Process flow diagram reconstruction method and device, medium and product

Abstract

A process flow diagram reconstruction method, device, medium and product, the process flow diagram reconstruction method comprising: using a first flow diagram processing model to identify the types and positions of all devices in a to-be-reconstructed process flow diagram to obtain the type information and position information of all devices, identifying the positions of all the device names in the to-be-reconstructed process flow diagram by using a second flow diagram processing model to obtain the position information of all the device names, and obtaining all the device names according to the obtained position information of all the device names and a character recognition tool, creating corresponding equipment on a configuration interface in a graphical mode according to the obtained type information and position information of all the equipment, and adding the obtained equipment names to the created equipment according to the obtained position information of all the equipment names so as to obtain a reconstructed process flow diagram, therefore, a large amount of labor cost and time cost are saved.

Description

TECHNICAL FIELD

[0001] The present application relates to computer processing technology, in particular to a process flow diagram reconstruction method, device, medium and product. BACKGROUND

[0002] The process flow diagram configuration in nuclear power engineering is an important part of nuclear power construction, which presents the logical relationship and technical details of key links such as nuclear facility operation, material transmission, energy conversion and quality control in a graphical manner.

[0003] In related technologies, when designing a process flow diagram, a completed flow diagram in other projects may be used, but even so, these ready-made flow diagrams cannot be directly applied and must be recreated on the interface of the current project, which undoubtedly increases the investment of manpower and time. SUMMARY

[0004] The embodiments of the present application provide a process flow diagram reconstruction method, device, medium and product, which can quickly transplant the perfected process flow diagram in other projects to a new project, thereby saving a lot of manpower and time costs.

[0005] The embodiments of the present application provide a process flow diagram reconstruction method, which comprises: The type and location of all devices in the process flow diagram to be reconstructed are identified by using a first flow diagram processing model trained in advance, to obtain the type information and location information of all devices in the process flow diagram to be reconstructed; The location of all device names in the process flow diagram to be reconstructed is identified by using a second flow diagram processing model trained in advance, to obtain the location information of all device names in the process flow diagram to be reconstructed, and the text recognition tool is used to obtain all device names in the process flow diagram to be reconstructed according to the obtained location information of all device names; According to the obtained type information and location information of all devices, corresponding devices are created in a graphical manner on the configuration interface, and the obtained device names are added to the created devices according to the obtained location information of all device names, to obtain a reconstructed process flow diagram.

[0006] The embodiments of the present application also provide an electronic device, comprising a memory and a processor. The memory is connected with the processor and is used for storing programs. The processor is used for realizing the process flow diagram reconstruction method as described above by running the programs in the memory.

[0007] The embodiment of the present application further provides a storage medium, wherein the storage medium stores a computer program, and the computer program is run by a processor to realize the process flow diagram reconstruction method.

[0008] The embodiment of the present application further provides a computer program product, comprising computer program instructions, which, when run by a processor, enable the processor to realize the process flow diagram reconstruction method.

[0009] The embodiment of the present application comprises: identifying the types and locations of all devices in a to-be-reconstructed process flow diagram by using a first pre-trained process flow diagram processing model, to obtain type information and location information of all devices in the to-be-reconstructed process flow diagram; identifying the locations of all device names in the to-be-reconstructed process flow diagram by using a second pre-trained process flow diagram processing model, to obtain location information of all device names in the to-be-reconstructed process flow diagram, and obtaining all device names in the to-be-reconstructed process flow diagram according to the obtained location information of all device names and a character recognition tool; creating corresponding devices in a graphical manner on a configuration interface according to the obtained type information and location information of all devices, and adding the obtained device names to the created devices according to the obtained location information of all device names, to obtain a reconstructed process flow diagram. Therefore, a perfected process flow diagram in other projects can be quickly transplanted and applied to a new project, thereby saving a large amount of human cost and time cost.

[0010] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. Other advantages of the present application can be realized and attained by means of the instrumentalities and combinations particularly pointed out in the description and appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0011] The accompanying drawings are included to provide an understanding of the present application, and constitute a part of the specification, and together with the embodiments of the present application serve to explain the technical solutions of the present application, and do not constitute a limitation on the technical solutions of the present application.

[0012] Figure 1 A process flow diagram reconstruction method of an embodiment of the present application is shown in the figure; Figure 2 A model training process of an embodiment of the present application is shown in the figure; Figure 3 A generation process of an intermediate file of an embodiment of the present application is shown in the figure; Figure 4 A device name recognition process of an embodiment of the present application is shown in the figure; Figure 5A process diagram for creating a corresponding device and adding a device name according to an embodiment of the present application; Figure 6 A structure diagram of a process flow diagram reconstruction device according to an embodiment of the present application; Figure 7 A structure diagram of another process flow diagram reconstruction device according to an embodiment of the present application; Figure 8 A structure diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0013] The present application describes a number of embodiments, but the description is exemplary rather than limiting and it will be apparent to those of ordinary skill in the art that numerous more embodiments and implementations are possible within the scope of the embodiments described in the present application. Although a number of possible combinations of features have been set forth in the accompanying figures and discussed above, many other combinations will be possible. Unless specifically intended for limitation of the scope of any embodiment, any feature or element of any embodiment can be used in combination with any other feature or element of any other embodiment, or can replace any other feature or element of any other embodiment.

[0014] The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in the present application can also be combined with any conventional features or elements to form unique inventive solutions. Any feature or element of any embodiment can also be combined with features or elements from other inventive solutions to form another unique inventive solution. Therefore, it should be understood that any feature shown and / or discussed in the present application can be implemented alone or in any suitable combination. Accordingly, the embodiments are not to be restricted, except as by the appended claims and their equivalents. Furthermore, various modifications and changes can be made within the scope of the appended claims.

[0015] Furthermore, in describing representative embodiments, the specification can have presented the method and / or process as a particular sequence of steps. However, to the extent that the method or process depends on more than one step, the method or process should not be limited to the particular sequence of steps described. Other sequences of steps can be possible, and are within the scope of the embodiments. Therefore, the particular order of the steps set forth in the specification is not an limitation on the claims. Further, the claims should not be limited to the steps of the method and / or process in the order in which they are written, as other sequences of steps can be possible and are within the scope of the embodiments.

[0016] The embodiment of the present disclosure provides a reconstruction method of a process flowchart, as shown in the accompanying drawings, comprising: Figure 1 Step 100, using a first flowchart processing model trained in advance to identify the types and locations of all devices in a process flowchart to be reconstructed to obtain the type information and location information of all devices in the process flowchart to be reconstructed; Step 110, using a second flowchart processing model trained in advance to identify the locations of all device names in the process flowchart to be reconstructed to obtain the location information of all device names in the process flowchart to be reconstructed, and using the obtained location information of all device names and a character recognition tool to obtain all device names in the process flowchart to be reconstructed; Step 120, creating corresponding devices in a graphical manner on a configuration interface according to the obtained type information and location information of all devices, and adding the obtained device names to the created devices according to the obtained location information of all device names to obtain a reconstructed process flowchart.

[0017] The first flowchart processing model is a model trained in advance for identifying the types and locations of all devices in a process flowchart, wherein the location refers to the location of the device in the process flowchart.

[0018] When identifying all device names in the reconstructed process flowchart, the locations of all device names in the reconstructed process flowchart need to be obtained first, which can improve the recognition accuracy and optimize the processing efficiency. The recognition accuracy can be improved because directly applying a character recognition tool to the entire image may encounter complex background, noise or non-text element interference, which will reduce the recognition accuracy, and by locating the character region first, the influence of these interference factors can be reduced, so that the character recognition process can focus more on processing the actual character part, thereby improving the recognition accuracy. The processing efficiency can be optimized because for an image containing a large amount of non-text content, if the location of the character is not determined first and the character recognition tool is directly processed, the calculation burden and processing time will be greatly increased, and after the character region is located, only the character recognition processing is required for the specific region, which can significantly reduce the amount of data to be analyzed, thereby improving the processing speed and efficiency.

[0019] ​The text recognition tool can be an optical character recognition (OCR) software or application. OCR is an algorithm that converts text images into text. With the rapid development of deep learning, OCR has evolved from traditional recognition methods based on template matching and shallow feature extraction to more efficient and intelligent recognition systems, providing solid technical support for full-process automated information extraction. Deep learning OCR includes input image, deep learning text region detection, preprocessing, feature extraction, deep learning recognizer, and deep learning post-processing.

[0020] In the application scenario of the nuclear power process flowchart, the text therein is clear printed matter, and the use of the deep learning version of the OCR technology recognition can achieve a high recognition accuracy. Therefore, the present application can use the open source OCR tool EasyOCR to recognize the device name. EasyOCR is based on a deep learning framework, which has powerful text detection and recognition capabilities, and still has good recognition performance under low resolution or complex background conditions. It has excellent recognition performance for simple structure and clear font device names.

[0021] Step 120 can be performed by using configuration software. The obtained type information and position information can be stored in an intermediate file in Excel format. The configuration software supports parsing and batch converting the intermediate file in Excel format into a process flowchart picture in MGP format that can be recognized by a graphic editing software. The configuration software supports batch conversion, and a plurality of Excel files can be converted into MGP pictures at a time. Each sheet of each Excel table corresponds to a process flowchart picture, and a row record in the sheet represents a graphic object.

[0022] The process flowchart reconstruction method provided by the embodiments of the present application uses a first process flowchart processing model trained in advance to identify the types and positions of all devices in a process flowchart to be reconstructed, to obtain type information and position information of all devices in the process flowchart to be reconstructed; uses a second process flowchart processing model trained in advance to identify the positions of all device names in the process flowchart to be reconstructed, to obtain position information of all device names in the process flowchart to be reconstructed, and to obtain all device names in the process flowchart to be reconstructed according to the obtained position information of all device names and a text recognition tool; creates corresponding devices in a graphical manner on a configuration interface according to the obtained type information and position information of all devices, and adds the obtained device names to the created devices according to the obtained position information of all device names, to obtain a reconstructed process flowchart. Therefore, the perfected process flowchart in other projects can be quickly transplanted and applied to new projects, thereby saving a large amount of human and time costs.

[0023] In an example embodiment, the method comprises: obtaining a plurality of sample process flowcharts, and type information and position information of all devices in all sample process flowcharts, wherein each of the sample process flowcharts comprises at least one device; training a pre-set first neural network model by taking all the obtained sample process flowcharts as input and taking the type information and position information of all devices in all sample process flowcharts as labels of the corresponding sample process flowcharts, to obtain the first process flowchart processing model.

[0024] The following illustrates how to train the pre-set first neural network model by taking all the obtained sample process flowcharts as input and taking the type information and position information of all devices in all sample process flowcharts as labels of the corresponding sample process flowcharts. Taking three sample process flowcharts as an example, the first sample process flowchart, the second sample process flowchart and the third sample process flowchart are taken as input, the type information and position information of all devices in the first sample process flowchart are taken as labels of the first sample process flowchart, the type information and position information of all devices in the second sample process flowchart are taken as labels of the second sample process flowchart, and the type information and position information of all devices in the third sample process flowchart are taken as labels of the third sample process flowchart, to train the pre-set first neural network model.

[0025] The first neural network model can be a target detection model (You Only Look Once, YOLO). YOLO is an advanced target detection algorithm, which is fast, accurate and lightweight and easy to use, and is widely used in various object detection and tracking, instance segmentation, image classification and pose estimation and other computer vision tasks. The network architecture of YOLO mainly consists of three core parts: the backbone network is responsible for extracting multi-level semantic features from the image; the feature enhancement network is responsible for fusing feature map information of different levels. The head is responsible for decoding the feature map and completing the result output. Through efficient stacking of convolutional neural networks, YOLO realizes an end-to-end target detection process, with excellent real-time performance, high precision and good generalization ability.

[0026] All sample process flowcharts and corresponding labels together form a labeled data set. A large number of reliable labeled data sets are one of the prerequisites for the success of deep learning. Due to the particularity of nuclear power process flowcharts, which do not belong to the category of regular object recognition, a special data set needs to be made to train the basic model. By providing sufficient training samples, the generalization ability of the model can be improved, the risk of overfitting can be effectively reduced, and the recognition accuracy can be significantly improved.

[0027] The sample process flowchart can be obtained by screenshot, shooting, etc. When the sample process flowchart is obtained and used for first neural network model training, an open source labeling tool LabelImg can be used to systematically label each device in the obtained sample, draw a bounding box for each device in the image and assign a corresponding class label to it, and finally form a labeled image with a bounding box and a class label (the labeled image can be a YOLO format labeled file), thereby obtaining a data set suitable for training the first neural network model.

[0028] During the training of the first neural network model, reasonable learning rate parameters, batch size, and network model iteration times can be set to ensure that the model can fully learn the characteristics of the devices in the process flowchart on the training set, maintain good generalization ability on the validation set, and avoid underfitting or overfitting problems. However, the learning rate parameters, batch size, and network model iteration times set may be different, and multiple training results may be generated during the model training process. For multiple training results, the key indicators (precision, recall, average precision mean, etc.) can be compared by a tool to select the training result with the best final performance as the first process flowchart processing model.

[0029] In an exemplary example, the method comprises: obtaining the position information of all device names in all sample process flowcharts; training the pre-set second neural network model by taking all sample process flowcharts as input and taking the position information of all device names in all sample process flowcharts as the labels of the corresponding sample process flowcharts, to obtain the second process flowchart processing model.

[0030] The following illustrates how to train the pre-set second neural network model by taking all sample process flowcharts as input and taking the position information of all device names in all sample process flowcharts as the labels of the corresponding sample process flowcharts. Taking three sample process flowcharts as an example, the first sample process flowchart, the second sample process flowchart, and the third sample process flowchart are taken as input, the position information of all device names in the first sample process flowchart is taken as the label of the first sample process flowchart, the position information of all device names in the second sample process flowchart is taken as the label of the second sample process flowchart, and the position information of all device names in the third sample process flowchart is taken as the label of the third sample process flowchart. The pre-set second neural network model is trained.

[0031] When the sample process flowchart is obtained and used for training of the second neural network model, an open-source labeling tool LabelImg can be used to systematically label each device name in the obtained sample, draw a bounding box for each device name in the image, and finally form a labeled image with a bounding box (the labeled image can be a YOLO format labeled file), so as to obtain a data set suitable for training the second neural network model.

[0032] Likewise, during the training of the second neural network model, reasonable learning rate parameters, batch sizes, and iteration numbers of the network model can be set to ensure that the model can fully learn the features of the device names in the process flowchart on the training set, maintain good generalization ability on the validation set, and avoid underfitting or overfitting problems.

[0033] The process of training the first neural network model to obtain the first flowchart processing model and the process of training the second neural network model to obtain the second flowchart processing model can be as shown in Figure 2 , comprising: Step 200, making a data set; Step 210, setting training parameters and then training; Step 220, verifying the performance of the trained model; Step 230, determining whether the performance of the trained model meets the preset standard. If not, return to execute 210. If yes, execute step 240; Step 240, saving the model parameters to obtain a final model.

[0034] In an exemplary example, the obtaining of all device names in the process flowchart to be reconstructed according to the position information of all obtained device names and the text recognition tool comprises: Cutting all device names in the process flowchart to be reconstructed according to the position information of all obtained device names, respectively, to obtain device name pictures; Using the text recognition tool to recognize all obtained device name pictures, respectively, to obtain all device names in the process flowchart to be reconstructed.

[0035] The text recognition tool can be OCR. Since the process flowchart contains a large amount of text information, the device name is the key information that needs to be distinguished and recognized from other text information. Since OCR does not have the ability to selectively recognize specific areas, it is difficult to achieve such a degree of distinction only by relying on the OCR text recognition component. However, the device name information in the process flowchart is different from other text information in terms of format, size, and color. The image recognition can be used to locate and crop the device name image part as an OCR recognition area for recognition.

[0036] In an example, the using the character recognition tool respectively identifies all the obtained device name pictures to obtain all the device names in the process flow diagram to be reconstructed, including: The cropped device name picture is subjected to at least one of the following image processing: grayscale processing and binary processing. The using the character recognition tool respectively identifies all the device name pictures subjected to the image processing to obtain all the device names in the process flow diagram to be reconstructed.

[0037] In order to improve the accuracy of the character recognition tool in recognizing the device names in the process flow diagram, the cropped device name image can be subjected to image preprocessing, and the preprocessing process can include two links of grayscale processing and binary processing. Through the image preprocessing, the contrast between the characters and the background can be enhanced, and the accuracy of the subsequent character recognition can be improved.

[0038] The grayscale processing is performed because in the image recognition process, color information is not a necessary factor, but will increase the calculation complexity and may introduce noise interference. Through the grayscale processing, the three color channels of the image can be combined into a single-channel grayscale image. The binary processing can separate the background in the image from the recognition information into black and white, enhance the contrast between the characters and the background, make the character outline clearer, and facilitate the better recognition of the characters by the OCR.

[0039] After the image preprocessing is completed, the open-source OCR tool EasyOCR can be used to perform high-precision character recognition on the image, and the device name information can be saved in an intermediate file in an Excel format according to a certain format.

[0040] The generation process of the intermediate file can be as shown in Figure 3 , including: Step 300, reading the process flow diagram to be reconstructed; Step 310, using the first flowchart processing model and the second flowchart processing model trained to obtain the type information and the position information of all the devices, and the position information of all the device names; Step 320, obtaining the intermediate file according to the obtained type information and position information.

[0041] The recognition process of the device name can be as shown in Figure 4 , including: Step 400, cropping the device name picture; Step 410, performing grayscale processing and binary processing on the cropped device name picture; Step 420, performing character recognition on the device name picture subjected to the image processing.

[0042] In an example embodiment, as shown in Figure 5 the created devices according to the obtained position information of all the device names, comprising: Step 500, obtaining the size ratio relationship between the display interface where the process flowchart to be reconstructed is located and the configuration interface; Step 510, for each device in the process flowchart to be reconstructed, obtaining target position information of the device on the configuration interface according to the position information of the device and the obtained size ratio relationship, calling a graph of a corresponding type from a graph library of the configuration interface according to the type information of the device, and creating the called graph at a corresponding position according to the target position information; Step 520, adding the obtained device names to the created devices according to the obtained position information of all the device names.

[0043] Obtaining the size ratio relationship between the display interface where the process flowchart to be reconstructed is located and the configuration interface is to enable each device and each device name in the process flowchart to be accurately restored to the configuration interface in proportion.

[0044] In practical applications, the configuration process can include: Step S1, directory selection: selecting a directory to save intermediate files.

[0045] Step S2, traversing Excel tables under the directory: traversing each Excel intermediate file under the directory.

[0046] Step S3, traversing each sheet page of the Excel table: one sheet page in each file table corresponds to one process flowchart, and information of each page is read.

[0047] Step S4, creating a process flowchart: creating a blank process flowchart.

[0048] Step S5, coordinate conversion according to records: converting record information of each page in the file into coordinates of the platform.

[0049] Step S6, adding different devices to the flowchart according to the records, adding the devices to the process flowchart according to the coordinates, and adding device names.

[0050] In an example embodiment, before the step of adding the obtained device names to the created devices according to the obtained position information of all the device names, the method further comprises: recording a correspondence between the obtained position information of all the device names and the obtained all the device names. adding the obtained device name to the created device according to the obtained position information of all device names. adding the obtained device name to the created device according to the obtained position information of all device names based on the obtained correspondence.

[0051] Corresponding to the reconstruction method of the process flowchart described above, the embodiment of the present application also provides a reconstruction device of a process flowchart. As shown in Figure 6 The reconstruction device of the process flowchart provided by the embodiment of the present application includes: The first acquisition unit 600 is configured to identify the types and positions of all devices in the process flowchart to be reconstructed by using the first flowchart processing model trained in advance, so as to obtain the type information and position information of all devices in the process flowchart to be reconstructed. The second acquisition unit 610 is configured to identify the positions of all device names in the process flowchart to be reconstructed by using the second flowchart processing model trained in advance, so as to obtain the position information of all device names in the process flowchart to be reconstructed, and obtain all device names in the process flowchart to be reconstructed according to the obtained position information of all device names and a character recognition tool. The processing unit 620 is configured to create corresponding devices in a graphical manner on a configuration interface according to the obtained type information and position information of all devices, and add the obtained device names to the created devices according to the obtained position information of all device names, so as to obtain a reconstructed process flowchart.

[0052] In an exemplary example, the model construction unit 630 is further configured to: obtain a plurality of sample process flowcharts, and the type information and position information of all devices in all sample process flowcharts; wherein each of the sample process flowcharts contains at least one device; train the first neural network model pre-set by taking all obtained sample process flowcharts as input and taking the type information and position information of all devices in all sample process flowcharts as labels of the corresponding sample process flowcharts, so as to obtain the first flowchart processing model.

[0053] In an exemplary example, the model construction unit 630 is further configured to: obtain the position information of all device names in all sample process flowcharts; train the second neural network model pre-set by taking all obtained sample process flowcharts as input and taking the position information of all device names in all sample process flowcharts as labels of the corresponding sample process flowcharts, so as to obtain the second flowchart processing model.

[0054] In an example, the second obtaining unit 610 is configured to: crop each of the device name pictures according to the position information of the device name to obtain a device name picture; recognize the device name pictures by using the text recognition tool to obtain all the device names in the process flow diagram to be reconstructed.

[0055] In an example, the second obtaining unit 610 is configured to: perform at least one of the following image processing on each of the cropped device name pictures: grayscale processing, binary processing; recognize the device name pictures by using the text recognition tool to obtain all the device names in the process flow diagram to be reconstructed.

[0056] In an example, the processing unit 620 is configured to: obtain a size ratio relationship between a display interface in which the process flow diagram to be reconstructed is located and a configuration interface; for each device in the process flow diagram to be reconstructed, obtain target position information of the device on the configuration interface according to position information of the device and the obtained size ratio relationship, call a graph of a corresponding type from a graph library of the configuration interface according to type information of the device, and create the called graph at a corresponding position according to the target position information; add the obtained device name to the created device according to the position information of the device name.

[0057] In an example, the processing unit 620 is further configured to: record a correspondence between the position information of all the obtained device names and all the obtained device names; the adding the obtained device name to the created device according to the position information of the device name comprises: adding the obtained device name to the created device according to the position information of the device name based on the obtained correspondence.

[0058] The process flow diagram reconstruction device provided by the embodiment is of the same application concept as the process flow diagram reconstruction method provided by the above-mentioned embodiments of the application, can execute the process flow diagram reconstruction method provided by any of the above-mentioned embodiments of the application, and has the corresponding function modules and beneficial effects of executing the process flow diagram reconstruction method. Technical details not described in detail in the embodiment can be found in the specific processing content of the process flow diagram reconstruction method provided by the above-mentioned embodiments of the application, which will not be described here again.

[0059] The embodiment of the application further provides a process flow diagram reconstruction device, as shown in Figure 7 The device includes an automatic identification module 700 and a process flow diagram reconstruction module 710. The automatic identification module 700 includes a device identification module 700a and a device name identification module 700b. The device identification module 700a is configured to make a training set, train a first flow chart processing model, and identify a device, and save the results to an intermediate file. The device name identification module 700b is configured to make a training set, train a second flow chart processing model, crop a text region image, pre-process the cropped text region image, and identify a device name, and save the results to an intermediate file. The process flow diagram reconstruction module 710 is configured to read the intermediate file, parse a coordinate format according to a configuration platform, and reconstruct a process flow diagram.

[0060] The process flow diagram reconstruction device provided by the embodiment of the application significantly reduces the workload of engineering personnel and improves the efficiency of the early-stage work of nuclear power engineering. The use of the cutting-edge technology in the field of computers provides a guarantee for the efficient completion of nuclear power engineering construction.

[0061] The embodiment of the application further provides an electronic device, as shown in Figure 8 The device includes a memory 800 and a processor 810. The memory 800 is connected to the processor 810 and is configured to store a program. The processor 810 is configured to execute the process flow diagram reconstruction method described in any of the above-mentioned embodiments by running the program in the memory 800.

[0062] Specifically, the electronic device can further include a bus, a communication interface 820, an input device 830, and an output device 840.

[0063] The processor 810, the memory 800, the communication interface 820, the input device 830, and the output device 840 are connected to each other through the bus. Among them: The bus can include a path for transmitting information between various components of a computer system.

[0064] The processor 810 can be a general processor, such as a general central processing unit (CPU), a microprocessor, or the like, or can be an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-to-use programmable gate array (FPGA), or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0065] The processor 810 can include a main processor and can further include a baseband chip, a modem, and the like.

[0066] The memory 800 stores programs for executing the technical solutions of the present application, and can also store operating systems and other key services. Specifically, the programs can include program codes, and the program codes include computer operation instructions. More specifically, the memory 800 can include read-only memory (ROM), other types of static storage devices that can store static information and instructions, random access memory (RAM), other types of dynamic storage devices that can store information and instructions, disk storage, flash, and the like.

[0067] The input device 830 can include a device that receives data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor, and the like.

[0068] The output device 840 can include a device that allows information to be output to a user, such as a display screen, a printer, a speaker, and the like.

[0069] The communication interface 820 can include a device using any transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), and the like.

[0070] The processor 810 executes the programs stored in the memory 800 and calls other devices, which can be used to implement each step of the reconstruction method of any one of the process flow diagrams provided by the embodiments of the present application.

[0071] In addition to the above method and device, the embodiments of the present application can also be a computer program product, which includes computer program instructions that, when executed by a processor, cause the processor to perform the steps of the reconstruction method of the process flow diagram according to various embodiments of the present application described in any of the embodiments of the present application.

[0072] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. The embodiments of methods described herein are implemented as program code, which is executed by a processor.

[0073] Furthermore, the embodiments of the present application also provide a storage medium, wherein the storage medium stores a computer program, and the computer program is run by a processor to implement the process flow reconstruction method described in any of the above embodiments.

[0074] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the functions of the modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations. In the hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be performed by several physical components in cooperation. Some or all of the components can be implemented as software executed by a processor, such as a digital signal processor or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on computer readable media, which can include computer storage media (or non-transitory media) and communication media (or transitory media). As is well known to those skilled in the art, the term "computer storage media" includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, it is common knowledge to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

Claims

1. A method for reconstructing a process flow chart, characterized in that: include: Using a pre-trained first flowchart processing model to identify the types and locations of all equipment in the process flowchart to be reconstructed, so as to obtain type information and location information of all equipment in the process flowchart to be reconstructed; Using a pre-trained second flowchart processing model to identify the locations of all equipment names in the process flow chart to be reconstructed, so as to obtain location information of all equipment names in the process flow chart to be reconstructed, and obtaining all equipment names in the process flow chart to be reconstructed based on the obtained location information of all equipment names and a text recognition tool; Corresponding equipment is created graphically on the configuration interface according to the acquired type information and location information of all equipment, and the acquired equipment names are added to the created equipment according to the acquired location information of all equipment names to obtain a reconstructed process flow chart.

2. The method according to claim 1, characterized in that The method comprises: Obtaining multiple sample process flow charts, and type information and location information of all equipment in all sample process flow charts; wherein each sample process flow chart contains at least one equipment; All the obtained sample process flow charts are used as input, the type information and location information of all equipment in all the sample process flow charts are used as labels of the corresponding sample process flow charts, and a pre-set first neural network model is trained to obtain the first flow chart processing model.

3. The method according to claim 2, characterized in that The method comprises: Get the location information of all equipment names in all sample process flow charts; All the obtained sample process flow charts are used as input, and the location information of all equipment names in all the sample process flow charts is used as labels of the corresponding sample process flow charts to train a pre-set second neural network model to obtain the second flow chart processing model.

4. The method according to claim 1, wherein The method of obtaining all the equipment names in the process flow diagram to be reconstructed based on the obtained location information of all the equipment names and the text recognition tool includes: All equipment names are cropped in the process flow chart to be reconstructed according to the obtained position information of all equipment names to obtain equipment name images; All the equipment name pictures obtained are respectively identified using the text recognition tool to obtain all the equipment names in the process flow chart to be reconstructed.

5. The method according to claim 4, characterized in that The character recognition tool is used to respectively identify all the equipment name images to obtain all the equipment names in the process flow chart to be reconstructed, including: Perform at least one of the following image processing on each cropped device name image: grayscale processing, binarization processing; The text recognition tool is used to respectively recognize all the device name images that have undergone image processing to obtain all the device names in the process flow chart to be reconstructed.

6. The method according to claim 1, characterized in that The step of creating corresponding devices in a graphical manner on the configuration interface according to the acquired type information and location information of all devices, and adding the acquired device names to the created devices according to the acquired location information of all device names, includes: Obtaining a size ratio relationship between the display interface where the process flow chart to be reconstructed is located and the configuration interface; For each device in the process flow chart to be reconstructed, the following operations are performed: obtaining target position information of the device on the configuration interface based on the position information of the device and the obtained size ratio relationship; calling a corresponding type of graphic from a graphic library of the configuration interface based on the type information of the device; and creating the called graphic at a corresponding position based on the target position information; The obtained device names are added to the created devices according to the obtained position information of all device names.

7. The method according to claim 6, characterized in that Before adding the obtained device names to the created devices according to the obtained location information of all device names, the method further includes: Record the location information of all the obtained device names and the corresponding relationship between all the obtained device names; The step of adding the obtained device names to the created devices according to the obtained location information of all device names includes: Based on the obtained correspondence, the obtained device names are added to the created devices according to the obtained location information of all device names.

8. An electronic device, characterized in that: include: memory and processor; The memory is connected to the processor and is used to store programs; The processor is configured to implement the method for reconstructing the process flow chart according to any one of claims 1 to 7 by running the program in the memory.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the method for reconstructing the process flow chart according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The method comprises computer program instructions, which, when executed by a processor, enable the processor to implement the method for reconstructing a process flow chart according to any one of claims 1 to 7.

Images