A data processing method and quality management system in product testing process

Abstract

The present application relates to a data processing method and quality management system in a product inspection process, the method comprising obtaining a data packet sent by a terminal, the data packet comprising a position number, an object number and a detection result image; processing the detection result image once, identifying a detection result image that cannot be used directly, and recording it as a detection result image to be processed; reconstructing the resolution and filling the content of the detection result image to be processed, and converting the detection result image to be processed into a detection result image; identifying the content in the detection result image, recording it as the detection result and storing the position number, object number and detection result. The data processing method and quality management system in a product inspection process disclosed in the present application divert the obtained images, reconstruct the resolution and fill the content of the images whose content cannot be directly identified, and then perform content identification processing to ensure the accuracy of the identified content.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method and a quality management system in a product testing process. Background Art

[0002] The quality management system is a structured system that regulates and guides the quality management activities within an organization through a series of documents, procedures and processes. In a specific usage scenario, the quality management system can automatically collect, organize and analyze data from the company's production inspection process (incoming materials, storage, processing, inspection, packaging, and delivery), and can identify problems and point out where they are.

[0003] To realize the above process, it is necessary to modify the communication function of the equipment or the current equipment has communication function, so that the automatic upload of data can be realized. However, for factories that have already started production, it is difficult to implement the modification. On the one hand, new equipment needs to be added, and on the other hand, some equipment cannot be modified for communication function due to its own reasons.

[0004] In order to solve this problem, an auxiliary data collection method was adopted, that is, to collect detection data by adding additional collection terminals. However, due to the influence of the factory environment and related shooting parameters, the obtained image quality cannot be kept stable. Relying solely on OCR recognition, there are problems of slow recognition speed and recognition error, which will lead to storage data errors and increase the difficulty of discovering problems and pointing out their locations. Summary of the invention

[0005] The present application provides a data processing method and quality management system in a product inspection process, which diverts the obtained images, reconstructs the resolution and fills the content of the images whose content cannot be directly identified, and then performs content identification processing to ensure the accuracy of the identified content.

[0006] The above-mentioned purpose of the present application is achieved through the following technical solutions:

[0007] In a first aspect, the present application provides a data processing method in a product testing process, comprising:

[0008] Obtaining a data packet sent by the terminal, the data packet including a location number, an object number, and a detection result image;

[0009] Process the detection result image once, identify the detection result image that cannot be used directly, and record it as the detection result image to be processed;

[0010] Perform resolution reconstruction and content filling processing on the detection result image to be processed, and convert the detection result image to be processed into a detection result image;

[0011] Identify the content in the detection result image and record it as the detection result;

[0012] The position number, object number and detection result are stored.

[0013] In a possible implementation manner of the first aspect, a data packet includes a plurality of detection result images, and when performing resolution reconstruction and content filling processing on the detection result image to be processed, the plurality of detection result images in the data packet are combined into one detection result image;

[0014] The synthesis methods include splicing processing and overlay processing.

[0015] In a possible implementation manner of the first aspect, reconstructing the resolution of the detection result image to be processed includes:

[0016] Identify a content area in the detection result image to be processed, where the number of the content areas is multiple;

[0017] Perform grayscale processing on the content area to obtain fuzzy characters;

[0018] Determine the primary edge of the fuzzy character;

[0019] Establishing a reconstruction region on the primary edge of the blurred character and determining a peak line of the reconstruction region;

[0020] Connect the obtained peak lines sequentially to obtain secondary edges;

[0021] Use secondary edges to replace ambiguous characters in the content area.

[0022] In a possible implementation manner of the first aspect, establishing a reconstruction area on a primary edge of the ambiguous character and determining a reconstructed peak line includes:

[0023] Sequentially divide the primary edge of the fuzzy character to obtain the reconstructed area;

[0024] Draw basic peak lines using pixel points inside the reconstruction area. There are multiple basic peak lines, and the values ​​of the pixel points on each basic peak line are the same or similar.

[0025] Merge multiple basic peak lines to obtain a peak line;

[0026] The value of a pixel is the average value of the pixel and its surrounding pixels.

[0027] The surrounding pixels participating in the mean calculation do not participate in the drawing of the basic peak line.

[0028] In a possible implementation manner of the first aspect, after obtaining the peak line, the method further includes removing a low-frequency portion of the peak line.

[0029] In a possible implementation manner of the first aspect, performing content filling processing on the detection result image to be processed includes:

[0030] Determine a content-free region and character contents associated with the content-free region, where the number of character contents is two or more;

[0031] Construct a filling curve based on the first character content;

[0032] The trajectory prediction based on the filling curve extends the filling curve based on the symmetry line until the filling curve touches other character contents;

[0033] When the filling curve extended based on the symmetry line contacts multiple character contents, only the filling curve extended based on the symmetry line with the shortest extension distance is retained.

[0034] In a possible implementation manner of the first aspect, predicting the trajectory based on the filling curve and extending the filling curve based on the symmetry line includes:

[0035] Selecting a character feature region on the character content associated with the content-free region;

[0036] Determine the symmetry line of the character feature area;

[0037] Selecting first prediction points at intervals on the symmetry line of the character feature region, with the first prediction points being at equal distances;

[0038] Calculate the change trend of the coordinates of the first prediction point on the sequential sequence;

[0039] Creating a second prediction point according to a change trend of the coordinates of the first prediction point;

[0040] The filling curve is extended based on the symmetry line, and the extended filling curve passes through each second prediction point sequentially.

[0041] In a second aspect, the present application provides a data processing device in a product detection process, comprising:

[0042] A data communication unit, used to obtain a data packet sent by the terminal, the data packet including a position number, an object number and a detection result image;

[0043] A primary processing unit, used to process the detection result image once, identify the detection result image that cannot be used directly, and record it as the detection result image to be processed;

[0044] A secondary processing unit is used to perform resolution reconstruction and content filling processing on the detection result image to be processed, and convert the detection result image to be processed into a detection result image;

[0045] A content recognition unit, used to recognize the content in the detection result image, recorded as the detection result;

[0046] The content storage unit is used to store the position number, object number and detection result.

[0047] In a third aspect, the present application provides a quality management system, the system comprising:

[0048] one or more memories for storing instructions; and

[0049] One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.

[0050] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium comprising:

[0051] Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0052] In a fifth aspect, the present application provides a computer program product, comprising program instructions. When the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0053] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0054] The chip system may be composed of chips, or may include chips and other discrete devices.

[0055] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a step flow diagram of a data processing method provided by this application.

[0057] Figure 2This is a schematic diagram of the sending path of a data packet in a quality management process provided by this application.

[0058] Figure 3 It is a schematic diagram of the processing process of a detection result image provided by this application.

[0059] Figure 4 This is a schematic diagram of a primary edge and a secondary edge provided by the present application.

[0060] Figure 5 This is a schematic diagram of the process of creating a basic peak line provided by this application.

[0061] Figure 6 This is a schematic diagram of a filling curve based on a symmetry line extension provided by the present application. DETAILED DESCRIPTION

[0062] The technical solution in this application is further described in detail below in conjunction with the accompanying drawings.

[0063] This application discloses a data processing method in the process of product testing. Figure 1 In some examples, the data processing method in the product detection process disclosed in this application includes the following steps:

[0064] S101, obtaining a data packet sent by a terminal, the data packet including a location number, an object number and a detection result image;

[0065] S102, processing the detection result image once, identifying a detection result image that cannot be used directly, and recording it as a detection result image to be processed;

[0066] S103, performing resolution reconstruction and content filling processing on the detection result image to be processed, and converting the detection result image to be processed into a detection result image;

[0067] S104, identifying the content in the detection result image and recording it as the detection result;

[0068] S105, storing the position number, object number and detection result.

[0069] Overall, the data processing method in the product inspection process disclosed in this application is applied to a quality management system, which consists of a data acquisition terminal and a server. The data acquisition terminal is deployed at the data collection location and sends image data to the server for processing by taking pictures. The server recognizes the content in the image data and stores it in the system for display and analysis of related content.

[0070] In terms of product quality, it can provide key information such as pass rate, unqualified location (factory), defect location (product, process), etc. It can also count the changing trends of unqualified location (factory) and defect location (product, process), and determine the specific cause of the problem, such as equipment reasons, inspection personnel reasons, inspection equipment reasons, etc., to help factories improve product quality.

[0071] In step S101, the server obtains a data packet sent by the terminal, which includes a location number, an object number, and a detection result image. Figure 2 The terminal here refers to the data acquisition terminal recorded in the previous text, the position number refers to the location of the data acquisition terminal, the object number refers to the detection object at the location of the data acquisition terminal, and the detection result image refers to the image obtained by the data acquisition terminal.

[0072] For object numbering, one implementation method is to directly assign a code to the surface of the product, and the object number can be obtained by reading the code; another implementation method is to add a coding device at the location of the data collection end, and the coding device directly displays the object number.

[0073] In step S102, refer to Figure 3 , the detection result images will be processed once, and the detection result images that cannot be used directly will be identified and recorded as detection result images to be processed. The purpose of one processing is to group the detection result images, one group is the detection result images that can be directly used for identification, and the other group is the detection result images that cannot be used directly. The detection result images that cannot be used directly are recorded as detection result images to be processed.

[0074] In step S103, the detection result image to be processed will be subjected to resolution reconstruction and content filling processing. The purpose of resolution reconstruction is to improve clarity, and the purpose of content filling processing is to fill in the vacant areas. After these two processing methods, the detection result image to be processed can be converted into a detection result image.

[0075] In step S104, the content in the detection result image is identified and recorded as the detection result, and finally in step S105, the position number, object number and detection result are stored. In this way, the complete detection record process of a product is completed, and a complete detection record process includes the detection process and the detection result at each detection process.

[0076] In general, the data processing method in the product testing process provided in this application can achieve the acquisition of full-process quality management data of the product without the need for major factory modifications and equipment updates, and the acquired data can be used for process analysis and result analysis.

[0077] In some examples, a data packet includes multiple detection result images. When performing resolution reconstruction and content filling processing on the detection result images to be processed, the multiple detection result images in one data packet are combined into one detection result image, which can save the amount of calculation.

[0078] It should be understood that in the process of shooting the detection result image, the specific parameters of each detection result image are inconsistent, such as light changes, focus changes, and device jitter. In order to solve this problem, the present application adopts the method of shooting multiple detection result images for processing. If the detection result image to be processed needs to be reconstructed in resolution and filled with content, multiple detection result images in a data packet are combined into one detection result image, that is, the available parts of the detection result image are pieced together to reduce the processing time of resolution reconstruction and content filling.

[0079] Because in the assembly line production process, too long processing time will cause data compression, resulting in untimely result updates.

[0080] There are two synthesis methods: stitching and overlay. Stitching is to crop the detection result image, retain the useful parts, and then synthesize these useful parts into a new detection result image; overlay is to directly merge multiple detection result images.

[0081] The premise of splicing is clarity judgment. In this application, the main focus is on character detection. One feasible method is to first identify the characters and then detect only the characters. The detection method is as follows:

[0082] Tenengrad gradient method: Use the Sobel operator to calculate the gradients in the horizontal and vertical directions respectively. In the same scene, the higher the gradient value, the clearer the image.

[0083] Variance method: Variance is a measurement method used in probability theory to examine the discrete (deviation) between a set of discrete data and its expectation (i.e., the mean of the data). A clearly focused image should have a larger grayscale difference between its data than a blurred image, that is, its variance should be larger. The image clarity can be measured by the variance of the image grayscale data. The larger the variance, the better the clarity.

[0084] The above detection methods are only examples and are not limitations of the present application. In addition to the above detection methods, other detection methods may also be used for detection.

[0085] The recognition of the detection result image to be processed is also carried out through clarity judgment. Specifically, multiple areas are randomly selected on the detection result image for clarity judgment. When the number of unclear areas exceeds the set allowed number or the proportion exceeds the set allowed ratio, the detection result image is recorded as the detection result image to be processed.

[0086] Under the premise that it is difficult to recognize characters, a color picking method can be used because there is a clear difference between the characters and the background on the display interface, and the background on the display interface is single.

[0087] Based on the above content, after the unclear characters are recognized, they are replaced by characters on other detection result images. Considering the processing speed, for one character, generally 3-5 judgment points are selected on the character.

[0088] If all the judgment points are unclear, characters on other detection result images are used as replacements.

[0089] When the stitching process is completed, if there are still unclear characters, they are processed by superposition. Specifically, the same character on multiple detection result images is fused to retain more information.

[0090] In some examples, the specific method of reconstructing the resolution of the detection result image to be processed is:

[0091] S201, identifying a content area in the detection result image to be processed, where the number of the content areas is multiple;

[0092] S202, grayscale processing is performed on the content area to obtain fuzzy characters;

[0093] S203, determining a primary edge of the fuzzy character;

[0094] S204, establishing a reconstruction area on the primary edge of the fuzzy character and determining a peak line of the reconstruction area;

[0095] S205, sequentially connecting the obtained peak lines to obtain secondary edges;

[0096] S206: Use secondary edges to replace the ambiguous characters in the content area.

[0097] In steps S201 to S206, super-resolution reconstruction is directly performed on the character edges in the detection result image to be processed. This is mainly based on the consideration of data processing volume and data processing speed. The characters in the detection result image to be processed are mainly detection items (text) and detection values ​​(numbers), which are referred to as characters here. If only the character edges are super-resolution reconstructed instead of all the characters, it is equivalent to discarding the background in the detection result image to be processed and the content inside the character edges. Considering the data volume, the data volume of super-resolution reconstruction of only the character edges is 1%-3% of the super-resolution reconstruction of the detection result image to be processed.

[0098] In step S201, the content area in the detection result image to be processed is first identified. The content area is the area where the characters are located. Then, in step S202, the content area is grayscale processed to obtain fuzzy characters. The purpose of grayscale processing is also to reduce the amount of data processing.

[0099] Next, in step S203, the primary edge of the fuzzy character is determined. Here, the primary edge of the fuzzy character refers to the approximate edge of the fuzzy character, such as Figure 4 As shown, there is a more obvious color difference on both sides of the primary edge, but it is not accurate, and the secondary edge is the real edge.

[0100] In step S204, a reconstructed area is established on the primary edge of the blurred character and the peak line of the reconstructed area is determined. After obtaining the peak line, the obtained peak lines are connected sequentially to obtain the secondary edge, which is the content in step S205. Finally, the secondary edge is used to replace the blurred characters in the content area.

[0101] From the above content, we can see that the purpose of determining the primary edge of the fuzzy character is to establish a reconstruction area, and then determine the peak line of the reconstruction area. The specific method is as follows:

[0102] Sequentially divide the primary edge of the fuzzy character to obtain the reconstructed area;

[0103] Draw basic peak lines using pixel points inside the reconstruction area. There are multiple basic peak lines, and the values ​​of the pixel points on each basic peak line are the same or similar.

[0104] Merge multiple basic peak lines to obtain a peak line;

[0105] The value of a pixel is the average value of the pixel and its surrounding pixels.

[0106] The surrounding pixels participating in the mean calculation do not participate in the drawing of the basic peak line.

[0107] In the above method, the primary edge of the fuzzy character is divided sequentially, and a plurality of reconstructed regions are obtained. The reconstructed regions are arranged in the order of division.

[0108] Next, the pixel points are used to draw basic peak lines inside the reconstructed area. There are multiple basic peak lines, and the values ​​of the pixels on each basic peak line are the same or similar. The basic peak line represents the edge. After obtaining multiple basic peak lines, they will be merged to obtain the peak line.

[0109] When drawing the basic peak line, pixel points are needed. The value of the pixel points belonging to the same basic peak line is the average of the values ​​of the pixel point and the surrounding pixel points. The purpose of using the average is to reduce the error of the pixel point value.

[0110] It should be understood that in the process of collecting pixel values, there is a collection error, that is, the theoretical value of the pixel is not equal to the actual value of the pixel. In order to reduce the difference between the theoretical value and the actual value, this application uses the average value of the surrounding pixel points of the pixel as the value of the pixel.

[0111] In the above method, the surrounding pixel points participating in the mean value calculation do not participate in the drawing of the basic peak line.

[0112] See also Figure 5 Different basic peak lines use different pixel values, which are generally determined based on the distance between adjacent basic peak lines. Generally, the distance is controlled within 5-8 pixels.

[0113] In some possible implementations, when drawing the basic peak line, the new basic peak line moves toward the direction close to the character until no new basic peak line can be generated, and then the basic peak line far from the character is screened according to the basic peak line closest to the character.

[0114] Because in the direction away from the character, the function of the pixels that can participate in drawing the basic peak line in guiding the shape of the basic peak line is weakened, resulting in an increase in the distortion of the basic peak line. Or it can be described as that in the direction close to the character, the degree of fit between the basic peak line and the corresponding character edge will continue to improve.

[0115] It should be noted here that the obtained basic peak line should be located in the blurred area, such as in the inner area of ​​the character, because the color tends to be uniform, which will result in the inability to generate the basic peak line. Similarly, the basic peak line cannot be generated in the background area.

[0116] In some possible implementations, 3-5 basic peak lines are retained during screening for merging and obtaining peak lines. The basic peak lines are merged by superimposing all the retained basic peak lines on the basic peak line closest to the character.

[0117] In some possible implementations, after obtaining the peak line, the low-frequency portion of the peak line is removed.

[0118] In some examples, the specific method of performing content filling processing on the detection result image to be processed is:

[0119] S301, determining a content-missing region and character contents associated with the content-missing region, wherein the number of the character contents is two or more;

[0120] S302, constructing a filling curve based on the first character content;

[0121] S303, extending the filling curve based on the symmetry line according to the trajectory prediction of the filling curve until the filling curve contacts other character contents;

[0122] When the filling curve extended based on the symmetry line contacts multiple character contents, only the filling curve extended based on the symmetry line with the shortest extension distance is retained.

[0123] See also Figure 6 In step S301 to step S303, first, determine the content missing area and the character content associated with the content missing area, the number of character content is two or more, then build a filling curve based on the first character content, and then extend the filling curve based on the symmetry line until the filling curve contacts other character content.

[0124] When extending the fill curve based on the symmetry line, prediction is required, which is done as follows:

[0125] S401, selecting a character feature region on the character content associated with the content vacancy region;

[0126] S402, determining a symmetry line of the character feature area;

[0127] S403, selecting first prediction points at intervals on the symmetry line of the character feature region, and the distances between the first prediction points are equal;

[0128] S404, calculating the change trend of the coordinates of the first prediction point in the sequential sequence;

[0129] S405, creating a second prediction point according to the change trend of the coordinates of the first prediction point;

[0130] S406, extending the filling curve based on the symmetry line, wherein the extended filling curve passes through each second prediction point in sequence.

[0131] In step S401 to step S405, firstly a character feature region is selected on the character content associated with the content-free region, and then the symmetry line of the character feature region is determined. The symmetry line can be a straight line or a curve, which is specifically determined according to the shape of the character feature region.

[0132] Then, first prediction points are selected at intervals on the symmetry line of the character feature region, and the distances between the first prediction points are equal. Here, the equal distances refer to that the lengths of the symmetry line between two adjacent first prediction points are equal.

[0133] The change trend of the coordinates of the first prediction point is calculated again in the sequential sequence. The coordinates of the first prediction point have two types, namely, abscissa and ordinate. The first method of predicting the change trend of the coordinates is to determine the increase or decrease of the coordinate values ​​(abscissa and ordinate).

[0134] In step S405 and step S406, the second prediction point is created according to the change trend of the coordinates of the first prediction point, and then the filling curve is extended based on the symmetry line. Here, the filling curve to be extended passes through each second prediction point in sequence.

[0135] In some possible implementations, the way to determine the increase or decrease of the coordinate values ​​(horizontal coordinates and vertical coordinates) is to use the existing horizontal coordinates to establish a line segment. At this time, the line segment may be a straight line or a curve. After obtaining the line segment, some points are randomly selected on the line segment. The differences between the horizontal coordinates of these points are equal, and then the difference in the vertical coordinates is calculated.

[0136] After obtaining the difference, the ordinate of the subsequent points can be predicted based on the trend of the difference. This method corresponds to a steady increase or steady decrease in the difference of the ordinate. If the difference sequence at this time has no obvious pattern, then the quadratic difference method is used. The quadratic difference is to calculate the difference between adjacent differences. The difference between adjacent differences can further reveal the change of the difference.

[0137] Of course, the filling curve can also be extended by making it contact with other character contents, that is, first find the destination of the filling curve, then extend the filling curve, and then use the method described in the above content to perform reverse verification.

[0138] After verification is completed, a filling curve with the shortest extension distance is retained.

[0139] The present application also provides a data processing device in a product detection process, comprising:

[0140] A data communication unit, used to obtain a data packet sent by the terminal, the data packet including a position number, an object number and a detection result image;

[0141] A primary processing unit, used to process the detection result image once, identify the detection result image that cannot be used directly, and record it as the detection result image to be processed;

[0142] A secondary processing unit is used to perform resolution reconstruction and content filling processing on the detection result image to be processed, and convert the detection result image to be processed into a detection result image;

[0143] A content recognition unit, used to recognize the content in the detection result image, recorded as the detection result;

[0144] The content storage unit is used to store the position number, object number and detection result.

[0145] Furthermore, a data packet includes a plurality of detection result images, and when performing resolution reconstruction and content filling processing on the detection result image to be processed, the plurality of detection result images in the data packet are combined into one detection result image;

[0146] The synthesis methods include splicing processing and overlay processing.

[0147] Furthermore, it also includes:

[0148] A region identification unit, used to identify a content region in the detection result image to be processed, where the number of the content regions is multiple;

[0149] A grayscale processing unit, used for performing grayscale processing on the content area to obtain fuzzy characters;

[0150] A primary edge unit, used to determine the primary edge of the ambiguous character;

[0151] A peak line generating unit, used for establishing a reconstruction area on a primary edge of the fuzzy character and determining a peak line of the reconstruction area;

[0152] A secondary edge unit is used to sequentially connect the obtained peak lines to obtain secondary edges;

[0153] A replacement unit that replaces ambiguous characters in the content area with a secondary edge.

[0154] Furthermore, it also includes:

[0155] A sequential division unit, used for sequentially dividing the primary edge of the fuzzy character to obtain a reconstructed area;

[0156] A basic peak line drawing unit is used to draw basic peak lines using pixel points inside the reconstruction area. There are multiple basic peak lines, and the values ​​of the pixel points on each basic peak line are the same or similar.

[0157] A merging processing unit, used for merging a plurality of basic peak lines to obtain a peak line;

[0158] The value of a pixel is the average value of the pixel and its surrounding pixels.

[0159] The surrounding pixels participating in the mean calculation do not participate in the drawing of the basic peak line.

[0160] Furthermore, after obtaining the peak line, the low-frequency part of the peak line is removed.

[0161] Furthermore, it also includes:

[0162] A first determining unit is used to determine a content-missing region and character contents associated with the content-missing region, wherein the number of the character contents is two or more;

[0163] A filling curve building unit, used for building a filling curve based on the first character content;

[0164] A filling curve primary extension unit, used for extending the filling curve based on the symmetry line based on the trajectory prediction of the filling curve, until the filling curve contacts other character contents;

[0165] When the filling curve extended based on the symmetry line contacts multiple character contents, only the filling curve extended based on the symmetry line with the shortest extension distance is retained.

[0166] Furthermore, it also includes:

[0167] A selection unit, used for selecting a character feature region on the character content associated with the content vacancy region;

[0168] A second determining unit, used to determine a symmetry line of the character feature area;

[0169] A prediction point selection unit, used for selecting first prediction points at intervals on a symmetry line of the character feature region, wherein the first prediction points are at equal distances;

[0170] A prediction unit, used for calculating a change trend of the coordinates of the first prediction point on the sequential sequence;

[0171] A prediction point creation unit, configured to create a second prediction point according to a change trend of the coordinates of the first prediction point;

[0172] The filling curve secondary extension unit is used to extend the filling curve based on the symmetry line, and the extended filling curve passes through each second prediction point in sequence.

[0173] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0174] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0175] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0176] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0177] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0178] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0179] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0180] It should also be understood that in various embodiments of the present application, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present application.

[0181] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0182] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0183] The present application also provides a quality management system, the system comprising:

[0184] one or more memories for storing instructions; and

[0185] One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0186] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0187] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0188] The chip system may be composed of chips, or may include chips and other discrete devices.

[0189] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0190] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0191] Optionally, the computer instructions are stored in a memory.

[0192] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0193] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0194] The non-volatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0195] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.

[0196] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A data processing method in a product detection process, characterized in that: include: Obtaining a data packet sent by the terminal, the data packet including a location number, an object number, and a detection result image; Process the detection result image once, identify the detection result image that cannot be used directly, and record it as the detection result image to be processed; Perform resolution reconstruction and content filling processing on the detection result image to be processed, and convert the detection result image to be processed into a detection result image; Identify the content in the detection result image and record it as the detection result; storing the position number, object number and detection result; The resolution reconstruction of the detection result image to be processed includes: Identify a content area in the detection result image to be processed, where the number of the content areas is multiple; Perform grayscale processing on the content area to obtain fuzzy characters; Determine the primary edge of the fuzzy character; Establishing a reconstruction region on the primary edge of the blurred character and determining a peak line of the reconstruction region; Connect the obtained peak lines sequentially to obtain secondary edges; Use secondary edges to replace obscure characters in the content area; Establishing a reconstruction area on the primary edge of the fuzzy character and determining the reconstruction peak line includes: Sequentially divide the primary edge of the fuzzy character to obtain the reconstructed area; Draw basic peak lines using pixel points inside the reconstruction area. There are multiple basic peak lines, and the values ​​of the pixel points on each basic peak line are the same or similar. Merge multiple basic peak lines to obtain a peak line; The value of a pixel is the average value of the pixel and its surrounding pixels. The surrounding pixels participating in the mean calculation do not participate in the drawing of the basic peak line.

2. The data processing method in the product detection process according to claim 1 is characterized in that: A data packet includes a plurality of detection result images, and when performing resolution reconstruction and content filling processing on the detection result image to be processed, the plurality of detection result images in the data packet are combined into one detection result image; The synthesis methods include splicing processing and overlay processing.

3. The data processing method in the product detection process according to claim 1 is characterized in that: After obtaining the peak line, the low-frequency part of the peak line is removed.

4. The data processing method in the product detection process according to claim 1 is characterized in that: The content filling process of the detection result image to be processed includes: Determine a content-free region and character contents associated with the content-free region, where the number of character contents is two or more; Construct a filling curve based on the first character content; The trajectory prediction based on the filling curve extends the filling curve based on the symmetry line until the filling curve contacts other character contents; When the filling curve extended based on the symmetry line contacts multiple character contents, only the filling curve extended based on the symmetry line with the shortest extension distance is retained.

5. The data processing method in the product detection process according to claim 4 is characterized in that: Trajectory prediction based on filled curves Extending filled curves based on symmetry lines includes: Selecting a character feature region on the character content associated with the content-free region; Determine the symmetry line of the character feature area; Selecting first prediction points at intervals on the symmetry line of the character feature region, wherein the lengths of the symmetry lines between two adjacent first prediction points are equal; Calculate the change trend of the coordinates of the first prediction point on the sequential sequence; Creating a second prediction point according to a change trend of the coordinates of the first prediction point; The filling curve is extended based on the symmetry line, and the extended filling curve passes through each second prediction point sequentially.

6. A data processing device in a product testing process, characterized in that: include: A data communication unit, used to obtain a data packet sent by the terminal, the data packet including a position number, an object number and a detection result image; A primary processing unit, used to process the detection result image once, identify the detection result image that cannot be used directly, and record it as the detection result image to be processed; A secondary processing unit is used to perform resolution reconstruction and content filling processing on the detection result image to be processed, and convert the detection result image to be processed into a detection result image; A content recognition unit, used to recognize the content in the detection result image, recorded as the detection result; A content storage unit, used for storing the position number, the object number and the detection result; A region identification unit, used to identify a content region in the detection result image to be processed, where the number of the content regions is multiple; A grayscale processing unit, used for performing grayscale processing on the content area to obtain fuzzy characters; A primary edge unit, used to determine the primary edge of the ambiguous character; A peak line generating unit, used for establishing a reconstruction area on a primary edge of the fuzzy character and determining a peak line of the reconstruction area; A secondary edge unit is used to sequentially connect the obtained peak lines to obtain secondary edges; a replacement unit for replacing ambiguous characters in the content area with secondary edges; A sequential division unit, used for sequentially dividing the primary edge of the fuzzy character to obtain a reconstructed area; A basic peak line drawing unit is used to draw basic peak lines using pixel points inside the reconstruction area. There are multiple basic peak lines, and the values ​​of the pixel points on each basic peak line are the same or similar. A merging processing unit, used for merging a plurality of basic peak lines to obtain a peak line; The value of a pixel is the average value of the pixel and its surrounding pixels. The surrounding pixels participating in the mean calculation do not participate in the drawing of the basic peak line.

7. A quality management system, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 5 is executed.

Images