Training sparring method, device, system and computer readable storage medium

Abstract

The application discloses a training mutual practice method, device, system and computer readable storage medium, the method comprises the following steps: acquiring a question set and a standard answer set corresponding to the question set, and generating an exercise question bank according to the question set, the standard answer set and a preset knowledge base; acquiring an answer configuration parameter, generating an exercise question set according to the answer configuration parameter and the exercise question bank, and performing training mutual practice based on the exercise question set. According to the question set and the corresponding standard answer set, the corresponding exercise question bank is generated in combination with the preset knowledge base, the question setting efficiency is improved, the exercise question set is generated according to the answer configuration parameter and the exercise question bank, and the training mutual practice is performed based on the exercise question set, the training effect of the training mutual practice on the training personnel is improved, and then the practicality of the training mutual practice is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a training method and device, a system and a computer readable storage medium. BACKGROUND

[0002] With the development of society, paperless office, online training and examination are becoming more and more mature. In the traditional training process, the correct standard answer corresponding to the question and the matching of the error or misleading standard answer need to be matched by artificial matching, and the corresponding answer mode cannot be determined according to the type of the question in the training process, which seriously affects the efficiency of the training and the effect of the training, and further reduces the practicability of the training. Therefore, how to improve the practicability of the training is a problem to be solved. SUMMARY

[0003] The main purpose of the present application is to provide a training method and device, a system and a computer readable storage medium, which aims to solve the problem of how to improve the accuracy of the training.

[0004] To achieve the above purpose, the present application provides a training method, which comprises the following steps:

[0005] Obtain a question set and a standard answer set corresponding to the question set, and generate an exercise question bank according to the question set, the standard answer set and a preset knowledge base;

[0006] Obtain an answer configuration parameter, generate an exercise question set according to the answer configuration parameter and the exercise question bank, and perform training and practice based on the exercise question set.

[0007] Optionally, the step of generating an exercise question bank according to the question set, the standard answer set and the preset knowledge base comprises:

[0008] According to the question set and the standard answer set, determine the standard answer corresponding to each question, and perform similarity analysis on each question and the standard answer corresponding to each question based on the preset knowledge base to obtain a similar question set and a similar answer set;

[0009] Generate an exercise question bank according to the question set, the standard answer set, the similar question set and the similar answer set.

[0010] Optionally, the step of performing similarity analysis on each question and the standard answer corresponding to each question based on the preset knowledge base to obtain a similar question set and a similar answer set comprises:

[0011] The key words are obtained by identifying each question and a standard answer corresponding to each question, and performing context relevance analysis and text similarity analysis on the key words based on a preset knowledge base to determine a synonym set corresponding to the key words;

[0012] According to the synonym set and the preset knowledge base, a similar question set and a similar answer set are obtained.

[0013] Optionally, the step of performing context relevance analysis and text similarity analysis on each key word in the key word set based on the preset knowledge base to determine a synonym set corresponding to the key word set comprises:

[0014] The fuzzy synonym set corresponding to the key word is determined in the preset knowledge base;

[0015] A first context corresponding to the key word is obtained in the question set and the standard answer set, a second context corresponding to each fuzzy synonym in the fuzzy synonym set is obtained in the preset knowledge base, and a first similarity between the key word and each fuzzy synonym is determined according to the first context and the second context;

[0016] The edit distance and the longest common subsequence between the key word and each fuzzy synonym in the fuzzy synonym set are calculated respectively, and a second similarity between the key word and each fuzzy synonym is determined according to the edit distance and the longest common subsequence;

[0017] According to the first similarity and the second similarity, a synonym set corresponding to the key word set is determined in the fuzzy synonym set.

[0018] Optionally, the exercise question set includes subjective questions and / or objective questions, and the step of training the training personnel based on the exercise question set comprises:

[0019] According to the answer configuration parameters, a subjective question display rule and / or an objective question display rule of the exercise question set are determined;

[0020] If all the exercise questions in the exercise question set are objective questions, the exercise question set is displayed to the training personnel according to the objective question display rule to perform the training;

[0021] If all the exercise questions in the exercise question set are subjective questions, the exercise question set is displayed to the training personnel according to the subjective question display rule and the reply answer of the training personnel to perform the training;

[0022] If the exercise set includes both objective questions and subjective questions, the subjective question display rule, the objective question display rule and the reply answer of the training personnel are used to display the exercise set to the training personnel for training.

[0023] Optionally, the step of displaying the exercise set to the training personnel according to the subjective question display rule and the reply answer of the training personnel comprises:

[0024] determining a to-be-displayed subjective question in the exercise set according to the subjective question display rule, and displaying the to-be-displayed subjective question to the training personnel;

[0025] receiving the reply answer of the training personnel, and calculating a third similarity between the reply answer and a standard answer corresponding to the to-be-displayed subjective question;

[0026] repeating the steps of determining a to-be-displayed subjective question in the exercise set according to the third similarity and the subjective question display rule, and displaying the to-be-displayed subjective question to the training personnel.

[0027] Optionally, after the step of obtaining the answer configuration parameter, generating the exercise set according to the answer configuration parameter and the exercise question bank, and performing the training and practice based on the exercise set, the method further comprises:

[0028] obtaining a training and practice result, analyzing the training and practice result, generating an analysis report, and displaying the analysis report to the training personnel.

[0029] In addition, to achieve the above object, the application further provides a training and practice device, which comprises:

[0030] an obtaining module, configured to obtain a question set and a standard answer set corresponding to the question set, and generate an exercise question bank according to the question set, the standard answer set and a preset knowledge base;

[0031] a generating module, configured to obtain an answer configuration parameter, generate an exercise set according to the answer configuration parameter and the exercise question bank, and perform training and practice based on the exercise set.

[0032] Preferably, the obtaining module is further configured to:

[0033] determine a standard answer corresponding to each question according to the question set and the standard answer set, and perform similarity analysis on each question and the standard answer corresponding to each question based on the preset knowledge base to obtain a similar question set and a similar answer set;

[0034] generate an exercise question bank according to the question set, the standard answer set, the similar question set and the similar answer set.

[0035] Preferably, the obtaining module is further configured to:

[0036] identify a keyword for each question and a standard answer corresponding to each question, and perform context relevance analysis and text similarity analysis on the keyword based on a preset knowledge base to determine a synonym set corresponding to the keyword;

[0037] obtain a similar question set and a similar answer set according to the synonym set and the preset knowledge base.

[0038] Preferably, the obtaining module is further configured to:

[0039] determine a fuzzy synonym set corresponding to the keyword in the preset knowledge base;

[0040] obtain a first context corresponding to the keyword in the question set and the standard answer set, obtain a second context corresponding to each fuzzy synonym in the fuzzy synonym set in the preset knowledge base, and determine a first similarity between the keyword and each fuzzy synonym according to the first context and the second context;

[0041] calculate an edit distance and a longest common subsequence between the keyword and each fuzzy synonym in the fuzzy synonym set, respectively, and determine a second similarity between the keyword and each fuzzy synonym according to the edit distance and the longest common subsequence;

[0042] determine a synonym set corresponding to the keyword set in the fuzzy synonym set according to the first similarity and the second similarity.

[0043] Preferably, the generating module further comprises a presenting module configured to:

[0044] determine a subjective question presenting rule and / or an objective question presenting rule for the exercise question set according to the answering configuration parameter;

[0045] if all exercise questions in the exercise question set are objective questions, present the exercise question set to the training personnel according to the objective question presenting rule to perform training and practice;

[0046] if all exercise questions in the exercise question set are subjective questions, present the exercise question set to the training personnel according to the subjective question presenting rule and the reply answer of the training personnel to perform training and practice;

[0047] If the exercise set includes both objective questions and subjective questions, the subjective question display rule, the objective question display rule and the reply answer of the training personnel are used to display the exercise set to the training personnel for training.

[0048] Preferably, the display module is further configured to:

[0049] determine a subjective question to be displayed in the exercise set according to the subjective question display rule, and display the subjective question to be displayed to the training personnel;

[0050] receive the reply answer of the training personnel, and calculate a third similarity between the reply answer and a standard answer corresponding to the subjective question to be displayed;

[0051] repeatedly perform the steps of determining a subjective question to be displayed in the exercise set according to the third similarity and the subjective question display rule, and displaying the subjective question to be displayed to the training personnel.

[0052] Preferably, the generation module further comprises an analysis module configured to:

[0053] obtain a training result, analyze the training result, generate an analysis report, and display the analysis report to the training personnel.

[0054] In addition, to achieve the above object, the present application also provides a training and drilling system, which comprises a memory, a processor and a training and drilling program stored in the memory and executable on the processor, and the training and drilling program implements the steps of the training and drilling method as described above when executed by the processor.

[0055] In addition, to achieve the above object, the present application also provides a computer readable storage medium having a training and drilling program stored thereon, and the training and drilling program implements the steps of the training and drilling method as described above when executed by a processor.

[0056] The training and drilling method provided by the present application obtains a question set and a standard answer set corresponding to the question set, generates an exercise question bank according to the question set, the standard answer set and a preset knowledge base, obtains a answering configuration parameter, generates an exercise set according to the answering configuration parameter and the exercise question bank, and performs training and drilling based on the exercise set. The present application generates a corresponding exercise question bank according to a question set and a corresponding standard answer set in combination with a preset knowledge base, thereby improving the efficiency of question setting. The present application generates an exercise set according to an answering configuration parameter and an exercise question bank, and performs training and drilling based on the exercise set, thereby improving the training effect of training and drilling on training personnel and further improving the practicality of training and drilling. Attached Figure Description

[0057] Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention;

[0058] Figure 2 This is a flowchart illustrating the first embodiment of the training and practice method of the present invention.

[0059] The realization of the objective of this invention, its functional features and advantages will be further explained with reference to the accompanying drawings through a series of embodiments. Detailed Implementation

[0060] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0061] like Figure 1 As shown, Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention.

[0062] The device in this embodiment of the invention can be a PC or a server.

[0063] like Figure 1 As shown, the device may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0064] Those skilled in the art will understand that Figure 1 The device structure shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0065] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a training and practice program.

[0066] The operating system is a program for managing and controlling the portable training and practicing system and software resources, supports the running of the network communication module, the user interface module, the training and practicing program and other programs or software; the network communication module is used for managing and controlling the network interface 1002; and the user interface module is used for managing and controlling the user interface 1003.

[0067] In Figure 1 In the training and practicing system shown in the figure, the training and practicing system calls the training and practicing program stored in the memory 1005 through the processor 1001, and performs the operations in each embodiment of the training and practicing method described below.

[0068] Based on the hardware structure described above, the training and practicing method embodiments of the present application are proposed.

[0069] Referring to Figure 2 , Figure 2 The flowchart of the first embodiment of the training and practicing method of the present application is shown in the figure, and the method comprises the following steps.

[0070] In step S10, a set of questions and a set of standard answers corresponding to the set of questions are obtained, and an exercise question bank is generated according to the set of questions, the set of standard answers and a preset knowledge base;

[0071] In step S20, a question answering configuration parameter is obtained, an exercise question set is generated according to the question answering configuration parameter and the exercise question bank, and training and practicing is performed based on the exercise question set.

[0072] The training and practicing method of the embodiment can be applied to a training and practicing system of a financial institution. The training and practicing system can be applied to a terminal device, including a PC device, a smart terminal, etc. The terminal device can interact with a pre-training personnel based on the training and practicing system to perform training and practicing. For the convenience of description, the training and practicing system is taken as an example for description. The training and practicing system obtains a question set uploaded by a related question setter and a standard answer set corresponding to the question set. According to the question set and the standard answer set, the standard answer corresponding to each question is determined, and similarity analysis is performed on each question and the standard answer corresponding to each question based on a preset knowledge base to obtain a similar question set and a similar answer set. According to the question set, the standard answer set, the similar question set and the similar answer set, an exercise question bank is generated. The training and practicing system determines a subjective question display rule and / or an objective question display rule of the exercise question set according to a question answering configuration parameter. If all the exercise questions of the exercise question set are objective questions, the exercise question set is displayed to the training personnel according to the objective question display rule to perform training and practicing. If all the exercise questions of the exercise question set are subjective questions, the exercise question set is displayed to the training personnel according to the subjective question display rule and a reply answer of the training personnel to perform training and practicing. If the exercise question set includes both objective questions and subjective questions, the exercise question set is displayed to the training personnel according to the subjective question display rule, the objective question display rule and the reply answer of the training personnel to perform training and practicing.

[0073] The training and practicing method of the embodiment obtains a question set and a standard answer set corresponding to the question set, and generates an exercise question bank according to the question set, the standard answer set and a preset knowledge base. A question answering configuration parameter is obtained, and an exercise question set is generated according to the question answering configuration parameter and the exercise question bank, and training and practicing is performed based on the exercise question set. The present application generates a corresponding exercise question bank according to the question set and the corresponding standard answer set in combination with the preset knowledge base, improves the question setting efficiency, generates an exercise question set according to the question answering configuration parameter and the exercise question bank, and improves the training effect of the training and practicing on the training personnel, thereby improving the practicality of the training and practicing.

[0074] The following will be described in detail:

[0075] In step S10, a question set and a standard answer set corresponding to the question set are obtained, and an exercise question bank is generated according to the question set, the standard answer set and a preset knowledge base.

[0076] In the embodiment, the training and practicing system acquires a question set uploaded by a related question setter and a standard answer set corresponding to the question set, and generates an exercise question bank according to the question set, the standard answer set and a preset knowledge base. It can be understood that the preset knowledge base is set in the training and practicing system in advance, and the preset knowledge base includes a large number of historical exercise questions and a standard answer corresponding to each historical exercise question. The training and practicing system can generate an exercise question bank for training and practicing according to the question set uploaded by the related question setter and the standard answer set corresponding to the question set, in combination with the historical exercise questions and the standard answer corresponding to each historical exercise question in the preset knowledge base.

[0077] Specifically, the step of generating the exercise question bank according to the question set, the standard answer set and the preset knowledge base includes:

[0078] In step a, the standard answer corresponding to each question is determined according to the question set and the standard answer set, and similarity analysis is performed on each question and the standard answer corresponding to each question based on the preset knowledge base to obtain a similar question set and a similar answer set.

[0079] In this step, the training and drilling system determines the similarity of each exercise in the preset knowledge base to each question in the question set based on the question set and the standard answer set, in which a standard answer corresponding to each question in the question set is matched, and obtains the text of all exercises in the preset knowledge base, and performs similarity analysis on the text of each question in the question set, and then obtains the text of the answers corresponding to all exercises in the preset knowledge base, and performs similarity analysis on the standard answers corresponding to each question in the question set, determines the similarity of all exercises in the preset knowledge base to each question in the question set, and sorts the exercises in the preset knowledge base with a similarity greater than a preset similarity threshold according to the corresponding similarity, and determines the preset number of exercises with the greatest similarity as the similar question set according to the sorting, and determines the similar answer set according to the answers corresponding to the exercises in the similar question set; in a feasible embodiment, assuming that the preset similarity threshold is 90%, the preset number is 3, and the question set contains two questions, after the training and drilling system determines the similarity of each exercise in the preset knowledge base to the two questions in the question set, it compares the similarity with the preset similarity threshold of 90%, and retains the exercises with a similarity greater than 90%, and sorts the exercises with a similarity greater than 90% to the first question in the question set according to the similarity of each exercise from large to small, and after sorting, takes the first three exercises at the beginning as the similar exercises corresponding to the first question in the question set, sorts the exercises with a similarity greater than 90% to the second question in the question set according to the similarity of each exercise from large to small, and after sorting, takes the first three exercises at the beginning as the similar exercises corresponding to the second question in the question set, and obtains the similar question set according to the similar exercises corresponding to the first question in the question set and the similar exercises corresponding to the second question in the question set, and determines the similar answer set according to the answers corresponding to the exercises in the similar question set.

[0080] Further, the step of performing similarity analysis on each question and the standard answer corresponding to each question based on the preset knowledge base to obtain the similar question set and the similar answer set includes:

[0081] Step a1, identifying each question and the standard answer corresponding to each question to obtain keywords, and performing context correlation analysis and text similarity analysis on the keywords based on the preset knowledge base to determine a synonym set corresponding to the keywords;

[0082] In this step, the training and drilling system identifies each question in the question set and the standard answer corresponding to each question, determines the keywords corresponding to each question, and obtains the text in all the practice questions in the preset knowledge base, determines the keywords corresponding to all the practice questions, and then determines the context corresponding to the keywords corresponding to each question and the context corresponding to the keywords corresponding to all the practice questions. The training and drilling system then calculates the similarity between the context corresponding to the keywords corresponding to each question and the context corresponding to the keywords corresponding to all the practice questions, and then calculates the similarity between the keywords corresponding to each question and the keywords corresponding to all the practice questions. The training and drilling system then calculates the similarity between the context corresponding to the keywords corresponding to each question and the context corresponding to the keywords corresponding to all the practice questions, and then calculates the similarity between the keywords corresponding to each question and the keywords corresponding to all the practice questions. The similarity between the context corresponding to the keywords corresponding to each question and the context corresponding to the keywords corresponding to all the practice questions, and the similarity between the keywords corresponding to each question and the keywords corresponding to all the practice questions, and the similarity between the keywords corresponding to each question and the keywords corresponding to all the practice questions. In all the keywords corresponding to the practice questions, select the preset number of keywords with the highest similarity to the keywords corresponding to each question to determine the synonym set.

[0083] Step a2, according to the synonym set and the preset knowledge base, obtain the similar question set and the similar answer set.

[0084] In this step, the training and drilling system determines, according to the synonym set, in which exercise questions in the preset knowledge base each synonym in the synonym set is located, takes the similarity between each synonym and the keyword corresponding to each question in the question set as the similarity between each exercise question corresponding to each synonym and each question in the question set, sorts the exercise questions with a similarity greater than a preset similarity threshold according to the corresponding similarity, determines a preset number of exercise questions with the greatest similarity as the similar exercise questions corresponding to each question according to the sorting, and further determines a similar question set. In order to facilitate the description, one question in the question set is described: it is assumed that the training and drilling system identifies a keyword in the question and the standard answer corresponding to the question, and identifies a keyword in each exercise question in the preset knowledge base. The keyword of the question in the question set and the keyword in each exercise question in the preset knowledge base are subjected to context similarity analysis and text similarity analysis to determine the similarity between the keyword in each exercise question in the preset knowledge base and the keyword of the question in the question set. The similarity between the keyword in each exercise question in the preset knowledge base and the keyword of the question in the question set corresponds to the similarity between each exercise question in the preset knowledge base and the question in the question set. Then, according to the similarity between each exercise question in the preset knowledge base and the question in the question set, the exercise questions with a similarity greater than a preset similarity threshold are selected and sorted, and a preset number of exercise questions with the greatest similarity are determined as the similar exercise questions corresponding to the question in the question set according to the sorting. Each question in the question set is subjected to the above steps to determine the corresponding similar exercise questions. Finally, the similar question set is determined according to the similar exercise questions corresponding to each question in the question set, and the similar answer set is determined according to the answers corresponding to the exercise questions in the similar question set.

[0085] Further, step a1 comprises:

[0086] Step a11, determining a fuzzy synonym set corresponding to the keyword in the preset knowledge base;

[0087] Step a12, obtaining a first context corresponding to the keyword in the question set and the standard answer set, obtaining a second context corresponding to each fuzzy synonym in the fuzzy synonym set in the preset knowledge base, and determining a first similarity between the keyword and each fuzzy synonym according to the first context and the second context;

[0088] Step a13, calculating the edit distance and the longest common subsequence between the keyword and each fuzzy synonym in the fuzzy synonym set, respectively, and determining a second similarity between the keyword and each fuzzy synonym according to the edit distance and the longest common subsequence;

[0089] Step a14, determining the synonym set corresponding to the keyword set in the fuzzy synonym set according to the first similarity and the second similarity.

[0090] In steps a11 to a14, after the training and practicing system determines the keywords corresponding to each question in the question set and the standard answer corresponding to each question, the training and practicing system determines the fuzzy synonym set corresponding to the keywords in the preset knowledge base, and the fuzzy synonym set includes all the keywords corresponding to the practice questions in the preset knowledge base; the training and practicing system obtains the first context of the keywords in the question set and the standard answer set, and obtains the second context of each fuzzy synonym in the fuzzy synonym set in the preset knowledge base, and calculates the word vector of the first context and the word vector of the second context by using word2vector; then, the training and practicing system calculates the cosine similarity of the first context according to the word vector of the first context, and calculates the cosine similarity of the second context according to the word vector of the second context, and determines the first similarity between the keywords and each fuzzy synonym according to the cosine similarity of the first context and the cosine similarity of the second context; the training and practicing system calculates the edit distance and the longest common subsequence between the keywords and each fuzzy synonym in the fuzzy synonym set, respectively, and determines the second similarity between the keywords and each fuzzy synonym according to the edit distance and the longest common subsequence; the training and practicing system determines the final similarity between each fuzzy synonym and the keywords in the fuzzy synonym set according to the first similarity and the second similarity, and selects the preset number of fuzzy synonyms with the maximum final similarity as the synonym set.

[0091] Step b, generating a practice question bank according to the question set, the standard answer set, the similar question set and the similar answer set.

[0092] In this step, after obtaining the similar question set and the similar answer set, the training and drilling system generates an exercise question bank according to the question set, the standard answer set, the similar question set and the similar answer set; for example, assuming that there are two questions in the question set, there are two corresponding standard answers in the standard answer set, and the similar question set contains six similar questions corresponding to the two questions in the question set, i.e., three similar questions corresponding to each question in the question set, and the similar answer set also contains answers corresponding to the six similar questions; the training and drilling system takes each question in the question set as the title of an exercise question, takes the standard answers in the standard answer set as the correct answers of each exercise question, and takes the answers corresponding to the three similar questions in the similar answer set as the wrong answers or interference answers of each exercise question, thereby generating the exercise question bank.

[0093] In step S20, the answer configuration parameters are obtained, the exercise question set is generated according to the answer configuration parameters and the exercise question bank, and the training and drilling is performed based on the exercise question set.

[0094] In this embodiment, the training and drilling system obtains the answer configuration parameters set by the training personnel or the training management personnel, generates the exercise question set according to the answer configuration parameters and the exercise question bank, displays the exercise question set to the training personnel, receives the reply answers of the training personnel to the displayed exercise questions, and performs the training and drilling.

[0095] Specifically, the step of performing the training and drilling based on the exercise question set comprises:

[0096] In step c, the subjective question display rule and / or the objective question display rule of the exercise question set are determined according to the answer configuration parameters.

[0097] In this step, the training and drilling system determines the subjective question display rule and / or the objective question display rule of the exercise question set according to the answer configuration parameters; it should be noted that the answer configuration parameters can include functions such as randomization, mandatory questions, random questions and timing, and the training and drilling system determines the subjective question display rule and / or the objective question display rule of the exercise question set according to the question order parameters in the answer configuration parameters after determining the exercise question set according to the answer configuration parameters. It can be understood that the exercise question set includes subjective questions and / or objective questions, the subjective question is a question that requires the training object to input the corresponding answer description, and the objective question is a question of the type of multiple-choice question or judgment question.

[0098] In step d, if all the exercise questions in the exercise question set are objective questions, the exercise question set is displayed to the training personnel according to the objective question display rule to perform the training and drilling.

[0099] In this step, if the training and drilling system determines that all the practice questions in the practice question set according to the answer configuration parameters are objective questions, the training and drilling system displays the practice question set to the training personnel according to the objective question display rule to perform the training and drilling.

[0100] Step e, if all the practice questions in the practice question set are subjective questions, the training and drilling system displays the practice question set to the training personnel according to the subjective question display rule and the reply answer of the training personnel to perform the training and drilling.

[0101] In this step, if the training and drilling system determines that all the practice questions in the practice question set according to the answer configuration parameters are subjective questions, the training and drilling system displays the practice question set to the training personnel according to the subjective question display rule and the reply answer of the training personnel to perform the training and drilling. It can be understood that the subjective question display rule needs to be combined with the reply answer of the training personnel to display the next question to the training personnel.

[0102] Step f, if the practice question set includes both objective questions and subjective questions, the training and drilling system displays the practice question set to the training personnel according to the subjective question display rule, the objective question display rule, and the reply answer of the training personnel to perform the training and drilling.

[0103] In this step, if the training and drilling system determines that the practice question set according to the answer configuration parameters includes both objective questions and subjective questions, the training and drilling system displays the subjective questions to the training personnel according to the subjective question display rule and the reply answer of the training personnel to perform the training and drilling, and displays the objective question set to the training personnel according to the objective question display rule to perform the training and drilling. It can be understood that, since the display rules of the subjective questions and the objective questions are different, generally, when the practice question set includes both objective questions and subjective questions, the training and drilling system displays the subjective questions to the training personnel first and then displays the objective questions, or displays the objective questions to the training personnel first and then displays the subjective questions.

[0104] Further, step e includes:

[0105] Step e1, determining the to-be-displayed subjective questions in the practice question set according to the subjective question display rule, and displaying the to-be-displayed subjective questions to the training personnel.

[0106] Step e2, receiving the reply answer of the training personnel, and calculating a third similarity between the reply answer and a standard answer corresponding to the to-be-displayed subjective questions.

[0107] Step e3, according to the third similarity and the subjective question display rule, repeatedly performing the steps of determining a to-be-displayed subjective question in the exercise question set, and displaying the to-be-displayed subjective question to the training personnel.

[0108] In steps e1-e3, the training pair system determines a first to-be-displayed subjective question in the exercise question set according to the subjective question display rule, and displays the first to-be-displayed subjective question to the training personnel. The training personnel inputs a corresponding reply answer to the training pair system according to the first to-be-displayed subjective question. The training pair system obtains a standard answer corresponding to the first to-be-displayed subjective question, calculates the similarity between the reply answer and the standard answer, and compares the similarity with a preset similarity threshold. If the similarity is greater than the preset similarity threshold, the next question is determined as a to-be-displayed subjective question according to the subjective question display rule and displayed to the training personnel. If the similarity is not greater than the preset similarity threshold, another question is determined as a to-be-displayed subjective question according to the subjective question display rule and displayed to the training personnel. The cycle is repeated until all subjective questions in the exercise question set are answered by the training personnel, and the training pair is completed.

[0109] Further, step S20 further comprises:

[0110] Step g, obtaining the training pair result, analyzing the training pair result, generating an analysis report, and displaying the analysis report to the training personnel.

[0111] In this step, after completing the training pair, the training pair system obtains the training pair result, analyzes the training pair result, generates an analysis report, and displays the analysis report to the training personnel. Further, the training pair result can also be used for reverse maintenance of the preset knowledge base and summary of key training content, further helping to improve the effect of the training pair and improve the practicality of the training pair.

[0112] The training and practicing system of the embodiment obtains a question set uploaded by a related question setter and a standard answer set corresponding to the question set, determines a standard answer corresponding to each question according to the question set and the standard answer set, and performs similarity analysis on each question and the standard answer corresponding to each question based on a preset knowledge base to obtain a similar question set and a similar answer set; generates an exercise question bank according to the question set, the standard answer set, the similar question set and the similar answer set; the training and practicing system determines a subjective question display rule and / or an objective question display rule of the exercise question set according to a question answering configuration parameter; if all exercise questions of the exercise question set are objective questions, the exercise question set is displayed to the training personnel according to the objective question display rule to perform training and practicing; if all exercise questions of the exercise question set are subjective questions, the exercise question set is displayed to the training personnel according to the subjective question display rule and a reply answer of the training personnel to perform training and practicing; if the exercise question set includes both objective questions and subjective questions, the exercise question set is displayed to the training personnel according to the subjective question display rule, the objective question display rule and the reply answer of the training personnel to perform training and practicing. The application generates a corresponding exercise question bank according to the question set and the corresponding standard answer set in combination with the preset knowledge base, improves the question setting efficiency, generates the exercise question set according to the question answering configuration parameter and the exercise question bank, and performs training and practicing based on the exercise question set, thereby improving the training effect of the training and practicing on the training personnel and improving the practicality of the training and practicing.

[0113] The application further provides a training and practicing device, which comprises:

[0114] The obtaining module is used for obtaining a question set and a standard answer set corresponding to the question set, and generating an exercise question bank according to the question set, the standard answer set and a preset knowledge base;

[0115] The generating module is used for obtaining a question answering configuration parameter, generating an exercise question set according to the question answering configuration parameter and the exercise question bank, and performing training and practicing based on the exercise question set.

[0116] Preferably, the obtaining module is further used for:

[0117] determining a standard answer corresponding to each question according to the question set and the standard answer set, and performing similarity analysis on each question and the standard answer corresponding to each question based on a preset knowledge base to obtain a similar question set and a similar answer set;

[0118] generating an exercise question bank according to the question set, the standard answer set, the similar question set and the similar answer set.

[0119] Preferably, the obtaining module is further used for:

[0120] identify each question and a standard answer corresponding to each question, obtain keywords, and perform context relevance analysis and text similarity analysis on the keywords based on a preset knowledge base to determine a synonym set corresponding to the keywords;

[0121] According to the synonym set and the preset knowledge base, a similar question set and a similar answer set are obtained.

[0122] Preferably, the obtaining module is further configured to:

[0123] determine a fuzzy synonym set corresponding to the keywords in the preset knowledge base;

[0124] obtain a first context corresponding to the keywords in the question set and the standard answer set, obtain a second context corresponding to each fuzzy synonym in the fuzzy synonym set in the preset knowledge base, and determine a first similarity between the keywords and each fuzzy synonym according to the first context and the second context;

[0125] calculate an edit distance and a longest common subsequence between the keywords and each fuzzy synonym in the fuzzy synonym set, respectively, and determine a second similarity between the keywords and each fuzzy synonym according to the edit distance and the longest common subsequence;

[0126] determine a synonym set corresponding to the keyword set in the fuzzy synonym set according to the first similarity and the second similarity.

[0127] Preferably, the generating module further includes a displaying module configured to:

[0128] determine subjective question display rules and / or objective question display rules of the practice question set according to the answering configuration parameters;

[0129] If all practice questions in the practice question set are objective questions, the practice question set is displayed to the training personnel according to the objective question display rules for training;

[0130] If all practice questions in the practice question set are subjective questions, the practice question set is displayed to the training personnel according to the subjective question display rules and the reply answers of the training personnel for training;

[0131] If the practice question set includes both objective questions and subjective questions, the practice question set is displayed to the training personnel according to the subjective question display rules, the objective question display rules, and the reply answers of the training personnel for training.

[0132] Preferably, the display module is further configured to:

[0133] According to the subjective question display rule, determining a to-be-displayed subjective question in the exercise question set, and displaying the to-be-displayed subjective question to the training personnel;

[0134] Receiving a reply answer of the training personnel, and calculating a third similarity between the reply answer and a standard answer corresponding to the to-be-displayed subjective question;

[0135] According to the third similarity and the subjective question display rule, repeating the steps of determining a to-be-displayed subjective question in the exercise question set, and displaying the to-be-displayed subjective question to the training personnel.

[0136] Preferably, the generation module further comprises an analysis module configured to:

[0137] Obtaining a training and practicing result, analyzing the training and practicing result, generating an analysis report, and displaying the analysis report to the training personnel.

[0138] The present application further provides a training and practicing system.

[0139] The training and practicing system of the present application comprises a memory, a processor, and a training and practicing program stored in the memory and executable on the processor, and the training and practicing program, when executed by the processor, implements the steps of the training and practicing method as described above.

[0140] The method implemented when the training and practicing program executable on the processor is executed can refer to the embodiments of the training and practicing method of the present application, and will not be repeated here.

[0141] The present application further provides a computer readable storage medium.

[0142] The training and practicing program is stored on the computer readable storage medium of the present application, and the training and practicing program, when executed by the processor, implements the steps of the training and practicing method as described above.

[0143] The method implemented when the training and practicing program executable on the processor is executed can refer to the embodiments of the training and practicing method of the present application, and will not be repeated here.

[0144] It should be noted that, in this document, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0145] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0146] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and the necessary general hardware platform, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) as described above, and includes a number of instructions for making a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the methods described in the various embodiments of the present application.

[0147] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, which is made by using the content of the specification and drawings of the present application, is also included in the patent protection scope of the present application.

Claims

1. A training practice method, characterized in that, The training and practice method includes the following steps: Obtain a set of questions and a set of standard answers corresponding to the set of questions, and generate a practice question bank based on the set of questions, the set of standard answers, and a preset knowledge base. This includes: determining the standard answer for each question based on the set of questions and the set of standard answers; performing a similarity analysis on each question and its corresponding standard answer based on the preset knowledge base to obtain a set of similar questions and a set of similar answers; and generating the practice question bank based on the set of questions, the set of standard answers, the set of similar questions, and the set of similar answers. Obtain the answer configuration parameters, generate a set of practice questions based on the answer configuration parameters and the practice question bank, and conduct training and practice based on the set of practice questions; The step of performing similarity analysis on each question and its corresponding standard answer based on a preset knowledge base to obtain a set of similar questions and a set of similar answers includes: Each question and its corresponding standard answer are identified to obtain keywords. Based on a preset knowledge base, contextual relevance analysis and text similarity analysis are performed on the keywords to determine the set of synonyms corresponding to the keywords. Based on the synonym set and the preset knowledge base, a set of similar questions and a set of similar answers are obtained; The step of performing context relevance analysis and text similarity analysis on each keyword in the keyword set based on a preset knowledge base to determine the synonym set corresponding to the keyword set includes: Determine the set of fuzzy synonyms corresponding to the keywords in the preset knowledge base; Obtain the first context corresponding to the keyword from the question set and the standard answer set; obtain the second context corresponding to each fuzzy synonym in the fuzzy synonym set from the preset knowledge base; and determine the first similarity between the keyword and each fuzzy synonym based on the first context and the second context. Calculate the edit distance and longest common subsequence between the keyword and each fuzzy synonym in the fuzzy synonym set, and determine the second similarity between the keyword and each fuzzy synonym based on the edit distance and the longest common subsequence. Based on the first similarity and the second similarity, the set of synonyms corresponding to the set of keywords is determined in the set of fuzzy synonyms.

2. The training and practice method as described in claim 1, characterized in that, The set of practice questions includes subjective questions and / or objective questions, and the step of conducting training exercises based on the set of practice questions includes: Based on the answer configuration parameters, determine the subjective question display rules and / or objective question display rules for the practice question set; If all the practice questions in the set are objective questions, then the set of practice questions will be shown to the trainees according to the objective question display rules for training practice. If all the practice questions in the set are subjective questions, then according to the subjective question display rules and the trainees' responses, the set of practice questions will be displayed to the trainees for training practice. If the set of practice questions includes both objective and subjective questions, then the set of practice questions will be shown to the trainees according to the display rules for subjective questions, the display rules for objective questions, and the trainees' responses, for training practice.

3. The training and practice method as described in claim 2, characterized in that, The step of presenting the set of practice questions to the trainees according to the subjective question presentation rules and the trainees' responses includes: According to the subjective question display rules, subjective questions to be displayed are determined from the set of practice questions, and these subjective questions are then displayed to the trainees. Receive the responses from the trainees and calculate the third similarity between the responses and the standard answers to the subjective questions to be displayed; Based on the third similarity and the subjective question display rules, the following steps are repeated: determine the subjective questions to be displayed in the set of practice questions, and display the subjective questions to be displayed to the trainees.

4. The training and practice method as described in claim 1, characterized in that, After the steps of obtaining the answer configuration parameters, generating a set of practice questions based on the answer configuration parameters and the practice question bank, and conducting training exercises based on the practice question set, the method includes: Obtain the training practice results, analyze the results, generate an analysis report, and present the analysis report to the trainees.

5. A training and practice device, characterized in that, The training and practice device includes: The acquisition module is used to acquire a set of questions and a set of standard answers corresponding to the set of questions, and to generate a practice question bank based on the set of questions, the set of standard answers, and a preset knowledge base. The acquisition module is also used to determine the standard answer corresponding to each question based on the set of questions and the set of standard answers, and to perform similarity analysis on each question and its corresponding standard answer based on the preset knowledge base to obtain a set of similar questions and a set of similar answers; to generate a practice question bank based on the set of questions, the set of standard answers, the set of similar questions, and the set of similar answers; the acquisition module is also used to identify each question and its corresponding standard answer to obtain keywords, and to perform contextual relevance analysis and text similarity analysis on the keywords based on the preset knowledge base to determine a set of synonyms corresponding to the keywords; and to determine the set of synonyms based on the set of synonyms and the preset knowledge base. The knowledge base is used to obtain a set of similar questions and a set of similar answers. The acquisition module is further used to determine the set of fuzzy synonyms corresponding to the keyword in the preset knowledge base; to obtain the first context corresponding to the keyword in the set of questions and the set of standard answers; to obtain the second context corresponding to each fuzzy synonym in the set of fuzzy synonyms in the preset knowledge base; and to determine the first similarity between the keyword and each fuzzy synonym based on the first context and the second context; to calculate the edit distance and the longest common subsequence between the keyword and each fuzzy synonym in the set of fuzzy synonyms respectively; to determine the second similarity between the keyword and each fuzzy synonym based on the edit distance and the longest common subsequence; and to determine the set of synonyms corresponding to the set of keywords in the set of fuzzy synonyms based on the first similarity and the second similarity. The generation module is used to obtain the answer configuration parameters, generate a set of practice questions based on the answer configuration parameters and the practice question bank, and conduct training and practice based on the set of practice questions.

6. A training and practice system, characterized in that, The training and practice system includes: a memory, a processor, and a training and practice program stored in the memory and executable on the processor. When the training and practice program is executed by the processor, it implements the steps of the training and practice method as described in any one of claims 1 to 3.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a training practice program, which, when executed by a processor, implements the steps of the training practice method as described in any one of claims 1 to 3.

Images