Method, system, device and medium for automatic positioning of chips in wafer inspection

Abstract

The present application relates to a method, system, device and medium for automatic positioning of core particles in wafer inspection, which belongs to the field of optoelectronic semiconductor inspection technology, and includes obtaining an overall image of the wafer; obtaining at least three core particle position coordinates located in the X / Y series based on the overall image of the wafer; obtaining a core particle pre-imaging model based on the at least three core particle position coordinates located in the X / Y series, the size of the core particle and the size of the wafer; verifying and marking the core particle position based on the core particle pre-imaging model; obtaining a core particle model based on the core particle pre-imaging model, the verified core particle position image and the outline of the wafer; and embedding the core particle model into the control program to position the core particle. The present application has the following effects: improving the inspection efficiency of the wafer and the positioning accuracy of the core particles.

Description

Technical Field

[0001] The present application relates to the technical field of optoelectronic semiconductor detection, and in particular to a method, system, device and medium for automatic positioning of a die during wafer detection. Background Art

[0002] Wafer refers to the silicon wafer used in the production of silicon semiconductor integrated circuits. It is the carrier used in the production of integrated circuits. Various circuit component structures can be processed on the silicon wafer to become IC products with specific electrical functions. Chips are semi-finished products after wafer cutting. Core particles are also called small chips. They can package multiple module chips with the underlying basic chips through internal interconnection technology, similar to building Lego blocks, to form a system chip (Soc chip).

[0003] With the continuous development of science and technology, the demand for wafers continues to rise, and the requirements for wafer accuracy and yield are also getting higher and higher. After wafer manufacturing is completed, wafer inspection is a very important test. During the inspection process, the electrical capabilities and circuit functions of each chip are tested.

[0004] During wafer inspection, the most important inspection point is the inspection of each core particle on the wafer. The inspection of the core particles requires a good judgment of the position of the core particles, that is, to align a single core particle and judge its specific position on the wafer. The existing method of judging the specific position on the wafer is more based on the position of the core particles on the scanning rows and columns, which is then presented on the image. However, this scanning method is relatively slow and is not suitable for large wafers. Summary of the invention

[0005] In order to solve the current problem of low efficiency in large wafer inspection, the present application provides a method, system, device and medium for automatic positioning of core particles in wafer inspection.

[0006] In a first aspect, the present application provides a method for automatically positioning a die during wafer inspection, which adopts the following technical solution:

[0007] A method for automatically positioning a core particle during wafer inspection, comprising:

[0008] Obtain the whole wafer image;

[0009] Based on the wafer overall image, obtaining at least three core particle position coordinates located in an X / Y sequence;

[0010] Based on the at least three core particle position coordinates located in the X / Y array, the size of the core particle and the crystal

[0011] The size of the circle, the core particle pre-image model is obtained;

[0012] Verifying and marking the core particle position based on the core particle pre-imaging model;

[0013] According to the core particle pre-imaging model, the verified core particle position image and the wafer contour,

[0014] Get the core particle model;

[0015] The core particle model is embedded into the control program to locate the core particle.

[0016] By adopting the above technical scheme, at least three core particle position coordinates located in the X / Y series are obtained according to the overall image of the wafer, and a core particle pre-imaging model is obtained according to the at least three core particle position coordinates located in the X / Y series and in combination with the size of the core particle and the overall size of the wafer. This core particle pre-imaging model is a pre-estimation of the global core particle position. The core particle position is then verified and marked based on the core particle pre-imaging model to determine whether the pre-estimated core particle position is consistent with the actual core particle position. The core particle model is then obtained according to the core particle pre-imaging model, the verified core particle position image and the overall size of the wafer. This core particle model is a core particle model actually distributed on the wafer. The core particle model is embedded in the control program to perform positioning operations on the core particles, thereby realizing automatic positioning of the core particles during the wafer inspection process and improving the inspection efficiency. In particular, for the inspection of some large wafers, the overall scanning of rows and columns takes a lot of time, and the method is used to locate the core particle position, which also improves the positioning accuracy.

[0017] Preferably, the core particle pre-imaging model is obtained based on the at least three core particle position coordinates.

[0018] include:

[0019] Based on the coordinates of at least three core particles located in the X / Y sequence, the coordinates of the core particles located in the X / Y sequence are obtained.

[0020] The spacing values ​​of at least three core particles in the sequence;

[0021] A local core particle model is obtained based on the spacing value;

[0022] Based on the local core particle model, the overall core particle model is pre-imaged to obtain a core particle pre-image.

[0023] Imaging model.

[0024] By adopting the above technical scheme, the pairwise spacing values ​​of at least three core particles located in the X / Y series can be obtained according to the coordinates of at least three core particle positions located in the X / Y series, and a local core particle model is obtained according to the above spacing values. Then, the overall core particle model is pre-imaged according to the local core particle model to obtain a core particle pre-imaging model. This core particle pre-imaging model is an estimate of the global core particle position based on the wafer size.

[0025] Preferably, the checking and marking of the core grain position based on the core grain pre-imaging model comprises:

[0026] A pre-distribution estimate of the overall core particle position is obtained based on the core particle pre-imaging model;

[0027] Controlling the probe and microscope to verify the position of the pre-distributed core particles;

[0028] Determine whether the pre-distributed core particle position exists, and obtain the verified core particle position image and

[0029] Wafer profile;

[0030] If the pre-distributed core particle position exists, marking the pre-distributed core particle position;

[0031] If the pre-distributed core particle position does not exist, the pre-distributed core particle position is not processed.

[0032] Marking is performed to record the outline of the wafer.

[0033] By adopting the above technical scheme, a pre-distributed estimate of the overall core particle position is obtained according to the core particle pre-imaging model, and the pre-distributed estimated core particle position is verified using a probe and a microscope, that is, whether the pre-distributed core particle position is consistent with the actual distributed core particle position is determined. If the pre-distributed core particle position exists, then the core particle position is consistent with the actual core particle position and the core particle position is marked. If the pre-distributed core particle position does not exist, it is not marked and the outline of the wafer at this position is recorded, thereby completing the verification of the pre-estimated core particle position.

[0034] Preferably, obtaining the core grain model according to the core grain pre-imaging model, the verified core grain position image and the wafer contour includes:

[0035] According to the core particle pre-imaging model, the verified core particle position image and the wafer contour,

[0036] The final image of the wafer is obtained by combining the rows;

[0037] Combining the final image of the wafer, the wafer outline and the actual die distribution position,

[0038] To obtain the spacing characteristics and orientation characteristics between the two core particles;

[0039] The spacing feature and the orientation feature are put into a neural network for training to obtain a core particle model.

[0040] By adopting the above technical scheme, the final image of the wafer is obtained by combining the core particle pre-imaging model, the verified core particle position image and the outline of the wafer. The spacing characteristics and orientation characteristics between two adjacent core particles on the wafer are obtained by combining the final image of the wafer, the outline of the wafer and the actual core particle distribution position. The above spacing characteristics and orientation characteristics are put into a neural network and trained using a neural network algorithm to obtain a core particle model.

[0041] Preferably, embedding the core particle model into a control program to locate the core particle position includes:

[0042] The search positioning and mark point positioning are used to find the first row and the first grain of the wafer and move the probe 1 to the corresponding core grain.

[0043] By adopting the above technical solution, the control program locates the core particle position using the methods of searching and marking point positioning.

[0044] Preferably, the searching and positioning comprises:

[0045] Look to the upper left corner for the first row and the first grain;

[0046] Move probe 1 to the center of the first particle in the first row to obtain the XY offset of the first particle in the first row from the identification position;

[0047] Click Auto Position to check the positioning effect.

[0048] By adopting the above technical solution, the probe 1 is moved to the corresponding core grain by finding the first row and the first grain of the wafer to achieve automatic positioning.

[0049] Preferably, the marker point positioning includes:

[0050] Edit marker templates;

[0051] Set the rough coordinates XY of the positioning of the marking point;

[0052] Positioning the marking point at a rough position of the screen recognition area;

[0053] Finding the marked point;

[0054] Move the first particle in the first row to under probe 1 and set the XY offset of the first particle in the first row to the same mark point.

[0055] By adopting the above technical solution, the position of the first grain in the first row is calculated by finding the marking point near the specified position, so as to realize automatic positioning.

[0056] In a second aspect, the present application provides a chip automatic positioning system for wafer inspection, which adopts the following technical solution:

[0057] A chip automatic positioning system for wafer inspection, comprising:

[0058] An acquisition module, used for acquiring an overall image of the wafer;

[0059] The position coordinate judgment module is used to obtain the position coordinates of the wafer based on the overall image of the wafer.

[0060] At least three core particle position coordinates;

[0061] A pre-imaging module is used to obtain the position coordinates of at least three core particles located in the X / Y series.

[0062] The size of the core particle and the size of the wafer are used to obtain a core particle pre-imaging model;

[0063] A verification module, used for verifying and marking the core grain position based on the core grain pre-imaging model;

[0064] The core particle model forming module is used to form a core particle model according to the core particle pre-imaging model and the verified core particle position.

[0065] The image and the outline of the wafer are used to obtain the core particle model;

[0066] The application module is used to embed the core particle model into the control program to locate the core particle position.

[0067] By adopting the above technical scheme, the position coordinate judgment module obtains at least three core particle position coordinates in the X / Y series according to the overall wafer image obtained by the acquisition module, the pre-imaging module obtains the core particle pre-imaging model according to the at least three core particle position coordinates located in the above X / Y series, the size of the core particle and the overall size of the wafer, the verification module verifies and marks the estimated global core particle position according to the core particle pre-imaging model, the core particle model formation module processes the overall core particle position according to the above core particle pre-imaging model, the verified core particle position image and the outline of the wafer to obtain the core particle model, and the above core particle model is embedded in the control program to realize automatic positioning of the core particle position.

[0068] In a third aspect, the present application provides a device, which adopts the following technical solution:

[0069] A device includes a memory, a processor, and a

[0070] A computer program running on a processor, wherein the processor implements the above-mentioned mineral identification and classification method when executing the computer program.

[0071] By adopting the above technical solution, the above-mentioned chip automatic positioning method for wafer detection is generated into computer instructions, and stored in the memory to be loaded and executed by the processor, so that a terminal device is manufactured according to the memory and the processor for easy use.

[0072] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0073] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the automatic positioning method of the core particles in the wafer detection is realized.

[0074] By adopting the above technical solution, the above-mentioned chip automatic positioning method for wafer detection is used to generate computer instructions, and the computer instructions are stored in a computer-readable storage medium so as to be loaded and executed by a processor. The computer-readable storage medium facilitates the reading and storage of computer instructions.

[0075] In summary, the present application includes at least one of the following beneficial technical effects:

[0076] 1. By obtaining the coordinates of at least three core particle positions in the X / Y sequence, and combining the size of the core particles and the size of the entire wafer, a preliminary estimate of the overall core particle position is made, namely, the core particle pre-imaging model. The preliminary estimated core particle position is then verified and the accurately estimated core particles are marked. The outline of the wafer at the inaccurate position is recorded to obtain the core particle position distribution image under actual conditions, namely, the core particle model. The core particle model is placed in the control program to realize automatic positioning of the core particle position, and the overall estimation is made using the local part to improve the detection efficiency. The estimated position is then verified and marked, which also improves the positioning accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a schematic diagram of the application environment of the method for automatic positioning of core particles in wafer inspection according to an embodiment of the present application.

[0078] Figure 2 This is a first flow chart of the method for automatic positioning of core particles in wafer inspection according to an embodiment of the present application.

[0079] Figure 3 This is the second flow chart of the method for automatic positioning of core particles in wafer inspection according to an embodiment of the present application.

[0080] Figure 4 This is the third flow chart of the method for automatic positioning of core particles in wafer inspection according to an embodiment of the present application.

[0081] Figure 5 This is the fourth flow chart of the method for automatic positioning of core particles in wafer inspection according to an embodiment of the present application.

[0082] Figure 6 This is the fifth flow chart of the method for automatic positioning of core particles in wafer inspection according to an embodiment of the present application.

[0083] Figure 7 This is the sixth flow chart of the method for automatic positioning of core particles in wafer inspection according to an embodiment of the present application.

[0084] Figure 8 It is a flowchart of the automatic chip positioning system for wafer inspection in the embodiment of the present application.

[0085] Fig. 9 It is a block diagram of the internal structure of the device according to the embodiment of the present application. DETAILED DESCRIPTION

[0086] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0087] The chip automatic positioning method for wafer inspection provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment, the automatic positioning method of the core particles of wafer detection is applied in the automatic positioning system of the core particles of wafer detection, and the automatic positioning system of the core particles of wafer detection includes a client and a server, wherein the client communicates with the server through a network. The client, also known as the user end, refers to a program corresponding to the server that provides local services to the client. Furthermore, the client is a computer-side program, an APP program for a smart device, or a third-party applet embedded in other APPs. The client can be installed on but not limited to various personal computers, laptops, smart phones, tablet computers, portable wearable devices and other devices. The server can be implemented with an independent server or a server cluster consisting of multiple servers.

[0088] The present application embodiment discloses a method for automatically positioning a die during wafer inspection. Figure 2 ,include:

[0089] S10. Obtain an overall image of the wafer.

[0090] S20. Based on the overall wafer image, obtain at least three core particle position coordinates located in the X / Y series.

[0091] S30. Based on at least three core particle position coordinates located in the X / Y array, the size of the core particle and the crystal

[0092] The size of the circle is used to obtain the core particle pre-imaging model.

[0093] S40. Verify and mark the core particle position based on the core particle pre-imaging model.

[0094] S50. Based on the core particle pre-imaging model, the verified core particle position image and the wafer contour,

[0095] Get the core particle model.

[0096] S60. Embed the core particle model into the control program to locate the core particle position.

[0097] The core particle pre-imaging model is an estimation of the overall core particle position, and the core particle model is a model of the core particles actually distributed on the wafer; verifying and marking the core particle position based on the core particle pre-imaging model refers to verifying and marking the estimated overall core particle position.

[0098] Specifically, the at least three core particle position coordinates located in the X / Y sequence refer to first determining the position of a core particle, and then there is one core particle adjacent to the core particle and located in the X / Y sequence.

[0099] Its function is to obtain at least three core particles located in the X\Y sequence according to the overall image of the wafer

[0100] Position coordinates, the present application adopts 3-5 core particle positions located in the front column of the X\Y series, and obtains a core particle pre-imaging model based on the above at least three core particle position coordinates and the size of the core particle and the overall size of the wafer. This core particle pre-imaging model is a pre-estimation of the global core particle position, and then the core particle position is verified and marked based on the core particle pre-imaging model to determine whether the pre-estimated core particle position is consistent with the actual core particle position, and then the core particle model is obtained based on the above core particle pre-imaging model, the verified core particle position image and the overall size of the wafer. This core particle model is a core particle model actually distributed on the wafer, and the core particle model is embedded in the control program to perform positioning operations on the core particles, thereby realizing automatic positioning of the core particles during the wafer inspection process and improving work efficiency. Especially for some large wafers, the method of scanning the core particle position on the overall rows and columns is no longer applicable. In addition, the method is used to automatically position the core particles with higher accuracy.

[0101] Reference Figure 3 , based on at least three core particle position coordinates located in the X / Y sequence, a core particle pre-imaging model is obtained, including:

[0102] S301. Based on the coordinates of at least three core particles located in the X / Y sequence, obtain the coordinates of the core particles located in the X / Y sequence.

[0103] The pairwise spacing values ​​of at least three core particles.

[0104] S302. Obtaining a local core particle model based on the spacing value;

[0105] S303. Perform pre-imaging processing on the overall core particle model based on the local core particle model to obtain the core particle pre-imaging

[0106] Imaging model.

[0107] Its function is to obtain the pairwise spacing values ​​of at least three core particles located in the X / Y series according to the position coordinates of at least three core particles located in the X / Y series, obtain a local core particle model according to the above spacing values, and then perform pre-imaging processing on the overall core particle model according to the local core particle model to obtain a core particle pre-imaging model. This core particle pre-imaging model is an estimate of the global core particle position based on the wafer size.

[0108] Reference Figure 4 , based on the core particle pre-imaging model, the core particle position is verified and marked, including:

[0109] S401. Obtain a pre-distribution estimate of the overall core particle position based on the core particle pre-imaging model;

[0110] S402. Control the probe and microscope to verify the position of the pre-distributed core particles;

[0111] S403. Determine whether the pre-distributed core particle position exists, and obtain the verified core particle position image and

[0112] Wafer profile;

[0113] If the pre-distributed core particle position exists, the pre-distributed core particle position is marked;

[0114] If the pre-distributed core particle position does not exist, the pre-distributed core particle position is not marked.

[0115] The wafer profile is recorded.

[0116] Its function is to obtain a pre-distributed estimate of the overall core particle position based on the core particle pre-imaging model, and use a probe and a microscope to verify the pre-distributed estimated core particle position, that is, to determine whether the pre-distributed core particle position is consistent with the actual distributed core particle position. If the pre-distributed core particle position exists, then the core particle position is consistent with the actual core particle position, and the core particle position is marked. If the pre-distributed core particle position does not exist, it is not marked, and the outline of the wafer at this position is recorded, thereby completing the verification of the pre-estimated core particle position.

[0117] Reference Figure 5 , according to the core grain pre-imaging model, the verified core grain position image and the wafer contour, the core grain model is obtained, including:

[0118] The core particle pre-imaging model, the verified core particle position image and the wafer contour are used to perform the structure

[0119] The final image of the wafer is obtained by combined processing;

[0120] Combine the final image of the wafer, the wafer outline and the actual die distribution position to obtain two

[0121] The spacing and orientation characteristics between core particles;

[0122] The spacing features and orientation features are put into the neural network for training to obtain the core particle model.

[0123] Its function is to obtain the final image of the wafer by combining the core particle pre-imaging model, the verified core particle position image and the outline of the wafer, and obtain the spacing characteristics and orientation characteristics between two adjacent core particles on the wafer by combining the final image of the wafer, the outline of the wafer and the actual core particle distribution position, and put the above spacing characteristics and orientation characteristics into a neural network and use a neural network algorithm for training to obtain a core particle model. The neural network algorithm includes but is not limited to the following: MLP neural network, GMM Gaussian mixture model, KNN nearest neighbor algorithm and support vector machine SVM algorithm.

[0124] The core particle model is embedded into the control program to locate the core particles, including:

[0125] The search positioning and mark point positioning are used to find the first row and the first grain of the wafer and move the probe 1 to the corresponding core grain.

[0126] Reference Figure 6 , search and locate include:

[0127] Look to the upper left corner for the first row and the first grain;

[0128] Move probe 1 to the center of the first particle in the first row to obtain the XY offset of the first particle in the first row from the identification position;

[0129] Click Auto Position to check the positioning effect.

[0130] Its function is to find the first row and the first grain of the wafer and move the probe 1 to the corresponding core grain to achieve automatic positioning.

[0131] Reference Figure 7 , marker positioning includes:

[0132] Edit marker templates;

[0133] Set the rough XY coordinates of the marker point;

[0134] Position the marker point roughly at the screen recognition area;

[0135] Find the marked point;

[0136] Move the first particle in the first row to under probe 1 and set the XY offset of the first particle in the first row to the same mark point.

[0137] Its function is to find the marking point near the specified position and calculate the position of the first grain in the first row to achieve automatic positioning.

[0138] In one embodiment, a chip automatic positioning system for wafer inspection is provided, referring to Figure 8 ,include:

[0139] An acquisition module 10 is used to acquire an overall image of the wafer;

[0140] The position coordinate judgment module 20 is used to obtain the position coordinates of the wafer in the X / Y series based on the overall image of the wafer.

[0141] At least three core particle position coordinates;

[0142] The pre-imaging module 30 is used to image the core particles based on at least three core particle position coordinates located in the X / Y series, the core particles

[0143] The size of the core and the size of the wafer are used to obtain a core pre-imaging model;

[0144] A verification module 40, used for verifying and marking the core particle position based on the core particle pre-imaging model;

[0145] The core particle model forming module 50 is used to generate a core particle model according to the core particle pre-imaging model and the verified core particle position.

[0146] The image and the outline of the wafer are used to obtain the core particle model;

[0147] The application module 60 is used to embed the core particle model into the control program to locate the core particle position.

[0148] Its function is that the position coordinate judgment module 20 obtains the overall position of the wafer 10 according to the acquisition module

[0149] The pre-imaging module 30 obtains a pre-imaging model of the core grain according to the at least three core grain position coordinates located in the above X / Y series, the size of the core grain and the overall size of the wafer. The verification module 40 verifies and marks the estimated global core grain position according to the pre-imaging model of the core grain. The core grain model forming module 50 processes the overall core grain position according to the pre-imaging model of the core grain, the verified core grain position image and the outline of the wafer to obtain the core grain model. The application module 60 embeds the above core grain model into the control program to realize automatic positioning of the core grain position.

[0150] For the specific definition of the automatic positioning system for core particles of wafer inspection, please refer to the definition of the automatic positioning method for core particles of wafer inspection in the above text, which will not be repeated here. Each module in the above-mentioned automatic positioning system for core particles of wafer inspection can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the device in the form of hardware, or can be stored in the memory in the device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0151] In one embodiment, a device is provided, which may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the device is used to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the device is used for data related to the automatic positioning method of the core grains for wafer detection. The network interface of the device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for automatic positioning of the core grains for wafer detection is implemented.

[0152] In one embodiment, a device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the automatic positioning method for wafer detection in the above embodiment is implemented, for example Figure 2 Alternatively, when the processor executes the computer program, the functions of each module / unit of the automatic positioning system for wafer detection in the above-mentioned embodiment are realized, for example Figure 8 The functions of the modules 10 to 60 are shown in Figure 1. To avoid repetition, they will not be described in detail here.

[0153] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the automatic positioning method of the die for wafer inspection in the above embodiment is implemented, for example Figure 2 Alternatively, when the computer program is executed by the processor, the functions of each module / unit in the chip automatic positioning system for wafer inspection in the above device embodiment are realized, for example Figure 8 The functions of the modules 10 to 60 are shown in Figure 1. To avoid repetition, they will not be described in detail here.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments of the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0155] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for automatically positioning a chip during wafer inspection, characterized in that: include: S10, obtaining an overall image of the wafer; S20, based on the wafer overall image, obtaining at least three core particle position coordinates located in the X / Y sequence; the at least three core particle position coordinates located in the X / Y sequence are obtained by first determining the position of a core particle, and each of the core particles adjacent to the core particle and located in the X / Y sequence has one; S30, obtaining a core particle pre-imaging model based on the at least three core particle position coordinates located in the X / Y sequence, the size of the core particle, and the size of the wafer; S40, verifying and marking the core particle position based on the core particle pre-imaging model; S50, obtaining a core particle model according to the core particle pre-imaging model, the verified core particle position image and the wafer contour; S60, embedding the core particle model into the control program to locate the core particle; Step S30 includes: S301, based on the position coordinates of at least three core particles located in the X / Y sequence, obtaining the spacing values ​​of at least three core particles located in the X / Y sequence; S302, obtaining a local core particle model based on the spacing value; S303 , performing pre-imaging processing on the overall core grain model based on the local core grain model to obtain the core grain pre-imaging model, wherein the core grain pre-imaging model is a pre-estimation of the global core grain position based on the wafer size.

2. The automatic chip positioning method for wafer inspection according to claim 1, characterized in that: Step S40 includes: S401, obtaining a pre-distribution estimate of the overall core particle position based on the core particle pre-imaging model; S402, controlling the probe and the microscope to verify the positions of the pre-distributed core particles; S403, determining whether the pre-distributed core particle position exists, and obtaining a verified core particle position image and wafer contour; If the pre-distributed core particle position exists, marking the pre-distributed core particle position; If the pre-distributed core particle position does not exist, the pre-distributed core particle position is not marked, and the outline of the wafer is recorded.

3. The automatic chip positioning method for wafer inspection according to claim 1, characterized in that: Step S50 includes: The final image of the wafer is obtained by combining the core particle pre-imaging model, the verified core particle position image and the wafer contour; Combining the final image of the wafer, the outline of the wafer and the actual distribution position of the core particles to obtain the spacing characteristics and orientation characteristics between the two core particles; The spacing feature and the orientation feature are put into a neural network for training to obtain a core particle model.

4. The automatic chip positioning method for wafer inspection according to claim 1, characterized in that: Step S60 includes: The search positioning and mark point positioning are used to find the first row and the first grain of the wafer and move the probe to the corresponding core grain.

5. The automatic chip positioning method for wafer inspection according to claim 4, characterized in that: The method for searching and locating comprises: Look to the upper left corner for the first row and the first grain; Move the probe to the center of the first particle in the first row to obtain the XY offset of the first particle in the first row from the identification position; Click Auto Position to check the positioning effect.

6. The automatic chip positioning method for wafer inspection according to claim 4, characterized in that: The method for positioning the marker point comprises: Edit marker templates; Set the rough coordinates XY of the positioning of the marking point; Positioning the marking point at a rough position of the screen recognition area; Finding the marked point; Move the first grain in the first row to under the probe and set the XY offset of the first grain in the first row to the same mark point.

7. A chip automatic positioning system for wafer inspection, characterized in that: A method for automatically positioning a die during wafer inspection as claimed in claim 1, wherein the system for automatically positioning a die during wafer inspection comprises: An acquisition module, used for acquiring an overall image of the wafer; A position coordinate judgment module, used for obtaining at least three core particle position coordinates located in an X / Y sequence based on the overall wafer image; A pre-imaging module, used for obtaining a pre-imaging model of the core particles based on the at least three core particle position coordinates located in the X / Y sequence, the size of the core particles and the size of the wafer; A verification module, used for verifying and marking the core grain position based on the core grain pre-imaging model; A core grain model forming module, used for obtaining a core grain model according to the core grain pre-imaging model, the verified core grain position image and the wafer contour; The application module is used to embed the core particle model into the control program to locate the core particle position.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for automatic positioning of core particles in wafer inspection according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for automatic positioning of core particles in wafer inspection according to any one of claims 1 to 6 is implemented.

Images