CN110765278B - Method for searching similar exercises, computer equipment and storage medium - Google Patents
Method for searching similar exercises, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110765278B CN110765278B CN201911015184.8A CN201911015184A CN110765278B CN 110765278 B CN110765278 B CN 110765278B CN 201911015184 A CN201911015184 A CN 201911015184A CN 110765278 B CN110765278 B CN 110765278B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- knowledge point
- exercises
- points
- point set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Animal Behavior & Ethology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Electrically Operated Instructional Devices (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a method, computer equipment and storage medium for searching similar exercises, wherein the method comprises the following steps: s1: receiving text information of the exercises; s2: extracting a knowledge point set corresponding to the exercise; extracting an error-prone point set; s4: searching all knowledge points of which the association degree is greater than the association degree threshold value and the difficulty difference value is less than the difficulty threshold value from the knowledge point spectrogram; s5: extracting all knowledge points of which the learning condition is smaller than a learning condition threshold value according to the learning condition vector, and forming a knowledge point set to be screened; s6: judging whether the knowledge point set to be screened is empty, if so, adjusting a relevant threshold value, and returning to S4; otherwise, entering S7; s7: and searching the problem with the highest similarity with the knowledge point set to be screened from the problem library to serve as the similar problem of the problem. The invention can customize the learning path according to the current learning condition of the user and teach according to the situation.
Description
Technical Field
The present invention relates to the field of learning material search, and in particular, to a method, a computer device, and a storage medium for searching similar exercises.
Background
The learning tool for arranging the wrong questions for the children, the smart phone APP, the wrong question printer or other intelligent devices assisting learning, which already exist in the industry, only realize that the user can digitally arrange the learning materials by taking pictures, or print the learning materials through a traditional thermal printer, so that the learning materials can be regularly studied in the future, and the learning tool is simple to apply to scenes of arranging the wrong questions or arranging other learning materials for the students.
The process of the student arrangement wrong question is that the student needs to pass through the wrong question, the knowledge points related to the back of the question are combed, the reason of the student's wrong question is solved, which traps generally exist in such examination points, which matters need to be noticed when the student meets similar questions and the like, the existing scheme only solves the problem of assisting the user to arrange the learning materials more efficiently, but does not pass through the process of arranging the learning materials by the student, the knowledge points contained behind the learning materials are analyzed, the learning situation of different students (namely the mastering situation of the knowledge points) is combined, the appropriate supplementary learning materials suitable for the student under the current learning state are accurately matched, and the student user is helped to accurately find the similar questions which are related to the question and can be used for evaluation training.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method, a computer device and a storage medium for searching similar exercises.
The specific scheme is as follows:
a method of finding similar problems comprising the steps of:
s1: receiving text information of the exercises;
s2: extracting a knowledge point set corresponding to the exercise through text information of the exercise;
s3: receiving all error-prone knowledge point information extracted from the knowledge point set corresponding to the exercises by the user, and forming an error-prone knowledge point set by the error-prone knowledge point information;
s4: according to the difficulty of each knowledge point in the knowledge point spectrogram and the association degree between every two knowledge points, all knowledge points of which the association degree corresponding to each knowledge point in the knowledge point set corresponding to the problem is greater than an association degree threshold value and the difficulty difference value is smaller than a difficulty threshold value are searched from the knowledge point spectrogram;
s5: extracting all knowledge points of which the learning conditions are smaller than a learning condition threshold value from all the knowledge points searched in the step S4 according to the learning condition vectors of the user aiming at the learning conditions of all the knowledge points, and forming a knowledge point set to be screened;
s6: judging whether the knowledge point set to be screened is empty, if so, adjusting one or more of a correlation threshold, a difficulty threshold and a learning condition threshold, and returning to S4; otherwise, entering S7;
s7: and searching out the exercises with the highest similarity with the knowledge point set to be screened from the exercise library according to the knowledge point set to be screened as the similar exercises of the exercises.
Further, the knowledge point spectrogram comprises the difficulty of a plurality of knowledge points and the association degree between every two knowledge points;
the difficulty of a knowledge point is represented by a difficulty vector V, V = V 1 ,v 2 ,…,v n Element v m Representing knowledge points m, v m The value of (a) is the difficulty of the knowledge point m, m is equal to [1, n ]]N represents the number of knowledge points contained in the knowledge point spectrogram;
the relevance between knowledge points is represented by a relevance matrix P with the size of n multiplied by n, and the element P in the relevance matrix P ij Representing the degree of association between knowledge point i and knowledge point j.
Furthermore, according to a certain time interval, updating the difficulty vector V and the association matrix P according to a knowledge point set and an error-prone point set contained in all the exercises received in the time interval.
Further, the difficulty vector V is updated by: setting the number of the exercises received in the time interval as T, and calculating the frequency S of each knowledge point appearing in T knowledge point sets corresponding to the T exercises for all the knowledge points contained in the T exercises 1 And the number of occurrences S in the T sets of error-prone points corresponding to the T problems 2 The value corresponding to the knowledge point contained in the difficulty vector V corresponding to the identification point spectrogram is according to S 1 And S 2 Is updated.
Further, the method for updating the relevancy matrix P comprises: setting the number of the exercises received in the time interval to be T, aiming at each element P of the relevance matrix P ij Calculating T knowledge point sets corresponding to the T exercises: number S of knowledge point sets including knowledge point i 3 Number S of knowledge point sets including knowledge point j 4 Number S of knowledge point sets containing both knowledge points i and knowledge points j 5 The element p ij According to a value of S 3 、S 4 And S 5 Is updated.
Furthermore, according to a certain time interval, updating the learning condition vector R according to the knowledge point set and the error-prone point set contained in all the exercises received in the time interval, wherein the updating method comprises the following steps: setting the number of exercises received in the time interval to T, and aiming at each element R in the learning condition vector R k The corresponding knowledge points are k, and the number S of the knowledge point sets containing the knowledge points k in the T knowledge point sets corresponding to the T exercises is calculated 6 And the number S of error-prone point sets including knowledge point k in the T error-prone point sets 7 When S is 6 When =0, the element R is k Is updated to a set intermediate value, otherwise, the element R is updated to the set intermediate value k According to the value of S 6 And S 7 Is updated.
Furthermore, the knowledge points in the knowledge point set corresponding to the extracted exercise are extracted by combining an algorithm extraction mode and a manual extraction mode.
Further, the artificial extraction is as follows: a list of standard knowledge points is called up from which the user selects knowledge points associated with the problem.
Further, the artificial extraction is as follows: searching whether a knowledge point set corresponding to the problem established by other users exists or not, if so, calling the knowledge point set, and selecting a knowledge point from the knowledge point set by the user; otherwise, searching the knowledge points according to the subject and the grade information of the exercise, displaying the searched knowledge points according to the sequence from high to low of the relevance, and selecting the knowledge points from the displayed knowledge points by the user.
Furthermore, the knowledge points in the knowledge point set corresponding to the problem established by the called other users are ranked and displayed according to one or more of the quoted times, the praise times and the comments, and the user selects from the displayed knowledge points.
Further, the artificial extraction is as follows: when the knowledge point sets corresponding to the exercises established by other users cannot be searched, searching knowledge points with highest similarity with the subject and the grade information from the knowledge point sets established by other users according to the subject and grade information corresponding to the knowledge points extracted by the algorithm, displaying the searched knowledge points in the sequence from high to low according to the similarity, and selecting the knowledge points from the displayed knowledge points by the user.
Further, the artificial extraction is as follows: the user manually creates knowledge points corresponding to the problem.
Further, the manually created knowledge points are composed of any one or more of disciplines, grades, chapters, sections, titles, and knowledge point descriptions.
Further, the method also comprises the following steps:
s8: judging whether the answer is correct or not according to the received answers of the similar exercises, if so, determining that the error-prone point set is empty, otherwise, receiving all error-prone knowledge point information extracted from the knowledge point set corresponding to the exercises by the user, and forming the error-prone point set by the error-prone knowledge point information;
s9: and updating the learning condition vector according to the knowledge point set and the error-prone point set of the similar exercises, and returning to S4.
A computer device for finding similar problems comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method of the embodiment of the present invention.
A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to an embodiment of the invention as described above.
The technical scheme adopted by the invention has the following beneficial effects:
(1) The method solves the problems that only the learning materials are simply sorted and the deep analysis is not carried out by combining the information of the learning materials in the prior method, and can help the user to find out the appropriate supplementary learning materials.
(2) The problem data uploaded by all users are fully utilized as big data, a complete map of the incidence relation among all knowledge points is carved by utilizing the big data, so that the knowledge points are not mutually isolated information any more, but have clear incidence relation, and the incidence degree among different problems can be more accurately found through the incidence relation.
(3) Make full use of all exercise data that each user uploaded as big data to combine the data of knowledge point map, thereby portray every user's study condition, the clear grasp condition of different students to each knowledge point, and portray according to this study condition, help the student to filter the fine knowledge point exercise of mastering at present, also filter the knowledge point exercise too much in advance to current student simultaneously, and only the propelling movement is fit for the study data of current student's study condition, play the customization study route, the effect of teaching in accordance with the material.
(4) The exercise data uploaded by all users are fully utilized as big data, and the learning condition proportion statistics of students on all knowledge points is combined, so that a difficulty coefficient is conjectured for each knowledge point, the purpose of classifying different knowledge points according to the difficulty coefficient can be achieved, and the exercise data which is most suitable for each student at present is screened out for the users on the basis of the difficulty coefficient.
(5) A set of closed-loop system is adopted, a user automatically acquires required data including related knowledge points, error knowledge points and other information in the process of organizing exercise data, and a knowledge point spectrum, a user learning condition portrait and the like are drawn through an algorithm by utilizing the information.
(6) The learning process of the student is digitalized by adopting the data unit with the knowledge points as the basic data unit, so that the data can be calculated through an algorithm, and the aim of accurately recommending proper learning materials for student users is fulfilled.
Drawings
Fig. 1 is a flowchart illustrating a first embodiment of the present invention.
Fig. 2 is a schematic diagram showing a knowledge point spectrogram in this embodiment.
Detailed Description
To further illustrate the various embodiments, the invention provides the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments. With these references, one of ordinary skill in the art will appreciate other possible embodiments and advantages of the present invention.
The invention will now be further described with reference to the accompanying drawings and detailed description.
The first embodiment is as follows:
the embodiment of the invention provides a method for searching similar exercises, which comprises the following steps as shown in figure 1:
step 1, receiving text information of exercises.
Step 1 can be realized by the following three ways:
1. and receiving the pictures of the exercises, and converting the pictures into text information.
The conversion of the picture into the text message may be performed by a conventional method, such as an OCR algorithm, which is not limited herein. The OCR algorithm used in this embodiment is an algorithm (e.g., an AI open platform) provided by a third-party open platform, and the OCR interface provided by the third-party open platform is called to extract text information included in a picture, thereby achieving the purpose of converting the picture into text information.
2. If the mobile phone of the user has an OCR function, the mobile phone can directly convert the exercise picture into text information after shooting the exercise picture, and then directly receive the text information sent by the user.
3. The user can directly and manually input the text information of the exercise.
4. The user may enter textual information for the problem by voice.
And 2, extracting all knowledge points corresponding to (namely related to) the exercises through the text information of the exercises to form a knowledge point set.
The extraction of the knowledge points corresponding to the exercises can adopt various modes, such as algorithm extraction, manual extraction and combination of algorithm extraction and manual extraction.
The algorithm extraction can adopt an API interface provided by a third-party open platform, such as an Afanti open interface or an operation side open interface and other existing algorithms.
Because the maturity of each algorithm is different and the result output by the algorithm does not guarantee enough accuracy at some time, the accuracy is often not high enough only by the algorithm extraction, and therefore, the embodiment adopts a mode of combining the algorithm extraction and the manual extraction for extraction.
The manual extraction method includes but is not limited to the following methods:
(1) And calling a standard knowledge point list, and selecting knowledge points related to the exercises from the standard knowledge point list by the user.
The standard knowledge point list is a list of standard knowledge points specified in a prestored textbook outline.
(2) And searching whether a knowledge point set corresponding to the problem (the problem with the same problem as the problem) established by other users exists, if so, calling the knowledge point set, and selecting the knowledge points by the user.
Preferably, the knowledge points in the called knowledge point set are displayed after being sorted according to one or more of the referenced times, the like times and the comments, and the user selects from the displayed knowledge points.
Further, if a plurality of knowledge point sets of the problem established by a plurality of users exist, the knowledge point sets are combined into one knowledge point set, the knowledge point sets are displayed according to the sequence of the occurrence frequency of each knowledge point in the combined knowledge point set from high to low, if the knowledge point with the highest occurrence frequency is arranged at the front, the knowledge point with the lowest occurrence frequency is arranged at the back, and the user selects from the displayed knowledge points.
And if the knowledge point set corresponding to the exercise established by other users does not exist, searching knowledge points according to the subject and the grade information of the exercise, displaying the searched knowledge points according to the sequence of the relevance from high to low, and selecting from the displayed knowledge points by the user.
If the knowledge point set corresponding to the problem established by other users does not exist, the knowledge point with the highest similarity with the subject and the grade information can be searched from the knowledge point sets established by other users according to the subject and the grade information corresponding to the knowledge point extracted by the algorithm, the searched knowledge points are displayed according to the sequence of the similarity from high to low, and the user selects from the displayed knowledge points.
(3) The user manually creates knowledge points corresponding to the problem.
The manually created knowledge points are composed of any one or more items in the descriptions of disciplines, grades, chapters, sections, titles, knowledge points and the like.
It should be noted that the knowledge points manually created by the user may also be used as knowledge points searched by other users when searching for the same problem or similar problem types.
And 3, receiving all error-prone knowledge point information extracted from the knowledge point set corresponding to the exercise by the user, and forming an error-prone knowledge point set by the user.
And the user extracts the knowledge points which are easy to make mistakes from the knowledge point set according to the self-mastery condition of the user, and the knowledge points which are easy to make mistakes and extracted by the user form an error-prone point set.
And 4, searching all knowledge points of which the association degree corresponding to each knowledge point in the knowledge point set corresponding to the problem is greater than an association degree threshold and the difficulty difference value is less than a difficulty threshold from the knowledge point spectrogram according to the difficulty of each knowledge point in the knowledge point spectrogram and the association degree between every two knowledge points.
As shown in fig. 2, the knowledge point spectrogram in this embodiment is a knowledge point spectrogram, where each knowledge point corresponds to a rectangular box, the size of the rectangular box represents the difficulty of the knowledge point, and the larger the area of the rectangular box represents the higher the difficulty of the corresponding knowledge point, and vice versa. The connection line between the two rectangular frames represents that the two corresponding knowledge points are related, the thickness of the connection line represents the strength of the association degree, the thicker the connection line between the two rectangular frames represents the stronger the association degree between the two corresponding knowledge points, and vice versa.
Therefore, the knowledge point spectrum diagram in this embodiment includes the difficulty of n knowledge points and the degree of association between every two knowledge points;
representing difficulty of a knowledge point by a difficulty vector V, V = V 1 ,v 2 ,…,v n Element v m Representing knowledge points m, v m Is the difficulty of the knowledge point m, m is equal to [1, n ]]And n represents the number of knowledge points included in the knowledge point spectrum diagram. v. of m ∈[0,1]Closer to 1 indicates greater difficulty.
The relevance between knowledge points is represented by a relevance matrix P with the size of n × n, wherein the element P in the relevance matrix P ij Representing the degree of association between knowledge point i and knowledge point j. p is a radical of formula ij ∈[0,1]Closer to 1 indicates higher degree of association.
Since the number of the received problems gradually increases with time, the grasping condition of the knowledge points by the user is continuously changed, the difficulty of the corresponding knowledge points and the association degree between the knowledge points are also changed, and therefore, the knowledge point spectrogram needs to be updated regularly. Wherein:
the updating method of the difficulty vector V comprises the following steps: setting the number of the exercises received in the time interval as T, and calculating the frequency S of each knowledge point appearing in T knowledge point sets corresponding to the T exercises for all the knowledge points contained in the T exercises 1 And the number of occurrences S in the T sets of error-prone points corresponding to the T problems 2 Updating the value corresponding to the knowledge point contained in the difficulty vector V corresponding to the knowledge point spectrogram into S 2 /S 1 。
The updating method of the relevance matrix P comprises the following steps: setting the number of the exercises received in the time interval to be T, aiming at each element P of the relevance matrix P ij Calculating T knowledge point sets corresponding to the T exercises: number S of knowledge point sets including knowledge point i 3 Number S of knowledge point sets including knowledge point j 4 Number S of knowledge point sets containing both knowledge points i and knowledge points j 5 The element p ij Is updated to (S) 5 /S 3 +S 5 /S 4 )/2。
The relevancy threshold and the difficulty threshold are set and adjusted by a person skilled in the art according to experience, and in this embodiment, the relevancy threshold is preferably set to be 0.7, and the difficulty threshold is preferably set to be 0.3.
And step 5, extracting all knowledge points of which the learning conditions are smaller than the learning condition threshold value from all the knowledge points searched in the step 4 according to the learning condition vectors of the user aiming at the learning conditions of all the knowledge points, and forming a knowledge point set to be screened.
The learning condition vector R is used for recording the learning conditions of the user for all knowledge points, wherein each element R k Corresponding to a knowledge point k, the element R k The value of (A) represents the learning condition, and the value range is R k ∈[0,1]A closer to 1 indicates a better learning situation.
As the number of received exercises increases with time, the learning condition of the knowledge point by the user changes, and the learning condition of the corresponding knowledge point changes accordingly, so that the learning condition vector R needs to be updated periodically.
In this embodiment, a learning condition vector R is updated according to a knowledge point set and error-prone point set included in all the exercises received in a certain time interval, and the updating method is as follows:
setting the number of exercises received in the time interval to T, and aiming at each element R in the learning condition vector R k The corresponding knowledge points are k, and the number S of the knowledge point sets containing the knowledge points k in the T knowledge point sets corresponding to the T exercises is calculated 6 And the number S of error-prone point sets including knowledge point k in the T error-prone point sets 7 When S is 6 If =0, the element R is added k Is updated to a set intermediate value, otherwise, the element R is updated k Is updated to Pi =1-S 7 /S 6 。
The learning threshold and the intermediate value are set and adjusted by those skilled in the art based on experience, and in this embodiment, the learning threshold is preferably set to 0.7, and the intermediate value is preferably set to 0.5.
Step 6, judging whether the knowledge point set to be screened is empty, if so, adjusting one or more of the relevance threshold, the difficulty threshold and the learning condition threshold, and returning to the step 4; otherwise, go to step 7.
The adjustment is carried out in a value range according to experience.
And 7, searching out the exercises with the highest similarity with the knowledge point set to be screened from the question bank according to the knowledge point set to be screened as similar exercises of the exercises, and sending the similar exercises to the user.
The similarity calculation may be to calculate similarities between knowledge points in the knowledge point set to be screened and knowledge points in the knowledge point set corresponding to the exercises in the exercise library. The specific similarity calculation method may be implemented by using an existing algorithm, and is not limited herein.
If the exercise with the highest similarity is multiple courses, one course is selected as a similar exercise.
Through steps 1-7, the process of extracting similar exercises through one exercise is completed, and when a user needs to obtain multiple similar exercises, the following steps are required:
and step 8, judging whether the answer is correct or not according to the received answers of the similar exercises, if so, judging that the error-prone point set is empty, otherwise, receiving all error-prone knowledge point information extracted from the knowledge point set corresponding to the exercises by the user, and forming the error-prone point set by the error-prone knowledge point information.
And after receiving the similar exercises, the user answers the similar exercises, and after answering, the user sends or inputs answers.
And 9, updating the learning condition vector R according to the knowledge point set and the error-prone point set of the similar exercises, and returning to S4.
Since the similar exercises are the exercises stored in the question bank, the question bank also stores the knowledge point set corresponding to the exercises.
The updating method of the learning situation vector R is the same as that in step S5.
Through the steps 1-9, corresponding similar exercises in the exercise library can be extracted according to the exercises and the learning conditions in a continuous and cyclic manner, and a user can conveniently master the unowned knowledge points in the exercises.
It should be noted that the above-mentioned update formula of the values of the elements in the difficulty vector V, the relevance matrix P, and the learning condition vector R is only a preferred embodiment in this embodiment, and those skilled in the art can simply change the formula according to the parameters contained therein, and the invention is not limited thereto.
The first embodiment of the invention has the following beneficial effects:
(1) The method solves the problems that only the learning materials are simply sorted and the deep analysis is not carried out by combining the information of the learning materials in the prior method, and can help the user to find out the appropriate supplementary learning materials.
(2) The problem data uploaded by all users are fully utilized as big data, a complete map of the incidence relation among all knowledge points is carved by utilizing the big data, so that the knowledge points are not mutually isolated information any more, but have clear incidence relation, and the incidence degree among different problems can be more accurately found through the incidence relation.
(3) Make full use of all exercise data that each user uploaded as big data to combine the data of knowledge point atlas, thereby portray every user's study condition and portrait, the clear different student of having mastered the condition to each knowledge point, and portrait according to this study condition, help the student filter the current fine knowledge point exercise of having mastered, it is too in the past knowledge point exercise to current student to filter simultaneously, and only the study data that the propelling movement is fit for current student's study condition, play the customization study route, the effect of teaching is executed to the reason.
(4) The exercise data uploaded by all users are fully utilized as big data, and the learning condition proportion statistics of students on all knowledge points is combined, so that a difficulty coefficient is conjectured for each knowledge point, the purpose of classifying different knowledge points according to the difficulty coefficient can be achieved, and the exercise data which is most suitable for each student at present is screened out for the users on the basis of the difficulty coefficient.
(5) A set of closed-loop system is adopted, a user automatically acquires required data including related knowledge points, error knowledge points and other information in the process of organizing exercise data, and a knowledge point spectrum, a user learning condition portrait and the like are drawn through an algorithm by utilizing the information.
(6) The learning process of the student is digitalized by adopting the data unit with the knowledge points as the basic data unit, so that the data can be calculated through an algorithm, and the aim of accurately recommending proper learning materials for student users is fulfilled.
Example two:
the invention also provides a computer device for searching similar exercises, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the method embodiment of the first embodiment of the invention.
Further, as an executable solution, the computer device for searching for similar exercises may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices.
Further, as an executable solution, the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, and the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like that is the control center of the computer device for finding similar problems, and various interfaces and lines are used to connect the various parts of the overall computer device for finding similar problems.
The memory may be used to store the computer programs and/or modules, and the processor may implement the various functions of the computer device for finding similar problems by running or executing the computer programs and/or modules stored in the memory and invoking the data stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the mobile phone, and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The invention also provides a computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the above-mentioned method of an embodiment of the invention.
The computer device integrated modules/units for finding similar problems, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM ), random Access Memory (RAM), software distribution medium, and the like.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (15)
1. A method for finding similar problems, comprising the steps of:
s1: receiving text information of the exercises;
s2: extracting a knowledge point set corresponding to the exercise through text information of the exercise;
s3: receiving all error-prone knowledge point information extracted from a knowledge point set corresponding to the exercise by a user, and forming an error-prone knowledge point set by the error-prone knowledge point information;
s4: according to the difficulty of each knowledge point in the knowledge point spectrogram and the association degree between every two knowledge points, searching all knowledge points of which the association degree corresponding to each knowledge point in the knowledge point set corresponding to the exercise is greater than an association degree threshold value and the difficulty difference value is less than a difficulty threshold value from the knowledge point spectrogram;
the knowledge point spectrogram comprises the difficulty of a plurality of knowledge points and the association degree between every two knowledge points;
the difficulty of a knowledge point is represented by a difficulty vector V, V = V 1 ,v 2 ,…,v n Element v m Representing knowledge points m, v m Is the difficulty of the knowledge point m, m is equal to [1, n ]]N represents the number of knowledge points contained in the knowledge point spectrogram;
the relevance between knowledge points is represented by a relevance matrix P with the size of n multiplied by n, and the element P in the relevance matrix P ij Representing the degree of association between the knowledge point i and the knowledge point j;
s5: extracting all knowledge points of which the learning conditions are smaller than a learning condition threshold value from all the knowledge points searched in the step S4 according to the learning condition vectors of the user aiming at the learning conditions of all the knowledge points, and forming a knowledge point set to be screened;
s6: judging whether the knowledge point set to be screened is empty, if so, adjusting one or more of a correlation threshold, a difficulty threshold and a learning condition threshold, and returning to S4; otherwise, entering S7;
s7: and searching out the exercises with the highest similarity to the knowledge point set to be screened from the question bank according to the knowledge point set to be screened, wherein the exercises are used as similar exercises of the exercises.
2. The method of finding similar problems of claim 1 wherein: and updating the difficulty vector V and the association matrix P according to a certain time interval and the knowledge point set and the error-prone point set contained in all the exercises received in the time interval.
3. The method of finding similar problems of claim 2 wherein: the updating method of the difficulty vector V comprises the following steps: setting the number of the exercises received in the time interval as T, and calculating the frequency S of each knowledge point appearing in T knowledge point sets corresponding to the T exercises for all the knowledge points contained in the T exercises 1 And the number of occurrences S in the T sets of error-prone points corresponding to the T problems 2 The value corresponding to the knowledge point contained in the difficulty vector V corresponding to the identification point spectrogram is determined according to S 1 And S 2 Is updated.
4. The method of finding similar problems of claim 2 wherein: the updating method of the relevance matrix P comprises the following steps: setting the number of the exercises received in the time interval to be T, aiming at each element P of the relevance matrix P ij Calculating T knowledge point sets corresponding to the T exercises: number S of knowledge point sets including knowledge point i 3 Number S of knowledge point sets including knowledge point j 4 Number S of knowledge point sets containing both knowledge points i and knowledge points j 5 The element p ij According to a value of S 3 、S 4 And S 5 Is updated.
5. The method of claim 1, wherein the method comprises searching for similar problemsIs characterized in that: according to a certain time interval, updating the learning condition vector R according to the knowledge point set and the error-prone point set contained in all the exercises received in the time interval, wherein the updating method comprises the following steps: setting the number of exercises received in the time interval to T, and aiming at each element R in the learning condition vector R k The corresponding knowledge points are k, and the number S of the knowledge point sets containing the knowledge points k in the T knowledge point sets corresponding to the T exercises is calculated 6 And the number S of error-prone point sets including knowledge point k in the T error-prone point sets 7 When S is 6 If =0, the element R is added k Is updated to a set intermediate value, otherwise, the element R is updated to the set intermediate value k According to S 6 And S 7 Is updated.
6. The method of finding similar problems of claim 1 wherein: and extracting knowledge points in the knowledge point set corresponding to the exercise by combining algorithm extraction and manual extraction.
7. The method of finding similar problems of claim 6 wherein: the artificial extraction comprises the following steps: a list of standard knowledge points is called up from which the user selects knowledge points associated with the problem.
8. The method of finding similar problems of claim 6 wherein: the artificial extraction comprises the following steps: searching whether a knowledge point set corresponding to the problem established by other users exists or not, if so, calling the knowledge point set, and selecting a knowledge point from the knowledge point set by the user; otherwise, searching the knowledge points according to the subject and the grade information of the exercise, displaying the searched knowledge points according to the sequence from high to low of the relevance, and selecting the knowledge points from the displayed knowledge points by the user.
9. The method of finding similar problems of claim 8 wherein: and sequencing and displaying the knowledge points in the knowledge point set corresponding to the exercises established by the called other users according to one or more of the quoted times, the praise times and the comments, and selecting the knowledge points from the displayed knowledge points by the user.
10. The method of finding similar problems of claim 6 wherein: the artificial extraction comprises the following steps: when the knowledge point sets corresponding to the exercises established by other users cannot be searched, searching knowledge points with highest similarity with the subject and the grade information from the knowledge point sets established by other users according to the subject and grade information corresponding to the knowledge points extracted by the algorithm, displaying the searched knowledge points in the sequence from high to low according to the similarity, and selecting the knowledge points from the displayed knowledge points by the user.
11. The method of finding similar problems of claim 6 wherein: the artificial extraction comprises the following steps: the user manually creates knowledge points corresponding to the problem.
12. The method of finding similar problems of claim 11 wherein: the manually created knowledge points are composed of any one or more of disciplines, grades, chapters, sections, titles and knowledge point descriptions.
13. The method of finding similar problems of claim 1 wherein: further comprising:
s8: judging whether the answer is correct or not according to the received answers of the similar exercises, if so, determining that the error-prone point set is empty, otherwise, receiving all error-prone knowledge point information extracted from the knowledge point set corresponding to the exercises by the user, and forming the error-prone point set by the error-prone knowledge point information;
s9: and updating the learning condition vector according to the knowledge point set and the error-prone point set of the similar exercises, and returning to S4.
14. A computer device for finding similar problems, comprising: comprising a processor, a memory and a computer program stored in said memory and running on said processor, said processor implementing the steps of the method according to any one of claims 1 to 13 when executing said computer program.
15. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911015184.8A CN110765278B (en) | 2019-10-24 | 2019-10-24 | Method for searching similar exercises, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911015184.8A CN110765278B (en) | 2019-10-24 | 2019-10-24 | Method for searching similar exercises, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110765278A CN110765278A (en) | 2020-02-07 |
| CN110765278B true CN110765278B (en) | 2022-10-25 |
Family
ID=69333866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911015184.8A Active CN110765278B (en) | 2019-10-24 | 2019-10-24 | Method for searching similar exercises, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110765278B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114913729B (en) * | 2021-02-09 | 2023-06-20 | 广州视源电子科技股份有限公司 | Question selecting method, device, computer equipment and storage medium |
| CN113722506A (en) * | 2021-08-31 | 2021-11-30 | 广东艾檬电子科技有限公司 | Intelligent knowledge point identification method, system, intelligent equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143163A (en) * | 2014-08-04 | 2014-11-12 | 兴天通讯技术（天津）有限公司 | Generating method and device for knowledge map |
| CN105761567A (en) * | 2016-05-04 | 2016-07-13 | 北京新唐思创教育科技有限公司 | Method and device for dynamically recommending exercises |
| CN105787839A (en) * | 2016-03-23 | 2016-07-20 | 成都准星云学科技有限公司 | Method and device for pushing learning resources |
| CN105955962A (en) * | 2016-05-10 | 2016-09-21 | 北京新唐思创教育科技有限公司 | Method and device for calculating similarity of topics |
| CN106781785A (en) * | 2017-01-04 | 2017-05-31 | 广东小天才科技有限公司 | A kind of item difficulty construction method and device, service equipment based on big data |
| CN106846962A (en) * | 2017-03-20 | 2017-06-13 | 安徽七天教育科技有限公司 | A kind of wrong answer list generation method based on the wrong topic of student and accurate recommendation |
| CN109035088A (en) * | 2018-07-19 | 2018-12-18 | 江苏黄金屋教育发展股份有限公司 | Adaptive learning method based on mistake topic |
| CN109191345A (en) * | 2018-09-17 | 2019-01-11 | 合肥工业大学 | A kind of cognitive diagnosis method of Student oriented cognitive process |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1363535B1 (en) * | 2001-01-30 | 2012-01-04 | R. Christopher Decharms | Methods for physiological monitoring, training, exercise and regulation |
| US8873813B2 (en) * | 2012-09-17 | 2014-10-28 | Z Advanced Computing, Inc. | Application of Z-webs and Z-factors to analytics, search engine, learning, recognition, natural language, and other utilities |
| US10162882B2 (en) * | 2014-07-14 | 2018-12-25 | Nternational Business Machines Corporation | Automatically linking text to concepts in a knowledge base |
-
2019
- 2019-10-24 CN CN201911015184.8A patent/CN110765278B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143163A (en) * | 2014-08-04 | 2014-11-12 | 兴天通讯技术（天津）有限公司 | Generating method and device for knowledge map |
| CN105787839A (en) * | 2016-03-23 | 2016-07-20 | 成都准星云学科技有限公司 | Method and device for pushing learning resources |
| CN105761567A (en) * | 2016-05-04 | 2016-07-13 | 北京新唐思创教育科技有限公司 | Method and device for dynamically recommending exercises |
| CN105955962A (en) * | 2016-05-10 | 2016-09-21 | 北京新唐思创教育科技有限公司 | Method and device for calculating similarity of topics |
| CN106781785A (en) * | 2017-01-04 | 2017-05-31 | 广东小天才科技有限公司 | A kind of item difficulty construction method and device, service equipment based on big data |
| CN106846962A (en) * | 2017-03-20 | 2017-06-13 | 安徽七天教育科技有限公司 | A kind of wrong answer list generation method based on the wrong topic of student and accurate recommendation |
| CN109035088A (en) * | 2018-07-19 | 2018-12-18 | 江苏黄金屋教育发展股份有限公司 | Adaptive learning method based on mistake topic |
| CN109191345A (en) * | 2018-09-17 | 2019-01-11 | 合肥工业大学 | A kind of cognitive diagnosis method of Student oriented cognitive process |
Non-Patent Citations (2)
| Title |
|---|
| "LearningAssistant: A novel learning resource recommendation system";Lei Liu 等;《Advances in Neural Information Processing Systems》;20150306;第1-5页 * |
| "基于隐式评分和相似度传递的学习资源推荐";付芬 等;《计算机应用研究》;20171231;第3725-3729页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110765278A (en) | 2020-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359215B (en) | Video intelligent pushing method and system | |
| CN109598995B (en) | Intelligent teaching system based on Bayesian knowledge tracking model | |
| CN109816265B (en) | Knowledge characteristic mastery degree evaluation method, question recommendation method and electronic equipment | |
| CN112395403B (en) | Knowledge graph-based question and answer method, system, electronic equipment and medium | |
| CN106127634B (en) | Student academic achievement prediction method and system based on naive Bayes model | |
| CN108563780A (en) | Course content recommends method and apparatus | |
| CN113395578B (en) | Method, device, equipment and storage medium for extracting video theme text | |
| CN110825867B (en) | Similar text recommendation method and device, electronic equipment and storage medium | |
| CN111046194A (en) | Method for constructing multi-mode teaching knowledge graph | |
| CN110765278B (en) | Method for searching similar exercises, computer equipment and storage medium | |
| CN110659311B (en) | Topic pushing method and device, electronic equipment and storage medium | |
| CN109785691B (en) | Method and system for assisting learning through terminal | |
| CN107544956A (en) | A kind of text wants point detecting method and system | |
| CN111008340A (en) | Course recommendation method, device and storage medium | |
| CN110765241B (en) | Super-outline detection method and device for recommendation questions, electronic equipment and storage medium | |
| CN109559576A (en) | A kind of children companion robot and its early teaching system self-learning method | |
| CN116204714A (en) | Recommendation method, recommendation device, electronic equipment and storage medium | |
| CN110110143B (en) | Video classification method and device | |
| CN117150151B (en) | Wrong question analysis and test question recommendation system and method based on large language model | |
| CN110321882A (en) | A kind of education resource acquisition methods, device, learning terminal and storage medium | |
| CN112800177B (en) | FAQ knowledge base automatic generation method and device based on complex data types | |
| CN107656760A (en) | Data processing method and device, electronic equipment | |
| CN113254752B (en) | Lesson preparation method and device based on big data and storage medium | |
| CN115984059A (en) | Collaborative fusion education attention training method, system, device and medium | |
| CN112163789B (en) | Teacher workload evaluation system and method for online education |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |