Automatic scoring method and system for computer examination

Abstract

The invention discloses an automatic scoring method and system for a computer examination, and the method and system have the beneficial effects that the typing speed and accuracy are calculated in real time, and the accuracy of a scoring result is improved; standard answers are intelligently processed, fault tolerance is improved, semantic extension, error correction mapping, region weighted matching and the like are introduced to process the standard answers, the matching diversity and fault tolerance are improved, and different examination requirements are met; the dynamic scoring rule adapts to multiple scenes: a dynamic weight adjustment mechanism flexibly configures the scoring rule according to the priorities of accuracy and speed, and meets the requirements of different examination scenes; a Levenshtein distance algorithm is improved, and context dynamic matching and a big data model are combined, so that multi-dimensional intelligent scoring is realized, comprehensive consideration of speed and accuracy is realized, and an accurate scoring result is obtained; automatic management is achieved, examination efficiency is improved, automatic scoring and statistics are achieved, scores can be fed back in real time, and efficiency and convenience are improved.

Description

Technical Field

[0001] The invention belongs to the field of computer test scoring, and in particular relates to an automatic scoring method and system for computer tests. Background Art

[0002] With the rapid development of computer technology, computer-based examinations have gradually become a new form of examination. Computer-based examinations have reduced the workload of staff to a certain extent and improved work efficiency. At the same time, computer-based examinations also have many advantages such as being fast, convenient, efficient, and safe. A very important process in computer-based examinations is automatic scoring.

[0003] In the field of computer-based examinations, automatic scoring technology has become relatively mature. Existing technologies usually evaluate test results based on the typing speed and accuracy of candidates. However, existing technologies have the following defects: (1) The impact of heterogeneous characters is not fully considered: In texts containing special characters or punctuation marks, traditional algorithms sometimes fail to accurately evaluate the heterogeneity of candidate input and the match with the standard answer; (2) It is difficult to conduct refined analysis: Some scoring systems fail to consider the diversity of candidate input habits, such as the flexibility of synonyms or approximate expressions; (3) Lack of real-time performance: In a certain writing method, real-time input increases the complexity of scoring while listening and typing. Existing algorithms are deficient in handling the dynamics of audio synchronous typing; (4) Inadequate error correction capabilities: The tolerance and penalty mechanism for input errors are not flexible enough, resulting in poor scoring results.

[0004] Therefore, how to design a method to improve the robustness and accuracy of automatic scoring algorithms to meet the high evaluation standards of computer-based examinations is a technical problem to be solved. Summary of the invention

[0005] Based on this, it is necessary to provide an automatic scoring method and system for computer examinations in response to the problems of the prior art.

[0006] In a first aspect, an embodiment of the present application provides an automatic scoring method for a computer test, comprising the following steps: S1: Collect all the computer key input events of the examinee in answering questions during the test, record the characters and input time of each input event, and the characters and input time of all the input events of the examinee's answering questions constitute the answer input data; S2: Based on the answer input data, obtaining the candidate's input time data, the input time data including the input time interval and average time interval of each character; S3: based on the answer input data and the input time data, obtaining the examinee's input average speed and net average input speed; S4: inputting the input average speed and the input net average speed into a preset speed model to obtain a total average speed; S5: Compare the input answer data with the standard answer to obtain a basic accuracy rate; S6: Performing a weighted comparison process on the input answer data and the standard answer to obtain a weighted accuracy rate; S7: performing error correction and comparison processing on the input answer data and the standard answer to obtain the error tolerance accuracy; S8: Inputting the basic accuracy, the weighted accuracy, and the error-tolerant accuracy into a preset accuracy model to obtain the total accuracy of the examinee; S9: inputting the total average speed and the total accuracy into a preset scoring model to obtain a comprehensive score of the examinee; The answer input data is stored in the form of a sequence: ; The total number of characters entered by the examinee when answering the question. and Respectively characters and their input time, .

[0007] Preferably, the input time interval of each character and the average time interval They are expressed by the following formulas: (1); (2); The input average speed is and enter the net average speed They are obtained by the following formulas: (3); (4); in, For the Characters and Characters The input time interval; is the total input time of the candidate, .

[0008] Preferably, the preset speed model is expressed by the following formula: (5); in, is the overall average speed.

[0009] Preferably, step S5 comprises: S51: Compare the answer input data with the standard answer to obtain the number of matching characters; S52: Obtaining a basic accuracy rate according to the number of matching characters and the total number of characters in the standard answer; Among them, the basic accuracy It is expressed by the following formula: (6); in, is the number of characters to match, is the total number of characters of the standard answer.

[0010] Preferably, step S6 comprises: S61: Divide the standard answer into a plurality of different regions according to importance and assign a weight to each region to obtain weighted standard answer data; S62: Compare the question input data with the weighted standard answer data to obtain the number of matching characters in each area; S63: Obtaining a weighted accuracy rate according to the number of matching characters in each region, the total number of characters in each region, and the weight of each region; Among them, the weighted accuracy It is expressed by the following formula: (7); in, The total number of regions divided by importance is the standard answer. For the Regions, No. The number of matching characters in the region, For the The total number of characters in the area, Requirements: .

[0011] Preferably, step S7 includes: S71: Correcting the answer input data based on the fault tolerance rule to obtain corrected test input data; S72: Compare the corrected answer input data with the standard answer to obtain a corrected matching character number; S73: Obtaining an error tolerance accuracy rate according to the corrected matching character number and the total character number of the standard answer; Among them, the error tolerance accuracy It is expressed by the following formula: (8); in, To correct the number of matching characters.

[0012] Preferably, the input answer data is compared with the standard answer by using a Levenshtein distance algorithm; Performing a weighted comparison between the input answer data and the standard answer using a Levenshtein distance algorithm; The input data for answering the question is compared with the standard answer through the Levenshtein distance algorithm for error correction.

[0013] Preferably, the preset accuracy model is expressed by the following formula: (9); in, is the overall accuracy, , and They are the weight of the basic accuracy, the weight of the weighted accuracy, and the weight of the fault-tolerant accuracy, and the three meet the following conditions: .

[0014] Preferably, the preset scoring model is expressed by the following formula: (10); in, For the comprehensive rating, is the accuracy weight, is the speed weight, and both satisfy the following conditions: and .

[0015] In a second aspect, an embodiment of the present application provides an automatic scoring system for a computer test, comprising: The answer data collection module is used to collect all the computer key input events of the examinee in answering questions during the examination, record the characters of each input event and the input time of the characters, and the characters of all the input events of the examinee's answering questions and the input time of the characters constitute the answer input data; A time data acquisition module, used to obtain the candidate's input time data based on the answer input data, wherein the input time data includes the input time interval and average time interval of each character; An average speed acquisition module, used to obtain the examinee's input average speed and input net average speed based on the answer input data and the input time data; A total speed acquisition module, used for inputting the input average speed and the input net average speed into a preset speed model to obtain a total average speed; A basic accuracy determination module is used to compare the answer input data with the standard answer to obtain a basic accuracy rate; A weighted accuracy determination module is used to perform a weighted comparison process on the answer input data and the standard answer to obtain a weighted accuracy rate; A fault tolerance accuracy determination module is used to perform error correction and comparison processing on the answer input data and the standard answer to obtain the fault tolerance accuracy; A total accuracy determination module, used for inputting the basic accuracy, the weighted accuracy, and the fault-tolerant accuracy into a preset accuracy model to obtain the total accuracy of the examinee; A comprehensive score determination module, used for inputting the total average speed and the total accuracy into a preset scoring model to obtain a comprehensive score for the examinee; The answer input data is stored in the form of a sequence: ; The total number of characters entered by the examinee when answering the question. and Respectively characters and their input time, .

[0016] Compared with the prior art, the present invention has the following beneficial effects: (1) Accurately control the scoring process and reduce manual errors: The present invention eliminates the subjective bias of manual scoring by calculating the typing speed and accuracy in real time, greatly improving the accuracy of the scoring results; (2) Intelligently process standard answers and improve fault tolerance and adaptability: The present invention introduces methods such as semantic expansion, error correction mapping and regional weighted matching to intelligently process standard answers, significantly improving the diversity and fault tolerance of answer matching, and can adapt to the needs of diversified examinations; (3) Dynamic scoring rules to adapt to multi-scenario needs: The scoring rules of the present invention are combined with a dynamic weight adjustment mechanism, and the scoring rules are flexibly configured according to the priority of accuracy and speed, which can meet the personalized requirements of different examination scenarios and expand the application scenarios; (4) Multi-dimensional algorithm optimization to improve scoring accuracy: The present invention is based on the Levenshtein distance algorithm for improvement, and combines context dynamic matching with big data models to achieve multi-dimensional intelligent scoring, ensuring that the comprehensive consideration of speed and accuracy is more refined to obtain more accurate scoring results; (5) Efficient automated management to improve examination efficiency: The present invention can realize automated scoring and statistical processes, and can provide real-time feedback on scores, greatly improving the efficiency and convenience of examination management and score analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By referring to the following drawings, the exemplary embodiments of the present invention can be more completely understood. The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present invention and do not constitute a limitation of the present invention. In the drawings, the same reference numerals generally represent the same parts or steps.

[0018] Figure 1 A flowchart of an automatic scoring method for a computer test provided in an embodiment of the present application; Figure 2 A schematic diagram of an automatic scoring system for a computer test provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0020] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0021] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0022] Example 1 Reference Figure 1 This embodiment discloses a method for automatic scoring of a computer test, comprising the following steps: S1: Collect all the computer key input events of the examinee during the test, record the characters and input time of each input event, and the characters and input time of all the input events of the examinee's answer constitute the answer input data; Specifically, during the test, the examinee types and inputs through the PC. The system monitors the input events of each key in real time and records the input characters and their input time. The system records the time of each character input and calculates the interval time between characters for subsequent calculation of typing speed.

[0023] In this embodiment, the answer input data is stored in the form of a sequence: ; The total number of characters entered by the examinee when answering the question. and Respectively characters and their input time, .

[0024] S2: Based on the answer input data, obtain the candidate's input time data, the input time data includes the input time interval and average time interval of each character; Specifically, the input time interval between characters It is obtained by the following formula (1): (1); After calculating the input time intervals between all characters, the average time interval is obtained based on all the time intervals. , which is expressed by the following formula (2): (2); in, For the Characters and Characters The input time interval.

[0025] S3: based on the answer input data and the input time data, obtaining the examinee's average input speed and net average input speed; Specifically, based on the total number of characters The total input time of the characters is used to obtain the average input speed of the candidates. , expressed by the following formula (3): (3); After removing the influence of idle time, the net average speed of the examinee's input is obtained. , expressed by the following formula (4): (4); in, is the total input time of the candidate, .

[0026] In actual operation, the average speed data can be further optimized by counting additional information, such as: (1) Counting the number of rollbacks: recording the number of characters deleted by the candidate , as a supplementary indicator for speed data evaluation; (2) Counting the total number of key presses: Counting the actual number of key presses , including all input characters and modification operations, as a supplementary indicator for speed data evaluation.

[0027] S4: inputting the input average speed and the input net average speed into a preset speed model to obtain a total average speed; Specifically, in order to balance the calculation error and obtain a more accurate speed, in this embodiment, the input average speed and the input net average speed are arithmetic averaged to obtain the total average speed through the following formula: : (5).

[0028] S5: Compare the answer input data with the standard answer to obtain the basic accuracy rate; Specifically, after obtaining the total average speed, according to the design of the algorithm, it is necessary to obtain the accuracy data of the examinees' answers. Before the accuracy data is obtained, the standard answers need to be processed first. The standard answers and test questions are entered into the system in advance by the administrator. The standard answers can be text data with full word matching, or they can be formatted as required. The system preprocesses the standard answers in multiple dimensions as follows: Semantic Chunking: Break down the standard answer of a long text into multiple small units (such as sentences or phrases) to facilitate local comparison and improve comparison efficiency.

[0029] Synonym expansion: Synonyms for standard answers are expanded through natural language processing technology (NLP), allowing synonymous expressions to be considered as correct answers.

[0030] Common error correction model: Use big data to analyze common typos and confusing characters, and establish mapping rules to ensure the system's fault tolerance.

[0031] In this embodiment, more specifically, the standard answer may be processed as follows: (1) Character-level cleaning: remove spaces and punctuation marks and convert them to lowercase; (2) NLP-based semantic expansion: Introduce semantic networks (such as WordNet) or machine learning models to generate acceptable alternative expressions for standard answers; example: expand "submit a report" to "submit a document" or "submit a document"; (3) Error correction and mapping: Correct the candidate input based on the common error model to make the matching process more robust. Example rules: “1” → “l”, “0” → “0”.

[0032] In this example, the accuracy data is determined by weighting the accuracy data of three dimensions (basic accuracy, weighted accuracy and fault-tolerant accuracy), which can make the accuracy assessment of the candidates more accurate.

[0033] Specifically, step S5 includes: S51: Compare the input data of the answer with the standard answer to obtain the number of matching characters ; S52: Obtaining a basic accuracy rate according to the number of matching characters and the total number of characters of the standard answer; Among them, the basic accuracy It is expressed by the following formula: (6); in, is the number of characters to match, is the total number of characters of the standard answer.

[0034] In this embodiment, the input data of the answer is compared with the standard answer by using the Levenshtein distance algorithm. The Levenshtein distance algorithm is a prior art and will not be described in detail here.

[0035] S6: Perform weighted comparison processing on the input data of the answer and the standard answer to obtain the weighted accuracy rate; Specifically, step S6 includes: S61: Divide the standard answer into multiple different areas according to importance and assign a weight to each area to obtain weighted standard answer data; S62: Compare the answer input data with the weighted standard answer data to obtain the number of matching characters in each area; S63: Obtaining a weighted accuracy rate according to the number of matching characters in each region, the total number of characters in each region, and the weight of each region; Among them, the weighted accuracy It is expressed by the following formula: (7); in, The total number of regions divided by importance is the standard answer. For the Regions, No. The number of matching characters in the region, For the The total number of characters in the region; Requirements: .

[0036] In this embodiment, the standard answers are weighted according to the importance of the content. For example, the beginning and the end are more important than the main text, and the regions with high weights are matched first, thereby improving the accuracy of the overall score. At the same time, considering the contextual information of character matching, dynamic weight matching is designed for each region, that is, The value of can be adjusted dynamically according to the content of the region. The specific adjustment principles are as follows: (1) when adjacent characters are similar but out of order, the matching penalty is reduced; (2) considering the higher tolerance of short texts, the penalty for character insertion or deletion is reduced.

[0037] In a preferred embodiment, a machine learning model can also be introduced to update the accuracy data, for example: a model is trained by large-scale computer test data to predict the similarity between the input and the standard answer. Example: Sentence embedding is calculated based on deep learning models such as BERT, and accuracy is scored directly through cosine similarity.

[0038] In this embodiment, the input data for answering the question is weightedly compared with the standard answer through the Levenshtein distance algorithm. The present invention significantly improves the adaptability and scoring accuracy of the traditional Levenshtein distance by introducing regional weighting and contextual dynamic distance, and at the same time has the dynamic adjustment capability supported by big data, which is significantly different from the prior art.

[0039] S7: Perform error correction and comparison processing on the answer input data and the standard answer to obtain the error tolerance accuracy; Specifically, step S7 includes: S71: Correcting the answer input data based on the fault tolerance rule to obtain corrected test input data; S72: Compare the corrected answer input data with the standard answer to obtain the corrected matching character number; S73: Obtaining an error tolerance accuracy rate according to the number of corrected matching characters and the total number of characters of the standard answer; Among them, the error tolerance accuracy It is expressed by the following formula: (8); in, To correct the number of matching characters.

[0040] In this example, the fault tolerance rules (i.e., the error mapping principle, such as "1" and "l", "0" and "0") can be adjusted as needed, and the matching rules can be redefined based on the error correction rules to improve fault tolerance.

[0041] In this example, the Levenshtein distance algorithm is used to compare the input data of the answer with the standard answer for error correction.

[0042] S8: input the basic accuracy, weighted accuracy, and error-tolerant accuracy into a preset accuracy model to obtain the total accuracy of the examinee; Among them, the preset accuracy model is expressed by the following formula: (9); Among them, the preset accuracy model obtains a comprehensive score by weighted combination of the scores of basic accuracy, weighted accuracy and fault-tolerant accuracy. is the overall accuracy, , and They are the weight of the basic accuracy, the weight of the weighted accuracy, and the weight of the fault-tolerant accuracy, and the three meet the following conditions: . Specifically, , and It can be adjusted dynamically according to actual conditions.

[0043] S9: Input the total average speed and total accuracy into the preset scoring model to obtain the comprehensive score of the examinee; Among them, the preset scoring model is expressed by the following formula: (10); in, For the comprehensive rating, is the accuracy weight, Speed ​​weights are used to achieve more refined and flexible scoring rules. The following design principles are used to define the weights of accuracy and typing speed: (1) Accuracy priority: For computer-based exams, accuracy is more important than speed. For example, the accuracy weight can be set to 70% and the typing speed weight can be set to 30%.

[0044] (2) Dynamic adjustment: For different exam types (such as competitions or daily training), weights can be dynamically configured. Adjust weights according to different exam difficulty levels, for example: Basic exam: Accuracy weight =0.8, speed weight =0.2; Speed ​​test: accuracy weight =0.6, speed weight =0.4.

[0045] Combining the design principles of (1) and (2) above, we can obtain and The conditions are: and .

[0046] Example of comprehensive score calculation: Assuming the accuracy is 96%, the typing speed is 85 characters per minute, and the weight is =0.7, =0.3, the comprehensive score .

[0047] After obtaining the comprehensive score of the examinee, the PC can display the examinee's typing speed, accuracy and current score in real time to ensure that the examinee understands his or her performance. At the same time, after the examinee completes the typing test, the final score will be displayed, and the test score will be synchronized to the test management system for subsequent query and statistics.

[0048] Compared with the prior art, the present invention has the following beneficial effects: (1) Accurately control the scoring process and reduce manual errors: The present invention eliminates the subjective bias of manual scoring by calculating the typing speed and accuracy in real time, greatly improving the accuracy of the scoring results; (2) Intelligently process standard answers and improve fault tolerance and adaptability: The present invention introduces methods such as semantic expansion, error correction mapping and regional weighted matching to intelligently process standard answers, significantly improving the diversity and fault tolerance of answer matching, and can adapt to the needs of diversified examinations; (3) Dynamic scoring rules to adapt to multi-scenario needs: The scoring rules of the present invention are combined with a dynamic weight adjustment mechanism, and the scoring rules are flexibly configured according to the priority of accuracy and speed, which can meet the personalized requirements of different examination scenarios and expand the application scenarios; (4) Multi-dimensional algorithm optimization to improve scoring accuracy: The present invention is based on the Levenshtein distance algorithm for improvement, and combines context dynamic matching with big data models to achieve multi-dimensional intelligent scoring, ensuring that the comprehensive consideration of speed and accuracy is more refined to obtain more accurate scoring results; (5) Efficient automated management to improve examination efficiency: The present invention can realize automated scoring and statistical processes, and can provide real-time feedback on scores, greatly improving the efficiency and convenience of examination management and score analysis.

[0049] Example 2 Reference Figure 1 This embodiment discloses an automatic scoring system for computer examinations, including: The answer data collection module is used to collect all the computer key input events of the examinee in answering questions during the examination, record the characters of each input event and the input time, and the characters of all the input events of the examinee's answering questions and the input time of the characters constitute the answer input data; A time data acquisition module is used to obtain the candidate's input time data based on the answer input data, and the input time data includes the input time interval and average time interval of each character; The average speed acquisition module is used to obtain the candidate's input average speed and input net average speed based on the answer input data and input time data; A total speed acquisition module is used to input the input average speed and the input net average speed into a preset speed model to obtain a total average speed; The basic accuracy determination module is used to compare the answer input data with the standard answer to obtain the basic accuracy; The weighted accuracy determination module is used to perform a weighted comparison between the answer input data and the standard answer to obtain the weighted accuracy; The error tolerance accuracy determination module is used to perform error correction and comparison processing on the answer input data and the standard answer to obtain the error tolerance accuracy; The total accuracy determination module is used to input the basic accuracy, weighted accuracy, and error-tolerant accuracy into a preset accuracy model to obtain the total accuracy of the examinee; A comprehensive score determination module is used to input the total average speed and the total accuracy into a preset scoring model to obtain a comprehensive score for the examinee; Among them, the answer input data is stored in sequence form: ; The total number of characters entered by the examinee when answering the question. and Respectively characters and their input time, .

[0050] The system of this embodiment supports administrators to customize scoring rules according to different needs and adjust the influence ratio of accuracy and typing speed on the total score; at the same time, the system of this embodiment can provide real-time feedback on the scores during the candidate's input process, helping the candidate to adjust his or her typing speed and accuracy; finally, the system of this embodiment supports data analysis and historical score backtracking, which is convenient for administrators to count and analyze the performance of candidates.

[0051] The system provided in the embodiment of the present application can implement the above method, and the system can be implemented by software, hardware or a combination of software and hardware. For example, the system may include integrated or separate functional modules or units to perform the corresponding steps in the above methods. In some implementations of the embodiment of the present application, the system provided in the embodiment of the present application is based on the same inventive concept as the method provided in the previous embodiment of the present application, and has the same beneficial effect. No further description is given here.

[0052] It should be noted that the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0053] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0054] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0055] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0056] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0057] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application.

Claims

1. A computer-aided automatic scoring method, characterized in that: The steps include: S1: Collect all the computer key input events of the examinee in answering questions during the test, record the characters and input time of each input event, and the characters and input time of all the input events of the examinee's answering questions constitute the answer input data; S2: Based on the answer input data, obtaining the candidate's input time data, the input time data including the input time interval and average time interval of each character; S3: based on the answer input data and the input time data, obtaining the examinee's input average speed and net average input speed; S4: inputting the input average speed and the input net average speed into a preset speed model to obtain a total average speed; S5: Compare the input answer data with the standard answer to obtain a basic accuracy rate; S6: Performing a weighted comparison process on the input answer data and the standard answer to obtain a weighted accuracy rate; S7: performing error correction and comparison processing on the input answer data and the standard answer to obtain the error tolerance accuracy; S8: Inputting the basic accuracy, the weighted accuracy and the error-tolerant accuracy into a preset accuracy model to obtain the total accuracy of the examinee; S9: inputting the total average speed and the total accuracy into a preset scoring model to obtain a comprehensive score of the examinee; The answer input data is stored in the form of a sequence: ; The total number of characters entered by the examinee when answering the question. and Respectively characters and their input time, .

2. The method according to claim 1, characterized in that The input time interval of each character and the average time interval They are expressed by the following formulas: （1）； （2）； The input average speed is and enter the net average speed They are obtained by the following formulas: （3）； （4）； in, For the Characters and Characters The input time interval; is the total input time of the candidate, .

3. The method according to claim 2, characterized in that The preset speed model is expressed by the following formula: （5）； in, is the overall average speed.

4. The method according to claim 3, characterized in that Step S5 includes: S51: Compare the answer input data with the standard answer to obtain the number of matching characters; S52: Obtaining a basic accuracy rate according to the number of matching characters and the total number of characters in the standard answer; Among them, the basic accuracy It is expressed by the following formula: （6）； in, is the number of characters to match, is the total number of characters of the standard answer.

5. The method according to claim 4, characterized in that Step S6 includes: S61: Divide the standard answer into a plurality of different regions according to importance and assign a weight to each region to obtain weighted standard answer data; S62: Compare the question input data with the weighted standard answer data to obtain the number of matching characters in each area; S63: Obtaining a weighted accuracy rate according to the number of matching characters in each region, the total number of characters in each region, and the weight of each region; Among them, the weighted accuracy It is expressed by the following formula: （7）； in, The total number of regions divided by importance is the standard answer. For the Regions, No. The number of matching characters in the region, For the The total number of characters in the area, Requirements: .

6. The method according to claim 5, characterized in that Step S7 includes: S71: Correcting the answer input data based on the fault tolerance rule to obtain corrected test input data; S72: Compare the corrected answer input data with the standard answer to obtain a corrected matching character number; S73: Obtaining an error tolerance accuracy rate according to the corrected matching character number and the total character number of the standard answer; Among them, the error tolerance accuracy It is expressed by the following formula: （8）； in, To correct the number of matching characters.

7. The method according to claim 6, characterized in that Compare the input answer data with the standard answer using the Levenshtein distance algorithm; Performing a weighted comparison between the input answer data and the standard answer using a Levenshtein distance algorithm; The input data for answering the question is compared with the standard answer through the Levenshtein distance algorithm for error correction.

8. The method according to claim 7, characterized in that The preset accuracy model is expressed by the following formula: （9）； in, is the overall accuracy, , and They are the weight of the basic accuracy, the weight of the weighted accuracy, and the weight of the fault-tolerant accuracy, and all three meet the following conditions: .

9. The method according to claim 8, characterized in that The preset scoring model is expressed by the following formula: （10）； in, For the comprehensive rating, is the accuracy weight, is the speed weight, and both satisfy the following conditions: and .

10. An automatic scoring system for computer examinations, characterized in that: include: The answer data collection module is used to collect all the computer key input events of the examinee in answering questions during the examination, record the characters of each input event and the input time of the characters, and the characters of all the input events of the examinee's answering questions and the input time of the characters constitute the answer input data; A time data acquisition module, used to obtain the candidate's input time data based on the answer input data, wherein the input time data includes the input time interval and average time interval of each character; An average speed acquisition module, used to obtain the examinee's input average speed and input net average speed based on the answer input data and the input time data; A total speed acquisition module, used for inputting the input average speed and the input net average speed into a preset speed model to obtain a total average speed; A basic accuracy determination module is used to compare the answer input data with the standard answer to obtain a basic accuracy rate; A weighted accuracy determination module is used to perform a weighted comparison process on the answer input data and the standard answer to obtain a weighted accuracy rate; A fault tolerance accuracy determination module is used to perform error correction and comparison processing on the answer input data and the standard answer to obtain the fault tolerance accuracy; A total accuracy determination module, used for inputting the basic accuracy, the weighted accuracy, and the fault-tolerant accuracy into a preset accuracy model to obtain the total accuracy of the examinee; A comprehensive score determination module, used for inputting the total average speed and the total accuracy into a preset scoring model to obtain a comprehensive score for the examinee; The answer input data is stored in the form of a sequence: ; The total number of characters entered by the examinee when answering the question. and Respectively characters and their input time, .

Images