Intelligent management method for interactive data of point reading pen

Abstract

The present invention relates to the technical field of data management, and in particular to a method for intelligent management of interactive data of a point reading pen, the method comprising: obtaining interactive data generated by a target user based on a point reading pen, and obtaining the point reading time information corresponding to each interactive data; determining the number of initial learning times and the number of review and consolidation times corresponding to each interactive data; screening out the target interactive data, and clustering all the target interactive data according to the subject to obtain the target subject data cluster; determining the learning difficulty index, error correction prompt index and learning status index of the target user under the subject represented by each target subject data cluster; generating the learning plan of the target user under the subject represented by all target subject data clusters according to the learning status index of the target user under the subject represented by all target subject data clusters. The present invention realizes the generation of a learning plan based on interactive data, and improves the rationality of the generation of the learning plan.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a method for intelligent management of interactive data of a reading pen. Background Art

[0002] Since the reading pen can read whatever is pointed at, users can learn through the reading pen. For example, students can learn knowledge of various subjects through the reading pen, and judge their own learning situation through the learning process and make their own learning plan. However, when students judge their own learning situation through their own learning process, they are often affected by subjective factors, which leads to inaccurate judgment of their own learning situation, and thus the rationality of generating learning plans is poor.

[0003] At present, there is also a common method of making a study plan: the teacher makes a study plan for the whole class. However, although the study plan made by the teacher for the whole class takes most students into consideration, it is often difficult to take into account the learning characteristics of each student. Therefore, the made study plan may not be suitable for each student, resulting in the rationality of the study plan made for each student being relatively poor. Summary of the invention

[0004] In order to solve the technical problem of poor rationality in generating a learning plan, the present invention proposes an intelligent management method for interactive data of a reading pen.

[0005] The present invention provides a method for intelligent management of interactive data of a point reading pen, the method comprising:

[0006] Obtain the interaction data generated by the target user based on the reading pen, and obtain the reading time information corresponding to each interaction data;

[0007] According to the reading time information corresponding to each interactive data, determine the initial learning times and review and consolidation times corresponding to each interactive data;

[0008] According to the number of review and consolidation times corresponding to the interaction data, the target interaction data is screened out from all the interaction data, and all the target interaction data are clustered according to the subject to obtain the target subject data cluster;

[0009] Determine the learning difficulty index of the target user under the subject represented by each target subject data cluster according to the initial learning times corresponding to all target interaction data in each target subject data cluster and the knowledge points included in all target interaction data in each target subject data cluster;

[0010] According to the initial learning times and review and consolidation times corresponding to all target interaction data in each target subject data cluster, determining the error correction prompt index of the target user under the subject represented by each target subject data cluster;

[0011] Determine the target user's learning status indicator under each target subject data cluster according to the target user's learning difficulty indicator and error correction prompt indicator under each target subject data cluster;

[0012] A learning plan for the target user in the subjects represented by all target subject data clusters is generated according to the learning status indicators of the target user in the subjects represented by all target subject data clusters.

[0013] Optionally, determining the initial learning times and review consolidation times corresponding to each interactive data according to the point reading time information corresponding to each interactive data includes:

[0014] Clustering each reading time included in the reading time information corresponding to each interactive data to obtain a time clustering cluster set corresponding to each interactive data;

[0015] The time cluster with the earliest average click-and-read time is selected from the time cluster set corresponding to each interaction data as the target time cluster, and the time clusters other than the target time cluster in the time cluster set are determined as reference time clusters;

[0016] The number of click-and-read times in the target time cluster in the time clustering cluster set corresponding to each interaction data is determined as the initial learning times corresponding to each interaction data;

[0017] The total number of click-and-read times in all reference time clusters in the time clustering cluster set corresponding to each interaction data is determined as the number of review and consolidation times corresponding to each interaction data.

[0018] Optionally, the step of selecting target interaction data from all interaction data according to the number of review and consolidation times corresponding to the interaction data includes:

[0019] The interaction data whose review and consolidation times are not 0 are determined as target interaction data.

[0020] Optionally, determining the learning difficulty index of the target user under the subject represented by each target subject data cluster according to the initial learning times corresponding to all target interaction data in each target subject data cluster and the knowledge points included in all target interaction data in each target subject data cluster includes:

[0021] Determine the knowledge association index corresponding to each target interaction data according to the knowledge points included in each target interaction data;

[0022] According to the knowledge association index and the initial learning times corresponding to all the target interaction data in each target subject data cluster, the learning difficulty index of the target user under the subject represented by each target subject data cluster is determined.

[0023] Optionally, determining the learning difficulty index of the target user under the subject represented by each target subject data cluster according to the knowledge association index and the initial learning times corresponding to all target interaction data in each target subject data cluster includes:

[0024] According to the mean of the knowledge association index corresponding to all the target interaction data in each target subject data cluster and the mean of the initial learning times corresponding to all the target interaction data in each target subject data cluster, the learning difficulty index of the target user in the subject represented by each target subject data cluster is determined.

[0025] Optionally, the formula corresponding to the learning difficulty index of the target user under the subject represented by the target subject data cluster is:

[0026]

[0027] Among them, T a is the learning difficulty index of the target user in the subject represented by the ath target subject data cluster; a is the sequence number of the target subject data cluster; FZ a is the mean value of the knowledge association index corresponding to all target interaction data in the a-th target subject data cluster; FZ a,max is the maximum value of the knowledge association index corresponding to all target interaction data in the a-th target subject data cluster; d a is the mean of the initial learning times corresponding to all target interaction data in the a-th target subject data cluster; n a is the number of target interaction data in the a-th target subject data cluster; b is the sequence number of the target interaction data in the a-th target subject data cluster; FZ ab is the knowledge association index corresponding to the bth target interaction data in the ath target subject data cluster; n ab is the number of knowledge points included in the bth target interaction data in the ath target subject data cluster; i and j are the serial numbers of the knowledge points included in the bth target interaction data in the ath target subject data cluster; abij is the degree of association between the i-th knowledge point and the j-th knowledge point included in the b-th target interaction data in the a-th target subject data cluster; ab is the overall correlation degree between all knowledge points included in the bth target interaction data in the ath target subject data cluster; N abij is the number of target interaction data including the first knowledge information in the ath target subject data cluster; the first knowledge information includes: the i-th knowledge point and the j-th knowledge point included in the b-th target interaction data; N abiis the number of target interaction data including the first knowledge point in the a-th target subject data cluster, where the first knowledge point is the i-th knowledge point included in the b-th target interaction data; N abj is the number of target interaction data including the second knowledge point in the a-th target subject data cluster, and the second knowledge point is the j-th knowledge point included in the b-th target interaction data; N ab is the number of target interaction data including the second knowledge information in the ath target subject data cluster; the second knowledge information includes: all knowledge points included in the bth target interaction data.

[0028] Optionally, determining the error correction prompt indicator of the target user under the subject represented by each target subject data cluster according to the initial learning times and review consolidation times corresponding to all target interaction data in each target subject data cluster includes:

[0029] According to the number of knowledge points included in each target interaction data and the number of review and consolidation times corresponding to each target interaction data, determine the target difficulty feature corresponding to each target interaction data;

[0030] According to the initial learning times and target difficulty characteristics corresponding to all target interaction data in each target subject data cluster, the error correction prompt index of the target user under the subject represented by each target subject data cluster is determined.

[0031] Optionally, the formula corresponding to the error correction prompt indicator of the target user under the subject represented by the target subject data cluster is:

[0032]

[0033]

[0034] F a,b =ln(1+B ab )×exp(G ab ×t ab ), where Q a is the error correction indicator for the target user in the subject represented by the ath target subject data cluster; a is the sequence number of the target subject data cluster; d a is the mean of the initial learning times corresponding to all target interaction data in the ath target subject data cluster; d is the cumulative value of the mean of the initial learning times corresponding to all target interaction data in all target subject data clusters; F a is the difficulty level of the target user in the subject represented by the ath target subject data cluster; N is the number of target subject data clusters; max() is the maximum value function; b is the sequence number of the target interaction data in the ath target subject data cluster; n a is the number of target interaction data in the a-th target subject data cluster; F a,1is the target difficulty feature corresponding to the first target interaction data in the ath target subject data cluster; F a,2 is the target difficulty feature corresponding to the second target interaction data in the ath target subject data cluster; F a,b is the target difficulty feature corresponding to the bth target interaction data in the ath target subject data cluster; F a,na is the nth in the ath target subject data cluster a The target difficulty feature corresponding to the target interaction data; d a,1 is the initial learning number corresponding to the first target interaction data in the ath target subject data cluster; d a,2 is the initial learning number corresponding to the second target interaction data in the ath target subject data cluster; d a,b is the initial learning number corresponding to the bth target interaction data in the ath target subject data cluster; d a,na is the nth in the ath target subject data cluster a The initial learning times corresponding to the target interaction data; ln(1+B ab ) is based on the natural constant 1+B ab The logarithm of B ab is the number of knowledge points included in the bth target interaction data in the ath target subject data cluster; exp() is an exponential function with a natural constant as the base; G ab is the number of review and consolidation times corresponding to the bth target interaction data in the ath target subject data cluster; t ab It is the reading duration corresponding to the bth target interaction data in the ath target subject data cluster.

[0035] Optionally, the formula corresponding to the target user's learning status indicator under the subject represented by the target subject data cluster is:

[0036] Among them, S a is the learning status indicator of the target user in the subject represented by the ath target subject data cluster; a is the serial number of the target subject data cluster; norm() is the normalization function; exp() is the exponential function with natural constant as the base; T a is the learning difficulty index of the target user in the subject represented by the ath target subject data cluster; Q a is the error correction prompt indicator of the target user in the subject represented by the ath target subject data cluster; γ is a pre-set factor greater than 0.

[0037] Optionally, generating a learning plan for the target user in the subjects represented by all target subject data clusters according to the learning status indicators of the target user in the subjects represented by all target subject data clusters includes:

[0038] According to the target user's learning status indicator under the subject represented by each target subject data cluster, determine the proportion of the target user's time to be studied under the subject represented by each target subject data cluster, wherein the learning status indicator is negatively correlated with the proportion of the time to be studied;

[0039] Determine the target learning time of the target user in the subject represented by each target subject data cluster according to the pre-acquired scheduled learning time and the proportion of the target user's learning time in the subject represented by each target subject data cluster;

[0040] A learning plan for the target user in the subjects represented by all target subject data clusters is generated according to the target learning duration of the target user in the subjects represented by all target subject data clusters.

[0041] The present invention has the following beneficial effects:

[0042] The intelligent management method of interactive data of a point-reading pen of the present invention realizes the generation of a learning plan based on interactive data, solves the technical problem of poor rationality of learning plan generation, and improves the rationality of learning plan generation. First, the interactive data generated by the target user based on the point-reading pen and the point-reading time information corresponding to each interactive data are obtained, which can facilitate the subsequent analysis of the learning situation of the target user. Then, the more initial learning times and review consolidation times corresponding to the quantified interactive data, the more times the interactive data needs to be learned and consolidated for the target user, and the more difficult the interactive data is for the target user. Then, the filtered target interactive data is clustered according to the subject, which can facilitate the subsequent analysis of the learning situation of the target user in each subject, and facilitate the subsequent fine formulation of the learning plan. Continuing, the larger the learning difficulty index of the quantified target user under the subject represented by the target subject data cluster, the more difficult the subject represented by the target subject data cluster is for the target user, and the more time the target user needs to spend learning the subject represented by the target subject data cluster. Afterwards, the larger the error correction prompt index of the quantified target user under the subject represented by the target subject data cluster, the more the target user needs error correction prompts when learning the subject represented by the target subject data cluster, and the more time the target user needs to spend learning the subject represented by the target subject data cluster. Therefore, based on the target user's learning difficulty index and error correction prompt index under the subject represented by the target subject data cluster, the quantified target user's learning status index under the subject represented by the target subject data cluster can represent the target user's learning situation for the subject represented by the target subject data cluster. Finally, based on the target user's learning status index under the subject represented by all target subject data clusters, the target user's learning plan under the subject represented by all target subject data clusters is generated, and the formulation of the target user's learning plan is realized. Compared with the formulation of the learning plan by artificial methods, the present invention quantifies multiple indicators related to the target user's learning situation, such as the learning difficulty index, the error correction prompt index and the learning status index, so as to more objectively generate the target user's learning plan under the subject represented by all target subject data clusters, thereby improving the rationality of the generation of the learning plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 The present invention is a flowchart of a method for intelligent management of interactive data of a point reading pen. DETAILED DESCRIPTION

[0045] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0046] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0047] refer to Figure 1 , shows the process of some embodiments of a method for intelligently managing interactive data of a point reading pen according to the present invention. The method for intelligently managing interactive data of a point reading pen comprises the following steps:

[0048] Step S1, obtaining the interaction data generated by the target user based on the reading pen, and obtaining the reading time information corresponding to each interaction data.

[0049] Among them, the target user may be a student who is to carry out study planning. The point reading pen is an intelligent reading and learning tool developed using optical image recognition technology and digital voice technology. The point reading pen can simultaneously realize many functions such as point reading, rereading, following reading, recording, and entertainment. The point reading method of the point reading pen is generally: using barcodes, RFID and other methods to recognize text, placing identification tags under Chinese characters in advance or placing invisible or visible identification codes next to Chinese characters, that is, preset identifiers. Different characters correspond to different preset identifiers. During the point reading process of the point reading pen, the user points the point reading pen to which preset identifier, and the point reading pen will recognize the preset identifier, and then decode, decode and convert the audio by calling the internal pre-stored data, restore the sound and finally realize the point reading. The content that the target user points to each time through the point reading pen can constitute an interactive data. The interactive data can be but not limited to: sentences, paragraphs or problem analysis. The point reading time information corresponding to the interactive data can include: the time when the target user points to the interactive data each time through the point reading pen. The time when the target user clicks on the interactive data through the reading pen each time can be used as a reading time.

[0050] It should be noted that obtaining the interaction data generated by the target user based on the reading pen and the reading time information corresponding to each interaction data can facilitate the subsequent analysis of the target user's learning situation.

[0051] As an example, the content that the target user points to each time with the reading pen can be collected as interaction data, and the time when the target user points to the interaction data each time with the reading pen can be recorded as the reading time of the interaction data, and all the reading times of the interaction data constitute the reading time information corresponding to the interaction data.

[0052] It should be noted that, in order to make the data more authentic and effective, the acquired interaction data may be preprocessed, and the interaction data after the data preprocessing may be used as the interaction data for subsequent analysis. The data preprocessing may include: data noise removal and data cleaning.

[0053] Step S2, determining the initial learning times and review and consolidation times corresponding to each interaction data according to the reading time information corresponding to each interaction data.

[0054] It should be noted that, the more initial learning times and review and consolidation times corresponding to the quantified interaction data, the more times the target user needs to learn and consolidate the interaction data, which often means that the interaction data is relatively more difficult for the target user.

[0055] As an example, this step may include the following steps:

[0056] In the first step, each reading time included in the reading time information corresponding to each interaction data is clustered to obtain a time clustering cluster set corresponding to each interaction data.

[0057] For example, in the click-and-read time information corresponding to the interaction data, the click-and-read times with a time interval of less than 20 minutes may be grouped into the same cluster as a time cluster, thereby obtaining a time cluster set corresponding to the interaction data.

[0058] In the second step, the time cluster with the earliest average click-to-read time is selected from the time cluster set corresponding to each interaction data as the target time cluster, and the time clusters in the time cluster set except the target time cluster are determined as reference time clusters.

[0059] It should be noted that when students first learn a new content, they can listen and read it multiple times through the reading pen. After a period of time, if they encounter questions about the content again and find that they have forgotten the content, they can read the content multiple times through the reading pen to review the content. The multiple reading times in the target time cluster often represent the time when the target user listens and reads the content multiple times through the reading pen when learning a new content. The reading times in the reference time cluster often represent the time when the content is reviewed through the reading pen.

[0060] In the third step, the number of click-through times in the target time cluster in the time clustering cluster set corresponding to each interaction data is determined as the initial learning times corresponding to each interaction data.

[0061] It should be noted that the initial learning times corresponding to the interaction data may indicate the learning times required for the target user to learn the interaction data through the reading pen. The larger the value is, the more difficult the interaction data is for the target user.

[0062] The fourth step is to determine the total number of click-to-read times in all reference time clusters in the time clustering cluster set corresponding to each interaction data as the number of review and consolidation times corresponding to each interaction data.

[0063] It should be noted that the number of review and consolidation times corresponding to the interaction data can indicate the number of times the target user needs to learn the interaction data again after learning it through the reading pen. The larger the value, the more difficult the interaction data is for the target user.

[0064] Step S3, according to the number of review and consolidation times corresponding to the interaction data, the target interaction data are screened out from all the interaction data, and all the target interaction data are clustered according to the subject to obtain the target subject data cluster.

[0065] It should be noted that clustering the filtered target interaction data according to subjects can facilitate subsequent analysis of the target user's learning situation in each subject and facilitate subsequent detailed formulation of a learning plan.

[0066] As an example, the interaction data with a non-zero review and consolidation times can be determined as target interaction data, and the target interaction data under the same subject can be grouped into the same cluster as the target subject data cluster. For example, all target interaction data belonging to the mathematics subject can form a target subject data cluster.

[0067] It should be noted that the target interaction data can represent the content that the target user will forget and needs to learn again.

[0068] Step S4, determining the learning difficulty index of the target user under the subject represented by each target subject data cluster according to the initial learning times corresponding to all target interaction data in each target subject data cluster and the knowledge points included in all target interaction data in each target subject data cluster.

[0069] It should be noted that the greater the learning difficulty index of the quantitative target user in the subject represented by the target subject data cluster, the more difficult the subject represented by the target subject data cluster is for the target user, and the more time the target user needs to spend learning the subject represented by the target subject data cluster.

[0070] As an example, this step may include the following steps:

[0071] The first step is to determine the knowledge association index corresponding to each target interaction data according to the knowledge points included in each target interaction data.

[0072] The second step is to determine the learning difficulty index of the target user in the subject represented by each target subject data cluster according to the knowledge association index and the initial learning times corresponding to all target interaction data in each target subject data cluster.

[0073] For example, the learning difficulty index of the target user in the subject represented by each target subject data cluster can be determined based on the mean of the knowledge association index corresponding to all target interaction data in each target subject data cluster and the mean of the initial learning times corresponding to all target interaction data in each target subject data cluster.

[0074] For example, the formula for determining the learning difficulty index of the target user in the subject represented by the target subject data cluster can be:

[0075]

[0076] Among them, T a is the learning difficulty index of the target user in the subject represented by the ath target subject data cluster. a is the sequence number of the target subject data cluster. FZ a is the mean value of the knowledge association index corresponding to all target interaction data in the a-th target subject data cluster. a,max It is the maximum value of the knowledge association index corresponding to all target interaction data in the a-th target subject data cluster. a is the mean of the initial learning times corresponding to all target interaction data in the a-th target subject data cluster. a is the number of target interaction data in the a-th target subject data cluster. b is the sequence number of the target interaction data in the a-th target subject data cluster. ab is the knowledge association index corresponding to the bth target interaction data in the ath target subject data cluster. ab is the number of knowledge points included in the bth target interaction data in the ath target subject data cluster. i and j are the serial numbers of the knowledge points included in the bth target interaction data in the ath target subject data cluster. abij is the degree of association between the i-th knowledge point and the j-th knowledge point included in the b-th target interaction data in the a-th target subject data cluster. ab It is the overall correlation degree between all knowledge points included in the bth target interaction data in the ath target subject data cluster. abij is the number of target interaction data including the first knowledge information in the ath target subject data cluster; the first knowledge information includes: the i-th knowledge point and the j-th knowledge point included in the b-th target interaction data. Nabi is the number of target interaction data including the first knowledge point in the a-th target subject data cluster, where the first knowledge point is the i-th knowledge point included in the b-th target interaction data. abj is the number of target interaction data including the second knowledge point in the ath target subject data cluster, and the second knowledge point is the jth knowledge point included in the bth target interaction data. N ab is the number of target interaction data including the second knowledge information in the ath target subject data cluster; the second knowledge information includes: all knowledge points included in the bth target interaction data.

[0077] It should be noted that when con abij When the value is larger, it often indicates that the probability of the i-th knowledge point and the j-th knowledge point appearing at the same time is relatively higher, and it often indicates that the degree of association and confusion between the i-th knowledge point and the j-th knowledge point included in the b-th target interaction data is greater. ab When the value is larger, it often indicates that the probability that different knowledge points appear at the same time in the bth target interaction data is relatively high, and it often indicates that the degree of association and confusion between all knowledge points included in the bth target interaction data is greater. Generally speaking, if the degree of association and confusion between different knowledge points in a subject is large, students often need to integrate different knowledge points when learning the subject, which often places higher demands on students and is often more difficult for students. ab When FZ is larger, it often means that the degree of association and confusion between different knowledge points included in the bth target interaction data is relatively larger, which often means that the bth target interaction data has higher requirements for the target user, and often means that the bth target interaction data is more difficult for the target user. a When d is larger, it often means that more target interaction data in the a-th target subject data cluster is more difficult for the target user, and it often means that the subject represented by the a-th target subject data cluster is more difficult for the target user. a When T is larger, it often means that the target interaction data in the a-th target subject data cluster has more initial learning times, which often means that the target user needs to spend more time learning new content in the subject represented by the a-th target subject data cluster, which often means that the subject represented by the a-th target subject data cluster is more difficult for the target user. a The larger it is, the more difficult the subject represented by the a-th target subject data cluster is for the target user.

[0078] Optionally, determine the learning difficulty index T of the target user in the subject represented by the ath target subject data cluster a The corresponding formula can also be:

[0079] T a =FZ a ×da .

[0080] Optionally, determine the knowledge association index FZ corresponding to the bth target interaction data in the ath target subject data cluster ab The corresponding formula can also be:

[0081]

[0082] Step S5, determining the error correction prompt index of the target user in the subject represented by each target subject data cluster according to the initial learning times and review consolidation times corresponding to all target interaction data in each target subject data cluster.

[0083] It should be noted that the larger the error correction prompt index of the quantitative target user in the subject represented by the target subject data cluster, the more the target user needs error correction prompts when learning the subject represented by the target subject data cluster, and the more time the target user needs to spend learning the subject represented by the target subject data cluster.

[0084] As an example, this step may include the following steps:

[0085] The first step is to determine the target difficulty characteristics corresponding to each target interaction data based on the number of knowledge points included in each target interaction data and the number of review and consolidation times corresponding to each target interaction data.

[0086] In the second step, according to the initial learning times and target difficulty characteristics corresponding to all target interaction data in each target subject data cluster, the error correction prompt indicators of the above target users in the subject represented by each target subject data cluster are determined.

[0087] For example, the formula corresponding to the error correction prompt indicator for the target user under the subject represented by the target subject data cluster may be:

[0088]

[0089]

[0090] F a,b =ln(1+B ab )×exp(G ab ×t ab ), where Q a is the error correction indicator of the target user in the subject represented by the ath target subject data cluster. a is the serial number of the target subject data cluster. d a is the mean of the initial learning times of all target interaction data in the ath target subject data cluster. d is the cumulative value of the mean of the initial learning times of all target interaction data in all target subject data clusters. ais the difficulty level of the target user in the subject represented by the a-th target subject data cluster. N is the number of target subject data clusters. max() is the maximum value function. b is the sequence number of the target interaction data in the a-th target subject data cluster. n a is the number of target interaction data in the ath target subject data cluster. a,1 is the target difficulty feature corresponding to the first target interaction data in the ath target subject data cluster. a,2 is the target difficulty feature corresponding to the second target interaction data in the ath target subject data cluster. a,b It is the target difficulty feature corresponding to the bth target interaction data in the ath target subject data cluster. is the nth in the ath target subject data cluster a The target difficulty feature corresponding to the target interaction data. a,1 is the initial learning number corresponding to the first target interaction data in the ath target subject data cluster. a,2 is the initial learning number corresponding to the second target interaction data in the ath target subject data cluster. a,b is the initial learning number corresponding to the bth target interaction data in the ath target subject data cluster. is the nth in the ath target subject data cluster a The initial learning times corresponding to the target interaction data. ln(1+B ab ) is based on the natural constant 1+B ab The logarithm of B ab is the number of knowledge points included in the bth target interaction data in the ath target subject data cluster. exp() is an exponential function with a natural constant as the base. G ab is the number of review and consolidation times corresponding to the bth target interaction data in the ath target subject data cluster; t ab It is the reading time corresponding to the bth target interaction data in the ath target subject data cluster. The reading time corresponding to the target interaction data is the reading time when the reading pen points to the target interaction data.

[0091] It should be noted that when d a When the value is larger, it often means that the target interaction data in the a-th target subject data cluster has more initial learning times, which often means that the target user needs to spend more time learning new content in the subject represented by the a-th target subject data cluster, which often means that the subject represented by the a-th target subject data cluster is more difficult for the target user. When B is larger, it often means that the subject represented by the a-th target subject data cluster is relatively more difficult for the target user. abWhen G is larger, it often means that the bth target interaction data in the ath target subject data cluster includes more knowledge points, which often means that the bth target interaction data needs to learn more content, which often means that the difficulty of learning the bth target interaction data is relatively greater, which often means that the target user is more likely to make mistakes when using the bth target interaction data, and which often means that the target user is more likely to need error correction prompts when using the bth target interaction data. ab When t is larger, it often means that the number of review and consolidation corresponding to the bth target interaction data in the ath target subject data cluster is greater, which often means that the target user needs to review the bth target interaction data more times, which often means that the target user is more likely to make mistakes when using the bth target interaction data, which often means that the target user is more likely to need error correction prompts when using the bth target interaction data. ab When F is larger, the reading time corresponding to the bth target interaction data in the ath target subject data cluster is longer, which often indicates that the bth target interaction data contains more content, which often indicates that the difficulty of learning the bth target interaction data is relatively greater, which often indicates that the target user is more likely to make mistakes when using the bth target interaction data, and which often indicates that the target user is more likely to need error correction prompts when using the bth target interaction data. Therefore, when F a,b The larger the value, the more likely it is that the target user needs error correction prompts when using the bth target interaction data. a,b When F is larger, it often means that the initial learning times corresponding to the bth target interaction data in the ath target subject data cluster are more, which often means that the target user needs to spend more learning times to learn the bth target interaction data, which often means that the bth target interaction data is more difficult for the target user. a When Q is larger, it often means that the subject represented by the a-th target subject data cluster is more difficult for the target user, and it often means that the target user is more likely to need error correction prompts when learning the subject represented by the a-th target subject data cluster. a The larger it is, the more likely it is that the target user will need error correction prompts when learning the subject represented by the a-th target subject data cluster. It often means that the target user has a poorer grasp of the subject represented by the a-th target subject data cluster, and it often means that the target user needs to put more effort in learning the subject represented by the a-th target subject data cluster.

[0092] Step S6, determining the target user's learning status indicator under each target subject data cluster according to the target user's learning difficulty indicator and error correction prompt indicator under the subject represented by each target subject data cluster.

[0093] It should be noted that, based on the target user's learning difficulty index and error correction prompt index in the subject represented by the target subject data cluster, the quantified target user's learning status index in the subject represented by the target subject data cluster can represent the target user's learning status in the subject represented by the target subject data cluster.

[0094] As an example, the formula corresponding to the target user's learning status indicator under the subject represented by the target subject data cluster may be:

[0095] Among them, S a is the target user's learning status indicator in the subject represented by the ath target subject data cluster. a is the serial number of the target subject data cluster. norm() is the normalization function. exp() is the exponential function with a natural constant as the base. T a It is the learning difficulty index of the target user in the subject represented by the ath target subject data cluster. a It is the error correction indicator of the target user in the subject represented by the ath target subject data cluster. γ is a pre-set factor greater than 0, mainly used to prevent the denominator from being, for example, γ can be 0.001.

[0096] It should be noted that when T a When Q is larger, it often means that the subject represented by the a-th target subject data cluster is more difficult for the target user. a When S is larger, it often indicates that the target user is more likely to need error correction prompts when learning the subject represented by the a-th target subject data cluster, and it often indicates that the target user has a poorer grasp of the subject represented by the a-th target subject data cluster. a When it is larger, it often indicates that the target user has a better grasp of the subject represented by the a-th target subject data cluster, and the target user's learning ability for the subject represented by the a-th target subject data cluster is relatively stronger. It often indicates that the target user's learning status for the subject represented by the a-th target subject data cluster is relatively better.

[0097] Step S7, generating a learning plan for the target user in the subjects represented by all target subject data clusters according to the target user's learning status indicators in the subjects represented by all target subject data clusters.

[0098] It should be noted that, based on the target user's learning status indicators in the subjects represented by all target subject data clusters, a learning plan for the target user in the subjects represented by all target subject data clusters is generated, thereby realizing the formulation of the target user's learning plan.

[0099] As an example, this step may include the following steps:

[0100] The first step is to determine the proportion of the target user's learning time under each target subject data cluster according to the target user's learning status indicators under the subject represented by each target subject data cluster.

[0101] Among them, the learning status index can be negatively correlated with the proportion of time to be learned.

[0102] For example, the formula for determining the proportion of the target user's time to be learned under the subject represented by the target subject data cluster may be:

[0103] H a =1-S a ; Among them, h a is the proportion of the target user's learning time in the subject represented by the ath target subject data cluster. a is the sequence number of the target subject data cluster. a is the time feature to be learned corresponding to the a-th target subject data cluster. H is the cumulative value of the time feature to be learned corresponding to all target subject data clusters. S a It is the learning status indicator of the target user in the subject represented by the ath target subject data cluster.

[0104] It should be noted that when S a The larger the H is, the better the target user's learning of the subject represented by the a-th target subject data cluster is. a When h is larger, it often indicates that the target user's learning status of the subject represented by the a-th target subject data cluster is relatively poor, and it often indicates that the target user needs to spend more time learning the subject represented by the a-th target subject data cluster. a The larger it is, the more time the target users need to spend learning the subject represented by the ath target subject data cluster.

[0105] The second step is to determine the target learning time of the target user in each subject represented by the target subject data cluster according to the pre-acquired scheduled learning time and the proportion of the target user's learning time in the subject represented by each target subject data cluster.

[0106] The time to be arranged for learning may be the time to be arranged for learning, for example, the time to be arranged for learning may be the free time of the target user, or the time to be arranged for learning may be the learning time that the target user can freely control.

[0107] For example, the product of the above-mentioned scheduled learning time and the proportion of the target user's learning time under the subject represented by each target subject data cluster can be determined as the target learning time of the target user under the subject represented by each target subject data cluster.

[0108] The third step is to generate a learning plan for the target user in the subjects represented by all target subject data clusters according to the target learning duration of the target user in the subjects represented by all target subject data clusters.

[0109] For example, the target learning time of the target user in the subject represented by each target subject data cluster can be used as the target user's learning time in the subject represented by each target subject data cluster; the target user's learning time in the subject represented by all target subject data clusters constitutes the target user's learning plan in the subject represented by all target subject data clusters.

[0110] For example, if the target user is studying mathematics, Chinese and English, and the scheduled study time is 2 hours, the target study time for mathematics, Chinese and English are 1 hour, 30 minutes and 30 minutes respectively, then the target user's study plan for mathematics, Chinese and English can be "Study mathematics for 1 hour, study Chinese for 30 minutes, and study English for 30 minutes within the scheduled study time".

[0111] In summary, compared with formulating learning plans through manual methods, the present invention quantifies multiple indicators related to the target user's learning situation, such as learning difficulty indicators, error correction prompt indicators and learning status indicators, thereby more objectively generating a learning plan for the target user in all subjects represented by the target subject data clusters, thereby improving the rationality of the generation of the learning plan.

[0112] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for intelligent management of interactive data of a point reading pen, characterized in that: The following steps are involved: Obtain the interaction data generated by the target user based on the reading pen, and obtain the reading time information corresponding to each interaction data; According to the reading time information corresponding to each interactive data, determine the initial learning times and review and consolidation times corresponding to each interactive data; According to the number of review and consolidation times corresponding to the interaction data, the target interaction data is screened out from all the interaction data, and all the target interaction data are clustered according to the subject to obtain the target subject data cluster; Determine the learning difficulty index of the target user under the subject represented by each target subject data cluster according to the initial learning times corresponding to all target interaction data in each target subject data cluster and the knowledge points included in all target interaction data in each target subject data cluster; According to the initial learning times and review and consolidation times corresponding to all target interaction data in each target subject data cluster, determining the error correction prompt index of the target user under the subject represented by each target subject data cluster; Determine the target user's learning status indicator under each target subject data cluster according to the target user's learning difficulty indicator and error correction prompt indicator under each target subject data cluster; Generate a learning plan for the target user in the subjects represented by all target subject data clusters according to the target user's learning status indicators in the subjects represented by all target subject data clusters; Determining the error correction prompt indicator of the target user under the subject represented by each target subject data cluster according to the initial learning times and review consolidation times corresponding to all target interaction data in each target subject data cluster includes: According to the number of knowledge points included in each target interaction data and the number of review and consolidation times corresponding to each target interaction data, determine the target difficulty feature corresponding to each target interaction data; Determine the error correction prompt indicator for the target user in the subject represented by each target subject data cluster according to the initial learning times and target difficulty characteristics corresponding to all target interaction data in each target subject data cluster; The formula corresponding to the error correction prompt indicator of the target user in the subject represented by the target subject data cluster is: F a,b =ln(1+B ab )×exp(G ab ×t ab ), where Q a is the error correction indicator for the target user in the subject represented by the ath target subject data cluster; a is the sequence number of the target subject data cluster; d a is the mean of the initial learning times corresponding to all target interaction data in the ath target subject data cluster; d is the cumulative value of the mean of the initial learning times corresponding to all target interaction data in all target subject data clusters; F a is the difficulty level of the target user in the subject represented by the ath target subject data cluster; N is the number of target subject data clusters; max() is the maximum value function; b is the sequence number of the target interaction data in the ath target subject data cluster; n a is the number of target interaction data in the a-th target subject data cluster; F a,1 is the target difficulty feature corresponding to the first target interaction data in the ath target subject data cluster; F a,2 is the target difficulty feature corresponding to the second target interaction data in the ath target subject data cluster; F a,b is the target difficulty feature corresponding to the bth target interaction data in the ath target subject data cluster; F a,na is the nth in the ath target subject data cluster a The target difficulty feature corresponding to the target interaction data; d a,1 is the initial learning number corresponding to the first target interaction data in the ath target subject data cluster; d a,2 is the initial learning number corresponding to the second target interaction data in the ath target subject data cluster; d a,b is the initial learning number corresponding to the bth target interaction data in the ath target subject data cluster; d a,na is the nth in the ath target subject data cluster a The initial learning times corresponding to the target interaction data; ln(1+B ab ) is based on the natural constant 1+B ab The logarithm of B ab is the number of knowledge points included in the bth target interaction data in the ath target subject data cluster; exp() is an exponential function with a natural constant as the base; G ab is the number of review and consolidation times corresponding to the bth target interaction data in the ath target subject data cluster; t ab It is the reading duration corresponding to the bth target interaction data in the ath target subject data cluster.

2. According to claim 1, a method for intelligent management of interactive data of a point reading pen is characterized in that: Determining the initial learning times and review consolidation times corresponding to each interactive data according to the point reading time information corresponding to each interactive data includes: Clustering each reading time included in the reading time information corresponding to each interactive data to obtain a time clustering cluster set corresponding to each interactive data; The time cluster with the earliest average click-and-read time is selected from the time cluster set corresponding to each interaction data as the target time cluster, and the time clusters other than the target time cluster in the time cluster set are determined as reference time clusters; The number of click-and-read times in the target time cluster in the time clustering cluster set corresponding to each interaction data is determined as the initial learning times corresponding to each interaction data; The total number of click-and-read times in all reference time clusters in the time clustering cluster set corresponding to each interaction data is determined as the number of review and consolidation times corresponding to each interaction data.

3. The method for intelligent management of interactive data of a point reading pen according to claim 1, characterized in that: The method of screening out target interaction data from all interaction data according to the number of review and consolidation times corresponding to the interaction data includes: The interaction data whose review and consolidation times are not 0 are determined as target interaction data.

4. The method for intelligent management of interactive data of a point reading pen according to claim 1, characterized in that: The determining of the learning difficulty index of the target user under the subject represented by each target subject data cluster according to the initial learning times corresponding to all target interaction data in each target subject data cluster and the knowledge points included in all target interaction data in each target subject data cluster includes: Determine the knowledge association index corresponding to each target interaction data according to the knowledge points included in each target interaction data; According to the knowledge association index and the initial learning times corresponding to all the target interaction data in each target subject data cluster, the learning difficulty index of the target user under the subject represented by each target subject data cluster is determined.

5. The method for intelligent management of interactive data of a point reading pen according to claim 4, characterized in that: Determining the learning difficulty index of the target user under the subject represented by each target subject data cluster according to the knowledge association index and the initial learning times corresponding to all target interaction data in each target subject data cluster includes: According to the mean of the knowledge association index corresponding to all the target interaction data in each target subject data cluster and the mean of the initial learning times corresponding to all the target interaction data in each target subject data cluster, the learning difficulty index of the target user in the subject represented by each target subject data cluster is determined.

6. The method for intelligent management of interactive data of a point reading pen according to claim 5, characterized in that: The formula corresponding to the target user's learning difficulty index in the subject represented by the target subject data cluster is: Among them, T a is the learning difficulty index of the target user in the subject represented by the ath target subject data cluster; a is the sequence number of the target subject data cluster; FZ a is the mean value of the knowledge association index corresponding to all target interaction data in the a-th target subject data cluster; FZ a,max is the maximum value of the knowledge association index corresponding to all target interaction data in the a-th target subject data cluster; d a is the mean of the initial learning times corresponding to all target interaction data in the a-th target subject data cluster; n a is the number of target interaction data in the a-th target subject data cluster; b is the sequence number of the target interaction data in the a-th target subject data cluster; FZ ab is the knowledge association index corresponding to the bth target interaction data in the ath target subject data cluster; n ab is the number of knowledge points included in the bth target interaction data in the ath target subject data cluster; i and j are the serial numbers of the knowledge points included in the bth target interaction data in the ath target subject data cluster; abij is the degree of association between the i-th knowledge point and the j-th knowledge point included in the b-th target interaction data in the a-th target subject data cluster; ab is the overall correlation degree between all knowledge points included in the bth target interaction data in the ath target subject data cluster; N abij is the number of target interaction data including the first knowledge information in the ath target subject data cluster; the first knowledge information includes: the i-th knowledge point and the j-th knowledge point included in the b-th target interaction data; N abi is the number of target interaction data including the first knowledge point in the a-th target subject data cluster, where the first knowledge point is the i-th knowledge point included in the b-th target interaction data; N abj is the number of target interaction data including the second knowledge point in the a-th target subject data cluster, and the second knowledge point is the j-th knowledge point included in the b-th target interaction data; N ab is the number of target interaction data including the second knowledge information in the ath target subject data cluster; the second knowledge information includes: all knowledge points included in the bth target interaction data.

7. The method for intelligent management of interactive data of a point reading pen according to claim 1, characterized in that: The formula corresponding to the target user's learning status indicator in the subject represented by the target subject data cluster is: Among them, S a is the learning status indicator of the target user in the subject represented by the ath target subject data cluster; a is the serial number of the target subject data cluster; norm() is the normalization function; exp() is the exponential function with natural constant as the base; T a is the learning difficulty index of the target user in the subject represented by the ath target subject data cluster; Q a is the error correction prompt indicator of the target user in the subject represented by the ath target subject data cluster; γ is a pre-set factor greater than 0.

8. The method for intelligent management of interactive data of a point reading pen according to claim 1, characterized in that: The step of generating a learning plan for the target user under the subjects represented by all target subject data clusters according to the learning status indicators of the target user under the subjects represented by all target subject data clusters comprises: According to the target user's learning status indicator under the subject represented by each target subject data cluster, determine the proportion of the target user's time to be studied under the subject represented by each target subject data cluster, wherein the learning status indicator is negatively correlated with the proportion of the time to be studied; Determine the target learning time of the target user in the subject represented by each target subject data cluster according to the pre-acquired scheduled learning time and the proportion of the target user's learning time in the subject represented by each target subject data cluster; A learning plan for the target user in the subjects represented by all target subject data clusters is generated according to the target learning duration of the target user in the subjects represented by all target subject data clusters.

Images