Carrier-like plate detection method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a carrier-like plate detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring an image of at least one candidate structure layer in a target carrier plate, and screening a target structure layer with dendritic crystals from the at least one candidate structure layer according to the image of the at least one candidate structure layer; for each target structure layer, according to the image of the target structure layer, identifying at least one line in which dendrites grow in the target structure layer; for each target structure layer, determining an electrochemical migration degree corresponding to the target structure layer according to the dendritic crystal length of the dendritic crystal corresponding to the at least one circuit; and under the condition that the electrochemical migration degree of at least one target structure layer is greater than the degree threshold value, a reliability detection result indicating that the detection of the target class carrier plate is not passed is obtained, so that the reliability detection accuracy of the class carrier plate is improved.

Description

Technical Field

[0001] The present application relates to the field of detection technologies, and in particular, to a method and device for detecting a type of carrier board, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the continuous development of semiconductor packaging and printed circuit board (PCB) technologies, the type of carrier board technology has emerged and become one of the key technologies to improve chip performance. The type of carrier board technology combines the characteristics of high-density interconnect (HDI) and IC (Integrated Circuit) carrier boards, achieving higher integration and finer circuit layouts, thus meeting the requirements of modern electronic products for high performance and miniaturization. However, with the continuous development of technology, the reliability requirements for the type of carrier board are also getting higher and higher. To ensure the reliability of the type of carrier board, it is particularly important to conduct a comprehensive inspection on it.

[0003] In the related art, the aging of the type of carrier board is usually accelerated manually, and the reliability of the type of carrier board is detected based on the performance degradation of the type of carrier board before and after aging. However, this method is actually a reliability detection method for printed circuit boards. Also, due to the differences in size, shape, and function between printed circuit boards and the type of carrier boards, directly using the method for printed circuit boards to detect the type of carrier board is very likely to result in low accuracy in detecting the type of carrier board. Summary of the Invention

[0004] Based on this, it is necessary to provide a method and device for detecting a type of carrier board, a computer device, a computer-readable storage medium, and a computer program product that can improve the accuracy of detecting the type of carrier board for the above technical problems.

[0005] In a first aspect, the present application provides a method for detecting a type of carrier board, including:

[0006] Obtaining images of at least one candidate structural layer in a target type of carrier board, and screening out a target structural layer with dendrites from the at least one candidate structural layer according to the images of the at least one candidate structural layer;

[0007] For each target structural layer, identifying at least one circuit in the target structural layer on which dendrites grow according to the image of the target structural layer;

[0008] For each target structural layer, determining the degree of electrochemical migration corresponding to the target structural layer according to the dendrite lengths of the dendrites corresponding to each of the at least one circuit;

[0009] In the case where the degree of electrochemical migration of at least one target structural layer is greater than a degree threshold, obtaining a reliability detection result indicating that the detection of the target type of carrier board fails.

[0010] Second aspect, the present application further provides a type of carrier board detection device, including:

[0011] An image acquisition module, configured to acquire images of at least one candidate structural layer in a target carrier board, and screen out a target structural layer with dendrites from the at least one candidate structural layer according to the images of the at least one candidate structural layer;

[0012] A circuit recognition module, configured to, for each target structural layer, recognize at least one circuit with dendrites growing in the target structural layer according to the image of the target structural layer;

[0013] A migration degree determination module, configured to, for each target structural layer, determine the electrochemical migration degree corresponding to the target structural layer according to the dendrite lengths of the dendrites corresponding to at least one circuit;

[0014] A reliability detection module, configured to obtain a reliability detection result indicating that the detection of the target carrier board fails when the electrochemical migration degree of at least one target structural layer is greater than a degree threshold.

[0015] Third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0016] Acquire images of at least one candidate structural layer in a target carrier board, and screen out a target structural layer with dendrites from the at least one candidate structural layer according to the images of the at least one candidate structural layer;

[0017] For each target structural layer, recognize at least one circuit with dendrites growing in the target structural layer according to the image of the target structural layer;

[0018] For each target structural layer, determine the electrochemical migration degree corresponding to the target structural layer according to the dendrite lengths of the dendrites corresponding to at least one circuit;

[0019] When the electrochemical migration degree of at least one target structural layer is greater than a degree threshold, obtain a reliability detection result indicating that the detection of the target carrier board fails.

[0020] Fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0021] Acquire images of at least one candidate structural layer in a target carrier board, and screen out a target structural layer with dendrites from the at least one candidate structural layer according to the images of the at least one candidate structural layer;

[0022] For each target structural layer, based on the image of the target structural layer, at least one circuit in the target structural layer where dendrites grow is identified;

[0023] For each target structural layer, based on the dendrite lengths of the dendrites corresponding to the at least one circuit respectively, the degree of electrochemical migration corresponding to the target structural layer is determined;

[0024] In the case where the degree of electrochemical migration of at least one target structural layer is greater than the degree threshold, a reliability detection result indicating that the detection of the target type of carrier board fails is obtained.

[0025] In a fifth aspect, the present application further provides a computer program product, including a computer program, which when executed by a processor implements the following steps:

[0026] Obtain images of at least one candidate structural layer in a target type of carrier board, and based on the images of the at least one candidate structural layer, screen out target structural layers with dendrites from the at least one candidate structural layer;

[0027] For each target structural layer, based on the image of the target structural layer, at least one circuit in the target structural layer where dendrites grow is identified;

[0028] For each target structural layer, based on the dendrite lengths of the dendrites corresponding to the at least one circuit respectively, the degree of electrochemical migration corresponding to the target structural layer is determined;

[0029] In the case where the degree of electrochemical migration of at least one target structural layer is greater than the degree threshold, a reliability detection result indicating that the detection of the target type of carrier board fails is obtained.

[0030] The above-mentioned carrier board detection method, device, computer device, computer-readable storage medium, and computer program product can screen out target structural layers with dendrites from at least one candidate structural layer in advance by obtaining images of at least one candidate structural layer in the target type of carrier board, avoiding detecting all candidate structural layers and improving the detection efficiency. For each target structural layer, based on the image of the target structural layer, at least one circuit in the target structural layer where dendrites grow can be effectively identified. Then, for each target structural layer, based on the dendrite lengths of the dendrites corresponding to the at least one circuit respectively, the degree of electrochemical migration corresponding to the target structural layer can be accurately estimated. Therefore, with the help of the degree of electrochemical migration, it can accurately reflect whether the target type of carrier board is effective. In the case where the degree of electrochemical migration of at least one target structural layer is greater than the degree threshold, a reliability detection result indicating that the detection of the target type of carrier board fails can be directly and accurately determined. Thus, accurate detection of the reliability of the carrier board is achieved, and the detection accuracy is improved. Description of the Drawings

[0031] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0032] Figure 1 It is an application environment diagram of the detection method for the build-up printed circuit board in an embodiment;

[0033] Figure 2 It is a schematic flowchart of the detection method for the build-up printed circuit board in an embodiment;

[0034] Figure 3 It is a schematic diagram of dendrites in the structure layer in an embodiment;

[0035] Figure 4 It is a schematic diagram of circuits in the structure layer in an embodiment;

[0036] Figure 5 It is a schematic diagram of dendrite length in an embodiment;

[0037] Figure 6 It is a structural block diagram of the detection device for the build-up printed circuit board in an embodiment;

[0038] Figure 7 It is an internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0039] In order to make the objectives, technical solutions, and advantages of the present application more clear and understandable, the following further details the present application in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] The detection method for the build-up printed circuit board provided by the embodiments of the present application can be applied to the application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. The detection method for the build-up printed circuit board provided by the embodiments of the present application can be executed independently by the terminal 102, or can be executed independently by the server 104, or can be executed collaboratively by the terminal 102 and the server 104.

[0041] In one embodiment, after the terminal 102 acquires and obtains images of at least one candidate structural layer in the target IC substrate, the terminal 102 sends the images of the at least one candidate structural layer to the server 104. The server 104 filters out the target structural layers with dendrites from the at least one candidate structural layer according to the images of the at least one candidate structural layer. For each target structural layer, the server 104 identifies at least one circuit with dendrites growing in the target structural layer according to the image of the target structural layer. For each target structural layer, the server 104 determines the degree of electrochemical migration corresponding to the target structural layer according to the dendrite lengths of the dendrites corresponding to the at least one circuit. In the case where the degree of electrochemical migration of at least one target structural layer is greater than the degree threshold, a reliability detection result indicating that the detection of the target IC substrate fails is obtained.

[0042] Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, etc. The server 104 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0043] In an exemplary embodiment, as Figure 2 shown, a method for detecting an IC substrate is provided. Taking this method applied to a computer device (which can be Figure 1 the terminal 102 or the server 104) as an example for illustration, it includes the following steps 202 to 208. Among them:

[0044] Step 202, acquire images of at least one candidate structural layer in the target IC substrate, and filter out the target structural layers with dendrites from the at least one candidate structural layer according to the images of the at least one candidate structural layer.

[0045] Among them, the target IC substrate is an IC substrate to be subjected to reliability detection. Exemplarily, in a scenario of testing whether a preset material can be used to manufacture an IC substrate, or in a scenario of testing whether the circuit design of an IC substrate is reasonable, the target IC substrate refers to the IC substrate obtained by aging the IC substrate sample provided by the IC substrate provider. The candidate structural layer refers to the structural layer included in the target IC substrate. For example, a conductive layer, an insulating layer, a conduction layer, etc. Exemplarily, the candidate structural layer refers to a structural layer that is prone to electrochemical migration, the target structural layer refers to a candidate structural layer with dendrites, and the dendrites are generated after the candidate structural layer undergoes electrochemical migration.

[0046] Optionally, when the computer device determines that the target class carrier board meets the reliability detection conditions, it determines the line spacing of each structural layer in the target class carrier board according to the corresponding design file of the target class carrier board, and filters out at least one candidate structural layer from multiple structural layers according to the line spacing of each structural layer. By cutting layer by layer, and using an image acquisition device to collect the cross-section of the target class carrier board after each cut one by one, images of each candidate structural layer are obtained. Cutting layer by layer is to cut out non-first-layer structural layers. For example, first, the image acquisition device identifies the image of the first layer, then, the first layer is cut for the first time to obtain the second structural layer, and the image of the second structural layer is identified by the image acquisition device, and this is executed in sequence until the image of the last layer is collected. After the computer device obtains the images of each candidate structural layer, the candidate structural layer with dendrites is used as the target structural layer.

[0047] Exemplarily, after determining the candidate structural layer, the image acquisition device collects the image of the candidate structural layer and identifies whether there is a dendrite pattern in the image of the candidate structural layer. If it exists, a dendrite identifier is marked on the image and sent to the computer device. The computer device uses the candidate structural layer corresponding to the image with the dendrite identifier as the target structural layer. Among them, the image acquisition device can be a microscopic observation device, such as an optical microscope or a scanning electron microscope. For example, after the collector collects the image, it further checks whether there are dendrites in the image. If there are, a dendrite identifier is marked.

[0048] Exemplarily, after collecting the images, through a dendrite recognition model, the images with dendrites are identified from the images of at least one candidate structural layer, and the candidate structural layer corresponding to the image with dendrites is used as the target structural layer.

[0049] Step 204, for each target structural layer, according to the image of the target structural layer, identify at least one circuit in the target structural layer where dendrites grow.

[0050] Optionally, for each target structural layer, the computer device locates at least one circuit where dendrites grow from multiple circuits of the target structural layer according to the image of the target structural layer.

[0051] Exemplarily, the computer device calls a dendrite positioning model to perform dendrite positioning on the image of the target structural layer and determines at least one circuit where dendrites grow. It should be noted that the previous dendrite recognition model and dendrite positioning model are different neural network models. The dendrite recognition model is used to verify whether there are dendrites, while the dendrite positioning model is to identify the circuit where dendrites grow. Their functions are different.

[0052] As Figure 3 shown, it is a schematic diagram of dendrites in a structural layer in an embodiment. Figure 3 In the white dashed box, there are dendrites between two circuits.Figure 3 Three dendrites are schematically shown.

[0053] Step 206: For each target structural layer, determine the degree of electrochemical migration corresponding to the target structural layer according to the dendrite lengths of the dendrites corresponding to at least one circuit.

[0054] Among them, the greater the degree of electrochemical migration, the higher the probability that the target type of carrier board fails or is unreliable.

[0055] Exemplarily, for each target structural layer, the computer device obtains the mapping relationship between the dendrite length and the degree of electrochemical migration, and determines the degree of electrochemical migration corresponding to the dendrite according to the dendrite lengths of the dendrites corresponding to at least one circuit and this mapping relationship. The computer device fuses the degrees of electrochemical migration corresponding to at least one dendrite in the target structural layer to obtain the degree of electrochemical migration corresponding to the target structural layer.

[0056] It should be noted that the longer the dendrite length, the greater the degree of electrochemical migration. Therefore, exemplarily, for each target structural layer, the computer device checks whether there is at least one dendrite length greater than or equal to the length threshold in the target structural layer. If so, it is determined that the degree of electrochemical migration corresponding to the target structural layer is the first degree of electrochemical migration. If not, it is determined that the degree of electrochemical migration corresponding to the target structural layer is the second degree of electrochemical migration. The first degree of electrochemical migration is greater than the degree threshold, and the degree threshold is greater than the second degree of electrochemical migration.

[0057] Step 208: In the case where the degree of electrochemical migration of at least one target structural layer is greater than the degree threshold, obtain a reliability detection result indicating that the target type of carrier board fails the detection.

[0058] Exemplarily, in the case where the degree of electrochemical migration of each target structural layer is less than or equal to the degree threshold, obtain a reliability detection result indicating that the target type of carrier board passes the detection.

[0059] In the above-mentioned carrier-like detection method, by acquiring an image of at least one candidate structural layer in the target carrier-like board, the target structural layer with dendrites can be screened out in advance from at least one candidate structural layer, avoiding the detection of all candidate structural layers, thereby improving the detection efficiency. For each target structural layer, based on the image of the target structural layer, at least one circuit with dendrites growing in the target structural layer can be effectively identified. Then, for each target structural layer, based on the dendrite length of the dendrites corresponding to at least one circuit, the electrochemical migration degree corresponding to the target structural layer can be accurately estimated. For this reason, the electrochemical migration degree can accurately reflect whether the target carrier-like board is valid. In the case where the electrochemical migration degree of at least one target structural layer is greater than the degree threshold, the reliability test result indicating that the target carrier-like board fails the detection can be directly and accurately determined. As a result, accurate detection of the reliability of the carrier-like board is achieved, and the accuracy of the detection is improved.

[0060] In one embodiment, the target-like carrier board determination step includes: obtaining attribute information of the similar carrier board sample, and querying stress conditions that match the similar carrier board sample based on the attribute information; based on the stress conditions, performing an aging treatment on the similar carrier board sample, and using the similar carrier board sample obtained by the aging treatment as the target-like carrier board.

[0061] Among them, the carrier-like sample is a carrier-like sample to be subjected to an aging test, and the attribute information can be the material used by the carrier-like sample, or the design information of the carrier-like sample, etc. The stress condition indicates the stress information in the use environment of the carrier-like sample, for example, the temperature, voltage, current and other information of the use environment of the carrier-like sample. Exemplarily, the stress condition can be a combination of multiple stresses, such as a combination of moisture / heat / electricity, moisture / heat / electricity / pressure; specifically, the temperature is 50~200±5℃, the relative humidity is 70~95±5%, and the bias voltage is 0.5~100V. In particular, the temperature is 110±5℃ and the relative humidity is 85±5%.

[0062] Exemplarily, after obtaining a carrier-like sample, the computer device queries the corresponding stress condition according to the attribute information of the carrier-like sample and the mapping relationship between the attribute information and the stress condition. The computer device inputs the stress condition into the aging treatment device to instruct the aging treatment device to set the stress condition so as to perform aging treatment on the carrier-like sample in the aging treatment device. After the aging treatment time reaches a preset treatment period, the carrier-like sample obtained by the aging treatment is used as the target carrier-like sample. The preset treatment period refers to the period when the dendrites are fully grown, ensuring that the target carrier-like sample used for detection can be fully aged to avoid inaccurate detection results due to incomplete dendrite growth. Exemplarily, the preset treatment period is 264 hours. Exemplarily, the preset treatment period is predetermined based on historical experience. Exemplarily, different types of carrier samples have different corresponding preset treatment periods.

[0063] In this embodiment, the matching stress conditions are pre-query based on the attribute information of the build-up board sample. Therefore, the build-up board sample can be pre-aged under the matching conditions in its corresponding usage environment to obtain the target build-up board. Subsequently, the detection of the target build-up board can reflect whether the build-up board sample is reasonable, ensuring the effectiveness and credibility of the detection.

[0064] In one embodiment, the method further includes: verifying whether the build-up board sample has a short-circuit phenomenon; in the case where it is verified that the build-up board sample does not have a short-circuit phenomenon, returning to the step of aging the build-up board sample based on the stress conditions.

[0065] Exemplarily, an insulation resistance test is performed on the build-up board sample to obtain a test result. In the case where the test result indicates that the build-up board does not have a short-circuit phenomenon, return to the step of aging the build-up board sample based on the stress conditions. In the case where the test result indicates that the build-up board has a short-circuit phenomenon, end the reliability test of the build-up board sample.

[0066] In this embodiment, before aging the build-up board sample, it is pre-verified that the build-up board sample does not have a short-circuit before aging. In this way, it is possible to avoid aging the build-up board sample that has already had a short-circuit. Subsequently, when it is determined that the reliability test result fails, it can be confirmed that the build-up board sample will cause a short-circuit due to electrochemical migration when used in the corresponding usage environment, ensuring the effectiveness of the reliability test.

[0067] In one embodiment, the step of determining at least one candidate structural layer includes: determining the line spacing of the structural layers other than the first layer in the target build-up board according to the design document of the target build-up board; in the case where the line spacing of each of the other structural layers is greater than or equal to the preset line spacing, taking the first layer as the candidate structural layer; in the case where there is at least one other structural layer with a line spacing less than the preset line spacing, taking at least one other structural layer and the first layer as the candidate structural layers.

[0068] Among them, the design document is used to record the layout of each structural layer in the target build-up board, the line spacing information in each structural layer, etc. The line spacing refers to the distance between two adjacent lines in the same structural layer. It should be noted that compared with the PCB, the build-up board has a shorter line spacing. The shorter the line spacing, the easier it is for electrochemical migration to occur between the two adjacent lines, and the easier it is to generate dendrites, making it easier for the two adjacent lines to conduct and thus cause a short-circuit phenomenon. As Figure 4 shown, it is a schematic diagram of the lines in the structural layer in one embodiment. Figure 4 It schematically shows the line layout of each structural layer in the build-up board.

[0069] Exemplarily, the computer device determines the minimum line pitch of each structural layer other than the first layer in the target type of carrier board according to the design file of the target type of carrier board. For each other structural layer, the computer device checks whether the minimum line pitch of the other structural layer is less than a preset line pitch. If it is less, the other structural layer is used as a candidate structural layer. If it is greater than or equal to the preset line pitch, the other structural layer is not used as a candidate structural layer. The computer device uses the first layer as a candidate structural layer.

[0070] Of course, in the case where the design file of the target type of carrier board is not obtained, that is, when the provider of the carrier board sample corresponding to the target type of carrier board does not provide the design file of the carrier board sample, the computer device directly uses each structural layer of the target type of carrier board as a candidate structural layer.

[0071] In this embodiment, candidate structural layers that are very likely to cause electrochemical migration can be pre-screened through the line pitch of non-first structural layers, avoiding performing reliability detection on each structural layer, and improving the efficiency and accuracy of reliability detection.

[0072] In one embodiment, according to the image of the target structural layer, identifying at least one circuit in the target structural layer where dendrites grow includes: according to the line pitch between two adjacent circuits in the image of the target structural layer, cropping out the area with dense line pitch in the image of the target structural layer; through a dendrite positioning model, performing dendrite positioning on the area with dense line pitch to determine at least one circuit in the target structural layer where dendrites grow.

[0073] Among them, the area with dense line pitch can be understood as a sub-image in the image of the target structural layer. The circuits in this sub-image are dense, and thus it is very easy to have electrochemical migration and dendrites are more likely to grow.

[0074] Exemplarily, the computer device calls an image segmentation model according to the line pitch of each pair of circuit combinations in the image of the target structural layer to determine the area with dense line pitch in the image. Each circuit combination includes two adjacent circuits in the target structural layer. The image segmentation model is a model built based on a neural network and is used to identify and segment the area with dense line pitch in the image.

[0075] Exemplarily, for the target structural layer, the computer device determines the minimum line pitch in the target structural layer, and based on the pitch increment and the minimum line pitch, determines the line pitch range. The computer device uses the area in the image of the target structural layer where the line pitch is within the line pitch range as the area with dense line pitch. The line pitch of any circuit combination in this area is within the line pitch range.

[0076] Exemplarily, after determining the line pitch dense area, input the line pitch dense area into the dendrite positioning model to perform dendrite positioning on the line pitch dense area, so as to determine at least one circuit in the target structural layer where dendrites have grown.

[0077] In this embodiment, through the line pitch between two adjacent circuits in the image of the target structural layer, the line pitch dense area in the image can be determined more accurately, and dendrite positioning can be directly performed on the line pitch dense area, without performing dendrite positioning on the entire image, greatly reducing the workload of positioning, thereby improving the reliability detection efficiency.

[0078] In one embodiment, determining the degree of electrochemical migration corresponding to the target structural layer according to the dendrite lengths of the dendrites corresponding to at least one circuit includes: determining the longest dendrite from the dendrites corresponding to at least one circuit, and taking the circuit from which the longest dendrite originates as the target circuit; determining the line pitch between the target circuit and the adjacent circuit adjacent thereto, and taking the degree of difference between the dendrite length of the longest dendrite and the line pitch as the degree of electrochemical migration corresponding to the target structural layer.

[0079] Wherein, the adjacent circuit refers to a circuit adjacent to the target circuit and having dendrites between the target circuit and the adjacent circuit, that is, the dendrites growing on the target circuit grow towards the adjacent circuit.

[0080] Exemplarily, for each circuit in at least one circuit, the computer device determines the dendrite lengths of at least one dendrite in the circuit, and the computer device selects the dendrite with the longest dendrite length among at least one circuit as the longest dendrite. The computer device takes the circuit on which the longest dendrite grows as the target circuit and determines the line pitch between the target circuit and the adjacent circuit. Taking the ratio of the dendrite length of the longest dendrite to the line pitch as the degree of difference. As Figure 5 shown, it is a schematic diagram of dendrite length in one embodiment. Figure 5 The distance between the lines in the middle refers to the line pitch between the target circuit and the adjacent circuit, Figure 5 and the dendrite distance in

[0081] Exemplarily, according to the degree of electrochemical migration, evaluate the usability of the carrier board sample corresponding to the target type of carrier board. For example, when the degree of electrochemical migration of all target structural layers is less than or equal to 20%, it is determined that no short-circuit phenomenon has occurred, the detection passes, and it is considered that the carrier board sample corresponding to the target type of carrier board is available, and the corresponding carrier board can be produced and applied with reference to the carrier board sample. When the degree of electrochemical migration of all target structural layers is between 20% and 50%, it is determined that no short-circuit phenomenon has occurred temporarily, the detection passes, and it is considered that the corresponding carrier board sample is considered available; when the degree of electrochemical migration of one target structural layer exceeds 50%, it is determined that the detection is unavailable, and it is considered that the carrier board sample cannot be used.

[0082] In this embodiment, the degree of difference between the dendrite length of the longest dendrite and the line spacing is directly used as the degree of electrochemical migration, without the need to calculate for all dendrites, reducing the amount of calculation, and thus improving the efficiency of reliability detection.

[0083] In a specific embodiment, the specific steps are as follows:

[0084] First step: The computer device obtains the attribute information of the substrate-like sample, queries the stress conditions matching the substrate-like sample according to the attribute information; checks whether the substrate-like sample has a short-circuit phenomenon; in the case where it is checked that the substrate-like sample does not have a short-circuit phenomenon, based on the stress conditions, the substrate-like sample is aged, and the aged substrate-like sample is used as the target substrate.

[0085] Second step: The computer device can perform one of the horizontal reliability detection and the vertical reliability detection on the target substrate. Among them, the vertical reliability detection is to longitudinally cut the target substrate and check whether dendrites are generated between two adjacent holes in the target substrate. If dendrites are generated, the ratio of the area of the dendrites to the area of the cut surface obtained by longitudinal cutting is determined. If the ratio is greater than or equal to the area threshold, it is determined that the target substrate fails the detection. If it is less than the area threshold, it is determined that the target substrate passes the detection. Among them, the horizontal reliability detection refers to detecting whether dendrites are generated between two adjacent lines in each structural layer. If dendrites are generated, it is further checked whether a short circuit occurs. If a short circuit occurs, the target substrate fails the detection. If no short circuit occurs, the target substrate passes the detection. The embodiment of the present application is horizontal reliability detection, and the specific steps are as follows:

[0086] Third step: The computer device determines the line spacing of other structural layers except the first layer in the target substrate according to the design file of the target substrate; in the case where the line spacing of each other structural layer is greater than or equal to the preset line spacing, the first layer is used as the candidate structural layer; in the case where the line spacing of at least one other structural layer is less than the preset line spacing, at least one other structural layer and the first layer are both used as the candidate structural layers.

[0087] Fourth step: By cutting layer by layer, and using an image acquisition device to collect the cross-section of the target substrate after each cut one by one, images of each candidate structural layer are obtained. After the computer device obtains the images of each candidate structural layer sent by the image acquisition device, according to the images of at least one candidate structural layer, the target structural layer with dendrites is screened out from at least one candidate structural layer;

[0088] Step 5: For each target structural layer, the computer device crops out the area with dense line spacing in the image of the target structural layer according to the line spacing between two adjacent lines in the image of the target structural layer; through the dendrite positioning model, dendrite positioning is performed on the area with dense line spacing to determine at least one line on which dendrites grow in the target structural layer.

[0089] Step 6: For each target structural layer, the computer device determines the longest dendrite from the dendrites corresponding to each of the at least one line, and takes the line from which the longest dendrite originates as the target line; determines the line spacing between the target line and the adjacent line adjacent thereto, and takes the degree of difference between the dendrite length of the longest dendrite and the line spacing as the degree of electrochemical migration corresponding to the target structural layer.

[0090] Step 7: When the degree of electrochemical migration of at least one target structural layer is greater than the degree threshold, the computer device obtains a reliability detection result indicating that the detection of the target type of carrier board fails. When the degree of electrochemical migration of each target structural layer is less than or equal to the degree threshold, the computer device obtains a reliability detection result indicating that the detection of the target type of carrier board passes.

[0091] In this embodiment, by acquiring the images of at least one candidate structural layer in the target type of carrier board, it is possible to pre-screen out the target structural layers with dendrites from at least one candidate structural layer, avoiding detecting all candidate structural layers and improving the detection efficiency. For each target structural layer, based on the image of the target structural layer, it is possible to effectively identify at least one line on which dendrites grow in the target structural layer. Then, for each target structural layer, based on the dendrite lengths of the dendrites corresponding to each of the at least one line, it is possible to accurately estimate the degree of electrochemical migration corresponding to the target structural layer. Therefore, by means of the degree of electrochemical migration, it is possible to accurately reflect whether the target type of carrier board is effective. When the degree of electrochemical migration of at least one target structural layer is greater than the degree threshold, it is possible to directly and accurately determine a reliability detection result indicating that the detection of the target type of carrier board fails. Thus, accurate detection of the reliability of the carrier board is achieved, and the accuracy of the detection is improved.

[0092] It should be understood that although the steps in the flowcharts involved in the above embodiments are sequentially shown according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0093] Based on the same inventive concept, an embodiment of the present application also provides a type of substrate detection device for implementing the type of substrate detection method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the type of substrate detection device provided below can refer to the limitations on the type of substrate detection method in the above text, and will not be repeated here.

[0094] In an exemplary embodiment, as Figure 6 shown, a type of substrate detection device 600 is provided, including: an image acquisition module 602, a circuit recognition module 604, a migration degree determination module 606, and a reliability detection module 608, where:

[0095] The image acquisition module 602 is configured to acquire an image of at least one candidate structure layer in the target type of substrate, and screen out a target structure layer with dendrites from at least one candidate structure layer according to the image of at least one candidate structure layer;

[0096] The circuit recognition module 604 is configured to, for each target structure layer, identify at least one circuit with dendrites growing in the target structure layer according to the image of the target structure layer;

[0097] The migration degree determination module 606 is configured to, for each target structure layer, determine the electrochemical migration degree corresponding to the target structure layer according to the dendrite lengths of the dendrites corresponding to at least one circuit;

[0098] The reliability detection module 608 is configured to obtain a reliability detection result indicating that the detection of the target type of substrate fails when the electrochemical migration degree of at least one target structure layer is greater than the degree threshold.

[0099] In one embodiment, the device further includes a build-up board determination module, configured to obtain the attribute information of the build-up board sample, query the stress conditions matching the build-up board sample according to the attribute information; based on the stress conditions, perform an aging process on the build-up board sample, and use the build-up board sample obtained by the aging process as the target build-up board.

[0100] In one embodiment, the build-up board determination module is further configured to verify whether a short circuit occurs in the build-up board sample; in the case where it is verified that no short circuit occurs in the build-up board sample, return to the step of performing an aging process on the build-up board sample based on the stress conditions.

[0101] In one embodiment, the device further includes a structure layer determination module, configured to determine the line pitch of other structure layers except the first layer in the target build-up board according to the design file of the target build-up board; in the case where the line pitch of each other structure layer is greater than or equal to the preset line pitch, use the first layer as the candidate structure layer; in the case where there is at least one other structure layer with a line pitch less than the preset line pitch, use at least one other structure layer and the first layer as the candidate structure layers.

[0102] In one embodiment, the circuit recognition module 604 is configured to crop out the area with dense line pitch in the image of the target structure layer according to the line pitch between two adjacent circuits in the image of the target structure layer; perform dendrite positioning on the area with dense line pitch through the dendrite positioning model to determine at least one circuit in the target structure layer where dendrites grow.

[0103] In one embodiment, the migration degree determination module 606 is configured to determine the longest dendrite from the dendrites corresponding to each of the at least one circuit, and use the circuit from which the longest dendrite originates as the target circuit; determine the line pitch between the target circuit and the adjacent circuit adjacent thereto, and use the difference degree between the dendrite length of the longest dendrite and the line pitch as the electrochemical migration degree corresponding to the target structure layer.

[0104] Each module in the above build-up board detection device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in hardware form or be independent of it, or can be stored in the memory in the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to the above respective modules.

[0105] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 7As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for detecting a carrier board.

[0106] Those skilled in the art can understand that Figure 7 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0107] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps in the above method embodiments are implemented.

[0108] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0109] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0110] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0111] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0112] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in this application.

[0113] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for detecting a type of carrier board, characterized in that, The method includes: Obtaining images of at least one candidate structural layer in a target substrate, and screening out a target structural layer with dendrites from the at least one candidate structural layer according to the images of the at least one candidate structural layer; For each target structural layer, identifying at least one circuit in the target structural layer where dendrites grow according to the image of the target structural layer; For each target structural layer, determining the degree of electrochemical migration corresponding to the target structural layer according to the dendrite lengths of the dendrites corresponding to the at least one circuit; In the case where the degree of electrochemical migration of at least one target structural layer is greater than a degree threshold, obtaining a reliability detection result indicating that the detection of the target substrate fails.

2. The method according to claim 1, wherein The step of determining the target substrate includes: Obtaining the attribute information of a substrate sample, and querying the stress conditions matching the substrate sample according to the attribute information; Based on the stress conditions, aging the substrate sample, and using the substrate sample obtained by the aging treatment as the target substrate.

3. The method according to claim 2, wherein The method further includes: Verifying whether the substrate sample has a short - circuit phenomenon; In the case where it is verified that the substrate sample does not have a short - circuit phenomenon, returning to the step of aging the substrate sample based on the stress conditions.

4. The method according to claim 1, wherein The step of determining the at least one candidate structural layer includes: According to the design document of the target substrate, determining the line pitch of the structural layers other than the first layer in the target substrate; In the case where the line pitch of each of the other structural layers is greater than or equal to a preset line pitch, taking the first layer as a candidate structural layer; In the case where there is at least one other structural layer with a line pitch less than the preset line pitch, taking the at least one other structural layer and the first layer as candidate structural layers.

5. The method according to claim 1, wherein The step of identifying at least one circuit in the target structural layer where dendrites grow according to the image of the target structural layer includes: According to the line pitch between two adjacent circuits in the image of the target structural layer, cropping out the area with dense line pitch in the image of the target structural layer; Through a dendrite positioning model, performing dendrite positioning on the area with dense line pitch to determine at least one circuit in the target structural layer where dendrites grow.

6. The method according to claim 1, wherein The step of determining the degree of electrochemical migration corresponding to the target structural layer according to the dendrite lengths of the dendrites corresponding to the at least one circuit includes: Determining the longest dendrite from the dendrites corresponding to the at least one circuit, and taking the circuit from which the longest dendrite originates as the target circuit; Determining the line pitch between the target circuit and its adjacent circuit, and taking the difference degree between the dendrite length of the longest dendrite and the line pitch as the degree of electrochemical migration corresponding to the target structural layer.

7. A kind of carrier board detection device, characterized in that, The device includes: An image acquisition module, configured to obtain images of at least one candidate structural layer in a target substrate, and screen out a target structural layer with dendrites from the at least one candidate structural layer according to the images of the at least one candidate structural layer; A circuit identification module, configured to, for each target structural layer, identify at least one circuit in the target structural layer where dendrites grow according to the image of the target structural layer; A migration degree determination module, configured to determine, for each target structural layer, an electrochemical migration degree corresponding to the target structural layer according to dendrite lengths of dendrites corresponding to at least one circuit respectively; A reliability detection module, configured to obtain a reliability detection result indicating that the detection of the target type of carrier board fails when the electrochemical migration degree of at least one target structural layer is greater than a degree threshold.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images