A method and device for detecting the electrical conductivity of a circuit board

Abstract

The present disclosure provides a detection method and apparatus. The method includes: after acquiring an image, inputting the image into a detection network, enabling the detection network to output first indication information for indicating the electrical conductivity of a circuit board according to the feature information of the circuit board in the image, and determining the electrical conductivity of the circuit board according to the first indication information. The above method uses a detection network to determine the electrical conductivity of the circuit board bound in the image, omits the process of measuring the resistance of the bound circuit board in the related art, improves the detection efficiency of the circuit board, and reduces the detection cost of the circuit board.

Description

Technical Field

[0001] The present disclosure relates to the technical field of display panels, and in particular, to a method and apparatus for detecting the electrical conductivity of a circuit board. Background Art

[0002] During the process of manufacturing a display panel, after binding the circuit board, it is necessary to detect the binding effect of the circuit board. In the related art, usually, the resistance value of the bound circuit board is measured, and the electrical conductivity of the bound circuit board is determined according to the resistance value.

[0003] Since in the related art, when detecting the binding effect of the circuit board, the process of measuring the resistance is added, resulting in a reduction in the detection efficiency of the circuit board and an increase in the detection cost, ultimately leading to a reduction in the production efficiency of the display panel and an increase in the production cost.

[0004] Therefore, those skilled in the art urgently need to develop a new method for detecting the electrical conductivity of a circuit board to improve the detection efficiency of the circuit board and reduce the detection cost of the circuit board. Summary of the Invention

[0005] In view of this, the present disclosure provides a method and apparatus for detecting the electrical conductivity of a circuit board to solve the above technical problems.

[0006] According to a first aspect of an embodiment of the present disclosure, there is provided a method for detecting the electrical conductivity of a circuit board, the method including:

[0007] Obtain an image, where the image includes a bound circuit board;

[0008] Input the image into a detection network, and enable the detection network to output first indication information for indicating the electrical conductivity of the circuit board according to the feature information of the circuit board in the image;

[0009] Determine the electrical conductivity of the circuit board according to the first indication information.

[0010] Optionally, the feature information of the circuit board includes: the morphology of conductive particles on the surface of the circuit board and / or the binding position of the circuit board.

[0011] Optionally, in the case where the feature information of the circuit board includes the morphology of conductive particles on the surface of the circuit board, the detection network outputs first indication information for indicating the electrical conductivity of the circuit board according to the feature information of the circuit board in the image, including:

[0012] The detection network determines a first probability that the morphology of the conductive particles corresponds to each preset electrical conductivity among a plurality of preset electrical conductivities;

[0013] The detection network determines the target preset conductivity corresponding to the maximum first probability, and uses the target preset conductivity as the conductivity of the circuit board;

[0014] The detection network outputs first indication information for indicating the target preset conductivity.

[0015] Optionally, when the feature information of the circuit board further includes the bonding position of the circuit board, the detection network outputs first indication information for indicating the conductivity of the circuit board according to the feature information of the circuit board in the image, and further includes:

[0016] The detection network determines a second probability that the bonding position of the circuit board is unqualified;

[0017] The detection network determines whether each of the first probability and the second probability satisfies a preset condition, and in response to each of the first probability and the second probability satisfying the preset condition, outputs first indication information for indicating the target preset conductivity.

[0018] Optionally, the detection network determines whether each of the first probability and the second probability satisfies a preset condition, including:

[0019] The detection network determines whether the second probability is less than each of the first probabilities.

[0020] Optionally, the detection network is obtained by the following method:

[0021] Obtain a sample image, which includes a bonded sample circuit board, and the sample image has annotation information indicating the conductivity of the sample circuit board;

[0022] Input the sample image into a detection network to be trained, so that the detection network to be trained outputs second indication information for indicating the conductivity of the sample circuit board according to the feature information of the sample circuit board in the sample image, and the feature information of the sample circuit board includes: the morphology of conductive particles on the surface of the sample circuit board and / or the bonding position of the sample circuit board;

[0023] Adjust the parameters of the detection network to be trained according to the difference between the annotation information and the second indication information to obtain the detection network.

[0024] Optionally, when the feature information of the sample circuit board includes the morphology of conductive particles on the surface of the sample circuit board, the detection network to be trained outputs second indication information for indicating the conductivity of the sample circuit board according to the feature information of the sample circuit board in the sample image, including:

[0025] For each of a plurality of preset conductivity properties, the to-be-trained detection network determines a third probability that the morphology of the conductive particles located on the surface of the sample circuit board corresponds to the preset conductivity property;

[0026] The to-be-trained detection network determines the preset conductivity property corresponding to the maximum third probability, and uses the preset conductivity property corresponding to the maximum third probability as the conductivity property of the sample circuit board;

[0027] The to-be-trained detection network outputs the second indication information, and the second indication information indicates the preset conductivity property corresponding to the maximum third probability.

[0028] Optionally, when the feature information of the sample circuit board further includes the bonding position of the sample circuit board, the to-be-trained detection network outputs second indication information for indicating the conductivity property of the sample circuit board according to the feature information of the sample circuit board in the sample image, and further includes:

[0029] The to-be-trained detection network determines a fourth probability that the bonding position of the sample circuit board is unqualified;

[0030] The to-be-trained detection network determines whether each of the third probabilities and the fourth probability satisfies the preset condition, and in response to each of the third probabilities and the fourth probability satisfying the preset condition, outputs the second indication information.

[0031] According to a second aspect of the embodiments of the present disclosure, there is provided a detection device for the conductivity property of a circuit board, and the device includes:

[0032] An image acquisition module, configured to acquire an image, where the image includes a bonded circuit board;

[0033] An image input module, configured to input the image into a detection network, so that the detection network outputs first indication information for indicating the conductivity property of the circuit board according to the feature information of the circuit board in the image;

[0034] A conductivity property determination module, configured to determine the conductivity property of the circuit board according to the first indication information.

[0035] Optionally, the feature information of the circuit board includes: the morphology of the conductive particles located on the surface of the circuit board and / or the bonding position of the circuit board.

[0036] Optionally, when the feature information of the circuit board includes the morphology of the conductive particles located on the surface of the circuit board, the detection network includes:

[0037] A first probability determination sub-network, configured to determine, for each of a plurality of preset conductivity properties, a first probability that the morphology of the conductive particles corresponds to the preset conductivity property;

[0038] A conductivity property determination sub-network, configured to determine a target preset conductivity property corresponding to the maximum first probability, and use the target preset conductivity property as the conductivity property of the circuit board;

[0039] A first indication information output sub-network, configured to output first indication information for indicating the target preset conductivity property.

[0040] Optionally, when the characteristic information of the circuit board further includes the bonding position of the circuit board, the detection network further includes:

[0041] A second probability determination sub-network, configured to determine a second probability that the bonding position of the circuit board is unqualified;

[0042] A first condition judgment sub-network, configured to determine whether each of the first probabilities and the second probability satisfies a preset condition, and in response to each of the first probabilities and the second probability satisfying the preset condition, output first indication information for indicating the target preset conductivity property.

[0043] Optionally, the condition judgment sub-network is configured to determine whether the second probability is less than each of the first probabilities.

[0044] Optionally, the apparatus further includes:

[0045] A sample image acquisition module, configured to acquire a sample image, where the sample image includes a sample circuit board that has been bonded, and the sample image has annotation information indicating the conductivity property of the sample circuit board;

[0046] A sample graphic input module, configured to input the sample image into a detection network to be trained, so that the detection network to be trained outputs second indication information for indicating the conductivity property of the sample circuit board according to the characteristic information of the sample circuit board in the sample image, where the characteristic information of the sample circuit board includes: the morphology of the conductive particles located on the surface of the sample circuit board and / or the bonding position of the sample circuit board;

[0047] A parameter adjustment module, configured to adjust the parameters of the detection network to be trained according to the difference between the annotation information and the second indication information, and obtain the detection network.

[0048] Optionally, when the characteristic information of the sample circuit board includes the morphology of the conductive particles located on the surface of the sample circuit board, the detection network to be trained includes:

[0049] A third probability determination sub-network, configured to determine, for each of a plurality of preset electrical conductivities, a third probability that the morphology of the conductive particles located on the surface of the sample circuit board corresponds to the preset electrical conductivity;

[0050] A second probability determination sub-network, configured to determine the preset electrical conductivity corresponding to the maximum third probability, and use the preset electrical conductivity corresponding to the maximum third probability as the electrical conductivity of the sample circuit board;

[0051] A second indication information output sub-network, configured to output the second indication information, where the second indication information indicates the preset electrical conductivity corresponding to the maximum third probability.

[0052] Optionally, when the feature information of the sample circuit board further includes the bonding position of the sample circuit board, the detection network to be trained further includes:

[0053] A fourth probability determination sub-network, configured to determine a fourth probability that the bonding position of the sample circuit board is unqualified;

[0054] A second condition judgment sub-network, configured to determine whether each of the third probabilities and the fourth probability satisfies the preset condition, and output the second indication information in response to each of the third probabilities and the fourth probability satisfying the preset condition.

[0055] According to a third aspect of the embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method according to any one of the first aspects are implemented.

[0056] According to a fourth aspect of the embodiments of the present disclosure, there is provided a detection device for the electrical conductivity of a circuit board, including:

[0057] A processor;

[0058] A memory for storing instructions executable by the processor;

[0059] Wherein, the processor is configured to:

[0060] Obtain an image, where the image includes a bonded circuit board;

[0061] Input the image into the detection network, so that the detection network outputs first indication information for indicating the electrical conductivity of the circuit board according to the feature information of the circuit board in the image;

[0062] Determine the electrical conductivity of the circuit board according to the first indication information.

[0063] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:

[0064] In the embodiments of the present disclosure, after obtaining an image, the image is input into a detection network, and the detection network outputs first indication information for indicating the electrical conductivity of the circuit board according to the feature information of the circuit board in the image, and determines the electrical conductivity of the circuit board according to the first indication information. The above method uses a detection network to determine the electrical conductivity of the circuit board bound in the image, omits the process of measuring the resistance of the bound circuit board in the related art, improves the detection efficiency of the circuit board, and reduces the detection cost of the circuit board.

[0065] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 is a flowchart of a method for detecting the electrical conductivity of a circuit board shown according to an exemplary embodiment;

[0067] Figure 2 is a flowchart of a method for training a detection network shown according to an exemplary embodiment;

[0068] Figure 3 is a block diagram of a device for detecting the electrical conductivity of a circuit board shown according to an exemplary embodiment;

[0069] Figure 4 is a schematic structural diagram of a device for detecting the electrical conductivity of a circuit board shown according to an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0071] The terms used in the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. The singular forms "a", "the" and "said" used in the present disclosure and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0072] It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0073] Figure 1 Flowchart of a method for detecting the electrical conductivity of a circuit board according to an exemplary embodiment Figure 1 The shown detection method includes the following steps:

[0074] In step 101, an image is acquired, and the image includes a bound circuit board.

[0075] After binding the circuit board, the bound circuit board can be photographed to obtain an image including the bound circuit board.

[0076] In step 102, the image is input into a detection network, and the detection network outputs first indication information for indicating the electrical conductivity of the circuit board according to the characteristic information of the circuit board in the image.

[0077] The input of the detection network is an image, and the output of the detection network is first indication information for indicating the electrical conductivity of the circuit board in the image. The detection network can determine the electrical conductivity of the circuit board according to the characteristic information located on the circuit board in the image and output first indication information for indicating the electrical conductivity of the circuit board.

[0078] In one embodiment, there are conductive particles on the surface of the circuit board, and the conductive particles have a conductive function when broken. The morphology of the conductive particles reflects the protrusion and breaking conditions of the conductive particles, and thus reflects the electrical conductivity of the circuit board.

[0079] The binding position of the circuit board affects the electrical conductivity of the circuit board. Generally, the greater the deviation between the actual binding position and the correct binding position of the circuit board, the worse the electrical conductivity of the circuit board.

[0080] Based on this, the characteristic information of the circuit board may include: the morphology of the conductive particles located on the surface of the circuit board, and / or, the binding position of the circuit board.

[0081] In one embodiment, the content of the first indication information has various types. For example, the conductivity value of the circuit board at the end of binding; the conductivity performance of the circuit board at the end of binding does not meet the preset requirements; the conductivity value of the circuit board at a certain time after the end of binding. For example, the conductivity value of the circuit board N months after the end of binding, where N is a positive integer; the conductivity performance of the circuit board fails within a certain period after the end of binding. For example, the conductivity performance of the circuit board fails within M months after the end of binding, where M is a positive integer; the conductivity performance of the circuit board does not fail (i.e., the conductivity performance is qualified) within a certain period after the end of binding. For example, the conductivity performance of the circuit board does not fail within M months after the end of binding, and so on.

[0082] The form of the first indication information has various types, such as text, symbols, combinations of text and symbols, etc.

[0083] In one embodiment, there are multiple preset conductivity performances. For example, the conductivity performance that does not meet the preset requirements at the end of binding; the conductivity performance that fails within a certain period after the end of binding. For example, the conductivity performance that fails within 1 month after the end of binding, the conductivity performance that fails within 1 - 3 months after the end of binding; the conductivity performance that does not fail within a certain period after the end of binding (i.e., the qualified conductivity performance). For example, the conductivity performance that does not fail within 3 months after the end of binding.

[0084] Based on this, when the characteristic information of the circuit board includes the morphology of conductive particles on the surface of the circuit board, the detection network outputs the first indication information for indicating the conductivity performance of the circuit board according to the characteristic information of the circuit board in the image, which may include: First, for each preset conductivity performance among the multiple preset conductivity performances, determine the first probability that the morphology of the conductive particles on the surface of the circuit board corresponds to the preset conductivity performance; Second, determine the target preset conductivity performance corresponding to the maximum first probability, and the target preset conductivity performance is used as the conductivity performance of the circuit board; Third, output the first indication information for indicating the target preset conductivity performance.

[0085] In one embodiment, based on the previous embodiment, the characteristic information of the circuit board may further include the binding position of the circuit board. At this time, when the detection network outputs the first indication information for indicating the conductivity performance of the circuit board according to the characteristic information of the circuit board in the image, it may further include: The first step: Determine the second probability that the binding position of the circuit board is unqualified; The second step: Determine whether each first probability and the second probability meet the preset conditions, and in response to each first probability and the second probability meeting the preset conditions, output the first indication information for indicating the target preset conductivity performance.

[0086] For example, the detection network determines whether the second probability is less than each first probability, and in response to the second probability being less than each first probability, outputs the first indication information for indicating the target preset conductivity performance.

[0087] Optionally, in response to determining that each of the first probability and the second probability does not meet the preset condition, the detection network outputs indication information (which may be referred to as third indication information) for indicating that the bonding position of the circuit board is unqualified.

[0088] For example, in response to the second probability being greater than or equal to at least one of the first probabilities, indication information for indicating that the bonding position of the circuit board is unqualified is output.

[0089] In step 103, according to the first indication information, the electrical conductivity of the circuit board is determined.

[0090] The first indication information indicates the electrical conductivity of the circuit board, and the electrical conductivity of the circuit board can be determined according to the first indication information.

[0091] In the embodiments of the present disclosure, after obtaining the image, the image is input into the detection network, so that the detection network outputs the first indication information for indicating the electrical conductivity of the circuit board according to the feature information of the circuit board in the image, and the electrical conductivity of the circuit board is determined according to the first indication information. The above method uses the detection network to determine the electrical conductivity of the bonded circuit board in the image, omits the process of measuring the resistance of the bonded circuit board in the related art, improves the detection efficiency of the circuit board, and reduces the detection cost of the circuit board.

[0092] In some of the above embodiments, the detection network can determine whether the electrical conductivity of the circuit board will fail within a future period of time according to the feature information of the circuit board in the image, and output corresponding indication information, so as to timely determine the circuit board whose current electrical conductivity detection is qualified but whose electrical conductivity will fail within a future period of time, prevent the occurrence of the failure of the electrical conductivity of the circuit board within a period of time after the display panel leaves the factory, ensure the accuracy of the detection result of the electrical conductivity of the circuit board, and ensure the quality of the display panel.

[0093] Figure 2 According to a flowchart of a method for training a detection network shown in an exemplary embodiment, Figure 2 The shown training method includes the following steps:

[0094] In step 201, a sample image is obtained. The sample image includes a bonded sample circuit board, and the sample image has annotation information indicating the electrical conductivity of the sample circuit board.

[0095] The content of the annotation information has various types. For example, the conductivity value of the circuit board at the end of binding; the conductivity performance of the circuit board at the end of binding does not meet the preset requirements; the conductivity value of the circuit board at a certain time after the end of binding, for example, the conductivity value of the circuit board at N months after the end of binding, where N is a positive integer such as 1, 2, 3, or 4, etc.; the conductivity performance of the circuit board fails within a certain period after the end of binding; the conductivity performance of the circuit board does not fail within a certain period after the end of binding, and so on.

[0096] In step 202, the sample image is input into the detection network to be trained, so that the detection network to be trained outputs second indication information for indicating the conductivity performance of the sample circuit board according to the feature information of the sample circuit board in the sample image. The feature information of the sample circuit board includes: the morphology of the conductive particles on the surface of the sample circuit board and / or the binding position of the sample circuit board.

[0097] In one embodiment, when the feature information of the sample circuit board includes the morphology of the conductive particles on the surface of the sample circuit board, the detection network to be trained outputs second indication information for indicating the conductivity performance of the sample circuit board according to the feature information of the sample circuit board in the sample image, which may include: First, for each preset conductivity performance among multiple preset conductivity performances, the detection network to be trained determines the third probability that the morphology of the conductive particles on the surface of the sample circuit board corresponds to the preset conductivity performance; Second, the detection network to be trained determines the preset conductivity performance corresponding to the maximum third probability, and the preset conductivity performance corresponding to the maximum third probability is used as the conductivity performance of the sample circuit board; Third, the detection network to be trained outputs the second indication information, and the second indication information indicates the preset conductivity performance corresponding to the maximum third probability.

[0098] In one embodiment, on the basis of the previous embodiment, the feature information of the sample circuit board may further include the binding position of the sample circuit board. At this time, the detection network to be trained outputs second indication information for indicating the conductivity performance of the sample circuit board according to the feature information of the sample circuit board in the sample image, which may further include: The first step: The detection network to be trained determines the fourth probability that the binding position of the sample circuit board is unqualified; The second step: The detection network to be trained determines whether each third probability and the fourth probability meet the preset conditions. In response to each third probability and the fourth probability meeting the preset conditions, the second indication information is output, and the second indication information indicates the preset conductivity performance corresponding to the maximum third probability.

[0099] The detection network to be trained may output indication information (which can be called the fourth indication information) for indicating that the binding position of the sample circuit board is unqualified after determining that each third probability and the fourth probability do not meet the preset conditions.

[0100] The preset conditions used by the detection network to be trained are the same as those used by the detection network after the training is completed.

[0101] In step 203, according to the difference between the annotation information and the second indication information, the parameters of the detection network to be trained are adjusted to obtain an adjusted detection network.

[0102] Using the above method to train the detection network to be trained, the obtained detection network can output indication information for indicating the conductive performance of the circuit board according to the feature information of the circuit board in the image. Further, the detection network can output indication information for indicating whether the binding position of the circuit board in the image is qualified, enriching the function of the detection network and facilitating the user to understand whether the binding position of the circuit board is qualified.

[0103] In one embodiment, the process of obtaining sample images is introduced by way of example.

[0104] First, after a sample circuit board is bound, the sample circuit board is photographed to obtain a target image, and the target image shows the morphology of the conductive particles on the surface of the sample circuit board and the binding position of the sample circuit board.

[0105] There may be binding marks, and the target image shows the relative positions of the sample circuit board and the binding marks. For example, there are horizontal binding marks and vertical binding marks, and the target image shows the relative positions of the horizontal edge of the sample circuit board and the horizontal binding marks, and the relative positions of the vertical edge of the sample circuit board and the vertical binding marks. It can be determined that the binding position of the circuit board is unqualified when the distance between the edge of the circuit board and the binding mark is greater than or equal to a preset distance, and it can be determined that the binding position of the circuit board is qualified when the distance between the edge of the circuit board and the binding mark is less than the preset distance.

[0106] Secondly, multiple grayscale images are extracted from the target image, and one grayscale image is used to generate one sample image. The grayscale image is cropped. The first cropped grayscale image only shows the morphology of the conductive particles on the surface of the sample circuit board, the second cropped grayscale image only shows the relative position of the horizontal edge of the sample circuit board and the X-axis binding mark, and the third cropped grayscale image only shows the relative position of the vertical edge of the sample circuit board and the Y-axis binding mark. The three cropped grayscale images are used as a group of sample images with the same annotation information. For example, each annotation information indicates the conductive performance of the same sample circuit board.

[0107] Thirdly, multiple groups of sample images are obtained by using the above method, and the multiple groups of sample images are used to train the detection network to be trained.

[0108] Next, the process of annotating sample images is introduced by way of example.

[0109] After binding the sample circuit board, measure the binding position and resistance of the bound sample circuit board; if the lateral position offset of the sample circuit board exceeds the preset value, label it as NG.X; if the longitudinal position offset of the sample circuit board exceeds the preset value, label it as NG.Y; if the binding position of the sample circuit board is qualified but the resistance value exceeds the specified value, label it as NG.0; if the resistance measurement passes, perform an electrical failure detection on the display panel of the bound sample circuit board. If the conductive performance of the sample circuit board fails within one month, label it as NG.1; if the conductive performance of the sample circuit board fails within one to three months, label it as NG.3. If the conductive performance of the sample circuit board does not fail within three months, it is determined that the conductive particle rupture state on its surface is good during the binding of the sample circuit board, and label it as Pass.

[0110] In one embodiment, the detection network can be a network improved based on the Alexnet network. The detection network can include a convolutional layer, a pooling layer, a fully connected layer, a classifier, etc. The batch normalization method can be used to process data between convolutional layers. The pooling layer can use the max pooling method for downsampling. The features output by the last convolutional layer have been processed into a one-dimensional vector, and the feature vector output by the fully connected layer will be input into the classifier.

[0111] The number of convolutional layers and pooling layers, as well as the size of the convolutional kernel used in the convolutional layer, the stride of the convolutional kernel movement, the number of output channels, etc. can be set as needed.

[0112] For the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present disclosure is not limited by the described action sequence, because according to the present disclosure, certain steps can be performed in other sequences or simultaneously.

[0113] Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present disclosure.

[0114] Corresponding to the foregoing method embodiments for realizing application functions, the present disclosure also provides embodiments of an apparatus for realizing application functions and a corresponding terminal.

[0115] Figure 3 It is a block diagram of a detection device for the conductive performance of a circuit board shown according to an exemplary embodiment. The device may include:

[0116] An image acquisition module 31, configured to acquire an image, where the image includes a bound circuit board;

[0117] An image input module 32, configured to input the image into the detection network, so that the detection network outputs first indication information for indicating the electrical conductivity of the circuit board according to the feature information of the circuit board in the image;

[0118] An electrical conductivity determination module 33, configured to determine the electrical conductivity of the circuit board according to the first indication information.

[0119] In one embodiment, the feature information of the circuit board may include: the morphology of conductive particles on the surface of the circuit board and / or the bonding position of the circuit board.

[0120] In one embodiment, when the feature information of the circuit board may include the morphology of conductive particles on the surface of the circuit board, the detection network may include:

[0121] A first probability determination sub-network, configured to determine, for each preset electrical conductivity among a plurality of preset electrical conductivities, a first probability that the morphology of the conductive particles corresponds to the preset electrical conductivity;

[0122] An electrical conductivity determination sub-network, configured to determine a target preset electrical conductivity corresponding to the maximum first probability, and use the target preset electrical conductivity as the electrical conductivity of the circuit board;

[0123] A first indication information output sub-network, configured to output first indication information for indicating the target preset electrical conductivity.

[0124] In one embodiment, when the feature information of the circuit board may further include the bonding position of the circuit board, the detection network may further include:

[0125] A second probability determination sub-network, configured to determine a second probability that the bonding position of the circuit board is unqualified;

[0126] A first condition judgment sub-network, configured to determine whether each of the first probabilities and the second probabilities satisfies a preset condition, and in response to each of the first probabilities and the second probabilities satisfying the preset condition, output first indication information for indicating the target preset electrical conductivity.

[0127] In one embodiment, the condition judgment sub-network may be configured to determine whether the second probability is less than each of the first probabilities.

[0128] In one embodiment, the device may further include:

[0129] A sample image acquisition module, configured to acquire a sample image, where the sample image includes a sample circuit board that has been bonded, and the sample image has annotation information indicating the electrical conductivity of the sample circuit board;

[0130] A sample graph input module, configured to input the sample image into a detection network to be trained, so that the detection network to be trained outputs second indication information for indicating the conductive performance of the sample circuit board according to the feature information of the sample circuit board in the sample image, where the feature information of the sample circuit board includes: the morphology of conductive particles located on the surface of the sample circuit board and / or the bonding position of the sample circuit board;

[0131] A parameter adjustment module, configured to adjust the parameters of the detection network to be trained according to the difference between the annotation information and the second indication information, and obtain the detection network.

[0132] In one embodiment, when the feature information of the sample circuit board includes the morphology of conductive particles located on the surface of the sample circuit board, the detection network to be trained may include:

[0133] A third probability determination sub-network, configured to determine, for each preset conductive performance among multiple preset conductive performances, the third probability that the morphology of conductive particles located on the surface of the sample circuit board corresponds to the preset conductive performance;

[0134] A second probability determination sub-network, configured to determine the preset conductive performance corresponding to the maximum third probability, and use the preset conductive performance corresponding to the maximum third probability as the conductive performance of the sample circuit board;

[0135] A second indication information output sub-network, configured to output the second indication information, where the second indication information indicates the preset conductive performance corresponding to the maximum third probability.

[0136] In one embodiment, when the feature information of the sample circuit board further includes the bonding position of the sample circuit board, the detection network to be trained may further include:

[0137] A fourth probability determination sub-network, configured to determine the fourth probability that the bonding position of the sample circuit board is unqualified;

[0138] A second condition judgment sub-network, configured to determine whether each of the third probabilities and the fourth probabilities satisfies the preset condition, and in response to each of the third probabilities and the fourth probabilities satisfying the preset condition, output the second indication information.

[0139] For the apparatus embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the descriptions of the method embodiments. The apparatus embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. A person of ordinary skill in the art can understand and implement it without creative efforts.

[0140] Figure 4 FIG. 1600 is a schematic structural diagram of an apparatus 1600 for detecting the electrical conductivity of a circuit board according to an exemplary embodiment. For example, the apparatus 1600 has a wireless Internet access function and may be a user equipment, specifically a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, a wearable device such as a smart watch, smart glasses, a smart bracelet, a smart running shoe, etc.

[0141] Referring Figure 4 to FIG. 1600, the apparatus 1600 may include one or more of the following components: a processing component 1602, a memory 1604, a power supply component 1606, a multimedia component 1608, an audio component 1610, an input / output (I / O) interface 1612, a sensor component 1614, and a communication component 1616.

[0142] The processing component 1602 generally controls the overall operation of the apparatus 1600, such as operations associated with display, telephone call, data communication, camera operation, and recording operation. The processing component 1602 may include one or more processors 1620 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 1602 may include one or more modules to facilitate the interaction between the processing component 1602 and other components. For example, the processing component 1602 may include a multimedia module to facilitate the interaction between the multimedia component 1608 and the processing component 1602.

[0143] The memory 1604 is configured to store various types of data to support the operation of the device 1600. Examples of such data include instructions for any application or method operating on the device 1600, contact data, phone book data, messages, pictures, videos, and the like. The memory 1604 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.

[0144] The power supply component 1606 provides power to various components of the device 1600. The power supply component 1606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 1600.

[0145] The multimedia component 1608 includes a screen that provides an output interface between the device 1600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors described above can sense not only the boundaries of touch or swipe actions but also scan the duration and pressure associated with the touch or swipe operations. In some embodiments, the multimedia component 1608 includes a front camera and / or a rear camera. When the device 1600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.

[0146] The audio component 1610 is configured to output and / or input audio signals. For example, the audio component 1610 includes a microphone (MIC) that is configured to receive external audio signals when the device 1600 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 1604 or transmitted via the communication component 1616. In some embodiments, the audio component 1610 further includes a speaker for outputting audio signals.

[0147] The I / O interface 1612 provides an interface between the processing component 1602 and a peripheral interface module, which can be a keyboard, a click wheel, buttons, etc. These buttons can include, but are not limited to: a home button, a volume button, a power-on button, and a lock button.

[0148] The sensor assembly 1614 includes one or more sensors for providing a status assessment of various aspects of the device 1600. For example, the sensor assembly 1614 can scan the on / off state of the device 1600, the relative positioning of components, such as the display and keypad of the device 1600 as described above. The sensor assembly 1614 can also scan for changes in the position of the device 1600 or a component of the device 1600, the presence or absence of user contact with the device 1600, the orientation or acceleration / deceleration of the device 1600, and temperature changes of the device 1600. The sensor assembly 1614 can include proximity sensors configured to scan for the presence of nearby objects without any physical contact. The sensor assembly 1614 can also include light sensors, such as CMOS or CCD image sensors, for use in imaging applications. In some embodiments, the sensor assembly 1614 can also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0149] The communication component 1616 is configured to facilitate communication between the device 1600 and other devices in a wired or wireless manner. The device 1600 can access a wireless network based on communication standards, such as WiFi, 2G, or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1616 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0150] In an exemplary embodiment, the device 1600 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described method.

[0151] In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided. For example, a memory 1604 including instructions, when the instructions in the storage medium are executed by a processor 1620 of the device 1600, enable the device 1600 to perform a detection method, the method including: obtaining an image that includes a bound circuit board, inputting the image into a detection network, causing the detection network to output first indication information for indicating the conductive performance of the circuit board according to the feature information of the circuit board in the image, and determining the conductive performance of the circuit board according to the first indication information.

[0152] The non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0153] Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common general knowledge or conventional technical means in the technical field not disclosed by the present disclosure. The specification and examples are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the following claims.

[0154] It should be understood that the present disclosure is not limited to the exact structures already described and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for detecting the electrical conductivity of a circuit board, characterized in that, The method includes: Obtain an image, where the image includes a bound circuit board; Input the image into a detection network, so that the detection network outputs first indication information for indicating the electrical conductivity of the circuit board according to the feature information of the circuit board in the image; the feature information of the circuit board includes: the morphology of conductive particles located on the surface of the circuit board and / or the binding position of the circuit board; Determine the electrical conductivity of the circuit board according to the first indication information.

2. The method according to claim 1, characterized in that, When the feature information of the circuit board includes the morphology of conductive particles located on the surface of the circuit board, the detection network outputs first indication information for indicating the electrical conductivity of the circuit board according to the feature information of the circuit board in the image, including: The detection network determines, for each preset electrical conductivity among a plurality of preset electrical conductivities, a first probability that the morphology of the conductive particles corresponds to the preset electrical conductivity; The detection network determines the target preset electrical conductivity corresponding to the maximum first probability, and the target preset electrical conductivity is used as the electrical conductivity of the circuit board; The detection network outputs first indication information for indicating the target preset electrical conductivity.

3. The method according to claim 2, wherein When the feature information of the circuit board further includes the binding position of the circuit board, the detection network outputs first indication information for indicating the electrical conductivity of the circuit board according to the feature information of the circuit board in the image, further including: The detection network determines a second probability that the binding position of the circuit board is unqualified; The detection network determines whether each of the first probabilities and the second probability satisfies a preset condition, and in response to each of the first probabilities and the second probability satisfying the preset condition, outputs first indication information for indicating the target preset electrical conductivity.

4. The method according to claim 3, characterized in that, The detection network determines whether each of the first probabilities and the second probability satisfies a preset condition, including: The detection network determines whether the second probability is less than each of the first probabilities.

5. The method according to claim 3 or 4, characterized in that, The detection network is obtained by the following method: Obtain a sample image, where the sample image includes a bound sample circuit board, and the sample image has annotation information indicating the electrical conductivity of the sample circuit board; Input the sample image into a detection network to be trained, so that the detection network to be trained outputs second indication information for indicating the electrical conductivity of the sample circuit board according to the feature information of the sample circuit board in the sample image, the feature information of the sample circuit board includes: the morphology of conductive particles located on the surface of the sample circuit board and / or the binding position of the sample circuit board; Adjust the parameters of the detection network to be trained according to the difference between the annotation information and the second indication information to obtain the detection network.

6. The method according to claim 5, wherein When the feature information of the sample circuit board includes the morphology of conductive particles located on the surface of the sample circuit board, the detection network to be trained outputs second indication information for indicating the electrical conductivity of the sample circuit board according to the feature information of the sample circuit board in the sample image, including: For each of a plurality of preset conductivity properties, the detection network to be trained determines a third probability that the morphology of the conductive particles located on the surface of the sample circuit board corresponds to the preset conductivity property; The detection network to be trained determines the preset conductivity property corresponding to the maximum third probability, and the preset conductivity property corresponding to the maximum third probability is used as the conductivity property of the sample circuit board; The detection network to be trained outputs the second indication information, and the second indication information indicates the preset conductivity property corresponding to the maximum third probability.

7. The method according to claim 6, wherein When the feature information of the sample circuit board further includes the bonding position of the sample circuit board, the detection network to be trained outputs, according to the feature information of the sample circuit board in the sample image, second indication information for indicating the conductivity property of the sample circuit board, and further includes: The detection network to be trained determines a fourth probability that the bonding position of the sample circuit board is unqualified; The detection network to be trained determines whether each of the third probabilities and the fourth probability satisfies the preset condition, and in response to each of the third probabilities and the fourth probability satisfying the preset condition, outputs the second indication information.

8. A detection device for the electrical conductivity of a circuit board, characterized in that, The apparatus includes: An image acquisition module configured to acquire an image, where the image includes a bonded circuit board; An image input module configured to input the image into a detection network, so that the detection network outputs, according to the feature information of the circuit board in the image, first indication information for indicating the conductivity property of the circuit board; the feature information of the circuit board includes: the morphology of the conductive particles located on the surface of the circuit board and / or the bonding position of the circuit board; A conductivity property determination module configured to determine the conductivity property of the circuit board according to the first indication information.

9. The device according to claim 8, wherein When the feature information of the circuit board includes the morphology of the conductive particles located on the surface of the circuit board, the detection network includes: A first probability determination sub-network configured to determine, for each of a plurality of preset conductivity properties, a first probability that the morphology of the conductive particles corresponds to the preset conductivity property; A conductivity property determination sub-network configured to determine a target preset conductivity property corresponding to the maximum first probability, and the target preset conductivity property is used as the conductivity property of the circuit board; A first indication information output sub-network configured to output first indication information for indicating the target preset conductivity property.

10. The device according to claim 9, characterized in that, When the feature information of the circuit board further includes the bonding position of the circuit board, the detection network further includes: A second probability determination sub-network configured to determine a second probability that the bonding position of the circuit board is unqualified; A first condition judgment sub-network configured to determine whether each of the first probabilities and the second probability satisfies a preset condition, and in response to each of the first probabilities and the second probability satisfying the preset condition, outputs first indication information for indicating the target preset conductivity property.

11. The device according to claim 10, wherein The condition judgment sub-network is configured to determine whether the second probability is less than each of the first probabilities.

12. The device according to claim 10 or 11, characterized in that, The apparatus further includes: A sample image acquisition module, configured to acquire a sample image, where the sample image includes a bound sample circuit board, and the sample image has annotation information indicating the conductive performance of the sample circuit board; A sample graphic input module, configured to input the sample image into a detection network to be trained, so that the detection network to be trained outputs second indication information for indicating the conductive performance of the sample circuit board according to the feature information of the sample circuit board in the sample image, where the feature information of the sample circuit board includes: the morphology of conductive particles on the surface of the sample circuit board and / or the binding position of the sample circuit board; A parameter adjustment module, configured to adjust the parameters of the detection network to be trained according to the difference between the annotation information and the second indication information, so as to obtain the detection network.

13. The device according to claim 12, characterized in that, When the feature information of the sample circuit board includes the morphology of conductive particles on the surface of the sample circuit board, the detection network to be trained includes: A third probability determination sub-network, configured to determine, for each preset conductive performance among a plurality of preset conductive performances, the third probability that the morphology of conductive particles on the surface of the sample circuit board corresponds to the preset conductive performance; A second probability determination sub-network, configured to determine the preset conductive performance corresponding to the maximum third probability, and use the preset conductive performance corresponding to the maximum third probability as the conductive performance of the sample circuit board; A second indication information output sub-network, configured to output the second indication information, where the second indication information indicates the preset conductive performance corresponding to the maximum third probability.

14. The device according to claim 13, characterized in that, When the feature information of the sample circuit board further includes the binding position of the sample circuit board, the detection network to be trained further includes: A fourth probability determination sub-network, configured to determine the fourth probability that the binding position of the sample circuit board is unqualified; A second condition judgment sub-network, configured to determine whether each of the third probabilities and the fourth probabilities satisfies the preset condition, and in response to each of the third probabilities and the fourth probabilities satisfying the preset condition, output the second indication information.

15. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

16. A detection device for the electrical conductivity of a circuit board, characterized in that, Including: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to: Acquire an image, where the image includes a bound circuit board; Input the image into a detection network, so that the detection network outputs first indication information for indicating the conductive performance of the circuit board according to the feature information of the circuit board in the image; the feature information of the circuit board includes: the morphology of conductive particles on the surface of the circuit board and / or the binding position of the circuit board; Determine the conductive performance of the circuit board according to the first indication information.

Images