Product production method and device and storage medium

Abstract

The invention relates to a product production method and device and a storage medium. The product production method comprises the steps that in the mainboard printing process, appearance detection is conducted on a target product, and the target product is a printed mainboard; in response to the situation that the appearance of the target product does not meet the appearance requirement, calling a target model to carry out production parameter adjustment; and the subsequent target product is produced based on the adjusted production parameters, so that the appearance of the subsequent target product meets the preset appearance requirement. According to the product production method provided by the embodiment of the invention, the target model is called to adjust the production parameters under the condition that the produced target product is identified to have the poor appearance, so that the poor appearance of the subsequent target product is eliminated, the yield of the production process is improved, and the cost waste of production and manufacturing is reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and particularly to a product production method, apparatus, and storage medium. Background Art

[0002] With the development of artificial intelligence technology, artificial intelligence models are widely used in various fields.

[0003] In related technologies, in the manufacturing industry, for the production of some process sites, the yield rate of products is very important. Among them, defective products of the product appearance type are usually detected manually. And for defective products of the appearance type, specialized technical personnel are also responsible for analyzing the causes of defects and making defect improvements to reduce the incidence of defective products of the product appearance type, thereby improving the yield rate of products.

[0004] However, the above-mentioned manual processing process is inefficient and seriously affects the production and delivery of products. Summary of the Invention

[0005] To overcome the problems existing in related technologies, the present disclosure provides a product production method, apparatus, and storage medium.

[0006] According to a first aspect of an embodiment of the present disclosure, a product production method is provided, including: during the process of printing on a main board, performing shape detection on a target product, where the target product is the printed main board; in response to the shape of the target product not meeting the shape requirement, invoking a target model to adjust production parameters; and producing subsequent target products based on the adjusted production parameters so that the shape of the subsequent target products meets a preset shape requirement.

[0007] In one implementation, the invoking a target model to adjust production parameters includes: determining first information based on the shape detection result of the target product, where the first information characterizes the cause of the shape of the target product not meeting the shape requirement; and adjusting production parameters based on the first information.

[0008] In another implementation, the adjusting production parameters based on the first information includes: determining the parameter category to be adjusted and the numerical adjustment range of the parameter based on the first information; and adjusting the parameter based on the parameter category and the numerical adjustment range of the parameter.

[0009] In another implementation manner, determining the first information based on the shape detection result of the target product includes: obtaining a first image, where the first image is an image including the target product; in the first image, identifying the target product whose shape does not meet the shape requirement, and determining second information, where the second information is the shape information of the target product that does not meet the shape requirement; determining the first information based on a first mapping relationship, where the first mapping relationship is the mapping relationship between the second information and the reason for the occurrence of the second information.

[0010] In another implementation manner, the target model is trained in the following way: obtaining a second image based on the historical production process of the target product, where the second image has annotation information, and the annotation information is used to represent a second mapping relationship, where the second mapping relationship is the mapping relationship between the production parameters and the shape of the target product; training a basic model based on the second image to obtain the target model.

[0011] In another implementation manner, identifying the target product whose shape does not meet the shape requirement includes: detecting a specified area of the target product in the first image to obtain first shape dimension information of the specified area; obtaining second shape dimension information of the first N products of the target product, where the second shape dimension information is the shape dimension corresponding to the specified area of each of the first N products, and each of the first N products corresponds to one second shape dimension information, where N is an integer greater than or equal to 1; obtaining a variance value based on the first shape dimension information and the N second shape dimension information; calculating a quality result corresponding to the target product through the first shape dimension information and the variance value, and if the quality result does not meet the result threshold, determining that the target product is the target product whose shape does not meet the shape requirement.

[0012] In another implementation manner, after performing shape detection on the target product, it further includes: obtaining the shape detection result of the target product and the production information corresponding to the target product, where the production information includes the resume information corresponding to the target product and the production parameters corresponding to the target product; obtaining a first image, where the first image is an image including the target product; using the shape detection result of the target product and the production parameters corresponding to the target product as the annotation information of the first image.

[0013] In another implementation manner, the parameter category includes: the process parameters of the target product and / or the environmental parameters during the production process of the target product.

[0014] According to a second aspect of the embodiments of the present disclosure, a product production device is provided, including a detection unit for performing shape detection on a target product during the printing process of the main board, where the target product is the printed main board; a processing unit for calling a target model to adjust production parameters in response to the shape of the target product not meeting the shape requirements; and the processing unit is further configured to produce subsequent target products based on the adjusted production parameters so that the shapes of the subsequent target products meet the preset shape requirements.

[0015] In one implementation, the processing unit calls the target model to adjust production parameters in the following manner: based on the shape detection result of the target product, determine first information, where the first information characterizes the cause of the shape of the target product not meeting the shape requirements; and adjust the production parameters based on the first information.

[0016] In another implementation, the processing unit adjusts the production parameters based on the first information in the following manner: based on the first information, determine the parameter category to be adjusted and the numerical adjustment range of the parameter; and perform parameter adjustment based on the parameter category and the numerical adjustment range of the parameter, where the parameter category includes: the process parameters of the target product and / or the environmental parameters during the production process of the target product.

[0017] In yet another implementation, the processing unit determines the first information based on the shape detection result of the target product in the following manner: obtain a first image, where the first image is an image including the target product; in the first image, identify the target product whose shape does not meet the shape requirements, and determine second information, where the second information is the shape information of the target product not meeting the shape requirements; and determine the first information based on a first mapping relationship, where the first mapping relationship is the mapping relationship between the second information and the cause of the second information occurring.

[0018] In yet another implementation, the target model is trained in the following manner: obtain a second image based on the historical production process of the target product, where the second image has annotation information, and the annotation information is used to characterize a second mapping relationship, where the second mapping relationship is the mapping relationship between the production parameters and the shape of the target product; and train a basic model based on the second image to obtain the target model.

[0019] In another implementation, the processing unit identifies a target product that does not meet the shape requirements in the following manner: detecting a specified area of the target product in the first image to obtain first shape dimension information of the specified area; obtaining second shape dimension information of the first N products of the target product, where the second shape dimension information is the shape dimension corresponding to the specified area of each of the first N products, and each of the first N products corresponds to one piece of second shape dimension information, where N is an integer greater than or equal to 1; obtaining a variance value based on the first shape dimension information and the N pieces of second shape dimension information; calculating a quality result corresponding to the target product through the first shape dimension information and the variance value, and if the quality result is greater than a result threshold, determining that the target product is a target product whose shape does not meet the shape requirements.

[0020] In another implementation, the processing unit is further configured to obtain an appearance detection result of the target product and production information corresponding to the target product, where the production information includes resume information corresponding to the target product and production parameters corresponding to the target product; obtain a first image, where the first image is an image including the target product; and use the appearance detection result of the target product and the production parameters corresponding to the target product as annotation information of the first image.

[0021] According to a third aspect of the embodiments of the present disclosure, a product production device is provided, including: a memory for storing processor-executable commands; where the processor is configured to: execute the product production method according to the first aspect or any one of the first aspect.

[0022] According to a fourth aspect of the embodiments of the present disclosure, a storage medium is provided, where the storage medium stores instructions that, when running on a device, cause the device to execute the product production method according to the first aspect or any one of the first aspect

[0023] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: The product production method provided by the embodiments of the present disclosure calls a target model to adjust production parameters when it is recognized that there are shape defects in the produced target products, so as to eliminate the shape defects of subsequent target products, thereby improving the yield rate of the process production and further reducing the cost waste of production and manufacturing.

[0024] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present disclosure and used together with the specification to explain the principles of the present disclosure.

[0026] Figure 1 It is a flowchart of a product production method shown according to an exemplary embodiment.

[0027] Figure 2 It is a schematic diagram of the process of adjusting target model parameters shown according to an exemplary embodiment.

[0028] Figure 3 It is a schematic diagram of the process of parameter adjustment based on the first information shown according to an exemplary embodiment.

[0029] Figure 4 It is a schematic diagram of the process of determining the first message shown according to an exemplary embodiment.

[0030] Figure 5 It is a schematic diagram of the process of training a target model shown according to an exemplary embodiment.

[0031] Figure 6 It is a schematic diagram of the process of identifying a target product shown according to an exemplary embodiment.

[0032] Figure 7 It is a schematic diagram of the process of product production shown according to an exemplary embodiment.

[0033] Figure 8 It is a schematic diagram of the process of product production shown according to an exemplary embodiment.

[0034] Figure 9 It is a block diagram of a product production device shown according to an exemplary embodiment.

[0035] Figure 10 It is a block diagram of a device for product production shown according to an exemplary embodiment.

[0036] Figure 11 It is a block diagram of a device for product production shown according to an exemplary embodiment. Detailed implementation manners

[0037] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all the implementation manners consistent with the present disclosure.

[0038] With the development and progress of industrial technologies, the concept of smart factories has gradually come into people's sight.

[0039] An intelligent factory refers to the use of advanced information technology and automation technology to achieve the automation, digitization, and intelligence of the production process through a highly integrated, intelligent, and collaborative production system. It connects devices, products, and personnel through technologies such as the Internet of Things, cloud computing, big data analysis, and artificial intelligence to achieve real-time monitoring, control, and optimization of the production process, improving production efficiency, quality, and flexibility.

[0040] In the manufacturing industry, the products produced are usually divided into two product states according to whether they can meet the user's requirements: "good products" and "defective products". It can be understood that those that can meet the user's requirements for the product are called "good products", and those that cannot meet the user's requirements for the product are called "defective products". And defective products usually come with one or more defective items.

[0041] In the related art, in order to ensure the yield rate of the current manufacturing process station, when the defective product rate is higher than a certain threshold, corresponding technical personnel will be arranged to conduct a cause analysis to improve the defective product rate.

[0042] For technical personnel, the usual processing method is to identify the defective items of defective products based on the technical experience they have mastered, and analyze the cause of occurrence in combination with auxiliary documents such as Failure Modes Analysis (FMEA), and finally based on the corresponding improvement measures, so as to improve the defective product rate.

[0043] However, the processing process based on personnel is relatively complex and time-consuming. It seriously affects the production and delivery of products.

[0044] Based on this, the embodiments of the present disclosure propose a product production method. During the production of the target product, the appearance of the target product is detected; in response to the appearance of the target product not meeting the appearance requirements, the target model is called to adjust the production parameters; the subsequent target products are produced based on the adjusted production parameters so that the appearance of the subsequent target products meets the preset appearance requirements. By calling the target model to adjust the production parameters when it is recognized that the target product produced has an appearance defect, the appearance defect of the subsequent target products is eliminated, thereby improving the yield rate of the manufacturing process and further reducing the cost waste of production and manufacturing.

[0045] It should be noted that the product production method involved in the embodiments of the present disclosure can be applied to terminals. In some embodiments, the terminal includes, for example, at least one of a mobile phone, a wearable device, an Internet of Things device, an automobile with communication function, a smart automobile, a tablet computer (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, and a wireless terminal device in smart home, but is not limited thereto.

[0046] For ease of understanding, in the following embodiments of the present disclosure, the exemplary description of "terminal" can be understood as "intelligent production equipment" without special emphasis.

[0047] It should be noted that, for ease of understanding the embodiments of the present disclosure, some terms in the embodiments of the present disclosure are explained below to facilitate the understanding of those skilled in the art.

[0048] Production parameters: In manufacturing, production parameters are a set of indicators used to measure and control the production process. These parameters are usually related to factors such as product quality, production efficiency, and resource utilization.

[0049] Generally, production parameters can include: equipment parameters, process parameters, etc.

[0050] For equipment parameters, they are a set of indicators used to describe and measure the performance and capabilities of manufacturing equipment. These parameters are usually related to factors such as the function, efficiency, accuracy, and reliability of the equipment.

[0051] It can be understood that by monitoring and controlling equipment parameters, manufacturing enterprises can optimize and adjust the equipment, improve production efficiency, reduce failure rates, and thus achieve higher production quality and benefits.

[0052] For process parameters, they are a set of indicators used to describe and control the production process. Process parameters are usually related to raw material use, process operations, equipment operation, etc.

[0053] It is understandable that by reasonably setting and controlling process parameters, manufacturing enterprises can ensure product consistency and quality stability, improve production efficiency, and meet customer requirements. The optimization of process parameters also helps to reduce the scrap rate (or defective rate), energy consumption, and resource waste.

[0054] It is understandable that the production parameters mentioned in the embodiments of the present disclosure, which can be understood as the relevant parameters used in the production of target products, in addition to the above-mentioned equipment parameters and process parameters, may also include environmental parameters (such as temperature and humidity parameters, static electricity parameters, cleanliness parameters, etc.) used in the production of target products.

[0055] Figure 1 is a flowchart of a product production method shown according to an exemplary embodiment, as Figure 1 shown, the method is used in a terminal and includes the following steps.

[0056] In step S11, during the process of printing the main board, the appearance of the target product is detected.

[0057] In step S12, in response to the appearance of the target product not meeting the appearance requirements, a target model is called to adjust the production parameters.

[0058] In step S13, based on the adjusted production parameters, subsequent target products are produced so that the appearance of the subsequent target products meets the preset appearance requirements.

[0059] The product production method provided by the embodiments of the present disclosure, by calling a target model to adjust production parameters when it is recognized that there are appearance defects in the produced target products, eliminates the appearance defects of subsequent target products, thereby improving the yield rate of the manufacturing process and further reducing the cost waste of production and manufacturing.

[0060] In some embodiments, the target product is the printed main board.

[0061] It is understandable that the target product can also be understood as the production product that completes the current process in the current process station. For example, if process station A is a process station in the main board printing process, then for process station A, the production product that completes the process of this station and has not undergone the next process can also be called the target product.

[0062] In some embodiments, the product production method is applied to a terminal.

[0063] In some embodiments, by calling the image acquisition device of the terminal, the appearance is detected during the production of the target product.

[0064] Exemplarily, the image acquisition device of the terminal can be an industrial camera, etc.

[0065] Through the method provided by the embodiments of the present disclosure, the shape of the target product can be detected based on an image by calling an image acquisition device during the production process, so that the shape of the target product can be detected in a timely and accurate manner.

[0066] In some embodiments, detecting the shape of the target product includes at least one of the following: detecting the external dimensions of the target product, or detecting the external shape of the target product.

[0067] Optionally, for the detection of the external dimensions of the target product, it includes: detecting at least one external dimension of the target product.

[0068] It can be understood that the target product may correspond to at least one external dimension. When detecting the external dimensions of the target product, which one or more external dimensions to specifically detect can be set according to user requirements.

[0069] Optionally, for the detection of the external dimensions of the target product, in the case where the detected external dimensions do not meet the preset dimension threshold (for example, the detected external dimensions are not within the range of the preset dimension threshold, etc.), it is regarded that the target shape does not meet the shape requirements.

[0070] Based on this, it is possible to judge whether the shape of the target product meets the shape requirements from the dimension dimension of the target product's shape, so as to determine whether the target product is a qualified product considering its shape.

[0071] In some embodiments, when evaluating the external dimensions of the target product, if the detected external dimensions do not meet the preset dimension threshold, it may include at least one of the following:

[0072] The absolute dimension of the current product does not meet the first preset dimension threshold (for example, the product dimension does not meet the product dimension specification), or the current production capacity measured based on the N products produced currently does not meet the second preset threshold (for example, the current process capability index is lower than 1.33, etc.), where N is an integer greater than or equal to 1.

[0073] Optionally, for the detection of the external shape of the target product, it includes: identifying the external contour of the target product, or identifying the external contour of a specified area of the target product.

[0074] It can be understood that the external contour of the target product has shape requirements. For example, it is required that the external contour of the target product is a rectangle, or a circle, etc. Or it is required that a certain area of the target product has shape requirements. For example, it is required that the contour of the area where the A device of the target product is located is a rectangle, etc.

[0075] Optionally, for the detection of the external shape of the target product, when it is detected that the external shape does not meet the preset shape (for example, the detected external shape of the target product is circular, but the requirement for the external shape of the target product is rectangular), it is regarded that the target external shape does not meet the external shape requirement.

[0076] Based on this, it is possible to judge whether the external shape of the target product meets the external shape requirement from the dimension of the external shape of the target product, so as to determine whether the target product is a qualified product considering its external shape.

[0077] It can be understood that the external dimensions and the external shape dimension of the target product can be detected simultaneously to judge whether the external shape of the target product meets the external shape requirement.

[0078] In some embodiments, the target model is obtained based on pre-training and deployed on the terminal.

[0079] In some embodiments, the target model is used to adjust the production parameters of the terminal when the external shape of the target product does not meet the external shape requirement.

[0080] Based on this, through the preset model, the automatic adjustment of production parameters can be realized, avoiding manual operation and improving production efficiency.

[0081] In some embodiments, terms such as "certain", "preseted", "preset", "set", "indicated", "a certain", "any", "first", etc. can be replaced with each other. "Specific A", "Preseted A", "Preset A", "Set A", "Indicated A", "A certain A", "Any A", "First A" can be interpreted as A pre-specified in a protocol, etc., or can be interpreted as A obtained through setting, configuration, or indication, etc., or can be interpreted as Specific A, A certain A, Any A, or First A, etc., but not limited thereto.

[0082] The product production method involved in the embodiments of the present disclosure may include at least one of steps S11 to S13. For example, step S11 can be implemented as an independent embodiment, step S12 can be implemented as an independent embodiment, step S11 + step S12 can be implemented as an independent embodiment, and step S11 + step S12 + step S13 can be implemented as an independent embodiment, but not limited thereto.

[0083] In some embodiments, steps S11 and S12 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0084] In some embodiments, steps S11 and S13 are optional, and in different embodiments, one or more of these steps can be omitted or replaced.

[0085] In some embodiments, steps S12 and S13 are optional, and in different embodiments, one or more of these steps can be omitted or replaced.

[0086] In some embodiments, Figure 2 is a schematic flowchart of a method for adjusting target model parameters shown according to an exemplary embodiment. The method includes the following steps.

[0087] In step S21, based on the shape detection result of the target product, first information is determined, and the first information characterizes the cause of the non - compliance of the shape of the target product with the shape requirement.

[0088] In step S22, production parameters are adjusted based on the first information.

[0089] The product production method provided by the embodiments of the present disclosure calls a model to judge the corresponding cause of occurrence according to the detected product shape result, and then adjusts the corresponding production parameters based on the judged cause of occurrence. It can improve the accuracy of the model for the parameter adjustment result, and facilitate the model to quickly and accurately improve the problem that the shape of the target product does not meet the shape requirement by adjusting the production parameters.

[0090] In some embodiments, the cause of the non - compliance of the shape of the target product characterized by the first information includes at least one of the following: the main cause, or the interference cause.

[0091] Among them, the main cause may include the cause directly acting on the production of the target product. Exemplarily, for example, the cause related to process parameters, or the cause related to equipment parameters, etc.

[0092] The interference cause may include the cause indirectly acting on the target product. Exemplarily, for example, the cause related to environmental parameters, etc.

[0093] In some embodiments, the target model obtains the shape detection result of the target product and determines the first information based on the shape detection result of the target product.

[0094] In some embodiments, "obtain", "acquire", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be replaced with each other, and it can be interpreted as receiving from other entities, but not limited thereto.

[0095] In some embodiments, the first information is carried on at least one of the following, including: the shape detection image of the target product, or the shape measurement data of the target detection result.

[0096] Exemplarily, the shape detection image of the target product can be obtained by invoking the image acquisition device of the terminal, and the target model determines the reason why the shape of the target product does not meet the shape requirement through the obtained detection image. For example, if the shape of the target product in the detection image does not meet the shape requirement, the detection image is sent to the target model, and the target model obtains the reason why the product shape does not meet the shape requirement through the recognition of the detection image, that is, the first information is obtained.

[0097] Exemplarily, the shape detection data of the target product can be obtained by invoking the image acquisition device of the terminal, and the target model determines the reason why the shape size of the target product does not meet the preset size threshold requirement through the obtained shape detection data. For example, if there is size data in the detection data that does not meet the preset size threshold, the data is sent to the target model, and the target model determines the cause through the analysis and interpretation of the read data, that is, the first information is obtained.

[0098] Based on this, the target model can obtain the cause corresponding to the shape detection result of the corresponding target product through different carrying methods, which can improve the universality of the method.

[0099] The product production method involved in the embodiments of the present disclosure may include at least one of steps S21 to step S22. For example, step S21 can be implemented as an independent embodiment, step S22 can be implemented as an independent embodiment, and step S21 + step S22 can be implemented as an independent embodiment, but not limited thereto.

[0100] In some embodiments, step S21 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0101] In some embodiments, step S22 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0102] In some embodiments, Figure 3 is a schematic flowchart of a method for parameter adjustment based on the first information shown in an exemplary embodiment, as Figure 3 shown, the method includes the following steps.

[0103] In step S31, based on the first information, determine the parameter category to be adjusted and the numerical adjustment range of the parameter.

[0104] In step S32, based on the parameter category and the numerical adjustment range of the parameter, perform parameter adjustment.

[0105] The product production method provided by the embodiments of the present disclosure determines the specific content of the parameters to be adjusted through the first information, so that the target model can be precisely adjusted in a targeted manner, improving the defect rate of the target product.

[0106] In some embodiments, based on the cause of the target product not meeting the shape requirements, the target model determines the parameter categories to be adjusted and the numerical adjustment ranges of the parameters.

[0107] The product production method provided by the embodiments of the present disclosure determines the specific content of the parameters to be adjusted through the first information, so that the target model can be precisely adjusted in a targeted manner, improving the defect rate of the target product.

[0108] The product production method involved in the embodiments of the present disclosure may include at least one of steps S31 to S32. For example, step S31 can be implemented as an independent embodiment, step S32 can be implemented as an independent embodiment, and step S31 + step S32 can be implemented as an independent embodiment, but not limited thereto.

[0109] In some embodiments, step S31 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0110] In some embodiments, step S32 is optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0111] In some embodiments, the parameter categories include: the process parameters of the target product, and / or the environmental parameters during the production process of the target product.

[0112] Optionally, the process parameters may include at least one of the following: process parameters, or equipment parameters.

[0113] Optionally, the process parameters correspond to at least one process parameter item, the equipment parameters correspond to at least one equipment parameter item, and the environmental parameters correspond to at least one environmental parameter item.

[0114] Exemplarily, the process parameter items may include at least one of the following: A pressure, B speed, and C temperature, etc.

[0115] Exemplarily, the equipment parameter items may include at least one of the following: the running speed of the D axis of the equipment, the vacuum degree of the E platform of the equipment, and the flatness of the F station of the equipment, etc.

[0116] Exemplarily, the environmental parameter items may include at least one of the following: environmental temperature and humidity, or environmental cleanliness, etc.

[0117] Exemplarily, taking the motherboard printing process as an example, its process parameters include at least one of the following: squeegee pressure, squeegee speed, demolding speed, demolding distance, printing gap, solder paste wiping frequency, etc.

[0118] In some embodiments, the target model determines one or more parameter items in the parameter category to be adjusted.

[0119] In some embodiments, the target model determines the parameter adjustment range corresponding to one or more parameter items.

[0120] In some embodiments, the target model adjusts one or more parameter items among the parameter categories to be adjusted.

[0121] In some embodiments, the target model adjusts the parameters corresponding to one or more parameter items to be adjusted according to the corresponding parameter adjustment range.

[0122] Based on this, the target model can accurately adjust specific parameter items, and can implement the parameter adjustment value corresponding to each parameter item within the corresponding parameter range, achieving precise control of the parameters.

[0123] In some embodiments, Figure 4 is a schematic flowchart of a method for determining a first message shown according to an exemplary embodiment, as Figure 4 shown, the method includes the following steps.

[0124] In step S41, a first image is obtained, and the first image is an image including a target product.

[0125] In step S42, in the first image, a target product whose appearance does not meet the appearance requirements is recognized, and second information is determined, where the second information is the appearance information indicating that the target product does not meet the appearance requirements.

[0126] In step S43, first information is determined based on a first mapping relationship, where the first mapping relationship is a mapping relationship between the second information and the cause of the occurrence of the second information.

[0127] The product production method provided by the embodiments of the present disclosure determines the information of the target product that does not meet the appearance requirements through the obtained first image, and then finds the matching cause based on the first mapping relationship. It enables the target model to recognize the corresponding cause based on the appearance characteristics represented by the defective products of the target product, facilitating the parameter adjustment of the target model based on the first information.

[0128] In some embodiments, the first image is obtained based on an image acquisition device of the terminal.

[0129] In some embodiments, the first image can be an image during the production process of the target product.

[0130] In some embodiments, the second information may include at least one of the following: information that the external dimensions of the target product do not meet the external requirements, or information that the external shape of the target product does not meet the external requirements.

[0131] Exemplarily, the information that the external dimensions of the target product do not meet the external requirements may be, for example, dimension data that does not meet the dimension threshold.

[0132] Exemplarily, the information that the external shape of the target product does not meet the external requirements may be, for example, image information corresponding to a shape that does not meet the external requirements.

[0133] Based on this, the target model can obtain the second information from different types of information carriers and different categories of information, improving the universality of the method.

[0134] In some embodiments, the first mapping relationship is a preset mapping relationship.

[0135] It can be understood that for each independent adverse manifestation, there will be corresponding reasons that may potentially induce the adverse manifestation. Therefore, each adverse manifestation will correspond to one or more occurrence reasons. The corresponding relationship between the adverse manifestation and the occurrence reasons can be understood as the second mapping relationship.

[0136] In some embodiments, words such as "adverse manifestation", "adverse characterization", and "adverse phenomenon" can be replaced with each other.

[0137] The product production method involved in the embodiments of the present disclosure may include at least one of steps S41 to S43. For example, step S41 can be implemented as an independent embodiment, step S42 can be implemented as an independent embodiment, step S41 + step S42 can be implemented as an independent embodiment, and step S41 + step S42 + step S43 can be implemented as an independent embodiment, but is not limited thereto.

[0138] In some embodiments, steps S41 and S42 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0139] In some embodiments, steps S41 and S43 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0140] In some embodiments, steps S42 and S43 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0141] In some embodiments, Figure 5It is a schematic flowchart of a target model training method shown according to an exemplary embodiment. As Figure 5 shown, the method includes the following steps.

[0142] In step S51, a second image is obtained based on the historical production process of the target product. The second image has annotation information, and the annotation information is used to represent a second mapping relationship, where the second mapping relationship is the mapping relationship between production parameters and the shape of the target product.

[0143] In step S52, a basic model is trained based on the second image to obtain a target model.

[0144] The product production method provided by the embodiments of the present disclosure annotates the images obtained during the historical production process of the target product, and then trains the annotated images to enable the model to learn the corresponding relationship between different production parameters and the product shape. Furthermore, the corresponding parameter range can be determined according to the shape state of the current target product, and then parameter adjustment can be performed.

[0145] In some embodiments, when annotating the images obtained during the historical production process of the target product, at least one of the following can be annotated:

[0146] The production parameters corresponding to the target product, whether the target product is a qualified product or the shape information of the target product, etc.

[0147] It can be understood that for the description of production parameters and the shape information of the target product in this embodiment, the relevant descriptions in the above embodiments can be referred to. For the convenience of understanding, they will not be elaborated here one by one.

[0148] In some embodiments, whether the target product is qualified may include at least one of the following: the target product is a qualified product, the target product is a non - qualified product.

[0149] Based on this, since the training samples (i.e., the second images) have the above - mentioned training information, the model can identify and distinguish all the above - mentioned training information during the application process. Thus, it can be realized that when the target model knows the defective phenomenon of the target product, it can timely lock the corresponding cause of generation and adjust the parameters accordingly, thereby improving the defective rate of the target product.

[0150] The product production method involved in the embodiments of the present disclosure may include at least one of step S51 to step S52. For example, step S51 can be implemented as an independent embodiment, step S52 can be implemented as an independent embodiment, and step S51 + step S52 can be implemented as an independent embodiment, but not limited thereto.

[0151] In some embodiments, step S51 is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0152] In some embodiments, step S52 is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0153] Figure 6 is a schematic flow diagram of a method for identifying a target product shown according to an exemplary embodiment, as Figure 6 shown, the method includes the following steps.

[0154] In step S61, a specified area of the target product is detected in the first image to obtain first contour dimension information of the specified area.

[0155] In step S62, second contour dimension information of the first N products of the target product is obtained, where N is an integer greater than or equal to 1.

[0156] In step S63, a variance value is obtained based on the first contour dimension information and the N second contour dimension information.

[0157] In step S64, a quality result corresponding to the target product is calculated through the first contour dimension information and the variance value. If the quality result does not meet the result threshold, it is determined that the target product is a target product whose contour does not meet the contour requirements.

[0158] In some embodiments, the second contour dimension information is the contour dimension corresponding to the specified area of each of the first N products, and each of the first N products corresponds to one second contour dimension information.

[0159] The product production method provided by the embodiments of the present disclosure determines whether the size of the current target product meets the contour requirements based on the variance value corresponding to the contour dimension of the current target product during the production process. It can quickly and accurately identify whether the contour of the target product meets the requirements during the production process, ensuring the stable production of the target product.

[0160] In some embodiments, the specified area of the target product may, for example, be a pre-specified measurement area of the target product.

[0161] Exemplarily, taking motherboard printing as an example, one or more solder printing points in the printed motherboard may be specified as the specified area. Then the first contour dimension can also be understood as the solder height dimension, volume dimension, etc. of the specified area such as the solder.

[0162] In some embodiments, the contour dimension information corresponding to each produced target product is obtained, and based on this information, the second contour dimension information of the first N products of the target product is obtained.

[0163] Exemplarily, continuing with the motherboard printing embodiment, during the motherboard printing process, the size information of each specified area of the motherboard printing is obtained and recorded and stored in a specified storage unit. In this way, the second outer dimension information of the first N products of the target product can be obtained.

[0164] It can be understood that the result of variance calculation requires at least two sets of data to be achieved. Therefore, the value of N needs to be greater than or equal to 1.

[0165] It should be noted that if the target product is the first product to be produced, only the outer dimension information is obtained, and the variance calculation is not performed. Or a trial production (production with a smaller production quantity) is carried out before the formal production, and the variance value is calculated based on the outer dimension data of the trial production.

[0166] In some embodiments, based on the first outer dimension information and the variance value, the corresponding quality result is calculated, including:

[0167] Based on the first dimension information and the variance value, the process capability index corresponding to the target product is calculated.

[0168] In some embodiments, the setting of the result threshold can be an absolute threshold or a relative threshold.

[0169] It can be understood that the absolute threshold can be understood as a constant threshold. For example, a certain value or a certain value range is fixed.

[0170] Exemplarily, continuing with the motherboard printing embodiment, when the result threshold is an absolute threshold and the quality result is the process capability index, if the quality result is less than the result threshold, it can be understood that the process capability index corresponding to the current target product is less than a fixed index threshold (for example, less than 1.33), then it is considered that the outer shape of the current target product does not meet the outer shape requirements, that is, the current target product is a target product that does not meet the outer shape requirements.

[0171] It can be understood that the relative threshold can be understood as a changing threshold. For example, the process capability index corresponding to the previous target product of the current target product can be used as the result threshold, or the process capability index corresponding to the previous M products of the current target product can be used as the result threshold (where M is an integer greater than 1).

[0172] Exemplarily, continuing with the motherboard printing embodiment, when the result threshold is the change threshold and the quality result is the process capability index, if the process capability index corresponding to the first M products before the current target product is less than the quality result (numerically less than, or the difference between the two is greater than a certain threshold), it is considered that the shape of the current target product does not meet the shape requirements, that is, the current target product is a target product that does not meet the shape requirements.

[0173] It should be noted that since the process capability index is calculated through variance. And each target product corresponds to its own variance, so each product will correspond to an independent process capability index.

[0174] It can be understood that the quality result can also be characterized by the variance value.

[0175] In the case where the quality result is characterized by the variance value, the result threshold can be understood as the variance result threshold. When the quality result is greater than the result threshold, it indicates that the shape size of the current target product has fluctuated greatly compared to the shape sizes of the previous products. Therefore, in some cases, it can be determined as a target product that does not meet the shape requirements.

[0176] For the case where the result threshold is the variance result threshold, the comparison between the quality result and the result threshold can refer to the corresponding embodiments above and will not be elaborated here one by one.

[0177] It should be noted that in the embodiments of the present disclosure, by way of example, the process capability index and variance are used to evaluate whether the size of the target product meets the shape requirements. This is an exemplary listing rather than an exhaustive one, and other related evaluation methods are also within the scope of protection involved in the embodiments of the present disclosure.

[0178] The product production method involved in the embodiments of the present disclosure may include at least one of steps S61 to S63. For example, step S61 can be implemented as an independent embodiment, step S62 can be implemented as an independent embodiment, step S61 + step S62 can be implemented as an independent embodiment, and step S61 + step S62 + step S63 can be implemented as an independent embodiment, but not limited thereto.

[0179] In some embodiments, steps S61 and S62 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0180] In some embodiments, steps S61 and S63 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0181] In some embodiments, step S62 and step S63 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0182] Figure 7 is a flowchart of a method for producing a product according to an exemplary embodiment. Figure 7 As shown, the method includes the following steps.

[0183] In step S71, the appearance detection result of the target product and the production information corresponding to the target product are obtained.

[0184] In step S72, a first image is acquired.

[0185] In step S73, the appearance detection result of the target product and the production parameters corresponding to the target product are used as the annotation information of the first image.

[0186] The product production method provided in the embodiment of the present disclosure uses the detection results and production information of the target product as the annotation information of the image, so that the annotated image can be used as the second image for model training.

[0187] In some embodiments, the production information includes: historical information corresponding to the target product and production parameters corresponding to the target product.

[0188] In some embodiments, the appearance detection result includes: the appearance detection is qualified, or the appearance detection is unqualified.

[0189] In some embodiments, the first image is an image including a target product.

[0190] Exemplarily, following the motherboard printing embodiment, during the motherboard printing process, the production information corresponding to the printed motherboard will be counted, such as production parameters, production time, and first external dimension information corresponding to the motherboard. The production information may include the production history of the product (e.g., whether the test result is qualified, whether it has been reworked and repaired if the test result is unqualified, etc.). The production parameters may include the process parameters in the above embodiments, and / or the environmental parameters of the target product production process.

[0191] After the target product production information and the judgment result are labeled on the first image, the labeled first image can be used as the second image for model training, so that the model can obtain labeled training samples based on previous production information.

[0192] The product production method involved in the embodiments of the present disclosure may include at least one of steps S71 to S73. For example, step S71 can be implemented as an independent embodiment, step S72 can be implemented as an independent embodiment, step S71 + step S72 can be implemented as an independent embodiment, and step S71 + step S72 + step S73 can be implemented as an independent embodiment, but not limited thereto.

[0193] In some embodiments, steps S71 and S72 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0194] In some embodiments, steps S71 and S73 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0195] In some embodiments, steps S72 and S73 are optional, and one or more of these steps can be omitted or replaced in different embodiments. In some embodiments, the embodiments of the present disclosure also propose a target product production method, which is applied to the field of motherboard printing. Through the target product method provided by the embodiments of the present disclosure, it is possible to quickly locate production problems during the motherboard printing production process, reduce the time cost of manual labor, and improve production efficiency. And it is possible to perform dynamic parameter adjustment of the system to achieve production automation. Furthermore, it can improve the motherboard printing yield and ensure product quality.

[0196] Figure 8 is a schematic flowchart of a product production method shown according to an exemplary embodiment, as Figure 8 shown. In some embodiments, it is mainly divided into two parts. The first part is the offline analysis and modeling part, and the second part is the prior application part.

[0197] In the first part, it is mainly necessary to perform new training on the model to be issued. For the training samples of the model, the production data can be collected (i.e., the data collection part in the figure) and the historical data can be obtained (i.e., the historical data part in the figure).

[0198] It can be understood that for the data collection part and the historical data acquisition part, the data of defective products during the production process or the data of defective products in the historical data can be obtained. And the main factors and interference factors for the occurrence of defective products are manually marked and analyzed (i.e., the data analysis part in the figure).

[0199] When the collected data accumulates to a certain extent, it is used as a training sample to iteratively train the basic model. The purpose is to enable the trained model to be able to match the corresponding causes of defective products after identifying the defective state of the product, so that the model can adjust parameters.

[0200] After the model is trained, the model is sent to production devices, that is, deployed to production terminals.

[0201] For the online application part, during the production process of the target product, the target product can be detected by the built-in detection system of the device and quality analysis can be performed to determine whether there are quality problems with the produced product.

[0202] When there are quality problems with the produced product or it does not meet the preset standards, the device issues a quality warning. In response to the quality warning of the device, the deployed model performs cause analysis and recommends a parameter adjustment plan based on the analyzed cause, and then performs parameter adjustment. The production device completes production based on the adjusted parameters, thereby improving the defective rate of the product.

[0203] Based on the same concept, the embodiments of the present disclosure also provide a product production device.

[0204] It can be understood that in order to implement the above functions, the product production device provided by the embodiments of the present disclosure includes the corresponding hardware structures and / or software modules for executing each function. Combining the units and algorithm steps of the examples disclosed in the embodiments of the present disclosure, the embodiments of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the technical solution of the embodiments of the present disclosure.

[0205] Figure 9 It is a block diagram of a product production device 100 shown according to an exemplary embodiment. Refer to Figure 9 , the device includes a detection unit 101 and a processing unit 102.

[0206] The detection unit 101 is used to perform shape detection on the target product during the printing process of the main board, where the target product is the printed main board.

[0207] The processing unit 102 is used to call the target model to adjust the production parameters in response to the shape of the target product not meeting the shape requirements.

[0208] The processing unit 102 is further used to produce subsequent target products based on the adjusted production parameters so that the shapes of the subsequent target products meet the preset shape requirements.

[0209] In some embodiments, the processing unit 102 calls the target model to adjust production parameters in the following manner: Based on the shape detection result of the target product, determine first information, where the first information characterizes the cause of the shape of the target product not meeting the shape requirements; and adjust the production parameters based on the first information.

[0210] In some embodiments, the processing unit 102 adjusts the production parameters based on the first information in the following manner: Based on the first information, determine the parameter category to be adjusted and the numerical adjustment range of the parameter; and perform parameter adjustment based on the parameter category and the numerical adjustment range of the parameter.

[0211] In some embodiments, the processing unit 102 determines the first information based on the shape detection result of the target product in the following manner: Obtain a first image, where the first image is an image including the target product; in the first image, identify the target product whose shape does not meet the shape requirements, and determine second information, where the second information is the shape information of the target product that does not meet the shape requirements; and determine the first information based on the first mapping relationship, where the first mapping relationship is the mapping relationship between the second information and the cause of the second information.

[0212] In some embodiments, the target model is trained in the following manner: Obtain a second image based on the historical production process of the target product, where the second image has annotation information, and the annotation information is used to characterize the second mapping relationship, where the second mapping relationship is the mapping relationship between the production parameters and the shape of the target product; and train the basic model based on the second image to obtain the target model.

[0213] In some embodiments, the processing unit 102 identifies the target product whose shape does not meet the requirements in the following manner: Detect the specified area of the target product in the first image to obtain the first shape dimension information of the specified area; obtain the second shape dimension information of the first N products of the target product, where the second shape dimension information is the shape dimension corresponding to the specified area of each of the first N products, and each of the first N products corresponds to one second shape dimension information, where N is an integer greater than or equal to 1; obtain a variance value based on the first shape dimension information and the N second shape dimension information; calculate the quality result corresponding to the target product through the first shape dimension information and the variance value, and if the quality result is greater than the result threshold, determine that the target product is the target product whose shape does not meet the requirements.

[0214] In some embodiments, the processing unit is further configured to obtain the shape detection result of the target product and the production information corresponding to the target product, where the production information includes the resume information corresponding to the target product and the production parameters corresponding to the target product; obtain a first image, where the first image is an image including the target product; and use the shape detection result of the target product and the production parameters corresponding to the target product as the annotation information of the first image.

[0215] In some embodiments, the parameter categories include: process parameters of the target product and / or environmental parameters during the production process of the target product.

[0216] Figure 10 FIG. 6 is a block diagram of an apparatus 200 for product production according to an exemplary embodiment. For example, the apparatus 200 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0217] Referring to Figure 10 , the product production apparatus 200 may include one or more of the following components: a processing component 202, a memory 204, a power component 206, a multimedia component 208, an audio component 210, an input / output (I / O) interface 212, a sensor component 214, and a communication component 216.

[0218] The processing component 202 generally controls the overall operation of the apparatus 200, such as operations associated with display, telephone calls, data communication, camera operations, and recording operations. The processing component 202 may include one or more processors 220 to execute instructions to complete all or part of the steps of the above-described method. In addition, the processing component 202 may include one or more modules to facilitate the interaction between the processing component 202 and other components. For example, the processing component 202 may include a multimedia module to facilitate the interaction between the multimedia component 208 and the processing component 202.

[0219] The memory 204 is configured to store various types of data to support the operation of the apparatus 200. Examples of such data include instructions for any application or method operating on the apparatus 200, contact data, phone book data, messages, pictures, videos, etc. The memory 204 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.

[0220] The power component 206 provides power to various components of the apparatus 200. The power component 206 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the apparatus 200.

[0221] The multimedia component 208 includes a screen that provides an output interface between the device 200 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 208 includes a front camera and / or a rear camera. When the device 200 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.

[0222] The audio component 210 is configured to output and / or input audio signals. For example, the audio component 210 includes a microphone (MIC) that is configured to receive external audio signals when the device 200 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 204 or transmitted via the communication component 216. In some embodiments, the audio component 210 further includes a speaker for outputting audio signals.

[0223] The I / O interface 212 provides an interface between the processing component 202 and a peripheral interface module, which can be a keyboard, a click wheel, buttons, etc. These buttons can include but are not limited to: a home button, a volume button, a power button, and a lock button.

[0224] The sensor component 214 includes one or more sensors for providing a status assessment of various aspects of the device 200. For example, the sensor component 214 can detect the on / off state of the device 200, the relative positioning of components, such as the display and the keypad of the device 200. The sensor component 214 can also detect a change in the position of the device 200 or a component of the device 200, the presence or absence of user contact with the device 200, the orientation or acceleration / deceleration of the device 200, and the temperature change of the device 200. The sensor component 214 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor component 214 can also include a light sensor, such as a CMOS or a CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 214 can further include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0225] The communication component 216 is configured to facilitate communication, either in a wired or wireless manner, between the device 200 and other devices. The device 200 can access a communication standard-based wireless network, such as WiFi, 2G, or 3G, or a combination thereof. In an exemplary embodiment, the communication component 216 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 216 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0226] In an exemplary embodiment, the device 200 can be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described method.

[0227] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as the memory 204 including instructions that can be executed by the processor 220 of the device 200 to complete the above-described method. For example, the non-transitory computer-readable storage medium can be a ROM, Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0228] Figure 11 is a block diagram of a device 300 for product production shown in accordance with an exemplary embodiment. For example, the device 300 can be provided as a server. Referring to Figure 11 , the device 300 includes a processing component 322, which further includes one or more processors, and memory resources represented by a memory 332 for storing instructions executable by the processing component 322, such as application programs. The application programs stored in the memory 332 can include one or more modules each corresponding to a set of instructions. In addition, the processing component 322 is configured to execute instructions to perform the above-described screen display method

[0229] The device 300 may further include a power component 326 configured to perform power management of the device 300, a wired or wireless network interface 350 configured to connect the device 300 to a network, and an input / output (I / O) interface 358. The device 300 can operate based on an operating system stored in the memory 332, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

[0230] It is understood that in this disclosure, "a plurality of" means two or more, and other quantifiers are similar. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after. The singular forms of "a", "the", and "said" are also intended to include the plural forms unless the context clearly indicates otherwise.

[0231] It can be further understood that terms such as "first", "second", etc. are used to describe various information, but this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other and do not represent a specific order or degree of importance. In fact, expressions such as "first" and "second" can be used interchangeably. For example, without departing from the scope of this disclosure, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information.

[0232] It can be further understood that the orientation or positional relationship indicated by terms such as "center", "longitudinal", "transverse", "front", "rear", "upper", "lower", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing this embodiment 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.

[0233] It can be further understood that unless otherwise specified, "connection" includes direct connection with no other components between the two, and also includes indirect connection with other elements between the two.

[0234] It can be further understood that although the operations are described in a specific order in the drawings in the embodiments of this disclosure, it should not be understood as requiring these operations to be performed in the specific order shown or in a serial order, or requiring all the operations shown to obtain the desired result. In a specific environment, multitasking and parallel processing may be beneficial.

[0235] Those skilled in the art will readily think of other embodiments of this disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common general knowledge or conventional technical means in the technical field not disclosed in this disclosure.

Claims

1. A product production method, characterized in that, Including: During the printing process of the main board, perform shape detection on the target product, where the target product is the printed main board; In response to the shape of the target product not meeting the shape requirements, call the target model to adjust the production parameters; Produce the subsequent target product based on the adjusted production parameters so that the shape of the subsequent target product meets the preset shape requirements.

2. The product production method according to claim 1, characterized in that, The calling of the target model to adjust the production parameters includes: Based on the shape detection result of the target product, determine the first information, where the first information characterizes the cause of the shape of the target product not meeting the shape requirements; Adjust the production parameters based on the first information.

3. The product production method according to claim 2, characterized in that, The adjusting the production parameters based on the first information includes: Based on the first information, determine the parameter category to be adjusted and the numerical adjustment range of the parameter; Based on the parameter category and the numerical adjustment range of the parameter, perform parameter adjustment.

4. The product production method according to claim 2, characterized in that, The determining the first information based on the shape detection result of the target product includes: Obtain a first image, where the first image is an image including the target product; In the first image, identify the target product whose shape does not meet the shape requirements, and determine the second information, where the second information is the shape information of the target product that does not meet the shape requirements; Determine the first information based on the first mapping relationship, where the first mapping relationship is the mapping relationship between the second information and the cause of the occurrence of the second information.

5. The product production method according to claim 1, characterized in that, The target model is trained in the following manner: Based on the historical production process of the target product, obtain a second image, where the second image has annotation information, and the annotation information is used to characterize the second mapping relationship, where the second mapping relationship is the mapping relationship between the production parameters and the shape of the target product; Train the basic model based on the second image to obtain the target model.

6. The product production method according to claim 4, characterized in that, The identifying the target product whose shape does not meet the shape requirements includes: Detect the specified area of the target product in the first image to obtain the first shape size information of the specified area; Obtain the second shape size information of the first N products of the target product, where the second shape size information is the shape size corresponding to the specified area of each of the first N products, and each of the first N products corresponds to a second shape size information, where N is an integer greater than or equal to 1; Obtain a variance value based on the first shape size information and the N second shape size information; Calculate the quality result corresponding to the target product through the first shape size information and the variance value, If the quality result does not meet the result threshold, determine that the target product is a target product whose shape does not meet the shape requirements.

7. The product production method according to claim 1, characterized in that, After the shape detection of the target product, it further includes: Obtain the shape detection result of the target product and the production information corresponding to the target product, where the production information includes the resume information corresponding to the target product and the production parameters corresponding to the target product; Obtain a first image, where the first image is an image including the target product; Use the shape detection result of the target product and the production parameters corresponding to the target product as the annotation information of the first image.

8. The product production method according to claim 3, characterized in that, The parameter categories include: the process parameters of the target product, and / or the environmental parameters during the production process of the target product.

9. A product production device, characterized in that, Include: A detection unit for performing shape detection on a target product during the printing of a main board, where the target product is the printed main board; A processing unit for calling a target model to adjust production parameters in response to the shape of the target product not meeting the shape requirements; The processing unit is further configured to produce subsequent target products based on the adjusted production parameters, so that the shapes of the subsequent target products meet the preset shape requirements.

10. A product production device, characterized in that, Include: A memory for storing processor-executable commands; Wherein, the processor is configured to execute the product production method according to any one of claims 1 to 8.

11. A storage medium, the storage medium stores instructions, characterized in that, When the instructions run on the device, the device is caused to execute the product production method according to any one of claims 1 to 8.

Images