Electrical element wiring diagram identification system using image segmentation technology

Abstract

The invention belongs to the technical field of electrical element wiring identification, and particularly relates to an electrical element wiring diagram identification system utilizing an image segmentation technology, which comprises the following steps of: extracting an original image quality indication and an image quality indication after electrical element segmentation by virtue of a historical identification record of an electrical element wiring diagram; therefore, the sensitive image quality indications of the electrical elements are analyzed and identified according to the fluctuation of the image quality indications, the image processing purpose can be effectively improved, the segmentation efficiency is improved to the maximum extent, and meanwhile, the segmentation duration is predicted by utilizing the electrical elements in the current electrical element wiring diagram, so that the segmentation accuracy is improved. And determining an initial segmentation sequence of the electrical elements according to a prediction result, and performing system resource detection in real time in operation according to the initial segmentation sequence, thereby dynamically adjusting the initial segmentation sequence. According to the method, self-adaptive adjustment based on the limited condition of the system resources can be realized, so that the electrical element segmentation is more in line with the actual condition of the system resources.

Description

Technical Field

[0001] The invention belongs to the technical field of electrical component wiring recognition, and in particular relates to an electrical component wiring diagram recognition system utilizing image segmentation technology. Background Art

[0002] As consumers' demand for electrical products, especially digital products, continues to increase, the demand for the production and assembly of electrical products has also increased significantly. In order to improve production efficiency and quality, modern manufacturing has widely adopted automated production lines, using assembly robots for efficient assembly. In this context, it is particularly important to efficiently identify the wiring diagram of electrical components. By efficiently identifying the wiring diagram of electrical components, automated production lines can quickly and accurately complete assembly tasks, reduce production cycles, and improve overall production efficiency.

[0003] There are usually multiple electrical components in the wiring diagram of electrical components. The identification of electrical components is actually to accurately segment each electrical component from the wiring diagram to determine its specific position and assembly position in the circuit. Image quality has a key impact on the segmentation effect during the segmentation operation of electrical components, because high-quality images can provide more detailed information, reduce noise and distortion, and thus improve the execution efficiency of the segmentation algorithm. Therefore, image quality often needs to be processed during the electrical component segmentation process. However, existing image quality processing methods are usually generalized, without considering the sensitivity of different electrical component segmentation to image quality indicators, resulting in a lack of pertinence in image quality processing. This generalized processing method is prone to waste a lot of time on image quality processing, and may result in the need for secondary processing, thereby increasing processing time and computing resource consumption, and reducing the overall segmentation efficiency.

[0004] In addition, in the existing electrical component segmentation process, certain principles are usually followed, that is, the more complex electrical components are segmented first to ensure the recognition accuracy of these complex components and reduce false detection and missed detection in subsequent processing. However, the segmentation of complex electrical components often consumes a lot of system resources. When the system resources are sufficient, this segmentation order will not cause problems. However, when the system resources are limited, if the complex electrical components are still segmented blindly, it is easy to cause segmentation interruption. On the one hand, it makes the current task unable to be completed and needs to be restarted, which increases the processing time and resource consumption. On the other hand, the segmentation interruption may cause some data loss, which needs to be re-collected and processed, affecting the continuity and integrity of the overall work. Summary of the invention

[0005] In view of this, the present invention aims to propose an electrical component wiring diagram recognition system using image segmentation technology, which can effectively solve the deficiencies in the prior art.

[0006] The purpose of the present invention can be achieved through the following technical solutions: an electrical component wiring diagram recognition system using image segmentation technology, comprising the following modules: a historical recognition record retrieval module, used to retrieve the historical recognition records of the electrical component wiring diagram, and extract the electrical components contained in the electrical component wiring diagram from the historical recognition records.

[0007] The image quality indicator extraction module is used to extract the image quality indicator of the original electrical component wiring diagram from the historical recognition record, recorded as the original image quality indicator, and at the same time extract the image quality indicator of each electrical component after segmentation.

[0008] The segmentation time extraction module is used to extract the segmentation time of each electrical component from the historical recognition record.

[0009] The sensitive image quality indicator analysis module is used to compare the image quality indicators of each electrical component after segmentation in the historical recognition record with the original image quality indicators, thereby analyzing the sensitive image quality indicators of each electrical component.

[0010] The sensitive segmentation association analysis module is used to associate the segmentation duration of the electrical component with the sensitive image quality indicator of the electrical component to obtain the sensitive association of the segmentation duration.

[0011] The current electrical component wiring extraction module is used to obtain the electrical components contained in the current electrical component wiring diagram, and extract the sensitive image quality indicators of each electrical component accordingly.

[0012] The segmentation determination module is used to perform image quality detection on the current electrical component wiring diagram to obtain the original image quality indicator, and combine it with the sensitive image quality indicator of each electrical component and the sensitive correlation of the segmentation time to determine the initial segmentation order and image processing method of the electrical components.

[0013] The segmentation dynamic implementation module is used to perform real-time system resource detection during the segmentation of the current electrical component wiring diagram according to the initial segmentation sequence of the electrical components, and dynamically adjust the initial segmentation sequence of the electrical components according to the system resource detection result.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. The present invention extracts the original image quality indicators and the image quality indicators after electrical component segmentation by means of the historical recognition records of the electrical component wiring diagram, thereby identifying the sensitive image quality indicators of the electrical components based on the fluctuation analysis of the image quality indicators, and providing targeted processing targets for the image processing during the segmentation of each electrical component, which can effectively improve the purposefulness of image processing and provide image background conditions that meet actual needs for the segmentation of electrical components, thereby maximizing the segmentation efficiency.

[0015] The present invention predicts the segmentation duration by using the electrical components in the current electrical component wiring diagram, and determines the initial segmentation order of the electrical components according to the prediction results, and then performs real-time system resource detection in the process of performing segmentation according to the initial segmentation order, and dynamically adjusts the initial segmentation order according to the detection results. This method can realize adaptive adjustment based on the limited system resources, so that the electrical component segmentation is more in line with the actual situation of the system resources, thereby significantly reducing the occurrence rate of segmentation interruption, ensuring the continuity of the segmentation process and the integrity of the image data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 It is a schematic diagram of the connection of each module of the system of the present invention.

[0018] Figure 2 The present invention is a flowchart for analyzing the sensitive image quality indicators of each electrical component.

[0019] Figure 3 It is a schematic diagram for implementing whether to adjust the initial segmentation sequence of electrical components in the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] The present invention proposes an electrical component wiring diagram recognition system using image segmentation technology, including a historical recognition record retrieval module, an image quality indicator extraction module, a segmentation duration extraction module, a sensitive image quality indicator analysis module, a sensitive segmentation association analysis module, a current electrical component wiring extraction module, a segmentation determination module and a segmentation dynamic implementation module.

[0022] See also Figure 1As shown, the above-mentioned historical identification record retrieval module is respectively connected to the image quality indicator extraction module and the segmentation duration extraction module, the image quality indicator extraction module is connected to the sensitive image quality indicator analysis module, the sensitive image quality indicator analysis module and the segmentation duration extraction module are both connected to the sensitive segmentation association analysis module, the sensitive image quality indicator analysis module is connected to the current electrical component wiring extraction module, the current electrical component wiring extraction module and the sensitive segmentation association analysis module are both connected to the segmentation determination module, and the segmentation determination module is connected to the segmentation dynamic implementation module.

[0023] It should be emphasized that the electrical component wiring diagram mentioned in the present invention is generated by computer-specific drawing software. Due to the influence of factors such as the display resolution, graphics rendering algorithm, file format conversion and output device of the computer system, the generated electrical component wiring diagram may have certain differences in image quality.

[0024] As an example, the physical resolution of a computer display determines the clarity of an image. A lower resolution may result in loss of details in the image, affecting the accuracy of identifying electrical components and connecting wires. As another example, the anti-aliasing algorithm used by drawing software when generating images may affect the smoothness of lines. Different anti-aliasing algorithms may result in different clarity of line edges, which in turn affects the recognition of electrical components. As another example, when saving wiring diagrams in different file formats, lossy or lossless compression may be performed. Lossy compression will reduce image quality, while lossless compression can retain more details. The choice of file format directly affects the clarity and recognizability of the image.

[0025] Therefore, the image quality of the electrical component wiring diagram that is not generated by a computer is high-quality and stable, and image processing is required during the electrical component recognition and segmentation.

[0026] The historical identification record retrieval module is used to retrieve the historical identification records of the electrical component wiring diagram and extract the electrical components contained in the electrical component wiring diagram from the historical identification records.

[0027] It is important to know that in the process of identifying the wiring diagram of electrical components, an identification record will be generated, which can be used as a reference for subsequent identification. The identification record usually contains the original image of the wiring diagram of electrical components, the image quality test results (such as resolution, contrast, signal-to-noise ratio, etc.), the segmentation time of each electrical component, the image quality indicator of each electrical component after segmentation, etc. In addition, in the wiring diagram of electrical components, a special area (called "component list" or "symbol description area") is usually reserved for the name and description of the electrical components contained therein, which is convenient for reference and comparison.

[0028] The image quality indicator extraction module is used to extract the image quality indicator of the original electrical component wiring diagram from the historical recognition record, recorded as the original image quality indicator, and at the same time extract the image quality indicator of each electrical component after segmentation.

[0029] In the example of the above scheme, the above-mentioned image quality indicators include but are not limited to resolution, contrast, signal-to-noise ratio, color depth, sharpness, etc.

[0030] Specifically, the resolution of an image refers to the number of pixels per unit length in the image. Generally speaking, high-resolution images contain more detail information, which helps to improve recognition accuracy; low-resolution images may cause loss of details and affect the segmentation effect.

[0031] Contrast refers to the difference in brightness between the brightest and darkest parts of an image. Generally speaking, the boundaries between electrical components and the background in high-contrast images are more obvious, which helps to improve the recognition accuracy of the segmentation algorithm; low-contrast images may cause blurred boundaries and increase the risk of false detection and missed detection.

[0032] The signal-to-noise ratio is the ratio between the target information (i.e., useful signal) and the background noise in the image. Generally speaking, noise will affect the accuracy of segmentation and recognition, especially for electrical components with complex shapes. Noise may change the boundaries of the components, causing shape features to be misidentified or lost.

[0033] Color depth refers to the number of colors that can be represented by each pixel in the image, specifically the number of bits for each color channel (such as red, green, and blue). Color depth determines the types and range of colors that can be displayed in the image. High color depth can represent more color types and provide richer color information. For example, wires of different colors may represent different voltage levels or signal types, and high color depth can ensure that these colors are accurately identified. Low color depth can only represent a limited number of colors, which may result in color distortion or uneven transitions between colors, which may make it difficult to distinguish certain electrical components with similar colors, increasing the risk of recognition errors.

[0034] Sharpness refers to the clarity of the edges in an image, reflecting whether the transition between different areas in the image is smooth. The edges in a high-sharpness image are clearer, which helps improve the recognition accuracy of the segmentation algorithm; the edges in a low-sharpness image may be blurred, affecting the segmentation effect.

[0035] It needs to be explained that after completing the image quality detection of the original electrical component wiring diagram, targeted image processing is required, such as denoising, contrast enhancement, sharpening, etc. to meet the needs of each electrical component identification and segmentation. Since different electrical components have different specific requirements for image quality, the performance of various image quality indicators will be different in the segmented image, which is mainly due to their physical properties, functional complexity, etc. Specifically, the first is that different electrical components have different shapes and sizes. For example, resistors are usually simple cylindrical or rectangular, while integrated circuits may have complex pin arrangements and multi-layer structures. Complex shapes and smaller sizes require higher resolution and edge clarity to ensure accurate identification and segmentation. Therefore, when segmenting resistors, it is necessary to ensure that the image has high resolution and edge clarity.

[0036] Second: The colors and materials of electrical components also vary. Some components (such as colored capacitors and light-emitting diodes LEDs) rely on specific colors for identification, while other components (such as relays with metal housings) may have reflective surfaces and are easily affected by lighting conditions. High color depth is essential for the identification of these components. Therefore, when segmenting colored capacitors, it is necessary to ensure that the image has a high color depth.

[0037] Third: Some electrical components (such as high-frequency oscillators and radio frequency components) are very sensitive to noise, and any slight interference may affect their performance. Therefore, when identifying and segmenting these components, it is necessary to minimize the noise in the image and maintain a high signal-to-noise ratio to ensure its accuracy and stability. Under this segmentation requirement, if the original electrical component wiring diagram does not have such an image quality indicator, it is necessary to perform targeted image processing when segmenting the corresponding electrical components to meet the segmentation requirements.

[0038] The segmentation duration extraction module is used to extract the segmentation duration of each electrical component from the historical recognition record. The specific operation is as follows: extract the electrical component, initial segmentation time and end segmentation time of each segmentation from the historical recognition record.

[0039] The end segmentation time of each segmentation of the electrical component is compared with the initial segmentation time to obtain the segmentation time of each electrical component in the historical recognition record.

[0040] The sensitive image quality indicator analysis module is used to compare the image quality indicators of each electrical component after segmentation in the historical recognition record with the original image quality indicators, thereby analyzing the sensitive image quality indicators of each electrical component, see Figure 2As shown, the specific analysis is as follows: the image quality indicator after segmentation of each electrical component in each historical recognition record is compared with the original image quality indicator to obtain the image quality indicator contrast difference, and the absolute value of the image quality indicator contrast difference is taken and divided by the original image quality indicator to obtain the image quality indicator fluctuation degree after segmentation of each electrical component.

[0041] The electrical components existing in all historical identification records are classified to form a plurality of historical identification records corresponding to each electrical component.

[0042] The fluctuations of the image quality indicators of the same electrical component after segmentation in each historical identification record are compared, and the image quality indicator corresponding to the maximum fluctuation is selected as the sensitive image quality indicator of the same electrical component in each historical identification record.

[0043] It is necessary to explain again that if an image quality indicator fluctuates significantly after a certain electrical component is segmented, this indicates that more intensive processing was performed on the indicator when the electrical component was segmented. This phenomenon indirectly reflects that the electrical component has a high dependence and sensitivity on the image quality indicator, which means that the indicator must be fine-tuned during the segmentation process to ensure the accuracy of recognition and segmentation. Applied to the above explanation, an image quality indicator with a smaller fluctuation usually means that the recognition and segmentation process of the electrical component is relatively stable and less affected by external factors. An image quality indicator with a large fluctuation usually means that more processing was performed on the indicator when the electrical component was segmented. For example, if the color depth fluctuates greatly, it means that in some recognition records, the color depth has been significantly adjusted to improve recognition accuracy. The color depth can be used as a sensitive image quality indicator.

[0044] The sensitive image quality indicators of the same electrical component in each historical identification record are compared, the mode is extracted from them, and the frequency of occurrence of each mode is obtained, and then the mean and standard deviation of the frequency of occurrence of each mode are calculated to perform discrete coefficient statistics, and then the discrete coefficient is compared with the set threshold. If the discrete coefficient reaches the set threshold, the maximum mode is taken as the sensitive image quality indicator corresponding to the corresponding electrical component. Otherwise, the mode whose frequency of occurrence of each mode is higher than the median frequency of occurrence is taken as the sensitive image quality indicator corresponding to the corresponding electrical component.

[0045] It should be understood that the mode is considered when determining the sensitive image quality indicators of electrical components based on the sensitive image quality indicators of the same electrical component in each historical identification record because the mode refers to the value that frequently appears in a set of data. By extracting the mode of the sensitive image quality indicators of the same electrical component in each historical identification record, it is possible to find those indicators that frequently appear in multiple identification processes. These indicators usually have a greater impact on the identification of the electrical component. When there is more than one mode, the dispersion coefficient of each mode is calculated. The dispersion coefficient is the ratio of the standard deviation to the mean and is used to measure the relative dispersion of the data. The larger the dispersion coefficient, the greater the volatility of the data, and the smaller the dispersion coefficient, the more stable the data. By comparing the dispersion coefficient with the preset threshold, when the dispersion coefficient reaches or exceeds the threshold, it means that the frequency distribution of the mode is relatively dispersed and there are multiple important image quality indicators. At this time, the largest mode is selected as the sensitive image quality indicator to ensure that the indicator selected is the most frequently occurring indicator with the greatest impact on recognition; conversely, when the dispersion coefficient is lower than the threshold, it means that the frequency distribution of the mode is relatively concentrated. At this time, the mode with a frequency higher than the median frequency is selected as the sensitive image quality indicator to ensure that the indicator selected is relatively stable and has a greater impact on recognition.

[0046] When determining the threshold of the dispersion coefficient, it is considered that the dispersion coefficient is the ratio of the standard deviation to the mean. When the standard deviation exceeds the mean, the dispersion coefficient will be greater than 1, which indicates that the difference between data points increases significantly and the frequency distribution becomes extremely dispersed. Therefore, the dispersion coefficient equal to 1 can be used as the critical point because it marks the turning point from relative stability to high volatility of data. When the dispersion coefficient is less than 1, the data is relatively concentrated and the volatility is small; when the dispersion coefficient is greater than 1, the volatility of the data increases significantly and the frequency distribution becomes more dispersed. In this case, choosing 0.8 as the threshold can find a reasonable balance between stability and flexibility. 0.8 is slightly lower than the critical point of 1, allowing a certain volatility, but not too loose, so as to ensure the robustness and accuracy of the recognition system.

[0047] The present invention is based on the basic principles of statistics and utilizes tools such as mode, frequency, mean, standard deviation and coefficient of dispersion to objectively evaluate the importance of different image quality indicators. This method not only considers the absolute value of the frequency, but also the relative distribution of the frequency, thus avoiding the limitations of a single indicator.

[0048] The sensitive segmentation association analysis module is used to associate the segmentation time of the electrical component with the sensitive image quality indicator of the electrical component to obtain the sensitive correlation of the segmentation time. The specific implementation process is as follows: based on the sensitive image quality indicator corresponding to each electrical component, the data of the sensitive image quality indicator in the original image quality indicator is extracted from several historical identification records corresponding to each electrical component and recorded as the original sensitive image quality indicator.

[0049] A plurality of historical identification records corresponding to each electrical component are formed into a segmentation time sensitive correlation curve corresponding to each electrical component in a coordinate system constructed with the original sensitive image quality indicator as the horizontal axis and the segmentation time as the vertical axis.

[0050] It should be added that in order to improve the accuracy of recognition and segmentation during the electrical component segmentation process, it is usually necessary to preprocess the original image, especially the processing of sensitive image quality indicators. The complexity and computational complexity of these processing steps directly affect the segmentation time. Therefore, the segmentation sensitive correlation curve can be constructed with the help of the original sensitive image quality indicators and segmentation time corresponding to each historical recognition record in the electrical component segmentation to reflect the correlation between the segmentation time and the sensitive image quality indicators.

[0051] The current electrical component wiring extraction module is used to obtain the electrical components contained in the current electrical component wiring diagram, which can be specifically obtained from the component list of the wiring diagram, and then the electrical components contained in the current electrical component wiring diagram are matched with the sensitive image quality indicators of each electrical component obtained from the analysis of the historical identification records, so as to obtain the sensitive image quality indicators of each electrical component in the current electrical component wiring diagram.

[0052] The segmentation determination module is used to perform image quality detection on the current electrical component wiring diagram to obtain the original image quality characteristics, and combine them with the sensitive image quality indicators of each electrical component and the sensitive correlation of the segmentation time to determine the initial segmentation order and image processing method of the electrical components.

[0053] In the preferred operation of the above scheme, the initial segmentation order of electrical components is determined by referring to the following process: based on the sensitive image quality indicators of each electrical component in the current electrical component wiring diagram, the segmentation time sensitivity correlation curve corresponding to each electrical component in the current electrical component wiring diagram is retrieved from the segmentation time sensitivity correlation curve corresponding to each electrical component.

[0054] The segmentation time of each electrical component in the current electrical component wiring diagram is predicted based on the original image quality indicator of the current electrical component wiring diagram and the segmentation time sensitive association curve corresponding to each electrical component. The specific prediction is as follows: the number of sensitive image quality indicators corresponding to each electrical component in the current electrical component wiring diagram is counted. If there is only one sensitive image quality indicator corresponding to an electrical component, the original sensitive image quality indicator in the current electrical component wiring diagram is used to extract the segmentation time corresponding to the original sensitive image quality indicator from the segmentation time sensitive association curve corresponding to the electrical component as the predicted segmentation time corresponding to the electrical component.

[0055] If there is more than one sensitive image quality indicator corresponding to a certain electrical component, the original sensitive image quality indicator in the current electrical component wiring diagram is used to extract the segmentation time corresponding to each original sensitive image quality indicator from the segmentation time sensitive association curve corresponding to the electrical component as the predicted segmentation time of the electrical component on each sensitive image quality indicator.

[0056] The predicted segmentation time of the electrical component on each sensitive image quality indicator is calculated by the range, where the range is the difference between the maximum and minimum values, and the calculated result is compared with the set critical value. For example, the critical value is 0.3. If the range does not reach the critical value, it means that the effects of different sensitive image quality indicators on the segmentation time are relatively consistent, and the average of these segmentation times can be taken as the final predicted segmentation time; if the range reaches or exceeds the critical value, it means that the effects of different sensitive image quality indicators on the segmentation time are quite different. At this time, the sensitive image quality indicators corresponding to the electrical component are weighted, and then the predicted segmentation time of the electrical component on each sensitive image quality indicator is combined with the weight value for weighted average calculation to obtain the predicted segmentation time corresponding to the electrical component. The weighted average can better reflect the comprehensive impact of different sensitive image quality indicators on the segmentation time and ensure the accuracy of the prediction results.

[0057] It should be added that the weight value of each sensitive image quality indicator mentioned above can be the occurrence frequency of each sensitive image quality indicator as the weight value.

[0058] By introducing the range calculation and critical value comparison, the present invention can effectively distinguish whether the effects of different sensitive image quality indicators on the segmentation duration are consistent. If the effects are consistent, the average can be taken; if the effects are quite different, weight assignment and weighted averaging can more accurately reflect the contribution of each sensitive image quality indicator and improve the accuracy of prediction.

[0059] The electrical components are arranged in descending order of segmentation time to obtain an initial segmentation order of the electrical components.

[0060] It should be emphasized that the electrical components with longer segmentation time are prioritized because the electrical components with longer segmentation time usually mean that these components have higher requirements on image quality. Prioritizing these complex components can ensure that they are fully processed in the early stages, thereby simplifying the subsequent segmentation tasks.

[0061] In a further preferred operation of the above scheme, the image processing method is determined as follows: the sensitive image quality indicators of the electrical components are extracted in sequence according to the initial segmentation order of the electrical components, and then the corresponding original sensitive image quality indicators of the current electrical component wiring diagram are preferentially processed before the segmentation operation of the electrical components is performed. This can improve the targetedness of the image processing and significantly improve the accuracy and efficiency of the electrical component segmentation.

[0062] The segmentation implementation module is used to perform system resource detection when segmenting the current electrical component wiring diagram according to the initial segmentation order of the electrical components. Specifically, the system resource detection is: during the identification and segmentation process of the current electrical component wiring diagram, system resource indication parameter detection is performed in real time, wherein the system resource indication parameters include CPU usage, memory usage and disk usage, and the initial segmentation order of the electrical components is dynamically adjusted according to the detection results.

[0063] The reasons for selecting CPU usage, memory usage and disk usage as system resource indicator parameters are as follows: First, the recognition and segmentation of electrical components usually involve a large number of computing operations, such as image processing, feature extraction, etc. These operations require high CPU computing power. By real-time monitoring of CPU usage, it is possible to promptly detect excessive CPU load. Secondly, electrical component wiring diagrams usually contain a large amount of image data, especially high-resolution images or multi-frame images, which require a large amount of memory space for storage and processing. By real-time monitoring of memory usage, it can be ensured that the system has enough memory to support the recognition and segmentation tasks. Finally, the recognition and segmentation tasks of electrical component wiring diagrams usually require loading image data from disk. If the disk read speed is slow, it may cause delays in the recognition and segmentation process, affecting the overall efficiency. By real-time monitoring of disk usage, it can be ensured that the disk has sufficient bandwidth to support fast data reading and writing operations.

[0064] In the innovative implementation of the above scheme, the initial segmentation order of electrical components is dynamically adjusted according to the detection results as follows: Based on the system resource detection results, it is identified whether there is resource limitation. Specifically, the detected system resource indication parameters are compared with the warning thresholds of the corresponding indication parameters. If a system resource indication parameter reaches the warning threshold, it is identified that there is resource limitation. If all system resource indication parameters do not reach the warning threshold, it is identified that there is no resource limitation.

[0065] The warning thresholds of the system resource indicator parameters mentioned above can be obtained from the system instructions based on the system model. This is because different models of hardware devices and system configurations have significant differences in performance, heat dissipation, power consumption, etc. Manufacturers usually provide recommended warning thresholds in the instructions based on the design and test results of their products to ensure that the system runs in the best state. For example, the recommended warning thresholds are as follows: CPU usage: The warning threshold is 80%. When the CPU usage continues to exceed this threshold, it indicates that the system may be facing a shortage of computing resources.

[0066] Memory usage: The warning threshold is 80%. If the memory usage exceeds this threshold continuously, there may be a risk of insufficient memory.

[0067] Disk usage: The warning threshold should be set according to the specific disk type and application scenario. For mechanical hard disks, the recommended warning threshold is 70% to avoid I / O bottlenecks; for solid-state drives, the recommended warning threshold is 85%, because SSDs have faster read and write speeds and can withstand higher usage.

[0068] See also Figure 3 As shown, if there is no resource limitation at a certain detection moment, the initial segmentation order of the electrical components will not be adjusted. If there is resource limitation at a certain detection moment, the electrical components to be segmented are extracted from the initial segmentation order of the electrical components as the target electrical components, and then the electrical components ranked last in the initial segmentation order of the electrical components are extracted as the adjusted target electrical components.

[0069] Move the adjusted target electrical component to the position to be segmented and regenerate the segmentation order.

[0070] It should be explained that when the identification resources are limited, the electrical component at the end is extracted and moved to the position to be split because the splitting time of the electrical component at the end is shorter. This ensures that the electrical components with shorter splitting time have the opportunity to be processed first when resources are limited, which helps to evenly distribute the processing load. In addition, when resources are limited, only one electrical component at the end is adjusted at a time, which can avoid frequent order adjustments and keep the splitting order relatively stable.

[0071] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. An electrical component wiring diagram recognition system using image segmentation technology, characterized in that: Includes the following modules: A historical identification record retrieval module is used to retrieve the historical identification record of the electronic component wiring diagram and extract the electrical components contained in the electronic component wiring diagram from the historical identification record; An image quality indicator extraction module is used to extract the image quality indicator of the original electrical component wiring diagram from the historical recognition record, recorded as the original image quality indicator, and at the same time extract the image quality indicator of each electrical component after segmentation; A segmentation time extraction module is used to extract the segmentation time of each electrical component from the historical recognition record; A sensitive image quality indicator analysis module is used to compare the image quality indicators of each electrical component after segmentation in the historical recognition record with the original image quality indicators, thereby analyzing the sensitive image quality indicators of each electrical component; A sensitive segmentation association analysis module is used to associate the segmentation duration of the electrical component with the sensitive image quality indicator of the electrical component to obtain the sensitive association of the segmentation duration; The current electrical component wiring extraction module is used to obtain the electrical components contained in the current electrical component wiring diagram, and extract the sensitive image quality indicators of each electrical component accordingly; The segmentation determination module is used to perform image quality detection on the current electrical component wiring diagram to obtain the original image quality indicator, and combine it with the sensitive image quality indicator of each electrical component and the segmentation time sensitivity correlation to determine the initial segmentation order and image processing method of the electrical components; The segmentation dynamic implementation module is used to perform real-time system resource detection during the segmentation of the current electrical component wiring diagram according to the initial segmentation sequence of the electrical components, and dynamically adjust the initial segmentation sequence of the electrical components according to the system resource detection result.

2. The electrical component wiring diagram recognition system using image segmentation technology as claimed in claim 1, characterized in that: The process of extracting the segmentation duration of each electrical component from the historical recognition record is as follows: Extract the electrical components, initial segmentation time and end segmentation time of each segmentation from the historical recognition records; The end segmentation time of each segmentation of the electrical component is compared with the initial segmentation time to obtain the segmentation time of each electrical component in the historical recognition record.

3. The electrical component wiring diagram recognition system using image segmentation technology as claimed in claim 1, characterized in that: The analysis of the sensitive image quality indicators of each electrical component is implemented as follows: The image quality indicator after segmentation of each electrical component in each historical recognition record is compared with the original image quality indicator to obtain the image quality indicator contrast difference, and the absolute value of the image quality indicator contrast difference is taken and divided by the original image quality indicator to obtain the image quality indicator fluctuation degree after segmentation of each electrical component; Classify all electrical components existing in the historical identification records to form a number of historical identification records corresponding to each electrical component; Compare the fluctuations of the image quality indicators of the same electrical component after segmentation in each historical recognition record, and select the image quality indicator corresponding to the maximum fluctuation as the sensitive image quality indicator of the same electrical component in each historical recognition record; The sensitive image quality indicators of the same electrical component in each historical identification record are compared, the mode is extracted from them, and the frequency of occurrence of each mode is obtained, and then the mean and standard deviation of the frequency of occurrence of each mode are calculated to perform discrete coefficient statistics, and then the discrete coefficient is compared with the set threshold. If the discrete coefficient reaches the set threshold, the maximum mode is taken as the sensitive image quality indicator corresponding to the corresponding electrical component. Otherwise, the mode whose frequency of occurrence of each mode is higher than the median frequency of occurrence is taken as the sensitive image quality indicator corresponding to the corresponding electrical component.

4. The electrical component wiring diagram recognition system using image segmentation technology as claimed in claim 1, characterized in that: The segmentation duration sensitive correlation is analyzed as follows: Extracting the sensitive image quality indicator from a number of historical identification records corresponding to each electrical component based on the sensitive image quality indicator corresponding to each electrical component, and recording the data in the original image quality indicator as the original sensitive image quality indicator; A plurality of historical identification records corresponding to each electrical component are formed into a segmentation time sensitive correlation curve corresponding to each electrical component in a coordinate system constructed with the original sensitive image quality indicator as the horizontal axis and the segmentation time as the vertical axis.

5. The electrical component wiring diagram recognition system using image segmentation technology as claimed in claim 4, characterized in that: The determination of the initial segmentation order of electrical components refers to the following process: Predicting the segmentation time of each electrical component in the current electrical component wiring diagram according to the original image quality indicator of the current electrical component wiring diagram and the segmentation time sensitivity correlation curve corresponding to each electrical component; The electrical components are arranged in descending order of segmentation time to obtain an initial segmentation order of the electrical components.

6. The electrical component wiring diagram recognition system using image segmentation technology as claimed in claim 5, characterized in that: The prediction of the segmentation duration of each electrical component in the current electrical component wiring diagram is implemented as follows: Count the number of sensitive image quality indicators corresponding to each electrical component in the current electrical component wiring diagram; if there is only one sensitive image quality indicator corresponding to a certain electrical component, use the original sensitive image quality indicator in the current electrical component wiring diagram to extract the segmentation time corresponding to the original sensitive image quality indicator from the segmentation time sensitive association curve corresponding to the electrical component as the predicted segmentation time corresponding to the electrical component; If there is more than one sensitive image quality indicator corresponding to a certain electrical component, the original sensitive image quality indicator in the current electrical component wiring diagram is used to extract the segmentation time corresponding to each original sensitive image quality indicator from the segmentation time sensitive association curve corresponding to the electrical component as the predicted segmentation time of the electrical component on each sensitive image quality indicator; The range of the predicted segmentation time of the electrical component on each sensitive image quality indicator is calculated, and the calculation result is compared with the set critical value. If the critical value is not reached, the average of the predicted segmentation time of the electrical component on each sensitive image quality indicator is taken as the predicted segmentation time corresponding to the electrical component. If the critical value is reached, the sensitive image quality indicators corresponding to the electrical component are weighted, and then the predicted segmentation time of the electrical component on each sensitive image quality indicator is combined with the weight value for weighted average calculation to obtain the predicted segmentation time corresponding to the electrical component.

7. The electrical component wiring diagram recognition system using image segmentation technology as claimed in claim 1, characterized in that: The image processing method is as follows: The sensitive image quality indicators of the electrical components are extracted in sequence according to the initial segmentation order of the electrical components, and then the corresponding original sensitive image quality indicators of the current electrical component wiring diagram are preferentially processed before the segmentation operation of the electrical components is performed.

8. The electrical component wiring diagram recognition system using image segmentation technology as claimed in claim 1, characterized in that: The system resource detection process is as follows: During the recognition and segmentation process of the current electrical component wiring diagram, system resource indication parameter detection is performed in real time, wherein the system resource indication parameters include CPU usage, memory usage and disk usage.

9. The electrical component wiring diagram recognition system using image segmentation technology as claimed in claim 8, characterized in that: The following operations are performed to dynamically adjust the initial segmentation order of electrical components according to the system resource detection result: Identify whether there is resource limitation according to the system resource detection result. If there is no resource limitation at a certain detection time, do not adjust the initial segmentation order of the electrical components. If there is resource limitation at a certain detection time, extract the electrical components to be segmented from the initial segmentation order of the electrical components at the current time as the target electrical components, and then extract the electrical components at the last position from the initial segmentation order of the electrical components as the adjusted target electrical components. Move the adjusted target electrical component to the position to be segmented and regenerate the segmentation order.

10. The electrical component wiring diagram recognition system using image segmentation technology as claimed in claim 9, characterized in that: The identification of whether there is resource limitation refers to the following process: The detected system resource indication parameters are compared with the warning thresholds of the corresponding indication parameters. If a system resource indication parameter reaches the warning threshold, it is identified that there is resource limitation. If all system resource indication parameters do not reach the warning threshold, it is identified that there is no resource limitation.

Images