CN115707349A

CN115707349A - Method for transferring electronic component, storage medium, and apparatus for transferring electronic component

Info

Publication number: CN115707349A
Application number: CN202180001456.8A
Authority: CN
Inventors: 李召辉; 初宇天; 董恩凯; 翟明; 齐嘉城; 孙亮; 曹鹏军
Original assignee: BOE Technology Group Co Ltd; BOE Jingxin Technology Co Ltd
Current assignee: BOE Technology Group Co Ltd; BOE Jingxin Technology Co Ltd
Priority date: 2021-06-04
Filing date: 2021-06-04
Publication date: 2023-02-17
Also published as: WO2022252232A1

Abstract

A method for transferring an electronic component, a computer-readable storage medium, and an apparatus for transferring an electronic component are provided, the method including: acquiring target characteristic data of a target slide (S610); acquiring initial coordinates of each electronic component according to the target characteristic data (S620); dividing the target slide into a plurality of regions and numbering the plurality of regions according to a first preset rule, wherein each region in the plurality of regions at least comprises one electronic element (S630); obtaining a target coordinate offset of the electronic component in each of the plurality of regions by using a pre-training model according to the target feature data and the number sequence of each region (S640); determining target coordinates of the electronic component in each of the plurality of regions according to the initial coordinates and the target coordinate offset amount (S650); the electronic components in the corresponding areas are sequentially moved to the target coordinates in the order of numbering and then the transfer operation is performed (S660). According to the technical scheme, the transfer precision of the electronic element is improved, and the transfer efficiency is improved.

Description

Method for transferring electronic component, storage medium, and apparatus for transferring electronic component

Technical Field

The present disclosure relates to the field of semiconductor manufacturing technologies, and in particular, to a method for transferring an electronic component, a computer-readable storage medium, and an apparatus for transferring an electronic component.

Background

With the development of the technology, sub-millimeter Light Emitting diodes (Mini LEDs) and Micro Light Emitting diodes (Micro LEDs) are gradually becoming a research focus in the field of display technology. For example, the Mini LED can be used in a backlight module of a liquid crystal display device as a light emitting element of the backlight module. Therefore, by utilizing the advantages of the Mini LED, the backlight module can realize the advantages of thin thickness, regional dimming, quick response, simple structure, long service life and the like. And the Micro LED has smaller size and can be directly used as a pixel point to realize color display. However, since a huge number of minileds or micro leds need to be transferred onto the corresponding receiving substrates by a mass transfer technique, it is difficult to achieve both precision and production efficiency in the prior art.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure is directed to a method for transferring an electronic component, a computer readable medium, and an apparatus for transferring an electronic component, so as to improve the accuracy of transferring an electronic component and improve the transferring efficiency at least to some extent.

According to a first aspect of the present disclosure, there is provided an electronic component transfer method for transferring a plurality of electronic components arranged in an array on a target chip, the transfer method including:

acquiring target characteristic data of the target slide;

acquiring initial coordinates of each electronic element according to the target characteristic data;

dividing the target slide into a plurality of areas and numbering the areas according to a first preset rule, wherein each area in the areas at least comprises one electronic element;

obtaining target coordinate offset of the electronic element in each of the multiple regions by using a pre-training model according to the target feature data and the number sequence of each region;

determining target coordinates of the electronic component in each of the plurality of regions according to the initial coordinates and the target coordinate offset;

and sequentially moving the electronic elements in the corresponding areas to the target coordinates according to the numbering sequence, and then executing transfer operation.

According to a second aspect of the present disclosure, there is provided a computer readable medium having stored thereon a computer program which, when executed by a processor, implements the method described above.

According to a third aspect of the present disclosure, there is provided an electronic component transfer apparatus for transferring a plurality of arrayed electronic components disposed on a target chip, the apparatus comprising:

the displacement assembly is used for controlling the target slide to move;

a controller for executing the above-mentioned electronic component transferring method.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty. In the drawings:

FIG. 1 is a schematic diagram illustrating a swing arm type electronic component transfer in the related art;

FIG. 2 is a schematic view showing a needle-punched electronic component transfer in the related art;

FIG. 3 schematically illustrates a diagram of a partitioned zone transfer;

FIG. 4 is a schematic diagram showing the difference of components in the X direction at the time of the partition transfer in FIG. 3;

FIG. 5A is a schematic diagram showing the difference in components in the Y direction after the partition transfer of FIG. 3;

FIG. 5B schematically shows a diagram of the component difference in the Y-direction after the transfer of the partitions according to FIG. 3;

fig. 6 schematically illustrates a flow chart of a transfer method of an electronic component in an exemplary embodiment of the present disclosure;

FIG. 7 schematically illustrates an intent to establish a rectangular coordinate system in an exemplary embodiment of the disclosure;

FIG. 8 schematically illustrates a schematic diagram for determining initial coordinates of electronic components in an exemplary embodiment of the disclosure;

FIG. 9 is a schematic diagram schematically illustrating offset characterization data after completing a P-column electronic component transfer in an exemplary embodiment of the disclosure;

FIG. 10 is a schematic diagram that schematically illustrates offset characterization data after completing a Q-column electronic component transfer in exemplary embodiments of the present disclosure;

fig. 11 schematically illustrates a diagram for determining an offset amount according to a needle mark in an exemplary embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

One way to transfer electronic components is the swing arm Pick and Place (Pick & Place) technique, as shown in fig. 1, an electronic component 103 is picked up and adsorbed from a carrier board by a robot arm 101 (step (1)), the robot arm moves to above a position where the electronic component is to be received by a receiving substrate 102 (step (2)), and the adsorbed electronic component 102 is placed on the position where the electronic component is to be received by the receiving substrate 102 by the robot arm (step (3)), thereby completing one electronic component transfer. The technology has low difficulty and strong universality, is widely applied to the SMT industry, but the inventor finds that the transfer precision of a Pick & Place technology is limited to reach a bottleneck within +/-30 mu m, the speed can not exceed 2.5-3 ten thousand per hour at most, and the technology is difficult to use in the transfer of electronic components with micron-scale dimensions

In other electronic component transferring methods, for example, transferring by mechanical force, as shown in fig. 2, the electronic component 103' to be transferred on the slide 202 is first moved to a position right above the target position on the receiving substrate 102, and then the electronic component 103 is transferred from the slide 202 to the receiving substrate 102 by using the needle 201, wherein the middle dotted circle in fig. 2 represents the transferred electronic component 1023. The transfer precision of the mechanical force transfer mode by using the needle can reach +/-15 um, the transfer speed can reach 18 ten thousand per hour, and compared with the Pick & Place (swing arm) technology, the transfer device has the advantages of great improvement, high production efficiency and high productivity.

It is understood that the shape of the orthographic projection of the electronic element 103 on the plane of the receiving substrate 102 may be a rectangle as shown in fig. 2, or a circle as shown in fig. 3, and is not limited herein.

For small-sized electronic components, for example electronic components having dimensions below 350 μm, for example between 150 and 350 μm, between 100 and 300 μm, or even less than 100 μm, typically tens of thousands of electronic components of the same specification and size are arranged on a growth substrate (for example a material such as silicon, silicon carbide, sapphire, etc.), or on a carrier sheet (a stretchable material film, such as a UV film, etc.); and then the required quantity of electronic components are transferred from the growth substrate or the slide to the receiving substrate through a transfer process. The inventors have found that the greater the number of electronic components arranged on a growth substrate or slide, the greater the probability that the substrate material or slide will run an undesirable risk after the transfer process has been performed a number of times. Such as breakage or deformation of the growth substrate or carrier, which leads to a reduction in transfer yield, loss of electronic components, etc., inevitably leads to an increase in production cost.

The inventors have also found that during the transfer of a plurality of electronic components 103 on the same growth substrate or slide, a relatively regular variation in the accuracy of the transfer occurs. As shown in fig. 3, the whole slide 202 may include 3N columns of electronic components 103, a first photograph of the slide is taken to obtain first position data of all the electronic components before transferring any electronic component, and then after transferring each electronic component 103 located in the first N columns, a second photograph of the slide is taken to obtain second position data of the electronic component (i.e., 2N columns of electronic components excluding the N columns of electronic components that have been transferred), and then transferring the electronic component 103 located in the middle N columns; next, a third photograph of the slide is taken to obtain third position data of the remaining electronic components (i.e., including the actual positions of the last N columns of electronic components and the electronic components that have been transferred), and the remaining N columns of electronic components are transferred finally 103. It will be appreciated that each shot is taken at the same position and angle and shooting parameters and, further, that the number of electronic components 103 actually included on the slide is not illustrated in fig. 3, and that the number of electronic components 103 actually included on the slide may be much greater than that shown in fig. 3.

In this embodiment, serial numbers are set for N columns of electronic components transferred last time on the slide in fig. 3, that is, serial numbers are set for N columns of electronic components retained during the third photographing, where the serial number of the electronic component located at the leftmost lower corner of the N columns of electronic components in the image obtained in the third photographing in fig. 3 is set to be 1, and serial numbers are set for the electronic components located in the same column as the electronic component with the serial number of 1 along the column direction Y, and the above manner is repeated one by one along the row direction X, so as to sequentially obtain the serial number of each electronic component, that is, the serial number of the electronic component 103 at the rightmost upper corner is the largest.

As shown in fig. 4, a curve 401 is a curve drawn by a component difference in the X direction of the third position data and the first position data of the N columns of electronic components to be transferred last in fig. 3, and a curve 402 is a curve drawn by a component difference in the X direction of the second position data and the first position data of the N columns of electronic components to be transferred last in fig. 3, so it can be seen that a component difference in the X direction of the second position data and the third position data is significant. Where the X direction is the direction in which the rows in figure 3 are located,

fig. 5A schematically shows a graph plotted according to a component difference in the Y direction of the second position data and the first position data of the last N columns of electronic components to be transferred in fig. 3, and fig. 5B schematically shows a graph plotted according to a component difference in the Y direction of the third position data and the first position data of the last N columns of electronic components to be transferred in fig. 3, and as shown in fig. 5A and 5B, a component in the Y direction of the position of the last N columns of electronic components to be transferred after the third photographing has a displacement distance from both the initial position (i.e., the first position data) and the intermediate position (i.e., the second position data). Therefore, if the electronic component 103 is transferred without considering the offset amount, there is a problem that the transfer accuracy of the electronic component is lowered.

It should be noted that fig. 4, fig. 5A, and fig. 5B do not show the position difference of all the electronic components in the last N columns, that is, fig. 4, fig. 5A, and fig. 5B are exemplary illustrations, and the number of the electronic components in the last N columns to be transferred is not specifically limited in this exemplary embodiment.

In view of the above problems, the solution that can be adopted includes loading and unloading the slide glass for a plurality of times, and/or taking a picture for a plurality of times, correcting the position offset of the electronic component 103 to be transferred by using the taken picture data, and ensuring that the electronic component is transferred after moving to the correct position, but this solution can lead to the great reduction of the production efficiency. It should be noted that the loading and unloading includes loading and unloading, where the loading includes mounting a carrier board including electronic components to be transferred to a corresponding area of the transfer apparatus, such as a carrier; and the blanking is to take the carrier plate down from the corresponding area in the transfer equipment.

It can be understood that the receiving substrate needs to be provided with pads which are in one-to-one correspondence and connected with pins of the electronic element to be transferred, and before the electronic element is transferred, the receiving substrate and a carrier including the electronic element to be transferred need to be aligned, and it is ensured that the geometric center of the electronic element to be transferred and the geometric center of the area of the receiving substrate where the corresponding pad is located are located on the same straight line in the direction perpendicular to the plane of the receiving substrate, and the two are spaced by a certain distance. Next, the electronic components are detached from the carrier and released onto the corresponding pads of the receiving substrate by a transfer process. Generally, in order to realize firm electrical connection between the electronic component and the pad, a reflow soldering process is adopted, that is, the solder paste is heated and cured to realize firm electrical connection between the electronic component and the pad; that is, it is necessary to provide solder paste on either the leads of the electronic component or the pads on the receiving substrate before transferring the electronic component so that a reflow process is performed after the transfer process to form a firm electrical connection between the two.

The present disclosure provides an electronic component transfer method for transferring a plurality of electronic components arranged in an array on a target chip.

Referring to fig. 6, the present disclosure proposes a method for transferring an electronic component, which may include the steps of:

step S610, acquiring target characteristic data of the target slide;

step S620, acquiring initial coordinates of each electronic element according to the target characteristic data;

step S630, dividing the target slide into a plurality of areas and numbering the areas according to a first preset rule, wherein each area in the areas at least comprises an electronic element;

step 640, obtaining a target coordinate offset of the electronic component in each of the plurality of regions by using a pre-training model according to the target feature data and the number sequence of each region;

step S650, determining a target coordinate of the electronic component in each of the plurality of regions according to the initial coordinate and the target coordinate offset;

and step 660, sequentially moving the electronic components in the corresponding areas to the target coordinates according to the numbering sequence, and then executing transfer operation.

Compared with the prior art, the method has the advantages that the slide glass 202 is divided into the regions, the coordinate offset of each region is obtained by the aid of the pre-training model, the target coordinate is obtained by calculation according to the pre-obtained initial coordinate and the coordinate offset, the problem of insufficient transfer precision caused by coordinate offset due to tension of the slide glass 202 is solved, multiple times of photographing is not needed, production time is saved, and production efficiency is improved.

The following describes in detail various steps described above.

In step S610, target characteristic data of the target slide is acquired.

In the present exemplary embodiment, the electronic element may be a Micro LED chip, a Mini LED chip, or any Micro (smaller than 500 um) sized electronic element, such as an electronic element with a size of 300-500 μm,100-300 μm, or even smaller than 100 μm, and is not limited in the present exemplary embodiment.

In an exemplary embodiment of the disclosure, the steps and the description are described by taking an electronic element as a Micro LED chip as an example, when the Micro LED chip and the transfer operation are performed, a product on which the Micro LED chip needs to be mounted, that is, a receiving substrate and a target slide having an array of the Micro LED chips are obtained first.

In this exemplary embodiment, the target feature data may include image data of a target slide and a type of a target slide, and after the target slide with the Micro LED chip array is obtained, an industrial camera may be used to take a picture to obtain the feature data of the target slide, or other acquisition devices may be used to obtain the feature data of the target slide, which is not specifically limited in this exemplary embodiment.

The image can include the arrangement mode of the Micro LED chips and the number of the Micro LED chips, wherein the type of the slide can be specifically the type of the slide material, that is, the target characteristic data includes the arrangement mode of the Micro LED chips, the number of the Micro LED chips and the type of the slide material. In another exemplary embodiment, the form of the feature data may be customized according to the requirement of the user, and is not specifically limited in this exemplary embodiment.

In step S620, initial coordinates of each of the electronic components are obtained according to the target feature data.

In an example embodiment of the present disclosure, a rectangular coordinate system may be first established according to a second preset rule, and initial coordinates of each electronic component 103 in the rectangular coordinate system may be obtained.

Specifically, referring to fig. 7, where the dotted line portion in the figure is a distribution region 701 of electronic components when all the electronic components are at the initial coordinates, that is, a range of the image data, where the array of the electronic components 103 can be determined as M columns and 2N rows, the second predetermined rule may be that the origin of the rectangular coordinate system is set at a midpoint position of the leftmost edge of the image data, the direction of the columns is the Y axis, and the direction of the rows is the X axis. The vertex angle of any one boundary of the array of electronic components 103 may be the origin, the direction of the columns may be the Y axis, and the direction of the rows may be the X axis.

In another exemplary embodiment, if the array of electronic components 103 is determined as row M2n +1, then row N +1 may be disposed above the X-axis, row N may be disposed below the X-axis, the origin may be disposed at the leftmost edge of the image data, i.e. the leftmost edge of the distribution region 701, and the direction of the row is the Y-axis and the direction of the column is the X-axis.

In the present exemplary embodiment, after the rectangular coordinate system is established, the initial coordinates of each electronic component are determined, wherein, referring to fig. 8, the dotted line part in the figure is the distribution region 701 of the electronic components before the transfer operation is not performed, each electronic component is located at the initial coordinates 801, and the initial coordinates 801 are the coordinates of the geometric center point of the electronic component 103 in the rectangular coordinate system.

In step S630, the target slide is divided into a plurality of regions and the plurality of regions are numbered according to a first preset rule, wherein each of the plurality of regions includes at least one electronic component.

In the present exemplary embodiment, each electronic component 103 in the target slide may be divided into regions according to a first preset rule, and the regions may be numbered, and each region may include at least one electronic component. The numbering can be carried out by Arabic numerals, so that the corresponding areas can be traversed sequentially when the process is executed by a software program in the following process; each area may also be numbered in other manners according to user requirements, and is not specifically limited in this exemplary embodiment.

In an example embodiment of the present disclosure, the first preset rule may be that each row in the array of electronic elements 103 is used as a region, and the regions are sequentially numbered along a direction of the column, specifically, the regions may be numbered from top to bottom along the direction of the column, or from bottom to top along the direction of the column, or from the middle to two sides along the direction of the column, or may be customized according to a user's requirement, which is not specifically limited in this example embodiment.

In another exemplary embodiment of the disclosure, each column of the electronic component 103 array may be used as an area, and the areas may be numbered sequentially along a direction of the row, specifically, the areas may be numbered sequentially along the direction of the row from left to right, or numbered sequentially along the direction of the row from right to left, or numbered sequentially along the direction of the row from middle to two sides, or may be customized according to a user requirement, which is not specifically limited in this exemplary embodiment.

In yet another exemplary embodiment of the present disclosure, each electronic component may be used as one area, and the specific numbering sequence may be numbering line by line, where when each line is numbered, the line may be numbered from the leftmost electronic component 103 to the rightmost electronic component 103, and the line may be numbered from the leftmost electronic component 103 to the rightmost electronic component 103.

When a plurality of electronic components are provided in the same area, since the coordinate offset of one electronic component 103 with respect to another electronic component 103 located in the same area is less affected, the transfer order of each electronic component 103 in the same area may be customized according to the user's needs without being limited.

In step S640, a target coordinate offset of the electronic component 103 in each of the plurality of regions is obtained by using a pre-training model according to the target feature data and the number sequence of each of the regions.

In an exemplary embodiment of the present disclosure, after the regions and the number sequences are determined, a target coordinate offset of each electronic component 103 is obtained by using a pre-trained model according to the feature data and the number sequences.

Specifically, a pre-training model with the feature data matched with each other may be obtained first, and then the feature data and the number sequence may be input to the pre-training model to obtain the target coordinate offset amount of each electronic component 103 of each region.

In the present exemplary embodiment, when the feature data may include the arrangement of the electronic components 103 and the number of the electronic components 103, and a pre-trained model matching the feature data is obtained, an initial model may be first obtained, which is input as the feature data and the number order of each region, and output as the coordinate offset.

In the present exemplary embodiment, after the initial model is obtained, reference feature data of a reference slide in which the arrangement of the plurality of electronic components 103 and the number of the electronic components 103 are the same may be extracted from the database, where the reference feature data may include the arrangement order of the plurality of electronic components 103 and the number of the electronic components 103 in the reference slide, and may further include a slide type of the reference slide.

In this exemplary embodiment, after the plurality of reference feature data are acquired, the reference slide corresponding to the reference feature data of the upper user may be divided into a plurality of reference regions according to a first preset rule, and each reference region is numbered according to the first preset rule, and then, the reference coordinate offset of each region of the electronic component 103 of each reference slide in different numbering sequences is calculated. The specific content of the first preset rule has already been described in detail when the target slide is divided into regions and numbered, and therefore, the detailed description thereof is omitted here.

Specifically, when the reference coordinate offset amount of the electronic component 103 in each of the plurality of regions of the electronic component 103 of each reference slide in the different numbering order is calculated, the initial coordinates 801 of the electronic component 103 of each region may be first acquired, then the transfer processing may be performed on the electronic components 103 of the respective regions in the numbering order, the reference coordinates of the electronic components 103 of the non-transferred reference region may be acquired after the transfer operation is performed on the reference region numbered n and before the transfer operation is not performed on the reference region numbered (n + 1), and the reference coordinate offset amount of each region may be calculated based on the reference coordinates and the initial coordinates 801. Wherein n is a positive integer, such as 1, 2, 3, etc.

It should be noted that the offset feature data of the camera reference slide may be reused after the transfer of the electronic components 103 to one reference region in the above reference slide is completed each time. The offset characteristic data may be reference image data of a reference slide acquired by photographing the reference slide after the transfer of the electronic component 103 in the partial reference area is completed. The reference coordinate offset of the electronic component in each of the plurality of regions may then be acquired from the offset characteristic data and the reference characteristic data.

In the present exemplary embodiment, the initial coordinates 801 of the electronic component 103 in the reference region may be first obtained, specifically, where the reference feature data includes image data, a rectangular coordinate system may be established according to the second preset rule based on the image data, and the initial coordinates 801 of the electronic component may be obtained.

It should be noted that, the specific content of the second preset rule has already been described in detail above, and therefore, the detailed description is omitted here.

After establishing the rectangular coordinate system corresponding to the reference slide, the initial coordinates 801 of the electronic component 103 in the reference slide 202 may be read out in the coordinate system, and then the reference coordinates of the electronic component 103 may be obtained by putting the reference image data in the offset feature data into the rectangular coordinate system.

For example, referring to fig. 9, after completing the transfer of P columns (where M > P > 0) of electronic components 103, obtaining the offset feature data of the remaining (M-P) columns of electronic components, where the offset feature data may be image data, and placing the image data into the coordinate system corresponding to the reference slide, it can be found that the initial coordinates 801 of the (M-P) columns of electronic components 103 to be transferred have an offset from the center point of the electronic component at the corresponding position in the reference slide. At this time, the center point of the electronic component at the corresponding position in the reference slide is taken as the reference coordinate, and the initial coordinate 801 of the electronic component 103 to be transferred is subtracted from the reference coordinate to obtain the reference offset.

For another example, as shown in fig. 10, after completing the transfer of the Q-column (where M > Q > P > 0) electronic components 103, acquiring the shift characteristic data, it can be found that the initial coordinates 801 of the (M-Q) -column electronic components 103 to be transferred have a shift from the center point of the electronic components 103 at the corresponding position in the reference slide, and the shift amount is larger than the shift amount after completing the transfer of only the P-column electronic components 103. At this time, the center point of the electronic component 103 at the corresponding position in the reference slide is used as a reference coordinate, and the initial coordinate 801 of the electronic component 103 to be transferred is subtracted from the reference coordinate to obtain a reference offset.

In this example embodiment, after the reference offset is obtained, the initial model may be trained by using the reference feature data and the reference coordinate offset of each region corresponding to the reference feature data to obtain a pre-trained model.

In this exemplary embodiment, the pre-training model includes an algorithm for obtaining coordinate offset when performing a transfer operation on the region using different numbering sequences.

The pre-training model is mainly a neural network model based on deep learning. For example, the pre-trained model may be based on a feed-forward neural network. The feed-forward network may be implemented as an acyclic graph, where nodes are arranged in layers. Typically, the feed-forward network topology comprises an input layer and an output layer, which are separated by at least one hidden layer. The hidden layer transforms input received by the input layer into a representation that is useful for generating output in the output layer. The network nodes are all connected to nodes in adjacent layers via edges, but no edges exist between nodes in each layer. Data received at nodes of the input layers of the feed-forward network are propagated (i.e., "fed-forward") to nodes of the output layers via activation functions that compute the state of the nodes of each successive layer in the network based on coefficients ("weights") respectively associated with each of the edges connecting these layers. The output of the pre-trained model may take various forms, which are not limited by this disclosure. The pre-training model may also include other neural network models, such as a Convolutional Neural Network (CNN) model, a Recurrent Neural Network (RNN) model, a generative confrontation network (GAN) model, but is not limited thereto, and other neural network models known to those skilled in the art may also be employed.

The pre-trained model typically needs to be obtained by training. The training of the initial model by the training algorithm may include the following steps: selecting a network topology; using a set of training data representing the problem modeled by the network; and adjusting the weights until the network model appears to have a minimum error for all instances of the training data set. For example, during a supervised learning training process for a neural network, the output produced by the network in response to an input representing an instance in a training data set is compared to the "correct" labeled output for that instance; calculating an error signal representing a difference between the output and the marked output; and adjusting weights associated with the connections to minimize the error as the error signal is propagated back through the layers of the network. When the error of each output generated from an instance of the training data set is minimized, the initial model is considered "trained" and defined as a pre-trained model, and can be used to perform the calculation of the target coordinate offset.

In this exemplary embodiment, after the pre-training model is obtained, the target feature data and the number sequence may be input to the pre-training model, so as to obtain the target coordinate offset of each electronic component 103 in the target feature data.

In the present exemplary embodiment, all the electronic components 103 to be transferred are disposed on the carrier sheet 202 by the adhesive, and when the transfer of the electronic components 103 is performed, the electronic components 103 are closer to the receiving substrate 102 with respect to the carrier sheet 202, and further, the pins of the electronic components 103 are closer to the receiving substrate 102 with respect to the carrier sheet 202. The electronic components to be transferred are hit at a high speed at a corresponding position on the carrier by a needle 201 using a mechanical force, so that the electronic components are separated from the carrier and transferred to the receiving substrate 102, thereby completing the transfer of the electronic components, and after the transfer, needle marks and marks of the electronic components 103 are left on the carrier sheet 202.

Referring to fig. 11, after the pre-trained model is obtained, a correction data set may also be obtained, wherein the correction data set may include a plurality of corrected image data of the slide after the electronic component 103 is transferred using a transfer method other than the presently disclosed transfer method, i.e., the transfer of the electronic component 103 is completed without regard to the offset of the electronic component, resulting in an image of the slide. The acquisition of the corrected image data may be performed by using a device capable of recognizing the mark 1203 and the pin mark 1201 of the electronic component, for example, a microscope having a photographing function, which is not limited in the present exemplary embodiment.

The corrected image data includes the mark of the original position of the electronic component 103 and the pin mark left by the impact of the pin 201. A correction offset may be calculated from the center point 1202 of the mark 1203 of the electronic component and the stitch 1201, and the correction offset may include an X-direction correction offset X and a Y-direction correction offset Y. Then, the correction data set can be used to perform correction optimization on the parameters in the pre-training model, so as to further improve the accuracy of transferring the electronic component 103.

In step S650, target coordinates of the electronic component in each of the plurality of regions are determined according to the initial coordinates and the target coordinate offset amount.

In step S660, the electronic components in the corresponding region are moved to the target coordinates in sequence in accordance with the numbering order, and then transferred.

In an exemplary embodiment of the present disclosure, after obtaining the target coordinate offset amount, the target coordinates of each electronic component 103 may be utilized by the initial coordinates 801 and the target coordinate offset amount to complete the transfer of the electronic component 103 according to the target coordinates.

Specifically, the target coordinate is obtained by adding the target coordinate offset amount to the initial coordinate 801. In the present exemplary embodiment, a lancet type transfer method is adopted, that is, the slide 202 is moved, and when the electronic component 103 on the slide is moved to the target coordinate corresponding to the electronic component 103, the needle is controlled to move downwards, so as to transfer the electronic component 103 on the slide to the receiving substrate 102.

At this time, the slide and the receiving substrate 102 may be controlled to move according to the target coordinates, and the positions corresponding to the target coordinates of the electronic components 103 may be sequentially moved to a position directly below the needle 201, so that the needle 201 may accurately impact and fix the electronic components 103 on the receiving substrate 102. The accuracy of the transfer of the electronic component 103 can be improved.

In summary, in the present disclosure, the slide 202 is firstly divided into regions, the coordinate offset of each region is respectively obtained by using the pre-training model, and the target coordinate is obtained by calculating according to the pre-obtained initial coordinate 801 and the coordinate offset, so that the problem of insufficient transfer precision caused by the coordinate offset due to the tension of the slide 202 is solved, meanwhile, multiple times of photographing is not required, the production time is saved, and the production efficiency is improved.

The present disclosure also provides an apparatus for transferring an electronic component 103, which may include a displacement assembly and a controller. Wherein the displacement assembly is used for controlling the target slide to move; the controller is connected to the displacement assembly and is used for executing the following steps: acquiring target characteristic data of a target slide including the electronic components 103 arranged in the array; acquiring initial coordinates of each electronic component 103 according to the target characteristic data; dividing a target slide into a plurality of areas and numbering the areas according to a first preset rule; obtaining a target coordinate offset of the electronic component 103 in each of the plurality of regions by using a pre-training model according to the target feature data and the number sequence of each region; determining target coordinates of the electronic component 103 in each of the plurality of regions from the initial coordinates and the target coordinate offset; and controlling the displacement assembly to sequentially move the electronic components 103 in the corresponding areas to the target coordinates according to the numbering sequence.

The steps executed by the controller have already been described in detail above, and therefore, the description thereof is omitted here.

In the present exemplary embodiment, the above-described transfer apparatus for electronic components 103 further includes a needle and a driving device. Wherein, the driving device is connected with the needle head and the controller; after controlling the displacement assembly to move the electronic component 103 to the target coordinate, the controller controls the driving device to drive the needle head to transfer the electronic component 103 onto the receiving substrate.

Specifically, after obtaining the target coordinates, the controller may control the displacement assembly to sequentially move the position corresponding to the target coordinates of each electronic component 103 to a position directly below the needle according to the target coordinates, and simultaneously drive the needle to move up and down, so that the needle can accurately impact and fix the electronic component 103 on the receiving substrate. The accuracy of component transfer can be improved.

In this example embodiment, the controller may include a processor, and the processor may be configured to perform the steps of obtaining initial coordinates 801 of each of the electronic components 103 according to the target feature data, dividing the target slide into a plurality of regions, numbering the plurality of regions according to a first preset rule, and obtaining a target coordinate offset of the electronic component 103 in each of the plurality of regions by using a pre-trained model according to the target feature data and a numbering sequence of each of the regions.

The specific contents of the steps executed by the processor are described in detail already when describing the transfer method of the electronic component 103, and therefore, the details are not described herein again.

In this exemplary embodiment, the controller may further include a collecting device, such as a camera, a microscope with a camera function, etc., which may be used to acquire the target characteristic data of the target slide, acquire the reference characteristic data of the reference slide, acquire the offset characteristic data, correct the characteristic data, etc. As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

Exemplary embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the disclosure as described in the above-mentioned "exemplary methods" section of this specification, when the program product is run on the terminal device.

It should be noted that the computer readable medium shown in the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Furthermore, program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In situations involving remote computing devices, the remote computing devices may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to external computing devices (e.g., through the internet using an internet service provider).

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is to be limited only by the terms of the appended claims.

Claims

A method for transferring electronic components, wherein the method is used for transferring a plurality of arrayed electronic components arranged on a target chip, and the method comprises the following steps:

acquiring target characteristic data of the target slide;

acquiring initial coordinates of each electronic element according to the target characteristic data;

dividing the target slide into a plurality of areas and numbering the areas according to a first preset rule, wherein each area in the areas at least comprises one electronic element;

obtaining a target coordinate offset of the electronic element in each of the plurality of regions by using a pre-training model according to the target feature data and the number sequence of each region;

determining target coordinates of the electronic components in each of the plurality of regions according to the initial coordinates and the target coordinate offset;

and sequentially moving the electronic components in the corresponding areas to the target coordinates according to the numbering sequence and then executing transfer operation.
The transfer method of claim 1, wherein obtaining a target coordinate offset for the electronic component in each of the plurality of regions using a pre-trained model based on the target feature data and the numbering order of the regions comprises:

acquiring a pre-training model matched with the target characteristic data;

and inputting the target characteristic data and the number sequence of each region into the pre-training model to obtain the target coordinate offset of the electronic component in each region of the plurality of regions.
The transfer method of claim 2, wherein said obtaining a pre-trained model that matches the target feature data comprises:

obtaining an initial model;

acquiring reference characteristic data of a reference slide, wherein the reference slide is the same as the target slide in characteristic data, and the characteristic data comprises the number and arrangement mode of electronic elements;

dividing the reference slide into a plurality of reference areas and numbering the reference areas according to a first preset rule;

calculating a reference coordinate offset for the electronic component in each of a plurality of reference regions of each reference slide;

and training the initial model by using the reference feature data and the reference coordinate offset of the electronic element in each of the plurality of reference areas corresponding to the reference feature data to obtain the pre-training model.
The transfer method of claim 3, wherein said calculating a reference coordinate offset for the electronic component in each of a plurality of reference regions of respective reference slides comprises:

acquiring initial coordinates of the electronic elements in each reference area;

sequentially executing transfer operation on the electronic components in the corresponding reference areas according to the numbering sequence;

acquiring reference coordinates of each electronic component of all reference areas which are not subjected to the transfer operation after the transfer operation is performed on the reference area with the number n and before the transfer operation is not performed on the reference area with the number (n + 1);

and calculating the reference coordinate offset of the electronic components in each area of all the untransferred areas according to the reference coordinates and the initial coordinates, wherein n is a positive integer.
The transfer method according to claim 4, wherein said acquiring reference coordinates of each of the electronic components of all the reference areas where the transfer operation is not performed comprises:

acquiring offset characteristic data of each electronic element in all reference areas of the reference slide, wherein the reference areas are not subjected to transfer operation, and acquiring reference coordinates of the electronic elements in each area of all the non-transfer areas according to the offset characteristic data and the reference characteristic data.
A transfer method according to claim 3 wherein the characteristic data further includes slide type.
The transfer method of claim 1, wherein dividing the target slide into a plurality of regions and numbering the plurality of regions according to a first preset rule comprises:

regarding the electronic elements positioned in the same column as one area, and numbering the areas in sequence along the row direction; or

The electronic components located in the same row are regarded as one region, and the regions are numbered in sequence in the column direction.
The transfer method of claim 1, wherein said obtaining initial coordinates of each of said electronic components from said target feature data comprises:

the target characteristic data comprise image data of a target slide, and a rectangular coordinate system is established for the image data according to a second preset rule;

the specific position of each electronic component in the rectangular coordinate is the corresponding initial coordinate.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the transfer method according to any one of claims 1 to 8.
An electronic component transfer apparatus for transferring a plurality of arrayed electronic components arranged on a target carrier, the apparatus comprising:

the displacement component is used for controlling the target slide to move;

a controller, coupled to the displacement assembly, for performing the method of transferring the electronic component of any one of claims 1-8.
The apparatus of claim 10, wherein the apparatus further comprises:

a needle head is arranged at the front end of the needle body,

a drive device connected to the needle and the controller;

and after controlling the displacement assembly to move the electronic element to the target coordinate, the controller controls the driving device to drive the needle head to transfer the electronic element to the receiving substrate.