Intelligent generation method, device and storage medium of optical scheme

Abstract

The present application provides a method, device and storage medium for intelligently generating an optical scheme, the method comprising: obtaining a required data set of a circuit board to be inspected, performing data preprocessing on the required data set, and generating standard defect information to be inspected; determining a preferred optical information set from a preset optical scheme database based on the standard defect information to be inspected; calculating the reference score of each optical scheme in the preferred optical information set, and marking the undetectable defect information in each optical scheme. The technical scheme provided by the present application can effectively select the corresponding optical scheme according to the defects to be inspected of the new circuit board, and mark the undetectable defects for subsequent further optimization of the optical scheme, avoiding the redesign of the optical scheme, reducing repetitive work, saving resources, and improving the generation efficiency of the optical scheme.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and storage medium for intelligently generating an optical solution. Background Art

[0002] As the core component of electronic products, the quality of printed circuit boards (PCBs) is directly related to the performance and life of the products. In order to ensure that the circuit boards can work stably in various complex environments, all aspects of the circuit boards must be strictly inspected. In the use of visual inspection technology to detect defects in the appearance of PCBs, the optical solution is the cornerstone of obtaining PCB images. Through reasonable optical design, such as selecting a suitable light source combination, the tiny components and fine lines on the PCB can be illuminated to ensure that various details on the PCB surface can be clearly captured, so that the camera can generate high-quality images. The appropriate optical solution helps to highlight different target features on the PCB and enhance the ability to identify PCB defects.

[0003] However, the inventors found that there is a lack of corresponding standard libraries for various defects on various circuit boards. When there is a need to detect new circuit boards, it is often necessary to start research from scratch and confirm the final optical solution by trial and error. This process causes waste of resources, and the corresponding repetitive work increases the time for the final confirmation of the optical solution. The efficiency is relatively low and is not conducive to the development of various types of boards and product lines. At the same time, it also creates a certain amount of stocking pressure on the supply chain. Summary of the invention

[0004] In view of this, the present application provides an intelligent generation method, device and storage medium of an optical solution to solve the technical problem in the prior art that the confirmation of optical solutions for new circuit board detection needs is time-consuming and inefficient.

[0005] In a first aspect, the present application provides a method for intelligently generating an optical solution, the method comprising:

[0006] Obtaining a required data set of the circuit board to be inspected, performing data preprocessing on the required data set, and generating standard defect information to be inspected;

[0007] Determine a preferred optical information set from a preset optical solution database based on the standard defect information to be inspected;

[0008] The reference score of each optical solution in the preferred optical information set is calculated, and the undetectable defect information in each optical solution is marked.

[0009] Preferably, the determining of a preferred optical information set from a preset optical solution database based on the standard defect information to be inspected comprises:

[0010] Sort the defects to be inspected according to the attribute characteristics of each defect in the standard defect information to be inspected;

[0011] Compare the sorted defects with the defect information in the preset optical solution database one by one, and select a set of optical solutions that preliminarily meet the requirements;

[0012] And based on the attribute characteristics of the defects that can be detected in each optical scheme, they are sorted, and the preferred optical information set is screened out from the set of optical schemes that preliminarily meet the requirements.

[0013] Preferably, the attribute characteristics of the defect include: defect priority, defect region, defect type, defect color and defect shape.

[0014] Preferably, calculating the reference score of each optical solution in the preferred optical information set comprises:

[0015] The weighted total score of all detectable defects of each optical scheme is calculated to obtain the reference score of each optical scheme.

[0016] Preferably, the intelligent generation method of the optical scheme further comprises extracting undetectable defect information in the selected optical scheme, and determining preferred compensating optical information corresponding to the selected optical scheme from a preset optical scheme database.

[0017] Preferably, the intelligent generation method of the optical scheme further comprises, before extracting the undetectable defect information in the selected optical scheme, ignoring and selecting any undetectable defect.

[0018] Preferably, the intelligent generation method of the optical scheme further comprises extracting the undetectable defect information in the preferred compensating optical information and generating the optical scheme recommendation information in combination with the preset optical scheme database.

[0019] In a second aspect, the present application provides an intelligent generation device for an optical solution, comprising:

[0020] An acquisition module is used to acquire a required data set of the circuit board to be inspected, perform data preprocessing on the required data set, and generate standard defect information to be inspected;

[0021] A selection module, used to determine a preferred optical information set from a preset optical solution database based on the standard defect information to be inspected;

[0022] The marking module is used to calculate the reference score of each optical solution in the preferred optical information set and mark the undetectable defect information in each optical solution.

[0023] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor implements the intelligent generation method of the optical scheme described in the first aspect by executing the computer instructions.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the intelligent generation method of the optical scheme described in the first aspect is implemented.

[0025] The intelligent generation method, device and storage medium of the optical solution provided in this application have at least the following beneficial effects:

[0026] The technical solution provided by the present application starts with obtaining the required data set of the circuit board to be inspected, generates standard defect information to be inspected through data preprocessing, and then screens and determines the preferred optical information set from the preset optical solution database based on this information, and finally calculates the reference score of each optical solution and marks the undetectable defect information, thereby realizing the intelligent and automated generation of the optical solution. The efficiency of optical solution generation is significantly improved, the tediousness and time-consuming of traditional manual design solutions are avoided, the manpower and time costs are greatly saved, and it is helpful to quickly respond to the production needs of new circuit boards, while improving the work efficiency of the entire inspection process. After determining the preferred optical information, it can be used as a basis for further optimizing the design and verification of the optical solution for the undetectable ones, which greatly improves the confirmation efficiency of the optical solution. The optical information corresponding to the detectable defects does not need to be redesigned and verified, which effectively avoids repetitive work, reduces resource waste, and alleviates the pressure of supply chain stocking. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the prior art descriptions. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings without creative work. It should be noted that the drawings described below are schematic and should not be understood as any limitation to the present application. In the drawings:

[0028] Figure 1 A schematic diagram showing a method for intelligently generating an optical solution in one embodiment of the present application is shown;

[0029] Figure 2 A schematic diagram of standard defect information to be inspected in one embodiment of the present application is shown;

[0030] Figure 3Shown based on Figure 2 A preferred optical information schematic diagram;

[0031] Figure 4 A schematic diagram of a smart generation device for an optical solution in one embodiment of the present application is shown;

[0032] Figure 5 A schematic diagram of a computer device in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0034] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0035] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, it can also be the internal connection of two components, it can be a wireless connection, or it can be a wired connection. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0036] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0037] Although the processes described below include multiple operations that appear in a specific order, it should be clearly understood that these processes may also include more or fewer operations, and these operations may be performed sequentially or in parallel.

[0038] Example 1

[0039] The intelligent generation method of optical solutions provided in the present application can be applicable to the application scenario of digitization of optical solutions for visual inspection of circuit boards. It should be noted that the intelligent generation of optical solutions is based on the premise of creating an optical solution database.

[0040] See also Figure 1 , an intelligent generation method of an optical solution provided in one embodiment of the present application may include the following steps.

[0041] S101, obtaining a required data set of a circuit board to be inspected, performing data preprocessing on the required data set, and generating standard defect information to be inspected.

[0042] In this embodiment, the demand data set of the circuit board to be inspected contains all the defect requirements to be inspected of the circuit board to be inspected. Figure 2 As shown, the standard defect information to be inspected includes the area information to which the defect belongs and the defect attribute detailed information.

[0043] S102: Determine a preferred optical information set from a preset optical solution database based on the standard defect information to be inspected.

[0044] In this embodiment, the preset optical scheme database stores the topology of standard optical information and defect information. Based on the defect information to be detected, the preset optical scheme database is matched as much as possible to determine the optical information set that can be basically matched, that is, the defect information corresponding to the topology in the determined optical information has overlap defects with the defect information to be detected. Optical information with a higher degree of overlap is preferably used to form the preferred optical information set.

[0045] S103: Calculate the reference score of each optical solution in the preferred optical information set, and mark the undetectable defect information in each optical solution.

[0046] In this embodiment, the reference score of the optical scheme is calculated based on the defects that overlap with the defect information to be inspected, and the marked undetectable defect information is the defect information to be inspected excluding the overlapping defects. Figure 2 The standard defect information to be inspected is shown in FIG. 1 , and a preferred optical information is determined by referring to FIG. Figure 3 As shown in the figure. The overlapping defects in the defect information to be inspected are the defects to be inspected. Figure 3 Indicated as clear, undetectable defects in Figure 3 After determining the optimal optical information, it can be used as a basis for further optimization, design and verification of the optical solution for undetectable defects, which greatly improves the confirmation efficiency of the optical solution. The optical information corresponding to the detectable defects does not need to be redesigned and verified, effectively avoiding duplication of work, reducing resource waste, and alleviating supply chain stocking pressure.

[0047] In this embodiment, starting from obtaining the required data set of the circuit board to be inspected, the standard defect information to be inspected is generated through data preprocessing, and then the preferred optical information set is screened and determined from the preset optical scheme database based on this information, and finally the reference score of each optical scheme is calculated and the undetectable defect information is marked, thus realizing the intelligent and automatic generation of optical schemes. The efficiency of optical scheme generation is significantly improved, the tedious and time-consuming traditional manual design schemes are avoided, the manpower and time costs are greatly saved, and it is helpful to quickly respond to the production needs of new circuit boards, while improving the work efficiency of the entire inspection process.

[0048] In this embodiment, in the data processing link, the required data set is preprocessed to generate standard defect information to be inspected, so that the defect information is more standardized and accurate, which is convenient for subsequent analysis and matching. The standard defect information to be inspected contains the area information to which the defect belongs and the detailed information of the defect attribute, which provides an accurate data basis for the subsequent optical information screening. This precise data processing method can effectively improve the matching degree between the optical information and the actual detection requirements, reduce the optical information deviation caused by inaccurate information, and thus improve the accuracy and reliability of the optical information. The method of determining the preferred optical information set from the preset optical information database based on the standard defect information to be inspected makes full use of the topological relationship between the standard optical information and the defect information stored in the database. By matching the defect information to be inspected as much as possible, the solution that best fits the actual needs can be screened out from a large number of optical information. In particular, when determining the preferred optical information set, optical information with a higher degree of overlap is given priority. This screening strategy ensures that the determined optical information has high pertinence and effectiveness in meeting the detection requirements, can cover the defects to be inspected to the greatest extent, and improve the quality of optical information.

[0049] In this embodiment, the reference score of each optical information in the preferred optical information set is calculated, and the undetectable defect information in each optical information is marked, providing a scientific and quantitative basis for the evaluation of the optical information. The reference score of the optical information is calculated based on the defects that overlap with the defect information to be detected. This calculation method can intuitively reflect the coverage of each optical information for the defects to be detected. Since the optical information is not the final optical solution, marking the undetectable defect information can allow the user to clearly understand the limitations of each optical information, which helps to make reasonable choices and optimizations according to specific circumstances in practical applications. This scientific solution evaluation method avoids the blindness of relying solely on experience to select solutions and improves the accuracy and reliability of optical information.

[0050] The intelligent generation method of optical solutions and the optical solution database involved in this application can be continuously updated and expanded with the continuous changes in detection needs and the development of optical technology, and store more standard optical information and defect information topological relationships. This makes it possible to adapt to the needs of circuit boards to be tested of different types and specifications, and has strong versatility and flexibility. At the same time, this database-based design method also facilitates the integration and management of new optical solutions, provides convenient conditions for further expansion and upgrading, and helps promote the continuous development and application of optical detection technology.

[0051] Preferably, the determining of a preferred optical information set from a preset optical solution database based on the standard defect information to be inspected comprises:

[0052] Sort the defects to be inspected according to the attribute characteristics of each defect in the standard defect information to be inspected;

[0053] Compare the sorted defects with the defect information in the preset optical solution database one by one, and select a set of optical solutions that preliminarily meet the requirements;

[0054] And based on the attribute characteristics of the defects that can be detected in each optical scheme, they are sorted, and the preferred optical information set is screened out from the set of optical schemes that preliminarily meet the requirements.

[0055] The attribute characteristics of the defect include: defect priority, defect region, defect type, defect color and defect shape.

[0056] In this embodiment, in the process of determining the preferred optical information set from the preset optical information database based on the standard defect information to be inspected, the defects to be inspected are sorted according to the attribute characteristics of each defect in the standard defect information to be inspected. This operation significantly improves the orderliness and systematicness of the defect information to be inspected. That is to say, the more important the defect is, the higher its ranking is, and the higher the score ratio is when the optical information score is calculated later. By considering multi-dimensional attribute characteristics such as defect priority, defect area, defect type, defect color and defect shape, the characteristics of each defect can be described more comprehensively and meticulously. This precise sorting method makes the subsequent comparison with the defect information in the preset optical information database more accurate and efficient. The one-by-one comparison method ensures that each defect to be inspected can be deeply analyzed, avoiding the omission of important information, thereby screening out a preliminary optical information set that meets the requirements, greatly improving the matching degree between the optical information and the defect to be inspected, reducing the scheme deviation caused by incomplete information analysis, and laying a solid foundation for the subsequent generation of more accurate and effective optical information.

[0057] In this embodiment, the optical information sets that initially meet the requirements are sorted again based on the attribute characteristics of the detectable defects in each optical information, and the preferred optical information set is screened out. This secondary screening process further optimizes the selection of optical information. By analyzing and sorting the attribute characteristics of detectable defects, the feasibility and effectiveness of each optical information in actual detection can be more intuitively evaluated. For example, for high-priority defects, optical information that can accurately detect these defects is given priority; for defects in specific areas, types, colors or shapes, the most suitable solutions can also be screened out according to their attribute characteristics. This secondary screening mechanism ensures that the final preferred optical information set has higher quality and reliability in meeting the detection requirements, and guarantees to the greatest extent that optical detection can accurately and comprehensively detect various defects on the circuit board to be inspected.

[0058] In this embodiment, a variety of attribute characteristics of defects are comprehensively considered, including defect priority, defect area, defect type, defect color and defect shape, so that the entire optical information intelligent generation method has stronger adaptability. Different circuit boards to be inspected may have defects of various types and characteristics. By comprehensively considering these attribute characteristics, the system can confirm and optimize the optical information according to the actual situation. Whether it is intensive defect detection in a specific area or identification of defects of different colors and shapes, suitable optical information can be screened out from the preset optical information database. This adaptability not only improves the system's versatility for different types of circuit boards to be inspected, but also meets diverse detection needs.

[0059] In this embodiment, the entire process from sorting defects to be inspected, comparing with the database to secondary screening forms a complete and optimized system. Through this refined operation process, the optimal optical information set that is most suitable for the circuit board to be inspected can be quickly and accurately determined from the preset optical solution database. This not only improves the efficiency of solution generation, reduces the time and energy cost of manual screening and adjustment of solutions, but also greatly improves the accuracy of optical information. Accurate optical information can provide an accurate basis for the subsequent final optical solution, ensure comprehensive and accurate detection of defects on the circuit board to be inspected, and timely discover and locate various defects, which helps to improve product quality and reduce production costs.

[0060] Preferably, calculating the reference score of each optical solution in the preferred optical information set comprises:

[0061] The weighted total score of all detectable defects of each optical scheme is calculated to obtain the reference score of each optical scheme.

[0062] In this embodiment, each defect to be inspected is assigned a defect score according to its attribute characteristics, for example: priority: major is 2 points, defect shape: flake is 3 points, etc. The defect score of each defect to be inspected is divided by the total score of all defects to be inspected to obtain a weighted score for each defect to be inspected. The weighted total score of all detectable defects of each optical scheme is weighted to obtain a reference score for each optical scheme. Figure 3 As shown, the score is 84%, which is the weighted total score of all clear defects.

[0063] In this embodiment, the reference score is determined by weighted calculation of the total weight score of all detectable defects of each optical scheme, so that the actual detection capability of the optical scheme can be accurately evaluated. Different defects have different effects on the overall performance and quality of the circuit board, and each detectable defect is given a corresponding weight, which fully takes these differences into account. For example, for those key defects that have a greater impact on the function of the circuit board and a higher probability of occurrence, a higher weight is given; while for some relatively minor defects, a lower weight is given. The reference score obtained in this way can comprehensively and accurately reflect the detection capability of the optical scheme for defects of different importance, helping users to more clearly understand the actual effect of each optical scheme, so as to make a more wise choice among many schemes. When choosing among many optical schemes, the reference score provides an objective and quantitative evaluation standard. Traditional scheme selection may rely more on experience or simple qualitative judgment, and is easily affected by subjective factors. The weighted calculation of the reference score converts the detection capability of each optical scheme into a specific value, making the comparison between schemes more intuitive and accurate. By comparing the reference scores of various solutions, users can directly determine which solution performs better in detecting defects to be inspected, thereby improving the scientificity and rationality of solution selection, avoiding blind decision-making, and ensuring that the selected optical solution can meet actual detection needs to the greatest extent.

[0064] The reference score can not only be used to select solutions, but also provide a clear direction for further improvement of optical solutions. By analyzing the total score of the detectable defect weights of each optical solution, the advantages and disadvantages of the solution in detecting certain types of defects can be found. For example, if a solution scores low in detecting high-weight defects, the solution can be optimized and improved for these defects. This feedback mechanism based on reference scores can prompt R&D personnel to continuously optimize optical solutions.

[0065] The method of weighted calculation of reference scores is highly flexible and adaptable, and can be applied to different types and sizes of circuit boards to be inspected and various inspection requirements. Whether it is a simple circuit board or a complex high-density integrated circuit board, appropriate weights can be set for detectable defects according to actual conditions to calculate accurate reference scores. This versatility enables the method to be widely used in different production environments and industries, enhances the compatibility and applicability of the entire optical solution generation method, and provides effective technical support for circuit board inspection in more fields.

[0066] Preferably, the intelligent generation method of the optical scheme further comprises extracting undetectable defect information in the selected optical scheme, and determining preferred compensating optical information corresponding to the selected optical scheme from a preset optical scheme database.

[0067] In this embodiment, by extracting the undetectable defect information and determining the preferred compensating optical information, the optical scheme is actually optimized and combined. The original single selected optical scheme is combined with the compensating optical information to form a more complete and comprehensive optical scheme. It can give full play to the advantages of the combination and make up for each other's shortcomings, thereby improving the adaptability of the overall optical scheme. Whether it is a complex circuit board structure or a variety of defect types, a more preferred combined optical scheme can be quickly determined in this way.

[0068] In this embodiment, the selected undetectable defect information is extracted, and the defect blind area can be clearly located, and it is clear which defects cannot be effectively detected by the currently selected optical scheme. Subsequently, the corresponding preferred compensating optical information is determined from the preset optical scheme database. This measure can make up for the defect blind area in a targeted manner. The comprehensiveness and accuracy of the optical scheme are improved, ensuring that the defects on the circuit board to be detected can be covered by the selected optical information and compensating optical information. The preferred compensating optical information corresponding to the selected optical scheme is determined from the database, and the large amount of data resources already in the database are fully utilized again to quickly find a suitable compensation scheme, saving the time and cost of redesigning the optical scheme. The generation and optimization process of the entire optical scheme is made more efficient and convenient, while also ensuring the reliability and scientificity of the compensating optical information, which helps to improve the performance of the entire optical scheme and further improves the generation efficiency of the optical scheme.

[0069] Preferably, the intelligent generation method of the optical scheme further comprises, before extracting the undetectable defect information in the selected optical scheme, ignoring and selecting any undetectable defect.

[0070] In this embodiment, before extracting the undetectable defect information in the selected optical scheme, any undetectable defect is ignored, which greatly improves the efficiency of generating the optical scheme. In the actual process, for those brand-new defects, there is no corresponding topology in the database, that is, only a single defect cannot match the corresponding optical information. If it continues to be included in the subsequent optical scheme generation process, it will undoubtedly waste a lot of time and computing resources. These defects often require subsequent separate targeted design and verification of the corresponding optical scheme. By ignoring these defects in advance, the entire optical scheme generation process can be simplified, unnecessary information processing links can be reduced, and more focus can be placed on the analysis and processing of other defects, so that the screened optical information is more accurate and an effective optical scheme can be generated more quickly for the circuit board to be inspected.

[0071] Preferably, the intelligent generation method of the optical scheme further comprises extracting the undetectable defect information in the preferred compensating optical information and generating the optical scheme recommendation information in combination with the preset optical scheme database.

[0072] In this embodiment, after extracting the undetectable defect information in the preferred compensation optical information, the optical solution suggestion information is generated in combination with the preset optical solution database. This process realizes the continuous optimization of the optical solution. By continuously exploring the undetectable defects that still exist in the compensation optical information, the potential blind spots in the detection process can be further clarified. Based on this information, the use of the preset optical solution database to generate new optical solution suggestions can help to continuously fill the loopholes in the optical solution and make the final optical solution more perfect, thereby significantly improving the comprehensiveness of circuit board defect detection, minimizing the risk of missed detection, and ensuring the reliability of product quality. The generated optical solution suggestions can be based on a large amount of existing experience and data, and have stronger scientificity and rationality. Compared with the method of relying solely on experience or simple trial and error, this method based on deep analysis of the database can provide a more reliable basis for the formulation of optical solutions, thereby improving the quality and effectiveness of optical detection solutions. Different circuit boards to be tested may have various complex defect situations, and with the development of technology and changes in production processes, detection requirements are also constantly evolving. By extracting the undetectable defect information from the optimal compensation optical information and generating optical solution suggestion information in combination with the database, we can better adapt to these complex and changing detection needs. Each mining of undetectable defects and generation of new solution suggestions is an optimization and adjustment, providing strong support for the detection of various circuit boards. The efficiency of generating optical solutions is further improved.

[0073] Example 2

[0074] This embodiment provides an intelligent generation device for an optical solution, which is described by applying the intelligent generation method for an optical solution provided in the above embodiment 1. Figure 4As shown, an intelligent generation device for an optical solution provided in one embodiment of the present application may include the following multiple modules.

[0075] An acquisition module is used to acquire a required data set of the circuit board to be inspected, perform data preprocessing on the required data set, and generate standard defect information to be inspected;

[0076] A selection module, used to determine a preferred optical information set from a preset optical solution database based on the standard defect information to be inspected;

[0077] The marking module is used to calculate the reference score of each optical solution in the preferred optical information set and mark the undetectable defect information in each optical solution.

[0078] The intelligent generation device of the optical solution provided in the embodiment of the present application can be applied to the intelligent generation method of the optical solution provided in the above-mentioned embodiment 1. For relevant details, refer to the above-mentioned method embodiment. The implementation principle and technical effect are similar and will not be repeated here.

[0079] It should be noted that: when the intelligent generation device of the optical scheme provided in the embodiment of the present application performs the intelligent generation of the optical scheme, only the division of the above-mentioned functional modules / functional units is used as an example. In practical applications, the above-mentioned functions can be assigned to different functional modules / functional units as needed, that is, the internal structure of the intelligent generation device of the optical scheme is divided into different functional modules / functional units to complete all or part of the functions described above. In addition, the implementation method of the intelligent generation method of the optical scheme provided in the above-mentioned method embodiment 1 and the implementation method of the intelligent generation device of the optical scheme provided in this embodiment 2 belong to the same concept. The specific implementation process of the intelligent generation device of the optical scheme provided in this embodiment 2 is detailed in the above-mentioned method embodiment 1, and will not be repeated here.

[0080] Example 3

[0081] See also Figure 5 As shown, one embodiment of the present application also provides a computer device, which can be a computer device such as a desktop computer, a laptop computer, a handheld computer, and a cloud server. The computer device can include, but is not limited to, a processor and a memory. The processor and the memory are connected via a bus or other means.

[0082] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, graphics processing units (GPU), embedded neural network processors (NPU) or other dedicated deep learning coprocessors, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above chips.

[0083] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the methods in the above-mentioned embodiments of the present application. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory, that is, implementing the methods in the above-mentioned method embodiments.

[0084] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0085] One embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program. When the computer program is executed by a processor, the method in the above method embodiment is implemented.

[0086] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned implementation methods of the present application can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the implementation methods of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0087] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0088] Although the embodiments of the present application are described in conjunction with the accompanying drawings, they cannot be understood as limiting the scope of the patent application. It should be pointed out that for ordinary technicians in this field, other different forms of changes or modifications can be made on the basis of the above description without departing from the concept of the present application. It is not necessary and impossible to list all the embodiments here. The obvious changes or modifications derived from this are still within the scope of protection created by the present application. Therefore, the scope of protection of the patent application shall be based on the attached claims.

Claims

1. A method for intelligently generating an optical solution, characterized in that: The method comprises: Obtaining a required data set of the circuit board to be inspected, performing data preprocessing on the required data set, and generating standard defect information to be inspected; Determine a preferred optical information set from a preset optical solution database based on the standard defect information to be inspected; The reference score of each optical solution in the preferred optical information set is calculated, and the undetectable defect information in each optical solution is marked.

2. The intelligent generation method of optical solutions according to claim 1, characterized in that: The step of determining a preferred optical information set from a preset optical solution database based on the standard defect information to be inspected comprises: Sort the defects to be inspected according to the attribute characteristics of each defect in the standard defect information to be inspected; Compare the sorted defects with the defect information in the preset optical solution database one by one, and select a set of optical solutions that preliminarily meet the requirements; And based on the attribute characteristics of the defects that can be detected in each optical scheme, they are sorted, and the preferred optical information set is screened out from the set of optical schemes that preliminarily meet the requirements.

3. The intelligent generation method of optical scheme according to claim 2, characterized in that: The attribute characteristics of the defect include: defect priority, defect region, defect type, defect color and defect shape.

4. The intelligent generation method of optical solutions according to claim 1, characterized in that: The calculating the reference score of each optical scheme in the preferred optical information set comprises: The weighted total score of all detectable defects of each optical scheme is calculated to obtain the reference score of each optical scheme.

5. The intelligent generation method of optical solutions according to claim 1, characterized in that: The method also includes extracting undetectable defect information in the selected optical scheme, and determining preferred compensating optical information corresponding to the selected optical scheme from a preset optical scheme database.

6. The intelligent generation method of optical solutions according to claim 5, characterized in that: The method also includes ignoring and selecting any undetectable defects before extracting the undetectable defect information in the selected optical scheme.

7. The intelligent generation method of optical solutions according to claim 5 or 6, characterized in that: The method also includes extracting undetectable defect information from the preferred compensating optical information and combining it with optical solution recommendation information generated by a preset optical solution database.

8. An intelligent generation device for optical solutions, characterized in that: include: An acquisition module is used to acquire a required data set of the circuit board to be inspected, perform data preprocessing on the required data set, and generate standard defect information to be inspected; A selection module, used to determine a preferred optical information set from a preset optical solution database based on the standard defect information to be inspected; The marking module is used to calculate the reference score of each optical solution in the preferred optical information set and mark the undetectable defect information in each optical solution.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor implements the intelligent generation method of the optical scheme as described in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the intelligent generation method of the optical solution according to any one of claims 1 to 7 is implemented.

Images