactive trigger data and the display response data, and constructing an interactive response difference parameter set; and an LED detection and evaluation module for performing LED detection and evaluation based on the interactive response difference parameter set, and generating interactive detection results.

[0015] The proposed sensor-based LED display interaction detection method and system first collects interaction trigger data from the LED display using sensors, including interaction timestamps, interaction spatial coordinates, interaction intensity parameters, and interaction type parameters. Then, based on the interaction trigger data, a valid interaction determination is made. Next, the corresponding LED display display's display response data is collected using sensors. This display response data includes display start-up time, response area brightness value, color parameters, and drive current parameters. Then, interaction response parameters between the interaction trigger data and the display response data are calculated to construct an interaction response difference parameter set. Finally, LED detection and evaluation are performed based on the interaction response difference parameter set to generate interaction detection results. Through the above process, the proposed method and system achieve the technical effect of improving the accuracy of anomaly identification and the reliability of detection results. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 This is a schematic flowchart of a sensor-based interactive detection method for LED displays provided in an embodiment of this application.

[0018] Figure 2 This is a schematic diagram of the structure of a sensor-based interactive detection system for LED displays provided in an embodiment of this application.

[0019] Figure labeling: Interactive trigger data acquisition module 10, display response data acquisition module 20, interactive response difference parameter set construction module 30, LED detection and evaluation module 40. Detailed Implementation

[0020] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0021] This application provides a sensor-based interactive detection method for LED displays, such as... Figure 1 As shown, the method includes: Step S100: Collect interactive trigger data from the LED display screen using sensors, including the interaction timestamp, interaction spatial coordinates, interaction intensity parameters, and interaction type parameters.

[0022] Specifically, interaction trigger data refers to a series of core parameters sensed and recorded by sensors when a user interacts with the LED display screen, such as through touch, gestures, or proximity; interaction timestamp refers to the specific time point when the interaction occurs; interaction spatial coordinates refer to the specific location coordinates of the interaction on the LED display screen surface; interaction intensity parameters refer to the force or signal strength of the interaction, such as touch pressure, gesture amplitude, and signal strength corresponding to proximity distance; and interaction type parameters refer to the specific method of interaction, such as single-point touch, multi-point touch, swipe gesture, wave sensing, and proximity sensing.

[0023] A multi-sensor fusion acquisition scheme is adopted, with a core combination of touch sensors, infrared distance sensors, and gesture sensors. The sensors are connected to the LED display's control board via an SPI interface, transmitting the acquired data in real time. The control board has a built-in data buffer module to prevent data loss. The raw data undergoes preliminary noise reduction processing using a sliding window filtering algorithm to remove abnormal data caused by sensor malfunctions, such as sudden signal changes or noise signals during periods of no interaction. For example, in a shopping mall LED interactive screen scenario, the capacitive touch sensor collects the pressure value and touch position coordinates when the user touches the screen, the infrared sensor collects the distance when the user approaches, and the gesture sensor collects the direction of the user's swipe. All data carries a timestamp and is uniformly transmitted to the control board for buffering.

[0024] In one possible implementation, interactive trigger data from the LED display screen is collected via sensors. Step S100 further includes step S110, analyzing the parameter sensitivity of the interactive trigger data corresponding to the interactive detection target. Specifically, a parameter sensitivity analysis algorithm, such as the Sobol sensitivity analysis algorithm, is used. The judgment result of the interactive detection target, such as valid / invalid, normal / abnormal, is used as the output variable, and the various parameters of the interactive trigger data are used as input variables. The degree of influence of each input variable on the output variable is calculated, i.e., the sensitivity coefficient. The larger the sensitivity coefficient, the more significant the influence of the parameter on the detection target. The sensitivity coefficient is calculated using the controlled variable method, i.e., keeping other parameters constant and only changing one parameter, observing the change in the judgment result of the detection target. The larger the change, the higher the sensitivity coefficient. At the same time, a sensitivity coefficient threshold is preset. Parameters with a sensitivity coefficient ≥ the sensitivity coefficient threshold are marked as high-sensitivity parameters, and those < the sensitivity coefficient threshold are marked as low-sensitivity parameters. High-sensitivity parameters are calibrated with emphasis.

[0025] Step S120: Using the parameter sensitivity as an index, the sensor acquisition parameters are searched and matched to identify calibration compensation conditions and compensation targets. Specifically, a sensor acquisition parameter library is built, storing the sensor acquisition parameter ranges and calibration compensation rules corresponding to different sensitivity coefficients, such as the allowable acquisition error range and compensation formula for high-sensitivity parameters. An index search algorithm, such as a hash index algorithm, is used to quickly retrieve the corresponding acquisition parameter information in the parameter library using the sensitivity coefficient as the index key. Through a matching algorithm, such as cosine similarity matching, the currently acquired high-sensitivity parameters are matched with standard parameters in the library. When the deviation between the acquired parameters and the standard parameters exceeds a preset error range, it is determined that calibration compensation is required, and the calibration compensation conditions are identified. At the same time, the compensation target is determined, that is, to adjust the acquired parameters to the corresponding standard parameter range in the library through compensation.

[0026] Step S130: The corresponding sensor for the interactive trigger data is parameter-compensated using the calibration compensation conditions and compensation target to calibrate the interactive trigger data. Specifically, a sensor parameter compensation module sends parameter adjustment commands to the corresponding sensor according to the compensation target and compensation formula. After receiving the command, the sensor adjusts its own acquisition parameters, such as sampling gain, reference voltage, trigger threshold, etc., and re-acquires the interactive trigger data, or corrects the previously acquired raw data. After compensation, the compensated data is verified to determine whether it conforms to the standard parameter range. If not, the compensation process is repeated until the requirements are met.

[0027] Step S200: After determining the effective interaction based on the interactive trigger data, the display response data of the corresponding LED display screen is collected by the sensor. The display response data includes the display start time, the brightness value of the response area, the color parameters, and the driving current parameters.

[0028] Specifically, effective interaction determination refers to filtering out interactions based on the user's true intent through preset rules, excluding accidental touches, invalid gestures, etc.; display response data refers to the various parameters of the LED display screen when it starts to change display after receiving an interaction command; display start time refers to the specific point in time when the display screen starts to change display after receiving an interaction command; response area brightness value refers to the brightness parameter of the corresponding interactive area on the display screen; color parameters refer to the color parameters of the response area; and driving current parameters refer to the magnitude of the current driving the pixels in the response area of ​​the LED display screen to emit light.

[0029] The interactive trigger data collected in step S100 is filtered and invalid data is removed based on preset valid interaction judgment rules. Once a valid interaction is determined, the control motherboard sends acquisition commands to the brightness sensor, color sensor, and current sensor. The sensors synchronously start acquisition, and the acquired display response data is associated with the corresponding interactive trigger data via timestamps and stored in the database. For example, when a user touches the play button on the LED interactive screen, the brightness sensor acquires the brightness value of the button area, the color sensor acquires the button's color change, and the current sensor acquires the current driving the pixels in that area, records the display start time, and associates it with the interaction occurrence timestamp.

[0030] In one possible implementation, after determining a valid interaction based on the interaction trigger data, the display response data of the corresponding LED display screen is collected by sensors. Step S200 further includes step S210, determining a preset timing response observation window corresponding to the valid interaction. Specifically, for each interaction determined to be valid, a fixed time window is set to collect the display response data of the display screen within this window, ensuring that the response process of the display screen can be completely captured. The preset timing response observation window has a base duration, with the start time being the time point when the valid interaction determination is completed and the end time being the start time plus the base duration. Simultaneously, the window duration is dynamically adjusted according to different interaction types. The adjustment rules are stored in the configuration file of the control motherboard and can be modified according to the actual application scenario. A timer module is used to control the start and end times of the observation window. After the window starts, various sensors are triggered to begin collecting display response data; after the window ends, data collection stops.

[0031] Step S220: After valid interaction determination, the brightness value, color parameter, and driving current parameter of the response area are continuously sampled within the preset timing response observation window to determine the display start anchor time and the stable arrival time of each response parameter. Specifically, a continuous sampling mode is adopted, with the brightness sensor, color sensor, and current sensor continuously sampling within the observation window and storing the data in a temporary cache. A data mutation detection algorithm, such as a first-order difference algorithm, is used to identify the display start anchor time: when the difference between the sampled data at a certain moment and the sampled data at the previous moment exceeds a preset mutation threshold, and the subsequent three consecutive sampled data maintain the trend after the mutation, then that moment is the display start anchor time. A stability determination algorithm is used to identify the stable arrival time of each response parameter: when the fluctuation amplitude of 10 consecutive sampled data of a certain response parameter is ≤5%, then the time point of the 10th sample is determined as the stable arrival time of that parameter. All sampled data and determination time points are associated with the timestamp of the interaction trigger data.

[0032] Step S230: Based on the display startup anchor time and the stable arrival time of each response parameter, calculate the parameter delay difference parameter and the response consistency parameter to obtain the display response data. Specifically, the core of calculating the parameter delay difference parameter is to calculate the difference between the stable arrival time of each response parameter and the display startup anchor time, as well as the difference between the stable arrival times of different parameters. For example, brightness stabilization delay = brightness stabilization arrival time - display startup anchor time; color and brightness delay difference = color stabilization arrival time - brightness stabilization arrival time. The response consistency parameter is calculated using an analysis of variance algorithm to calculate the variance of the sampled data of each response parameter before stabilization. The smaller the variance, the smoother the response process of the parameter and the better the consistency. For example, brightness response consistency parameter = variance of brightness sampled data / brightness stable value; the smaller the ratio, the better the consistency. The calculated parameter delay difference parameter and response consistency parameter are summarized with the collected display startup time, brightness value, color parameter, and drive current parameter, organized according to a preset data format, to form complete display response data, which is then stored in the database.

[0033] Step S300: Calculate the interaction response parameters between the interaction trigger data and the display response data, and construct an interaction response difference parameter set.

[0034] Specifically, interactive response parameters refer to parameters used to describe the relationship between interactive triggering and display response, such as response time difference and display parameter deviation; the interactive response difference parameter set refers to the set of parameters with deviations among all interactive response parameters, used for anomaly localization.

[0035] A timing alignment algorithm is employed, using the interaction timestamp as a baseline to align the display startup time and calculate the difference between the two, i.e., the response time difference. A deviation calculation model is used to calculate the deviations of the response area's brightness value, color parameters, and driving current parameters from preset standard values. The calculated response time difference, brightness deviation, color deviation, and current deviation are then aggregated to form an interactive response difference parameter set. Simultaneously, a standard response threshold is preset for each response parameter; parameters exceeding the threshold in the difference parameter set are marked to initially locate potentially abnormal areas.

[0036] In one possible implementation, the interaction response parameters of the interaction trigger data and the display response data are calculated to construct an interaction response difference parameter set. Step S300 further includes step S310, which performs timing alignment processing based on the interaction occurrence timestamp and the display startup time to determine the response time difference between the interaction trigger data and the display response data. Specifically, a timing alignment algorithm, such as a linear interpolation alignment algorithm, is used to convert the interaction occurrence timestamp and the display startup time into a unified time format. The time deviation between the two is judged. If the display startup time is earlier than the interaction occurrence timestamp, it indicates that there is a time synchronization error. Linear interpolation is used to correct the display startup time to a reasonable time after the interaction occurrence timestamp, based on the synchronization delay between the sensor and the display screen. If the display startup time is later than the interaction occurrence timestamp, the difference between the two is directly calculated, which is the response time difference.

[0037] Step S320: Based on the response time difference, perform deviation analysis on the brightness value, color parameters, and driving current parameters of the response area to construct an interactive response difference parameter set including time difference parameters and display deviation parameters. Then, match and determine the interactive response difference parameter set based on the standard response threshold of each response parameter to locate preliminary abnormal areas. Specifically, the time difference parameter refers to the time deviation between the interaction and the display startup; the display deviation parameter refers to the deviation between the display response data and the standard value. Preset standard values ​​and standard response thresholds for each response parameter, and use a deviation analysis algorithm to calculate the deviation between the actual value and the standard value of each parameter. Summarize the response time difference, brightness deviation, color deviation, and current deviation to form the interactive response difference parameter set. Use a threshold matching algorithm to compare each parameter in the difference parameter set with the corresponding standard response threshold. If one or more parameters exceed the threshold, the display screen response area corresponding to the interaction is marked as a preliminary abnormal area. Simultaneously, record the specific value of the abnormal parameter and the extent to which it exceeds the threshold to provide a basis for accurate anomaly determination.

[0038] Step S400: Perform LED detection and evaluation based on the interactive response difference parameter set to generate interactive detection results.

[0039] Specifically, LED testing and evaluation refers to comprehensively scoring the response performance and health status of a display screen based on a set of interactive response difference parameters and preset standards. Each parameter in the interactive response difference parameter set is compared with a preset health benchmark response model, and the degree of deviation of each parameter is calculated using a deviation ratio formula. Combined with the regional neighborhood consistency parameter of the initial abnormal area (i.e., whether the response parameters of the surrounding areas of the abnormal area are normal), the response area is judged as abnormal. A preset threshold for the number of consecutive abnormalities is set, such as 3 times. When the response parameters of the same area exceed the corresponding preset threshold for 3 consecutive times, the area is marked as an abnormal area. The frequency of abnormality occurrence in each abnormal area is statistically analyzed, different abnormality types are preset with weights, and a module health score is calculated using a health scoring formula. Based on the health score, the module health status is output, and specific abnormality warning information is generated for abnormal areas and abnormality types.

[0040] In one possible implementation, LED detection and evaluation are performed based on the interactive response difference parameter set to generate interactive detection results. Step S400 further includes step S410, comparing each response difference parameter in the interactive response difference parameter set with a preset health benchmark response model to determine the degree of deviation of each response parameter relative to the model benchmark. The degree of deviation includes the degree of time deviation and the degree of display parameter deviation. Specifically, the preset health benchmark response model is a standard model established based on a large amount of interactive response data of LED displays under normal conditions, using a data fitting algorithm such as the least squares method. The model includes the standard range, standard deviation, and standard change trend of each response parameter for comparison and judgment of anomalies. The degree of deviation refers to the percentage difference between the actual response parameter and the benchmark model parameter, and is divided into the degree of time deviation and the degree of display parameter deviation. A comparison algorithm, such as the Euclidean distance comparison algorithm, is used to compare each parameter in the interactive response difference parameter set with the corresponding benchmark parameter in the model, calculating the degree of deviation: Time deviation = (Actual response time difference - Model standard response time difference) / Model standard response time difference × 100% (absolute value); Display parameter deviation = (Actual display deviation - Model standard display deviation) / Model standard display deviation range × 100% (absolute value). The deviation range is 0%-100%, with larger values ​​indicating more severe deviation from the benchmark. After comparison, a deviation report is generated, specifying the deviation type and specific value for each parameter.

[0041] Step S420: Based on the deviation degree and the regional neighborhood consistency parameter of the initial abnormal region, anomaly determination is performed on the response region. Specifically, when the response parameters of the same region exceed the corresponding preset threshold for a preset number of consecutive times, the region is marked as an abnormal region. The calculation method for the regional neighborhood consistency parameter is as follows: Select a 3×3 grid region surrounding the initial abnormal region, totaling 9 regions, including the initial abnormal region. Calculate the variance of the deviation degree of all response parameters within this grid region. The smaller the variance, the more consistent the response parameters of the neighboring regions, and the more likely the anomaly of the initial abnormal region is a genuine anomaly. Preset deviation degree thresholds and neighborhood consistency thresholds are used. When the parameter deviation degree of a region is ≥ the preset deviation degree threshold, and its neighborhood consistency parameter is ≤ the neighborhood consistency threshold, it is further determined whether the region meets the continuous anomaly condition. A preset threshold for the number of consecutive anomalies is set, such as 3 times. By querying the historical interaction response data of the region in the database, the number of times the parameter deviation exceeds the threshold is counted. When the number of consecutive occurrences is ≥ 3, the region is officially marked as an abnormal region. If the deviation is less than the preset deviation threshold, or the neighborhood consistency parameter is greater than the neighborhood consistency threshold, then it is determined to be a non-abnormal region and the initial abnormality label is removed.

[0042] Step S430: Statistically calculate the frequency of anomalies in each abnormal area and, based on preset anomaly weights, calculate the health score of the corresponding LED display module. Output the module's health status and anomaly warning information as the interaction detection result based on the health score. Specifically, a statistical time period is set, and the total number of interactions and the number of abnormal interactions in each abnormal area within that time period are queried from the database. The anomaly frequency = (number of abnormal interactions / total number of interactions) × 100%. Preset weights for different anomaly types. If multiple anomaly types exist in a certain abnormal area, the anomaly type with the highest weight is used for calculation, or a weighted average anomaly frequency is calculated: Weighted average anomaly frequency = Σ(frequency of a certain anomaly type × corresponding weight). The health score is calculated using a deduction system, with a base score of 100 points. Health score = 100 - (weighted average anomaly frequency × 100). Preset health score levels: ≥80 points are normal, 60-79 points are slightly abnormal, and <60 points are severely abnormal. Based on the health score, the module's health status is determined. Combined with the location, anomaly type, and anomaly frequency of the abnormal area, specific anomaly warning information is generated and output to the monitoring terminal through the display control interface.

[0043] In one possible implementation, before comparing with a preset health benchmark response model, step S410 further includes step S411, which involves parsing the target sensing parameters based on the mapping relationship between the display detection target and the interactive response parameters. Specifically, according to the LED display target to be detected, such as response speed detection, display consistency detection, module stability detection, etc., sensing parameters directly related to the detection target and needed to establish a health benchmark are selected from the existing interactive response parameters. These parameters are the target sensing parameters. A mapping table between the detection target and the interactive response parameters is pre-configured in the display control motherboard. For example, response speed detection corresponds to response time difference and parameter delay difference parameters; display effect detection corresponds to deviations in brightness value, color parameters, and drive current parameters; and stability detection corresponds to response consistency parameters. The control motherboard reads the mapping table according to the currently configured detection target, extracts the corresponding parameters from the interactive trigger data and display response data as target sensing parameters, and filters out parameters irrelevant to the current detection target, retaining only the valid parameters used for modeling.

[0044] Step S412: Calculate the response characteristic value based on the response correlation between the target sensing parameters and the interaction trigger parameters. Specifically, analyze how the target sensing parameters change with the interaction trigger parameters, quantifying this correspondence into a numerical value that can be used for modeling, i.e., the response characteristic value. The control motherboard reads the interaction trigger parameters and target sensing parameters under the same set of interactive events. Using multiple sets of normal interaction samples, statistically analyze the changes in target sensing parameters with interaction intensity, interaction spatial coordinates, and interaction type. Use moving average and normalization processing to unify parameters of different magnitudes into the same numerical range, and then obtain the response characteristic value through weighted summation. This characteristic value represents the normal response level that the display screen should theoretically present under the current interaction conditions. For example, the greater the interaction intensity, the faster the brightness rises and the more stable the driving current under normal circumstances. Weighted calculation of the changing trends of these parameters yields a set of response characteristic values ​​that can represent the normal response level.

[0045] Step S413: Based on the detection constraints of the target LED display screen, the response feature values ​​are screened and normalized to establish the preset health benchmark response model. Specifically, according to the actual detection requirements of the display screen, such as the maximum allowable delay, minimum brightness consistency, and maximum current fluctuation, the response feature values ​​are filtered and standardized to form a preset health benchmark response model that can be directly used for subsequent comparisons. First, feature value screening conditions are set according to the detection constraints, such as retaining only response feature values ​​with response time within the normal range, brightness fluctuation less than a set value, and no sudden current changes. The screened feature values ​​are normalized to their maximum and minimum values ​​so that all feature values ​​fall within a unified range. Then, multiple sets of samples under normal working conditions are used for fitting to form a health benchmark response model that includes a standard response time range, a standard brightness change range, a standard drive current range, and a standard response consistency range. The model is then stored in the storage area of ​​the display screen control motherboard for real-time comparison.

[0046] In one possible implementation, based on the response correlation between the target sensing parameters and the interactive triggering parameters, response feature values ​​are calculated. Step S412 further includes step S4121, which, based on the response correlation between the target sensing parameters and the interactive triggering parameters, performs feature change time window, response linkage range, and range fluctuation relationship constraint analysis on the response feature values ​​to generate response time window features, response range features, and range fluctuation features, thus obtaining response relationship constraint features. Specifically, constraint analysis is performed on the change law of response feature values ​​from three dimensions: time, spatial region, and parameter fluctuation, resulting in three types of constraint features that together constitute the response relationship constraint features. In continuous multi-frame interactive response data, a fixed-length feature change time window is set, and the change rate and number of changes of response feature values ​​within each time window are statistically analyzed to form response time window features. The response linkage area on the display screen is determined based on the interactive spatial coordinates, and the distribution range of feature values ​​within this area is statistically analyzed to form response range features. The fluctuation magnitude of feature values ​​within the linkage range is calculated to form range fluctuation features. These three types of features are combined to obtain response relationship constraint features that can constrain normal response behavior, used to determine whether the response conforms to normal patterns.

[0047] Step S4122: The response feature values ​​are constrained and marked based on the response relationship constraint features. Specifically, each response feature value is marked using the response relationship constraint features to indicate whether it falls within the normal constraint range, facilitating rapid differentiation between normal and abnormal features. The control board compares the currently calculated response feature value with the time variation range, spatial distribution range, and allowable fluctuation range specified in the response relationship constraint features. If all are within the constraint range, it is marked as a compliant feature; if any one exceeds the constraint range, it is marked as a feature to be verified. The marking results are stored in conjunction with the response feature values ​​and are directly used when entering the health benchmark model comparison stage, without repeated analysis of the constraint conditions.

[0048] In one possible implementation, the response feature values ​​are constrained based on the response relationship constraint features. Step S4122 further includes step S41221, which, based on the response relationship constraint features, performs statistical analysis on the mean, variance, and variation amplitude of the response feature values ​​within a preset time window to generate time stability features. Specifically, over a continuous period of time, the average level, dispersion, and variation magnitude of the response feature values ​​are statistically analyzed to form time stability features used to determine whether the response is stable. Taking all response feature values ​​within the preset time window as objects, their arithmetic mean is calculated to reflect the overall response level; the variance is calculated to reflect the dispersion of the response; and the difference between the maximum and minimum values ​​is calculated to reflect the variation amplitude. The mean, variance, and variation amplitude are combined to form the time stability features. The smaller the variance and the smaller the variation amplitude, the more stable the display screen's response is in the time dimension.

[0049] Step S41222: Based on a preset response correlation interval, perform range consistency analysis on the response feature values ​​to generate interval convergence features and fluctuation trend features. Specifically, determine whether the response feature values ​​are concentrated within a normal range, and determine whether their overall trend is stable, rising, or falling, thus forming interval convergence features and fluctuation trend features. A preset response correlation interval is set according to the health benchmark, and the proportion of response feature values ​​falling within this interval is counted to obtain the interval convergence feature; a higher proportion indicates better consistency. The response feature values ​​within the time window are judged chronologically to determine whether the feature values ​​are generally stable, gradually increasing, or gradually decreasing, thus forming fluctuation trend features. Only features with high convergence and stable trends are considered normal features that meet the health benchmark.

[0050] Step S41223 involves performing feature quantization and standardization on the time stability features, interval convergence features, and fluctuation trend features to obtain a response relationship constraint feature vector. This response relationship constraint feature vector is then used as a constraint marker and appended to the response feature values. Specifically, the time stability features, interval convergence features, and fluctuation trend features are quantized according to preset levels and then standardized by uniformly scaling them to the same numerical range, forming a set of ordered numerical response relationship constraint feature vectors. This vector is combined with the response feature values ​​and stored as a constraint marker for the current response. When comparing with a health baseline response model, this vector is directly used for similarity calculation to quickly determine whether the response deviates from the normal state.

[0051] In one possible implementation, after marking the response area as an abnormal area, step S420 further includes step S421, which performs spatial clustering analysis on the abnormal area. When multiple adjacent display areas have the same type of difference parameter anomaly within a preset time window, an abnormal cluster is established. Specifically, the control motherboard divides the LED screen into continuous grid areas based on interactive spatial coordinates. Within the preset time window, all preliminary abnormal areas are traversed to determine whether the abnormal areas are adjacent and whether the anomaly types are the same, such as both being low brightness or both being excessively long response delay. If they are adjacent and of the same type, these areas are merged into an abnormal cluster, and the coverage area, anomaly type, and occurrence time of the abnormal cluster are recorded.

[0052] Step S422: When the number of regions in the abnormal cluster exceeds a preset coverage ratio, it is determined to be a system-level abnormality. Specifically, a threshold ratio of the number of abnormal cluster regions to the total number of display regions is preset. When the proportion of regions contained in the abnormal cluster exceeds this threshold, it is directly determined to be a system-level abnormality, such as an overall driver board output abnormality, sensor synchronization abnormality, or main control program timing abnormality, and is no longer treated as an individual module abnormality.

[0053] Step S423: When the abnormal cluster is limited to a single module or the number of adjacent areas is less than a preset threshold, it is determined to be a local module abnormality. Specifically, when the abnormal cluster falls only within the physical range of a single LED display module, or when the number of adjacent areas contained in the abnormal cluster is less than a preset threshold, it is determined to be a local module abnormality, such as problems with the LED beads, driver chip, or circuitry of that module. The control motherboard locates the specific physical module based on the coordinates of the abnormal area, records the module number, abnormality type, and abnormality severity, and uses this information for health scoring and early warning output.

[0054] This application embodiment uses sensors to collect interactive trigger data from an LED display screen, including interaction timestamps, spatial coordinates, intensity, and type parameters. It then performs effective interaction determination on the interactive trigger data. Upon successful determination, it collects display response data from the display screen, including display start-up time, response area brightness, color, and drive current parameters. It calculates the interaction response parameters between the interactive trigger data and the display response data, constructs an interaction response difference parameter set, and uses this parameter set to detect and evaluate the LED display screen, generating corresponding interaction detection results. These technical means solve the technical problem of poor reliability in existing LED display screen interaction detection, achieving the technical effect of improving the accuracy of anomaly identification and the reliability of detection results.

[0055] In the above text, refer to Figure 1 A sensor-based interactive detection method for LED displays according to embodiments of the present invention has been described in detail. Next, reference will be made to... Figure 2 A sensor-based interactive detection system for LED displays according to an embodiment of the present invention is described.

[0056] The sensor-based interactive LED display screen detection system according to embodiments of the present invention addresses the technical problem of poor reliability in anomaly detection in existing LED display screen interactive detection systems, thereby improving the accuracy of anomaly identification and the reliability of detection results. The sensor-based interactive LED display screen detection system includes: an interactive trigger data acquisition module 10, a display response data acquisition module 20, an interactive response difference parameter set construction module 30, and an LED detection and evaluation module 40.

[0057] The interactive trigger data acquisition module 10 is used to acquire interactive trigger data of the LED display screen through sensors, including interactive timestamp, interactive spatial coordinates, interactive intensity parameters, and interactive type parameters; the display response data acquisition module 20 is used to acquire display response data of the corresponding LED display screen through sensors after determining the effective interaction based on the interactive trigger data, the display response data including display start time, response area brightness value, color parameters, and driving current parameters; the interactive response difference parameter set construction module 30 is used to calculate the interactive response parameters of the interactive trigger data and the display response data, and construct an interactive response difference parameter set; the LED detection and evaluation module 40 is used to perform LED detection and evaluation based on the interactive response difference parameter set and generate interactive detection results.

[0058] The detailed description of the specific configuration of the interactive response difference parameter set construction module 30 is as follows: As mentioned above, the interactive response parameters of the interactive trigger data and the display response data are calculated to construct an interactive response difference parameter set. The interactive response difference parameter set construction module 30 may further include: a timing alignment processing unit used to perform timing alignment processing based on the interaction occurrence timestamp and the display start time to determine the response time difference between the interactive trigger data and the display response data; and a deviation analysis unit used to perform deviation analysis on the brightness value, color parameters, and driving current parameters of the response area based on the response time difference to construct an interactive response difference parameter set including time difference parameters and display deviation parameters, and to match and determine the interactive response difference parameter set based on the standard response threshold of each response parameter to locate the initial abnormal area.

[0059] The detailed description of the specific configuration of the LED detection and evaluation module 40 is explained as follows: As mentioned above, the LED detection and evaluation module 40 generates interactive detection results based on the interactive response difference parameter set. The LED detection and evaluation module 40 may further include: a deviation degree comparison unit for comparing each response difference parameter in the interactive response difference parameter set with a preset health benchmark response model to determine the deviation degree of each response parameter relative to the model benchmark, wherein the deviation degree includes the time deviation degree and the display parameter deviation degree; an anomaly determination unit for determining an anomaly of the response area based on the deviation degree and the regional neighborhood consistency parameter of the preliminary anomaly area, wherein when the response parameters of the same area exceed the corresponding preset threshold for a preset number of consecutive times, the area is marked as an anomaly area; and a health score calculation unit for statistically analyzing the anomaly occurrence frequency of each anomaly area and, in combination with a preset anomaly weight, calculating the health score of the corresponding LED display module, and outputting the module health status and anomaly warning information as the interactive detection result based on the health score.

[0060] Before comparing with the preset health benchmark response model, the deviation comparison unit may further include: a target sensing parameter parsing subunit for parsing target sensing parameters based on the mapping relationship between the target detected by the display screen and the interactive response parameters; a response feature value calculation subunit for calculating response feature values ​​based on the response correlation between the target sensing parameters and the interactive trigger parameters; and a preset health benchmark response model establishment subunit for filtering and normalizing the response feature values ​​based on the detection constraint target of the target LED display screen to establish the preset health benchmark response model.

[0061] Specifically, based on the response correlation between the target sensing parameters and the interactive triggering parameters, a response feature value is calculated. The response feature value calculation subunit may further include: a constraint analysis component used to perform constraint analysis on the response feature value based on the response correlation between the target sensing parameters and the interactive triggering parameters, including feature change time window, response linkage range, and range fluctuation relationship, to generate response time window features, response range features, and range fluctuation features, thereby obtaining response relationship constraint features; and a constraint marking component used to mark the response feature value based on the response relationship constraint features.

[0062] Specifically, the constraint labeling component for the response feature values ​​based on the response relationship constraint features may further include: a statistical sub-component for performing mean, variance, and variation amplitude statistics on the response feature values ​​within a preset time window based on the response relationship constraint features, generating time stability features; a range consistency analysis sub-component for performing range consistency analysis on the response feature values ​​based on a preset response correlation interval, generating interval convergence features and fluctuation trend features; and a feature quantization sub-component for performing feature quantization and standardization processing on the time stability features, interval convergence features, and fluctuation trend features to obtain a response relationship constraint feature vector, which is then appended to the response feature values ​​as constraint labels.

[0063] After marking the response area as an abnormal area, the anomaly determination unit may further include: a spatial clustering analysis subunit for performing spatial clustering analysis on the abnormal area, and establishing an anomaly cluster when multiple adjacent display areas have the same type of difference parameter anomaly within a preset time window; a system-level anomaly determination subunit for determining a system-level anomaly when the number of areas in the anomaly cluster exceeds a preset coverage ratio; and a local module anomaly determination subunit for determining a local module anomaly when the anomaly cluster is limited to a single module or the number of adjacent areas is less than a preset threshold.

[0064] The detailed description of the specific configuration of the interactive trigger data acquisition module 10 is explained as follows: As mentioned above, the interactive trigger data acquisition module 10 acquires interactive trigger data from the LED display screen through sensors. The interactive trigger data acquisition module 10 may further include: a parameter sensitivity analysis unit for analyzing the parameter sensitivity of the interactive trigger data corresponding to the interactive detection target; a search and matching unit for searching and matching the sensor acquisition parameters using the parameter sensitivity as an index, and identifying calibration compensation conditions and compensation targets; and a calibration unit for using the calibration compensation conditions and compensation targets to perform parameter compensation on the corresponding sensor of the interactive trigger data for calibrating the interactive trigger data.

[0065] The detailed description of the specific configuration of the display response data acquisition module 20 is explained as follows: As mentioned above, after determining the effective interaction based on the interactive trigger data, the display response data of the corresponding LED display screen is acquired through sensors. The display response data acquisition module 20 may further include: a preset timing response observation window determination unit for determining the preset timing response observation window corresponding to the effective interaction; a continuous sampling unit for continuously sampling the brightness value, color parameters, and driving current parameters of the response area within the preset timing response observation window after determining the effective interaction, to determine the display start-up anchor time and the stable arrival time of each response parameter; and a parameter calculation unit for calculating the parameter delay difference parameter and the response consistency parameter based on the display start-up anchor time and the stable arrival time of each response parameter, to obtain the display response data.

[0066] The sensor-based LED display interactive detection system provided in this embodiment of the invention can execute the sensor-based LED display interactive detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0067] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0068] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A sensor-based interactive detection method for LED displays, characterized in that, include: The system collects interactive trigger data from the LED display screen using sensors, including the timestamp of the interaction, the spatial coordinates of the interaction, the interaction intensity parameter, and the interaction type parameter. After determining the effective interaction based on the interactive trigger data, the corresponding LED display screen is collected by the sensor. The display response data includes the display start time, the brightness value of the response area, the color parameters, and the driving current parameters. Calculate the interaction response parameters between the interaction trigger data and the display response data, and construct an interaction response difference parameter set; LED detection and evaluation are performed based on the set of interactive response difference parameters to generate interactive detection results.

2. The sensor-based interactive detection method for LED displays according to claim 1, characterized in that, Calculate the interaction response parameters between the interaction trigger data and the display response data, and construct an interaction response difference parameter set, including: Based on the interaction occurrence timestamp and the display start time, timing alignment processing is performed to determine the response time difference between the interaction trigger data and the display response data; Based on the response time difference, deviation analysis is performed on the brightness value, color parameters, and driving current parameters of the response area to construct an interactive response difference parameter set including time difference parameters and display deviation parameters. The interactive response difference parameter set is then matched and judged based on the standard response threshold of each response parameter to locate the initial abnormal area.

3. The sensor-based interactive detection method for LED displays according to claim 2, characterized in that, LED detection and evaluation are performed based on the set of interactive response difference parameters to generate interactive detection results, including: Each response difference parameter in the interactive response difference parameter set is compared with a preset health benchmark response model to determine the degree of deviation of each response parameter relative to the model benchmark. The degree of deviation includes the degree of time deviation and the degree of display parameter deviation. Based on the degree of deviation and the regional neighborhood consistency parameter of the preliminary abnormal region, the response region is determined to be abnormal. When the response parameter of the same region exceeds the corresponding preset threshold for a preset number of consecutive preset times, the region is marked as an abnormal region. The frequency of anomalies in each abnormal area is statistically analyzed, and combined with the preset anomaly weight, the health score of the corresponding LED display module is calculated. Based on the health score, the module's health status and anomaly warning information are output as interactive detection results.

4. The sensor-based interactive detection method for LED displays according to claim 3, characterized in that, Before comparing with a preset health baseline response model, the following is included: Based on the mapping relationship between the target detected by the display screen and the interactive response parameters, the target sensing parameters are analyzed; Calculate the response characteristic value based on the response correlation between the target sensing parameters and the interaction trigger parameters; Based on the detection constraints of the target LED display screen, the response feature values ​​are filtered and normalized to establish the preset health benchmark response model.

5. The sensor-based interactive detection method for LED displays according to claim 4, characterized in that, Based on the response correlation between the target sensing parameters and the interaction trigger parameters, response feature values ​​are calculated, including: Based on the response correlation between the target sensing parameters and the interactive triggering parameters, the response feature values ​​are subjected to feature change time window, response linkage range and range fluctuation relationship constraint analysis to generate response time window features, response range features and range fluctuation features, and obtain response relationship constraint features. The response feature values ​​are constrained and labeled based on the response relationship constraint features.

6. The sensor-based interactive detection method for LED displays according to claim 5, characterized in that, Constraint labeling of the response feature values ​​based on the response relationship constraint features includes: Based on the aforementioned response relationship constraint features, the mean, variance, and magnitude of change of the response feature values ​​are statistically analyzed within a preset time window to generate time stability features. Based on a preset response correlation interval, range consistency analysis is performed on the response feature values ​​to generate interval convergence features and fluctuation trend features. The time stability feature, interval convergence feature, and fluctuation trend feature are subjected to feature quantization and standardization to obtain the response relationship constraint feature vector. The response relationship constraint feature vector is then used as a constraint label and appended to the response feature value.

7. The sensor-based interactive detection method for LED displays according to claim 3, characterized in that, After marking the response region as an anomalous region, the following is also included: Spatial clustering analysis is performed on the abnormal regions. When multiple adjacent display regions have the same type of abnormal difference parameters within a preset time window, an abnormal cluster is established. When the number of regions of the abnormal cluster exceeds a preset coverage ratio, it is determined to be a system-level abnormality; When the abnormal cluster is limited to a single module or the number of adjacent regions is less than a preset threshold, it is determined to be a local module abnormality.

8. The sensor-based interactive detection method for LED displays according to claim 1, characterized in that, Interactive trigger data for the LED display screen is collected via sensors, including: Analyze the parameter sensitivity of the interaction trigger data corresponding to the interaction detection target; Using the parameter sensitivity as an index, the sensor-acquired parameters are searched and matched to identify calibration compensation conditions and compensation targets; The parameters of the corresponding sensor for the interactive trigger data are compensated using the calibration compensation conditions and compensation targets to calibrate the interactive trigger data.

9. The sensor-based interactive detection method for LED displays according to claim 1, characterized in that, After determining a valid interaction based on the aforementioned interactive trigger data, the display response data of the corresponding LED display screen is collected via sensors, including: Determine the preset timing response observation window corresponding to the effective interaction; After valid interaction determination, the brightness value, color parameter and driving current parameter of the response area are continuously sampled in the preset timing response observation window to determine the display start anchor point time and the stable arrival time of each response parameter. Based on the display startup anchor time and the stable arrival time of each response parameter, the parameter delay difference parameter and the response consistency parameter are calculated to obtain the display response data.

10. A sensor-based interactive detection system for LED displays, characterized in that, The system is used to implement the sensor-based interactive detection method for LED displays according to any one of claims 1-9, the system comprising: The interactive trigger data acquisition module is used to collect interactive trigger data of the LED display screen through sensors, including the interaction timestamp, interaction spatial coordinates, interaction intensity parameters, and interaction type parameters. The display response data acquisition module is used to acquire the display response data of the corresponding LED display screen through sensors after determining the effective interaction based on the interactive trigger data. The display response data includes display start time, response area brightness value, color parameters and driving current parameters. An interactive response difference parameter set construction module is used to calculate the interactive response parameters between the interactive trigger data and the display response data, and to construct an interactive response difference parameter set. The LED detection and evaluation module is used to perform LED detection and evaluation based on the interactive response difference parameter set and generate interactive detection results.

Images