A management system for answer sheet generation and preparation
By analyzing task requests and historical records in the answer sheet generation management system, optimizing the answer sheet generation method and regional distribution, the problems of low-quality answer sheet generation efficiency and poor regional design in the existing technology are solved, and more efficient and accurate The answer sheet is generated.
Patent Information
- Application Number
- CN202411044942.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-01
AI Technical Summary
The existing technology cannot perform task combination processing based on the actual number of requested tasks and the correlation situation, resulting in low efficiency in answer sheet generation and inability to optimize the answer sheet area based on historical usage, making it difficult to meet the user needs during peak periods.
A management system for answer sheet generation and preparation is designed, including storage unit, data analysis unit, processing unit and combination processing unit. By analyzing task requests and historical records, the test paper analysis status is determined, the answer sheet generation method is optimized, and the questions are adjusted. area, optimize the answer area, and adapt to the processing methods of different task combinations.
It improves the efficiency and accuracy of answer sheet generation, can better cope with user needs during peak periods, avoid repeated searches and resource imbalance, and improves the system's processing capabilities.
Smart Images

Figure CN118627476B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent paper marking, and in particular to a management system for generating and preparing answer sheets. Background Art
[0002] With the continuous improvement of the informatization of modern education examinations, the application of digital education is increasing. Online answer sheet production based on network marking is to quickly generate answer sheet templates by combining various question types required for the test answer sheet, so that teachers can easily print and print, improving efficiency. However, in the current answer sheet production process, there is a problem that the test paper cannot be automatically classified, which increases the workload of answer sheet production, and the answer area cannot be optimized according to the actual answer situation, resulting in a poor answer sheet user experience. Therefore, how to improve the preparation efficiency of the answer sheet preparation process and the regional distribution design effect of the answer sheet is a technical problem that technical personnel in this field need to solve urgently.
[0003] Chinese patent publication number CN110765995A discloses an answer sheet generation method, identification method, device and storage medium, the method includes: presetting answer sheet style information and UI models corresponding to each question type; generating answer sheets according to answer sheet style information, question information and UI models corresponding to each question type; calculating the coordinate parameters of the filling area of each question in the answer sheet, generating a template file of the answer sheet; storing the answer sheet and the template file of the answer sheet in a preset file format. It can be seen that the above technical solution has the following problems: for multi-request tasks, it is impossible to perform task combination processing according to the number of actual request tasks and related situations, resulting in low task processing efficiency, and it is impossible to optimize the answer sheet according to the historical use of the answer sheet, resulting in the speed and effect of answer sheet preparation being difficult to meet the needs of users during peak usage periods. Summary of the invention
[0004] To this end, the present invention provides a management system for answer sheet generation and preparation, so as to overcome the problems in the prior art that task combination processing cannot be performed according to the number of actually requested tasks and related situations, resulting in low task processing efficiency and the answer sheet cannot be optimized according to the historical usage of the answer sheet, resulting in the answer sheet preparation speed and preparation effect being difficult to meet the user needs during peak usage periods.
[0005] To achieve the above object, the present invention provides a management system for answer sheet generation and preparation, comprising:
[0006] A storage unit for storing matching templates and historical answer records;
[0007] A data analysis unit connected to the storage unit, used to determine the test paper analysis status according to the task request reference value and the task estimated duration, and determine the processing method according to the test paper analysis status, including analyzing the associated status of the requested task, or setting a priority coefficient according to the requested task question quantity reference value;
[0008] a first processing unit, which is connected to the storage unit and the data analysis unit respectively, and is used to determine the association status between each requested task according to the test paper subject corresponding to the requested task and the number of a type of question, and to divide them to obtain a plurality of task combinations, and to determine the answer sheet generation method corresponding to each task combination according to the association status of each task combination, and the answer sheet generation method is reference template matching or combination allocation for the requested task according to the estimated task duration;
[0009] A second processing unit, which is connected to the storage unit and the data analysis unit respectively, and is used to set a priority coefficient according to a reference value of the requested task quantity;
[0010] A combination processing unit is respectively connected to the storage unit, the data analysis unit and the first processing unit, and is used to perform reference template matching for a single task combination, adjust the area of the two-type question answering area of the answer sheet corresponding to each requested task in the task combination according to the reference template, and optimize the answering area for each of the two-type questions according to historical answer records.
[0011] Furthermore, the data analysis unit determines a processing method according to the test paper analysis state, wherein in the first test paper analysis state, an analysis is performed on the associated state of the requested task, or in the second test paper analysis state, a priority coefficient is set according to a reference value of the number of questions in the requested task.
[0012] Furthermore, the data analysis unit determines the test paper analysis status based on the task request reference value and the task estimated duration, the test paper analysis status including a first test paper analysis status in which the task request reference value is greater than a preset task request reference value or the task estimated duration is greater than a preset task estimated duration, and a second test paper analysis status in which the task request reference value is less than or equal to the preset task request reference value and the task estimated duration is less than or equal to the preset task estimated duration.
[0013] Further, the first processing unit determines the answer sheet generation method according to the association state of the requested task in response to the first analysis condition;
[0014] If the association state is the first preset association state, the first processing unit determines that the answer sheet generation method of the corresponding request task is to perform reference template matching;
[0015] If the association state is the second preset association state, the first processing unit determines that the answer sheet generation method for the corresponding request task is to perform a combination allocation for the request task according to the estimated duration of the task;
[0016] The first analysis condition is that the test paper analysis state is the first test paper analysis state.
[0017] Further, the first processing unit performs analysis according to the association status between each request task, and records the request tasks that are in the first preset association status with each other as a task combination, a single task combination includes at least two request tasks, and the association status between the request tasks in the single task combination is the first preset association status; the association status is determined according to the test paper subject corresponding to the request task and the number of a type of question, and the association status includes the first preset association status and the second preset association status;
[0018] In the first preset association state, each test paper corresponding to each request task is of the same subject and has the same number of questions of the same question type;
[0019] In the second preset association state, each test paper corresponding to each request task has a different number of questions of the same subject or question type.
[0020] Furthermore, the combination processing unit performs reference template matching for a single task combination, wherein the reference test paper of the task combination is searched and matched with each matching template, and the matching template with the greatest matching degree corresponding to the reference test paper is detected and recorded as the reference template;
[0021] The matching degree is determined according to the difference between the number of questions of the second type of question in the matching template and the number of questions of the second type of question in the reference test paper;
[0022] The matching degree is negatively correlated with the difference between the number of questions of the second type of question in the matching template and the number of questions of the second type of question in the reference test paper;
[0023] The reference test paper is a test paper corresponding to any requested task in the task combination in the first preset association state.
[0024] Further, the combination processing unit adjusts the area of the second type of question answering area of the answer sheet corresponding to each requested task in the task combination according to the reference template under the first processing condition;
[0025] For a single request task, the area of the answer area of each second-type question is determined according to the area of the second-type question answer area of the reference template and the reference number of answers to the second-type question of the request task;
[0026] The first processing condition is that the reference template matching of a single task combination by the combination processing unit is completed.
[0027] Further, under the second processing condition, the combined processing unit performs a similarity search for the two types of questions in the test paper of each requested task to obtain historical answer records corresponding to the questions of each type of question, and performs regional optimization for the answer area of each type of question;
[0028] Regional optimization includes:
[0029] Determine a number of reference historical answer records corresponding to the i-th second-type question in the test paper of the requested task, based on the i-th second-type question in the test paper of the requested task and the second-type question corresponding to the historical answer record being of the same subject and having a reference value of the number of keywords similar to the question;
[0030] Detect the reference values that need to be optimized for each reference history answer record;
[0031] If the reference value to be optimized is within the preset reference value range to be optimized, the area of the answer area of the corresponding second type of question is increased or decreased according to the reference value to be optimized;
[0032] The reference value to be optimized is positively correlated with the reference area of the unconventional answer;
[0033] The second processing condition is that the combination processing unit completes the adjustment of the areas of the two types of question answering areas on the answer sheet corresponding to each requested task in the task combination.
[0034] Furthermore, the combination processing unit performs combination processing according to the estimated duration of the tasks, wherein a combination analysis is performed on each request task in order of the estimated duration of the tasks from large to small, and the combination analysis is to record the request task undergoing the combination analysis and the request task with the smallest estimated duration as a task combination.
[0035] Furthermore, the second processing unit sets a priority coefficient according to a reference value of the requested task quantity;
[0036] The reference value of the number of questions in the requested task is positively correlated with the priority coefficient of the requested task in the second test paper analysis state.
[0037] Compared with the prior art, the beneficial effect of the present invention lies in that, in the technical scheme of the present invention, the data analysis unit determines the test paper analysis status according to the task request reference value and the task estimated duration, effectively reflects the processing status of the current system through the test paper analysis status, and adaptively selects the processing method, so that the selection of the processing method is more in line with the actual work scenario, avoiding the problem of too long answer sheet generation time due to too many actual requested tasks, thereby improving the efficiency of the system in generating answer sheets.
[0038] Furthermore, the first processing unit in the present invention responds to the first analysis condition, determines the answer sheet generation method according to the association status of the task combination, determines the association status of the requested task by the test paper subject and the number of a type of question, effectively classifies the test paper, and effectively groups the requested tasks according to the actual association between the test papers corresponding to each requested task, thereby avoiding the problem of low preparation efficiency caused by repeated search templates, and then selecting corresponding reference templates for different groups, thereby improving the efficiency of answer sheet generation.
[0039] Furthermore, the combination processing unit in the present invention searches and matches the reference test paper of the task combination with each matching template, and adjusts the area of the two types of question answer areas of the answer sheet corresponding to each requested task in the task combination according to the reference template, so that the answer area of the prepared answer sheet can meet the answering requirements, thereby improving the accuracy of the answer area setting.
[0040] Furthermore, the combined processing unit in the present invention performs a similarity search for the two types of questions in the test papers of each requested task, and obtains the historical answer records corresponding to the two types of questions, so as to adaptively optimize the answer area according to the use of the answer sheets by the examinees in the historical process, so that the determination of the area of the answer area is more in line with the actual application scenario, further improving the use effect of the answer sheet.
[0041] Furthermore, the combination processing unit in the present invention performs combination processing according to the estimated duration of the tasks, and combines the request task to be subjected to combination analysis with the request task with the shortest estimated duration. This allows the task with a short estimated duration to be quickly processed while waiting for the task with a longer estimated duration to be completed. The system can better balance the allocation of resources, which is beneficial to improving the system processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 A unit connection diagram of a management system for preparing answer sheets according to the present invention;
[0043] Figure 2 This is a flow chart of the present invention determining a processing method according to a test paper analysis state;
[0044] Figure 3 It is a flow chart of determining the association status of a request task according to the subject of the test paper and the number of a type of question in the present invention;
[0045] Figure 4 The present invention is a flow chart of determining the answer sheet generation method according to the association status of the task combination. DETAILED DESCRIPTION
[0046] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0047] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.
[0048] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.
[0049] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0050] See also Figures 1 to 4 As shown, the present invention provides a management system for answer sheet generation and preparation, comprising:
[0051] A storage unit for storing matching templates and historical answer records;
[0052] A data analysis unit connected to the storage unit, used to determine the test paper analysis status according to the task request reference value and the task estimated duration, and determine the processing method according to the test paper analysis status, including analyzing the associated status of the requested task, or setting a priority coefficient according to the requested task question quantity reference value;
[0053] a first processing unit, which is connected to the storage unit and the data analysis unit respectively, and is used to determine the association status between each requested task according to the test paper subject corresponding to the requested task and the number of a type of question, and to divide them to obtain a plurality of task combinations, and to determine the answer sheet generation method corresponding to each task combination according to the association status of each task combination, and the answer sheet generation method is reference template matching or combination allocation for the requested task according to the estimated task duration;
[0054] A second processing unit, which is connected to the storage unit and the data analysis unit respectively, and is used to set a priority coefficient according to a reference value of the requested task quantity;
[0055] A combination processing unit is respectively connected to the storage unit, the data analysis unit and the first processing unit, and is used to perform reference template matching for a single task combination, adjust the area of the two-type question answering area of the answer sheet corresponding to each requested task in the task combination according to the reference template, and optimize the answering area for each of the two-type questions according to historical answer records.
[0056] The request task in the present invention is a test paper image uploaded by the user that needs to generate a corresponding answer sheet; the first type of question type is objective questions, including multiple-choice questions, fill-in-the-blank questions, and true-or-false questions; the second type of question type is subjective questions, including short-answer questions, discussion questions, application questions, and composition questions. The recognition of the first and second types of question types in the request task can be achieved through machine vision and deep learning networks. This is content that is easy for technical personnel in this field to understand and will not be elaborated here.
[0057] Specifically, the data analysis unit determines the processing method according to the test paper analysis state, wherein the associated state of the requested task is analyzed in the first test paper analysis state, or the priority coefficient is set according to the reference value of the number of questions of the requested task in the second test paper analysis state.
[0058] Specifically, the data analysis unit determines the test paper analysis status based on the task request reference value and the task estimated duration. The test paper analysis status includes a first test paper analysis status in which the task request reference value is greater than a preset task request reference value or the task estimated duration is greater than a preset task estimated duration, and a second test paper analysis status in which the task request reference value is less than or equal to the preset task request reference value and the task estimated duration is less than or equal to the preset task estimated duration.
[0059] The task request reference value is the sum of the number of test papers corresponding to each request task; the task estimated duration is the time required to complete the processing of each request task at present. The user can obtain the completion time of each request task in the historical generation process, and record the average completion time of each request task in the historical generation process as the single task duration reference value. The time required to complete the processing of each request task at present = the sum of the number of test papers corresponding to each request task × the single task duration reference value; the value of the preset task request reference value and the preset task estimated duration can be determined by the user according to the historical usage record of the system. The greater the user's demand for the answer sheet preparation rate, the smaller the value of the preset task request reference value and the preset task estimated duration. It can be understood that when the request task is too large, the system operation stability is difficult to guarantee, which may easily lead to a decrease in the system processing capacity. A value of a preset task request reference value is provided, and the preset task request reference value is 500. A value of a preset task estimated duration is provided. The task estimated duration corresponding to the records of the same task request reference value as the current one in the historical generation process is detected, and the average value of the task estimated duration whose processing speed meets the user's needs is recorded as the preset task estimated duration.
[0060] Specifically, the first processing unit responds to the first analysis condition and determines the answer sheet generation method according to the association status of the requested task;
[0061] If the association state is the first preset association state, the first processing unit determines that the answer sheet generation method of the corresponding request task is to perform reference template matching;
[0062] If the association state is the second preset association state, the first processing unit determines that the answer sheet generation method for the corresponding request task is to perform a combination allocation for the request task according to the estimated duration of the task;
[0063] The first analysis condition is that the test paper analysis state is the first test paper analysis state.
[0064] It can be understood that there may be several task combinations in the first preset association state, and the number of task combinations depends on the actual test subject of the requested task and the number of question types.
[0065] Specifically, the first processing unit analyzes the association status between the request tasks, and records the request tasks that are in the first preset association status with each other as a task combination, a single task combination includes at least two request tasks, and the association status between the request tasks in the single task combination is the first preset association status; the association status is determined according to the test subject corresponding to the request task and the number of a type of question, and the association status includes the first preset association status and the second preset association status;
[0066] In the first preset association state, each test paper corresponding to each request task is of the same subject and has the same number of questions of the same question type;
[0067] In the second preset association state, each test paper corresponding to each request task has a different number of questions of the same subject or question type.
[0068] Specifically, the combination processing unit performs reference template matching for a single task combination, wherein the reference test paper of the task combination is searched and matched with each matching template, and the matching template with the greatest matching degree corresponding to the reference test paper is detected and recorded as the reference template;
[0069] The matching degree is determined according to the difference between the number of questions of the second type of question in the matching template and the number of questions of the second type of question in the reference test paper;
[0070] The matching degree is negatively correlated with the difference between the number of questions of the second type of question in the matching template and the number of questions of the second type of question in the reference test paper;
[0071] The reference test paper is a test paper corresponding to any requested task in the task combination in the first preset association state.
[0072] The matching templates are the answer sheet templates uploaded by the user and the answer sheet templates generated by the system history.
[0073] Specifically, the combination processing unit adjusts the area of the second type of question answering area of the answer sheet corresponding to each requested task in the task combination according to the reference template under the first processing condition;
[0074] For a single request task, the area of the answer area of each second-type question is determined according to the area of the second-type question answer area of the reference template and the reference number of answers to the second-type question of the request task;
[0075] The first processing condition is that the reference template matching of a single task combination by the combination processing unit is completed.
[0076] For a single request task, the area of the answer area corresponding to the i-th type II question in the test paper corresponding to the single request task = the average area of the type II answer area of the reference template × α, where α is the adjustment coefficient, and α is positively correlated with the number of reference answers to the i-th type II question, i = 1, 2, 3, ..., n, n is the total number of type II questions in the test paper corresponding to the single request task, and α is confirmed in the following way: when the number of reference answers to a single type II question is 0-50, α is α 1, when the reference number of answers to a single type II question is 50-100, α is α2, when the reference number of answers to a single type II question is 100-150, α is α3, when the reference number of answers to a single type II question is greater than 150, α is α4, where α1, α2, α3 and α4 are the first coefficient, the second coefficient, the third coefficient and the fourth coefficient respectively, α1<α2<α3<α4, and a value is provided, α1=0.7, α2=0.8, α3=0.9, α4=1. The reference number of answers to the i-th type II question is the number of all characters of the answer to the i-th type II question in the corresponding request task, and the characters include Chinese characters, letters, numbers and symbols.
[0077] Specifically, under the second processing condition, the combined processing unit performs a similarity search for the two types of questions in the test paper of each requested task to obtain historical answer records corresponding to the questions of each type of question, and performs regional optimization for the answer area of each type of question;
[0078] Regional optimization includes:
[0079] Determine a number of reference historical answer records corresponding to the i-th second-type question in the test paper of the requested task, based on the i-th second-type question in the test paper of the requested task and the second-type question corresponding to the historical answer record being of the same subject and having a reference value of the number of keywords similar to the question;
[0080] Detect the reference values that need to be optimized for each reference history answer record;
[0081] If the reference value to be optimized is within the preset reference value range to be optimized, the area of the answer area of the corresponding second type of question is increased or decreased according to the reference value to be optimized;
[0082] The reference value to be optimized is positively correlated with the reference area of the unconventional answer;
[0083] The second processing condition is that the combination processing unit completes the adjustment of the areas of the two types of question answering areas on the answer sheet corresponding to each requested task in the task combination.
[0084] Similar searches include:
[0085] When a history answer record has a second-category question type and a single second-category question type in the requested task paper, which is the same subject and the reference value of the number of similar keywords in the question is greater than the preset reference value of the number of similar keywords in the question, the second-category question type is recorded as a reference second-category question type, and the corresponding historical answer record is recorded as a reference historical answer record. The reference value of the number of similar keywords in the question is the same keywords in the single second-category question type in the historical answer record and the single second-category question type in the requested task paper. Keyword detection can be achieved through a deep learning network. This is a technical problem that technicians in this field are urgently required to solve and will not be elaborated on here. The value of the preset reference value of the number of similar keywords in the question can be determined by the user according to the historical usage record of the system. The greater the user's demand for question similarity detection, the greater the value of the preset reference value of the number of similar keywords in the question. A value of the preset reference value of the number of similar keywords in the question is provided. The preset reference value of the number of similar keywords in the question is 80% of the number of all keywords in the single second-category question type in the requested task paper.
[0086] The historical answer records corresponding to the questions of each type of question are the stored answer information of all examinees answering the questions of each type of question;
[0087] The reference value to be optimized for a single reference historical answer record = the average value of the difference between the reference answer area area of each reference second-type question and the area of the answer area corresponding to the i-th second-type question in the test paper corresponding to the requested task. If the reference value to be optimized is greater than the maximum allowable value of the preset reference value range to be optimized, the area of the answer area for the corresponding second-type question will be increased. If the optimized reference value is less than the minimum allowable value of the preset reference value range to be optimized, the area of the answer area for the corresponding second-type question will be decreased. The unconventional answer reference area is the area of the reference answer area that is different from the area of the answer area corresponding to the i-th second-type question in the test paper corresponding to the single requested task.
[0088] The values within the preset reference value range to be optimized are all greater than or equal to the minimum value allowed and less than or equal to the maximum value allowed. The minimum and maximum values allowed can be determined by the user based on the historical usage records of the system. The greater the user's demand for the area of the answer sheet to meet the historical answer records, the greater the minimum value allowed and the smaller the maximum value allowed. Provide a minimum and maximum value allowed, and the minimum allowed is -2cm 2 And the maximum allowed is 2cm 2 .
[0089] The method for confirming the area of the reference answer area for the reference type 2 question is to establish a rectangle with the minimum area that includes the answer area, and record the area of the rectangle as the area of the reference answer area for the reference type 2 question.
[0090] Specifically, the combination processing unit performs combination processing according to the estimated duration of the tasks, wherein a combination analysis is performed on each request task in the order of the estimated duration of the tasks from large to small, and the combination analysis is to record the request task undergoing combination analysis and the request task with the smallest estimated duration as a task combination.
[0091] Then, each task combination is randomly sorted and answer sheet generation is performed. For the answer sheet generation process of a single request task, the test paper corresponding to the request task is matched with each matching template. If the maximum value of the corresponding matching degree is less than the preset matching degree, the answer sheet is re-established.
[0092] If the maximum value of the corresponding matching degree is greater than or equal to the preset matching degree, the corresponding matching template is recorded as the answer sheet module of the requested task, and the answer sheet is generated and sent to the user;
[0093] The user can determine the value of the preset matching degree based on the historical usage records of the system. The greater the user's demand for the combination to generate the answer sheet, the smaller the value of the preset matching degree. A value of the preset matching degree is provided, and the preset matching degree is 5.
[0094] Specifically, the second processing unit sets a priority coefficient according to a reference value of the requested task quantity;
[0095] The reference value of the number of questions in the requested task is positively correlated with the priority coefficient of the requested task in the second test paper analysis state.
[0096] The reference value for the number of requested task questions is the sum of the number of type 1 questions and type 2 questions in each test paper in the second test paper analysis state.
[0097] In the present invention, for a single request task, if the corresponding test paper does not have a matching template with a matching degree greater than a preset matching degree, the answer sheet is re-established online. Online establishment of the answer sheet is content that can be understood by those skilled in the art. Here, a establishment method is provided, including:
[0098] Parse the data format generated by the answer sheet, read the data structure of the answer sheet, and store the data in HTML format;
[0099] Restore the original layout and content of the answer sheet through specific algorithms and features;
[0100] Use machine vision and deep learning networks to verify whether the formulas and image resources in the answer sheet are correctly loaded and displayed, and set the standard paper size and margins when it is determined that they are indeed loaded and displayed;
[0101] Determine whether the webpage is accessed normally, otherwise re-execute the operation of parsing the answer sheet format:
[0102] Check whether the web page source of the answer sheet is accessible. If not, reparse the data format;
[0103] Convert web pages to standard PDF:
[0104] Convert the web content of the answer sheet to PDF format to ensure printing quality and format consistency.
[0105] The specific steps of restoring the original layout and content of the answer sheet through specific algorithms and features include:
[0106] I. Get all values of the data structure:
[0107] Extract all necessary information from the data source, including title, options, format, etc.
[0108] II. Break down this set of data one by one:
[0109] Break data down into its individual elements for further processing.
[0110] III. Get the data packages for each question type:
[0111] Group the data according to question type.
[0112] IV. Parse the data packets according to the order of the specified question types:
[0113] Parse the data packet in the order of questions to ensure the logical order of the answer sheet.
[0114] V. Check whether the data of each question type and the related resources are complete, and ensure that the data and resources of all question types are complete and correct.
[0115] VI. Return the correct web page format data according to the verification result: Generate the correct answer sheet web page format according to the verification result and prepare to convert it to PDF. The prescribed question type order is objective questions, fill-in-the-blank questions, answer questions, essays, non-answer questions, and optional questions.
[0116] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.
[0117] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A management system for answer sheet generation and preparation, characterized in that: include: A storage unit for storing matching templates and historical answer records; A data analysis unit connected to the storage unit, used to determine the test paper analysis status according to the task request reference value and the task estimated duration, and determine the processing method according to the test paper analysis status, including analyzing the associated status of the requested task, or setting a priority coefficient according to the requested task question quantity reference value; a first processing unit, which is connected to the storage unit and the data analysis unit respectively, and is used to determine the association status between each requested task according to the test paper subject corresponding to the requested task and the number of a type of question, and to divide them to obtain a plurality of task combinations, and to determine the answer sheet generation method corresponding to each task combination according to the association status of each task combination, and the answer sheet generation method is reference template matching or combination allocation for the requested task according to the estimated task duration; A second processing unit, which is connected to the storage unit and the data analysis unit respectively, and is used to set a priority coefficient according to a reference value of the requested task quantity; a combination processing unit, which is connected to the storage unit, the data analysis unit and the first processing unit respectively, and is used to perform reference template matching for a single task combination, adjust the area of the two-type question answering area of the answer sheet corresponding to each requested task in the task combination according to the reference template, and optimize the area of the answering area for each of the two-type questions according to the historical answering records; The first processing unit responds to the first analysis condition and determines the answer sheet generation method according to the associated state of the requested task; If the association state is the first preset association state, the first processing unit determines that the answer sheet generation method of the corresponding request task is to perform reference template matching; If the association state is the second preset association state, the first processing unit determines that the answer sheet generation method for the corresponding request task is to perform a combination allocation for the request task according to the estimated duration of the task; The first analysis condition is that the test paper analysis state is the first test paper analysis state; The first processing unit analyzes the association status between the request tasks, and records the request tasks that are in the first preset association status with each other as a task combination, a single task combination includes at least two request tasks, and the association status between the request tasks in the single task combination is the first preset association status; the association status is determined according to the test subject corresponding to the request task and the number of a type of question, and the association status includes the first preset association status and the second preset association status; In the first preset association state, each test paper corresponding to each request task is of the same subject and has the same number of questions of the same question type; In the second preset association state, the number of questions in each test paper corresponding to each request task is different from the same subject or the same question type; The second processing unit sets a priority coefficient according to a reference value of the requested task quantity; The reference value of the number of questions in the requested task is positively correlated with the priority coefficient of the requested task in the second test paper analysis state; The combination processing unit performs reference template matching for a single task combination, wherein the reference test paper of the task combination is searched and matched with each matching template, and the matching template with the greatest matching degree corresponding to the reference test paper is detected and recorded as the reference template; The matching degree is determined according to the difference between the number of questions of the second type of question in the matching template and the number of questions of the second type of question in the reference test paper; The matching degree is negatively correlated with the difference between the number of questions of the second type of question in the matching template and the number of questions of the second type of question in the reference test paper; The reference test paper is a test paper corresponding to any requested task in the task combination of the first preset association state; The combined processing unit performs similarity search for the two types of questions in the test paper of each requested task under the second processing condition to obtain historical answer records corresponding to the questions of each type of question, and performs regional optimization for the answer area of each type of question; Regional optimization includes: Determine a number of reference historical answer records corresponding to the i-th second-type question in the test paper of the requested task, based on the i-th second-type question in the test paper of the requested task and the second-type question corresponding to the historical answer record being of the same subject and having a reference value of the number of keywords similar to the question; Detect the reference values that need to be optimized for each reference history answer record; If the reference value to be optimized is within the preset reference value range to be optimized, the area of the answer area of the corresponding second type of question is increased or decreased according to the reference value to be optimized; The reference value to be optimized is positively correlated with the reference area of the unconventional answer; The unconventional answer reference area is a reference answer area area that is different from the area of the answer area corresponding to the i-th type II question in the test paper corresponding to the single request task; The second processing condition is that the combination processing unit completes the adjustment of the areas of the two types of question answering areas on the answer sheet corresponding to each requested task in the task combination.
2. The management system for answer sheet generation and preparation according to claim 1, characterized in that: The data analysis unit determines the processing method according to the test paper analysis state, wherein the associated state of the requested task is analyzed in the first test paper analysis state, or the priority coefficient is set according to the reference value of the number of questions of the requested task in the second test paper analysis state.
3. The management system for answer sheet generation and preparation according to claim 2, characterized in that: The data analysis unit determines the test paper analysis status based on the task request reference value and the task estimated duration. The test paper analysis status includes a first test paper analysis status in which the task request reference value is greater than a preset task request reference value or the task estimated duration is greater than a preset task estimated duration, and a second test paper analysis status in which the task request reference value is less than or equal to the preset task request reference value and the task estimated duration is less than or equal to the preset task estimated duration.
4. The management system for answer sheet generation and preparation according to claim 3, characterized in that: The combination processing unit adjusts the area of the second type of question answering area of the answer sheet corresponding to each requested task in the task combination according to the reference template under the first processing condition; For a single request task, the area of the answer area of each second-type question is determined according to the area of the second-type question answer area of the reference template and the reference number of answers to the second-type question of the request task; The first processing condition is that the reference template matching of a single task combination by the combination processing unit is completed.
5. The management system for answer sheet generation and preparation according to claim 4, characterized in that: The combination processing unit performs combination processing according to the estimated duration of the tasks, wherein a combination analysis is performed on each request task in the order of the estimated duration of the tasks from large to small, and the combination analysis is to record the request task undergoing combination analysis and the request task with the smallest estimated duration as a task combination.
