CN112015780B - Intelligent proposition analysis processing method and system based on deep learning - Google Patents
Intelligent proposition analysis processing method and system based on deep learning Download PDFInfo
- Publication number
- CN112015780B CN112015780B CN202010856601.8A CN202010856601A CN112015780B CN 112015780 B CN112015780 B CN 112015780B CN 202010856601 A CN202010856601 A CN 202010856601A CN 112015780 B CN112015780 B CN 112015780B
- Authority
- CN
- China
- Prior art keywords
- proposition
- same type
- propositions
- historical
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a proposition intelligent analysis processing method and a proposition intelligent analysis processing system based on deep learning, which analyze and process historical proposition data in a deep learning mode so as to determine a comprehensive appearance rule evaluation value of propositions of the same type, and then determine proposition proportion weighted values corresponding to the propositions of the same type by combining a historical examination proposition schema and historical hotspot proposition information so as to obtain and display corresponding prediction proposition information, thereby quickly and accurately forming a reliable test paper and simultaneously facilitating the comprehensive examination of the learning effect of students.
Description
Technical Field
The invention relates to the technical field of intelligent education, in particular to a proposition intelligent analysis processing method and system based on deep learning.
Background
At present, in the teaching process, the examination is still an important means for examining the knowledge learning effect of students, because the knowledge content data learned by students is more and the coverage range of the examination outline of corresponding subjects is larger, in order to effectively prepare the examination, the proposition content of the examination generally needs to be predicted, but the existing proposition analysis mode is that teachers search corresponding examination questions in an examination question bank to form test papers, the examination outline cannot be effectively and comprehensively covered, a large amount of time needs to be consumed to form a whole set of test papers, the examination papers are not favorable for quickly and accurately forming reliable test papers, and the learning effect of the students is not favorable for comprehensively examining.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a proposition intelligent analysis processing method and a system based on deep learning, which determine the comprehensive appearance rule evaluation value of the same type proposition by acquiring the historical proposition data corresponding to the preset target subject, determining the appearance time information and the appearance frequency information corresponding to the same type proposition from the historical proposition data, optimize the comprehensive appearance rule evaluation value according to the historical examination proposition schema and the historical hotspot proposition information, determining the historical proposition rule information of the same type proposition, determining the proposition proportion weighted value corresponding to the same type proposition according to the historical proposition rule information, finally determining the corresponding prediction proposition information according to the proposition proportion weighted value corresponding to the same type proposition, and displaying the prediction proposition information in a visual way for a user to select, generating a plurality of simulation examination questions matched with the prediction proposition information selected by the user; therefore, the intelligent analysis processing method and system for propositions based on deep learning analyze and process historical proposition data in a deep learning mode, determine comprehensive appearance rule evaluation values of propositions of the same type, determine proposition proportion weighted values corresponding to the propositions of the same type by combining a historical examination proposition schema and historical hotspot proposition information, and obtain and display corresponding prediction proposition information, so that reliable test paper is formed quickly and accurately, and meanwhile, the learning effect of students is conveniently and comprehensively examined.
The invention provides a proposition intelligent analysis processing method based on deep learning, which comprises the following steps:
step S1, acquiring historical proposition data corresponding to a preset target subject, and determining appearance time information and appearance frequency information corresponding to the same type proposition from the historical proposition data so as to determine a comprehensive appearance rule evaluation value of the same type proposition;
step S2, according to the theme schema of the historical test and the theme information of the historical hotspot, optimizing the comprehensive appearance rule evaluation value of the same type of theme so as to determine the comprehensive appearance rule evaluation value after the optimization processing of the same type of theme and determine the theme proportion weight value corresponding to the same type of theme;
step S3, according to the optimized comprehensive appearance rule evaluation value and proposition proportion weight value of the same type proposition, determining the prediction proposition information, and visually displaying the prediction proposition information for the user to select;
and step S4, receiving the prediction proposition information selected by the user, and generating the examination paper corresponding to the prediction proposition information selected by the user.
In one embodiment, in step S1, acquiring historical proposition data corresponding to a preset target subject, and determining occurrence time information and occurrence frequency information corresponding to propositions of the same type from the historical proposition data, so as to determine the comprehensive occurrence law evaluation value of the propositions of the same type specifically includes:
step S101, selecting historical proposition data corresponding to a preset target subject from a preset proposition historical database according to subject category information of the preset target subject;
step S102, according to historical examination timestamp information of the preset target subject, identifying the historical proposition data, and determining appearance time information and appearance frequency information corresponding to the same type of proposition in the historical proposition data;
step S103, determining a comprehensive appearance rule evaluation value A of the propositions of the same type according to the appearance time information, the appearance frequency information and the following formula (1):
in the above formula (1), m1 represents the total number of occurrences of all types of propositions of knowledge content corresponding to the same type of proposition determined according to the historical examination timestamp information in the historical proposition data, and m0 represents the total number of occurrences of the same type of proposition determined according to the historical examination timestamp information in the historical proposition data; in the historical proposition data, sequencing all types of propositions of the knowledge content corresponding to the same type of proposition according to the historical examination time stamp information and the sequence of examination time from front to back to form a proposition sequence of the knowledge content corresponding to the same type of proposition, wherein m0-1 represents the number of propositions spaced between two adjacent same type propositions of the m0-1 group in the proposition sequence; deltakRepresenting the appearance time interval between two adjacent propositions of the same type in the kth group, and T (delta m') representing the maximum value in the appearance time interval between two adjacent propositions of the same type in the m0-1 group; t (Δ m ") represents the minimum value in the occurrence time interval between two of the same type propositions adjacent to the m0-1 group.
In one embodiment, in step S2, according to the theme schema of the historical test and the theme information of the historical hotspot, optimizing the comprehensive appearance law evaluation value of the same type of theme to determine the comprehensive appearance law evaluation value after the optimization processing of the same type of theme, and determining a theme proportion weight value corresponding to the same type of theme specifically includes:
step S201, according to the historical examination proposition schema, the historical hotspot proposition information and the following formula (2), optimizing the comprehensive appearance law evaluation value A of the same type proposition, so as to obtain the comprehensive appearance law evaluation value A' after the optimization processing of the same type proposition:
in the formula (2), n represents the total number of times of the historical examinations determined according to the timestamp information of the historical examinations, si represents the probability value of occurrence of propositions of the knowledge content corresponding to the propositions of the same type in the proposition schema of the examination corresponding to the ith historical examination, i is 1, 2, 3, … and n, pi represents the heat value of the knowledge content corresponding to the propositions of the same type in the hotspot proposition corresponding to the ith historical examination, and i is 1, 2, 3, … and n;
step S202, sorting the optimized comprehensive appearance rule evaluation values A' of all the propositions of the same type according to a descending order to obtain a proposition sorting sequence of the same type;
step S203, obtaining respective proposition keywords of each proposition of the same type in the proposition sorting sequence of the same type, and respectively determining a proposition proportion weight value corresponding to each proposition of the same type according to the following formula (3):
in the above formula (3), wjRepresenting proposition proportion weight values corresponding to jth proposition of the same type in the proposition sequencing sequence of the same type; m represents the total times of all question setting keywords included in the history question setting data corresponding to the preset target subject in all historical examinations; beta is ajRepresenting the corresponding total occurrence times of the jth proposition key word in the history proposition data corresponding to the preset target subject in all the historical examinations,
representing all propositions containing jth proposition key words in the historical proposition dataA data bit fraction; the proposition keywords of the proposition of the same type comprise the type keywords of the proposition type and the keywords of the knowledge content corresponding to the proposition;
and step S204, recording each same-type proposition in the same-type proposition sorting sequence and the corresponding proposition proportion weight value in a one-to-one correspondence mode to form a proposition prediction reference list.
In one embodiment, in step S3, determining predicted proposition information according to the optimized integrated occurrence rule evaluation value and proposition proportion weight value of the proposition of the same type, and visually displaying the predicted proposition information for a user to select specifically includes:
step S301, selecting same type propositions of front X bits from the proposition prediction reference list;
step S302, determining the reference proposition quantity corresponding to the previous X-bit proposition of the same type according to the proposition proportion weight value of the previous X-bit proposition of the same type and the preset total quantity of the test paper propositions;
step S303, aiming at each proposition of the same type in the first X-bit propositions: calling Y propositions corresponding to the propositions of the same type from a preset proposition library, wherein Y is equal to or more than the number of reference propositions corresponding to the propositions of the same type;
and S304, taking all the propositions corresponding to the same type propositions of the front X bits as prediction proposition information, and carrying out visual display on the prediction proposition information for the user to select.
In an embodiment, the step S302, determining a reference proposition number corresponding to each proposition of the same type of the previous X digits according to the proposition proportion weight value of each proposition of the same type of the previous X digits and the preset total number of the propositions of the test paper, includes:
and multiplying the total number of the preset test paper propositions by the proposition proportion weighted value of each proposition of the same type to obtain the reference proposition number corresponding to each proposition of the same type.
The embodiment of the invention also provides an intelligent proposition analysis and processing system for deep learning, which comprises:
the system comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for acquiring historical proposition data corresponding to a preset target subject, and determining appearance time information and appearance frequency information corresponding to the same type proposition from the historical proposition data so as to determine a comprehensive appearance rule evaluation value of the same type proposition;
the second determination module is used for optimizing the comprehensive appearance rule evaluation value of the same type of propositions according to the proposition schema of the historical test and the proposition information of the historical hotspots so as to determine the comprehensive appearance rule evaluation value after the optimization processing of the same type of propositions and determine proposition proportion weight values corresponding to the same type of propositions;
the third determining module is used for determining the predicted proposition information according to the comprehensive appearance rule evaluation value and proposition proportion weight value after the optimization processing of the same type proposition, and visually displaying the predicted proposition information for the user to select;
and the generation module is used for receiving the prediction proposition information selected by the user and generating the examination paper corresponding to the prediction proposition information selected by the user.
In one embodiment, the first determining module is further configured to perform the following steps:
step S101, selecting historical proposition data corresponding to a preset target subject from a preset proposition historical database according to subject category information of the preset target subject;
step S102, according to historical examination timestamp information of the preset target subject, identifying the historical proposition data, and determining appearance time information and appearance frequency information corresponding to the same type of proposition in the historical proposition data;
step S103, determining a comprehensive appearance rule evaluation value A of the propositions of the same type according to the appearance time information, the appearance frequency information and the following formula (1):
in the above formula (1), m1 represents the total number of occurrences of all types of propositions of all knowledge contents in the history proposition data, and m0 represents the total number of occurrences of the same type of propositions determined according to the history examination timestamp information in the history proposition data; in the historical proposition data, sequencing all types of propositions of all knowledge contents according to the sequence of examination time from front to back according to the historical examination time stamp information to form a proposition sequence, wherein at the moment, m0-1 represents the spaced proposition number between two adjacent propositions of the same type in an m0-1 group in the proposition sequence; deltakRepresenting the appearance time interval between two adjacent propositions of the same type in the kth group in the proposition sequence, and T (delta m') representing the maximum value in the appearance time interval between two adjacent propositions of the same type in the m0-1 group in the proposition sequence; t (Δ m ") represents the minimum value in the appearance time interval between two adjacent propositions of the same type in the m0-1 group in the propositional sequence.
Wherein m0 times of said same-type propositions are shared in said historical propositions data, every two adjacent two of said same-type propositions are referred to as a set of two adjacent same-type propositions, and thus, a total of m0-1 sets of two adjacent same-type propositions.
In one embodiment, the second determining module is further configured to perform the following steps:
step S201, according to the historical examination proposition schema, the historical hotspot proposition information and the following formula (2), optimizing the comprehensive appearance law evaluation value A of the same type proposition, so as to obtain the comprehensive appearance law evaluation value A' after the optimization processing of the same type proposition:
in the formula (2), n represents the total number of times of the historical examinations determined according to the timestamp information of the historical examinations, si represents the probability value of occurrence of propositions of the knowledge content corresponding to the propositions of the same type in the proposition schema of the examination corresponding to the ith historical examination, i is 1, 2, 3, … and n, pi represents the heat value of the knowledge content corresponding to the propositions of the same type in the hotspot proposition corresponding to the ith historical examination, and i is 1, 2, 3, … and n;
step S202, sorting the optimized comprehensive appearance rule evaluation values A' of all the propositions of the same type according to a descending order to obtain a proposition sorting sequence of the same type;
step S203, obtaining respective proposition keywords of each proposition of the same type in the proposition sorting sequence of the same type, and respectively determining a proposition proportion weight value corresponding to each proposition of the same type according to the following formula (3):
in the above formula (3), wjRepresenting proposition proportion weight values corresponding to jth proposition of the same type in the proposition sequencing sequence of the same type; m represents the total times of all question setting keywords included in the history question setting data corresponding to the preset target subject in all historical examinations; beta is ajRepresenting the corresponding total occurrence times of the jth proposition key word in the history proposition data corresponding to the preset target subject in all the historical examinations,
representing the data bit ratio of all propositions containing the jth proposition keyword in the historical proposition data; the proposition keywords of the proposition of the same type comprise the type keywords of the proposition type and the keywords of the knowledge content corresponding to the proposition;
and step S204, recording each same-type proposition in the same-type proposition sorting sequence and the corresponding proposition proportion weight value in a one-to-one correspondence mode to form a proposition prediction reference list.
In one embodiment, the third determining module is further configured to perform the following steps:
step S301, selecting same type propositions of front X bits from the proposition prediction reference list;
step S302, determining the reference proposition quantity corresponding to the previous X-bit proposition of the same type according to the proposition proportion weight value of the previous X-bit proposition of the same type and the preset total quantity of the test paper propositions;
step S303, aiming at each proposition of the same type in the first X-bit propositions: calling Y propositions corresponding to the propositions of the same type from a preset proposition library, wherein Y is equal to or more than the number of reference propositions corresponding to the propositions of the same type;
and S304, taking all the propositions corresponding to the same type propositions of the front X bits as prediction proposition information, and carrying out visual display on the prediction proposition information for the user to select.
Compared with the prior art, the intelligent analysis processing method and system for proposing based on deep learning can obtain the historical proposition data corresponding to the preset target subject, and determining the appearance time information and the appearance frequency information corresponding to the propositions of the same type from the historical propositions data, so as to determine the comprehensive appearance rule evaluation value of the proposition of the same type, and according to the proposition schema of the historical test and the proposition information of the historical hotspot, optimizing the evaluation value of the comprehensive appearance rule to determine historical proposition rule information of the proposition of the type, determining proposition proportion weight value corresponding to the proposition of the same type according to the historical proposition rule information, and finally determining corresponding prediction proposition information according to the proposition proportion weight corresponding to the proposition of the same type, the forecast proposition information is displayed visually for the user to select, and a plurality of simulated examination questions matched with the forecast proposition information are also generated; therefore, the intelligent analysis processing method and system for propositions based on deep learning analyze and process historical proposition data in a deep learning mode, determine comprehensive appearance rule evaluation values of propositions of the same type, determine proposition proportion weighted values corresponding to the propositions of the same type by combining a historical examination proposition schema and historical hotspot proposition information, and obtain and display corresponding prediction proposition information, so that reliable test paper is formed quickly and accurately, and meanwhile, the learning effect of students is conveniently and comprehensively examined.
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 hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow diagram of the intelligent proposition analysis processing method based on deep learning provided by the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of an intelligent proposition analysis processing method based on deep learning according to an embodiment of the present invention. The intelligent proposition analysis processing method based on deep learning comprises the following steps:
step S1, acquiring historical proposition data corresponding to a preset target subject, and determining appearance time information and appearance frequency information corresponding to the same type proposition from the historical proposition data so as to determine a comprehensive appearance rule evaluation value of the same type proposition; the same type of questions are the same type of question questions aiming at the same knowledge content, and the same type of questions comprise selection questions, filling questions, judgment questions or question and answer questions.
And step S2, optimizing the comprehensive appearance rule evaluation value of the same type of propositions according to the proposition schema of the historical test and the proposition information of the historical hotspots, determining the comprehensive appearance rule evaluation value after the optimization processing of the same type of propositions, and determining the proposition proportion weight value corresponding to the same type of propositions.
And step S3, determining prediction proposition information according to the optimized comprehensive appearance rule evaluation value and proposition proportion weight value of the same type proposition, and carrying out visual display on the prediction proposition information for a user to select.
And step S4, receiving the prediction proposition information selected by the user, and generating the examination paper corresponding to the prediction proposition information selected by the user.
In one embodiment, in step S1, acquiring historical proposition data corresponding to a preset target subject, and determining occurrence time information and occurrence frequency information corresponding to propositions of the same type from the historical proposition data, so as to determine the comprehensive occurrence law evaluation value of the propositions of the same type specifically includes:
step S101, selecting historical proposition data corresponding to a preset target subject from a preset proposition historical database according to subject category information of the preset target subject;
step S102, according to historical examination timestamp information of the preset target subject, identifying the historical proposition data, and determining appearance time information and appearance frequency information corresponding to the same type of proposition in the historical proposition data;
step S103, determining a comprehensive appearance rule evaluation value A of the propositions of the same type according to the appearance time information, the appearance frequency information and the following formula (1):
in the above formula (1), m1 represents the total number of occurrences of all types of propositions of all knowledge contents in the history proposition data, and m0 represents the total number of occurrences of the same type of propositions determined according to the history examination timestamp information in the history proposition data; in the historical proposition data, sequencing all types of propositions of all knowledge contents according to the sequence of examination time from front to back according to the historical examination time stamp information to form a proposition sequence, wherein at the moment, m0-1 represents the spaced proposition number between two adjacent propositions of the same type in an m0-1 group in the proposition sequence; deltakRepresenting the appearance time interval between two adjacent propositions of the same type in the kth group in the proposition sequence, and T (delta m') representing the maximum value in the appearance time interval between two adjacent propositions of the same type in the m0-1 group in the proposition sequence; t (Δ m ") represents the minimum value in the appearance time interval between two adjacent propositions of the same type in the m0-1 group in the propositional sequence.
Wherein m0 times of said same-type propositions are shared in said historical propositions data, every two adjacent two of said same-type propositions are referred to as a set of two adjacent same-type propositions, and thus, a total of m0-1 sets of two adjacent same-type propositions.
In one embodiment, in the step S2, according to the theme schema of the historical test and the theme information of the historical hotspot, optimizing the comprehensive appearance law evaluation value of the same type of theme to determine the comprehensive appearance law evaluation value after the optimization processing of the same type of theme, and determining a theme proportion weight value corresponding to the same type of theme specifically includes steps S201 to 204:
step S201, according to the historical examination proposition schema, the historical hotspot proposition information and the following formula (2), optimizing the comprehensive appearance law evaluation value A of the same type proposition, so as to obtain the comprehensive appearance law evaluation value A' after the optimization processing of the same type proposition:
in the formula (2), n represents the total number of times of the historical examinations determined according to the timestamp information of the historical examinations, si represents the probability value of occurrence of propositions of the knowledge content corresponding to the propositions of the same type in the proposition schema of the examination corresponding to the ith historical examination, i is 1, 2, 3, … and n, pi represents the heat value of the knowledge content corresponding to the propositions of the same type in the hotspot proposition corresponding to the ith historical examination, and i is 1, 2, 3, … and n;
the method for calculating the probability value of the occurrence of the proposition corresponding to the knowledge content corresponding to the proposition of the same type in the test proposition schema corresponding to the ith historical test comprises the following steps: the ratio of the value occupied by the knowledge content corresponding to the same type of proposition specified in the test proposition schema corresponding to the ith historical test to the total value of the test; the total test score is the total test score specified in the test proposition schema corresponding to the ith historical test.
The corresponding heat value of the knowledge content corresponding to the proposition of the same type in the hotspot proposition corresponding to the ith historical examination is as follows: in the ith historical examination, the ratio of the score occupied by the knowledge content corresponding to the proposition of the same type to the total score of the ith historical examination.
Step S202, sorting the optimized comprehensive appearance rule evaluation values A' of all the propositions of the same type according to a descending order to obtain a proposition sorting sequence of the same type;
step S203, obtaining respective proposition keywords of each proposition of the same type in the proposition sorting sequence of the same type, and respectively determining a proposition proportion weight value corresponding to each proposition of the same type according to the following formula (3):
in the above formula (3), wjRepresenting proposition proportion weight values corresponding to jth proposition of the same type in the proposition sequencing sequence of the same type; m represents the preset targetThe total times of all topic-proposing keywords included in the historical topic-proposing data corresponding to the subject appearing in all historical examinations; beta is ajRepresenting the corresponding total occurrence times of the jth proposition key word in the history proposition data corresponding to the preset target subject in all the historical examinations,
representing the data bit ratio of all propositions containing the jth proposition keyword in the historical proposition data; the proposition keywords of the proposition of the same type comprise the type keywords of the proposition type and the keywords of the knowledge content corresponding to the proposition;
and step S204, recording each same-type proposition in the same-type proposition sorting sequence and the corresponding proposition proportion weight value in a one-to-one correspondence mode to form a proposition prediction reference list.
In one embodiment, in step S3, determining predicted proposition information according to the optimized integrated occurrence rule evaluation value and proposition proportion weight value of the proposition of the same type, and visually displaying the predicted proposition information for a user to select specifically includes:
step S301, selecting same type propositions of front X bits from the proposition prediction reference list;
step S302, determining the reference proposition quantity corresponding to the previous X-bit proposition of the same type according to the proposition proportion weight value of the previous X-bit proposition of the same type and the preset total quantity of the test paper propositions;
step S303, aiming at each proposition of the same type in the first X-bit propositions: calling Y propositions corresponding to the propositions of the same type from a preset proposition library, wherein Y is equal to or more than the number of reference propositions corresponding to the propositions of the same type;
and S304, taking all the propositions corresponding to the same type propositions of the front X bits as prediction proposition information, and carrying out visual display on the prediction proposition information for the user to select.
In an embodiment, the step S302, determining a reference proposition number corresponding to each proposition of the same type of the previous X digits according to the proposition proportion weight value of each proposition of the same type of the previous X digits and the preset total number of the propositions of the test paper, includes:
and multiplying the total number of the preset test paper propositions by the proposition proportion weighted value of each proposition of the same type to obtain the reference proposition number corresponding to each proposition of the same type.
Compared with the prior art, the intelligent analysis processing method and system for proposing based on deep learning can obtain the historical proposition data corresponding to the preset target subject, and determining the appearance time information and the appearance frequency information corresponding to the propositions of the same type from the historical propositions data, so as to determine the comprehensive appearance rule evaluation value of the proposition of the same type, and according to the proposition schema of the historical test and the proposition information of the historical hotspot, optimizing the evaluation value of the comprehensive appearance rule to determine historical proposition rule information of the proposition of the type, determining proposition proportion weight value corresponding to the proposition of the same type according to the historical proposition rule information, and finally determining corresponding prediction proposition information according to the proposition proportion weight corresponding to the proposition of the same type, the forecast proposition information is displayed visually for the user to select, and a plurality of simulated examination questions matched with the forecast proposition information are also generated; therefore, the intelligent proposition analysis and processing method and system based on deep learning can analyze and process historical proposition data in a deep learning mode, determining the comprehensive appearance rule evaluation value of the same type of proposition, determining proposition proportion weight value corresponding to the same type of proposition by combining the scheme of the same type of proposition and the proposition information of the historical hot spot, obtaining and displaying corresponding prediction proposition information, therefore, reliable test paper can be formed quickly and accurately, the formed test paper can cover the historical examination outline and the actual examination hotspot, the knowledge content which may be related to the examination can be covered comprehensively, the intelligent generation is realized, the test paper of students can be examined comprehensively, the intelligence of the test paper generation is improved, the test paper is generated without depending on the subjective consciousness of the paper-taker, the test paper generation is more scientific, the examination range is comprehensive, and the test paper generation efficiency is improved.
Corresponding to the intelligent analysis processing method for propositions, the embodiment of the invention also provides an intelligent analysis processing system for propositions of deep learning, which comprises the following steps:
the system comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for acquiring historical proposition data corresponding to a preset target subject, and determining appearance time information and appearance frequency information corresponding to the same type proposition from the historical proposition data so as to determine a comprehensive appearance rule evaluation value of the same type proposition;
the second determination module is used for optimizing the comprehensive appearance rule evaluation value of the same type of propositions according to the proposition schema of the historical test and the proposition information of the historical hotspots so as to determine the comprehensive appearance rule evaluation value after the optimization processing of the same type of propositions and determine proposition proportion weight values corresponding to the same type of propositions;
the third determining module is used for determining the predicted proposition information according to the comprehensive appearance rule evaluation value and proposition proportion weight value after the optimization processing of the same type proposition, and visually displaying the predicted proposition information for the user to select;
and the generation module is used for receiving the prediction proposition information selected by the user and generating the examination paper corresponding to the prediction proposition information selected by the user.
In one embodiment, the first determining module is further configured to perform the following steps:
step S101, selecting historical proposition data corresponding to a preset target subject from a preset proposition historical database according to subject category information of the preset target subject;
step S102, according to historical examination timestamp information of the preset target subject, identifying the historical proposition data, and determining appearance time information and appearance frequency information corresponding to the same type of proposition in the historical proposition data;
step S103, determining a comprehensive appearance rule evaluation value A of the propositions of the same type according to the appearance time information, the appearance frequency information and the following formula (1):
in the above formula (1), m1 represents the total number of occurrences of all types of propositions of knowledge content corresponding to the same type of proposition determined according to the historical examination timestamp information in the historical proposition data, and m0 represents the total number of occurrences of the same type of proposition determined according to the historical examination timestamp information in the historical proposition data; in the historical proposition data, sequencing all types of propositions of the knowledge content corresponding to the same type of proposition according to the historical examination time stamp information and the sequence of examination time from front to back to form a proposition sequence of the knowledge content corresponding to the same type of proposition, wherein m0-1 represents the number of propositions spaced between two adjacent same type propositions of the m0-1 group in the proposition sequence; deltakRepresenting the appearance time interval between two adjacent propositions of the same type in the kth group, and T (delta m') representing the maximum value in the appearance time interval between two adjacent propositions of the same type in the m0-1 group; t (Δ m ") represents the minimum value in the occurrence time interval between two of the same type propositions adjacent to the m0-1 group.
In one embodiment, the second determining module is further configured to perform the following steps:
step S201, according to the historical examination proposition schema, the historical hotspot proposition information and the following formula (2), optimizing the comprehensive appearance law evaluation value A of the same type proposition, so as to obtain the comprehensive appearance law evaluation value A' after the optimization processing of the same type proposition:
in the formula (2), n represents the total number of times of the historical examinations determined according to the timestamp information of the historical examinations, si represents the probability value of occurrence of propositions of the knowledge content corresponding to the propositions of the same type in the proposition schema of the examination corresponding to the ith historical examination, i is 1, 2, 3, … and n, pi represents the heat value of the knowledge content corresponding to the propositions of the same type in the hotspot proposition corresponding to the ith historical examination, and i is 1, 2, 3, … and n;
step S202, sorting the optimized comprehensive appearance rule evaluation values A' of all the propositions of the same type according to a descending order to obtain a proposition sorting sequence of the same type;
step S203, obtaining respective proposition keywords of each proposition of the same type in the proposition sorting sequence of the same type, and respectively determining a proposition proportion weight value corresponding to each proposition of the same type according to the following formula (3):
in the above formula (3), wjRepresenting proposition proportion weight values corresponding to jth proposition of the same type in the proposition sequencing sequence of the same type; m represents the total times of all question setting keywords included in the history question setting data corresponding to the preset target subject in all historical examinations; beta is ajRepresenting the corresponding total occurrence times of the jth proposition key word in the history proposition data corresponding to the preset target subject in all the historical examinations,
representing the data bit ratio of all propositions containing the jth proposition keyword in the historical proposition data; the proposition keywords of the proposition of the same type comprise the type keywords of the proposition type and the keywords of the knowledge content corresponding to the proposition;
and step S204, recording each same-type proposition in the same-type proposition sorting sequence and the corresponding proposition proportion weight value in a one-to-one correspondence mode to form a proposition prediction reference list.
In one embodiment, the third determining module is further configured to perform the following steps:
step S301, selecting same type propositions of front X bits from the proposition prediction reference list;
step S302, determining the reference proposition quantity corresponding to the previous X-bit proposition of the same type according to the proposition proportion weight value of the previous X-bit proposition of the same type and the preset total quantity of the test paper propositions;
step S303, aiming at each proposition of the same type in the first X-bit propositions: calling Y propositions corresponding to the propositions of the same type from a preset proposition library, wherein Y is equal to or more than the number of reference propositions corresponding to the propositions of the same type;
and S304, taking all the propositions corresponding to the same type propositions of the front X bits as prediction proposition information, and carrying out visual display on the prediction proposition information for the user to select.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (3)
1. The proposition intelligent analysis processing method based on deep learning is characterized by comprising the following steps:
step S1, acquiring historical proposition data corresponding to a preset target subject, and determining appearance time information and appearance frequency information corresponding to the same type proposition from the historical proposition data so as to determine a comprehensive appearance rule evaluation value of the same type proposition;
step S2, according to the theme schema of the historical test and the theme information of the historical hotspot, optimizing the comprehensive appearance rule evaluation value of the same type of theme so as to determine the comprehensive appearance rule evaluation value after the optimization processing of the same type of theme and determine the theme proportion weight value corresponding to the same type of theme;
step S3, according to the optimized comprehensive appearance rule evaluation value and proposition proportion weight value of the same type proposition, determining the prediction proposition information, and visually displaying the prediction proposition information for the user to select;
step S4, receiving the prediction proposition information selected by the user, and generating an examination paper corresponding to the prediction proposition information selected by the user;
in step S1, acquiring historical proposition data corresponding to a preset target subject, and determining occurrence time information and occurrence frequency information corresponding to propositions of the same type from the historical proposition data, so as to determine a comprehensive occurrence law evaluation value of the propositions of the same type specifically includes:
step S101, selecting historical proposition data corresponding to a preset target subject from a preset proposition historical database according to subject category information of the preset target subject;
step S102, according to historical examination timestamp information of the preset target subject, identifying the historical proposition data, and determining appearance time information and appearance frequency information corresponding to the same type of proposition in the historical proposition data;
step S103, determining a comprehensive appearance rule evaluation value A of the propositions of the same type according to the appearance time information, the appearance frequency information and the following formula (1):
in the above formula (1), m1 represents the total number of occurrences of all types of propositions of knowledge content corresponding to the same type of proposition determined according to the historical examination timestamp information in the historical proposition data, and m0 represents the total number of occurrences of the same type of proposition determined according to the historical examination timestamp information in the historical proposition data; in the historical proposition data, sequencing all types of propositions of the knowledge content corresponding to the same type of proposition according to the historical examination time stamp information and the sequence of examination time from front to back to form a proposition sequence of the knowledge content corresponding to the same type of proposition, wherein m0-1 represents the number of propositions spaced between two adjacent same type propositions of the m0-1 group in the proposition sequence; deltakIndicating that the k-th group is adjacent(ii) the time interval of occurrence between two of said same-type propositions, T (Δ m') representing the maximum value in the time interval of occurrence between two of said same-type propositions adjacent in the m0-1 group; t (Δ m ") represents the minimum value in the appearance time interval between two adjacent propositions of the same type in the m0-1 group;
in step S2, according to the theme schema of the historical test and the theme information of the historical hotspot, optimizing the comprehensive appearance law evaluation value of the same type of theme to determine the comprehensive appearance law evaluation value after the optimization processing of the same type of theme, and determining a theme proportion weight value corresponding to the same type of theme specifically includes:
step S201, according to the historical examination proposition schema, the historical hotspot proposition information and the following formula (2), optimizing the comprehensive appearance law evaluation value A of the same type proposition, so as to obtain the comprehensive appearance law evaluation value A' after the optimization processing of the same type proposition:
in the above formula (2), n represents the total number of times of the historic test determined based on the historic test time stamp information, siRepresenting the probability value of occurrence of corresponding propositions of the knowledge contents corresponding to the propositions of the same type in the test proposition schema corresponding to the ith historical test, wherein i is 1, 2, 3, …, n, piRepresenting the heat value of the knowledge content corresponding to the proposition of the same type in the hot proposition corresponding to the ith historical examination, wherein i is 1, 2, 3, … and n;
step S202, sorting the optimized comprehensive appearance rule evaluation values A' of all the propositions of the same type according to a descending order to obtain a proposition sorting sequence of the same type;
step S203, obtaining respective proposition keywords of each proposition of the same type in the proposition sorting sequence of the same type, and respectively determining a proposition proportion weight value corresponding to each proposition of the same type according to the following formula (3):
in the above formula (3), wjRepresenting proposition proportion weight values corresponding to jth proposition of the same type in the proposition sequencing sequence of the same type; m represents the total times of all question setting keywords included in the history question setting data corresponding to the preset target subject in all historical examinations; beta is ajRepresenting the corresponding total occurrence times of the jth proposition key word in the history proposition data corresponding to the preset target subject in all the historical examinations,
representing the data bit ratio of all propositions containing the jth proposition keyword in the historical proposition data; the proposition keywords of the proposition of the same type comprise the type keywords of the proposition type and the keywords of the knowledge content corresponding to the proposition;
step S204, recording each proposition of the same type in the proposition sorting sequence and the corresponding proposition proportion weight value in a one-to-one correspondence manner to form a proposition prediction reference list;
in step S3, determining predicted proposition information according to the optimized comprehensive occurrence rule evaluation value and proposition proportion weight value of the same type proposition, and visually displaying the predicted proposition information for the user to select specifically includes:
step S301, selecting same type propositions of front X bits from the proposition prediction reference list;
step S302, determining the reference proposition quantity corresponding to the previous X-bit proposition of the same type according to the proposition proportion weight value of the previous X-bit proposition of the same type and the preset total quantity of the test paper propositions;
step S303, aiming at each proposition of the same type in the first X-bit propositions: calling Y propositions corresponding to the propositions of the same type from a preset proposition library, wherein Y is equal to or more than the number of reference propositions corresponding to the propositions of the same type;
and S304, taking all the propositions corresponding to the same type propositions of the front X bits as prediction proposition information, and carrying out visual display on the prediction proposition information for the user to select.
2. The intelligent propositional analysis processing method according to claim 1, characterized in that:
step S302, determining the reference proposition number corresponding to the preceding X-bit proposition of the same type according to the proposition proportion weight value of the preceding X-bit proposition of the same type and the preset total number of the test paper propositions, including:
and multiplying the total number of the preset test paper propositions by the proposition proportion weighted value of each proposition of the same type to obtain the reference proposition number corresponding to each proposition of the same type.
3. Intelligent system of proposition analysis processing system of deep learning, its characterized in that includes:
the system comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for acquiring historical proposition data corresponding to a preset target subject, and determining appearance time information and appearance frequency information corresponding to the same type proposition from the historical proposition data so as to determine a comprehensive appearance rule evaluation value of the same type proposition;
the second determination module is used for optimizing the comprehensive appearance rule evaluation value of the same type of propositions according to the proposition schema of the historical test and the proposition information of the historical hotspots so as to determine the comprehensive appearance rule evaluation value after the optimization processing of the same type of propositions and determine proposition proportion weight values corresponding to the same type of propositions;
the third determining module is used for determining the predicted proposition information according to the comprehensive appearance rule evaluation value and proposition proportion weight value after the optimization processing of the same type proposition, and visually displaying the predicted proposition information for the user to select;
the generation module is used for receiving the prediction proposition information selected by the user and generating an examination paper corresponding to the prediction proposition information selected by the user;
wherein the first determining module is further configured to perform the following steps:
step S101, selecting historical proposition data corresponding to a preset target subject from a preset proposition historical database according to subject category information of the preset target subject;
step S102, according to historical examination timestamp information of the preset target subject, identifying the historical proposition data, and determining appearance time information and appearance frequency information corresponding to the same type of proposition in the historical proposition data;
step S103, determining a comprehensive appearance rule evaluation value A of the propositions of the same type according to the appearance time information, the appearance frequency information and the following formula (1):
in the above formula (1), m1 represents the total number of occurrences of all types of propositions of knowledge content corresponding to the same type of proposition determined according to the historical examination timestamp information in the historical proposition data, and m0 represents the total number of occurrences of the same type of proposition determined according to the historical examination timestamp information in the historical proposition data; in the historical proposition data, sequencing all types of propositions of the knowledge content corresponding to the same type of proposition according to the historical examination time stamp information and the sequence of examination time from front to back to form a proposition sequence of the knowledge content corresponding to the same type of proposition, wherein m0-1 represents the number of propositions spaced between two adjacent same type propositions of the m0-1 group in the proposition sequence; deltakRepresenting the appearance time interval between two adjacent propositions of the same type in the kth group, and T (delta m') representing the maximum value in the appearance time interval between two adjacent propositions of the same type in the m0-1 group; t (Δ m ") represents the minimum value in the appearance time interval between two adjacent propositions of the same type in the m0-1 group;
wherein the second determining module is further configured to perform the following steps:
step S201, according to the historical examination proposition schema, the historical hotspot proposition information and the following formula (2), optimizing the comprehensive appearance law evaluation value A of the same type proposition, so as to obtain the comprehensive appearance law evaluation value A' after the optimization processing of the same type proposition:
in the above formula (2), n represents the total number of times of the historic test determined based on the historic test time stamp information, siRepresenting the probability value of occurrence of corresponding propositions of the knowledge contents corresponding to the propositions of the same type in the test proposition schema corresponding to the ith historical test, wherein i is 1, 2, 3, …, n, piRepresenting the heat value of the knowledge content corresponding to the proposition of the same type in the hot proposition corresponding to the ith historical examination, wherein i is 1, 2, 3, … and n;
step S202, sorting the optimized comprehensive appearance rule evaluation values A' of all the propositions of the same type according to a descending order to obtain a proposition sorting sequence of the same type;
step S203, obtaining respective proposition keywords of each proposition of the same type in the proposition sorting sequence of the same type, and respectively determining a proposition proportion weight value corresponding to each proposition of the same type according to the following formula (3):
in the above formula (3), wjRepresenting proposition proportion weight values corresponding to jth proposition of the same type in the proposition sequencing sequence of the same type; m represents the total times of all question setting keywords included in the history question setting data corresponding to the preset target subject in all historical examinations; beta is ajShowing that the jth proposition keyword in the history proposition data corresponding to the preset target subject is at the placeThere is a corresponding total number of occurrences in the historic test,
representing the data bit ratio of all propositions containing the jth proposition keyword in the historical proposition data; the proposition keywords of the proposition of the same type comprise the type keywords of the proposition type and the keywords of the knowledge content corresponding to the proposition;
step S204, recording each proposition of the same type in the proposition sorting sequence and the corresponding proposition proportion weight value in a one-to-one correspondence manner to form a proposition prediction reference list;
wherein the third determining module is further configured to perform the following steps:
step S301, selecting same type propositions of front X bits from the proposition prediction reference list;
step S302, determining the reference proposition quantity corresponding to the previous X-bit proposition of the same type according to the proposition proportion weight value of the previous X-bit proposition of the same type and the preset total quantity of the test paper propositions;
step S303, aiming at each proposition of the same type in the first X-bit propositions: calling Y propositions corresponding to the propositions of the same type from a preset proposition library, wherein Y is equal to or more than the number of reference propositions corresponding to the propositions of the same type;
and S304, taking all the propositions corresponding to the same type propositions of the front X bits as prediction proposition information, and carrying out visual display on the prediction proposition information for the user to select.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010856601.8A CN112015780B (en) | 2020-08-24 | 2020-08-24 | Intelligent proposition analysis processing method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010856601.8A CN112015780B (en) | 2020-08-24 | 2020-08-24 | Intelligent proposition analysis processing method and system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112015780A CN112015780A (en) | 2020-12-01 |
| CN112015780B true CN112015780B (en) | 2021-06-01 |
Family
ID=73504220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010856601.8A Active CN112015780B (en) | 2020-08-24 | 2020-08-24 | Intelligent proposition analysis processing method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112015780B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321361A (en) * | 2019-06-15 | 2019-10-11 | 河南大学 | Test question recommendation and judgment method based on improved LSTM neural network model |
| CN110399541A (en) * | 2019-05-31 | 2019-11-01 | 平安国际智慧城市科技股份有限公司 | Topic recommended method, device and storage medium based on deep learning |
| CN110704510A (en) * | 2019-10-12 | 2020-01-17 | 中森云链(成都)科技有限责任公司 | User portrait combined question recommendation method and system |
| CN111444432A (en) * | 2020-04-01 | 2020-07-24 | 中国科学技术大学 | Domain-adaptive deep knowledge tracking and personalized exercise recommendation method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007264490A (en) * | 2006-03-29 | 2007-10-11 | National Univ Corp Shizuoka Univ | Information presentation evaluation system |
| US9869486B2 (en) * | 2015-01-27 | 2018-01-16 | Patrick Andrew Shiel | Method of reducing heating energy consumption in commercial buildings |
| CN105912614A (en) * | 2016-04-07 | 2016-08-31 | 重庆智考信息技术有限公司 | Personalization item bank learning system |
| CN110298514A (en) * | 2019-07-02 | 2019-10-01 | 陕西文都教育科技有限公司 | A kind of MBA math exam point prediction method based on time series models and Difference Between Coefficients of Variation method |
-
2020
- 2020-08-24 CN CN202010856601.8A patent/CN112015780B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110399541A (en) * | 2019-05-31 | 2019-11-01 | 平安国际智慧城市科技股份有限公司 | Topic recommended method, device and storage medium based on deep learning |
| CN110321361A (en) * | 2019-06-15 | 2019-10-11 | 河南大学 | Test question recommendation and judgment method based on improved LSTM neural network model |
| CN110704510A (en) * | 2019-10-12 | 2020-01-17 | 中森云链(成都)科技有限责任公司 | User portrait combined question recommendation method and system |
| CN111444432A (en) * | 2020-04-01 | 2020-07-24 | 中国科学技术大学 | Domain-adaptive deep knowledge tracking and personalized exercise recommendation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112015780A (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rubin | Multiple imputation | |
| CN107230174B (en) | Online interactive learning system and method based on network | |
| Graesser et al. | The construction of causal inferences while reading expository texts on science and technology | |
| CN109858797A (en) | The various dimensions information analysis of the students method of knowledge based network exact on-line education system | |
| CN110443427A (en) | Result prediction method and its system based on cognitive knowledge spectrum | |
| Wiberg et al. | Students’ self-reported background SES measures in TIMSS in relation to register SES measures when analysing students’ achievements in Sweden | |
| Mgala et al. | Data-driven intervention-level prediction modeling for academic performance | |
| Embretson | FOCUS ARTICLE: the second century of ability testing: some predictions and speculations | |
| Olshavsky et al. | An information processing probe into conjoint analysis | |
| Tatsuoka | Validation of cognitive sensitivity for item response curves | |
| Negeri et al. | Meta Analysis of Entrepreneurial Skill and Entrepreneurial Motivation On Business Performance: Mediating Role Of Strategic Leadership In Sme Sector Of Ethiopia | |
| Neumann et al. | Determinants of students' instructional evaluation: A comparison of four levels of academic areas-a | |
| Aji et al. | An implementation of C4. 5 classification algorithm to analyze student’s performance | |
| CN112015780B (en) | Intelligent proposition analysis processing method and system based on deep learning | |
| CN114492848B (en) | Self-adaptive learning system, method and application compatible with multiple learning models | |
| Zhang et al. | Package ‘R2MLwiN’ | |
| CN116342082A (en) | Knowledge graph-based post competence judging method, device, medium and equipment | |
| Chen et al. | A competition model for prediction of admission scores of colleges and universities in Chinese college entrance examination | |
| Gilliland et al. | Cost-benefit determinants of decision process and accuracy | |
| CN113919983A (en) | Test question portrait method, device, electronic equipment and storage medium | |
| Weaver et al. | Model specification for cognitive assessment of proportional reasoning | |
| KR100700376B1 (en) | Real-time quality measurement method of bibliographic database | |
| Chen | Selecting Potential Medical Professional Ability Students in Chinese NCEE by Predicting GPA through Data Mining | |
| CN110110969A (en) | A kind of space environment forecast product gross examines appraisal procedure and system automatically | |
| CN117932039B (en) | Interpretable text review method and system based on heuristic question-answer reasoning |
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 | ||
| PP01 | Preservation of patent right | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20221020 Granted publication date: 20210601 |