CN115563263B - Content recommendation method based on AI - Google Patents
Content recommendation method based on AI Download PDFInfo
- Publication number
- CN115563263B CN115563263B CN202211135681.3A CN202211135681A CN115563263B CN 115563263 B CN115563263 B CN 115563263B CN 202211135681 A CN202211135681 A CN 202211135681A CN 115563263 B CN115563263 B CN 115563263B
- Authority
- CN
- China
- Prior art keywords
- information
- control unit
- central control
- student
- level
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
Abstract
The invention relates to a content recommendation method based on AI, an information acquisition unit acquires basic information of a student and extracts historical performance information of the student from a database in a school according to the basic information; the central control unit records the browsing footprint and the searching footprint of the student after the student finishes browsing or searching the information to determine the first browsing preference of the student, and simultaneously searches the average score of each single department in the history examination of the student to determine the second browsing preference of the student; the central control unit outputs corresponding information extension links to the display unit according to the first browsing preference and the second browsing preference of the learner, and the learner clicks the corresponding information extension links on the display unit to acquire content containing corresponding information; according to the invention, by recording the browsing footprint and the searching footprint of the student, and searching the total score and the ranking of the score of each subject, the student is effectively ensured to obtain accurate information, and the learning efficiency is further improved.
Description
Technical Field
The invention relates to the technical field of communication, in particular to an AI-based content recommendation method.
Background
Content recommendation, i.e. "web broadcasting", is a new technology for reducing information overload by periodically transmitting information required by a user over the internet through a certain technical standard or protocol. Push technology reduces the time for searching on a network by automatically delivering information to the user. It regularly recommends content to users, helping users to efficiently discover valuable information.
Chinese patent publication No.: CN111191111a discloses a content recommendation method, device and storage medium, the content recommendation method firstly needs to obtain industry information of industries to which users of a first terminal belong, then searches corpus corresponding to the industry information from a corpus to form a target corpus set, secondly obtains a first keyword sent by the first terminal, searches corpus in the target corpus set according to the first keyword, and finally constructs first recommendation content based on the corpus searched from the target corpus set, so as to send the first recommendation content to the first terminal. The method and the device can provide information for the user accurately in a targeted manner, avoid providing useless contents for the user, avoid difficult information acquisition of the user caused by excessive information, and improve user experience.
Therefore, the technical scheme cannot customize and adjust the pushing information according to the actual achievement of the student and the information browsing preference, so that the problem of low information content pushing efficiency for the student is solved.
Disclosure of Invention
Therefore, the invention provides an AI-based content recommendation method for overcoming the problem of low information content pushing efficiency in the prior art.
To achieve the above object, the present invention provides an AI-based content recommendation method, comprising:
step S1, an information acquisition unit acquires basic information of a student and extracts historical performance information of the student from a database in a school according to the basic information; the historical performance information comprises an average annual ranking of the total performance of the student in the past exam and an average annual ranking of the performance of each single department;
step s2, the cloud platform selects corresponding information according to browsing data of information in big data and keyword searching quantity in a database in descending order and pushes the selected information to a first-time logged-in student;
step s3, the central control unit records the browsing footprint and the searching footprint of the student after the student finishes browsing or searching the information to determine the first browsing preference of the student, and simultaneously determines the second browsing preference of the student according to the average annual group ranking of the total score and the average annual group ranking of the single-department score in the history examination of the student, and the central control unit ranks the student according to the average annual group ranking of the total score of the student and corrects the information pushing quantity aiming at the student according to the ranking result; the central control unit adjusts the information duty ratio of the corresponding first level in the information of the student aiming at the student according to the average annual ranking of the single-department achievements of the student;
Step s4, the central control unit adjusts the ratio of the single label to the total number of the same-level labels in the historical browsing information, the number of the extended links pushed to the student and the ratio of the information with the corresponding label to the total information in the extended links to the corresponding value according to the first browsing preference and the second browsing preference of the student, and outputs the corresponding information extended links to the display unit after the adjustment is completed, so that the student can acquire the content containing the corresponding information by clicking the corresponding information extended links on the display unit;
step 5, the central control unit ranks the importance degree of each information according to the occurrence frequency of each information in the big data; when the ratio of the number of the single-level information extension links output by the central control unit to the total number of the information extension links output by the central control unit reaches a preset value, the central control unit does not output the information extension links corresponding to the information and outputs the information extension links of the upper level corresponding to the information.
Further, in the step s3, when the central control unit determines the first browsing preference of the learner, the central control unit counts the number of each label in the information of the history browse of the learner and counts the number of each keyword in the history search of the learner;
For a single tag, if the ratio of the number of the tags to the total number of the tags of the same level in the historical browsing information is within a preset ratio interval, the central control unit judges that the tag belongs to the first browsing preference of the student;
for the single keyword, if the ratio of the number of the keywords to the total number of the historical search keywords is larger than a preset value, the central control unit judges that the keyword belongs to the first browsing preference of the student.
Further, the labels comprise a subject label as a first level, a domain label as a second level and a knowledge point label as a third level; the central control unit selects a corresponding preset duty ratio interval as an evaluation reference when judging the duty ratio of the single tag to the total number of the same-level tags in the historical browsing information,
when the central control unit judges that the labels belong to a first level and the ratio F of the number of the labels to the total number of the labels of the same level in the total historical browsing information is more than 1/8, the central control unit judges the labels as a first browsing preference aiming at the student;
when the central control unit judges that the labels belong to a second level and the ratio F of the number of the labels to the total number of the labels of the same level in the total historical browsing information meets 1/40 < F < 1/8, the central control unit judges the labels as a first browsing preference aiming at the student;
When the central control unit judges that the labels belong to the third level and the ratio F of the number of the labels to the total number of the labels of the same level in the total historical browsing information meets 1/100 < F < 1/40, the central control unit judges the labels as a first browsing preference aiming at the student.
Further, when the central control unit determines that a plurality of labels positioned in the corresponding preset duty ratio interval exist,
if the levels of the labels are the same and the labels belong to the first level, the central control unit judges the label with the highest occupation ratio as a first browsing preference for the student;
if the levels of the labels are the same and the labels belong to the second level, for two of the labels, if the two labels belong to different first levels, calculating a duty ratio difference DeltaF, determining a first browsing preference of the student, wherein the central control unit is provided with a preset duty ratio difference DeltaF 0,
if DeltaF < DeltaF0, the central control unit judges the label with the second level with the highest occupation ratio as a first browsing preference for the student;
if DeltaF > DeltaF0, the central control unit judges the first-level tag with the highest proportion in the first-level tags to which the tags of the second level belong as a first browsing preference for the student;
If the levels of the labels are the same and the labels belong to the second level, for two labels, if the two labels belong to the same first level, the central control unit judges the label with the highest occupation ratio in the second level as a first browsing preference for the student;
if the levels of the labels are the same and the labels belong to the third level, the central control unit judges the label with the highest occupation ratio in the third level as the first browsing preference aiming at the student.
Further, the central control unit determines the number of extended links pushed to the student and the ratio of information with corresponding labels in the extended links to the total information according to the average annual ranking of the total score of the student in the past exam and the average annual ranking of the score of each single department.
Further, the central control unit ranks the students according to the average ranking of the overall achievements of the students and corrects the information pushing quantity Q for the students according to the ranking result, the central control unit stores a first average ranking Wa of the overall achievements, a second average ranking Wb of the overall achievements, a first average ranking Va of the single achievements and a second average ranking Vb of the single achievements in advance, wherein Wa is less than Wb, va is less than Vb,
When the central control unit ranks the students according to the average ranking W of the overall achievements of the students, if W is less than or equal to W, the central control unit judges that the students are first-level students, if W is less than or equal to W and less than Wb, the central control unit judges that the students are second-level students, and if W is more than Wb, the central control unit judges that the students are third-level students;
when the central control unit ranks the students according to the single-subject score average ranking V of the students, if V is less than or equal to Va, the central control unit judges that the students are primary subjects in the subjects, if Va is less than or equal to V is less than Vb, the central control unit judges that the students are secondary subjects in the subjects, and if V is more than Vb, the central control unit judges that the students are tertiary subjects in the subjects;
the central control unit is also provided with a pushing quantity correction coefficient alpha, and the pushing quantity correction coefficient alpha is set to be more than 0 and less than 0.6;
when the central control unit judges that the student is a first-level student, the central control unit corrects the information pushing quantity Q of the student, the corrected information pushing quantity is marked as Q ', and Q' =Q×alpha is set;
when the central control unit judges that the student is a secondary student, the central control unit does not correct the information pushing quantity of the student;
when the central control unit judges that the student is a three-level student, the central control unit corrects the information pushing quantity Q of the student, the corrected information pushing quantity is marked as Q ', and Q' =Q× (1+alpha) is set.
Further, the AI-based content recommendation method as recited in claim 4, wherein the central control unit adjusts a duty ratio of information corresponding to the first hierarchical label in information pushed for a learner according to an average ranking of individual achievements of the learner, the central control unit is provided with a duty ratio adjustment coefficient beta corresponding to the first hierarchical information, 0.2 < beta < 0.5,
if V is less than or equal to Va, the central control unit judges that the student is a first-level subject student, the central control unit adjusts the information duty ratio P of the corresponding first level in the information pushing quantity of the student, the information duty ratio of the corresponding first level in the information pushing quantity after adjustment is recorded as P ', and P' =Px (1-beta) is set;
if Va is less than or equal to V and less than Vb, the central control unit judges that the student is a secondary student, and the central control unit does not adjust the information duty ratio P of the corresponding first level in the information pushing quantity of the student;
if V > Vb, the central control unit determines that the student is a three-stage subject student, adjusts the information duty ratio P corresponding to the first level in the information pushing quantity, marks the information duty ratio P 'corresponding to the first level in the information pushing quantity after adjustment, and sets P' =p× (1+β).
Further, when the central control unit determines that the information duty ratio of the corresponding first level in the information pushing quantity is required to be adjusted to P ', the central control unit compares P' with a preset duty ratio P0 set in the central control unit to complete the adjustment of the information duty ratio of the corresponding first level in the information pushing quantity,
if P 'is less than or equal to P0, the central control unit adjusts P' to P0 and does not adjust Q;
if P '> P0, the central control unit adjusts Q to Q' so that P '/Q' -P0 is not more than Q ', wherein Q' is the total information push quantity after adjustment.
Further, the central control unit marks the label duty ratio determined according to the first browsing preference as G, compares G with P',
if the label in the information of G is the first level, the central control unit judges that P 'and G meet P' +G < 0.6;
if the label in the information of G is a second level or a third level and the subject to which the label belongs is different from the subject in the information of P ', the central control unit judges that P ' and G meet P ' +G < 0.85;
if the label in the information belonging to G is the second level or the third level and the subject belonging to the label is the same as the subject in the information belonging to P',
if P' < G, the central control unit sets the duty ratio of the information of the label corresponding to the second level or the third level in the pushed information as G;
If P 'is more than or equal to G, the central control unit sets the proportion of the information with the label corresponding to the first level in the pushed information as P' and sets the proportion of the information with the label corresponding to the second level or the third level in the information with the label of the first level as G.
Further, in the step s5, the central control unit ranks the importance degree of each information according to the frequency of occurrence of each information in the past examination, the ranking is periodic ranking, the central control unit sets a preset duty ratio H0 for the frequency of occurrence of each knowledge point in the past examination, compares the frequency of occurrence of each knowledge point in one period with the preset duty ratio, ranks each information according to the comparison result,
if H > H0, the central control unit judges that the information is the first-level information of the high-frequency test point;
if H is less than or equal to H0, the central control unit judges that the information is the secondary information of the non-high frequency test point.
Compared with the prior art, the invention has the beneficial effects that the browsing preference of the student is determined by recording the browsing footprint and the searching footprint of the student, and the corresponding information is extended and linked to be output to the display unit, so that the student obtains interested contents, the student is effectively ensured to obtain accurate information, and the time waste for screening is avoided; meanwhile, the average annual ranking of the total achievements in the past exam of the students and the average annual ranking of the achievements of the single departments are searched, so that the total amount of information pushed to the students and the information proportion corresponding to the first level are determined, the reading rate of the students for the pushed information is improved, and the pushing efficiency of the method for the information content of the students is further improved.
Further, the central control unit determines browsing preference of the learner by judging whether the single tag or the single keyword belongs to the first browsing preference, so that corresponding information is accurately pushed to the learner, time for the learner to search and screen the information is saved, and reading efficiency of the learner is improved.
Furthermore, the central control unit divides the levels for the single tag, divides the information of each level into intervals, and enables the students to quickly locate the first browsing preference of the students through the intervals, so that the reading efficiency of the students is effectively improved, and the pushing efficiency of the method for the information content of the students is further improved.
Further, when the central control unit judges that a plurality of labels located in the corresponding preset duty ratio interval exist, how to judge whether the labels are the first browsing preference of the student or not according to the condition that the levels of the labels are the same or different, the pushed information quantity can be effectively updated through the setting, the reading rate of the student for the pushed information is improved, and the pushing efficiency of the method for the information content of the student is further improved.
Furthermore, a plurality of total score average ranks and pushing quantity correction coefficients are prestored in the central control unit, and the method judges the learning condition of the students by comparing the total score average ranks of the students with the prestored total score average ranks, and timely adjusts the quantity of pushing information according to the result, so that the situation that the students consume too much or too little information pushing quantity to screen useful information or insufficient learning content can be effectively avoided, and the pushing efficiency of the method for the information content of the students with different scores is further improved.
Further, the central control unit adjusts the information proportion corresponding to the first level in the pushed information received by the students according to the average rank of the single-family achievements of the students.
Further, the central control unit is provided with a preset duty ratio P0 for the information of the first level corresponding to the single subject, and the information content pushing method for the students effectively improves the reading efficiency of the students by adjusting the duty ratio of the information of the first level in the information pushing quantity and comparing the adjusted duty ratio with the preset duty ratio and adjusting the duty ratio of the information of the first level in the information pushing quantity according to the comparison result.
Further, the central control unit ranks the importance degree of each information according to the occurrence frequency of each information in the examination, and the importance degree of each information is determined through the ranking, so that the pushing quantity and pushing frequency of each information are adjusted, the learning degree of the students on knowledge points when pushing the information to different students is effectively ensured, the reading efficiency of the students is effectively improved, and the pushing efficiency of the information content of the students is further improved.
Drawings
Fig. 1 is a block diagram of a content recommendation method based on AI according to the present embodiment of the invention.
Fig. 2 is a flowchart of the content recommendation method based on AI according to the present invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1, a block diagram of an AI-based content recommendation method according to the present embodiment of the invention is shown, in which an information collecting unit is configured to collect basic information of a student and extract historical performance information of the student; the cloud platform is used for selecting corresponding information in descending order of browsing data of information in big data and keyword searching quantity in a database and pushing the information to a first logged-in student; the display unit is used for displaying the corresponding information extension links for the students to read; the central control unit controls the information acquisition unit to acquire data, selects information to push to a first logged-in student according to browsing data of the information in the cloud platform and keyword searching quantity in the database, adjusts the number of extension links pushed to the student according to first browsing preference and second browsing preference of the student, and outputs information to the display unit, wherein the information acquisition unit, the cloud platform and the display unit are respectively connected.
Referring to fig. 2, which is a flowchart of the content recommendation method based on AI according to the present invention,
the content recommendation method based on AI comprises the following steps:
step S1, an information acquisition unit acquires basic information of a student and extracts historical performance information of the student from a database in a school according to the basic information; the historical performance information comprises an average annual ranking of the total performance of the student in the past exam and an average annual ranking of the performance of each single department;
step s2, the cloud platform selects corresponding information according to browsing data of information in big data and keyword searching quantity in a database in descending order and pushes the selected information to a first-time logged-in student;
step s3, the central control unit records the browsing footprint and the searching footprint of the student after the student finishes browsing or searching the information to determine the first browsing preference of the student, and simultaneously determines the second browsing preference of the student according to the average annual group ranking of the total score and the average annual group ranking of the single-department score in the history examination of the student, and the central control unit ranks the student according to the average annual group ranking of the total score of the student and corrects the information pushing quantity aiming at the student according to the ranking result; the central control unit adjusts the information duty ratio of the corresponding first level in the information of the student aiming at the student according to the average annual ranking of the single-department achievements of the student;
Step s4, the central control unit adjusts the ratio of the single label to the total number of the same-level labels in the historical browsing information, the number of the extended links pushed to the student and the ratio of the information with the corresponding label to the total information in the extended links to the corresponding value according to the first browsing preference and the second browsing preference of the student, and outputs the corresponding information extended links to the display unit after the adjustment is completed, so that the student can acquire the content containing the corresponding information by clicking the corresponding information extended links on the display unit;
step 5, the central control unit ranks the importance degree of each information according to the occurrence frequency of each information in the big data; when the ratio of the number of the single-level information extension links output by the central control unit to the total number of the information extension links output by the central control unit reaches a preset value, the central control unit does not output the information extension links corresponding to the information and outputs the information extension links of the upper level corresponding to the information.
Specifically, in the step s3, when the central control unit determines the first browsing preference of the learner, the central control unit counts the number of each label in the information of the history browsing of the learner and counts the number of each keyword in the history searching of the learner;
For a single tag, if the ratio of the number of the tags to the total number of the tags of the same level in the historical browsing information is within a preset ratio interval, the central control unit judges that the tag belongs to the first browsing preference of the student;
for the single keyword, if the ratio of the number of the keywords to the total number of the historical search keywords is larger than a preset value, the central control unit judges that the keyword belongs to the first browsing preference of the student.
According to the invention, the central control unit determines the browsing preference of the student by judging whether the single tag or the single keyword belongs to the first browsing preference, so that the corresponding information is accurately pushed to the student, the time for the student to search and screen the information is saved, and the reading efficiency of the student is improved.
Specifically, the label is a structural block diagram of the label according to the embodiment of the invention, and the label comprises a subject label serving as a first level, a domain label serving as a second level and a knowledge point label serving as a third level; the central control unit selects a corresponding preset duty ratio interval as an evaluation reference when judging the duty ratio of the single tag to the total number of the same-level tags in the historical browsing information,
When the central control unit judges that the labels belong to a first level and the ratio F of the number of the labels to the total number of the labels of the same level in the total historical browsing information is more than 1/8, the central control unit judges the labels as a first browsing preference aiming at the student;
when the central control unit judges that the labels belong to a second level and the ratio F of the number of the labels to the total number of the labels of the same level in the total historical browsing information meets 1/40 < F < 1/8, the central control unit judges the labels as a first browsing preference aiming at the student;
when the central control unit judges that the labels belong to the third level and the ratio F of the number of the labels to the total number of the labels of the same level in the total historical browsing information meets 1/100 < F < 1/40, the central control unit judges the labels as a first browsing preference aiming at the student.
According to the method, the central control unit divides the levels for the single tag, and divides the information of each level into the intervals, so that the students can quickly position the first browsing preference of the students through the arrangement of the intervals, the reading efficiency of the students is effectively improved, and the pushing efficiency of the method for the information content of the students is further improved.
Specifically, when the central control unit determines that a plurality of labels located in the corresponding preset duty ratio interval exist,
if the levels of the labels are the same and the labels belong to the first level, the central control unit judges the label with the highest occupation ratio as a first browsing preference for the student;
if the levels of the labels are the same and the labels belong to the second level, for two of the labels, if the two labels belong to different first levels, calculating a duty ratio difference DeltaF, determining a first browsing preference of the student, wherein the central control unit is provided with a preset duty ratio difference DeltaF 0,
if DeltaF < DeltaF0, the central control unit judges the label with the second level with the highest occupation ratio as a first browsing preference for the student;
if DeltaF > DeltaF0, the central control unit judges the first-level tag with the highest proportion in the first-level tags to which the tags of the second level belong as a first browsing preference for the student;
if the levels of the labels are the same and the labels belong to the second level, for two labels, if the two labels belong to the same first level, the central control unit judges the label with the highest occupation ratio in the second level as a first browsing preference for the student;
If the levels of the labels are the same and the labels belong to the third level, the central control unit judges the label with the highest occupation ratio in the third level as the first browsing preference aiming at the student.
When judging that a plurality of labels located in a corresponding preset duty ratio interval exist, the central control unit of the invention states how to judge whether the labels are the first browsing preference of the student or not according to the situation, and by the setting, the pushed information quantity can be effectively updated, so that the reading rate of the student for the pushed information is improved, and the pushing efficiency of the method for the information content of the student is further improved.
Specifically, the central control unit determines the number of extension links pushed to the student and the ratio of information with corresponding labels in the extension links to total information according to the average annual group ranking of the total score of the student in the past exam and the average annual group ranking of the score of each single department.
Specifically, the central control unit ranks the students according to the average ranking of the overall achievements of the students and corrects the information pushing quantity Q for the students according to the ranking result, the central control unit stores a first average ranking Wa of the overall achievements, a second average ranking Wb of the overall achievements, a first average ranking Va of the achievements of the single departments and a second average ranking Vb of the achievements of the single departments in advance, wherein Wa is less than Wb, va is less than Vb,
When the central control unit ranks the students according to the average ranking W of the overall achievements of the students, if W is less than or equal to W, the central control unit judges that the students are first-level students, if W is less than or equal to W and less than Wb, the central control unit judges that the students are second-level students, and if W is more than Wb, the central control unit judges that the students are third-level students;
when the central control unit ranks the students according to the single-subject score average ranking V of the students, if V is less than or equal to Va, the central control unit judges that the students are primary subjects in the subjects, if Va is less than or equal to V is less than Vb, the central control unit judges that the students are secondary subjects in the subjects, and if V is more than Vb, the central control unit judges that the students are tertiary subjects in the subjects;
the central control unit is also provided with a pushing quantity correction coefficient alpha, and the pushing quantity correction coefficient alpha is set to be more than 0 and less than 0.6;
when the central control unit judges that the student is a first-level student, the central control unit corrects the information pushing quantity Q of the student, the corrected information pushing quantity is marked as Q ', and Q' =Q×alpha is set;
when the central control unit judges that the student is a secondary student, the central control unit does not correct the information pushing quantity of the student;
when the central control unit judges that the student is a three-level student, the central control unit corrects the information pushing quantity Q of the student, the corrected information pushing quantity is marked as Q ', and Q' =Q× (1+alpha) is set.
The invention compares the average ranking of the total score of the students with the average ranking of the prestored total score, judges the learning condition of the students, and timely adjusts the quantity of the pushed information according to the result, thereby effectively avoiding the situation that the students consume too much or too little information pushing quantity to screen useful information or insufficient learning content, and further improving the pushing efficiency of the method aiming at the information content of different students.
Specifically, the central control unit adjusts the duty ratio of the information corresponding to the first-level label in the information pushed by the student according to the average ranking of the individual achievements of the student, the central control unit is provided with a duty ratio adjustment coefficient beta corresponding to the first-level information, 0.2 < beta < 0.5,
if V is less than or equal to Va, the central control unit judges that the student is a first-level subject student, the central control unit adjusts the information duty ratio P of the corresponding first level in the information pushing quantity of the student, the information duty ratio of the corresponding first level in the information pushing quantity after adjustment is recorded as P ', and P' =Px (1-beta) is set;
If Va is less than or equal to V and less than Vb, the central control unit judges that the student is a secondary student, and the central control unit does not adjust the information duty ratio P of the corresponding first level in the information pushing quantity of the student;
if V > Vb, the central control unit determines that the student is a three-stage subject student, adjusts the information duty ratio P corresponding to the first level in the information pushing quantity, marks the information duty ratio P 'corresponding to the first level in the information pushing quantity after adjustment, and sets P' =p× (1+β).
According to the method, the central control unit adjusts the information proportion corresponding to the first level in the pushed information received by the students according to the average rank of the single-family achievements of the students, and by adjusting the information proportion corresponding to the first level in the information for different students, different learning information can be effectively pushed for the students with different family achievements, so that the effectiveness of pushing the information for the students is improved, and meanwhile, the reading efficiency of the method for different students with different family aims is further improved.
Specifically, the central control unit sets a preset duty ratio P0 for the information of the first level corresponding to the single subject,
when the central control unit determines that the information duty ratio of the corresponding first level in the information pushing quantity is required to be adjusted to P ', the central control unit compares P' with a preset duty ratio P0 set in the central control unit to finish the adjustment of the information duty ratio of the corresponding first level in the information pushing quantity,
If P 'is less than or equal to P0, the central control unit adjusts P' to P0 and does not adjust Q;
if P '> P0, the central control unit adjusts Q to Q' so that P '/Q' -P0 is not more than Q ', wherein Q' is the total information push quantity after adjustment.
According to the invention, the central control unit is provided with the preset duty ratio P0 for the information of the first level corresponding to the single subject, and the information content pushing efficiency of the method for the students is further improved by adjusting the duty ratio of the information of the first level in the information pushing quantity, comparing the adjusted duty ratio with the preset duty ratio and adjusting the duty ratio of the information of the first level in the information pushing quantity according to the comparison result.
Specifically, the central control unit marks the label duty ratio determined according to the first browsing preference as G, compares G with P',
if the label in the information of G is the first level, the central control unit judges that P 'and G meet P' +G < 0.6;
if the label in the information of G is a second level or a third level and the subject to which the label belongs is different from the subject in the information of P ', the central control unit judges that P ' and G meet P ' +G < 0.85;
If the label in the information belonging to G is the second level or the third level and the subject belonging to the label is the same as the subject in the information belonging to P',
if P' < G, the central control unit sets the duty ratio of the information of the label corresponding to the second level or the third level in the pushed information as G;
if P 'is more than or equal to G, the central control unit sets the proportion of the information with the label corresponding to the first level in the pushed information as P' and sets the proportion of the information with the label corresponding to the second level or the third level in the information with the label of the first level as G.
Specifically, in the step s5, the central control unit ranks the importance degree of each information according to the number of occurrences of each information in the past examination, the ranking is periodic ranking, the central control unit sets a preset duty ratio H0 for the number of occurrences of each knowledge point in the past examination, compares the number of occurrences of each knowledge point in one period with the preset duty ratio, ranks each information according to the comparison result,
if H > H0, the central control unit judges that the information is the first-level information of the high-frequency test point;
if H is less than or equal to H0, the central control unit judges that the information is the secondary information of the non-high frequency test point.
The central control unit of the invention ranks the importance degree of each information according to the occurrence frequency of each information in the examination, and determines the importance degree of each information through the ranking, so as to adjust the pushing quantity and pushing frequency of each information, effectively ensure the learning degree of the students on knowledge points when pushing the information to different students, effectively improve the reading efficiency of the students, and further improve the pushing efficiency of the information content of the students.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. An AI-based content recommendation method, comprising:
step S1, an information acquisition unit acquires basic information of a student and extracts historical performance information of the student from a database in a school according to the basic information; the historical performance information comprises an average annual ranking of the total performance of the student in the past exam and an average annual ranking of the performance of each single department;
step s2, the cloud platform selects corresponding information according to browsing data of information in big data and keyword searching quantity in a database in descending order and pushes the selected information to a first-time logged-in student;
step s3, the central control unit records the browsing footprint and the searching footprint of the student after the student finishes browsing or searching the information to determine the first browsing preference of the student, and simultaneously determines the second browsing preference of the student according to the average annual group ranking of the total score and the average annual group ranking of the single-department score in the history examination of the student, and the central control unit ranks the student according to the average annual group ranking of the total score of the student and corrects the information pushing quantity aiming at the student according to the ranking result; the central control unit adjusts the information duty ratio of the corresponding first level in the information of the student aiming at the student according to the average annual ranking of the single-department achievements of the student;
Step s4, the central control unit adjusts the ratio of the single label to the total number of the same-level labels in the historical browsing information, the number of the extended links pushed to the student and the ratio of the information with the corresponding label to the total information in the extended links to the corresponding value according to the first browsing preference and the second browsing preference of the student, and outputs the corresponding information extended links to the display unit after the adjustment is completed, so that the student can acquire the content containing the corresponding information by clicking the corresponding information extended links on the display unit;
step 5, the central control unit ranks the importance degree of each information according to the occurrence frequency of each information in the big data; when the ratio of the number of the single-level information extension links output by the central control unit to the total number of the information extension links output by the central control unit reaches a preset value, the central control unit does not output the information extension links corresponding to the information and outputs the information extension links of the upper level corresponding to the information;
when the central control unit determines the first browsing preference of the student, the central control unit counts the number of each tag in the information browsed by the history of the student and counts the number of each keyword in the history retrieval of the student;
For a single tag, if the ratio of the number of the tags to the total number of the tags of the same level in the historical browsing information is within a preset ratio interval, the central control unit judges that the tag belongs to the first browsing preference of the student;
for the single keywords, if the ratio of the number of the keywords to the total number of the historical search keywords is larger than a preset value, the central control unit judges that the keywords belong to the first browsing preference of the student;
the labels comprise a subject label as a first level, a domain label as a second level and a knowledge point label as a third level; the central control unit selects a corresponding preset duty ratio interval as an evaluation reference when judging the duty ratio of the single tag to the total number of the same-level tags in the historical browsing information,
when the central control unit judges that the labels belong to a first level and the ratio F of the number of the labels to the total number of the labels of the same level in the total historical browsing information is more than 1/8, the central control unit judges the labels as a first browsing preference aiming at the student;
when the central control unit judges that the labels belong to a second level and the ratio F of the number of the labels to the total number of the labels of the same level in the total historical browsing information meets 1/40 < F < 1/8, the central control unit judges the labels as a first browsing preference aiming at the student;
When the central control unit judges that the labels belong to the third level and the ratio F of the number of the labels to the total number of the labels of the same level in the total historical browsing information meets 1/100 < F < 1/40, the central control unit judges the labels as a first browsing preference aiming at the student.
2. The AI-based content recommendation method according to claim 1, wherein the central control unit, upon determining that there are a plurality of tags located within the corresponding preset duty cycle interval,
if the levels of the labels are the same and the labels belong to the first level, the central control unit judges the label with the highest occupation ratio as a first browsing preference for the student;
if the levels of the labels are the same and the labels belong to the second level, for two of the labels, if the two labels belong to different first levels, calculating a duty ratio difference DeltaF, determining a first browsing preference of the student, wherein the central control unit is provided with a preset duty ratio difference DeltaF 0,
if DeltaF < DeltaF0, the central control unit judges the label with the second level with the highest occupation ratio as a first browsing preference for the student;
if DeltaF > DeltaF0, the central control unit judges the first-level tag with the highest proportion in the first-level tags to which the tags of the second level belong as a first browsing preference for the student;
If the levels of the labels are the same and the labels belong to the second level, for two labels, if the two labels belong to the same first level, the central control unit judges the label with the highest occupation ratio in the second level as a first browsing preference for the student;
if the levels of the labels are the same and the labels belong to the third level, the central control unit judges the label with the highest occupation ratio in the third level as the first browsing preference aiming at the student.
3. The AI-based content recommendation method of claim 1, wherein the central control unit determines the number of extension links pushed to the learner and the ratio of information with corresponding labels in the extension links to total information based on the average annual ranking of the learner's total performance in the past exam and the average annual ranking of the individual achievements.
4. The AI-based content recommendation method according to claim 1, wherein the central control unit ranks a student according to an average ranking of the overall score of the student and corrects the information push quantity Q for the student according to the result of the ranking, the central control unit pre-stores a first average ranking Wa, a second average ranking Wb, a first average ranking Va of the score of a single department, and a second average ranking Vb of the score of a single department, wherein Wa < Wb, va < Vb,
When the central control unit ranks the students according to the average ranking W of the overall achievements of the students, if W is less than or equal to W, the central control unit judges that the students are first-level students, if W is less than or equal to W and less than Wb, the central control unit judges that the students are second-level students, and if W is more than Wb, the central control unit judges that the students are third-level students;
when the central control unit ranks the students according to the single-subject score average ranking V of the students, if V is less than or equal to Va, the central control unit judges that the students are primary subjects in the subjects, if Va is less than or equal to V is less than Vb, the central control unit judges that the students are secondary subjects in the subjects, and if V is more than Vb, the central control unit judges that the students are tertiary subjects in the subjects;
the central control unit is also provided with a pushing quantity correction coefficient alpha, and the pushing quantity correction coefficient alpha is set to be more than 0 and less than 0.6;
when the central control unit judges that the student is a first-level student, the central control unit corrects the information pushing quantity Q of the student, the corrected information pushing quantity is marked as Q ', and Q' =Q×alpha is set;
when the central control unit judges that the student is a secondary student, the central control unit does not correct the information pushing quantity of the student;
when the central control unit judges that the student is a three-level student, the central control unit corrects the information pushing quantity Q of the student, the corrected information pushing quantity is marked as Q ', and Q' =Q× (1+alpha) is set.
5. The AI-based content recommendation method as recited in claim 2, wherein the central control unit adjusts a duty ratio of information with a corresponding first-level tag in information pushed for a student according to an average ranking of individual achievements of the student, the central control unit is provided with a duty ratio adjustment coefficient beta corresponding to the first-level information, 0.2 < beta < 0.5,
if V is less than or equal to Va, the central control unit judges that the student is a first-level subject student, the central control unit adjusts the information duty ratio P of the corresponding first level in the information pushing quantity of the student, the information duty ratio of the corresponding first level in the information pushing quantity after adjustment is recorded as P ', and P' =Px (1-beta) is set;
if Va is less than or equal to V and less than Vb, the central control unit judges that the student is a secondary student, and the central control unit does not adjust the information duty ratio P of the corresponding first level in the information pushing quantity of the student;
if V > Vb, the central control unit determines that the student is a three-stage subject student, adjusts the information duty ratio P corresponding to the first level in the information pushing quantity, marks the information duty ratio P 'corresponding to the first level in the information pushing quantity after adjustment, and sets P' =p× (1+β).
6. The AI-based content recommendation method as recited in claim 5, wherein when the central control unit determines that the information duty ratio of the corresponding first level in the information push amount is to be adjusted to P ', the central control unit compares P' with a preset duty ratio P0 set in the central control unit to complete the adjustment of the information duty ratio of the corresponding first level in the information push amount,
if P 'is less than or equal to P0, the central control unit adjusts P' to P0 and does not adjust Q;
if P '> P0, the central control unit adjusts Q to Q' so that P '/Q' -P0 is not more than Q ', wherein Q' is the total information push quantity after adjustment.
7. The AI-based content recommendation method as recited in claim 6, wherein the tag duty ratio determined by the central control unit based on the first browsing preference is denoted as G, and G is compared with P',
if the label in the information of G is the first level, the central control unit judges that P 'and G meet P' +G < 0.6;
if the label in the information of G is a second level or a third level and the subject to which the label belongs is different from the subject in the information of P ', the central control unit judges that P ' and G meet P ' +G < 0.85;
if the label in the information belonging to G is the second level or the third level and the subject belonging to the label is the same as the subject in the information belonging to P',
If P' < G, the central control unit sets the duty ratio of the information of the label corresponding to the second level or the third level in the pushed information as G;
if P 'is more than or equal to G, the central control unit sets the proportion of the information with the label corresponding to the first level in the pushed information as P' and sets the proportion of the information with the label corresponding to the second level or the third level in the information with the label of the first level as G.
8. The AI-based content recommendation method according to claim 1, wherein in the step s5 the central control unit rates the importance of each information according to the number of occurrences of each information in the past examination, the rate being a periodic rate, the central control unit sets a preset duty ratio H0 for the number of occurrences of each knowledge point in the past examination, and by comparing the number of occurrences of each knowledge point in one period H with the preset duty ratio and rates each information according to the comparison result,
if H > H0, the central control unit judges that the information is the first-level information of the high-frequency test point; if H is less than or equal to H0, the central control unit judges that the information is the secondary information of the non-high frequency test point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211135681.3A CN115563263B (en) | 2022-09-19 | 2022-09-19 | Content recommendation method based on AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211135681.3A CN115563263B (en) | 2022-09-19 | 2022-09-19 | Content recommendation method based on AI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115563263A CN115563263A (en) | 2023-01-03 |
| CN115563263B true CN115563263B (en) | 2023-09-05 |
Family
ID=84741813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211135681.3A Active CN115563263B (en) | 2022-09-19 | 2022-09-19 | Content recommendation method based on AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115563263B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739649A (en) * | 2020-07-04 | 2020-10-02 | 广州云莫凡信息科技有限公司 | User portrait capturing method, device and system |
| CN111931073A (en) * | 2020-10-10 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Content pushing method and device, electronic equipment and computer readable medium |
| CN112905518A (en) * | 2021-01-29 | 2021-06-04 | 上海莎沙教育科技有限公司 | Knowledge learning clamping plate with automatic recommendation function for preschool education |
| CN113286166A (en) * | 2021-07-21 | 2021-08-20 | 广州凡科互联网科技股份有限公司 | Method for pushing real-time interactive information in network education live broadcast |
| WO2022116536A1 (en) * | 2020-12-04 | 2022-06-09 | 上海帜讯信息技术股份有限公司 | Information service providing method and apparatus, electronic device, and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7242988B1 (en) * | 1991-12-23 | 2007-07-10 | Linda Irene Hoffberg | Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore |
-
2022
- 2022-09-19 CN CN202211135681.3A patent/CN115563263B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739649A (en) * | 2020-07-04 | 2020-10-02 | 广州云莫凡信息科技有限公司 | User portrait capturing method, device and system |
| CN111931073A (en) * | 2020-10-10 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Content pushing method and device, electronic equipment and computer readable medium |
| WO2022116536A1 (en) * | 2020-12-04 | 2022-06-09 | 上海帜讯信息技术股份有限公司 | Information service providing method and apparatus, electronic device, and storage medium |
| CN112905518A (en) * | 2021-01-29 | 2021-06-04 | 上海莎沙教育科技有限公司 | Knowledge learning clamping plate with automatic recommendation function for preschool education |
| CN113286166A (en) * | 2021-07-21 | 2021-08-20 | 广州凡科互联网科技股份有限公司 | Method for pushing real-time interactive information in network education live broadcast |
Non-Patent Citations (1)
| Title |
|---|
| An Adaptive Personalized Recommender Based on Web-Browsing Behavior Learning;Kosuke Takano 等;《 2009 International Conference on Advanced Information Networking and Applications Workshops》;654-660 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115563263A (en) | 2023-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7631008B2 (en) | System and method for generating functions to predict the clickability of advertisements | |
| KR101284788B1 (en) | Apparatus for question answering based on answer trustworthiness and method thereof | |
| US6640218B1 (en) | Estimating the usefulness of an item in a collection of information | |
| US8447766B2 (en) | Method and system for searching unstructured textual data for quantitative answers to queries | |
| CN101361068B (en) | Inferring search category synonyms method and system from user logs | |
| US20130232154A1 (en) | Social network message categorization systems and methods | |
| CN101154224B (en) | Websites navigation method and system thereof | |
| US7831474B2 (en) | System and method for associating an unvalued search term with a valued search term | |
| US8060517B2 (en) | Methods and systems for adjusting a scoring measure based on query breadth | |
| US8271495B1 (en) | System and method for automating categorization and aggregation of content from network sites | |
| US20090024605A1 (en) | Method and system for user and reference ranking in a database | |
| CA2720167A1 (en) | An automated media analysis and document management system | |
| CN103049440A (en) | Recommendation processing method and processing system for related articles | |
| JP2014157623A (en) | System and method for improving ranking of news articles | |
| RU2720954C1 (en) | Search index construction method and system using machine learning algorithm | |
| CN112348602A (en) | Automatic advertisement putting management system based on big data | |
| CN104424342A (en) | Method for keyword matching, and device, server and system of method | |
| WO2009031759A1 (en) | Method and system for generating search collection of query | |
| CN103020066A (en) | Method and device for recognizing search demand | |
| CN103729424A (en) | Method and system for assessing answers in Q&A (questions and answers) community | |
| JP3964630B2 (en) | Information search apparatus, information search program, and recording medium recording the program | |
| CN112699309A (en) | Resource recommendation method, device, readable medium and equipment | |
| CN116308657A (en) | Commodity recommendation method and system for digital marketing platform | |
| CN110275943B (en) | Article pushing method and device | |
| CN115563263B (en) | Content recommendation method based on AI |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |