Relevance determination, apparatus, electronic device and computer-readable storage medium

Abstract

The present disclosure relates to a correlation determination method and device, electronic equipment and a computer readable storage medium, the method comprising: obtaining measurement information and defect information of a display panel, wherein the measurement information comprises measurement values and measurement positions of measurement indexes, and the defect information comprises defect types; determining an influence weight of the measurement indexes with the measurement values at the measurement positions on the defect information of the defect types; determining a correlation coefficient of the influence weight and the measurement values, and determining a correlation degree of the measurement information and the defect information according to the correlation coefficient. According to the present disclosure, the analysis accuracy and speed of the defect cause are improved, the analysis cost is reduced, the utilization rate of the measurement information is improved, and the data value is improved.

Description

Technical Field

[0001] This disclosure relates to the field of display technology, and more particularly to correlation determination methods, correlation determination apparatus, electronic devices, and computer-readable storage media. Background Technology

[0002] The manufacturing process of display panels is affected by factors such as manufacturing techniques and the environment, which can lead to some defects in the finished display panels. During the manufacturing process, sampling can be used to measure certain indicators and obtain measurement information for subsequent analysis.

[0003] Currently, the analysis of defects mainly involves marking the measurement information at the corresponding positions on the display panel and displaying the defect information on the display panel. By comparing the positions of the measurement information and the defect information with the human eye, the degree of influence of the measurement indicators on the defects can be judged.

[0004] This method of judgment is mainly based on manual implementation, which is affected by subjective factors and experience, making it difficult to guarantee accuracy. It is also inefficient and has a low utilization rate of measurement information, making it difficult to achieve large-scale and standardized implementation. Summary of the Invention

[0005] This disclosure provides a method, apparatus, electronic device, and computer-readable storage medium for determining relevance, in order to address the shortcomings of related technologies.

[0006] According to a first aspect of the present disclosure, a correlation determination method is proposed, comprising: acquiring measurement information and defect information of a display panel, wherein the measurement information includes a measurement value and a measurement location for a measurement indicator, and the defect information includes a defect type; determining the influence weight of the measurement indicator having the measurement value at the measurement location on the defect information of the defect type; determining the correlation coefficient between the influence weight and the measurement value; and determining the correlation between the measurement information and the defect information based on the correlation coefficient.

[0007] Optionally, the measurement parameters include at least one of the following: film thickness, resistance, and forward voltage.

[0008] Optionally, the defect type includes at least one of the following: bright spot, dark spot, bright line, dark line, touch failure, and resistance.

[0009] Optionally, the adverse information also includes the adverse location, and the influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type includes: for each measurement location, determining the influence weight based on the measurement location and the adverse location respectively.

[0010] Optionally, determining the influence weight for each measurement location based on the measurement location and the defective location includes:

[0011] For each of the measurement locations ( The influence weights are determined respectively:

[0012] ;

[0013] in,( ) represents the defective location, k is the attenuation parameter, and R is the range parameter.

[0014] Optionally, the method further includes: determining, among the defective locations, a target defective location whose distance to the measurement location is less than a distance threshold;

[0015] Wherein, the distance threshold is determined based on R, ( This belongs to the target defect location.

[0016] Optionally, the adverse information does not include the adverse location, and the determination of the influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type includes: determining the influence weight as a preset value.

[0017] Optionally, determining the correlation coefficient between the influence weight and the measurement value includes: determining the correlation coefficient according to at least one correlation coefficient determination method.

[0018] Optionally, determining the correlation coefficient between the influence weight and the measurement value further includes determining the confidence level of the correlation coefficient.

[0019] Optionally, determining the correlation coefficient according to at least one correlation coefficient determination method includes: determining the independent correlation coefficients of the influence weight and the measurement value respectively according to multiple correlation coefficient determination algorithms; wherein, determining the correlation coefficient of the influence weight and the measurement value further includes: determining the correlation weight of each independent correlation coefficient according to the confidence level of each independent correlation coefficient; and performing a weighted summation of each independent correlation coefficient according to the correlation weight to obtain a joint correlation coefficient.

[0020] According to a second aspect of the present disclosure, a correlation determination apparatus is provided, comprising one or more processors, the processors being configured to: acquire measurement information and defect information of a display panel, wherein the measurement information includes a measurement value and a measurement location for a measurement indicator, and the defect information includes a defect type; determine the influence weight of the measurement indicator having the measurement value at the measurement location on the defect information of the defect type; determine the correlation coefficient between the influence weight and the measurement value; and determine the correlation between the measurement information and the defect information based on the correlation coefficient.

[0021] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above-described correlation determination method.

[0022] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps in the above-described correlation determination method.

[0023] According to embodiments of this disclosure, after obtaining measurement information of the display panel during the manufacturing process and defect information after manufacturing, an intermediate index can be determined to reflect the influence of the measurement point on the surrounding defects, so as to subsequently determine the correlation between the measurement information and the defect information based on the intermediate index.

[0024] Specifically, the influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type can be determined as an intermediate index, and then the correlation coefficient between the influence weight and the measurement value can be determined, and the correlation between the measurement information and the adverse information can be determined based on the correlation coefficient.

[0025] Therefore, by constructing influence weights to reflect the impact of measurement points on surrounding defects, the correlation between measurement information and defect information can be established. Furthermore, through correlation calculations, the correlation between measurement information and defect information can be quantitatively determined. This improves the accuracy and speed of defect cause analysis, reduces analysis costs, increases the utilization rate of measurement information, and enhances data value.

[0026] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0028] Figure 1This is a schematic flowchart illustrating a correlation determination method according to an embodiment of the present disclosure.

[0029] Figure 2 This is a schematic diagram illustrating an embodiment of the present disclosure for acquiring measurement information and defect information.

[0030] Figure 3 This is a schematic flowchart illustrating another correlation determination method according to an embodiment of the present disclosure.

[0031] Figure 4 This is a schematic diagram illustrating the relationship between a range parameter and an influence weight, according to an embodiment of the present disclosure.

[0032] Figure 5 This is a schematic flowchart illustrating another correlation determination method according to an embodiment of the present disclosure.

[0033] Figure 6 This is a schematic flowchart illustrating another correlation determination method according to an embodiment of the present disclosure.

[0034] Figure 7 This is a schematic flowchart illustrating another correlation determination method according to an embodiment of the present disclosure.

[0035] Figure 8 This is a schematic block diagram illustrating an apparatus for determining correlation according to embodiments of the present disclosure. Detailed Implementation

[0036] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0037] Figure 1 This is a schematic flowchart illustrating a relevance determination method according to an embodiment of this disclosure. The method shown in this embodiment can be applied to devices such as terminals and servers.

[0038] like Figure 1 As shown, the method may include the following steps:

[0039] In step S101, measurement information and defect information of the display panel are obtained, wherein the measurement information includes the measurement value and measurement location of the measurement index, and the defect information includes the defect type;

[0040] In step S102, the influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type is determined;

[0041] In step S103, the correlation coefficient between the influence weight and the measurement value is determined, and the correlation between the measurement information and the adverse information is determined based on the correlation coefficient.

[0042] In one embodiment, the display panel includes a liquid crystal display (LCD) panel and an organic light-emitting diode (OLED) display panel.

[0043] Display panels consist of multiple film layers. For example, in the array substrate of a display panel, multiple film layers need to be fabricated to manufacture thin-film transistors. During the manufacturing process of a display panel, sampling measurements can be performed on each film layer, specifically measuring one or more parameters of the film layer.

[0044] In one embodiment, the measurement parameters include at least one of the following: film thickness, resistance, and forward voltage. Subsequent embodiments primarily focus on the film thickness measurement parameter, providing illustrative descriptions of the technical solutions disclosed herein.

[0045] In one embodiment, the measurement information obtained by sampling and measuring the film layer during the manufacturing process, as well as the defect information identified in the display panel during and after the manufacturing process, can be stored in the YMS (Yield Manager System) database. Then, the required information can be extracted from the YMS database (e.g., through Structured Query Language SQL) and stored in the HBase database in a form suitable for subsequent calculations.

[0046] The measurement information includes the measurement values ​​obtained by sampling and measuring one or more physical quantities of the film layer (such as the aforementioned resistance, film thickness, etc.) during the manufacturing process; the defect information includes the test results of one or more film layers during the manufacturing process and / or one or more functions of the display panel after manufacturing, such as display function, touch function, etc. Taking the display function as an example, it can specifically include one or more defect types, such as bright spots, dark spots, bright lines, dark lines, etc.

[0047] In one embodiment, the measurement information can be obtained by sampling measurements during the fabrication of the film layer on the initial glass substrate, or by sampling measurements during the fabrication of the film layer on two half-substrates, A and B, obtained by halving the initial glass substrate. Defect information, however, is obtained after the initial glass substrate is cut into the final panel.

[0048] Because the coordinate systems on Glass, Half-Glass, and panel are different, the measurement information obtained by sampling during the fabrication of the film on Glass, the measurement information obtained by sampling during the fabrication of the film on Half-Glass, and the defect information determined on the panel can be transformed to the same coordinate system, such as the coordinate system of Glass.

[0049] Figure 2 This is a schematic diagram illustrating an embodiment of the present disclosure for acquiring measurement information and defect information.

[0050] like Figure 2 As shown, data can be extracted from the YMS database using SQL. The extracted data includes three parts: measurement information obtained by sampling during the manufacturing of the film in Glass, measurement information obtained by sampling during the manufacturing of the film in Half-Glass, and defect information identified on the panel.

[0051] Measurement information obtained from sampling measurements during Half-Glass film fabrication can determine whether it belongs to plate A or plate B, allowing for coordinate transformation to the Glass coordinate system. Similarly, defective signals identified on the panel can also be transformed to the Glass coordinate system.

[0052] The three parts of data can then be input into an ETL (Extract Transform Load) tool, such as Pentaho, for processing, and finally stored in an HBase database.

[0053] In one embodiment, the measurement information obtained by sampling during the glass film manufacturing process, the measurement information obtained by sampling during the half-glass film manufacturing process, and the defect information identified on the panel can be stored in the HBase database in the form of the following three tables.

[0054]

[0055] Table 1

[0056] The measurement information obtained from the film layer formed on Glass can be stored according to Table 1.

[0057] The Glass ID of the Glass being measured can be selected as the primary key ROWKEY. Station indicates the measurement site. The indicator name is the above-mentioned measurement indicator, including but not limited to film thickness, resistance, conduction voltage, etc. For each indicator, the measurement location and the measured value can be determined, i.e., the measurement value, which is stored in Table 1.

[0058]

[0059] Table 2

[0060] The measurement information obtained from the measurement of the film layer formed on Half-Glass can be stored according to Table 2.

[0061] The Half-Glass ID of the Half-Glass under test can be selected as the primary key ROWKEY. "station" indicates the measurement site, and the indicator name is the aforementioned measurement indicator, including but not limited to film thickness, resistance, and forward voltage. Measurements are performed on each indicator to determine the measurement location and the measured value, which is stored in Table 2. Additionally, for convenient coordinate system transformation, the location of the Half Glass within the Glass can also be stored in Table 2.

[0062]

[0063] Table 3

[0064] For the negative information identified in the Panel, it can be stored according to Table 3.

[0065] The Panel ID of the panel containing the defect information can be selected as the primary key ROWKEY. The Defect Code indicates the defect type. In one embodiment, the defect type includes at least one of the following: bright spot, dark spot, bright line, dark line, touch failure, and tactile resistance.

[0066] For defective information, if the location can be determined, such as a bright spot, the location of the defect can be recorded, and the coordinates of the defective location need to be transformed into the Glass coordinate system for representation so that calculations can be performed in the same coordinate system as the measurement location. For defective information where the location cannot be determined, such as touch failure, NaN (Not a Number) can be used as the coordinates.

[0067] According to embodiments of this disclosure, after obtaining measurement information of the display panel during the manufacturing process and defect information after manufacturing, an intermediate index can be determined to reflect the influence of the measurement point on the surrounding defects, so as to subsequently determine the correlation between the measurement information and the defect information based on the intermediate index.

[0068] Specifically, the influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type can be determined as an intermediate index, and then the correlation coefficient between the influence weight and the measurement value can be determined, and the correlation between the measurement information and the adverse information can be determined based on the correlation coefficient.

[0069] Therefore, by constructing influence weights to reflect the impact of measurement points on surrounding defects, the correlation between measurement information and defect information can be established. Furthermore, through correlation calculations, the correlation between measurement information and defect information can be quantitatively determined. This improves the accuracy and speed of defect cause analysis, reduces analysis costs, increases the utilization rate of measurement information, and enhances data value.

[0070] In one embodiment, the correlation coefficient can be used as the relevance of bad information, or the correlation coefficient can be further processed and used as the relevance, for example, by multiplying it by a scaling factor.

[0071] In one embodiment, detecting unwanted information may include the following steps A through D:

[0072] In step A, defect information in the current film layer and defect information in the historical film layer are obtained, wherein the historical film layer was formed before the current film layer;

[0073] In step B, the target location of the defective information in the current film layer is determined, and it is determined whether there is defective information at the corresponding location of the target location in the historical film layer;

[0074] In step C, if there is defective information at the target location in the historical film layer, the defective information detected at the target location in the current film layer is deleted;

[0075] In step D, if there is no adverse information at the target location in the historical film layer, the adverse information detected at the target location in the current film layer is retained.

[0076] In one embodiment, the method for detecting defective information can be selected as needed, for example, by means of automated optical inspection (AOI).

[0077] In one embodiment, the current membrane layer can be the most recently formed membrane layer. After the formation of the first membrane layer (e.g., the bottommost membrane layer), each time a membrane layer is formed, the formed membrane layer can be used as the current membrane layer to perform the above steps A to D.

[0078] In one embodiment, when malicious information is detected, the location (e.g., coordinates) of the malicious information can be recorded.

[0079] In one embodiment, during the manufacturing of a display panel, if it is necessary to cut a glass substrate to obtain multiple display panels, and the detection of defective information occurs before cutting, the position of the defective information in the glass substrate can be recorded first. Then, after cutting, the display panel where the defective information is located and its coordinates within the display panel can be determined based on the cutting method. In all embodiments of this disclosure, "display panel" can refer to the cut display panel.

[0080] According to steps A to D above, when defective information is detected at the target location in the current film layer, the detected defective information is not directly recorded. Instead, it is determined whether defective information also exists at the corresponding location in the previously formed historical film layer (such as the target location or a location within a certain range of the target location).

[0081] If there is also adverse information, it means that the adverse information at the target location in the current membrane layer is caused by the adverse information at the target location in the historical membrane layer. Therefore, the adverse information at the target location in the current membrane layer can be deleted. If there is no adverse information, it means that the adverse information at the target location in the current membrane layer is not caused by the adverse information at the target location in the historical membrane layer, but by the current membrane layer's own factors (the implementation environment of the current membrane layer, the process of forming the current membrane layer, etc.). Therefore, the adverse information at the target location in the current membrane layer can be retained.

[0082] Therefore, for the adverse information in the current membrane layer, only the adverse information caused by the current membrane layer itself can be retained, instead of retaining the adverse information caused by the historical membrane layers. On the one hand, this can reduce the amount of data stored, and on the other hand, it can simplify the complexity of subsequent analysis of adverse information.

[0083] In one embodiment, determining whether there is any adverse information at the corresponding position of the target position in the historical film layer includes: determining whether there is any adverse information within a preset distance threshold range of the target position in the historical film layer; if there is adverse information, determining whether there is any adverse information at the corresponding position of the target position in the historical film layer.

[0084] In one embodiment, if defective information in a historical membrane layer leads to defective information in the current membrane layer, the location of the defective information in the historical membrane layer and the location of the defective information in the current membrane layer may have slight differences due to factors such as manufacturing process and membrane layer structure.

[0085] Therefore, when determining whether there is any defective information at the corresponding position of the target position in the historical film layer, it can be determined whether there is any defective information within a preset distance threshold range of the target position in the historical film layer. For example, the distance between the coordinates of the defective information in the historical film layer and the coordinates of the target position in the historical film layer can be calculated. If the distance is less than the distance threshold, it can be determined that there is defective information at the target position in the historical film layer. If the distance is greater than the distance threshold, it can be determined that there is no defective information at the target position in the historical film layer.

[0086] If the distance is equal to the distance threshold, it can be divided into cases where the distance is less than the distance threshold or greater than the distance threshold, as needed.

[0087] In one embodiment, if there are linear defects in the current film layer, such as row direction defects, column direction defects, diagonal direction defects, etc., the corresponding straight line of the linear defect can be determined in the historical film layer. Then, it is determined whether there is defect information in the defect information of the historical film layer whose distance to the straight line is less than a preset distance threshold. If so, it is determined that the corresponding position of the target position in the historical film layer is defect information.

[0088] In one embodiment, determining whether there is any adverse information within a preset distance threshold range of the target position in the historical film layer includes: if there is an adverse information in the row direction in the current film layer, determining whether there is any adverse information within a preset distance threshold range in the column direction of the target position in the historical film layer; if there is adverse information, determining that there is adverse information at the corresponding position of the target position in the historical film layer.

[0089] In one embodiment, determining the distance between the defective location containing defective information in the historical film layer and the target location includes: if there is a column-direction defect in the current film layer, determining whether there is defective information within a preset distance threshold range in the row direction of the target location in the historical film layer; if defective information exists, determining that there is defective information at the corresponding location of the target location in the historical film layer.

[0090] Since the structure in the display panel generally affects the entire row of pixels or the entire column of pixels, for example, a problem with the query line may affect the entire row of pixels, and a problem with the data line may affect the entire column of pixels, therefore, the bad information in the film layer can be bad in the row direction, such as the entire row of pixels not lighting up or the light emission being uncontrolled, or it can be bad in the column direction, such as the entire column of pixels not lighting up or the light emission being uncontrolled.

[0091] For defects in the row direction, the defect information extends across the entire panel in the row direction, equivalent to a straight line along the row. Therefore, determining the distance from a point to this line only requires considering the distance from the point to the perpendicular direction of the line. For a straight line along the row direction, it is only necessary to consider the distance from the location of the defect information in the historical film layer to this line in the column direction. That is, it calculates whether defect information exists within a preset distance threshold range in the column direction of the target location in the historical film layer. If defect information exists, it can be determined that the target location in the historical film layer contains defect information. Here, the target location can be a row, not a single point.

[0092] Correspondingly, for defects in the column direction, the defect information extends across the entire panel in the column direction, equivalent to a straight line along the column direction. Therefore, determining the distance from a point to the line only requires considering the distance from the point to the perpendicular direction of the line. For a straight line along the column direction, it is only necessary to consider the distance from the location of the defect information in the historical film layer to the line in the row direction. That is, it calculates whether defect information exists within a preset distance threshold range in the row direction of the target location in the historical film layer. If defect information exists, it can be determined that the target location in the historical film layer contains defect information. Here, the target location can be not a point, but a column.

[0093] In one embodiment, before acquiring defect information in the current film layer and defect information in historical film layers, the method further includes: determining the defect location of the defect information in the current film layer, and the cutting information of the display panel where the defect location is located; determining the correlation between the coordinates in the display panel and the coordinates in the glass substrate where the display panel was located before cutting based on the cutting history information; and determining the location of the defect location in the glass substrate based on the correlation.

[0094] In the process of manufacturing a display panel, it is generally necessary to cut a relatively large glass substrate to obtain multiple relatively small display panels. The aforementioned film layer may include the film layer formed before cutting or the film layer formed after cutting.

[0095] The operation of detecting defects in the film layer is generally performed after the current film layer is made and before the next film layer is made. Therefore, for the film layer formed on the glass substrate before cutting, the position of the defect information recorded during detection is the coordinate in the glass substrate coordinate system. However, for the film layer formed on the display panel after cutting, the position of the defect information recorded during detection is the coordinate in the display panel coordinate system. This results in the defect information in different film layers being located in different coordinate systems, which is not convenient for subsequent processing.

[0096] Before obtaining defect information in the current film layer and defect information in the historical film layers, this embodiment can first determine the defect location of the defect information in the current film layer, as well as the cutting information of the display panel where the defect location is located.

[0097] The cutting information may include, for example, the number of the display panel in the glass substrate before cutting, the cutting method of the glass substrate, and the spatial correspondence between the number and the cutting method.

[0098] Based on the cutting information, the correlation between the coordinates in the display panel and the coordinates in the glass substrate where the display panel was located before cutting can be determined. This correlation can characterize the relationship between the glass substrate coordinate system and the display panel coordinate system, including but not limited to rotation, translation, and other relationships.

[0099] Then, the location of the defective position in the glass substrate is determined according to the correlation. For example, the correlation is a transformation matrix from the coordinate system of the display panel to the coordinate system of the glass substrate. The location information of the defective information detected in the display panel can be transformed by the transformation matrix to obtain the location of the defective information in the glass substrate.

[0100] Accordingly, the location information of all defective information in the display panel can be converted to the coordinate system of the glass substrate, which facilitates subsequent processing, such as determining the target location of defective information in the current film layer, determining whether there is defective information at the corresponding position of the target location in the historical film layer, and performing operations such as aggregating defective information.

[0101] In one embodiment, the method for determining defective information further includes: storing the recorded defective information in a first data table; aggregating the data in the first data table according to the process flow information in the manufacturing process to obtain a second data table; and querying (also known as scanning) the data in the second data table according to the received query instruction.

[0102] Because the manufacturing process of display panels requires the production of multiple layers of film, and there may be a lot of defect information detected on each layer, if a large number of display panels are produced in multiple factories, the number of defect information detected when testing all display panels in multiple factories will be enormous.

[0103] According to this embodiment, the recorded defect information can be first stored in a first data table, and then the data in the first data table can be aggregated according to the process flow information during the manufacturing process to obtain a second data table. The process flow information includes, but is not limited to, the following:

[0104] Factory (the factory that manufactures the membrane), Date (the date the membrane is manufactured), Site (the site where the membrane is tested), Equipment (the equipment to which the membrane belongs), Product (the product to which the membrane belongs), Defect Type (the type of defect information in the membrane).

[0105] Among them, aggregating the data in the first data table based on the process flow information during the production process can refer to integrating multiple defective information entries with the same process flow information into a single data entry.

[0106] Taking process flow information including date, testing site, and defect type as an example, consider the following 9 defect information entries:

[0107] Bad Information 1: Date: April 25, 2021; Detection Station: Station1; Type: CodeA1; Coordinates: (x1, y1);

[0108] Bad Information 2: Date: April 25, 2021; Detection Station: Station1; Type: CodeA1; Coordinates: (x2, y2);

[0109] Bad Information 3: Date: April 25, 2021; Detection Station: Station1; Type: CodeA1; Coordinates: (x3, y3);

[0110] Bad Information 4: Date: April 25, 2021; Detection Station: Station1; Type: CodeA1; Coordinates: (x4, y4);

[0111] Bad Information 5: Date: April 25, 2021; Detection Station: Station1; Type: CodeA2; Coordinates: (x5, y5);

[0112] Bad Information 6: Date: April 25, 2021; Detection Station: Station1; Type: CodeA2; Coordinates: (x6, y6);

[0113] Bad Information 7: Date: April 25, 2021; Detection Station: Station1; Type: CodeA2; Coordinates: (x7, y7);

[0114] Bad Information 8: Date: April 25, 2021; Detection Station: Station1; Type: CodeA2; Coordinates: (x8, y8);

[0115] Bad Information 9: Date: April 25, 2021; Detection Station: Station1; Type: CodeA2; Coordinates: (x9, y9);

[0116] The dates, detection sites, and types of the aforementioned negative information 1 to 4 are the same, so these four pieces of negative information can be aggregated into one data point. Similarly, the dates, detection sites, and types of the aforementioned negative information 5 to 9 are the same, so these five pieces of negative information can be aggregated into one data point. Thus, the aforementioned nine data points can be aggregated into two data points, as shown below:

[0117] Date 2021.4.25, detection station station1, type codeA1, coordinates (x1,y1), (x2,y2), (x3,y3), (x4,y4); and date 2021.4.25, detection station station1, type codeA2, coordinates (x5,y5), (x6,y6), (x7,y7), (x8,y8), (x9,y9).

[0118] Therefore, multiple defective information entries with the same process flow information can be integrated into one data entry instead of being treated as multiple data entries, which helps to improve the speed of subsequent queries.

[0119] In one embodiment, the first data table and / or the second data table are data tables in an HBase database.

[0120] Because HBase databases have the characteristics of massive storage, columnar storage, easy expansion, high concurrency, and sparsity, they are easy to store large amounts of bad information. Moreover, HBase primary keys can be designed according to the process information on which the aggregated data is based, so that the aggregated data can be stored more reasonably in HBase data tables.

[0121] In one embodiment, the primary key of the first data table is the identifier of the display panel; and / or the primary key of the second data table includes at least one of the following: factory, date, inspection site, equipment, product, and defect type.

[0122] For example, the first data table can be shown in Table A below, and the second data table can be shown in Table B below:

[0123]

[0124] Table A

[0125]

[0126] Table B

[0127] In the first data table, the display panel identifier is used as the primary key to facilitate data loading and storage. In the second data table, the primary key can be designed based on the process flow information upon which the aggregated data is based. For example, the process flow information and the primary key can be the same, making the aggregated data more rationally stored in the second data table and facilitating subsequent retrieval of data in the second data table based on the primary key.

[0128] For example, storing multiple pieces of negative information in the second data table results in a single piece of data, as shown in Table C below:

[0129]

[0130] Table C

[0131] That is, the data for the 5 pieces of negative information:

[0132] Factory EAC2, Date 20191001, Site C33000N, Equipment BCXCT01, Product ABCD, Defect Type AD0100, Coordinates (98.01, 60.51);

[0133] Factory EAC2, Date 20191001, Site C33000N, Equipment BCXCT01, Product ABCD, Defect Type AD0100, Coordinates (198.1, 160.5);

[0134] Factory EAC2, Date 20191001, Site C33000N, Equipment BCXCT01, Product ABCD, Defect Type AD0100, Coordinates (298.1, 260.5);

[0135] Factory EAC2, Date 20191001, Site C33000N, Equipment BCXCT01, Product ABCD, Defect Type AD0100, Coordinates (180.1, 160.5);

[0136] Factory EAC2, Date 20191001, Site C33000N, Equipment BCXCT01, Product ABCD, Defect Type AD0100, Coordinates (218.1, 262.5);

[0137] These five data entries share the same factory, date, site, equipment, product, and defect type. By storing them according to the storage structure of the second data table, we can obtain a single HBase data entry as shown in Table C. This aggregates multiple defect information entries into a single data entry, facilitating subsequent queries.

[0138] In one embodiment, the method for determining adverse information further includes: statistically analyzing at least one of the following and storing it in the second data table: the ratio of adverse information deleted from the current membrane layer to all adverse information in the current membrane layer; the ratio of adverse information recorded in the current membrane layer to all adverse information in the current membrane layer; and the ratio of adverse information recorded in the current membrane layer to all adverse information in all membrane layers.

[0139] When deleting undesirable information in the current membrane layer that was affected by historical membrane layers, since this deleted undesirable information still has some analytical value, although it is not necessary to record this undesirable information in detail, we can statistically analyze the relevant information of this undesirable information for subsequent analysis.

[0140] In one embodiment, the method of determining the defective information further includes: before determining the target location of the defective information in the current film layer, aggregating the detected defective information according to the display panel to which the detected defective information belongs.

[0141] During the testing process, the testing targets all film layers in all display panels. If we determine whether the defective information in the current film layer of all display panels is affected by the defective information in the historical film layer, it may be possible to determine that the defective information in the current film layer of one display panel is affected by the defective information in the historical film layer of another display panel. However, such a determination is meaningless because the film layers of different display panels do not have a direct impact on each other.

[0142] Therefore, before determining the target location of the defective information in the current film layer, this embodiment can first aggregate the detected defective information according to the display panel to which the detected defective information belongs, so as to ensure that the determination of whether the defective information in the current film layer is affected by the defective information in the historical film layer for the same display panel avoids recording unnecessary information.

[0143] In one embodiment, the method of determining adverse information further includes: reading historical adverse information recorded for historical film layers before aggregating the detected adverse information according to the display panel to which the detected adverse information belongs; and loading the adverse information detected in the current film layer into the historical adverse information.

[0144] In the manufacturing process of display panels, multiple film layers are generally made in sequence. Different film layers are made at different times, and some film layers are not even made on the same day. Defect information detected for each film layer can be stored. Therefore, there will be defect information recorded for the film layers formed earlier and defect information recorded for the film layers formed later.

[0145] In this embodiment, when detecting the current film layer, historical defect information recorded for historical film layers can be read, and then the defect information detected in the current film layer can be loaded into the historical defect information, so that the loaded information includes defect information of all film layers in the display panel, so as to determine whether there is defect information at the target position in the historical film layer for all film layers in the subsequent process.

[0146] In one embodiment, querying data in the second data table according to the received query instruction includes: receiving a query instruction sent by the client; querying the second data table according to the query instruction; and generating front-end data based on the query results.

[0147] In one embodiment, generating front-end data based on the query results includes: displaying the trend of adverse information based on the query results; and / or displaying the distribution of adverse information based on the query results. By displaying the trend of adverse information, users can easily view the changes in adverse information over time; by displaying the distribution of adverse information, users can easily view the distribution of adverse information in each film layer and each panel.

[0148] In one embodiment, the method for obtaining measurement information and defect information as described in this disclosure can be implemented based on data warehouse technology ETL. ETL can be implemented based on YMS (Yield Manager System), Hive (a data warehouse tool), Spark (a computing engine), and HBase database. For specific implementation methods, please refer to the subsequent embodiments related to the product information query system. The following embodiments mainly describe the acquisition of defect information, but they are also applicable to measurement information.

[0149] First, all detected problematic information can be stored in YMS. Then, the problematic information is extracted from YMS and written to Hive. Finally, Spark is used to query the problematic information from Hive and write it to the HBase database. The steps in the above embodiment can mainly be completed by Spark, such as recording and deleting problematic information and aggregating data.

[0150] Users can enter query commands on the client side, which can then be input into the server module. The server module interacts with HBase, retrieves data from the second data table in HBase based on the query commands, and sends the retrieved data to the client for display. The client can display the query results according to its settings, such as displaying bar charts or the distribution of negative information.

[0151] The client interface can mainly consist of three parts. The first area is for the user to input query elements, such as the primary key in the second data table. The second area is used to display the trend of the query results, such as time on the horizontal axis and the amount of defective information on the vertical axis. The display method can be a bar chart or other methods can be set as needed. The other areas of the interface are used to display the location of defective information in each membrane layer and the distribution of defective information recorded in steps A to D on the display panel.

[0152] Users can generate query commands by entering query elements in the client interface and send them to the server module. The server module then queries data from the second data table in HBase based on the query commands, returns the query results to the client, and displays them on the client interface.

[0153] In addition, embodiments of this disclosure also provide a data detail download function. For example, data download can be based on negative information in a batch display panel. For instance, after a user clicks on a bar chart or enters an LOT ID (each LOT can correspond to a batch display panel), the client sends an LOT detail query request to the Server module, generating a corresponding query task for the original data table after front-end filtering, generating the corresponding data detail file, and returning it to the front-end for download.

[0154] In one embodiment, when performing data aggregation, a time range can be entered first to determine historical film defects within that time range;

[0155] Spark can then record the defect information of the current film layer detected by each station from Hive. If it is necessary to cut the glass substrate, it can also transform the coordinates of the defect information in the glass substrate to the cut panel.

[0156] When forming a historical membrane layer, defects in the historical membrane layer can be recorded in a first data table. When forming the current membrane layer, defect information of the historical membrane layer can be obtained from the first data table, and defect information detected in the current membrane layer can be loaded into the defect information of the historical membrane layer.

[0157] Next, the detected negative information can be aggregated according to the display panel to which it belongs;

[0158] Based on steps A to D, record the adverse information in the current membrane layer that is not due to the influence of the historical membrane layer. The recording results can be updated to the first data table. Thus, the adverse information stored in the first data table includes both the adverse information of the current membrane layer and the adverse information of the historical membrane layer.

[0159] Finally, the data in the first data table can be aggregated based on the process flow information during the manufacturing process, and the aggregated data can be stored in the second data table. The primary key of the second data table can be the same as the process flow information.

[0160] Steps A to D, as well as the steps in S101 such as obtaining measurement information and obtaining defect information, can be implemented based on a product information query system. The system includes a data processing device, a display device, and a distributed storage device. The system can be used to query defect information and measurement information of products. The products may include multiple film layers, including but not limited to organic light-emitting diode display panels and liquid crystal display panels.

[0161] The distributed storage device is used to store defect information and measurement information detected in the current membrane layer and defect information and measurement information in historical membrane layers, wherein the historical membrane layers were formed before the current membrane layer;

[0162] The data processing device is used to obtain the detected defect information and measurement information in the current film layer from the distributed storage device, and to determine the target position of the defect information and measurement information in the current film layer, and to determine whether there is defect information at the corresponding position of the target position in the historical film layer. If there is defect information at the target position in the historical film layer, the device deletes the defect information detected at the target position in the current film layer. If there is no defect information at the target position in the historical film layer, the device retains the defect information detected at the target position in the current film layer, and stores the measurement information and the retained defect information in the distributed storage device.

[0163] The display device is used to query the bad information and measurement information in the distributed storage device according to the received query command, and generate front-end data.

[0164] In one embodiment, the data processing device is further configured to store the recorded defect information and measurement information into a first data table; aggregate the data in the first data table according to the process flow information in the manufacturing process to obtain a second data table; and the display device is configured to query the defect information and measurement information in the second data table according to the query instruction.

[0165] Currently, industrial product production lines consist of several process devices, and any malfunction or abnormal operating parameters of any of these devices can affect product yield. When defective products are produced, production personnel need to pinpoint the cause. However, the large volume of data generated by the process devices on the production line increases the complexity of locating the cause, resulting in a significant time commitment in identifying the culprit.

[0166] This disclosure provides a product information query system. The product information query system includes a data processing device, a display device, and a distributed storage device. The data processing device is connected to both the display device and the distributed storage device.

[0167] Distributed storage devices are used to store production data generated by multiple sample production devices (or factory equipment). For example, the production data generated by multiple sample production devices includes production records of multiple sample production devices; for example, the production records include information about the sample production devices that multiple samples passed through during the production process and information about the types of defects that occurred. Each sample goes through multiple sample production devices during the production process, and each sample production device participates in the production process of only a portion of the multiple samples.

[0168] In this context, a distributed storage device stores relatively complete data (such as a database). A distributed storage device can include multiple hardware storage devices distributed in different physical locations (such as different factories or different production lines), and they exchange information wirelessly (e.g., via networks). This results in a distributed data structure, but logically constitutes a database based on big data technology.

[0169] For the data stream of the product information query system, a large amount of raw data from different sample production equipment, such as defect information and measurement information of the film layer in the product, is stored in the relational databases (such as Oracle, MySQL, etc.) of the corresponding production and manufacturing systems, such as YMS (Yield Management System), FDC (Fault Detection & Classification), MES (Manufacturing Execution System). This raw data can be extracted from the original tables by data extraction tools (such as Sqoop, Kettle, etc.) and transmitted to distributed storage devices (such as distributed file systems, Hadoop Distributed File System, abbreviated as HDFS) to reduce the load on the sample production equipment and the production and manufacturing system, and facilitate data reading by subsequent analysis equipment.

[0170] Data in distributed storage devices can be stored using Hive tools and HBase database formats. For example, the raw data is first stored in a data lake using Hive. Then, it can undergo preprocessing in Hive according to its application theme and scenario, such as data cleaning and transformation, to obtain data warehouses with different themes (e.g., production history, testing data, equipment data) and data marts with different scenarios (e.g., equipment analysis, parameter analysis), such as HBase. These data marts can then connect to display devices, analysis devices, etc., through different API interfaces to achieve data interaction with these devices.

[0171] Because this involves multiple sample production equipment across multiple factories, the amount of raw data is substantial. For example, the raw data generated by all the sample production equipment each day could be several hundred gigabytes, and the data generated each hour could be tens of gigabytes.

[0172] In one embodiment, there are two main solutions for storing and computing massive amounts of structured data: a grid computing solution using a Relational Database Management System (RDBMS); and a big data solution using a Distributed File System (DFS).

[0173] Big data technologies based on Distributed File System (DFS) allow for the construction of large clusters using multiple inexpensive hardware devices to process massive amounts of data. For example, Hive is a data warehouse tool based on Hadoop, used for data extraction, transformation, and loading (ETL). Hive defines a simple SQL-like query language and also allows for complex analysis tasks that the default tool cannot perform through custom MapReduce mappers and reducers. Hive does not have a specific data storage format or indexes; users can freely organize the tables and process the data in the database. It is evident that the parallel processing of distributed file management can meet the storage and processing requirements of massive amounts of data. Users can process simple data through SQL queries, while complex processing can be achieved using custom functions. Therefore, when analyzing massive amounts of data from a factory, it is necessary to extract the data from the factory database into a distributed file system. This avoids damage to the original data and improves data analysis efficiency.

[0174] In one embodiment, the distributed storage device can be a single memory, multiple memories, or a collective term for multiple storage elements. For example, the memory may include: Random Access Memory (RAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDR SRAM), and may also include non-volatile memory, such as disk storage, flash memory, etc.

[0175] The data processing device is used to implement the above-mentioned operations of acquiring measurement information and acquiring defect information, and can be implemented, for example, based on Spark (a computing engine). The data processing device can obtain production records of one or more sample production equipment from a distributed storage device, such as defect information and measurement information in the film layer of the product. Specifically, it can obtain the defect information and measurement information detected in the current film layer from the distributed storage device (e.g., from HBase), determine the target location of the defect information and measurement information in the current film layer, and determine whether there is defect information at the corresponding location of the target location in the historical film layer. If defect information exists at the target location in the historical film layer, the defect information detected at the target location in the current film layer is deleted. If defect information does not exist at the target location in the historical film layer, the defect information detected at the target location in the current film layer is retained. The measurement information and the retained defect information are stored in the distributed storage device (e.g., stored in HBase).

[0176] The display device is used to display front-end data and for user interaction. For example, the interface may include a first interface, a second interface, and a third interface, as described below. For instance, the display device may display the processing results of the data processing device.

[0177] In one embodiment, the display device may be a monitor, or a product including a monitor, such as a television, computer (all-in-one or desktop), computer, tablet computer, mobile phone, electronic display, etc. In one embodiment, the display device may be any device that displays images, whether moving (e.g., video) or fixed (e.g., still image), and whether text or images. More specifically, the embodiments are contemplated to be implemented in or associated with a variety of electronic devices, such as (but not limited to) game consoles, television monitors, flat panel displays, computer monitors, automotive displays (e.g., odometer displays, etc.), navigators, cockpit controllers and / or displays, electronic photographs, electronic billboards or signs, projectors, architectural structures, packaging and aesthetic structures (e.g., a display of an image of a piece of jewelry), etc.

[0178] In one embodiment, the display device described herein may include one or more displays, including one or more terminals with display functions, so that the data processing device can send its processed data (e.g., influencing parameters) to the display device, which then displays it. In other words, through the interface of the display device (i.e., the user interface), the user can fully interact with the system for analyzing the causes of sample defects (controlling and receiving results).

[0179] Figure 3 This is a schematic flowchart illustrating another relevance determination method according to an embodiment of this disclosure. Figure 3 As shown, the defect information also includes defect location. In this case, the defect type in the defect information is a defect type whose defect location can be determined. Then, the influence weight of the measurement index that determines the measurement value at the measurement location on the defect type of the defect information includes:

[0180] In step S301, for each measurement location, the influence weight is determined based on the measurement location and the defective location.

[0181] In one embodiment, there are various types of defects. Some defect types have identifiable locations, such as bright spots and dark spots, so the location of the defect can be recorded. However, some defect information cannot or is difficult to determine the location of the defect, such as the entire display panel being unresponsive to touch. In such cases, NaN can be used as the coordinate. For example, defect information can be shown in Table 4 below:

[0182]

[0183] Table 4

[0184] As shown in Table 4, x and y represent the horizontal and vertical coordinates, respectively. Seven locations on the display panel were found to have defects of the type of bright spots, and touch failure of the display panel was also detected.

[0185] In one embodiment, sampling measurements can be performed separately for each membrane layer to obtain measurement information.

[0186]

[0187] Table 5

[0188] As shown in Table 5, x and y represent the horizontal and vertical axes, respectively. Taking the thickness THK as the measurement index and the measurement of 4 measurement points in each film layer as an example, in film layer GAT1, the measurement value at measurement position (10,10) is 1.2, the measurement value at measurement position (90,10) is 1.3, the measurement value at measurement position (90,90) is 1.5, and the measurement value at measurement position (10,90) is 1.4; in film layer GAT2, the measurement value at measurement position (10,10) is 1.2, the measurement value at measurement position (90,10) is 1.3, the measurement value at measurement position (90,90) is 1.5, and the measurement value at measurement position (10,90) is 1.4.

[0189] The units for the horizontal and vertical axes and the thickness can be determined according to the actual situation. For example, the units for the horizontal and vertical axes are pixels, and the units for the thickness are millimeters.

[0190] It should be noted that since the display panel is obtained by segmenting the Glass, the display panel generally only corresponds to a part of the Glass, while the measurement information includes the measurement information within the entire Glass range. In order to reduce the amount of computation, when determining the influence weight of bad information in a certain panel, the measurement information obtained can be obtained by first determining the corresponding area of ​​the panel in the Glass, and then obtaining the measurement information for that area.

[0191] For the "bright spot" defect type in Table 4, since the location of the defect can be determined, and although there should be an intuitive correlation between measurement information and defect information, there is currently no indicator that can link the two. The influence weight of the measurement point in the film layer on the defect is related to the measurement location of the measurement point and the location of the defect. Therefore, for each measurement point, the influence weight can be determined according to the measurement location and the defect location, and then used as an intermediate indicator to link the measurement information and the defect information. The degree of correlation between the measurement information and the defect information can be determined according to the influence weight.

[0192] In one embodiment, the influence weight is inversely correlated with the distance between the measurement location and the defective location. For example, the distance between the measurement location and the defective location can be determined first, and then a relationship between the influence weight and the distance can be established, where the distance is inversely correlated with the influence weight. That is, the farther the defective location is from the measurement point, the smaller the influence of the measurement point on it.

[0193] In one embodiment, determining the influence weight for each measurement location based on the measurement location and the defective location includes:

[0194] For each of the measurement locations ( The influence weights are determined respectively:

[0195] ;

[0196] in,( ) represents the defective location, k is the attenuation parameter, and R is the range parameter.

[0197] In one embodiment, in addition to considering the measurement location and the defective location, other parameters may be further considered to determine the influence weight, such as the attenuation parameter k and the range parameter R.

[0198] Both k and R are adjustable. Adjusting k controls the rate of distance decay, while adjusting R adjusts the range of unfavorable locations near the measurement point that are considered in determining the influence weights. This allows for flexible adjustment of the formula for determining the influence weights, enabling the appropriate determination of influence weights based on actual needs. For example, k=1 and R=20 mm can be set.

[0199] It should be noted that in the above formula, for each measurement point, the influence weight of the measurement point on all defect locations needs to be determined. For example, taking Tables 4 and 5 as examples, for the measurement point (10,10) in film layer GTA1, the 8 locations in Table 4 need to be substituted into the above formula for summation to determine the influence weight. , indicating that the measured value of the measurement point (10,10) in membrane layer GTA1 is 1.2, which is the influence weight of the defect type "bright spot" in Table 4; similarly, for the 4 measurement points in membrane layer GTA1 in Table 5, 4 influence weights can be obtained, and for the 4 measurement points in membrane layer GTA2 in Table 5, 4 influence weights can also be obtained.

[0200] In one embodiment, the defect information does not include defect location. In this case, the defect type in the defect information is a defect type for which the defect location cannot be determined. Then, determining the influence weight of the measurement index having the measurement value at the measurement location on the defect type of defect information includes: determining the influence weight to a preset value, for example, it can be set to 1, while for the case of no defect information, the influence weight can be set to 0.

[0201] Taking Tables 4 and 5 above as examples, for the type of defect called touch failure, four influence weights can be obtained for the four measurement points in film layer GTA1 in Table 5, all of which are 1. Four influence weights can also be obtained for the four measurement points in film layer GTA2 in Table 5, all of which are also 1.

[0202] Based on Tables 4 and 5, the determined impact weights for the two types, "bright spots" and "touch failure," are shown in Table 6:

[0203]

[0204] Table 6

[0205] As shown in Table 6, only some of the influence weights obtained based on Tables 4 and 5 are shown. For example, in film layer GAT1, the measured value of 1.2 at measurement position (10,10) has an influence weight of 0.60653 for the defect type "bright spot" in the actual panel; for example, in film layer GAT2, the measured value of 1.5 at measurement position (90,90) has an influence weight of 2.463531 for the defect type "bright spot" in the actual panel.

[0206] In one embodiment, the method further includes:

[0207] Among the defective locations, target defective locations are identified where the distance to the measurement location is less than a distance threshold; wherein, the distance threshold is determined based on R, ( This belongs to the target defect location.

[0208] Figure 4 This is a schematic diagram illustrating the relationship between a range parameter and an influence weight, according to an embodiment of the present disclosure.

[0209] like Figure 4 As shown, taking R=20 mm as an example, when R is greater than 60 mm, the influence of weights is... The value is approximately zero, meaning that the measurement point has virtually no effect on defects located more than 60 millimeters away. Therefore, there is no need to consider the influence of the measurement point on defects located more than 60 millimeters away.

[0210] Therefore, among the defective locations, target defective locations whose distance to the measurement location is less than a distance threshold can be determined, and ( The location of the defective element is considered as belonging to the target defective location. This means that only the defective location closest to the measurement point needs to be substituted into the above formula for determination. This reduces the number of determinations without affecting the result. The distance threshold can be determined based on R, for example, it can be set to 3R.

[0211] Figure 5 This is a schematic flowchart illustrating another correlation determination method according to an embodiment of this disclosure. Figure 5 As shown, determining the correlation coefficient between the influence weight and the measurement value includes:

[0212] In step S501, the correlation coefficient is determined according to at least one correlation coefficient determination method.

[0213] In one embodiment, the correlation coefficient between the influencing weights and the measured values ​​can be determined based on whether the set of influencing weights and the set of measured values ​​are on a straight line.

[0214] One or more correlation coefficient determination algorithms can be selected as needed, such as the Pearson algorithm, Spearmans algorithm, etc.

[0215] Taking the Pearson algorithm as an example, and using the influence weights shown in Table 6 as an example, the influence weights and measured values ​​can be used as x and y in the Pearson algorithm, respectively, and can be represented in tabular form as shown in Tables 7 and 8:

[0216]

[0217] Table 7

[0218]

[0219] Table 8

[0220] Table 7 shows the impact weight of the defect type "bright spots", and Table 8 shows the impact weight of the defect type "touch failure".

[0221] The Pearson correlation coefficient, determined by the Pearson algorithm, is primarily used to measure whether two data sets, x and y, are aligned. The formula is as follows:

[0222] Correlation coefficient .

[0223] The correlation coefficient can be determined for each type of defect. For example, by substituting x and y in Table 7 above into the Pearson correlation coefficient formula, the obtained correlation coefficient can be used to represent the correlation between thickness and bright spots. Similarly, by substituting x and y in Table 8 above into the Pearson correlation coefficient formula, the obtained correlation coefficient can be used to represent the correlation between thickness and touch failure.

[0224] Figure 6 This is a schematic flowchart illustrating another correlation determination method according to an embodiment of this disclosure. Figure 6 As shown, determining the correlation coefficient between the influence weight and the measured value further includes:

[0225] In step S601, the confidence level of the correlation coefficient is determined.

[0226] In one embodiment, for the determined correlation coefficient, the confidence level of the correlation coefficient can be further determined in order to judge the reasonableness of the correlation coefficient.

[0227] There are several ways to determine the confidence level, and the specific method can be chosen according to the needs. For example, the p-value can be used to represent the confidence level. Constructing a t-distribution based on relevant statistical test theory and substituting it into the t-distribution yields:

[0228] ;

[0229] ;

[0230] in, Let T be a t-distribution with N-2 combined degrees of freedom.

[0231] The correlation coefficient and confidence level values ​​are shown in Table 9:

[0232]

[0233] Table 9

[0234] The smaller the p-value, the higher the confidence level. Generally, a correlation coefficient with a p-value < 0.05 can be considered a reliable correlation coefficient.

[0235] It should be noted that, in addition to determining the Pearson correlation coefficient based on the above embodiments, other methods can also be used to determine the correlation coefficient.

[0236] In one embodiment, the correlation coefficient between the influence weight and the measured value can be determined based on the level corresponding to the average descending position of the influence weight among all influence weights and the level corresponding to the average descending position of the measured value among all measured values.

[0237] For example, to determine the Spearmans correlation coefficient, the measured values ​​can be classified into levels according to the mean value set in the process. The maximum and minimum values ​​of the index can be set, and expressed in a form similar to 5±1, for example, taking 5 as θ and 1 as δ. The numerical conversion formula is shown in Table 10.

[0238]

[0239] Table 10

[0240] The Spearmans correlation coefficient and confidence level values ​​determined accordingly are shown in Table 11:

[0241]

[0242] Table 11

[0243] Figure 7 This is a schematic flowchart illustrating another correlation determination method according to an embodiment of this disclosure. Figure 7 As shown, determining the correlation coefficient according to at least one correlation coefficient determination method includes:

[0244] In step S701, the independent correlation coefficients of the influence weight and the measurement value are determined according to multiple correlation coefficient determination algorithms.

[0245] The determination of the correlation coefficient between the influence weight and the measurement value further includes:

[0246] In step S702, the relevant weight of each independent correlation coefficient is determined based on the confidence level of each independent correlation coefficient;

[0247] In step S703, each independent correlation coefficient is weighted and summed according to the relevant weights to obtain the joint correlation coefficient.

[0248] In one embodiment, the correlation coefficient can be determined according to multiple correlation coefficient determination algorithms, and then the determined correlation coefficients can be weighted and summed to obtain the final correlation coefficient.

[0249] For example, the independent correlation coefficients of the influence weights and the measurement values ​​can be determined first using multiple correlation coefficient determination algorithms. Then, based on the confidence level of each independent correlation coefficient, the correlation weight of each independent correlation coefficient can be determined. Finally, the independent correlation coefficients are weighted and summed using the determined weights.

[0250] To determine the Pearson correlation coefficient Correlation coefficient with Spearmans For example, among which The confidence level is , The confidence level is Then, the joint correlation coefficient r can be obtained by weighted summation according to the following formula:

[0251] The joint correlation coefficient r and confidence level values ​​are shown in Table 12:

[0252]

[0253] Table 12

[0254] Since each algorithm considers different perspectives when determining the correlation coefficient, the joint correlation coefficient obtained by combining the correlation coefficients calculated by multiple algorithms is beneficial to ensuring accuracy in more scenarios.

[0255] According to embodiments of this disclosure, in the user interface (UI), defect information can be displayed separately according to defect type. Users can click on a defect type to execute the steps in the method described in any of the above embodiments, obtaining the correlation between measurement information and defect information, such as the correlation coefficient mentioned above. Furthermore, the confidence level of each correlation can be displayed, for example, in the form of tables 9, 11, and 12 in the above embodiments, so that users can comprehensively analyze the reliability of the correlation. Users can also click on any row in the table to display a comparison chart of the measurement information and defect information in that row on the display panel, allowing users to intuitively view the status of the measurement information and defect information.

[0256] Corresponding to the embodiments of the correlation determination method described above, this disclosure also proposes embodiments of a correlation determination apparatus.

[0257] This disclosure provides a relevance determination device, which may be a terminal, server, or other similar device. In one embodiment, the device includes one or more processors, which are configured to:

[0258] Acquire measurement information and defect information of the display panel, wherein the measurement information includes the measurement value and measurement location of the measurement index, and the defect information includes the defect type;

[0259] Determine the influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type;

[0260] Determine the correlation coefficient between the influence weight and the measurement value, and determine the correlation between the measurement information and the adverse information based on the correlation coefficient.

[0261] In one embodiment, the measurement parameters include at least one of the following: film thickness, resistance, and forward voltage.

[0262] In one embodiment, the defect type includes at least one of the following: bright spot, dark spot, bright line, dark line, touch failure, and sexual resistance.

[0263] In one embodiment, the defect information further includes defect locations, and the processor is configured to determine the influence weight for each measurement location based on the measurement location and the defect location.

[0264] In one embodiment, the processor is configured to: for each of the measurement locations ( The influence weights are determined respectively:

[0265] ;

[0266] in,( ) represents the defective location, k is the attenuation parameter, and R is the range parameter.

[0267] In one embodiment, the processor is configured to: determine, within the defect location, a target defect location whose distance to the measurement location is less than a distance threshold; wherein the distance threshold is determined based on R, ( This belongs to the target defect location.

[0268] In one embodiment, the adverse information does not include adverse locations, and the processor is configured to determine the influence weight as a preset value.

[0269] In one embodiment, the processor is configured to determine the correlation coefficient according to at least one correlation coefficient determination method.

[0270] In one embodiment, the processor is further configured to determine the confidence level of the correlation coefficient.

[0271] In one embodiment, the processor is configured to: determine the influence weights and the independent correlation coefficients of the measurement values ​​according to multiple correlation coefficient determination methods; determine the correlation weight of each independent correlation coefficient according to the confidence level of each independent correlation coefficient; and perform a weighted summation of each independent correlation coefficient according to the correlation weights to obtain a joint correlation coefficient.

[0272] Embodiments of this disclosure also provide an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the relevance determination method described in any of the above embodiments.

[0273] Embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the relevance determination method described in any of the above embodiments.

[0274] Figure 8 This is a schematic block diagram illustrating an apparatus 800 for relevance determination according to embodiments of the present disclosure. For example, apparatus 800 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0275] Reference Figure 8 The device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0276] Processing component 802 typically controls the overall operation of device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0277] Memory 804 is configured to store various types of data to support the operation of device 800. Examples of this data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0278] Power supply component 806 provides power to various components of device 800. Power supply component 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to device 800.

[0279] Multimedia component 808 includes a screen that provides an output interface between the device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0280] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0281] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0282] Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of device 800. For example, sensor assembly 814 may detect the on / off state of device 800, the relative positioning of components such as the display and keypad of device 800, changes in the position of device 800 or a component of device 800, the presence or absence of user contact with device 800, the orientation or acceleration / deceleration of device 800, and temperature changes of device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0283] Communication component 816 is configured to facilitate wired or wireless communication between device 800 and other devices. Device 800 can access wireless networks based on communication standards, such as WiFi, 2G or 3G, 4G LTE, 5G NR, or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0284] In an exemplary embodiment, the apparatus 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0285] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of the device 800 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0286] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0287] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0288] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0289] The methods and apparatus provided in the embodiments of this disclosure have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this disclosure. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this disclosure. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this disclosure. Therefore, the content of this specification should not be construed as a limitation of this disclosure.

Claims

1. A method for determining relevance, characterized in that, include: Acquire measurement information and defect information of the display panel, wherein the measurement information includes the measurement value and measurement location of the measurement index, and the defect information includes the defect type; Determine the influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type; Determine the correlation coefficient between the influence weight and the measurement value, and determine the correlation between the measurement information and the adverse information based on the correlation coefficient.

2. The method according to claim 1, characterized in that, The measurement index includes at least one of the following: Film thickness, resistance, and forward voltage.

3. The method according to claim 1, characterized in that, The defect type includes at least one of the following: Bright spots, dark spots, bright lines, dark lines, touch failure.

4. The method according to claim 1, characterized in that, The adverse information also includes the location of the adverse condition, and the influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type includes: For each measurement location, the influence weight is determined based on the measurement location and the defective location.

5. The method according to claim 4, characterized in that, The influence weight is inversely correlated with the distance between the measurement location and the defective location.

6. The method according to claim 5, characterized in that, Determining the influence weight for each measurement location based on the measurement location and the defective location includes: For each of the measurement locations ( The influence weights are determined respectively: ； in,( ) represents the defective location, k is the attenuation parameter, and R is the range parameter.

7. The method according to claim 6, characterized in that, The method further includes: Among the defective locations, target defective locations whose distance to the measurement location is less than a distance threshold are identified; Wherein, the distance threshold is determined based on R, ( This belongs to the target defect location.

8. The method according to claim 1, characterized in that, The adverse information does not include the location of the adverse condition. The influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type includes: The influence weight is determined to be a preset value.

9. The method according to claim 1, characterized in that, Determining the correlation coefficient between the influence weight and the measurement value includes: The correlation coefficient is determined according to at least one correlation coefficient determination method.

10. The method according to claim 9, characterized in that, Determining the correlation coefficient between the influence weight and the measurement value further includes: Determine the confidence level of the correlation coefficient.

11. The method according to claim 10, characterized in that, Determining the correlation coefficient according to at least one correlation coefficient determination method includes: The independent correlation coefficients of the influence weights and the measurement values ​​are determined using multiple correlation coefficient determination algorithms. The determination of the correlation coefficient between the influence weight and the measurement value further includes: The relevant weight of each independent correlation coefficient is determined based on the confidence level of each independent correlation coefficient; The independent correlation coefficients are weighted and summed according to the relevant weights to obtain the joint correlation coefficient.

12. A correlation determination device, characterized in that, Includes one or more processors, said processors being configured to: Acquire measurement information and defect information of the display panel, wherein the measurement information includes the measurement value and measurement location of the measurement index, and the defect information includes the defect type; Determine the influence weight of the measurement index having the measurement value at the measurement location on the adverse information of the adverse type; Determine the correlation coefficient between the influence weight and the measurement value, and determine the correlation between the measurement information and the adverse information based on the correlation coefficient.

13. The apparatus according to claim 12, characterized in that, The defect information also includes defect locations, and the processor is configured to determine the influence weight for each measurement location based on the measurement location and the defect location.

14. The apparatus according to claim 13, characterized in that, The processor is configured to: for each of the measurement locations ( The influence weights are determined respectively: ； in,( ) represents the defective location, k is the attenuation parameter, and R is the range parameter.

15. The apparatus according to claim 14, characterized in that, The processor is configured to: determine, within the defective locations, target defective locations whose distance to the measurement location is less than a distance threshold; wherein the distance threshold is determined based on R, ( This belongs to the target defect location.

16. The apparatus according to claim 12, characterized in that, The processor is configured to determine the correlation coefficient according to at least one correlation coefficient determination method.

17. The apparatus according to claim 16, characterized in that, The processor is also configured to determine the confidence level of the correlation coefficient.

18. The apparatus according to claim 17, characterized in that, The processor is configured to: determine the influence weights and the independent correlation coefficients of the measurement values ​​according to multiple correlation coefficient determination methods; determine the correlation weights of each independent correlation coefficient according to the confidence level of each independent correlation coefficient; and perform a weighted summation of each independent correlation coefficient according to the correlation weights to obtain a joint correlation coefficient.

19. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement the relevance determination method according to any one of claims 1 to 11.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the relevance determination method according to any one of claims 1 to 11.

Images