Child mathematical thinking training effect evaluation method and system based on data mining

Abstract

The invention relates to the technical field of evaluation methods, and discloses a data mining-based child mathematical thinking training effect evaluation method and system, and the method comprises the steps: obtaining the interaction number data, interaction time data and user age of a user on a mathematical thinking training platform; performing mathematical thinking analysis according to the interaction quantity data to obtain a mathematical thinking level; performing learning effect analysis according to the interaction time data, and calculating to obtain a learning effect coefficient; grading according to the user age and a preset age grade threshold to obtain a user age grade; performing mathematical ability analysis according to the mathematical thinking level, the learning effect coefficient and the user age level to obtain a mathematical ability score; and according to the mathematical ability score, in combination with a preset ability score threshold, performing grading evaluation on a child thinking training effect. The method can improve the evaluation accuracy of the mathematical thinking training effect of children.

Description

Technical Field

[0001] The present invention relates to the technical field of evaluation methods, and in particular to a method and system for evaluating the effect of children's mathematical thinking training based on data mining. Background Art

[0002] At present, mathematical thinking training is a widely used learning method in today's education field. Its core goal is to help children not only improve their basic mathematical knowledge and skills, but also enhance their ability to solve mathematical problems and cultivate innovative thinking. In order to ensure that every child can get the most from this training, educators and researchers are paying more and more attention to the in-depth understanding of the individual learning characteristics and training results of children in the process of mathematical thinking training. This process requires the use of a continuous and accurate evaluation mechanism so that customized guidance and support can be provided according to the specific needs of each child, thereby effectively promoting their achievements and interest in mathematics.

[0003] In one prior art, standardized testing is a common way to evaluate training results. It uses a series of designed math questions to evaluate children's math knowledge and skill levels. Such tests include multiple-choice questions, fill-in-the-blank questions, and essay questions, which are designed to examine students' calculation ability, logical reasoning ability, problem-solving ability, etc. At the same time, with the development of information technology, there are now many computer- and Internet-based evaluation tools, such as online tests and math games, which can automatically record children's learning process and results, provide instant feedback, and even adjust the difficulty according to children's performance to achieve personalized learning.

[0004] In the prior art, traditional math thinking tests are limited to paper-and-pencil tests, which cannot fully and accurately evaluate children's math thinking abilities in practical applications, because they often only involve limited math knowledge and skills, and cannot dynamically evaluate children's learning in a short period of time. At the same time, the children's learning effects are only evaluated based on the final scores, while ignoring the changes in their interest, attitude and participation in the course. Such an evaluation method is difficult to fully reflect the actual performance and progress of children in math thinking training. In general, the evaluation of the effectiveness of children's math thinking training is not accurate. Summary of the invention

[0005] The present invention provides a method and system for evaluating the effect of children's mathematical thinking training based on data mining, so as to improve the accuracy of the evaluation of the effect of children's mathematical thinking training.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a method for evaluating the effect of children's mathematical thinking training based on data mining, comprising: Obtain the user's interaction quantity data, interaction time data and user age on the mathematical thinking training platform; Performing mathematical thinking analysis based on the interaction quantity data to obtain a mathematical thinking level; Performing a learning effect analysis based on the interaction time data and calculating a learning effect coefficient; Performing classification according to the user's age and a preset age level threshold to obtain the user's age level; Performing a mathematical ability analysis according to the mathematical thinking level, the learning effect coefficient and the user's age level to obtain a mathematical ability score; The effect of children's thinking training is graded and evaluated based on the mathematical ability score combined with a preset ability score threshold.

[0007] In an optional implementation, performing mathematical thinking analysis based on the interactive quantity data to obtain a mathematical thinking level includes: The interaction quantity data includes the total number of interaction questions, the number of user interactions, the interaction results and the interaction difficulty; Calculate the average number of interactions based on the total number of interactive topics and the number of user interactions; Calculating the correctness rate according to the total number of interactive questions and the interactive results; Calculating difficulty adaptability according to the interaction difficulty and the interaction result; The mathematical thinking level is calculated by the following formula: ; in, For the level of mathematical thinking, are the first weight, the second weight and the third weight respectively, is the average number of interactions, For the accuracy, It is the difficulty adaptation.

[0008] In an optional implementation, performing learning effect analysis based on the interaction time data to calculate a learning effect coefficient includes: The exercise score is calculated using the following formula: ; The learning effect coefficient is calculated by the following formula: ; in, is the score of the i-th question, is the completion status of question i, is the difficulty coefficient of the i-th question, The time it takes for the user to complete question i, is the average time for all users to complete the i-th question, i is the question number, is the learning effect coefficient, The total number of questions.

[0009] In an optional implementation, the grading according to the user age and a preset age grade threshold to obtain the user age grade includes: When the user's age is lower than a preset first age threshold, classifying the user's age level as a toddler level; When the user age is higher than the first age threshold and the user age is lower than a preset second age threshold, the user age level is classified as primary; The user age level includes: infant level, elementary level, intermediate level or advanced level.

[0010] In an optional implementation, the performing of mathematical ability analysis according to the mathematical thinking level, the learning effect coefficient and the user age level to obtain a mathematical ability score includes: digitizing the user's age level to obtain a normalized age level; The math ability score is calculated using the following formula: ; in, is the math ability score, is the normalized age level, is the learning effect coefficient, For the level of mathematical thinking, It is the Mth power of the natural constant.

[0011] In an optional implementation, the step of performing a graded evaluation on the effect of children's thinking training based on the math ability score combined with a preset ability score threshold includes: When the math ability score is higher than a preset first ability score threshold, determining that the user's math ability level is excellent; When the math ability score is lower than a preset second ability score threshold, determining that the user's math ability level is unqualified; When the math ability score is lower than or equal to a preset first ability score threshold and higher than or equal to a preset second ability score threshold, it is determined that the user's math ability level is good.

[0012] In an optional implementation, after the evaluation of the children's thinking training effect is performed according to the math ability score combined with the preset ability score threshold, the method further includes: When the user's math ability level is determined to be unqualified, a reminder message is sent to the user, and the difficulty of math thinking training is reduced and the training time is extended.

[0013] In an optional implementation, the obtaining of the user's interaction quantity data and interaction time data on the mathematical thinking training platform includes: Monitor whether the scanning pen is pressed. When the scanning pen is pressed, analyze the user's intention based on the movement characteristics of the scanning pen to obtain the user's true intention; According to the real intention of the user, the user is matched from the platform content library to obtain the historical user learning behavior; The historical user learning behavior is uploaded to a cloud server, and the historical user learning behavior is obtained through the cloud server; wherein the historical user learning behavior includes the user's interaction quantity data and interaction time data.

[0014] In a second aspect, the present invention provides a children's mathematical thinking training effect evaluation system based on data mining, comprising: A data acquisition module is used to obtain the user's interaction quantity data, interaction time data and user age on the mathematical thinking training platform; A thinking level module, used for performing mathematical thinking analysis according to the interactive quantity data to obtain a mathematical thinking level; A learning effect module, used to analyze the learning effect according to the interaction time data and calculate the learning effect coefficient; An age rating module, used to perform classification according to the user's age and a preset age rating threshold to obtain the user's age rating; A mathematics ability module, used to perform mathematics ability analysis according to the mathematics thinking level, the learning effect coefficient and the user age level to obtain a mathematics ability score; The grading assessment module is used to perform a grading assessment on the effect of children's thinking training according to the mathematical ability score combined with a preset ability score threshold.

[0015] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements any one of the above-mentioned methods for evaluating the effectiveness of children's mathematical thinking training based on data mining.

[0016] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for evaluating the effectiveness of children's mathematical thinking training based on data mining.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention obtains the children's mathematical thinking level by analyzing the number of interactive questions of children on a mathematical thinking training platform, the children's learning behavior data on the mathematical thinking training platform and the children's problem-solving result data, combined with the average level of all users of the same age group. This can not only understand the children's mathematical thinking ability level, but also, by combining with a mathematical thinking ability algorithm, can more comprehensively and accurately evaluate the children's mathematical thinking ability, thereby improving the reliability and effectiveness of the evaluation. By analyzing the children's interactive data in the learning process, their thinking methods and strategies can be understood more specifically, their difficulties in certain types of questions can be discovered, and the scientific nature of the evaluation results can be improved.

[0018] The present invention calculates the learning effect coefficient by analyzing the completion time of children's interactive questions on the mathematical thinking training platform, the children's learning behavior data on the platform, and the children's question-solving results data, combined with the average level of all users of the same age group. This method can not only reflect the learning efficiency and quality of children, but also more comprehensively and accurately evaluate the learning effect of children by combining the algorithm of mathematical thinking ability and learning time, thereby enhancing the reliability and effectiveness of the evaluation. By deeply analyzing the time investment and interactive data of children in the learning process, their learning habits and efficiency can be understood more specifically, and the obstacles existing in specific types of questions can be identified, thereby making the evaluation algorithm more scientific.

[0019] The present invention analyzes the children's mathematical thinking level, learning effect coefficient and user age level, combines these multi-dimensional data to conduct a comprehensive mathematical ability analysis, and finally calculates the mathematical ability score. Taking into account that different age groups have different requirements for mathematical thinking levels and learning effects, this method can not only fully reflect the children's current mathematical ability level, but also conduct personalized assessments based on the characteristics of different age groups. By integrating algorithms that integrate mathematical thinking, learning efficiency and age development characteristics, children's mathematical ability can be more accurately assessed, improving the reliability and effectiveness of the assessment. By carefully analyzing the children's performance in the learning process, including problem-solving speed, accuracy and comparison with their peers, their mathematical strengths and weaknesses can be understood more specifically. This helps to improve the accuracy of the evaluation of the effect of children's mathematical thinking training. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flowchart of a method for evaluating the effect of children's mathematical thinking training based on data mining provided by the first embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of a children's mathematical thinking training effect evaluation system based on data mining provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] At present, mathematical thinking training is a widely used learning method in today's education field. Its core goal is to help children not only improve their basic mathematical knowledge and skills, but also enhance their ability to solve mathematical problems and cultivate innovative thinking. In order to ensure that every child can get the most from this training, educators and researchers are paying more and more attention to the in-depth understanding of the individual learning characteristics and training results of children in the process of mathematical thinking training. This process requires the use of a continuous and accurate evaluation mechanism so that customized guidance and support can be provided according to the specific needs of each child, thereby effectively promoting their achievements and interest in mathematics.

[0023] In one prior art, standardized testing is a common way to evaluate training results. It uses a series of designed math questions to evaluate children's math knowledge and skill levels. Such tests include multiple-choice questions, fill-in-the-blank questions, and essay questions, which are designed to examine students' calculation ability, logical reasoning ability, problem-solving ability, etc. At the same time, with the development of information technology, there are now many computer- and Internet-based evaluation tools, such as online tests and math games, which can automatically record children's learning process and results, provide instant feedback, and even adjust the difficulty according to children's performance to achieve personalized learning.

[0024] In the prior art, traditional math thinking tests are limited to paper-and-pencil tests, which cannot fully and accurately evaluate children's math thinking abilities in practical applications, because they often only involve limited math knowledge and skills, and cannot dynamically evaluate children's learning in a short period of time. At the same time, the children's learning effects are only evaluated based on the final scores, while ignoring the changes in their interest, attitude and participation in the course. Such an evaluation method is difficult to fully reflect the actual performance and progress of children in math thinking training. In general, the evaluation of the effectiveness of children's math thinking training is not accurate.

[0025] To solve the above problems, refer to Figure 1 The first embodiment of the present invention provides a method for evaluating the effect of children's mathematical thinking training based on data mining, comprising the following steps: S11, obtaining the user's interaction quantity data, interaction time data and user age on the mathematical thinking training platform; S12, performing mathematical thinking analysis according to the interaction quantity data to obtain a mathematical thinking level; S13, performing a learning effect analysis based on the interaction time data, and calculating a learning effect coefficient; S14, performing classification according to the user age and a preset age level threshold to obtain the user age level; S15, performing a mathematical ability analysis according to the mathematical thinking level, the learning effect coefficient and the user's age level to obtain a mathematical ability score; S16, performing a graded evaluation on the effect of the children's thinking training according to the mathematical ability score combined with a preset ability score threshold.

[0026] In step S11, the user's interaction quantity data, interaction time data and user age on the mathematical thinking training platform are obtained.

[0027] In one implementation, the mathematical thinking training platform records every interactive operation of the user, including logging in, answering questions, submitting homework, etc. These operations will be recorded in the log file of the platform, thereby obtaining the interactive quantity data and interactive time data. The platform's database stores the user's personal information (such as user age), answering records, interactive records and other data. This method reads the information in the database through an API interface.

[0028] In one embodiment, the user's interaction quantity data and interaction time data are extracted from historical user learning behaviors, and the historical user learning behaviors can be obtained through the motion characteristics of the scanning pen. Specifically, the acquisition of historical user learning behaviors includes: Monitor whether the scanning pen is pressed. When the scanning pen is pressed, analyze the user's intention based on the movement characteristics of the scanning pen to obtain the user's true intention; According to the real intention of the user, the user is matched from the platform content library to obtain the historical user learning behavior; The historical user learning behavior is uploaded to a cloud server, and the historical user learning behavior is obtained through the cloud server.

[0029] In a specific application, it monitors whether the scanning pen is pressed. When the scanning pen is pressed, the camera is initialized to prepare for taking pictures. While the scanning pen is pressed, pictures are continuously taken and generated according to a preset frame difference, and pictures and timestamps are continuously read from the cache of the camera. The cached images taken out from the cache are numbered, and a timestamp is added to each of the cached images to obtain numbered scanning pen images. The scanning pen motion analysis is performed based on the numbered scanning pen images to obtain scanning pen motion features. The user intention analysis is performed based on the scanning pen motion features to obtain the user's real intention. Matching is performed from the platform content library based on the user's real intention to obtain historical user learning behavior. The historical user learning behavior is uploaded to the cloud server, and the historical user learning behavior is obtained through the cloud server. The historical user learning behavior includes the user's interaction quantity data and interaction time data.

[0030] In this embodiment, the user's scanning behavior is accurately captured by monitoring the pressing action of the scanning pen and combining it with the continuously captured images. Specifically, when the scanning pen is pressed, the system initializes the camera to prepare for taking pictures; while the scanning pen is pressed, it continuously captures and generates pictures according to the preset frame difference, and continuously reads pictures and timestamps from the camera's cache. The system numbers the cached images taken from the cache, and adds a timestamp to each cached image to obtain a numbered scanning pen image. Subsequently, the system performs scanning pen motion analysis based on the numbered scanning pen image to obtain scanning pen motion features, including motion direction, motion angle, and motion distance. By analyzing these features, the system can distinguish between the user's intentional operations and unintentional touches, and reduce the impact of misoperation on user intent recognition.

[0031] The present invention analyzes the motion characteristics of the scanning pen through image processing technology, including grayscale processing, contour detection, minimum circumscribed circle calculation and other steps. First, the numbered scanning pen image is grayscaled to obtain the scanning pen grayscale image; then, the grayscale image is contour detected to obtain the scanning pen contour; finally, the minimum circumscribed circle is calculated for the scanning pen contour, and the center coordinates of the minimum circumscribed circle are used as the scanning pen center coordinates. These steps accurately capture and analyze the motion characteristics of the scanning pen, thereby improving the accuracy of user intention recognition. The present invention monitors the pressing action of the scanning pen, continuously captures images, analyzes motion characteristics and user intentions, and finally matches from the platform content library according to the user's true intention to obtain historical user learning behavior; the historical user learning behavior is uploaded to the cloud server, and the historical user learning behavior is obtained through the cloud server. The platform content library classifies the learning content according to the dimensions of subject, grade, difficulty, etc., and adds labels to each learning content, such as "mathematics", "third grade", "multiplication", etc.

[0032] In step S12, mathematical thinking analysis is performed based on the interaction quantity data to obtain a mathematical thinking level.

[0033] In one embodiment, the interaction quantity data includes the total number of interaction questions, the number of user interactions, the interaction results and the interaction difficulty; Calculate the average number of interactions based on the total number of interactive topics and the number of user interactions; Calculating the correctness rate according to the total number of interactive questions and the interactive results; Calculating difficulty adaptability according to the interaction difficulty and the interaction result; The mathematical thinking level is calculated by the following formula: ; in, For the level of mathematical thinking, are the first weight, the second weight and the third weight respectively, is the average number of interactions, For the accuracy, It is the difficulty adaptation.

[0034] It is worth noting that the total number of interactive questions indicates the total number of questions that users have tried on the platform. The number of user interactions is calculated by recording the number of interactions of users on each question, including the number of attempts, the number of answers submitted, etc. The interactive results are calculated by recording the results of each user interaction, such as correct, wrong, partially correct, etc. The interactive difficulty is calculated by recording the difficulty level of each question. The interactive result is numerically 1 for correct, 0 for wrong, and 0.5 for partially correct. The interactive difficulty is the average score of all users. The average number of interactions refers to the average number of interactions of users on each question, which is obtained by dividing the total number of user interactions by the total number of interactive questions. The correctness rate refers to the proportion of correct answers of users in all questions, which is obtained by dividing the sum of the numerical interaction results by the total number of interactive questions. Difficulty fitness refers to the performance of users on questions of different difficulty levels, which is obtained by taking the interactive difficulty as the weight and weighting the interaction results. The first weight, the second weight, and the third weight are the weights of the average number of interactions, the correctness rate, and the difficulty fitness, respectively. The maximum value of the mathematical thinking level is controlled by adjusting the weights, which is used for the subsequent calculation of mathematical ability scores. In subsequent processing, the mathematical thinking level will be normalized by dividing the obtained mathematical thinking level by the maximum value to obtain the normalized mathematical thinking level.

[0035] In step S13, a learning effect analysis is performed based on the interaction time data to calculate a learning effect coefficient.

[0036] In one implementation, the exercise score is calculated using the following formula: ; The learning effect coefficient is calculated by the following formula: ; in, is the score of the i-th question, is the completion status of question i, is the difficulty coefficient of the i-th question, The time it takes for the user to complete question i, is the average time for all users to complete the i-th question, i is the question number, is the learning effect coefficient, The total number of questions.

[0037] It is worth mentioning that is the completion status of the i-th question, and its value is 1 or 0, representing completion and incomplete respectively. is the difficulty coefficient of the i-th question, which is calculated based on the average of all users, and is between 0 and 1. The larger the value, the greater the difficulty. If the user completes the question, the completion status is 1, and if it is not completed, the completion status is 0, which means that only completed questions will affect the score of the exercise. For the exercise score, if the user spends less time than the average time to complete the question, the score will be higher. If the user spends more time than the average time to complete the question, the score will be lower. The higher the difficulty coefficient, the higher the score, which encourages users to challenge difficult questions. The less time the user spends to complete the question, the higher the score, which encourages users to complete the question efficiently. The learning effect coefficient is the average of all question scores, reflecting the overall performance of the user on all questions. By taking the average value, the impact of the performance of a single question on the overall evaluation is avoided, and a comprehensive evaluation is obtained.

[0038] In step S14, the user age is classified according to the user age and a preset age level threshold to obtain the user age level.

[0039] In one implementation, when the user age is lower than a preset first age threshold, the user age level is classified as a toddler level; when the user age is higher than the first age threshold and the user age is lower than a preset second age threshold, the user age level is classified as a primary level; wherein the user age levels include: toddler level, primary level, intermediate level or advanced level. The first age threshold and the second age threshold are set according to usage. For example, the first age threshold is set to 6 years old, which is the boundary between the toddler level and the primary level. The second age threshold is the boundary between the primary level and the intermediate level, and is set to 10 years old. The third age threshold is the boundary between the intermediate level and the advanced level, and is set to 14 years old. For a 4-year-old user, the user age level is determined to be a toddler level. For a 10-year-old user, the user age level is determined to be an intermediate level.

[0040] In step S15, a mathematical ability analysis is performed according to the mathematical thinking level, the learning effect coefficient and the user age level to obtain a mathematical ability score.

[0041] In one implementation, the user age level is digitized to obtain a normalized age level; The math ability score is calculated using the following formula: ; in, is the math ability score, is the normalized age level, is the learning effect coefficient, For the level of mathematical thinking, It is the Mth power of the natural constant.

[0042] It is worth noting that the user age level is quantified to obtain a normalized age level including: a user whose user age level is infant level has a normalized age level of 0; a user whose user age level is elementary level has a normalized age level of 0.33; a user whose user age level is intermediate level has a normalized age level of 0.67; and a user whose user age level is advanced level has a normalized age level of 1.

[0043] It is worth noting that for a user with a math thinking level of 0.7, a normalized age level of 0.33, and a learning effect coefficient of 0.8, his math ability score is 1.2. The learning effect coefficient reflects the user's overall performance on all questions. The normalized age level reflects the user's age relative to other users. The math thinking level reflects the user's math thinking ability and amplifies the impact of the math thinking level through exponential power. The higher the learning effect coefficient, the better the user's performance on all questions and the higher the score. The higher the normalized age level, the older the user, the larger the denominator, which leads to a smaller score, which means that older users need a higher learning effect coefficient to get a higher math ability score. The math thinking level reflects the user's math thinking ability, including the average number of interactions, accuracy, and difficulty adaptability. The higher the math thinking level, the stronger the user's math thinking ability, which is due to the increase in the number of interactions or the increase in the single score. The former indicates that the user has a high interest in mathematics, and the latter indicates high talent, both of which mean that the math thinking is high. The user performed very well on all questions and scored high. The user has strong mathematical thinking ability and can quickly solve difficult problems. Under the same circumstances, the younger the user is, the higher the mathematical ability score can be. Users with low learning effect coefficients perform poorly on many questions and have low scores. Users with low mathematical thinking levels have weak mathematical thinking ability and find it difficult to solve difficult problems. Older users have higher learning requirements, so they may also have low scores.

[0044] In step S16, the effect of children's thinking training is graded and evaluated according to the mathematical ability score and a preset ability score threshold.

[0045] In one embodiment, when the math ability score is higher than a preset first ability score threshold, the user's math ability level is determined to be excellent; when the math ability score is lower than a preset second ability score threshold, the user's math ability level is determined to be unqualified; when the math ability score is lower than or equal to the preset first ability score threshold, and higher than or equal to the preset second ability score threshold, the user's math ability level is determined to be good.

[0046] It is worth noting that the first ability score threshold is set to 1.5, and the second ability score threshold is set to 0.5. For user 1, the math ability score is 1.2083, which is between 0.5 and 1.5, and is judged as good; for user 2, the math ability score is 0.5935, which is between 0.5 and 1.5, and is judged as good; for user 3, the math ability score is 1.6602, which is higher than 1.5, and is judged as excellent. For user 4, the math ability score is 0.2984, which is lower than 0.5, and is judged as unqualified.

[0047] It is worth noting that this data mining-based evaluation method for the effectiveness of children's mathematical thinking training is mainly suitable for child users, especially those who learn and practice on the mathematical thinking training platform. Specifically, preschool children aged 3 to 6 are in the early stages of mathematical thinking development and need to develop basic mathematical concepts and problem-solving skills through simple and intuitive mathematical activities. Primary school students aged 6 to 12 gradually mature in mathematical thinking and are able to understand and solve more complex mathematical problems, requiring systematic mathematical training and evaluation. Junior high school students aged 12 to 15 have further improved mathematical thinking ability and are able to handle abstract mathematical concepts and complex problems, requiring higher-level mathematical training and evaluation. Furthermore, for children in special education, there are learning disabilities or special needs, and personalized mathematical training and evaluation methods are required.

[0048] In one embodiment, after the effect of children's thinking training is graded and evaluated according to the mathematical ability score combined with the preset ability score threshold, it also includes: when the user's mathematical ability level is determined to be unqualified, a reminder message is sent to the user, and the difficulty of mathematical thinking training is reduced and the training time is extended. The user is clearly informed that the current mathematical ability level is unqualified, and the user is advised to strengthen mathematical thinking training, provide specific improvement directions and suggestions, and encourage and support the user at the same time, emphasizing that mathematical ability can be improved through hard work. In order to help users understand and master mathematical knowledge more easily, the difficulty of mathematical thinking training can be appropriately reduced, including: decomposing complex questions into simpler sub-questions, gradually guiding users to understand; adding more prompts and auxiliary information to the questions to help users find problem-solving ideas; providing more problem-solving examples and explanations to help users understand problem-solving methods. In order to ensure that users have enough time to practice and consolidate, the training time can be appropriately extended, including: increasing the number of practice questions per day to ensure that users have sufficient practice opportunities; extending the cycle of each training module to ensure that users have enough time to master each knowledge point; regularly arranging review plans to help users consolidate the knowledge they have learned.

[0049] It is worth noting that the present invention is based on a children's education intelligent platform and belongs to the data output link. The output end data is analyzed by this method to achieve the evaluation of the platform effect. The children's education intelligent platform is a comprehensive system integrating multiple technologies, aiming to improve the efficiency and quality of children's education. The data input link of the platform accurately captures the user's scanning behavior through the user intention recognition technology of the scanning pen, reduces misoperation, and obtains accurate input data. The data processing link includes a children's education content intelligent recommendation system based on knowledge graph, which analyzes children's learning data and preferences and recommends personalized education content for children; and a platform interactive interface adaptive adjustment system based on image recognition, which identifies the environment and equipment when children interact with the platform, automatically adjusts the interactive interface, and improves the user experience. In addition, there is an intelligent education platform interaction system based on children's voice behavior analysis, which understands children's language habits and expressions and provides a natural and friendly interactive experience. The data output link analyzes children's learning performance and progress through a children's mathematical thinking training effect evaluation system based on data mining, evaluates the effect of the education platform, and helps educators and parents adjust education strategies in a timely manner. Overall, the platform covers the entire process from data input to processing to output, providing children with a personalized, interactive and measurable educational environment.

[0050] In summary, the present invention discloses a method and system for evaluating the effect of children's mathematical thinking training based on data mining, aiming to improve the accuracy of children's mathematical thinking training effect evaluation. The method includes the following main steps: first, obtaining the interaction quantity data, interaction time data and user age of users on the mathematical thinking training platform. The interaction quantity data includes the total number of questions attempted by users on the platform, the number of user interactions, the interaction results and the interaction difficulty, etc. The interaction time data records the time for users to complete each question and the average time for all users to complete the question. The user age information is used for subsequent age level classification. Secondly, mathematical thinking analysis is performed based on the interaction quantity data to calculate the mathematical thinking level. Specifically, by calculating the average number of interactions, the correct rate and the difficulty adaptability, and combining the corresponding weights, the mathematical thinking level is obtained using the mathematical thinking level formula. Among them, the average number of interactions refers to the average number of interactions of users on each question, the correct rate refers to the proportion of users' correct answers in all questions, and the difficulty adaptability refers to the performance of users on questions of different difficulty levels, and the weights correspond to the importance of these three indicators. Then, the learning effect analysis is performed based on the interaction time data to calculate the learning effect coefficient. The specific calculation method is to first calculate the exercise score of each question through the exercise score formula, where the completion status refers to whether the user has completed the question, the difficulty coefficient refers to the difficulty of the question, the user completion time refers to the time it takes the user to complete the question, and the average completion time of all users refers to the average time it takes all users to complete the question. Then, the learning effect coefficient is calculated through the learning effect coefficient formula, where the total number of questions refers to the number of questions completed by the user. Subsequently, the user is graded according to the age and the preset age level threshold to obtain the user age level.

[0051] Specifically, when the user's age is lower than the preset first age threshold, the user's age level is divided into the infant level; when the user's age is higher than the first age threshold and lower than the preset second age threshold, the user's age level is divided into the primary level; and so on, it can also be divided into intermediate and advanced levels. Next, the mathematical ability analysis is performed according to the mathematical thinking level, the learning effect coefficient and the user's age level, and the mathematical ability score is calculated. The specific calculation method is to first digitize the user's age level to obtain the normalized age level, and then calculate the mathematical ability score through the mathematical ability score formula. Among them, the learning effect coefficient reflects the user's overall performance on all questions, the mathematical thinking level reflects the user's mathematical thinking ability, and the mathematical thinking level power of the natural constant amplifies the influence of the mathematical thinking level. Finally, the effect of children's thinking training is graded and evaluated according to the mathematical ability score combined with the preset ability score threshold. When the mathematical ability score is higher than the preset first ability score, the user's mathematical ability level is judged to be excellent; when the mathematical ability score is lower than the preset second ability score, the user's mathematical ability level is judged to be unqualified. In addition, when a user's math ability level is judged to be unqualified, the system will send a reminder message to the user and take measures to reduce the difficulty of math thinking training and increase the training time to help the user improve his math ability.

[0052] The present invention obtains the mathematical thinking level of children by analyzing the number of interactive questions, learning behavior data and problem-solving result data of children on the mathematical thinking training platform, combined with the average level of all users of the same age group, so as to not only understand the level of children's mathematical thinking ability, but also more comprehensively and accurately evaluate children's mathematical thinking ability. By analyzing the interactive data of children in the learning process, their thinking mode and strategy can be understood more specifically, and their difficulties in certain types of questions can be found, so as to improve the scientific nature of the evaluation results. At the same time, by analyzing the completion time, learning behavior data and problem-solving result data of children's interactive questions on the mathematical thinking training platform, combined with the average level of all users of the same age group, the learning effect coefficient is calculated, which can not only reflect the learning efficiency and quality of children, but also more comprehensively and accurately evaluate the learning effect of children. By deeply analyzing the time investment and interactive data of children in the learning process, their learning habits and efficiency can be understood more specifically, and the obstacles existing in specific types of questions can be identified, so that the evaluation algorithm can be more scientific.

[0053] In addition, by analyzing children's mathematical thinking level, learning effect coefficient and user age level, a comprehensive mathematical ability analysis is conducted by combining these multi-dimensional data, and finally the mathematical ability score is calculated. Taking into account that different age groups have different requirements for mathematical thinking level and learning effect, this method can not only comprehensively reflect the current level of children's mathematical ability, but also conduct personalized assessments based on the characteristics of different age groups. By integrating algorithms that integrate mathematical thinking, learning efficiency and age development characteristics, children's mathematical ability can be more accurately assessed, improving the reliability and effectiveness of the assessment. By carefully analyzing children's performance in the learning process, including problem-solving speed, accuracy and comparison with their peers, we can understand their mathematical strengths and weaknesses more specifically, which helps to improve the accuracy of the evaluation of children's mathematical thinking training effects.

[0054] Reference Figure 2 The second embodiment of the present invention provides a children's mathematical thinking training effect evaluation system based on data mining, including: A data acquisition module is used to obtain the user's interaction quantity data, interaction time data and user age on the mathematical thinking training platform; A thinking level module, used for performing mathematical thinking analysis according to the interactive quantity data to obtain a mathematical thinking level; A learning effect module, used to analyze the learning effect according to the interaction time data and calculate the learning effect coefficient; An age rating module, used to perform classification according to the user's age and a preset age rating threshold to obtain the user's age rating; A mathematics ability module, used to perform mathematics ability analysis according to the mathematics thinking level, the learning effect coefficient and the user age level to obtain a mathematics ability score; The grading assessment module is used to perform a grading assessment on the effect of children's thinking training according to the mathematical ability score combined with a preset ability score threshold.

[0055] Preferably, the data acquisition module is used to: Obtain the user's interaction quantity data, interaction time data and user age on the mathematical thinking training platform.

[0056] Preferably, the thinking level module is used to: Mathematical thinking analysis is performed based on the interaction quantity data to obtain the mathematical thinking level, including: The interaction quantity data includes the total number of interaction questions, the number of user interactions, the interaction results and the interaction difficulty; Calculate the average number of interactions based on the total number of interactive topics and the number of user interactions; Calculating the correctness rate according to the total number of interactive questions and the interactive results; Calculating difficulty adaptability according to the interaction difficulty and the interaction result; The mathematical thinking level is calculated by the following formula: ; in, For the level of mathematical thinking, are the first weight, the second weight and the third weight respectively, is the average number of interactions, For the accuracy, It is the difficulty adaptation.

[0057] Preferably, the learning effect module is used to: The learning effect analysis is performed according to the interaction time data to calculate the learning effect coefficient, including: The exercise score is calculated using the following formula: ; The learning effect coefficient is calculated by the following formula: ; in, is the score of the i-th question, is the completion status of question i, is the difficulty coefficient of the i-th question, The time it takes for the user to complete question i, is the average time for all users to complete the i-th question, i is the question number, is the learning effect coefficient, The total number of questions.

[0058] Preferably, the age rating module is used to: The user age level is obtained by performing classification according to the user age and a preset age level threshold, including: When the user's age is lower than a preset first age threshold, classifying the user's age level as a toddler level; When the user age is higher than the first age threshold and the user age is lower than a preset second age threshold, the user age level is classified as primary; The user age level includes: infant level, elementary level, intermediate level or advanced level.

[0059] Preferably, the mathematical ability module is used to: Performing a mathematical ability analysis according to the mathematical thinking level, the learning effect coefficient and the user age level to obtain a mathematical ability score includes: digitizing the user's age level to obtain a normalized age level; The math ability score is calculated using the following formula: ; in, is the math ability score, is the normalized age level, is the learning effect coefficient, For the level of mathematical thinking, It is the Mth power of the natural constant.

[0060] Preferably, the grading assessment module is used to: The effect of children's thinking training is graded and evaluated according to the mathematical ability score and the preset ability score threshold, including: When the math ability score is higher than a preset first ability score threshold, determining that the user's math ability level is excellent; When the math ability score is lower than a preset second ability score threshold, it is determined that the user's math ability level is unqualified.

[0061] Preferably, after the evaluation of the children's thinking training effect is graded according to the math ability score combined with a preset ability score threshold, the method further includes: When the user's math ability level is determined to be unqualified, a reminder message is sent to the user, and the difficulty of math thinking training is reduced and the training time is extended.

[0062] It should be noted that a children's mathematical thinking training effect evaluation system based on data mining provided in an embodiment of the present invention is used to execute all the process steps of a children's mathematical thinking training effect evaluation method based on data mining in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0063] The embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, the steps in the above-mentioned embodiments of the method for evaluating the effect of children's mathematical thinking training based on data mining are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the data acquisition module.

[0064] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0065] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0066] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0067] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0068] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0069] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0070] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for evaluating the effect of children's mathematical thinking training based on data mining, characterized in that: include: Obtain the user's interaction quantity data, interaction time data and user age on the mathematical thinking training platform; Performing mathematical thinking analysis based on the interaction quantity data to obtain a mathematical thinking level; Performing a learning effect analysis based on the interaction time data and calculating a learning effect coefficient; Performing classification according to the user's age and a preset age level threshold to obtain the user's age level; Performing a mathematical ability analysis according to the mathematical thinking level, the learning effect coefficient and the user's age level to obtain a mathematical ability score; The effect of children's thinking training is graded and evaluated based on the mathematical ability score combined with a preset ability score threshold.

2. The method for evaluating the effect of children's mathematical thinking training based on data mining according to claim 1 is characterized in that: The mathematical thinking analysis is performed according to the interactive quantity data to obtain the mathematical thinking level, including: The interaction quantity data includes the total number of interaction questions, the number of user interactions, the interaction results and the interaction difficulty; Calculate the average number of interactions based on the total number of interactive topics and the number of user interactions; Calculating the correctness rate according to the total number of interactive questions and the interactive results; Calculating difficulty adaptability according to the interaction difficulty and the interaction result; The mathematical thinking level is calculated by the following formula: ； in, For the level of mathematical thinking, are the first weight, the second weight and the third weight respectively, is the average number of interactions, For the accuracy, It is the difficulty adaptation.

3. The method for evaluating the effect of children's mathematical thinking training based on data mining according to claim 1 is characterized in that: The performing of learning effect analysis based on the interaction time data and calculating the learning effect coefficient includes: The exercise score is calculated using the following formula: ； The learning effect coefficient is calculated by the following formula: ； in, is the score of the i-th question, is the completion status of question i, is the difficulty coefficient of the i-th question, The time it takes for the user to complete question i, is the average time for all users to complete the i-th question, i is the question number, is the learning effect coefficient, The total number of questions.

4. The method for evaluating the effect of children's mathematical thinking training based on data mining according to claim 1 is characterized in that: The step of performing classification according to the user age and a preset age level threshold to obtain the user age level includes: When the user's age is lower than a preset first age threshold, classifying the user's age level as a toddler level; When the user age is higher than the first age threshold and the user age is lower than a preset second age threshold, the user age level is classified as primary; The user age level includes: infant level, elementary level, intermediate level or advanced level.

5. The method for evaluating the effect of children's mathematical thinking training based on data mining according to claim 1 is characterized in that: The mathematical ability analysis is performed according to the mathematical thinking level, the learning effect coefficient and the user age level to obtain a mathematical ability score, including: digitizing the user's age level to obtain a normalized age level; The math ability score is calculated using the following formula: ； in, is the math ability score, is the normalized age level, is the learning effect coefficient, For the level of mathematical thinking, It is the Mth power of the natural constant.

6. The method for evaluating the effect of children's mathematical thinking training based on data mining according to claim 1 is characterized in that: The step of performing a graded evaluation on the effect of children's thinking training according to the mathematical ability score combined with a preset ability score threshold comprises: When the math ability score is higher than a preset first ability score threshold, determining that the user's math ability level is excellent; When the math ability score is lower than a preset second ability score threshold, determining that the user's math ability level is unqualified; When the math ability score is lower than or equal to a preset first ability score threshold and higher than or equal to a preset second ability score threshold, it is determined that the user's math ability level is good.

7. The method for evaluating the effect of children's mathematical thinking training based on data mining according to claim 1 is characterized in that: After the method of performing a graded evaluation on the effect of the children's thinking training according to the mathematical ability score combined with the preset ability score threshold, the method further includes: When the user's math ability level is determined to be unqualified, a reminder message is sent to the user, and the difficulty of math thinking training is reduced and the training time is extended.

8. The method for evaluating the effect of children's mathematical thinking training based on data mining according to claim 1 is characterized in that: The acquisition of the user's interaction quantity data and interaction time data on the mathematical thinking training platform includes: Monitor whether the scanning pen is pressed. When the scanning pen is pressed, analyze the user's intention based on the movement characteristics of the scanning pen to obtain the user's true intention; According to the real intention of the user, the user is matched from the platform content library to obtain the historical user learning behavior; The historical user learning behavior is uploaded to a cloud server, and the historical user learning behavior is obtained through the cloud server; wherein the historical user learning behavior includes the user's interaction quantity data and interaction time data.

9. A children's mathematical thinking training effect evaluation system based on data mining, characterized in that: include: A data acquisition module is used to obtain the user's interaction quantity data, interaction time data and user age on the mathematical thinking training platform; A thinking level module, used for performing mathematical thinking analysis according to the interactive quantity data to obtain a mathematical thinking level; A learning effect module, used to analyze the learning effect according to the interaction time data and calculate the learning effect coefficient; An age rating module, used to perform classification according to the user's age and a preset age rating threshold to obtain the user's age rating; A mathematics ability module, used to perform mathematics ability analysis according to the mathematics thinking level, the learning effect coefficient and the user age level to obtain a mathematics ability score; The grading assessment module is used to perform a grading assessment on the effect of children's thinking training according to the mathematical ability score combined with a preset ability score threshold.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for evaluating the effect of children's mathematical thinking training based on data mining as described in any one of claims 1 to 8.

Images