CN117934804B - Method and related device for determining whether wafer is qualified for needle insertion - Google Patents

Method and related device for determining whether wafer is qualified for needle insertion Download PDF

Info

Publication number
CN117934804B
CN117934804B CN202410294703.3A CN202410294703A CN117934804B CN 117934804 B CN117934804 B CN 117934804B CN 202410294703 A CN202410294703 A CN 202410294703A CN 117934804 B CN117934804 B CN 117934804B
Authority
CN
China
Prior art keywords
electrode
rectangular frame
horizontal
needle mark
coordinate
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202410294703.3A
Other languages
Chinese (zh)
Other versions
CN117934804A (en
Inventor
刘世文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Senmei Xieer Technology Co ltd
Original Assignee
Shenzhen Senmei Xieer Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Senmei Xieer Technology Co ltd filed Critical Shenzhen Senmei Xieer Technology Co ltd
Priority to CN202410294703.3A priority Critical patent/CN117934804B/en
Publication of CN117934804A publication Critical patent/CN117934804A/en
Application granted granted Critical
Publication of CN117934804B publication Critical patent/CN117934804B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30Computing systems specially adapted for manufacturing

Landscapes

  • Testing Or Measuring Of Semiconductors Or The Like (AREA)

Abstract

The application discloses a method and a related device for determining whether a wafer is qualified for needle insertion, wherein the method comprises the following steps: acquiring a first horizontal external rectangular frame corresponding to each electrode and a second horizontal external rectangular frame corresponding to each needle mark in a target wafer; the following is performed for each electrode: obtaining a first slice horizontal rectangular frame according to the first horizontal external rectangular frame; acquiring a first image feature of an image area where a first slice horizontal rectangular frame is located; acquiring a first electrode offset and a first needle mark offset according to a first electrode coordinate of the electrode, a first needle mark coordinate of a needle mark corresponding to the electrode and a first image characteristic; determining a target electrode coordinate according to the first electrode offset, and determining a target needle mark coordinate according to the first needle mark offset; and judging whether the electrode is qualified for needling according to the target electrode coordinates and the target needle mark coordinates. The application can improve the speed of judging whether the puncture is qualified or not under the condition of ensuring the positioning precision of the counter electrode and the needle mark.

Description

Method and related device for determining whether wafer is qualified for needle insertion
Technical Field
The present application relates to the field of semiconductor device applications, and more particularly, to a method and apparatus for determining whether a wafer is properly inserted.
Background
Along with the continuous progress of the technology in the semiconductor field, in order to know the yield of the wafer in time in the production process, the wafer needs to be tested through a probe card, the probe card is provided with a plurality of probes, the probes of the probe card touch electrodes in a chip to detect whether the function of the chip is abnormal, after the probes touch the electrodes in the chip, the probe card needs to detect needle marks, and whether the needle insertion effect is qualified is judged through the detection of the needle marks.
The current needle mark detection method cannot consider the speed of judging whether the needle insertion is qualified or not under the condition of ensuring accurate positioning.
Disclosure of Invention
The embodiment of the application provides a method and a related device for determining whether a wafer is inserted into a needle or not, so that the speed for judging whether the needle is inserted into the needle is improved under the condition of ensuring the positioning precision of a counter electrode and a needle mark.
In a first aspect, an embodiment of the present application provides a method for determining whether a wafer is qualified for being inserted, including:
Acquiring a first horizontal external rectangular frame corresponding to each electrode and a second horizontal external rectangular frame corresponding to each needle mark in a target wafer through a pre-trained first model, wherein an electrode area of each electrode is completely included in the corresponding first horizontal external rectangular frame, a needle mark area of each needle mark is completely included in the corresponding second horizontal external rectangular frame, each first horizontal external rectangular frame corresponds to a first electrode coordinate, and each second horizontal external rectangular frame corresponds to a first needle mark coordinate;
The following is performed for each electrode:
Obtaining a first slice horizontal rectangular frame according to a first horizontal external rectangular frame corresponding to the electrode, wherein the first slice horizontal rectangular frame is identical to the central point of the first horizontal external rectangular frame, and the area of the first slice horizontal rectangular frame is M times of the area of the first horizontal external rectangular frame;
acquiring a first image feature of an image area where the first slice horizontal rectangular frame is located;
Inputting a pre-trained second model according to a first electrode coordinate of the electrode, a first needle mark coordinate of a needle mark corresponding to the electrode and the first image characteristic, and obtaining a first electrode offset and a first needle mark offset;
acquiring a target electrode coordinate according to the first electrode offset and the first electrode coordinate, and acquiring a target needle mark coordinate according to the first needle mark offset and the first needle mark coordinate of the needle mark corresponding to the electrode;
and judging whether the electrode is qualified for needling according to the target electrode coordinates and the target needle mark coordinates.
In a second aspect, an embodiment of the present application provides an apparatus for determining whether a wafer is qualified for being inserted, including:
The device comprises an acquisition unit, a first horizontal external rectangular frame, a second horizontal external rectangular frame, a first electrode coordinate and a second electrode coordinate, wherein the first horizontal external rectangular frame corresponds to each electrode in a target wafer and the second horizontal external rectangular frame corresponds to each needle mark through a pre-trained first model;
An execution unit for executing the following operations for each electrode: obtaining a first slice horizontal rectangular frame according to a first horizontal external rectangular frame corresponding to the electrode, wherein the first slice horizontal rectangular frame is identical to the central point of the first horizontal external rectangular frame, and the area of the first slice horizontal rectangular frame is M times of the area of the first horizontal external rectangular frame; acquiring a first image characteristic of an image area where the first slice horizontal rectangular frame is located; inputting a first needle mark coordinate of a needle mark corresponding to the electrode and the first image characteristic into a pre-trained second model according to the first electrode coordinate of the electrode to obtain a first electrode offset and a first needle mark offset; obtaining a target electrode coordinate according to the first electrode offset and the first electrode coordinate, and obtaining a target needle mark coordinate according to the first needle mark offset and the first needle mark coordinate of the needle mark with the corresponding relation with the electrode; and judging whether the electrode is qualified for needling according to the target electrode coordinates and the target needle mark coordinates.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory storing execution instructions, the memory storing one or more programs; the processor performs the method as described in the first aspect when the processor executes the execution instructions stored in the memory.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing an energy data management program comprising execution instructions, which when executed by a processor of an electronic device, perform a method as described in the first aspect.
It can be seen that, in the embodiment of the present application, first, a first horizontal circumscribed rectangular frame corresponding to each electrode and a second horizontal circumscribed rectangular frame corresponding to each needle trace in a target wafer are obtained through a first model trained in advance, an electrode area of each electrode is completely included in the corresponding first horizontal circumscribed rectangular frame, a needle trace area of each needle trace is completely included in the corresponding second horizontal circumscribed rectangular frame, each first horizontal circumscribed rectangular frame corresponds to a first electrode coordinate, and each second horizontal circumscribed rectangular frame corresponds to a first needle trace coordinate; the following is then performed for each electrode: obtaining a first slice horizontal rectangular frame according to a first horizontal external rectangular frame corresponding to the electrode, wherein the first slice horizontal rectangular frame is identical to the central point of the first horizontal external rectangular frame, and the area of the first slice horizontal rectangular frame is M times of the area of the first horizontal external rectangular frame; acquiring a first image feature of an image area where the first slice horizontal rectangular frame is located; inputting a pre-trained second model according to a first electrode coordinate of the electrode, a first needle mark coordinate of a needle mark corresponding to the electrode and the first image characteristic, and obtaining a first electrode offset and a first needle mark offset; acquiring a target electrode coordinate according to the first electrode offset and the first electrode coordinate, and acquiring a target needle mark coordinate according to the first needle mark offset and the first needle mark coordinate of the needle mark corresponding to the electrode; and finally judging whether the electrode is qualified for needling according to the target electrode coordinates and the target needle mark coordinates. The application comprehensively analyzes whether the puncture is qualified by determining the positions of the electrode and the needle mark, so that the speed for judging whether the puncture is qualified is improved under the condition of ensuring the positioning accuracy of the electrode and the needle mark.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for determining whether a wafer is qualified for needle punching according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a horizontal circumscribed rectangular frame according to an embodiment of the present application;
FIG. 3 is a schematic view of a sliced horizontal rectangular frame according to an embodiment of the present application;
FIG. 4 is a schematic diagram showing the relationship between electrodes and a horizontal circumscribed rectangular frame of a trace according to an embodiment of the present application;
FIG. 5 is a functional block diagram of an apparatus for determining whether a wafer is eligible for needle punching according to an embodiment of the present application;
FIG. 6 is a functional block diagram of another apparatus for determining whether a wafer is eligible for a needle insertion according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
At present, the speed and the positioning accuracy cannot be considered when the needle mark is detected.
Referring to fig. 1, fig. 1 is a flowchart of a method for determining whether a wafer is qualified for being inserted, and as shown in fig. 1, the method includes the following steps.
S110, acquiring a first horizontal circumscribed rectangle frame corresponding to each electrode and a second horizontal circumscribed rectangle corresponding to each needle mark in the target wafer through a pre-trained first model.
According to the marked electrode pictures and the needle mark pictures, the target detection model yolov model based on the deep learning is used as an initial model for training, and a trained first model is obtained. Wherein yolov's 4 model learns features in an image by using convolutional neural networks and uses these features to predict the location and class of objects in the image. Referring to fig. 2, fig. 2 is a schematic diagram of a horizontal circumscribed rectangular frame according to an embodiment of the present application, as shown in fig. 2, the horizontal circumscribed rectangular frame 20, and the images 210, a, B, C, D of the needle mark respectively represent the coordinates of four corners of the horizontal circumscribed rectangular frame 20, wherein the origin coordinates are not limited herein, and may be any point on the wafer. Based on the abscissa and ordinate of the point a on the horizontal bounding rectangle 20, and the width and height of the horizontal bounding rectangle 20, i.e. one needle mark coordinate is denoted (x 2, y2, w2, h 2). In the case where the electrode image is inside the horizontal circumscribed rectangular frame 20, it is determined based on the abscissa and ordinate of the point a on the horizontal circumscribed rectangular frame 20, and the width and height of the horizontal circumscribed rectangular frame 20, that is, one electrode coordinate is expressed as (x 1, y1, w1, h 1).
After the first electrode coordinates and the first needle mark coordinates are obtained, ordering each first electrode coordinate and each first needle mark coordinate, and determining that the electrode included in the first horizontal external rectangular frame corresponds to the needle mark included in the second horizontal external rectangular frame one by one if the first horizontal external rectangular frame completely comprises the second horizontal external rectangular frame; if the first horizontal circumscribed rectangular frame does not completely comprise the second horizontal circumscribed rectangular frame, namely only a part of the first horizontal circumscribed rectangular frame is intersected, modifying the needle mark coordinates included in the second horizontal circumscribed rectangular frame into null values; and if the second horizontal circumscribed rectangular frame and any one of the first horizontal circumscribed rectangular frames have no corresponding relation, deleting the first needle mark coordinates.
S120, obtaining a first slice horizontal rectangular frame according to the first horizontal external rectangular frame corresponding to the electrode.
The first horizontal rectangular frame is identical to the first horizontal circumscribed rectangular frame in center point, and the area of the first horizontal rectangular frame is M times of the area of the first horizontal circumscribed rectangular frame, wherein M is larger than 1. Referring to fig. 3, fig. 3 is a schematic diagram of a sliced horizontal rectangular frame according to an embodiment of the present application, and as shown in fig. 3, a sliced horizontal rectangular frame 30 is obtained by enlarging a horizontal circumscribed rectangular frame in equal proportion.
S130, acquiring a first image feature of an image area where the first slice horizontal rectangular frame is located.
The number of patterns on the wafer is large, and the complexity of the image can be determined according to the number of contours, so that the first image features can include an average gray value of the image, the number of pixels with gray values larger than a certain preset value, the number of pixels with gray values smaller than a certain preset value, and the number of contours after binarization. The binarization is a process of setting the gray value of a pixel point on an image to 0 or 255, that is, displaying a clear black-and-white effect on the whole image, so as to analyze the shape and contour of an object.
And S140, inputting a pre-trained second model according to the first electrode coordinate of the electrode, the first needle mark coordinate of the needle mark corresponding to the electrode and the first image characteristic, and obtaining a first electrode offset and a first needle mark offset.
And training the second model by taking the electrode coordinates, the needle mark coordinates and the image characteristics as inputs and taking the electrode offset and the needle mark offset as outputs to obtain a trained second model. The method comprises the steps of obtaining a contour map of an electrode or a needle mark in a slice horizontal rectangular frame through a traditional image positioning algorithm, obtaining a horizontal external rectangular frame of the contour map, positioning electrode coordinates (x 3, y3, w3, h 3) or positioning needle mark coordinates (x 4, y4, w4, h 4) according to the horizontal external rectangular frame of the contour map, calculating electrode offset according to (x 1, y1, w1, h 1) and (x 3, y3, w3, h 3), and calculating the needle mark offset according to (x 2, y2, w2, h 2) and (x 4, y4, w4, h 4).
S150, acquiring target electrode coordinates according to the first electrode offset and the first electrode coordinates, and acquiring target needle mark coordinates according to the first needle mark offset and the first needle mark coordinates of the needle mark with the corresponding relation with the electrode;
After the target electrode coordinate and the target trace coordinate are obtained, firstly determining whether the target trace coordinate corresponding to the target electrode coordinate is a null value, if so, indicating that the probe does not detect the electrode or that the probe is abnormal, and outputting an alarm signal to prompt a worker to check.
And S160, judging whether the electrode is qualified by needling according to the target electrode coordinates and the target needle mark coordinates.
Under the condition that the target needle mark coordinate corresponding to the target electrode coordinate is not null, respectively acquiring the target electrode coordinate and a new horizontal external rectangular frame corresponding to the target needle mark coordinate, and determining that the needle insertion is not qualified when the distance between the central points of the two horizontal external rectangular frames is larger than a preset value or when the area of the horizontal external rectangular frame corresponding to the target needle mark coordinate is not within a preset area range. I.e. the needle insertion criteria may be: needle marks exist on the electrode; the distance between the center points of the two horizontal external rectangular frames is smaller than a preset value; and the area of the horizontal circumscribed rectangular frame corresponding to the target needle mark coordinate is within a preset area range.
Therefore, in this embodiment, by determining the positions of the electrode and the needle mark, whether the puncture is qualified is comprehensively analyzed, so that the speed of judging whether the puncture is qualified is improved under the condition that the positioning accuracy of the electrode and the needle mark is ensured.
In one possible embodiment, before the inputting the first image feature into the pre-trained second model according to the first electrode coordinate of the electrode, the first needle mark coordinate of the needle mark corresponding to the electrode, and the first image feature, the method further includes: acquiring a third horizontal external rectangular frame corresponding to each electrode and a fourth horizontal external rectangular frame corresponding to each needle mark in a reference wafer for training through a pre-trained first model, wherein each third horizontal external rectangular frame corresponds to a second electrode coordinate, and each fourth horizontal external rectangular frame corresponds to a second needle mark coordinate; acquiring a second slice horizontal rectangular frame corresponding to each electrode according to a third horizontal circumscribed rectangular frame corresponding to each electrode, wherein the second slice horizontal rectangular frame is the same as the center point of the third horizontal circumscribed rectangular frame, and the area of the second slice horizontal rectangular frame is S times of the area of the third horizontal circumscribed rectangular frame; determining a third electrode coordinate of each electrode according to the second slice horizontal rectangular frame; obtaining a third slice horizontal rectangular frame corresponding to each needle mark according to the fourth horizontal circumscribed rectangular frame of each needle mark, wherein the center point of the third slice horizontal rectangular frame is the same as that of the fourth horizontal circumscribed rectangular frame, and the area of the third slice horizontal rectangular frame is P times that of the fourth horizontal circumscribed rectangular frame; determining a third needle mark coordinate of each needle mark according to the third slice horizontal rectangular frame; acquiring a second image characteristic of an image area where a second slice horizontal rectangular frame corresponding to each electrode is located; determining a second electrode offset of each electrode according to the second electrode coordinates of each electrode and the third electrode coordinates of each electrode, and determining a second needle mark offset of each needle mark according to the second needle mark coordinates of each needle mark and the third needle mark coordinates of each needle mark; and training the second model according to the electrode coordinates, the second needle mark coordinates of each needle mark, the second image characteristic of each electrode, the second electrode offset of each electrode and the second needle mark offset of each needle mark to obtain the pre-trained second model.
The method comprises the steps of obtaining a plurality of electrode coordinate sets and needle mark coordinate sets on a wafer for training, wherein each electrode coordinate set comprises a plurality of electrode coordinates, each electrode coordinate corresponds to a horizontal external rectangular frame, each horizontal external rectangular frame comprises an electrode, the electrode coordinates are determined by the horizontal coordinate and the vertical coordinate of the upper left corner of the horizontal external rectangular frame, and the width and the height of the horizontal external rectangular frame, namely, one electrode coordinate is expressed as (x 1, y1, w1, h 1). The needle mark coordinate sets are contracted, each needle mark coordinate set comprises a plurality of needle mark coordinates, each needle mark coordinate corresponds to a horizontal external rectangular frame, each horizontal external rectangular frame comprises a needle mark, the needle mark coordinates are determined by the horizontal coordinate and the vertical coordinate of the upper left corner of the horizontal external rectangular frame and the width and the height of the horizontal external rectangular frame, namely, one needle mark coordinate is expressed as (x 2, y2, w2, h 2). And then preprocessing a plurality of electrode coordinate sets and needle mark coordinate sets, and screening the needle mark coordinates so that one needle mark corresponds to one electrode. And then, randomly taking a horizontal external rectangular frame corresponding to the electrode coordinates, and amplifying the horizontal external rectangular frame by M times to obtain a tangent plane horizontal rectangular frame of the electrode, wherein the sizes of the horizontal external rectangular frames corresponding to the electrode coordinates are equal. Determining a new horizontal external rectangular frame of the electrode from an image corresponding to the slice horizontal rectangular frame of the electrode according to the outline drawing of the electrode through a traditional image positioning algorithm, positioning the positioning coordinates (x 3, y3, w3, h 3) of the electrode according to the new horizontal external rectangular frame of the electrode, and calculating the electrode offset according to (x 1, y1, w1, h 1) and (x 3, y3, w3, h 3), wherein the needle marks are the same, and the needle mark offset is obtained.
The image analysis may be used to obtain a plurality of image features of the image corresponding to the slice horizontal rectangular frame of the electrode, which may include an average gray value of the image, a number of pixels with a gray value greater than 200, a number of pixels with a gray value less than 50, and a number of contours after binarization. The method comprises the steps of predicting electrode offset and needle mark offset through a plurality of image features, electrode coordinates and needle mark coordinates, calculating a predicted value and a truly calculated difference through a loss function, and finally updating parameters of a second model by using a gradient descent method to minimize the loss function. And continuously repeating the steps, training each data in the electrode coordinate sets and the needle mark coordinate sets, and finally obtaining a trained second model.
Wherein S, P and M may be the same.
It can be seen that in this embodiment, the accuracy of determining the positions of the electrode and the needle mark is improved.
In one possible embodiment, the determining the third electrode coordinates of each electrode according to the second slice horizontal rectangular frame includes: acquiring a contour map of an electrode included in each second slice horizontal rectangular frame; and determining a fifth horizontal circumscribed rectangular frame of the electrode included in each second slice horizontal rectangular frame according to the outline map, wherein the fifth horizontal circumscribed rectangular frame corresponds to a third electrode coordinate.
Referring to fig. 3, the image in the slice horizontal rectangular frame 30 is thresholded or edge detected to be converted into a binary image. An exemplary background is 255 and the foreground is 0, i.e. the outline of the black object is found in the binarized image. Wherein the step of determining the binarized image profile is as follows: 1. the binarized image is traversed to find a certain black pixel, and then the black pixel is taken as a starting point. 2. Dividing the starting 8 neighborhood into 8 directions, starting from 0 direction, setting the point as the current pixel if the 0 direction is a black pixel, otherwise adding one direction (rotating 45 degrees clockwise), continuing to judge until the black pixel exists, and discarding the current starting point if all the eight directions are traversed without the black pixel. 3. According to the new center point found in the second step, traversing the 8 neighborhood of the new center point along the direction of 90 degrees counterclockwise in the direction of the second step is started, and the operation is the same as that in the second step. As shown in fig. 3, the outline of the black object, i.e. the outline of the electrode, is determined. The bounding rectangle of each contour may be obtained using a function, drawn on the original image, and then the coordinates of the electrodes determined from the horizontal bounding rectangle of the resulting contour.
It can be seen that in this embodiment, redundant information is removed by binary statutory image coordinates, so that offset calculation is performed with the coordinates determined by the first model later, thereby training the second model.
In one possible embodiment, after the obtaining, by the pre-trained first model, the first horizontal circumscribed rectangular frame corresponding to each electrode and the second horizontal circumscribed rectangular frame corresponding to each needle mark in the target wafer, the method further includes: sequencing the first electrode coordinates corresponding to each first horizontal circumscribed rectangular frame and the first needle mark coordinates corresponding to each second horizontal circumscribed rectangular frame to obtain a sequencing result, wherein the sequencing result is used for indicating the corresponding relation between the first horizontal circumscribed rectangular frame and the second horizontal circumscribed rectangular frame; and screening the first needle mark coordinates corresponding to each second horizontal external rectangular frame according to the sequencing result to obtain a needle mark coordinate set, wherein each first needle mark coordinate in the needle mark coordinate set corresponds to one first electrode coordinate, each second horizontal external rectangular frame corresponding to each first needle mark coordinate in the needle mark coordinate set is contained in a first horizontal external rectangular frame corresponding to the first electrode coordinate with the corresponding relation, and the first electrode coordinate corresponds to one first needle mark coordinate or corresponds to a null value.
The method comprises the steps of carrying out corresponding sequencing on electrode coordinates and needle mark coordinates, namely analyzing according to a second horizontal external rectangular frame and a first horizontal external rectangular frame, determining the needle mark coordinates and the electrode coordinates as corresponding inclusion relations when the first horizontal external rectangular frame comprises the second horizontal external rectangular frame, and reserving the needle mark coordinates; if the first horizontal external rectangular frame is intersected with the second horizontal external rectangular frame, marking the needle mark coordinate as a null value; and deleting the needle mark coordinate if the second horizontal circumscribed rectangular frame is not related to any one of the first horizontal circumscribed rectangular frames. And finally obtaining the needle mark coordinates and electrode coordinates which correspond to each other one by one. Referring to fig. 4 for an exemplary illustration, fig. 4 is a schematic diagram showing a relationship between an electrode and a horizontal circumscribed rectangular frame of a needle trace according to an embodiment of the present application, as shown in fig. 4, a horizontal unidirectional long arrow indicates a horizontal coordinate X-axis, a vertical unidirectional long arrow indicates a vertical coordinate Y-axis, and assuming that the electrode coordinate is (13,15,3,4), the needle trace coordinate is (14,14,2,3), that is, a first horizontal circumscribed rectangular frame corresponding to a first electrode coordinate in fig. 4 completely includes a second horizontal circumscribed rectangular frame corresponding to a first needle trace coordinate; if the electrode coordinates are (2,4,3,4), the needle mark coordinates are (1, 2, 3), that is, the fourth horizontal circumscribed rectangular frame corresponding to the second electrode coordinates in fig. 4 does not completely include the third horizontal circumscribed rectangular frame corresponding to the second needle mark coordinates, and the needle mark coordinates are determined as null values in the intersecting relation; if the needle mark coordinate is (12,14,2,3), that is, the fifth horizontal circumscribed rectangular frame corresponding to the third needle mark coordinate in fig. 4 has no correlation with any horizontal circumscribed rectangular frame corresponding to the electrode coordinate, the needle mark coordinate is deleted.
Therefore, in this embodiment, by screening the needle marks, the needle marks and the electrodes are in one-to-one correspondence, so as to facilitate the subsequent judgment of whether the needle insertion is qualified.
In one possible embodiment, the determining whether the electrode is inserted into the needle is acceptable according to the target electrode coordinate and the target needle mark coordinate includes: acquiring a sixth horizontal circumscribed rectangular frame corresponding to the target electrode coordinate and a seventh horizontal circumscribed rectangular frame corresponding to the target needle mark coordinate; determining that the electrode needle insertion is not qualified when the distance between the center points of the seventh horizontal circumscribed rectangular frame and the sixth horizontal circumscribed rectangular frame is larger than a first preset value or when the area of the seventh horizontal circumscribed rectangular frame is not within a preset area range; and when the needle mark coordinate corresponding to the first electrode coordinate of the target electrode coordinate is determined to be a null value, outputting an alarm signal, wherein the alarm signal is used for prompting a worker that the probe is abnormal.
After the target electrode coordinate and the target trace coordinate are obtained, firstly determining whether the target trace coordinate corresponding to the target electrode coordinate is a null value, if so, indicating that the probe does not detect the electrode or that the probe is abnormal, and outputting an alarm signal to prompt a worker to check. When the target needle mark coordinate corresponding to the target electrode coordinate is not a null value, the target electrode coordinate and the target needle mark coordinate are obtained through calculation according to the offset, so that new horizontal external rectangular frames corresponding to the target electrode coordinate and the target needle mark coordinate are respectively obtained, and when the distance between the central points of the two horizontal external rectangular frames is larger than a preset value, or when the area of the horizontal external rectangular frame corresponding to the target needle mark coordinate is not within a preset area range, the needle insertion is determined to be unqualified. Namely, 3 conditions are required to be met when the needle insertion is qualified, namely, firstly, needle marks exist on the electrode, the electrode and the needle marks are sequenced, and whether the needle marks exist in the electrode is determined when the needle mark coordinates are screened; secondly, the distance between the center points of the two horizontal external rectangular frames corresponding to the target electrode coordinates and the target needle mark coordinates is smaller than or equal to a preset value, after the two horizontal external rectangular frames are obtained, the positions of the center points of the two horizontal external rectangular frames are respectively determined, and the distance between the two horizontal external rectangular frames is determined according to the positions of the center points; and finally, determining the area of the corresponding horizontal circumscribed rectangular frame according to the last two bits in the target needle mark coordinates when the area of the corresponding horizontal circumscribed rectangular frame is in a preset area range, and judging whether the area is in the preset area or not.
It can be seen that in this embodiment, whether the puncture is qualified is determined by the above 3 puncture qualification determining conditions, so that the accuracy of determining whether the puncture is qualified is improved.
In one possible embodiment, after the determining that the electrode is not needled, the method further comprises: and adjusting the initial position of the probe according to the distance between the center points of the seventh horizontal external rectangular frame and the sixth horizontal external rectangular frame, or adjusting the needle penetration depth of the probe according to the area of the seventh horizontal external rectangular frame.
If the reason of disqualification of the needle insertion is determined that the distance between the center points of the two horizontal external rectangular frames corresponding to the target electrode coordinates and the target needle mark coordinates is larger than a preset value, properly adjusting the initial position of the probe according to the distance between the center points; if the reason of the disqualification of the puncture is that the area of the horizontal circumscribed rectangular frame corresponding to the target needle mark coordinate is not in the preset threshold range, if the area of the horizontal circumscribed rectangular frame corresponding to the target needle mark coordinate is smaller than the minimum value of the area of the preset horizontal circumscribed rectangular frame, the puncture is judged to be too shallow, if the horizontal circumscribed rectangular frame corresponding to the target needle mark coordinate is larger than the maximum value of the area of the standard needle mark rectangular frame, the puncture is judged to be too deep, and the puncture depth is properly adjusted according to the puncture condition determined by the disqualification of the puncture.
It can be seen that in the present embodiment, by adjusting the position of the probe and the depth of the needle insertion according to the cause of failure after determining that the needle insertion is failed, the efficiency of the needle insertion thereafter can be improved.
In a possible embodiment, the first image feature comprises a standard gray value, a number of pixels having a gray value greater than a second preset value, a number of pixels having a gray value less than a third preset value, and/or a binarized contour number.
Exemplary first image features may include, among other things, an average gray value for the image, a number of pixels with gray values greater than 200, a number of pixels with gray values less than 50, and a number of contours binarized.
It can be seen that in this embodiment, considering that there are many patterns on the wafer, the complexity of the image may be determined according to the number of contours.
In accordance with the above embodiments, referring to fig. 5, fig. 5 is a functional unit block diagram of an apparatus for determining whether a wafer is qualified for needling according to an embodiment of the present application. The apparatus 50 for determining whether a wafer is eligible for needle punching includes: the obtaining unit 51 is configured to obtain, by using a pre-trained first model, a first horizontal circumscribed rectangular frame corresponding to each electrode and a second horizontal circumscribed rectangular frame corresponding to each needle mark in the target wafer, where an electrode area of each electrode is completely included in the corresponding first horizontal circumscribed rectangular frame, a needle mark area of each needle mark is completely included in the corresponding second horizontal circumscribed rectangular frame, each first horizontal circumscribed rectangular frame corresponds to a first electrode coordinate, and each second horizontal circumscribed rectangular frame corresponds to a first needle mark coordinate; an execution unit 52 for executing the following operations for each electrode: obtaining a first slice horizontal rectangular frame according to a first horizontal external rectangular frame corresponding to the electrode, wherein the first slice horizontal rectangular frame is identical to the central point of the first horizontal external rectangular frame, and the area of the first slice horizontal rectangular frame is M times of the area of the first horizontal external rectangular frame; acquiring a first image characteristic of an image area where the first slice horizontal rectangular frame is located; inputting a first needle mark coordinate of a needle mark corresponding to the electrode and the first image characteristic into a pre-trained second model according to the first electrode coordinate of the electrode to obtain a first electrode offset and a first needle mark offset; obtaining a target electrode coordinate according to the first electrode offset and the first electrode coordinate, and obtaining a target needle mark coordinate according to the first needle mark offset and the first needle mark coordinate of the needle mark with the corresponding relation with the electrode; and judging whether the electrode is qualified for needling according to the target electrode coordinates and the target needle mark coordinates.
In one possible embodiment, before inputting the first model trained in advance according to the first electrode coordinates of the electrode, the first needle mark coordinates of the needle mark corresponding to the electrode, and the first image feature, the apparatus 50 for determining whether the wafer is qualified for the needle insertion is further configured to: acquiring a third horizontal external rectangular frame corresponding to each electrode and a fourth horizontal external rectangular frame corresponding to each needle mark in a reference wafer for training through a pre-trained first model, wherein each third horizontal external rectangular frame corresponds to a second electrode coordinate, and each fourth horizontal external rectangular frame corresponds to a second needle mark coordinate; acquiring a second slice horizontal rectangular frame corresponding to each electrode according to a third horizontal circumscribed rectangular frame corresponding to each electrode, wherein the second slice horizontal rectangular frame is the same as the center point of the third horizontal circumscribed rectangular frame, and the area of the second slice horizontal rectangular frame is S times of the area of the third horizontal circumscribed rectangular frame; determining a third electrode coordinate of each electrode according to the second slice horizontal rectangular frame; obtaining a third slice horizontal rectangular frame corresponding to each needle mark according to the fourth horizontal circumscribed rectangular frame of each needle mark, wherein the center point of the third slice horizontal rectangular frame is the same as that of the fourth horizontal circumscribed rectangular frame, and the area of the third slice horizontal rectangular frame is P times that of the fourth horizontal circumscribed rectangular frame; determining a third needle mark coordinate of each needle mark according to the third slice horizontal rectangular frame; acquiring a second image characteristic of an image area where a second slice horizontal rectangular frame corresponding to each electrode is located; determining a second electrode offset of each electrode according to the second electrode coordinates of each electrode and the third electrode coordinates of each electrode, and determining a second needle mark offset of each needle mark according to the second needle mark coordinates of each needle mark and the third needle mark coordinates of each needle mark; and training the second model according to the second electrode coordinates of each electrode, the second needle mark coordinates of each needle mark, the second image characteristics of each electrode, the second electrode offset of each electrode and the second needle mark offset of each needle mark, and obtaining the pre-trained second model.
In one possible embodiment, the apparatus 50 for determining whether the wafer is eligible for needle punching in determining the third electrode coordinates of each electrode based on the second slice horizontal rectangular frame is further configured to: acquiring a contour map of an electrode included in each second slice horizontal rectangular frame; and determining a fifth horizontal circumscribed rectangular frame of the electrode included in each second slice horizontal rectangular frame according to the outline map, wherein the fifth horizontal circumscribed rectangular frame corresponds to a third electrode coordinate.
In one possible embodiment, after acquiring the first horizontal circumscribed rectangular frame corresponding to each electrode and the second horizontal circumscribed rectangular frame corresponding to each needle mark in the target wafer through the pre-trained first model, the apparatus 50 for determining whether the wafer is qualified for the needle insertion is further configured to: sequencing the first electrode coordinates corresponding to each first horizontal circumscribed rectangular frame and the first needle mark coordinates corresponding to each second horizontal circumscribed rectangular frame to obtain a sequencing result, wherein the sequencing result is used for indicating the corresponding relation between the first horizontal circumscribed rectangular frame and the second horizontal circumscribed rectangular frame; and screening the first needle mark coordinates corresponding to each second horizontal external rectangular frame according to the sequencing result to obtain a needle mark coordinate set, wherein each first needle mark coordinate in the needle mark coordinate set corresponds to one first electrode coordinate, each second horizontal external rectangular frame corresponding to each first needle mark coordinate in the needle mark coordinate set is contained in a first horizontal external rectangular frame corresponding to the first electrode coordinate with the corresponding relation, and the first electrode coordinate corresponds to one first needle mark coordinate or corresponds to a null value.
In one possible embodiment, the execution unit 52 is specifically configured to, in determining whether the electrode is qualified for being inserted according to the target electrode coordinates and the target needle mark coordinates: acquiring a sixth horizontal circumscribed rectangular frame corresponding to the target electrode coordinate and a seventh horizontal circumscribed rectangular frame corresponding to the target needle mark coordinate; determining that the electrode needle insertion is not qualified when the distance between the center points of the seventh horizontal circumscribed rectangular frame and the sixth horizontal circumscribed rectangular frame is larger than a first preset value or when the area of the seventh horizontal circumscribed rectangular frame is not within a preset area range; and when the needle mark coordinate corresponding to the first electrode coordinate of the target electrode coordinate is determined to be a null value, outputting an alarm signal, wherein the alarm signal is used for prompting a worker that the probe is abnormal.
In one possible embodiment, after determining that the electrode is not needled, the means 50 for determining whether the wafer is needled is further configured to: and adjusting the initial position of the probe according to the distance between the center points of the seventh horizontal external rectangular frame and the sixth horizontal external rectangular frame, or adjusting the needle penetration depth of the probe according to the area of the seventh horizontal external rectangular frame.
In one possible embodiment, the apparatus 50 for determining whether a wafer is eligible for needle punching in acquiring the first image feature is further configured to: the first image feature comprises a standard gray value, the number of pixels with gray values larger than a second preset value, the number of pixels with gray values smaller than a third preset value and/or the number of binarized contours.
It can be understood that, since the method embodiment and the apparatus embodiment are different presentation forms of the same technical concept, the content of the method embodiment portion in the present application should be synchronously adapted to the apparatus embodiment portion, which is not described herein.
In the case of using integrated units, referring to fig. 6, fig. 6 is a block diagram illustrating functional units of another apparatus for determining whether a wafer is qualified for needling according to an embodiment of the present application. In fig. 6, an apparatus 50 for determining whether a wafer is eligible for needle punching includes: a processing module 502 and a communication module 501. The processing module 502 is configured to determine whether the wafer is needle-punched to perform the actions of the apparatus 50 for controlling management, e.g., performing the steps of the acquisition unit 51 and the execution unit 52, and/or for performing other processes of the techniques described herein. The communication module 501 is used to determine interactions between the apparatus 50 and other devices that are qualified for wafer puncture. As shown in fig. 6, the apparatus 50 for determining whether a wafer is eligible for a needle insertion may further include a memory module 503, where the memory module 503 is configured to store program code and data for the apparatus 50 for determining whether a wafer is eligible for a needle insertion.
The processing module 502 may be a processor or controller, such as a central processing unit (Central Processing Unit, CPU), a general purpose processor, a digital signal processor (DigitalSignalProcessor, DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. The processor may also be a combination that performs the function of a computation, e.g., a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 501 may be a transceiver, RF circuitry, or a communication interface, etc. The storage module 503 may be a memory.
All relevant contents of each scenario related to the above method embodiment may be cited to the functional description of the corresponding functional module, which is not described herein. The apparatus 50 for determining whether a wafer is properly inserted may perform the method for determining whether a wafer is properly inserted as shown in fig. 1.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application, as shown in fig. 7, the electronic device 700 includes a processor 710, a memory 720, a communication interface 730, and one or more programs 721, where the one or more programs 721 are stored in the memory and configured to be executed by the processor, where the program includes some or all of the steps of any of the methods for determining whether a wafer is qualified for insertion according to the embodiment of the method, and the processor, the memory, and the communication interface are connected to each other and perform communication therebetween;
The memory may be volatile memory such as dynamic random access memory DRAM, or nonvolatile memory such as a mechanical hard disk. The memory is configured to store a set of executable program code and the processor is configured to invoke the executable program code stored in the memory to perform some or all of the steps of any of the energy data management methods described in the method embodiments described above for determining whether a wafer is eligible for a needle stick.
It can be seen that, in the electronic device 700 described in the embodiment of the present application, first, a first horizontal external rectangular frame corresponding to each electrode and a second horizontal external rectangular frame corresponding to each needle trace in the target wafer are obtained through a pre-trained first model, an electrode area of each electrode is completely included in the corresponding first horizontal external rectangular frame, a needle trace area of each needle trace is completely included in the corresponding second horizontal external rectangular frame, each first horizontal external rectangular frame corresponds to one first electrode coordinate, and each second horizontal external rectangular frame corresponds to one first needle trace coordinate; the following is then performed for each electrode: obtaining a first slice horizontal rectangular frame according to a first horizontal external rectangular frame corresponding to the electrode, wherein the first slice horizontal rectangular frame is identical to the central point of the first horizontal external rectangular frame, and the area of the first slice horizontal rectangular frame is M times of the area of the first horizontal external rectangular frame; acquiring a first image feature of an image area where the first slice horizontal rectangular frame is located; inputting a pre-trained second model according to a first electrode coordinate of the electrode, a first needle mark coordinate of a needle mark corresponding to the electrode and the first image characteristic, and obtaining a first electrode offset and a first needle mark offset; acquiring a target electrode coordinate according to the first electrode offset and the first electrode coordinate, and acquiring a target needle mark coordinate according to the first needle mark offset and the first needle mark coordinate of the needle mark corresponding to the electrode; and finally judging whether the electrode is qualified for needling according to the target electrode coordinates and the target needle mark coordinates. The application comprehensively analyzes whether the puncture is qualified by determining the positions of the electrode and the needle mark, so that the speed for judging whether the puncture is qualified is improved under the condition of ensuring the positioning accuracy of the electrode and the needle mark.
The embodiment of the application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program makes a computer execute part or all of the steps of any one of the above method embodiments, and the computer includes an electronic device.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are alternative embodiments, and that the acts and modules involved are not necessarily required for the present application.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional divisions when actually implemented, such as multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units described above may be implemented either in hardware or in software program modules.
The integrated units, if implemented in the form of software program modules, may be stored in a computer-readable memory for sale or use as a stand-alone product. Based on this understanding, the technical solution of the present application may be embodied essentially or partly in the form of a software product or all or part of the technical solution, which is stored in a memory, and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned memory includes: a usb disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, and the memory may include: flash disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.
The foregoing has outlined rather broadly the more detailed description of the embodiments of the application in order that the detailed description of the principles and embodiments of the application may be implemented in conjunction with the detailed description of the embodiments that follows, the claims being merely intended to facilitate the understanding of the method and concepts underlying the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims (10)

1. A method of determining whether a wafer is eligible for needle punching, the method comprising:
Acquiring a first horizontal external rectangular frame corresponding to each electrode and a second horizontal external rectangular frame corresponding to each needle mark in a target wafer through a pre-trained first model, wherein an electrode area of each electrode is completely included in the corresponding first horizontal external rectangular frame, a needle mark area of each needle mark is completely included in the corresponding second horizontal external rectangular frame, each first horizontal external rectangular frame corresponds to a first electrode coordinate, and each second horizontal external rectangular frame corresponds to a first needle mark coordinate;
The following is performed for each electrode:
Obtaining a first slice horizontal rectangular frame according to a first horizontal external rectangular frame corresponding to the electrode, wherein the first slice horizontal rectangular frame is identical to the central point of the first horizontal external rectangular frame, and the area of the first slice horizontal rectangular frame is M times of the area of the first horizontal external rectangular frame;
acquiring a first image feature of an image area where the first slice horizontal rectangular frame is located;
Inputting a pre-trained second model according to a first electrode coordinate of the electrode, a first needle mark coordinate of a needle mark corresponding to the electrode and the first image characteristic, and obtaining a first electrode offset and a first needle mark offset;
acquiring a target electrode coordinate according to the first electrode offset and the first electrode coordinate, and acquiring a target needle mark coordinate according to the first needle mark offset and the first needle mark coordinate of the needle mark corresponding to the electrode;
and judging whether the electrode is qualified for needling according to the target electrode coordinates and the target needle mark coordinates.
2. The method of claim 1, wherein before the inputting of the first image feature into the pre-trained second model according to the first electrode coordinates of the electrode, the first needle mark coordinates of the needle mark in correspondence with the electrode, and the first image feature, the method further comprises:
Acquiring a third horizontal external rectangular frame corresponding to each electrode and a fourth horizontal external rectangular frame corresponding to each needle mark in a reference wafer for training through a pre-trained first model, wherein each third horizontal external rectangular frame corresponds to a second electrode coordinate, and each fourth horizontal external rectangular frame corresponds to a second needle mark coordinate;
Acquiring a second slice horizontal rectangular frame corresponding to each electrode according to a third horizontal circumscribed rectangular frame corresponding to each electrode, wherein the second slice horizontal rectangular frame is the same as the center point of the third horizontal circumscribed rectangular frame, and the area of the second slice horizontal rectangular frame is S times of the area of the third horizontal circumscribed rectangular frame;
Determining a third electrode coordinate of each electrode according to the second slice horizontal rectangular frame;
Obtaining a third slice horizontal rectangular frame corresponding to each needle mark according to the fourth horizontal circumscribed rectangular frame of each needle mark, wherein the center point of the third slice horizontal rectangular frame is the same as that of the fourth horizontal circumscribed rectangular frame, and the area of the third slice horizontal rectangular frame is P times that of the fourth horizontal circumscribed rectangular frame;
determining a third needle mark coordinate of each needle mark according to the third slice horizontal rectangular frame;
Acquiring a second image characteristic of an image area where a second slice horizontal rectangular frame corresponding to each electrode is located;
determining a second electrode offset of each electrode according to the second electrode coordinates of each electrode and the third electrode coordinates of each electrode, and determining a second needle mark offset of each needle mark according to the second needle mark coordinates of each needle mark and the third needle mark coordinates of each needle mark;
and training the second model according to the second electrode coordinates of each electrode, the second needle mark coordinates of each needle mark, the second image characteristics of each electrode, the second electrode offset of each electrode and the second needle mark offset of each needle mark, and obtaining the pre-trained second model.
3. The method of claim 2, wherein said determining the third electrode coordinates of each electrode from the second slice horizontal rectangular box comprises:
acquiring a contour map of an electrode included in each second slice horizontal rectangular frame;
and determining a fifth horizontal circumscribed rectangular frame of the electrode included in each second slice horizontal rectangular frame according to the outline map, wherein the fifth horizontal circumscribed rectangular frame corresponds to a third electrode coordinate.
4. The method of claim 1, wherein after the obtaining, by the pre-trained first model, a first horizontal bounding rectangle box corresponding to each electrode and a second horizontal bounding rectangle box corresponding to each needle mark in the target wafer, the method further comprises:
Sequencing the first electrode coordinates corresponding to each first horizontal circumscribed rectangular frame and the first needle mark coordinates corresponding to each second horizontal circumscribed rectangular frame to obtain a sequencing result, wherein the sequencing result is used for indicating the corresponding relation between the first horizontal circumscribed rectangular frame and the second horizontal circumscribed rectangular frame;
And screening the first needle mark coordinates corresponding to each second horizontal external rectangular frame according to the sequencing result to obtain a needle mark coordinate set, wherein each first needle mark coordinate in the needle mark coordinate set corresponds to one first electrode coordinate, each second horizontal external rectangular frame corresponding to each first needle mark coordinate in the needle mark coordinate set is contained in a first horizontal external rectangular frame corresponding to the first electrode coordinate with the corresponding relation, and the first electrode coordinate corresponds to one first needle mark coordinate or corresponds to a null value.
5. The method of claim 4, wherein said determining whether the electrode is properly needled based on the target electrode coordinates and the target needle mark coordinates comprises:
Acquiring a sixth horizontal circumscribed rectangular frame corresponding to the target electrode coordinate and a seventh horizontal circumscribed rectangular frame corresponding to the target needle mark coordinate;
determining that the electrode needle insertion is not qualified when the distance between the center points of the seventh horizontal circumscribed rectangular frame and the sixth horizontal circumscribed rectangular frame is larger than a first preset value or when the area of the seventh horizontal circumscribed rectangular frame is not within a preset area range;
And when the needle mark coordinate corresponding to the first electrode coordinate of the target electrode coordinate is determined to be a null value, outputting an alarm signal, wherein the alarm signal is used for prompting a worker that the probe is abnormal.
6. The method of claim 5, wherein after the determining that the electrode needle is failed, the method further comprises:
and adjusting the initial position of the probe according to the distance between the center points of the seventh horizontal external rectangular frame and the sixth horizontal external rectangular frame, or adjusting the needle penetration depth of the probe according to the area of the seventh horizontal external rectangular frame.
7. The method of claim 1, wherein the first image feature comprises a standard gray value, a number of pixels having a gray value greater than a second preset value, a number of pixels having a gray value less than a third preset value, and/or a binarized profile number.
8. An apparatus for determining whether a wafer is eligible for a needle insertion, the apparatus comprising:
The device comprises an acquisition unit, a first horizontal external rectangular frame, a second horizontal external rectangular frame, a first electrode coordinate and a second electrode coordinate, wherein the first horizontal external rectangular frame corresponds to each electrode in a target wafer and the second horizontal external rectangular frame corresponds to each needle mark through a pre-trained first model;
An execution unit for executing the following operations for each electrode: obtaining a first slice horizontal rectangular frame according to a first horizontal external rectangular frame corresponding to the electrode, wherein the first slice horizontal rectangular frame is identical to the central point of the first horizontal external rectangular frame, and the area of the first slice horizontal rectangular frame is M times of the area of the first horizontal external rectangular frame; acquiring a first image characteristic of an image area where the first slice horizontal rectangular frame is located; inputting a first needle mark coordinate of a needle mark corresponding to the electrode and the first image characteristic into a pre-trained second model according to the first electrode coordinate of the electrode to obtain a first electrode offset and a first needle mark offset; obtaining a target electrode coordinate according to the first electrode offset and the first electrode coordinate, and obtaining a target needle mark coordinate according to the first needle mark offset and the first needle mark coordinate of the needle mark with the corresponding relation with the electrode; and judging whether the electrode is qualified for needling according to the target electrode coordinates and the target needle mark coordinates.
9. An electronic device comprising a processor and a memory storing instructions for execution, the memory storing one or more programs; when the processor executes the execution instructions stored in the memory, the processor performs the method of any one of claims 1-7.
10. A computer readable storage medium, characterized in that an energy data management program is stored, comprising execution instructions which, when executed by a processor of an electronic device, perform the method according to any of claims 1-7.
CN202410294703.3A 2024-03-15 2024-03-15 Method and related device for determining whether wafer is qualified for needle insertion Active CN117934804B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410294703.3A CN117934804B (en) 2024-03-15 2024-03-15 Method and related device for determining whether wafer is qualified for needle insertion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410294703.3A CN117934804B (en) 2024-03-15 2024-03-15 Method and related device for determining whether wafer is qualified for needle insertion

Publications (2)

Publication Number Publication Date
CN117934804A CN117934804A (en) 2024-04-26
CN117934804B true CN117934804B (en) 2024-06-04

Family

ID=90766902

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410294703.3A Active CN117934804B (en) 2024-03-15 2024-03-15 Method and related device for determining whether wafer is qualified for needle insertion

Country Status (1)

Country Link
CN (1) CN117934804B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101443897A (en) * 2006-05-16 2009-05-27 东京毅力科创株式会社 Image binarizing method, image processing device and computer program
KR20090122125A (en) * 2008-05-23 2009-11-26 도쿄엘렉트론가부시키가이샤 Probe mark inspection apparatus, probe apparatus, probe mark inspection method and storage medium
CN114565929A (en) * 2022-02-14 2022-05-31 南京红松信息技术有限公司 Lead tracking identification method based on gradient transformation
WO2022148143A1 (en) * 2021-01-08 2022-07-14 华为技术有限公司 Target detection method and device
CN115272204A (en) * 2022-07-15 2022-11-01 中国石油大学(华东) Bearing surface scratch detection method based on machine vision
CN115578318A (en) * 2022-09-08 2023-01-06 山东万腾电子科技有限公司 Probe needle mark detection method and system based on image processing

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101443897A (en) * 2006-05-16 2009-05-27 东京毅力科创株式会社 Image binarizing method, image processing device and computer program
KR20090122125A (en) * 2008-05-23 2009-11-26 도쿄엘렉트론가부시키가이샤 Probe mark inspection apparatus, probe apparatus, probe mark inspection method and storage medium
WO2022148143A1 (en) * 2021-01-08 2022-07-14 华为技术有限公司 Target detection method and device
CN114565929A (en) * 2022-02-14 2022-05-31 南京红松信息技术有限公司 Lead tracking identification method based on gradient transformation
CN115272204A (en) * 2022-07-15 2022-11-01 中国石油大学(华东) Bearing surface scratch detection method based on machine vision
CN115578318A (en) * 2022-09-08 2023-01-06 山东万腾电子科技有限公司 Probe needle mark detection method and system based on image processing

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
一种新的精密光学镜片表面疵病宽度测量方法;朱聪等;《计算机应用与软件》;20141215(第12期);第260页至第261页 *

Also Published As

Publication number Publication date
CN117934804A (en) 2024-04-26

Similar Documents

Publication Publication Date Title
CN111640089B (en) Defect detection method and device based on feature map center point
TWI748242B (en) Method and system for scanning wafer
CN114627092A (en) Defect detection method and device, electronic equipment and readable storage medium
US8542912B2 (en) Determining the uniqueness of a model for machine vision
CN111739020B (en) Automatic labeling method, device, equipment and medium for periodic texture background defect label
CN111814905A (en) Target detection method, target detection device, computer equipment and storage medium
CN111144372A (en) Vehicle detection method, device, computer equipment and storage medium
CN116503415B (en) Defect detection method, defect detection device, computer equipment and computer readable storage medium
CN111931704A (en) Method, device, equipment and computer readable storage medium for evaluating map quality
CN113222913A (en) Circuit board defect detection positioning method and device and storage medium
CN112215811A (en) Image detection method and device, electronic equipment and storage medium
CN116245817A (en) PCB defect detection method based on improved YOLOv5 and storage medium
EP3291179B1 (en) Image processing device, image processing method, and image processing program
CN116542926B (en) Method, device, equipment and storage medium for identifying defects of two-dimension codes of battery
CN117934804B (en) Method and related device for determining whether wafer is qualified for needle insertion
CN116777861B (en) Marking quality detection method and system for laser engraving machine
CN112651315A (en) Information extraction method and device of line graph, computer equipment and storage medium
CN115661131B (en) Image identification method and device, electronic equipment and storage medium
CN114937037B (en) Product defect detection method, device and equipment and readable storage medium
US11769322B2 (en) Program creation device, object detection system, anchor setting method, and anchor setting program
CN114897797A (en) Method, device and equipment for detecting defects of printed circuit board and storage medium
CN114332016A (en) Equipment screen light spot detection method and device
CN113310438B (en) Flatness measuring method, flatness measuring device, computer equipment and storage medium
CN117974839B (en) Drawing method of wafer map and related device
CN115830043B (en) Boundary detection method, device, equipment and storage medium for wireless charging magnet

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant