A circuit experiment report automatic marking method and device

Abstract

The application discloses an experimental report automatic marking method and device, the method comprises the following steps: first, obtaining an electronic version of a circuit experiment report, and performing scanning analysis on the circuit experiment report to obtain report data, wherein the report data at least comprises a circuit diagram, a waveform diagram, experimental data and text information; then, marking based on the report data and a preset standard database. The circuit experiment report can be quickly and accurately automatically audited and marked.

Description

Technical Field

[0001] This invention belongs to the field of automatic processing technology of experimental reports, and specifically relates to a method and device for automatic grading of experimental reports. Background Technology

[0002] In the field of education, circuit experiment reports submitted by students or test takers are usually reviewed by teachers who then provide their review results. However, this method is time-consuming, labor-intensive, and wastes teacher resources.

[0003] Therefore, how to avoid manual review and approval, and thus quickly and accurately automate the review and approval of circuit experiment reports, is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to solve the technical problem that in the prior art, circuit experiment reports can only be reviewed manually, which is time-consuming and labor-intensive.

[0005] To achieve the above technical objectives, in one aspect, the present invention provides a method for automatically grading circuit experiment reports, the method comprising:

[0006] Obtain an electronic version of the circuit experiment report, and scan and parse the circuit experiment report to obtain report data. The report data includes at least circuit diagrams, waveform diagrams, experimental data, and text information.

[0007] The review is based on report data and a pre-set standard database.

[0008] Furthermore, the preset standard database is a preset standard database generated based on the experimental instructions, standard circuit diagrams, reference waveform diagrams, and review guidelines.

[0009] Furthermore, the review based on report data and a preset standard database specifically includes:

[0010] Generate integrity detection results based on the text information;

[0011] Based on the circuit diagram and the preset standard database, generate circuit connection logic judgment results;

[0012] The experimental data detection results are obtained based on the waveform diagram, experimental data, and preset standard database.

[0013] The integrity test results, circuit connection logic judgment results, and experimental data test results are combined into the review results.

[0014] Furthermore, the step of generating circuit connection logic judgment results based on the circuit diagram and a preset standard database specifically includes:

[0015] The circuit diagram is preprocessed to obtain an image of the circuit to be identified;

[0016] The image of the circuit to be identified is used to extract information about each component and its parameters, as well as a candidate set of wires.

[0017] The electrical connection relationships between different components are determined based on the candidate set of wires, each component and its parameter information.

[0018] Based on the electrical connections and components, generate a circuit topology diagram or circuit netlist to be reviewed;

[0019] The circuit connection logic judgment result is obtained by reviewing the circuit topology diagram or circuit netlist to be reviewed based on the preset standard database.

[0020] Furthermore, obtaining the experimental data detection results based on the waveform, experimental data, and preset standard database specifically includes:

[0021] The waveform image is preprocessed to obtain the waveform image to be identified, and the experimental data is processed and extracted to obtain the structured result of the experimental data.

[0022] The waveform image to be identified is identified to obtain waveform curve data, and the fields in the experimental data structured result are replaced with standard fields to obtain the experimental data to be compared.

[0023] Extract waveform features from waveform curve data;

[0024] The waveform data and the experimental data to be compared are compared with a preset standard database to obtain the corresponding waveform comparison results and experimental data rationality judgment results.

[0025] The waveform comparison results and the experimental data rationality judgment results are combined to form the experimental data detection results.

[0026] Furthermore, the step of generating an integrity detection result based on the text information specifically includes:

[0027] Based on a preset text framework, each section of the text to be detected is extracted from the text information. The text framework includes the experimental objective, experimental principle, experimental steps, and experimental conclusions.

[0028] After matching each text section to be detected with the preset report section, a validity check is performed again. The matching check specifically detects whether each preset report section appears in the corresponding text section to be detected.

[0029] Integrity detection results are generated based on the matching detection results and validity detection results.

[0030] Furthermore, the validity detection specifically includes:

[0031] Obtain the set of necessary knowledge points and the set of necessary content items corresponding to the circuit experiment report from the preset report chapters;

[0032] The corresponding text chapters to be detected are subjected to text recognition to obtain content features;

[0033] The validity detection results are obtained by matching the content features with the set of required knowledge points and the set of required content items, respectively.

[0034] On the other hand, the present invention also provides an automatic grading device for experimental reports, the device comprising:

[0035] The scanning module is used to acquire an electronic version of the circuit experiment report and to scan and parse the circuit experiment report to obtain report data. The report data includes at least circuit diagrams, waveform diagrams, experimental data, and text information.

[0036] The review module is used to review reports based on data and a preset standard database.

[0037] This invention provides a method and apparatus for automatically grading experimental reports. Compared with existing technologies, this method first acquires an electronic version of the circuit experiment report, and then scans and parses the report to obtain report data. The report data includes at least circuit diagrams, waveform diagrams, experimental data, and text information. Then, it performs grading based on the report data and a preset standard database. This method enables rapid and accurate automatic review and grading of circuit experiment reports. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 The diagram shown is a flowchart illustrating the automatic grading method for experimental reports provided in the embodiments of this specification.

[0040] Figure 2 The diagram shown is a structural schematic of the automatic grading device for experimental reports provided in the embodiments of this specification. Detailed Implementation

[0041] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] like Figure 1 The diagram shows a flowchart of the automatic grading method for experimental reports provided in the embodiments of this specification. Although this specification provides the method operation steps or device structure shown in the following embodiments or figures, based on convention or without creative effort, the method or device may include more or fewer operation steps or module units after partial merging. In steps or structures where there is no necessary causal relationship in logic, the execution order of these steps or the module structure of the device are not limited to the execution order or module structure shown in the embodiments or figures of this specification. When the method or module structure is applied in actual devices, servers, or terminal products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even in a distributed processing or server cluster implementation environment).

[0043] The automatic grading method for experimental reports provided in the embodiments of this specification can be applied to terminal devices such as client and server, for example... Figure 1 As shown, the method specifically includes the following steps:

[0044] Step S101: Obtain the electronic version of the circuit experiment report, and scan and parse the circuit experiment report to obtain report data. The report data includes at least circuit diagrams, waveform diagrams, experimental data, and text information.

[0045] Specifically, the system retrieves the report file and performs multimodal content parsing. The student-submitted report includes circuit diagrams, waveform screenshots, and data tables. The system first parses the overall structure of the report, identifying whether it contains pre-defined sections such as experimental objective, experimental principle, experimental steps, experimental data, experimental analysis, and experimental conclusions. Then, it extracts the main text, experimental images, experimental data tables, and any existing simulation code or hardware descriptions. For the text portion, the system extracts theoretical analysis, formula derivations, and experimental conclusions. For the image portion, the system identifies the types of components, parameter labels, and connection relationships in the circuit diagram, and identifies peak characteristics, amplitude changes, and response trends in the oscilloscope waveforms. For the table portion, the system extracts the field names and specific values ​​of the experimental data for subsequent rationality analysis.

[0046] During the image analysis stage, this invention goes beyond simply identifying component symbols; it further extracts the wire connection relationships in the circuit diagram and reconstructs the corresponding logical topology. This aligns with the "logical topology semantic understanding of image analysis" and "deep extraction of circuit topology logic" described in the "Explanation of Core Patent Differences," meaning it not only identifies "what components are present" but also "how these components are connected and whether the connections satisfy the corresponding physical logic."

[0047] Step S102: Review the report data and the preset standard database.

[0048] Specifically, the default standard database first obtains the experiment manual (PDF format), standard circuit diagram (image format), reference waveform diagram (oscilloscope screenshot), and grading details (Word format). In addition, it can also include historical excellent experiment reports, safety specification documents, and common error cases for subsequent knowledge base expansion and incremental updates of bad cases.

[0049] After receiving the aforementioned standard answer package, the system executes a batch-based incremental multimodal knowledge base construction process. The following processing steps are performed sequentially: the first batch processes historical excellent reports, the second batch processes relevant chapters from lab manuals and textbooks, and the third batch adds safety specifications and common error cases. After each batch of documents is processed, the system backs up the current knowledge base and saves the processing progress to support resume functionality and subsequent incremental updates.

[0050] In the specific processing, the system performs multimodal parsing on each document to extract knowledge entities and relational information. For lab manuals, the system extracts the experiment name, experimental principle, formulas, key knowledge points, experimental specifications, and safety requirements; for standard circuit diagrams, the system extracts information on components such as resistors, capacitors, and inductors, as well as their connection relationships; for reference waveform diagrams, the system extracts peak positions, frequency variations, and amplitude characteristics; and for grading rules, the system extracts grading dimensions, grading weights, and corresponding evaluation rules. Subsequently, the system automatically constructs an entity-relationship knowledge graph based on the extraction results, forming a standard knowledge base for grading lab reports for this course.

[0051] In this embodiment of the application, the review based on report data and a preset standard database specifically includes:

[0052] Generate integrity detection results based on the text information;

[0053] Based on the circuit diagram and the preset standard database, generate circuit connection logic judgment results;

[0054] The experimental data detection results are obtained based on the waveform diagram, experimental data, and preset standard database.

[0055] The integrity test results, circuit connection logic judgment results, and experimental data test results are combined into the review results.

[0056] Specifically, the preset standard database is generated based on the experimental manual, standard circuit diagrams, reference waveform diagrams, and grading guidelines. Student-submitted reports include circuit diagrams, waveform screenshots, data tables, and other data. The system first parses the overall structure of the report, identifying whether it contains preset sections such as experimental objective, experimental principle, experimental steps, experimental data, experimental analysis, and experimental conclusions. Then, it extracts the main text, experimental images, experimental data tables, and any existing simulation code or hardware descriptions. For the text portion, the system extracts theoretical analysis, formula derivations, and experimental conclusions; for the image portion, the system identifies the types of components, parameter labels, and connection relationships in the circuit diagram, and identifies peak characteristics, amplitude changes, and response trends in the oscilloscope waveforms; for the table portion, the system extracts the field names and specific values ​​of the experimental data for subsequent rationality analysis.

[0057] In this embodiment of the application, the step of generating circuit connection logic judgment results based on the circuit diagram and a preset standard database specifically includes:

[0058] The circuit diagram is preprocessed to obtain an image of the circuit to be identified;

[0059] The image of the circuit to be identified is used to extract information about each component and its parameters, as well as a candidate set of wires.

[0060] The electrical connection relationships between different components are determined based on the candidate set of wires, each component and its parameter information.

[0061] Based on the electrical connections and components, generate a circuit topology diagram or circuit netlist to be reviewed;

[0062] The circuit connection logic judgment result is obtained by reviewing the circuit topology diagram or circuit netlist to be reviewed based on the preset standard database.

[0063] Specifically, firstly, the circuit diagram undergoes image preprocessing to obtain the circuit image to be identified. Image preprocessing includes, but is not limited to, one or more combinations of image denoising, grayscale conversion, binarization, tilt correction, edge enhancement, and layout cropping. Then, existing image recognition algorithms, line segment detection algorithms, contour analysis algorithms, image segmentation algorithms, etc., are used to identify the circuit image to obtain component identification results and wire identification results. The component identification results include at least the component type, component location, component port location, component label, and component parameters. The wire candidate set includes each identified candidate wire. Then, based on the wire candidate set, component port location, ... Node identifiers and text annotations determine the electrical connections between different components via which ports they are connected. Then, based on the electrical connections and component identification results, a circuit topology diagram and a circuit netlist to be approved are generated. Finally, the circuit topology diagram or circuit netlist to be approved is matched with a standard circuit topology diagram or standard circuit netlist in a preset standard database to obtain a circuit connection logic judgment result. The circuit connection logic judgment result includes at least one or more of the following: correct connection, incorrect connection, missing connection, redundant connection, missing component, incorrect component type, incorrect component parameter, incorrect port access, and incorrect node connection.

[0064] In this embodiment of the application, obtaining the experimental data detection result based on the waveform, experimental data, and preset standard database specifically includes:

[0065] The waveform image is preprocessed to obtain the waveform image to be identified, and the experimental data is processed and extracted to obtain the structured result of the experimental data.

[0066] The waveform image to be identified is identified to obtain waveform curve data, and the fields in the experimental data structured result are replaced with standard fields to obtain the experimental data to be compared.

[0067] Extract waveform features from waveform curve data;

[0068] The waveform data and the experimental data to be compared are compared with a preset standard database to obtain the corresponding waveform comparison results and experimental data rationality judgment results.

[0069] The waveform comparison results and the experimental data rationality judgment results are combined to form the experimental data detection results.

[0070] Specifically, image preprocessing of the waveform image includes one or more of the following: image denoising, grayscale conversion, coordinate axis enhancement, curve enhancement, layout cropping, and tilt correction. Then, existing image recognition algorithms, curve detection algorithms, pixel trajectory extraction algorithms, and multimodal visual understanding models are used to locate and identify the waveform image to be recognized, obtaining waveform curve data, coordinate axis information, scale information, waveform curve regions, waveform annotation information, and channel identification information. The waveform curve data may include coordinate axis information and scale information. Then, waveform features are calculated based on the coordinate axis information, scale information, and waveform curve data. Waveform features include at least one or more of the following: amplitude, period, frequency, peak value, valley value, phase difference, duty cycle, rising edge, falling edge, and waveform change trend. After processing the experimental data, the structured experimental data results are extracted. Specifically, the experimental data undergoes table structure recognition and data field extraction to obtain the structured experimental data results. The structured experimental data results include at least one or more of the following: variable names, measured values, units, experimental conditions, calculation results, and error analysis data. Then, based on a semantic understanding model or rule matching algorithm, the variable names, units, and experimental conditions in the structured experimental data results are standardized to correspond to standard fields in the preset standard database. The waveform features and the structured experimental data results are compared with reference waveform features, standard experimental data ranges, theoretical calculation results, and scoring rules in the preset standard database to obtain waveform matching results and data reasonableness judgment results. Based on the waveform matching results and data reasonableness judgment results, experimental data detection results are generated. These experimental data detection results include at least one or more of the following: correct waveform, abnormal waveform, abnormal amplitude, abnormal frequency, abnormal phase, missing data, data outside the reasonable range, incorrect units, incorrect calculation results, and missing error analysis data.

[0071] In this embodiment of the application, generating an integrity detection result based on the text information specifically includes:

[0072] Based on a preset text framework, each section of the text to be detected is extracted from the text information. The text framework includes the experimental objective, experimental principle, experimental steps, and experimental conclusions.

[0073] After matching each text section to be detected with the preset report section, a validity check is performed again. The matching check specifically involves checking whether each preset report section appears in the corresponding text section to be detected.

[0074] Integrity detection results are generated based on the matching detection results and validity detection results.

[0075] Specifically, the preset text framework includes, but is not limited to, one or more of the following: experimental objective, experimental principle, experimental steps, experimental data, experimental analysis, and experimental conclusions. After preprocessing the text information, the text to be detected is obtained. Preprocessing includes at least one or more of the following: header and footer removal, table of contents removal, whitespace character normalization, paragraph merging, garbled character correction, and duplicate text removal. Then, chapter title recognition and paragraph boundary recognition are performed on the text to be detected to obtain each chapter of the text to be detected. Each chapter includes the chapter and its corresponding main text content. Finally, based on one or more of the following: a preset chapter template, keyword matching rules, semantic similarity model, or large language model, the multiple candidate chapters are... Each section is mapped to a preset report chapter, which at least includes the experimental objective, experimental principle, experimental steps, experimental data, experimental analysis, and experimental conclusions, i.e., corresponds to a preset text framework. Then, it is detected whether each preset report chapter appears in the corresponding text chapter to be detected to obtain a matching detection result. At the same time, a validity detection is performed to obtain a validity detection result. Based on the matching detection result and the validity detection result, missing chapters, blank chapters, chapters with insufficient content, and chapters with abnormal content can be identified. The completeness detection result includes at least one or more of the following: chapter complete, chapter missing, chapter order abnormal, chapter content insufficient, chapter content not matching the title, and missing necessary content.

[0076] In this embodiment of the application, the validity detection specifically includes:

[0077] Obtain the set of necessary knowledge points and the set of necessary content items corresponding to the circuit experiment report from the preset report chapters;

[0078] The corresponding text chapters to be detected are subjected to text recognition to obtain content features;

[0079] The validity detection results are obtained by matching the content features with the set of required knowledge points and the set of required content items, respectively.

[0080] Specifically, validity detection can be described as determining whether the main text content of a corresponding chapter meets preset validity conditions. These preset validity conditions include at least one or more of the following: the main text length reaches a preset threshold, it contains key terms, it contains necessary formulas, it contains experimental operation descriptions, and it contains result analysis statements. First, the necessary knowledge point set and necessary content item set corresponding to the circuit experiment report are obtained from the preset report chapters. Then, entity recognition, keyword extraction, and semantic vectorization are performed on the corresponding text chapters to be detected to obtain the chapter's content features. These content features are then matched with the necessary knowledge point set and necessary content item set to obtain the knowledge point coverage result. Finally, the content features are matched with the necessary knowledge point set and necessary content item set respectively, i.e., it is determined whether the above-mentioned preset validity conditions are met, thereby obtaining the validity detection result.

[0081] During the image analysis stage, this invention does not merely stop at the level of component symbol recognition, but further extracts the wire connection relationships in the circuit diagram and reconstructs the corresponding logical topology. This point is consistent with the "logical topology semantic understanding of image analysis" and "deep extraction of circuit topology logic" described in the "Explanation of Core Patent Differences," that is, it not only identifies "what components are there," but also identifies "how these components are connected and whether the connection satisfies the corresponding physical logic."

[0082] In this embodiment, student lab reports are evaluated from at least the following dimensions:

[0083] First, the system checks the report's structural integrity. It automatically checks whether the report includes sections such as the experimental objective, principle, procedure, data, analysis, and conclusions, and identifies and records any missing items.

[0084] Second, the accuracy of theoretical analysis is evaluated. The system performs semantic understanding on the theoretical analysis content in student reports and combines it with standard knowledge points in the knowledge graph to calculate coverage and similarity matching in order to determine whether the formula derivation, experimental principle explanation, and analysis process are accurate.

[0085] Third, image content understanding and circuit connection correctness evaluation. The system extracts component information and logical topology from the circuit diagrams in student reports and matches them with the knowledge graph structure corresponding to standard circuit diagrams to determine whether the circuit connections are correct and the parameter annotations are accurate. This process enables the judgment of the physical connection logic of the circuit, rather than just pixel-level or symbol-level recognition.

[0086] Fourth, waveform feature recognition and experimental data rationality analysis. The system extracts waveform features from oscilloscope screenshots and compares them with the numerical trends in the experimental data table to determine whether the experimental data is within a reasonable range, whether the waveform meets theoretical expectations, and whether necessary experimental results such as frequency response curves are missing.

[0087] Fifth, compliance check for experimental safety regulations. Based on the experimental regulations and safety requirements in the knowledge base, the system determines whether the report contains necessary experimental specification instructions, error analysis, or safety-related content.

[0088] After scoring is completed, the system enters the personalized diagnostic report generation stage. This process corresponds to "Innovation Point 3: Personalized Diagnostic Report Generation" in the application documents. The system automatically locates the error, specifically at the paragraph, chart, or line of code; and generates hierarchical feedback based on the error type, including fatal errors, main problems, and improvement suggestions; it also provides a reference index and excellent report examples in conjunction with a knowledge base.

[0089] In this embodiment, the diagnostic report output by the system includes at least an overall evaluation, advantages, main problems, improvement suggestions, and reference examples. The main problems may include "The formula derivation on page 3 is incorrect," etc. Figure 2 The report contained errors such as "incorrect C1 parameter labeling," "missing frequency response curve," and "failure to analyze the variation of the quality factor Q value." Suggestions for improvement could include "re-deriving the relevant formulas from the textbook," "adding a frequency response curve," and "modifying the report based on excellent examples." This output method not only provides the scoring results but also offers good interpretability and guidance.

[0090] Based on the above-described method for automatically grading experimental reports, one or more embodiments of this specification also provide a platform or terminal for automatically grading experimental reports. This platform or terminal may include devices, software, modules, plug-ins, servers, clients, etc., using the methods described in the embodiments of this specification, combined with necessary hardware implementation devices. Based on the same innovative concept, the systems in one or more embodiments provided in this specification are as described in the following embodiments. Since the implementation schemes and methods for solving the system problem are similar, the specific system implementation in the embodiments of this specification can refer to the implementation of the aforementioned methods. Repeated details will not be repeated. The terms "unit" or "module" used below can refer to a combination of software and / or hardware that achieves a predetermined function. Although the systems described in the following embodiments are preferably implemented in software, hardware implementation, and a combination of software and hardware, are also possible and contemplated.

[0091] Specifically, Figure 2 This is a schematic diagram of the module structure of one embodiment of the automatic experimental report grading device provided in this specification, as shown below. Figure 2 As shown, the automatic grading device for experimental reports provided in this manual includes:

[0092] The scanning module 201 is used to acquire an electronic version of the circuit experiment report and to scan and parse the circuit experiment report to obtain report data. The report data includes at least circuit diagrams, waveform diagrams, experimental data, and text information.

[0093] The review module 202 is used to review reports based on report data and a preset standard database.

[0094] It should be noted that the above system may include other implementation methods according to the description of the corresponding method embodiments. The specific implementation methods can be referred to the description of the corresponding method embodiments above, and will not be elaborated here.

[0095] This application also provides an electronic device, including:

[0096] processor;

[0097] Memory used to store the processor's executable instructions;

[0098] The processor is configured to perform the methods provided in the embodiments described above.

[0099] The electronic device provided in this application embodiment stores executable instructions of the processor in its memory. When the processor executes the executable instructions, it can first obtain an electronic version of the circuit experiment report, and then scan and parse the circuit experiment report to obtain report data. The report data includes at least circuit diagrams, waveform diagrams, experimental data, and text information. Then, it reviews the report data based on a preset standard database. This allows for quick and accurate automatic review and approval of circuit experiment reports.

[0100] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0101] The methods or apparatus described in the above embodiments of this specification can implement business logic through a computer program and record it on a storage medium. The storage medium can be read and executed by a computer to achieve the effects of the solutions described in the embodiments of this specification, such as:

[0102] Obtain an electronic version of the circuit experiment report, and scan and parse the circuit experiment report to obtain report data. The report data includes at least circuit diagrams, waveform diagrams, experimental data, and text information.

[0103] The review is based on report data and a pre-set standard database.

[0104] The storage medium can include physical devices for storing information, typically digitizing the information and then storing it using electrical, magnetic, or optical methods. The storage medium can include: devices that store information using electrical energy, such as various types of memory, like RAM and ROM; devices that store information using magnetic energy, such as hard disks, floppy disks, magnetic tapes, magnetic core memory, bubble memory, and USB flash drives; and devices that store information using optical methods, such as CDs or DVDs. Of course, there are other readable storage media, such as quantum memories and graphene memories.

[0105] The embodiments in this specification are not limited to conforming to industry communication standards, standard computer resource data update and data storage rules, or the situations described in one or more embodiments of this specification. Slightly modified implementations based on certain industry standards or custom methods or embodiments can also achieve the same, equivalent, or similar, or predictable, implementation effects as described above. Embodiments that utilize these modified or modified methods for data acquisition, storage, judgment, and processing still fall within the scope of optional implementations of the embodiments in this specification.

[0106] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0107] The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or plug-ins may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0108] These computer program instructions can also be loaded onto a computer or other programmable resource data updating device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0109] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0110] Those skilled in the art will recognize that the embodiments described herein are intended to help the reader understand the principles of the invention, and should be understood that the scope of protection of the invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific modifications and combinations based on the technical teachings disclosed in this invention without departing from the spirit of the invention, and these modifications and combinations are still within the scope of protection of this invention.

Claims

1. A method for automatically grading experimental reports, characterized in that, The method includes: Obtain an electronic version of the circuit experiment report, and scan and parse the circuit experiment report to obtain report data. The report data includes at least circuit diagrams, waveform diagrams, experimental data, and text information. The review is based on report data and a pre-set standard database.

2. The automatic grading method for circuit experiment reports as described in claim 1, characterized in that, The preset standard database is generated based on the experimental instructions, standard circuit diagrams, reference waveform diagrams, and review guidelines.

3. The automatic grading method for circuit experiment reports as described in claim 1, characterized in that, The review process based on report data and a preset standard database specifically includes: Generate integrity detection results based on the text information; Based on the circuit diagram and the preset standard database, generate circuit connection logic judgment results; The experimental data detection results are obtained based on the waveform diagram, experimental data, and preset standard database. The integrity test results, circuit connection logic judgment results, and experimental data test results are combined into the review results.

4. The automatic grading method for circuit experiment reports as described in claim 3, characterized in that, The generation of circuit connection logic judgment results based on the circuit diagram and the preset standard database specifically includes: The circuit diagram is preprocessed to obtain an image of the circuit to be identified; The image of the circuit to be identified is used to extract information about each component and its parameters, as well as a candidate set of wires. The electrical connection relationships between different components are determined based on the candidate set of wires, each component and its parameter information. Based on the electrical connections and components, generate a circuit topology diagram or circuit netlist to be reviewed; The circuit connection logic judgment result is obtained by reviewing the circuit topology diagram or circuit netlist to be reviewed based on the preset standard database.

5. The automatic grading method for circuit experiment reports as described in claim 3, characterized in that, The experimental data detection results obtained based on the waveform, experimental data, and preset standard database specifically include: The waveform image is preprocessed to obtain the waveform image to be identified, and the experimental data is processed and extracted to obtain the structured result of the experimental data. The waveform image to be identified is identified to obtain waveform curve data, and the fields in the experimental data structured result are replaced with standard fields to obtain the experimental data to be compared. Extract waveform features from waveform curve data; The waveform data and the experimental data to be compared are compared with a preset standard database to obtain the corresponding waveform comparison results and experimental data rationality judgment results. The waveform comparison results and the experimental data rationality judgment results are combined to form the experimental data detection results.

6. The automatic grading method for circuit experiment reports as described in claim 3, characterized in that, The generation of integrity detection results based on the text information specifically includes: Based on a preset text framework, each section of the text to be detected is extracted from the text information. The text framework includes the experimental objective, experimental principle, experimental steps, and experimental conclusions. After matching each text section to be detected with the preset report section, a validity check is performed again. The matching check specifically involves checking whether each preset report section appears in the corresponding text section to be detected. Integrity detection results are generated based on the matching detection results and validity detection results.

7. The automatic grading method for circuit experiment reports as described in claim 6, characterized in that, The validity test specifically includes: Obtain the set of necessary knowledge points and the set of necessary content items corresponding to the circuit experiment report from the preset report chapters; The corresponding text chapters to be detected are subjected to text recognition to obtain content features; The validity detection results are obtained by matching the content features with the set of required knowledge points and the set of required content items, respectively.

8. An automatic grading device for experimental reports, characterized in that, The device includes: The scanning module is used to acquire an electronic version of the circuit experiment report and to scan and parse the circuit experiment report to obtain report data. The report data includes at least circuit diagrams, waveform diagrams, experimental data, and text information. The review module is used to review reports based on data and a preset standard database.

Images