Performance optimization method and system for organic electroluminescent device

Abstract

The invention relates to the technical field of organic electroluminescent devices, and discloses a performance optimization method and system for an organic electroluminescent device, and the method comprises the steps: obtaining and analyzing a historical similar work log of a to-be-optimized organic electroluminescent device, and constructing a historical performance evaluation value change curve according to an analysis result; performing attention node marking and data analysis on the historical performance sub evaluation value change curve to obtain corresponding historical performance characterization data, setting a plurality of preset data intervals of the historical performance characterization data, and configuring corresponding preset performance coefficients; the method comprises the following steps: acquiring real-time performance characterization data of a to-be-optimized organic light-emitting device, calculating a corresponding real-time comprehensive performance coefficient, judging whether performance optimization is carried out or not according to the real-time comprehensive performance coefficient, and if yes, screening out to-be-optimized data and generating a performance optimization instruction, thereby improving data monitoring and analysis accuracy, reducing data processing amount, and improving the performance optimization efficiency of the to-be-optimized organic light-emitting device. The performance evaluation accuracy is ensured, and the performance optimization efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of organic electroluminescent devices, and particularly to a method and system for optimizing the performance of organic electroluminescent devices. Background Art

[0002] Organic electroluminescent devices are a type of devices that generate light through current driving and are widely used in the field of modern display technology. As an advanced display technology, organic electroluminescent devices are not only welcomed by the market due to their excellent display performance, but also face the challenges of continuous technological innovation and industrial upgrading. With the development of future technologies and the expansion of applications, organic electroluminescent devices are expected to demonstrate their unique value in more fields.

[0003] In the prior art, the performance optimization methods of organic electroluminescent devices mostly rely on real-time monitoring of device states to achieve performance evaluation. However, due to a large amount of monitoring data and processing volume, the accuracy of performance evaluation is reduced, resulting in poor performance optimization effects. Therefore, how to improve the accuracy of data monitoring, analysis, and performance evaluation is a technical problem to be solved at present. Summary of the Invention

[0004] To solve the above technical problems, the present application provides a method and system for optimizing the performance of organic electroluminescent devices. By determining the historical performance characterization data of the organic electroluminescent device to be optimized and corresponding several preset data intervals, and configuring corresponding preset performance coefficients for each preset data interval, a real-time comprehensive performance coefficient is obtained, which improves the accuracy of data monitoring and analysis, reduces the data processing volume, ensures the accuracy of performance evaluation, and improves the performance optimization efficiency.

[0005] In some embodiments of the present application, a method for optimizing the performance of an organic electroluminescent device is provided, including: Obtaining the basic information of the organic electroluminescent device to be optimized, screening out historical similar working logs according to the basic information and analyzing them, and constructing a change curve of historical performance sub-evaluation values of several preset performance indicators according to the analysis results; Marking attention nodes and performing data analysis on the change curve of historical performance sub-evaluation values, determining corresponding historical performance characterization data according to the marking results and analysis results, setting several preset data intervals for the historical performance characterization data, and configuring corresponding preset performance coefficients for each preset data interval; Obtaining the real-time performance characterization data of the organic electroluminescent device to be optimized, calculating the corresponding real-time comprehensive performance coefficient, and judging whether to perform performance optimization according to the real-time comprehensive performance coefficient. If so, screening out the data to be optimized and generating a performance optimization instruction.

[0006] In some embodiments of the present application, historical performance sub-evaluation value change curves of a number of preset performance indicators are constructed according to the analysis results, including: The basic information is divided into its own information and preset working information, and a number of similar organic electroluminescent devices are selected based on the own information of the organic electroluminescent device to be optimized currently; Obtain the historical work logs of the similar organic electroluminescent devices, extract the historical work information in the historical work logs, and analyze the historical work information and the preset working information to obtain the similarity; Set the historical work logs corresponding to the historical work information with a similarity greater than the preset similarity threshold as historical similar work logs; Analyze the historical similar work logs to obtain the historical working hours of each historical similar work log, establish a time reference line according to the historical working hours, and set analysis nodes at preset time intervals; Based on each analysis node, generate historical performance sub-evaluation values of a number of preset performance indicators of the corresponding similar organic electroluminescent devices, and map them to the corresponding time reference line to obtain historical performance sub-evaluation value change curves of a number of preset performance indicators.

[0007] In some embodiments of the present application, corresponding historical performance characterization data is determined according to the marking result and the analysis result, including: Pre-set a number of performance sub-evaluation value intervals for each preset performance indicator, and the performance sub-evaluation value intervals include abnormal performance sub-evaluation value intervals, suspected abnormal performance sub-evaluation intervals, general performance sub-evaluation intervals, and good performance sub-evaluation value intervals; Analyze the historical performance sub-evaluation value change curves of each preset performance indicator of each historical similar work log to obtain the performance sub-evaluation value interval where the historical performance sub-evaluation value is located at each analysis node in the historical performance sub-evaluation value change curve, and map the corresponding marking labels, and the marking labels include abnormal labels, suspected abnormal labels, general labels, and good labels; According to the marking labels at each analysis node in the historical performance sub-evaluation value change curve of each preset performance indicator, divide the corresponding historical performance sub-evaluation value change curve to obtain the first segmented curve segment, the second segmented curve segment, the third segmented curve segment, and the fourth segmented curve segment of each historical performance sub-evaluation change curve; Collect the historical monitoring data of the similar organic electroluminescent devices in the corresponding historical similar work logs according to each analysis node in the first segmented curve segment, the second segmented curve segment, the third segmented curve segment, and the fourth segmented curve segment, and map them into the corresponding curve segments to obtain the first segmented curve segment - data analysis diagram, the second segmented curve segment - data analysis diagram, the third segmented curve segment - data analysis diagram, and the fourth segmented curve segment - data analysis diagram; Perform data analysis on the data analysis diagrams of the first segmentation curve segment, the second segmentation curve segment, the third segmentation curve segment, and the fourth segmentation curve segment, and determine the historical performance characterization data of each preset performance indicator according to the analysis results.

[0008] In some embodiments of the present application, determining the historical performance characterization data of each preset performance indicator according to the analysis results includes: Based on the same marked label comparison principle, perform data correlation analysis on the data analysis diagrams of the first segmentation curve segment, the second segmentation curve segment, the third segmentation curve segment, and the fourth segmentation curve segment of the same preset performance indicator in different historical similar working logs, and obtain several first correlation monitoring data groups, several second correlation monitoring data groups, several third correlation monitoring data groups, and several fourth correlation monitoring data groups of the same preset performance indicator; Among them, each correlation monitoring data group includes several historical correlation monitoring data, and each historical correlation monitoring data is mapped with a corresponding correlation coefficient; Generate the first performance characterization coefficient of the corresponding historical correlation monitoring data according to the occurrence proportion of the same historical correlation monitoring data and the corresponding correlation coefficient; Perform data comparison analysis on the data analysis diagrams of the first segmentation curve segment, the second segmentation curve segment, the third segmentation curve segment, and the fourth segmentation curve segment of the same preset performance indicator in the same historical similar working log, and obtain the intersection proportion of the historical data intervals where the same historical monitoring data is located in different segmentation curve segments; Set the historical monitoring data with the intersection proportion less than the corresponding preset intersection proportion threshold as historical comparison monitoring data, and construct several data difference groups according to the historical comparison monitoring data, where the number of the data difference groups is 6; Generate the second performance characterization coefficient of the corresponding historical comparison monitoring data according to the difference between the intersection proportion of the same historical comparison monitoring data in different data difference groups and the corresponding preset intersection proportion threshold; Determine the historical performance characterization data of each preset performance indicator according to the first performance characterization coefficient and the second performance characterization coefficient.

[0009] In some embodiments of the present application, determining the historical performance characterization data of each preset performance indicator according to the first performance characterization coefficient and the second performance characterization coefficient includes: The calculation formula of the first performance characterization coefficient is: ; Among them, B1 is the first performance characterization coefficient, and b1 is the first performance characterization conversion coefficient. is the occurrence proportion of historical relevant monitoring data in the x-th relevant monitoring data group. is the occurrence times of historical relevant monitoring data in the x-th relevant monitoring data group. is the total number of groups of historical relevant monitoring data in the x-th relevant monitoring data group, and ax is the weight coefficient of the x-th relevant monitoring data group. is the i-th correlation coefficient of historical relevant monitoring data in the x-th relevant monitoring data group. The calculation formula of the second performance characterization coefficient is: ; Among them, B2 is the second performance characterization coefficient, b3 is the third performance characterization conversion coefficient, and w is the total number of historical similar work logs. is the interval intersection proportion of historical comparison monitoring data in the s-th data difference group of the c-th historical similar work log. is the preset interval intersection proportion threshold of the s-th data difference group, and ds is the weight coefficient of the s-th data difference group. When the historical relevant monitoring data and the historical comparison monitoring data are the same data, the final performance characterization coefficient of the corresponding data is generated according to the first performance characterization coefficient and the second performance characterization coefficient. When the historical relevant monitoring data and the historical comparison monitoring data are not the same data, the first performance characterization coefficient or the second performance characterization coefficient is set as the final performance characterization coefficient of the corresponding data. Pre-performance characterization coefficient threshold; When the final performance characterization coefficient is greater than the performance characterization coefficient threshold, the corresponding data is set as historical performance characterization data.

[0010] In some embodiments of the present application, a number of preset data intervals of historical performance characterization data are set, and corresponding preset performance coefficients are configured for each preset data interval, including: Perform probability analysis on the interval intersection part of the historical performance characterization data in the historical data intervals in different marker tags, and re-divide the interval intersection part according to the probability analysis result to obtain a number of preset data intervals of the historical performance characterization data. Map the preset data intervals to the corresponding marker tags to obtain the marker tags mapped by each preset data interval. Based on the marker tag - performance coefficient mapping table, select the preset performance coefficients of the corresponding preset data intervals. Generate the preset performance coefficients of the corresponding preset data intervals according to the final performance characterization coefficient corresponding to the historical performance characterization data and the initial performance coefficients corresponding to each preset data interval.

[0011] In some embodiments of the present application, calculating the corresponding real-time comprehensive performance coefficient includes: Obtaining the real-time performance characterization data of the organic electroluminescent device to be optimized, and selecting the real-time performance coefficient according to the preset data interval where the real-time performance characterization data is located; Classifying the real-time performance characterization data according to the corresponding preset performance indicators, and generating the real-time performance sub-coefficient corresponding to the preset performance indicator by using the final performance characterization coefficient and the real-time performance coefficient corresponding to the real-time performance characterization data of the same preset performance indicator; Generating the real-time comprehensive performance coefficient of the organic electroluminescent device to be optimized according to the real-time performance sub-coefficients of multiple preset performance indicators and the weight coefficients corresponding to the preset performance indicators.

[0012] In some embodiments of the present application, judging whether to perform performance optimization according to the real-time comprehensive performance coefficient. If so, screening out the data to be optimized and generating a performance optimization instruction, including: Presetting a performance coefficient threshold and a performance sub-coefficient threshold for each preset performance indicator; If the real-time comprehensive performance coefficient is greater than the performance coefficient threshold, no performance optimization is performed; If the real-time comprehensive performance coefficient is less than the performance coefficient threshold, comparing the real-time performance sub-coefficient of each preset performance indicator with the corresponding performance sub-coefficient threshold, and determining the performance indicator to be optimized according to the comparison result; Determining the data to be optimized according to the preset data interval where each real-time characterization data in the performance indicator to be optimized is located; Constructing a historical optimization data-performance optimization strategy mapping table, traversing the data to be optimized in the historical optimization data-performance optimization strategy mapping table, and determining the corresponding performance optimization strategy; Generating a corresponding performance optimization instruction according to the performance optimization strategy.

[0013] In some embodiments of the present application, there is also provided a performance optimization system for an organic electroluminescent device: An acquisition module, configured to acquire the basic information of the organic electroluminescent device to be optimized, screen out and analyze the historical similar working day logs according to the basic information, and construct a change curve of the historical performance sub-evaluation values of several preset performance indicators according to the analysis result; A determination module, configured to perform attention node marking and data analysis on the change curve of the historical performance sub-evaluation values, determine the corresponding historical performance characterization data according to the marking result and the analysis result, set several preset data intervals for the historical performance characterization data, and configure corresponding preset performance coefficients for each preset data interval; An optimization module is configured to obtain real-time performance characterization data of an organic electroluminescent device to be optimized, calculate a corresponding real-time comprehensive performance coefficient, determine whether to perform performance optimization based on the real-time comprehensive performance coefficient, and if so, filter out the data to be optimized and generate a performance optimization instruction.

[0014] Compared with the prior art, a performance optimization method and system for an organic electroluminescent device according to an embodiment of the present application have the following beneficial effects: By determining historical performance characterization data of an organic electroluminescent device to be optimized and corresponding several preset data intervals, and configuring a corresponding preset performance coefficient for each preset data interval to obtain a real-time comprehensive performance coefficient, the accuracy of data monitoring and analysis is improved, the data processing volume is reduced, the accuracy of performance evaluation is ensured, and the performance optimization efficiency is improved. Description of the Drawings

[0015] Figure 1 is a schematic flowchart of a performance optimization method for an organic electroluminescent device according to an embodiment of the present application; Figure 2 is a schematic diagram of a performance optimization system for an organic electroluminescent device according to an embodiment of the present application. Detailed Embodiments

[0016] The following describes in further detail the specific embodiments of the present application in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present application but are not intended to limit the scope of the present application.

[0017] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present application.

[0018] The terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0019] In the description of the present application, it should be noted that unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations.

[0020] As Figure 1 shown, a method for optimizing the performance of an organic electroluminescent device according to an embodiment of the present application includes: Step S101: Obtain the basic information of the organic electroluminescent device to be optimized, screen out historical similar work logs according to the basic information and analyze them, and construct a change curve of historical performance sub-evaluation values of several preset performance indicators according to the analysis results; Step S102: Mark the attention nodes and perform data analysis on the change curve of historical performance sub-evaluation values, determine the corresponding historical performance characterization data according to the marking results and analysis results, set several preset data intervals for the historical performance characterization data, and configure corresponding preset performance coefficients for each preset data interval; Step S103: Obtain the real-time performance characterization data of the organic electroluminescent device to be optimized, calculate the corresponding real-time comprehensive performance coefficient, and determine whether to perform performance optimization according to the real-time comprehensive performance coefficient. If so, screen out the data to be optimized and generate a performance optimization instruction.

[0021] In this embodiment, the basic information includes the own information of the organic electroluminescent device to be optimized and the preset working information. Among them, the own information includes material properties, types, etc., and the preset working information refers to the working environment and working conditions of the operation, etc.

[0022] In this embodiment, the preset performance indicators include material surface morphology indicators, dynamic performance indicators, optical performance indicators, electrical performance indicators, etc. Among them, the material surface morphology indicators refer to the surface morphology and particle distribution of the material, the dynamic performance indicators refer to the dynamic response time, current-voltage relationship, etc. of the organic electroluminescent device, the optical performance indicators refer to the luminous brightness, luminous efficiency, luminous chromaticity, lifespan, etc., and the electrical performance indicators refer to the conductivity, electron transport ability, etc.

[0023] In this embodiment, the change curve of historical performance sub-evaluation values is constructed according to multiple historical performance sub-evaluation values of the corresponding preset performance indicators of the organic electroluminescent device.

[0024] In some embodiments of the present application, constructing a change curve of historical performance sub-evaluation values of several preset performance indicators according to the analysis results includes: Divide the basic information into its own information and preset working information, and screen out several similar organic electroluminescent devices based on the own information of the organic electroluminescent device to be optimized currently; Obtain the historical work logs of the similar organic electroluminescent devices, extract the historical work information in the historical work logs, analyze the historical work information and the preset working information to obtain the similarity; Set the historical work logs corresponding to the historical work information with a similarity greater than the preset similarity threshold as the historical similar work logs; Analyze the historical similar work logs to obtain the historical working hours of each historical similar work log, establish a time reference line according to the historical working hours, and set analysis nodes at preset time intervals; Generate historical performance sub-evaluation values of several preset performance indicators of the corresponding similar organic electroluminescent devices based on each analysis node, and map them to the corresponding time reference line to obtain the change curves of the historical performance sub-evaluation values of several preset performance indicators.

[0025] In this embodiment, based on each analysis node, obtain the preset historical monitoring data of several preset performance indicators in the corresponding historical similar work log, and input the preset historical monitoring data into the preset performance evaluation model of the corresponding preset performance indicator to obtain the historical performance sub-evaluation value of the corresponding preset performance indicator. The preset historical monitoring data refers to the data for evaluating the historical performance sub-evaluation value of the corresponding preset performance indicator set in advance.

[0026] In this embodiment, the similarity refers to the degree of similarity between the preset working environment and preset working conditions in the preset working information and the historical working environment and historical working conditions in the historical work information.

[0027] In this embodiment, by determining the historical similar work logs of the organic electroluminescent device to be optimized and constructing the change curves of the historical performance sub-evaluation values, it lays a foundation for determining the historical performance characterization data later, improves the evaluation accuracy of the performance indicators, thereby ensuring the performance optimization efficiency and maximizing the application efficiency of the organic electroluminescent device.

[0028] In some embodiments of the present application, determine the corresponding historical performance characterization data according to the marking result and the analysis result, including: Pre-set several performance sub-evaluation value intervals for each preset performance indicator, and the performance sub-evaluation value intervals include abnormal performance sub-evaluation value intervals, suspected abnormal performance sub-evaluation intervals, general performance sub-evaluation intervals, and good performance sub-evaluation value intervals; Analyze the change curves of the historical performance sub-evaluation values of each preset performance indicator for each historical similar working day log, obtain the performance sub-evaluation value intervals where the historical performance sub-evaluation values are located at each analysis node in the change curves of the historical performance sub-evaluation values, and map the corresponding marking labels, where the marking labels include abnormal labels, suspected abnormal labels, general labels, and good labels; Segment the change curves of the historical performance sub-evaluation values according to the marking labels at each analysis node in the change curves of the historical performance sub-evaluation values of each preset performance indicator, and obtain the first segmented curve segment, the second segmented curve segment, the third segmented curve segment, and the fourth segmented curve segment of each change curve of the historical performance sub-evaluation; Collect the historical monitoring data of the similar organic electroluminescent devices in the corresponding historical similar working day logs according to each analysis node in the first segmented curve segment, the second segmented curve segment, the third segmented curve segment, and the fourth segmented curve segment, and map them into the corresponding curve segments to obtain the first segmented curve segment - data analysis diagram, the second segmented curve segment - data analysis diagram, the third segmented curve segment - data analysis diagram, and the fourth segmented curve segment - data analysis diagram; Conduct data analysis on the first segmented curve segment - data analysis diagram, the second segmented curve segment - data analysis diagram, the third segmented curve segment - data analysis diagram, and the fourth segmented curve segment - data analysis diagram, and determine the historical performance characterization data of each preset performance indicator according to the analysis results.

[0029] In this embodiment, the first segmented curve segment, the second segmented curve segment, the third segmented curve segment, and the fourth segmented curve segment respectively refer to the curve segments of the change curves of the historical performance sub-evaluation values at the continuous analysis nodes where the marking labels in the change curves of the historical performance sub-evaluation values are abnormal labels, suspected abnormal labels, general labels, and good labels.

[0030] In this embodiment, the first segmented curve segment - data analysis diagram, the second segmented curve segment - data analysis diagram, the third segmented curve segment - data analysis diagram, and the fourth segmented curve segment - data analysis diagram all include the corresponding curve segments of the historical performance sub-evaluation values and several historical monitoring data change curve segments.

[0031] In this embodiment, by segmenting the curve of the historical performance sub-evaluation value, obtaining the segmented curve segments with different marking labels, collecting the historical monitoring data change curves of each segmented curve segment and conducting data analysis and data comparison, the historical performance characterization data of each preset performance indicator, that is, the data accurately representing the performance state of the preset performance indicator, is determined, laying a foundation for determining the real-time comprehensive performance coefficient in the follow-up, improving the performance evaluation efficiency and accuracy, and ensuring the performance optimization efficiency.

[0032] In some embodiments of the present application, historical performance characterization data for each preset performance indicator is determined according to the analysis results, including: Based on the same marked label comparison principle, data correlation analysis is performed on the first segmentation curve segment - data analysis diagram, the second segmentation curve segment - data analysis diagram, the third segmentation curve segment - data analysis diagram, and the fourth segmentation curve segment - data analysis diagram of the same preset performance indicator in different historical similar working logs, to obtain several first relevant monitoring data groups, several second relevant monitoring data groups, several third relevant monitoring data groups, and several fourth relevant monitoring data groups for the same preset performance indicator; Wherein, each relevant monitoring data group includes several historical relevant monitoring data, and each historical relevant monitoring data is mapped with a corresponding correlation coefficient; A first performance characterization coefficient for the corresponding historical relevant monitoring data is generated according to the occurrence proportion of the same historical relevant monitoring data and the corresponding correlation coefficient; Data comparison analysis is performed on the first segmentation curve segment - data analysis diagram, the second segmentation curve segment - data analysis diagram, the third segmentation curve segment - data analysis diagram, and the fourth segmentation curve segment - data analysis diagram of the same preset performance indicator in the same historical similar working log, to obtain the intersection proportion of the historical data intervals where the same historical monitoring data is located in different segmentation curve segments; Historical monitoring data with an intersection proportion less than the corresponding preset intersection proportion threshold is set as historical comparison monitoring data, and several data difference groups are constructed according to the historical comparison monitoring data, where the number of the data difference groups is 6; A second performance characterization coefficient for the corresponding historical comparison monitoring data is generated according to the difference between the intersection proportion of the same historical comparison monitoring data in different data difference groups and the corresponding preset intersection proportion threshold; The historical performance characterization data for each preset performance indicator is determined according to the first performance characterization coefficient and the second performance characterization coefficient.

[0033] In this embodiment, the same marked label comparison principle refers to comparing the segmentation curve segment - data analysis diagrams of the same marked labels of the same preset performance indicator in different historical similar working logs. The first relevant monitoring data group, the second relevant monitoring data group, the third relevant monitoring data group, and the fourth relevant monitoring data group respectively refer to the combinations of historical relevant monitoring data of the same preset performance indicator in different historical similar working logs with abnormal labels, suspected abnormal labels, general labels, and good labels.

[0034] In this embodiment, data correlation analysis refers to the correlation analysis between the corresponding historical performance sub-evaluation value curve segments and several historical monitoring data change curve segments in terms of curve change trends, curve shapes, and curve topological structures, that is, to determine whether there is a linear or non-linear correlation between each historical monitoring data and the historical performance sub-evaluation value of the corresponding preset performance indicator. If there is a correlation, the corresponding historical monitoring data is set as historical correlated monitoring data, and the corresponding correlation degree is calculated. The greater the correlation degree, the greater the corresponding correlation coefficient, and vice versa.

[0035] In this embodiment, the interval intersection ratio refers to the overlapping part of the historical data intervals where the same historical monitoring data corresponding to different segmented curve segments is located. The preset interval intersection ratio thresholds for the historical monitoring data corresponding to different segmented curve segments are different. For example, the preset interval intersection ratio threshold for the historical monitoring data in the first segmented curve segment - data analysis diagram and the second segmented curve segment - data analysis diagram is 50%, and the preset interval intersection ratio threshold for the historical monitoring data in the first segmented curve segment - data analysis diagram and the third segmented curve segment - data analysis diagram is 15%. These are set according to the historical data intervals where the historical monitoring data is located and the actual situation.

[0036] In this embodiment, the six groups of data difference groups include three groups of data difference groups where the first segmented curve segment - data analysis diagram is respectively compared with the second segmented curve segment - data analysis diagram, the third segmented curve segment - data analysis diagram, and the fourth segmented curve segment - data analysis diagram, two groups of data difference groups where the second segmented curve segment - data analysis diagram is respectively compared with the third segmented curve segment - data analysis diagram and the fourth segmented curve segment - data analysis diagram, and one group of data difference group where the third segmented curve segment - data analysis diagram is compared with the fourth segmented curve segment - data analysis diagram.

[0037] In this embodiment, the correlation degree between the corresponding data and the preset performance indicator is accurately evaluated through the first performance characterization coefficient and the second performance characterization coefficient, that is, it represents the accuracy of the performance state of the preset performance indicator, thereby determining the historical performance characterization data, laying a foundation for improving the accuracy of data monitoring and analysis in the follow-up, reducing the data processing volume, and improving the performance evaluation efficiency and the performance optimization accuracy rate.

[0038] In some embodiments of the present application, determining the historical performance characterization data of each preset performance indicator according to the first performance characterization coefficient and the second performance characterization coefficient includes: The calculation formula for the first performance characterization coefficient is: ; where B1 is the first performance characterization coefficient, b1 is the first performance characterization conversion coefficient, is the occurrence ratio of the historical correlated monitoring data in the xth correlated monitoring data group, is the number of occurrences of historical relevant monitoring data in the x-th relevant monitoring data group, is the total number of groups of historical relevant monitoring data in the x-th relevant monitoring data group, and ax is the weight coefficient of the x-th relevant monitoring data group, is the i-th correlation coefficient of historical relevant monitoring data in the x-th relevant monitoring data group; The calculation formula of the second performance characterization coefficient is: ; where B2 is the second performance characterization coefficient, b3 is the third performance characterization conversion coefficient, and w is the total number of historical similar work logs, is the intersection ratio of intervals in the s-th data difference group of the c-th historical similar work log of historical comparison monitoring data, is the preset intersection ratio threshold of the s-th data difference group, and ds is the weight coefficient of the s-th data difference group; When the historical relevant monitoring data and the historical comparison monitoring data are the same data, generate the final performance characterization coefficient of the corresponding data according to the first performance characterization coefficient and the second performance characterization coefficient; When the historical relevant monitoring data and the historical comparison monitoring data are not the same data, set the first performance characterization coefficient or the second performance characterization coefficient as the final performance characterization coefficient of the corresponding data; Pre-performance characterization coefficient threshold; When the final performance characterization coefficient is greater than the performance characterization coefficient threshold, set the corresponding data as historical performance characterization data.

[0039] In this embodiment, when the historical relevant monitoring data and the historical comparison monitoring data are the same data, generate the final performance characterization coefficient according to the first performance characterization coefficient, the second performance characterization coefficient and the corresponding weight coefficients, and the final performance characterization coefficients are all greater than the first performance characterization coefficient and the second performance characterization coefficient.

[0040] In this embodiment, by calculating the final performance characterization coefficient, reduce the subsequent data monitoring volume and analysis and processing volume, greatly improve the performance evaluation efficiency and performance evaluation effect, lay a data foundation for calculating the real-time comprehensive performance coefficient in the future, improve the data monitoring accuracy and performance evaluation accuracy, so as to ensure the performance optimization effect.

[0041] In some embodiments of the present application, set several preset data intervals of historical performance characterization data, and configure corresponding preset performance coefficients for each preset data interval, including: Perform probability analysis on the intersection part of the historical data intervals of the historical performance characterization data in different marker tags, and re-divide the intersection part according to the probability analysis results to obtain several preset data intervals of the historical performance characterization data; Map the preset data intervals to the corresponding marker tags to obtain the marker tags mapped by each preset data interval; Based on the marker tag - performance coefficient mapping table, select the preset performance coefficients for the corresponding preset data intervals; Generate the preset performance coefficients for the corresponding preset data intervals according to the final performance characterization coefficient corresponding to the historical performance characterization data and the initial performance coefficients corresponding to each preset data interval.

[0042] In this embodiment, the marker tag - performance coefficient mapping table refers to the performance coefficients preset for the corresponding abnormal tags, suspected abnormal tags, general tags, and good tags, where the performance coefficients of the abnormal tags, suspected abnormal tags, general tags, and good tags increase in sequence.

[0043] In this embodiment, set the correction coefficient of the initial performance coefficient according to the final performance characterization coefficient corresponding to the historical performance characterization data. When the final performance characterization coefficient is larger, the corresponding correction coefficient is larger, and vice versa. The value range of the correction coefficient is (0, 1).

[0044] In some embodiments of the present application, calculating the corresponding real - time comprehensive performance coefficient includes: Obtain the real - time performance characterization data of the organic electroluminescent device to be optimized, and select the real - time performance coefficient according to the preset data interval where the real - time performance characterization data is located; Classify the real - time performance characterization data according to the corresponding preset performance indicators, and generate the real - time performance sub - coefficients corresponding to the real - time performance characterization data of the same preset performance indicator based on the final performance characterization coefficient and the real - time performance coefficient; Generate the real - time comprehensive performance coefficient of the organic electroluminescent device to be optimized according to the real - time performance sub - coefficients of multiple preset performance indicators and the weight coefficients corresponding to the preset performance indicators.

[0045] In this embodiment, judge whether the current node needs to be optimized by calculating the real - time comprehensive performance coefficient, ensure the timeliness of performance optimization and the accuracy of performance optimization strategies, and improve the application efficiency of the organic electroluminescent device.

[0046] In some embodiments of the present application, judge whether to perform performance optimization according to the real - time comprehensive performance coefficient. If so, screen out the data to be optimized and generate a performance optimization instruction, including: Preset the performance coefficient threshold and the performance sub - coefficient threshold of each preset performance indicator; If the real-time comprehensive performance coefficient is greater than the performance coefficient threshold, no performance optimization is performed; If the real-time comprehensive performance coefficient is less than the performance coefficient threshold, compare the real-time performance sub-coefficient of each preset performance index with the corresponding performance sub-coefficient threshold, and determine the performance index to be optimized according to the comparison result; Determine the data to be optimized according to the preset data interval where each real-time characterization data in the performance index to be optimized is located; Construct a historical optimization data - performance optimization strategy mapping table, traverse the data to be optimized in the historical optimization data - performance optimization strategy mapping table, and determine the corresponding performance optimization strategy; Generate the corresponding performance optimization instruction according to the performance optimization strategy.

[0047] In this embodiment, the historical optimization data - performance optimization strategy mapping table is set in advance, and each historical optimization data corresponds to an optimization strategy.

[0048] In this embodiment, by setting the performance optimization strategy, precise performance monitoring and dynamic optimization of the organic electroluminescent device are realized, ensuring the maximization of application efficiency, reducing manual intervention, and prolonging the device life.

[0049] In some embodiments of the present application, as Figure 2 shown, it further includes a performance optimization system for an organic electroluminescent device: An acquisition module, configured to acquire the basic information of the organic electroluminescent device to be optimized, screen and analyze the historical similar working day logs according to the basic information, and construct a change curve of the historical performance sub-evaluation values of several preset performance indexes according to the analysis result; A determination module, configured to mark the attention nodes of the change curve of the historical performance sub-evaluation values and perform data analysis, determine the corresponding historical performance characterization data according to the marking result and the analysis result, set several preset data intervals for the historical performance characterization data, and configure corresponding preset performance coefficients for each preset data interval; An optimization module, configured to acquire the real-time performance characterization data of the organic electroluminescent device to be optimized, calculate the corresponding real-time comprehensive performance coefficient, determine whether to perform performance optimization according to the real-time comprehensive performance coefficient, and if so, screen out the data to be optimized and generate a performance optimization instruction.

[0050] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present application, several improvements and replacements can still be made, and these improvements and replacements should also be regarded as the protection scope of the present application.

Claims

1. A method for optimizing the performance of an organic electroluminescent device, characterized in that, Including: Obtain the basic information of the organic electroluminescent device to be optimized, screen out the historical similar work logs according to the basic information and analyze them, and construct the change curves of the historical performance sub-evaluation values of several preset performance indicators according to the analysis results; Mark the attention nodes and perform data analysis on the change curves of the historical performance sub-evaluation values, determine the corresponding historical performance characterization data according to the marking results and the analysis results, set several preset data intervals for the historical performance characterization data, and configure corresponding preset performance coefficients for each preset data interval; Obtain the real-time performance characterization data of the organic electroluminescent device to be optimized, calculate the corresponding real-time comprehensive performance coefficient, and judge whether to perform performance optimization according to the real-time comprehensive performance coefficient. If so, screen out the data to be optimized and generate a performance optimization instruction.

2. The performance optimization method for an organic electroluminescent device according to claim 1, characterized in that, Construct the change curves of the historical performance sub-evaluation values of several preset performance indicators according to the analysis results, including: Divide the basic information into its own information and preset work information, and screen out several similar organic electroluminescent devices based on the own information of the current organic electroluminescent device to be optimized; Obtain the historical work logs of the similar organic electroluminescent devices, extract the historical work information from the historical work logs, and analyze the historical work information and the preset work information to obtain the similarity; Set the historical work logs corresponding to the historical work information with a similarity greater than the preset similarity threshold as the historical similar work logs; Analyze the historical similar work logs to obtain the historical working hours of each historical similar work log, establish a time reference line according to the historical working hours, and set analysis nodes at preset time intervals; Generate the historical performance sub-evaluation values of several preset performance indicators of the corresponding similar organic electroluminescent devices based on each analysis node, and map them to the corresponding time reference line to obtain the change curves of the historical performance sub-evaluation values of several preset performance indicators.

3. The performance optimization method for an organic electroluminescent device according to claim 2, characterized in that Determine the corresponding historical performance characterization data according to the marking results and the analysis results, including: Preset several performance sub-evaluation value intervals for each preset performance indicator, and the performance sub-evaluation value intervals include abnormal performance sub-evaluation value intervals, suspected abnormal performance sub-evaluation intervals, general performance sub-evaluation intervals, and good performance sub-evaluation value intervals; Analyze the change curves of the historical performance sub-evaluation values of each preset performance indicator of each historical similar work log to obtain the performance sub-evaluation value intervals where the historical performance sub-evaluation values at each analysis node in the change curves of the historical performance sub-evaluation values are located, and map the corresponding marking labels, and the marking labels include abnormal labels, suspected abnormal labels, general labels, and good labels; Divide the corresponding change curves of the historical performance sub-evaluation values according to the marking labels at each analysis node in the change curves of the historical performance sub-evaluation values of each preset performance indicator to obtain the first segmented curve segment, the second segmented curve segment, the third segmented curve segment, and the fourth segmented curve segment of each historical performance sub-evaluation change curve; Collect the historical monitoring data of similar organic electroluminescent devices in the corresponding historical similar working logs according to each analysis node in the first segmentation curve segment, the second segmentation curve segment, the third segmentation curve segment, and the fourth segmentation curve segment, and map them into the corresponding curve segments to obtain the first segmentation curve segment - data analysis diagram, the second segmentation curve segment - data analysis diagram, the third segmentation curve segment - data analysis diagram, and the fourth segmentation curve segment - data analysis diagram; Conduct data analysis on the first segmentation curve segment - data analysis diagram, the second segmentation curve segment - data analysis diagram, the third segmentation curve segment - data analysis diagram, and the fourth segmentation curve segment - data analysis diagram, and determine the historical performance characterization data of each preset performance indicator according to the analysis results.

4. The performance optimization method for an organic electroluminescent device according to claim 3, wherein Determine the historical performance characterization data of each preset performance indicator according to the analysis results, including: Based on the same marked label comparison principle, conduct data correlation analysis on the first segmentation curve segment - data analysis diagram, the second segmentation curve segment - data analysis diagram, the third segmentation curve segment - data analysis diagram, and the fourth segmentation curve segment - data analysis diagram of the same preset performance indicator in different historical similar working logs to obtain several first correlation monitoring data groups, several second correlation monitoring data groups, several third correlation monitoring data groups, and several fourth correlation monitoring data groups of the same preset performance indicator; Among them, each correlation monitoring data group includes several historical correlation monitoring data, and each historical correlation monitoring data is mapped with a corresponding correlation coefficient; Generate the first performance characterization coefficient of the corresponding historical correlation monitoring data according to the occurrence ratio of the same historical correlation monitoring data and the corresponding correlation coefficient; Conduct data comparison analysis on the first segmentation curve segment - data analysis diagram, the second segmentation curve segment - data analysis diagram, the third segmentation curve segment - data analysis diagram, and the fourth segmentation curve segment - data analysis diagram of the same preset performance indicator in the same historical similar working log to obtain the intersection ratio of the historical data intervals where the same historical monitoring data is located in different segmentation curve segments; Set the historical monitoring data with the intersection ratio less than the corresponding preset intersection ratio threshold as the historical comparison monitoring data, and construct several data difference groups according to the historical comparison monitoring data. Among them, the number of the data difference groups is 6; Generate the second performance characterization coefficient of the corresponding historical comparison monitoring data according to the intersection ratio difference between the intersection ratio of the same historical comparison monitoring data in different data difference groups and the corresponding preset intersection ratio threshold; Determine the historical performance characterization data of each preset performance indicator according to the first performance characterization coefficient and the second performance characterization coefficient.

5. The performance optimization method for an organic electroluminescent device according to claim 4, wherein Determine the historical performance characterization data of each preset performance indicator according to the first performance characterization coefficient and the second performance characterization coefficient, including: The calculation formula of the first performance characterization coefficient is: ； Among them, B1 is the first performance characterization coefficient, and b1 is the first performance characterization conversion coefficient. is the occurrence proportion of the historical relevant monitoring data in the x-th relevant monitoring data group. is the occurrence times of the historical relevant monitoring data in the x-th relevant monitoring data group. is the total number of groups of the historical relevant monitoring data in the x-th relevant monitoring data group, and ax is the weight coefficient of the x-th relevant monitoring data group. is the i-th correlation coefficient of the historical relevant monitoring data in the x-th relevant monitoring data group. The calculation formula of the second performance characterization coefficient is: ； Among them, B2 is the second performance characterization coefficient, b3 is the third performance characterization conversion coefficient, w is the total number of historical similar work logs, is the interval intersection ratio in the s-th data difference group of the c-th historical similar work log of the historical comparison monitoring data, is the preset interval intersection ratio threshold of the s-th data difference group, and ds is the weight coefficient of the s-th data difference group; When the historical correlation monitoring data and the historical comparison monitoring data are the same data, generate the final performance characterization coefficient of the corresponding data according to the first performance characterization coefficient and the second performance characterization coefficient; When the historical related monitoring data and the historical comparison monitoring data are not the same data, set the first performance characterization coefficient or the second performance characterization coefficient as the final performance characterization coefficient of the corresponding data; Pre-performance characterization coefficient threshold; When the final performance characterization coefficient is greater than the performance characterization coefficient threshold, set the corresponding data as historical performance characterization data.

6. The performance optimization method for an organic electroluminescent device according to claim 5, characterized in that, Set several preset data intervals for the historical performance characterization data, and configure corresponding preset performance coefficients for each preset data interval, including: Perform probability analysis on the intersection part of the historical data intervals where the historical performance characterization data is located in different marker tags, and re-divide the intersection part according to the probability analysis result to obtain several preset data intervals of the historical performance characterization data; Map the preset data intervals to the corresponding marker tags to obtain the marker tags mapped by each preset data interval; Based on the marker tag - performance coefficient mapping table, select the preset performance coefficient of the corresponding preset data interval; Generate the preset performance coefficient of the corresponding preset data interval according to the final performance characterization coefficient corresponding to the historical performance characterization data and the initial performance coefficient corresponding to each preset data interval.

7. The performance optimization method for an organic electroluminescent device according to claim 6, wherein Calculate the corresponding real-time comprehensive performance coefficient, including: Obtain the real-time performance characterization data of the organic electroluminescent device to be optimized, and select the real-time performance coefficient according to the preset data interval where the real-time performance characterization data is located; Classify the real-time performance characterization data according to the corresponding preset performance indicators, and generate the real-time performance sub-coefficient of the corresponding preset performance indicator by combining the final performance characterization coefficient and the real-time performance coefficient of the real-time performance characterization data with the same preset performance indicator; Generate the real-time comprehensive performance coefficient of the organic electroluminescent device to be optimized according to the real-time performance sub-coefficients of multiple preset performance indicators and the weight coefficients of the corresponding preset performance indicators.

8. The performance optimization method for an organic electroluminescent device according to claim 7, characterized in that, Judge whether to perform performance optimization according to the real-time comprehensive performance coefficient. If so, screen out the data to be optimized and generate a performance optimization instruction, including: Preset a performance coefficient threshold and a performance sub-coefficient threshold for each preset performance indicator in advance; If the real-time comprehensive performance coefficient is greater than the performance coefficient threshold, do not perform performance optimization; If the real-time comprehensive performance coefficient is less than the performance coefficient threshold, compare the real-time performance sub-coefficient of each preset performance indicator with the corresponding performance sub-coefficient threshold, and determine the performance indicator to be optimized according to the comparison result; Determine the data to be optimized according to the preset data interval where each real-time characterization data in the performance indicator to be optimized is located; Construct a historical optimization data - performance optimization strategy mapping table, traverse the data to be optimized in the historical optimization data - performance optimization strategy mapping table, and determine the corresponding performance optimization strategy; Generate the corresponding performance optimization instruction according to the performance optimization strategy.

9. A performance optimization system for an organic electroluminescent device, characterized in that, Including: An acquisition module, configured to acquire the basic information of the organic electroluminescent device to be optimized, screen out and analyze the historical similar working logs according to the basic information, and construct a change curve of the historical performance sub-evaluation values of several preset performance indicators; A determination module is used to perform attention node marking and data analysis on the historical performance sub-evaluation value change curve, determine the corresponding historical performance characterization data according to the marking result and the analysis result, set several preset data intervals for the historical performance characterization data, and configure corresponding preset performance coefficients for each preset data interval; An optimization module is used to obtain the real-time performance characterization data of the organic electroluminescent device to be optimized, calculate the corresponding real-time comprehensive performance coefficient, judge whether to perform performance optimization according to the real-time comprehensive performance coefficient, and if so, screen out the data to be optimized and generate a performance optimization instruction.

Images