CN115766853B - University student learning behavior analysis method based on big data - Google Patents
University student learning behavior analysis method based on big data Download PDFInfo
- Publication number
- CN115766853B CN115766853B CN202211431402.8A CN202211431402A CN115766853B CN 115766853 B CN115766853 B CN 115766853B CN 202211431402 A CN202211431402 A CN 202211431402A CN 115766853 B CN115766853 B CN 115766853B
- Authority
- CN
- China
- Prior art keywords
- learning
- data
- information
- students
- college
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000006399 behavior Effects 0.000 title claims abstract description 37
- 238000004458 analytical method Methods 0.000 title claims abstract description 30
- 239000000463 material Substances 0.000 claims abstract description 120
- 238000000034 method Methods 0.000 claims description 59
- 230000008569 process Effects 0.000 claims description 46
- 238000012216 screening Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 19
- 230000009471 action Effects 0.000 claims description 11
- 238000004806 packaging method and process Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 230000003340 mental effect Effects 0.000 claims 1
- 238000011156 evaluation Methods 0.000 description 10
- 230000009286 beneficial effect Effects 0.000 description 9
- 238000013467 fragmentation Methods 0.000 description 4
- 238000006062 fragmentation reaction Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 241001122315 Polites Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides a university student learning behavior analysis method based on big data, which is used for analyzing student behaviors in a lesson period and a non-lesson period, comprehensively determining the actual watching and browsing states of the university students on different knowledge contents, determining the interested degree of the university students on the different knowledge contents, conveniently searching proper learning document materials from a preset learning resource database, directionally pushing the learning document materials to the university students at proper time through a learning terminal machine, conveniently improving the initiative and the efficiency of learning the knowledge contents of the students, and pushing proper learning materials for the students at proper time according to the learning characteristics of the different students, and improving the reliability of learning by using fragmented time.
Description
Technical Field
The invention relates to the technical field of big data analysis and processing, in particular to a method for analyzing learning behaviors of college students based on big data.
Background
In the learning process of students, the learning behavior actions and character preferences of the students directly influence the learning interest of the students on different knowledge contents. The prior teaching mode is based on a fixed teaching flow to teach the students corresponding knowledge content, and although the mode can systematically teach the knowledge content to the students, the method can not individually push the proper knowledge content to the students according to the corresponding learning interests of the students in the learning process, can not improve the initiative and efficiency of learning the knowledge content of the students, and can not push the proper learning materials to the students at proper time according to the learning characteristics of different students, thereby reducing the reliability of learning by using fragmented time.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides a university student learning behavior analysis method based on the university data, which analyzes the lesson process images of the university students to obtain corresponding lesson behavior information so as to determine the watching state information of the knowledge content displayed on a classroom screen by the university students in the lesson process; analyzing the data browsing record of the learning terminal held by the college student in the non-lesson time period, so as to determine the browsing state information of the centering knowledge content of the college student in the process of using the learning terminal; according to the viewing state information and the browsing state information of the knowledge content, the interested knowledge content of the college students is determined, so that matched learning document materials are screened from a preset learning resource database, and the learning document materials are directionally pushed to a learning terminal; according to the method, the behaviors of the students are analyzed in the lesson period and the non-lesson period, the actual watching and browsing states of the college students on different knowledge contents are comprehensively determined, the interested degree of the college students on the different knowledge contents is determined, the college students can conveniently find out proper learning document materials from the preset learning resource database, the learning document materials are directionally pushed to the college students through the learning terminal at proper time, the initiative and the efficiency of learning the knowledge contents of the students are conveniently improved, the proper learning materials can be pushed to the students at proper time according to the learning characteristics of the different students, and the reliability of learning by utilizing the fragmentation time is improved.
The invention provides a university student learning behavior analysis method based on big data, which comprises the following steps:
step S1, shooting a lesson process of a college student to obtain a corresponding lesson process image, analyzing and processing the lesson process image, and extracting lesson behavior information of the college student; according to the lesson behavior information, determining viewing state information of knowledge content displayed on a classroom screen by college students in the lesson process;
step S2, acquiring data browsing records of a learning terminal held by the college student in a non-lesson time period, analyzing and processing the data browsing records, and determining browsing state information of middle knowledge content of the college student in the process of using the learning terminal;
step S3, determining interested knowledge content of college students according to the viewing state information of the knowledge content and the browsing state information of the knowledge content; screening matched learning document materials from a preset learning resource database according to the interesting knowledge content;
step S4, acquiring the working state of the learning terminal machine, and judging whether the learning terminal machine is in a proper material pushing state currently according to the working state; and if yes, directionally pushing the screened learning document materials to the learning terminal.
Further, in the step S1, shooting the course of the college student to obtain a corresponding course image, analyzing and processing the course image, and extracting the course behavior information of the college student specifically includes:
carrying out panoramic scanning shooting on the course of the university students to obtain panoramic images of the course of the university students; performing face recognition processing on the panoramic image in the course of lessons, so as to extract a picture part of the course of lessons corresponding to the college students from the panoramic image in the course of lessons; then the picture part of the lesson process is identified, the gazing action information of the college students on the classroom screen in the lesson process is determined and used as the lesson action information,
further, in the step S1, determining, according to the lesson-taking behavior information, viewing state information of knowledge content displayed on a classroom screen by a college student in a lesson-taking process specifically includes:
according to the gazing action information, gazing line-of-sight direction change state information of college students in the course is obtained; according to the gazing line-of-sight direction change state information, determining time period distribution information of the college students in a classroom screen gazing state in the course of lessons;
and comparing the time period distribution information of the college students in the watching state of the classroom screen in the course of teaching with the display time sequence information of different knowledge contents on the classroom screen, so as to determine the respective watching duration information of the college students on the different knowledge contents displayed on the classroom screen, and using the information as the watching state information of the knowledge contents displayed on the classroom screen.
Further, in the step S2, a data browsing record of the learning terminal held by the college student in a non-lesson time period is obtained, the data browsing record is analyzed and processed, and the determining of browsing status information of the college student on the knowledge content in the process of using the learning terminal specifically includes:
and acquiring data browsing records of the learning terminal held by the college student on a specific application program in a non-lesson time period, performing text semantic recognition processing on the data browsing records, and determining browsing frequency information of different knowledge contents of the college student in the process of using the learning terminal, wherein the browsing frequency information is used as the browsing state information.
Further, in the step S2, the method further includes:
obtaining answer result data of a test question set of seven personality grid segments of college students on a learning terminal; wherein the seven personality segments include a thinking feature, a mood matter, a personality preference, a learning interest, a behavioral tendency, a team role, and a planning awareness;
judging, analyzing and processing the answer result data to obtain character feature preference analysis results of college students; determining learning interest information of college students according to the character feature preference analysis result; the learning interest information comprises subject preference information and answer type preference information of college students.
Further, in the step S3, determining knowledge content of interest of the college student according to the viewing state information of the knowledge content and the browsing state information of the knowledge content specifically includes:
screening to obtain knowledge contents corresponding to the watching duration time greater than or equal to a preset time threshold according to the watching duration time information of the college students on the different knowledge contents displayed on the classroom screen;
according to the browsing frequency information of each of different knowledge contents in the process of using the learning terminal by college students, screening to obtain knowledge contents corresponding to the browsing frequency greater than or equal to a preset frequency threshold;
and taking the knowledge content obtained by screening as the interested knowledge content of the college students.
Further, in the step S3, screening matched learning document materials from a preset learning resource database according to the knowledge content of interest specifically includes:
extracting corresponding knowledge content keywords from the interested knowledge content, taking the knowledge content keywords as retrieval index information, and screening from a preset learning resource database to obtain matched learning document materials;
secondly screening the screened learning document materials according to the subject preference information and the answer type preference information, so as to obtain screened learning document materials matched with the learning interest information; and compressing and packaging the screened learning document materials, so as to form corresponding document material packages.
Further, in the step S3, the screened learning document material is compressed and packaged, so as to form a corresponding document material package, and then the display application program of the learning terminal is instructed to decompress the document material package, where the process is as follows:
step S301, using the following formula (1), obtaining data division point position values and symbol data according to the screening learning document material data,
（1）；
in the above-mentioned formula (1),representing symbol data; />Representing data segmentation point location values; />A 16-ary form representing the screened learned document material data; />Representation data->A 16-ary value on the first bit of (2);all represent converting the values in brackets into a 10-ary form; />Representation data->1 st to->A 16-ary data segment on a bit; />Representation data->Is>Bit to->A 16-ary data segment on a bit; />Representation data->Is a total number of bits of (2);
step S302, compressing and packaging the screened learning document material according to the data segmentation points and the symbol data by using the following formula (2),
（2）；
in the above-mentioned formula (2),a 16-system form of compressed data after compressing and packaging the screened learning document material is represented; />Representing end-to-end concatenation of comma-separated 16-ary numbers in brackets to form new 16-ary data; />The absolute value is calculated by representation; />Representing the conversion of the values in brackets into a 16-ary form;
step S303, decompressing the document material package by using the following formula (3),
（3）；
in the above-mentioned formula (3),a 16-system form representing decompressed data after the document material package is decompressed; />A 16-ary form representing the document material package; />Representation data->A 16-ary value on bit 1 of (2); />Representation data->A 16-ary value on bit 2 of (2); />Representing data2 nd to->A 16-ary data segment on a bit; />Representing dataIs>Bit to->A 16-ary data segment on a bit; />Representation data->Is a total number of bits of (2); />Representing that left and right 16 system numbers separated by commas in brackets are connected end to form new 16 system data; />All represent intermediate data; />The values in brackets are converted to a 10-ary form.
Further, in the step S4, a working state of the learning terminal is obtained, and whether the learning terminal is in a proper material pushing state or not is judged according to the working state; if yes, directionally pushing the screened learning document materials to the learning terminal machine specifically comprises the following steps:
judging whether a specific application program of the learning terminal is in a foreground running state or not; if yes, judging that the current learning terminal is not in a material pushing proper state, and if not, judging that the current learning terminal is in the material pushing proper state.
And if the learning terminal is in a proper material pushing state, the document material package is directionally pushed to a material display application program of the learning terminal, and the document material package is decompressed and dynamically displayed through the material display application program.
Compared with the prior art, the university student learning behavior analysis method based on the big data analyzes the lesson process images of the university students to obtain corresponding lesson behavior information, so that the viewing state information of the knowledge content displayed on the classroom screen by the university students in the lesson process is determined; analyzing the data browsing record of the learning terminal held by the college student in the non-lesson time period, so as to determine the browsing state information of the centering knowledge content of the college student in the process of using the learning terminal; according to the viewing state information and the browsing state information of the knowledge content, the interested knowledge content of the college students is determined, so that matched learning document materials are screened from a preset learning resource database, and the learning document materials are directionally pushed to a learning terminal; according to the method, the behaviors of the students are analyzed in the lesson period and the non-lesson period, the actual watching and browsing states of the college students on different knowledge contents are comprehensively determined, the interested degree of the college students on the different knowledge contents is determined, the college students can conveniently find out proper learning document materials from the preset learning resource database, the learning document materials are directionally pushed to the college students through the learning terminal at proper time, the initiative and the efficiency of learning the knowledge contents of the students are conveniently improved, the proper learning materials can be pushed to the students at proper time according to the learning characteristics of the different students, and the reliability of learning by utilizing the fragmentation time is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a university student learning behavior analysis method based on big data.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flow chart of a university student learning behavior analysis method based on big data according to an embodiment of the present invention is shown. The university student learning behavior analysis method based on big data comprises the following steps:
step S1, shooting a lesson process of a college student to obtain a corresponding lesson process image, analyzing and processing the lesson process image, and extracting lesson behavior information of the college student; according to the lesson behavior information, determining viewing state information of knowledge content displayed on a classroom screen by college students in the lesson process;
step S2, acquiring data browsing records of a learning terminal held by the college student in a non-lesson time period, analyzing and processing the data browsing records, and determining browsing state information of the middle knowledge content of the college student in the process of using the learning terminal;
step S3, according to the viewing state information of the knowledge content and the browsing state information of the knowledge content, the interested knowledge content of the college student is determined; screening matched learning document materials from a preset learning resource database according to the interesting knowledge content;
step S4, acquiring the working state of the learning terminal machine, and judging whether the learning terminal machine is in a proper material pushing state or not according to the working state; if yes, the screened learning document materials are directionally pushed to the learning terminal.
The beneficial effects of the technical scheme are as follows: the university student learning behavior analysis method based on the big data analyzes the lesson process images of the university students to obtain corresponding lesson behavior information, so as to determine the watching state information of the university students on the knowledge content displayed on the classroom screen in the lesson process; analyzing the data browsing record of the learning terminal held by the college student in the non-lesson time period, so as to determine the browsing state information of the centering knowledge content of the college student in the process of using the learning terminal; according to the viewing state information and the browsing state information of the knowledge content, the interested knowledge content of the college students is determined, so that matched learning document materials are screened from a preset learning resource database, and the learning document materials are directionally pushed to a learning terminal; according to the method, the behaviors of the students are analyzed in the lesson period and the non-lesson period, the actual watching and browsing states of the college students on different knowledge contents are comprehensively determined, the interested degree of the college students on the different knowledge contents is determined, the college students can conveniently find out proper learning document materials from the preset learning resource database, the learning document materials are directionally pushed to the college students through the learning terminal at proper time, the initiative and the efficiency of learning the knowledge contents of the students are conveniently improved, the proper learning materials can be pushed to the students at proper time according to the learning characteristics of the different students, and the reliability of learning by utilizing the fragmentation time is improved.
Preferably, in the step S1, the course of the college student is photographed, so as to obtain a corresponding course image, and the course image is analyzed and processed, so that the course behavior information of the college student is extracted specifically including:
carrying out panoramic scanning shooting on the course of the university students to obtain panoramic images of the course of the university students; performing face recognition processing on the panoramic image in the course of lessons, so as to extract a picture part of the course of lessons corresponding to the college student from the panoramic image in the course of lessons; and then, carrying out recognition processing on the picture part in the course of the lesson, and determining the gazing action information of the college students on the classroom screen in the course of the lesson, so as to serve as the lesson action information.
The beneficial effects of the technical scheme are as follows: in actual work, a scanning camera can be installed in a classroom, panoramic scanning shooting is carried out on the internal environment of the classroom in the course of a college student, so that a course panoramic image is obtained, the course panoramic image comprises course images of all college students, and in order to specifically identify a specific college student, the picture part of the course corresponding to each college student can be extracted from the course panoramic image on the basis of facial features of the college student, so that the course live of each college student can be accurately extracted; and then, the watching action of the college students on the projection screen of the classroom in the course of the lesson is further identified from the picture part of the course of the lesson, so that the analysis record of the whole course of the watching state of the images displayed on the projection screen by the college students in the course of the lesson can be carried out.
Preferably, in the step S1, determining viewing state information of knowledge content displayed on a classroom screen by a college student during a lesson includes:
according to the gazing action information, obtaining gazing line-of-sight direction change state information of college students in the course of lessons; according to the gaze direction change state information, determining time period distribution information of the college students in a classroom screen gaze state in the course of lessons;
and comparing the time period distribution information of the college students in the watching state of the classroom screen in the course of teaching with the display time sequence information of different knowledge contents on the classroom screen, so as to determine the respective watching duration information of the college students on the different knowledge contents displayed on the classroom screen, and using the information as the watching state information of the knowledge contents displayed on the classroom screen.
The beneficial effects of the technical scheme are as follows: in the process of watching images displayed on the classroom projection screen, the display states of the image contents (corresponding to the knowledge contents) displayed on the classroom projection screen are different for college students, namely, in different watching time periods of the college students, the actually watched image contents are changed, and the time period distribution information of the college students in the watching state of the classroom screen in the course of lessng is compared with the display time sequence information of the different knowledge contents on the classroom screen, so that the watching duration information of the college students on the different knowledge contents displayed on the classroom screen can be determined in a refined manner, and the knowledge contents interested by the college students can be screened conveniently based on the watching duration time of the knowledge contents.
Preferably, in the step S2, a data browsing record of a learning terminal held by the college student in a non-lesson time period is obtained, the data browsing record is analyzed, and the determining of browsing status information of the college student on knowledge content in the process of using the learning terminal specifically includes:
and acquiring data browsing records of the learning terminal held by the college student on a specific application program in a non-lesson time period, performing text semantic recognition processing on the data browsing records, and determining browsing frequency information of different knowledge contents of the college student in the process of using the learning terminal, wherein the browsing frequency information is used as the browsing state information.
The beneficial effects of the technical scheme are as follows: by the method, the corresponding data browsing record of the knowledge content data of the university students through the specific application program is taken as a reference, and the respective browsing frequency of different knowledge contents of the university students in the process of using the learning terminal machine is determined, so that the knowledge content interested by the university students can be conveniently screened by taking the browsing frequency of the knowledge content as the reference.
Preferably, in this step S2, further comprising:
obtaining answer result data of a test question set of seven personality grid segments of college students on a learning terminal; wherein the seven personality segments include a thinking feature, a mood matter, a personality preference, a learning interest, a behavioral tendency, a team role, and a planning awareness;
judging, analyzing and processing the answer result data to obtain character feature preference analysis results of college students; determining learning interest information of college students according to the character feature preference analysis result; the learning interest information comprises subject preference information and answer type preference information of college students.
The beneficial effects of the technical scheme are as follows: in actual operation, the process of testing the topic set according to the seven personality segment trip may be:
the first step: based on the research method of the root taking theory, the technology of the prior psychology on character research is used for completing the research design of the evaluation items required by the construction of the evaluation system in the analysis of the invention, and the comprehensive investigation (interview is the main part, part of the questionnaire investigation is implemented) of the object to be tested, namely the student principal, the parents, the college and university instructor and the university professional class teacher is performed, and the data summarization is primarily completed;
and a second step of: taking the college students meeting the main stream value as a target, extracting character evaluation item data, deleting repeated or ambiguous items, screening and reserving effective evaluation items, classifying all the reserved items according to causal relation and logic analysis thought of the reserved items, and finally determining seven outstanding character feature fragments of reserved character features, psychological diathesis, character preference, learning interests, behavior tendency, team roles and planning consciousness;
and a third step of: setting up an A-G total 7 personality grid segment evaluation module, and designing an evaluation item library according to the seven personality grid feature segments determined in the second step. Each module is provided with three levels of indexes, and the first level of indexes correspond to the corresponding character feature segments A-G;
a-thinking feature, designing 5 secondary indexes: collective consciousness, thanksgiving and rewarding, value observation, integrity and responsibility, legal concept, 13 three-level observation points;
b, psychological diathesis, designing 4 secondary indexes: confidence, frustration, concentricity and perseverance, self-control capability, 11 three-level observation points;
c-character preference, 5 secondary indexes are designed: personality tendency, expression desire, response to other people's views, attitudes for other people's evaluation, expression mode, 12 three-level observation points in total;
d, learning interest, designing 5 secondary indexes: learning attitude, learning habit, self-learning ability, self-evaluation of the existing learning ability and innovative thinking, and 15 three-level observation points are provided; additionally setting 3 observation points of learning interests, and performing preliminary analysis on the humane, artistic and reasonable interests of the evaluation object;
e-behavior tendency, 5 secondary indexes are designed: the method comprises the steps of operating ability, behavior habit, independence, interpersonal tendencies and polite habit, wherein 15 three-level observation points are provided;
f, team role, designing 5 secondary indexes: cooperative consciousness, communication capacity, participation enthusiasm, viewpoint acceptance and personal roles, and 15 observation points are all provided;
g-planning consciousness, designing 4 secondary and tertiary indexes: planning consciousness, target self-evaluation, target acceptance, execution, and 12 observation points in total;
total test questions total 96 questions (with 3 study point of interest analyses). The evaluator evaluates according to the degree of coincidence between the described scene of each question and the viewpoint of the evaluator according to 1-7 scores, and the higher the score given by the evaluator, the more the expression situation accords with the description scene of the stem.
Then, judging, analyzing and processing the answer result data to obtain character feature preference analysis results of college students; the answer result data can be input into the corresponding character analysis model, so that character feature preference analysis results of college students can be accurately judged, and the answer result data belongs to conventional technical means in the field and are not described in detail here. Finally, determining learning interest information of the college students according to the character feature preference analysis result; the learning interest information comprises subject preference information and answer type preference information of college students; in actual work, the actual learning interest information of the college students can be determined according to a comparison relation table between the preset character characteristic preference and the learning interest information, which belongs to the conventional technical means in the field and is not described in detail here.
Preferably, in the step S3, determining knowledge content of interest of the college student based on the viewing state information of the knowledge content and the browsing state information of the knowledge content specifically includes:
screening to obtain knowledge contents corresponding to the watching duration time greater than or equal to a preset time threshold according to the watching duration time information of the college students on the different knowledge contents displayed on the classroom screen;
according to the browsing frequency information of each of different knowledge contents in the process of using the learning terminal by college students, screening to obtain knowledge contents corresponding to the browsing frequency greater than or equal to a preset frequency threshold;
and taking the knowledge content obtained by screening as the interested knowledge content of the college students.
The beneficial effects of the technical scheme are as follows: by the method, the interested knowledge content of the college students can be accurately determined from the watching state or the browsing state of the college students about different knowledge content in the lesson period and the non-lesson period.
Preferably, in the step S3, screening matched learning document materials from a preset learning resource database according to the knowledge content of interest specifically includes:
extracting corresponding knowledge content keywords from the interested knowledge content, taking the knowledge content keywords as retrieval index information, and screening from a preset learning resource database to obtain matched learning document materials;
secondly screening the screened learning document materials according to the subject preference information and the answer type preference information, so as to obtain screened learning document materials matched with the learning interest information; and compressing and packaging the screened learning document material to form a corresponding document material package.
The beneficial effects of the technical scheme are as follows: through the method, the corresponding knowledge content keywords are extracted from the interested knowledge content, the knowledge content keywords are used as the tight turns, the matched learning document materials are screened from the preset learning resource database and are used as the learning document material set to be pushed to the college students, and the secondary screening is carried out on the learning document material set by utilizing the subject preference information and the answer type preference information of the college students, so that the matching property of the learning document materials obtained through the final screening and the learning preference of the college students can be improved.
Preferably, in the step S3, after the screened learning document material is compressed and packaged to form a corresponding document material packet, the display application program of the learning terminal is further instructed to decompress the document material packet, which includes the following steps:
step S301, using the following formula (1), learning document material data according to the screening to obtain data division point position values and symbol data,
（1）；
in the above-mentioned formula (1),representing symbol data; />Representing data segmentation point location values; />A 16-ary form representing the screened learned document material data; />Representation data->A 16-ary value on the first bit of (2);all represent converting the values in brackets into a 10-ary form; />Representation data->1 st to->A 16-ary data segment on a bit; />Representation data->Is>Bit to->A 16-ary data segment on a bit; />Representation data->Is a total number of bits of (2);
step S302, compressing and packaging the screened learning document material according to the data segmentation points and the symbol data by using the following formula (2),
（2）；
in the above-mentioned formula (2),a 16-system form of compressed data after compressing and packaging the screened learning document material is represented; />Representing end-to-end concatenation of comma-separated 16-ary numbers in brackets to form new 16-ary data; />The absolute value is calculated by representation; />Representing the conversion of the values in brackets into a 16-ary form;
step S303, decompressing the document material package by using the following formula (3),
（3）；
in the above-mentioned formula (3),a 16-ary form representing decompressed data after the document material package is decompressed; />A 16-ary form representing the document material package; />Representation data->A 16-ary value on bit 1 of (2);/>representation data->A 16-ary value on bit 2 of (2); />Representation data->2 nd to->A 16-ary data segment on a bit; />Representation data->Is>Bit to->A 16-ary data segment on a bit; />Representation data->Is a total number of bits of (2); />Representing that left and right 16 system numbers separated by commas in brackets are connected end to form new 16 system data; />All represent intermediate data; />The values in brackets are converted to a 10-ary form.
The beneficial effects of the technical scheme are as follows: according to the screening learning document material data, the data segmentation point position value and the symbol data are obtained by utilizing the formula (1), so that the subsequent compression and decompression can be automatically completed by utilizing the formula, and the intellectualization of the system is embodied; then, according to the data dividing points and the symbol data, the screened learning document materials are compressed and packed by utilizing the formula (2), and packing compression time can be optimized by compressing the first numerical value, so that the system efficiency is improved; and finally, decompressing the document material package by using the formula (3) to ensure the consistency between decompressed data and original data.
Preferably, in the step S4, the working state of the learning terminal is obtained, and according to the working state, whether the learning terminal is in a proper state for pushing materials is judged; if yes, directionally pushing the screened learning document materials to the learning terminal machine specifically comprises the following steps:
judging whether a specific application program of the learning terminal is in a foreground running state or not; if yes, judging that the current learning terminal is not in a material pushing proper state, and if not, judging that the current learning terminal is in the material pushing proper state.
And if the learning terminal is in a proper material pushing state, the document material package is directionally pushed to a material display application program of the learning terminal, and the document material package is decompressed and dynamically displayed through the material display application program.
The beneficial effects of the technical scheme are as follows: through the mode, when specific application programs such as an online course application program of the learning terminal are in a foreground running state, the fact that college students are currently performing online learning by using the learning terminal is indicated, at the moment, the learning terminal cannot display the pushed document material package to the college students in real time, namely, the learning terminal is not in a proper material pushing state. And the document material package is directionally pushed to the material display application program of the learning terminal until the specific application programs such as the online course application program of the learning terminal are not in a foreground running state, so that the material display application program can timely decompress and dynamically display the document material package, thereby facilitating the university students to watch and learn the corresponding document material in real time.
According to the content of the embodiment, the university student learning behavior analysis method based on the big data analyzes the lesson process images of the university students to obtain corresponding lesson behavior information, so that the viewing state information of the knowledge content displayed on the classroom screen by the university students in the lesson process is determined; analyzing the data browsing record of the learning terminal held by the college student in the non-lesson time period, so as to determine the browsing state information of the centering knowledge content of the college student in the process of using the learning terminal; according to the viewing state information and the browsing state information of the knowledge content, the interested knowledge content of the college students is determined, so that matched learning document materials are screened from a preset learning resource database, and the learning document materials are directionally pushed to a learning terminal; according to the method, the behaviors of the students are analyzed in the lesson period and the non-lesson period, the actual watching and browsing states of the college students on different knowledge contents are comprehensively determined, the interested degree of the college students on the different knowledge contents is determined, the college students can conveniently find out proper learning document materials from the preset learning resource database, the learning document materials are directionally pushed to the college students through the learning terminal at proper time, the initiative and the efficiency of learning the knowledge contents of the students are conveniently improved, the proper learning materials can be pushed to the students at proper time according to the learning characteristics of the different students, and the reliability of learning by utilizing the fragmentation time is improved.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (4)
1. The university student learning behavior analysis method based on big data is characterized by comprising the following steps:
step S1, shooting a lesson process of a college student to obtain a corresponding lesson process image, analyzing and processing the lesson process image, and extracting lesson behavior information of the college student, wherein the step comprises the following steps:
carrying out panoramic scanning shooting on the course of the university students to obtain panoramic images of the course of the university students; performing face recognition processing on the panoramic image in the course of lessons, so as to extract a picture part of the course of lessons corresponding to the college students from the panoramic image in the course of lessons; then, the picture part in the course of the lesson is identified, and the gazing action information of the college students on the classroom screen in the course of the lesson is determined and used as the lesson action information;
according to the lesson behavior information, determining viewing state information of knowledge content displayed on a classroom screen by college students in the lesson process, including:
according to the gazing action information, gazing line-of-sight direction change state information of college students in the course is obtained; according to the gazing line-of-sight direction change state information, determining time period distribution information of the college students in a classroom screen gazing state in the course of lessons;
comparing the time period distribution information of the college students in the watching state of the classroom screen in the course of teaching with the display time sequence information of different knowledge contents on the classroom screen, so as to determine the respective watching duration information of the college students on the different knowledge contents displayed on the classroom screen, and using the information as the watching state information of the knowledge contents displayed on the classroom screen;
step S2, acquiring data browsing records of a learning terminal held by the college student in a non-lesson time period, analyzing and processing the data browsing records, and determining browsing state information of the college student on knowledge content in the process of using the learning terminal;
step S3, determining interested knowledge content of college students according to the viewing state information of the knowledge content and the browsing state information of the knowledge content;
screening matched learning document materials from a preset learning resource database according to the interesting knowledge content, wherein the method comprises the following steps:
extracting corresponding knowledge content keywords from the interested knowledge content, taking the knowledge content keywords as retrieval index information, and screening from a preset learning resource database to obtain matched learning document materials;
secondly screening the screened learning document materials according to the subject preference information and the answer type preference information, so as to obtain screened learning document materials matched with learning interest information; and compressing and packaging the screened learning document materials to form corresponding document material packages, and then instructing a material display application program of the learning terminal to decompress the document material packages, wherein the process is as follows:
step S301, using the following formula (1), obtaining data division point position values and symbol data according to the screened learning document material data,
in the above formula (1), F 16 Representing symbol data; r represents a data segmentation point position value; d (D) 16 A 16-ary form representing the screened learned document material data; d (D) 16 (1) Representing data D 16 A 16-ary value on the first bit of (2); [] 10 Representing the conversion of the values in brackets into a 10-ary form; d (D) 16 (1→R) represents data D 16 16-ary data segments on bit 1 through bit R; d (D) 16 (R+1- > n) represents data D 16 16-ary data segments on the (R+1) -th bit; n represents data D 16 Is a total number of bits of (2);
step S302, compressing and packaging the screened learning document material according to the data segmentation point position value and the symbol data by using the following formula (2),
B 16 ＝{F 16 ,D 16 (1→R),{|[D 16 (1→R)] 10 -[D 16 (R+1→n)] 10 |} 16 } (2)
in the above formula (2), B 16 A 16-system form of compressed data after the screened learning document material is compressed and packaged is represented; {, } means that 16 system numbers separated by commas in brackets are connected end to form new 16 system data; the absolute value is calculated by the expression; {} 16 Representing the conversion of the values in brackets into a 16-ary form;
step S303, decompressing the document material package by using the following formula (3),
in the above formula (3), d 16 A 16-ary form representing decompressed data after the document material package is decompressed; b 16 A 16-ary form representing the document material package; b 16 (1) Representation data b 16 A 16-ary value on bit 1 of (2); b 16 (2) Representation data b 16 A 16-ary value on bit 2 of (2); b 16 {2→[b 16 (2)+1]Data b 16 2 nd to [ b ] 16 (2)+1]A 16-ary data segment on a bit; b 16 {[b 16 (2)+2]Data b is represented by → m } 16 [ b ] of 16 (2)+2]Bits to 16 th bit data segment; m represents data b 16 Is a total number of bits of (2); {, } means that the left and right 16 system numbers separated by commas in brackets are connected end to form new 16 system data; d1 16 ，d2 16 All represent intermediate data; [] 10 ,{ } 10 All represent converting the values in brackets into a 10-ary form;
step S4, acquiring the working state of the learning terminal machine, and judging whether the learning terminal machine is in a proper material pushing state currently according to the working state; if yes, directionally pushing the screened learning document materials to the learning terminal;
in the step S2, a data browsing record of a learning terminal held by a college student in a non-class time period is obtained, the data browsing record is analyzed and processed, and the browsing status information of the college student on the knowledge content in the process of using the learning terminal is determined specifically including:
and acquiring data browsing records of the learning terminal held by the college student on a specific application program in a non-lesson time period, performing text semantic recognition processing on the data browsing records, and determining browsing frequency information of different knowledge contents of the college student in the process of using the learning terminal, wherein the browsing frequency information is used as the browsing state information.
2. The university student's learning behavior analysis method based on big data as claimed in claim 1, wherein:
in the step S2, further includes:
obtaining answer result data of a test question set of seven personality grid segments of college students on a learning terminal; wherein the seven personality compartment includes a personality trait, a mental quality, a personality preference, a learning interest, a behavioral trend, a team role, and a planning awareness;
judging, analyzing and processing the answer result data to obtain character feature preference analysis results of college students; determining learning interest information of college students according to the character feature preference analysis result; the learning interest information comprises subject preference information and answer type preference information of college students.
3. The university student's learning behavior analysis method based on big data as claimed in claim 2, wherein:
in the step S3, determining knowledge content of interest of the college student according to the viewing state information of the knowledge content and the browsing state information of the knowledge content specifically includes:
screening to obtain knowledge contents corresponding to the watching duration time greater than or equal to a preset time threshold according to the watching duration time information of the college students on the different knowledge contents displayed on the classroom screen;
according to the browsing frequency information of each of different knowledge contents in the process of using the learning terminal by college students, screening to obtain knowledge contents corresponding to the browsing frequency greater than or equal to a preset frequency threshold;
and taking the knowledge content obtained by screening as the interested knowledge content of the college students.
4. A college student learning behavior analysis method based on big data as set forth in claim 3, wherein:
in the step S4, a working state of the learning terminal is obtained, and whether the learning terminal is in a proper material pushing state or not is judged according to the working state; if yes, directionally pushing the screened learning document materials to the learning terminal machine specifically comprises the following steps:
judging whether a specific application program of the learning terminal is in a foreground running state or not; if yes, judging that the current learning terminal is not in a material pushing proper state, and if not, judging that the current learning terminal is in the material pushing proper state;
and if the learning terminal is in a proper material pushing state, the document material package is directionally pushed to a material display application program of the learning terminal, and the document material package is decompressed and dynamically displayed through the material display application program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211431402.8A CN115766853B (en) | 2022-11-14 | 2022-11-14 | University student learning behavior analysis method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211431402.8A CN115766853B (en) | 2022-11-14 | 2022-11-14 | University student learning behavior analysis method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115766853A CN115766853A (en) | 2023-03-07 |
| CN115766853B true CN115766853B (en) | 2024-04-12 |
Family
ID=85371516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211431402.8A Active CN115766853B (en) | 2022-11-14 | 2022-11-14 | University student learning behavior analysis method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115766853B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992741A (en) * | 2019-11-15 | 2020-04-10 | 深圳算子科技有限公司 | Learning auxiliary method and system based on classroom emotion and behavior analysis |
| CN112015779A (en) * | 2020-08-20 | 2020-12-01 | 上海松鼠课堂人工智能科技有限公司 | Method, system and device for predicting preference of students |
| CN112766130A (en) * | 2021-01-12 | 2021-05-07 | 深圳市小熊创新科技有限公司 | Classroom teaching quality monitoring method, system, terminal and storage medium |
| CN112949562A (en) * | 2020-06-08 | 2021-06-11 | 上海松鼠课堂人工智能科技有限公司 | Intelligent adaptive learning method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200051450A1 (en) * | 2018-08-13 | 2020-02-13 | Facil Ltd.Co. | Audio-visual teaching platform and recommendation subsystem, analysis subsystem, recommendation method, analysis method thereof |
-
2022
- 2022-11-14 CN CN202211431402.8A patent/CN115766853B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992741A (en) * | 2019-11-15 | 2020-04-10 | 深圳算子科技有限公司 | Learning auxiliary method and system based on classroom emotion and behavior analysis |
| CN112949562A (en) * | 2020-06-08 | 2021-06-11 | 上海松鼠课堂人工智能科技有限公司 | Intelligent adaptive learning method and system |
| CN112015779A (en) * | 2020-08-20 | 2020-12-01 | 上海松鼠课堂人工智能科技有限公司 | Method, system and device for predicting preference of students |
| CN112766130A (en) * | 2021-01-12 | 2021-05-07 | 深圳市小熊创新科技有限公司 | Classroom teaching quality monitoring method, system, terminal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115766853A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cavalcanti et al. | An analysis of the use of good feedback practices in online learning courses | |
| CN112287037B (en) | Multi-entity mixed knowledge graph construction method, device and storage medium | |
| CN110782375B (en) | Online learning overall process dynamic analysis method and system based on data | |
| CN114339285B (en) | Knowledge point processing method, video processing method, device and electronic equipment | |
| CN105427696A (en) | Method for distinguishing answer to target question | |
| Tuna et al. | Indexed captioned searchable videos: A learning companion for STEM coursework | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| CN112995690B (en) | Live content category identification method, device, electronic equipment and readable storage medium | |
| CN111614986A (en) | Bullet screen generation method, system, equipment and storage medium based on online education | |
| CN117150151B (en) | Wrong question analysis and test question recommendation system and method based on large language model | |
| CN106777040A (en) | A kind of across media microblogging the analysis of public opinion methods based on feeling polarities perception algorithm | |
| CN111597305B (en) | Entity marking method, entity marking device, computer equipment and storage medium | |
| Marshall | Contribution of open-ended questions in student evaluation of teaching | |
| CN113779345B (en) | Teaching material generation method and device, computer equipment and storage medium | |
| CN115766853B (en) | University student learning behavior analysis method based on big data | |
| CN117708416A (en) | Intelligent recommendation method for teaching content | |
| CN117765783A (en) | Intelligent interactive training system based on virtual reality technology | |
| CN117473078A (en) | Visual reading system of long literature based on cross-domain named entity recognition | |
| CN111415283A (en) | Factor analysis method and device for effective online teaching | |
| Zhou | Application investigation and technological development of intelligent product in college English teaching | |
| KR20200099042A (en) | Learning style prediction system and method through analysis of teaching activity data | |
| Dobashi | Time series analysis of the in class page view history of digital teaching materials using cross table | |
| CN113920802A (en) | Intelligent soil mechanics teaching system based on AR augmented reality technology | |
| CN115129971A (en) | Course recommendation method and device based on capability evaluation data and readable storage medium | |
| Ogunkunle et al. | A data mining based optimization of selecting learning material in an intelligent tutoring system for advancing STEM education |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240318 Address after: Within Chengdu General Aviation Industry New City, Jintang County, Chengdu City, Sichuan Province, 610000, it is adjacent to Wei'er Road to the north, Weisan Road to the south, Jingsi Road to the west, and Jingsan Road to the east Applicant after: Huigu Science Park Education Technology Industry Co.,Ltd. Country or region after: China Address before: 101B, Unit 1, Building 1, No. 88, Tianchen Road, Chengdu, Sichuan, 610000 Applicant before: Electronic Science Park Education Center Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |