CN114818921B - Multi-dimensional book grading method, system, readable medium and equipment - Google Patents
Multi-dimensional book grading method, system, readable medium and equipment Download PDFInfo
- Publication number
- CN114818921B CN114818921B CN202210444525.9A CN202210444525A CN114818921B CN 114818921 B CN114818921 B CN 114818921B CN 202210444525 A CN202210444525 A CN 202210444525A CN 114818921 B CN114818921 B CN 114818921B
- Authority
- CN
- China
- Prior art keywords
- reading
- book
- historical
- reader
- grading
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a multi-dimensional book grading method, a system, a readable medium and equipment, wherein the method comprises the following steps: obtaining historical reading information of a reader, and calling a reading test question from a preset database; receiving test feedback of a reader on the reading test questions, constructing a feedback matrix, and determining the reading capacity of the reader based on a preset analysis model; based on the reading requirements of readers, calling a book set to be analyzed from a book database, respectively obtaining the book theme and the book abstract of each reading book in the book set to be analyzed, and determining the book reading difficulty of each reading book; establishing reading characteristics related to readers based on reading capacity and book reading difficulty, dividing the reading characteristics into a plurality of reading dimensions, and matching corresponding book grading modes; according to the multi-dimensional book grading mode, multi-dimensional grading is carried out, difficulty in advanced reading is achieved, reading experience can be improved, and reading requirements can be met.
Description
Technical Field
The invention relates to the technical field of book grading, in particular to a multi-dimensional book grading method, a multi-dimensional book grading system, a readable medium and multi-dimensional book grading equipment.
Background
The reading ability of each reader is different, and the receiving ability of each reader to the book to be read is also different, so that the reading requirements of different readers are also different, that is, the book needs to be read by different readers in a targeted manner.
In a traditional book grading system, books are graded rigidly through a manually set grading rule, for example, grading is performed through an age stage, and the grading is popular grading, but cannot well meet the reading experience and reading requirements of each reader.
Therefore, the invention provides a multi-dimensional book grading method, a multi-dimensional book grading system, a readable medium and multi-dimensional book grading equipment.
Disclosure of Invention
The invention provides a multi-dimensional book grading method, a multi-dimensional book grading system, a readable medium and multi-dimensional book grading equipment, which are used for determining reading capacity based on a preset analysis model by acquiring test questions of readers, and matching a multi-dimensional grading mode according to reading difficulty and reading capacity to realize reading experience and reading requirements of the readers.
The invention provides a multi-dimensional book grading method, which comprises the following steps:
obtaining historical reading information of a reader, and calling a reading test question from a preset database according to the historical reading information;
receiving test feedback of the reader on the reading test question, constructing a feedback matrix, and determining the reading capacity of the reader based on a preset analysis model;
calling a book set to be analyzed from a book database, respectively acquiring the book theme and the book abstract of each read book in the book set to be analyzed, and determining the book reading difficulty of each read book;
establishing reading characteristics related to the readers based on the reading capacity and the book reading difficulty, dividing the reading characteristics into a plurality of reading dimensions, and matching the book grading mode of each reading dimension;
and carrying out multi-dimensional grading on the book sets to be graded according to a multi-dimensional book grading mode, so as to realize difficulty advanced reading.
Preferably, the method for obtaining the historical reading information of the reader and calling the reading test question from the preset database according to the historical reading information comprises the following steps:
based on the historical reading information, acquiring the book type read by the reader, the reading time of each historical book, the reading progress of each historical book and the understanding degree of each chapter in each historical book;
classifying all history books based on the book categories, determining the number of the rows in the list according to the classified number, and establishing the number of the cells of the corresponding rows according to the number of the history books contained in the same category;
determining the reading absorption condition of the reader on the corresponding history book based on the reading time, the reading progress and the understanding degree;
acquiring historical reading validity of the corresponding historical book based on an absorption-validity database;
sorting all the historical reading effectiveness corresponding to the historical books of the same category, and sequentially placing the historical reading effectiveness in corresponding cells from large to small;
acquiring elements in a first column of cells in the list, constructing a first column vector based on the row attribute of each row in the list, acquiring elements in a last full element column of cells in the list, and constructing a tail column vector based on the row attribute of each row in the list;
dividing elements at the same level in the first column vector, respectively acquiring a maximum element and a minimum element in each level, and simultaneously dividing elements at the same level in the tail column vector, respectively acquiring a first element and a second element in each level;
determining book types of the history books corresponding to the positions of the maximum element and the minimum element, determining book types of the history books corresponding to the positions of the first element and the second element, calling reading test questions consistent with each type from a preset database based on the type determination result, and testing by the reader.
Preferably, the receiving of the test feedback of the reader to the reading test question and the constructing of the feedback matrix include:
performing picture scanning on a reading screen of the reader, and judging whether the current reading test question is received within a first preset time after the current reading test question is issued to a reading end of the reader;
if so, judging that a transmission interface for transmitting the current reading test question is normal, and counting a first response time of the reader to the current reading test question and corresponding first response content;
if the answer is not received, the current reading test question is received within a second preset time, and second answer time of the reader to the current reading test question and corresponding second answer content are counted; collecting a current log of a transmission interface corresponding to the current reading test subject and a historical log of the same reading test subject in normal transmission;
performing first analysis on the current log to obtain first operation data, and performing second analysis on the historical log to obtain second operation data;
comparing the first operating data with the second operating data with the same timestamp to obtain difference data, and extracting difference parameters at the same comparison time point;
drawing corresponding difference discrete points based on the difference parameters to obtain a difference discrete graph;
performing same-parameter outermost edge envelope drawing and innermost edge envelope drawing on the difference discrete graph;
determining the difference area corresponding to the same parameter based on the same parameter envelope drawing result;
determining the delay proportion corresponding to the same parameter from the parameter-area-proportion list according to the difference area of each same parameter;
acquiring a time delay adjustment factor based on all delay proportions;
determining a current receiving time point based on the second preset time and a normal receiving time point within the first preset time to obtain initial delay time;
adjusting the initial delay time based on the time delay adjustment factor to obtain the current delay time;
based on the current delay time, correcting the second response time of the current reading test question of the reader to obtain a third response time;
-taking the first reply time and first reply content as test feedback and the third reply time and second reply content as test feedback;
and acquiring a feedback vector of each test feedback, and sequentially inputting the feedback vector into the blank matrix to obtain a feedback matrix.
Preferably, determining the reading ability of the reader based on a preset analysis model includes:
and acquiring the row vectors in the feedback matrix, and sequentially inputting the row vectors into a preset analysis model to obtain the reading capability of the reader.
Preferably, the method for retrieving the book set to be analyzed from the book database, and respectively obtaining the book theme and the book abstract of each reading book in the book set to be analyzed, and determining the book reading difficulty of each reading book includes:
extracting a primary theme and a secondary theme of each reading book in the book set to be analyzed, and respectively acquiring a first abstract corresponding to the primary theme and a second abstract corresponding to the secondary theme;
acquiring a content deployment framework of each reading book to determine a first framework weight of each primary theme and a second framework weight of each secondary theme contained in the primary theme;
determining the same chapter framework weight based on the first framework weight and the second framework weight;
matching corresponding feature extraction modes based on the same chapter framework weight, and extracting features of a first abstract and a second abstract contained in the same chapter according to the feature extraction modes;
all the extracted features of the books read by the same book are obtained, and the book reading difficulty of the books read by the same book is obtained based on the reading difficulty analysis model.
Preferably, based on the reading ability and the book reading difficulty, establishing a reading characteristic related to the reader, dividing the reading characteristic into a plurality of reading dimensions, and matching a book grading mode of each reading dimension, including:
establishing a first relation between the reading capacity and the reading difficulty of each book and the book category of the corresponding reading book;
acquiring a preset capacity range and a preset difficulty range corresponding to each reading test subject, and further acquiring a corresponding comprehensive capacity range and a corresponding comprehensive difficulty range;
establishing a second relation between the comprehensive capacity range and the reading capacity and a third relation between the comprehensive difficulty range and the reading difficulty of each book and the book category of the reading book;
according to the relation constraint condition, carrying out preset constraint on the first relation, the second relation and the third relation, and establishing to obtain reading characteristics;
dividing the reading characteristics to obtain a plurality of reading dimensions;
and matching the unique dimension identification of each reading dimension from the identification-grading database to obtain a book grading mode corresponding to the unique dimension identification.
Preferably, the book set to be graded is graded in multiple dimensions according to a multi-dimensional book grading mode, so as to realize difficulty advanced reading, including:
after a book grading mode is obtained according to the unique dimension identification matching, a reading book subset of the category matched with the unique dimension identification is obtained;
determining a first reading difficulty of a first book in the reading book subset and a priority value of a first book category;
wherein Y is i A priority value indicating the ith first book; is a direct change i Representing a first reading difficulty of the ith first book;
a conversion coefficient indicating a category of the ith first book; e represents normal maturity, and the value is 2.6; sigma i The historical priority recommendation coefficient of the ith first book is represented; s. the i The current value of the single reading dimension corresponding to the unique dimension identification of the ith first book is represented; s i,1 Representing a left boundary value of a single reading dimension corresponding to the corresponding unique dimension identification; s i,2 A right bound value representing the corresponding unique dimension identification single reading dimension, wherein S i,2 Greater than S i,1 And S is i ∈[S i,1 ，S i,2 ]；
And based on all book grading modes, grading all priority values corresponding to each grading mode in size, completing sub-grading of the same reading book subset, further completing multi-dimensional grading of the book set to be graded, and realizing difficulty advanced reading.
The invention provides a multi-dimensional book grading system, which comprises:
the question calling module is used for acquiring historical reading information of readers and calling reading test questions from a preset database according to the historical reading information;
the ability determining module is used for receiving the test feedback of the reader to the reading test questions, constructing a feedback matrix, and determining the reading ability of the reader based on a preset analysis model;
the difficulty determining module is used for calling a book set to be analyzed from a book database, respectively obtaining the book theme and the book abstract of each read book in the book set to be analyzed, and determining the book reading difficulty of each read book;
the mode matching module is used for establishing reading characteristics related to the readers based on the reading capacity and the book reading difficulty, dividing the reading characteristics into a plurality of reading dimensions, and matching book grading modes of each reading dimension;
and the multidimensional grading module is used for carrying out multidimensional grading on the book sets to be graded according to a multidimensional book grading mode so as to realize difficulty advanced reading.
The invention provides a computer readable medium, storing a computer program which, when executed by a processor, causes the processor to perform the steps of any of the methods.
The invention provides a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of any of the methods.
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
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a multi-dimensional book ranking method according to an embodiment of the present invention;
FIG. 2 is a block diagram of a multi-dimensional book rating system in an embodiment of the present invention;
FIG. 3 is a diagram illustrating variance in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
In one embodiment, the present invention provides a multi-dimensional book ranking method, as shown in fig. 1, comprising:
step 1: obtaining historical reading information of a reader, and calling a reading test question from a preset database according to the historical reading information;
and 2, step: receiving test feedback of the reader on the reading test questions, constructing a feedback matrix, and determining the reading capacity of the reader based on a preset analysis model;
and step 3: based on the reading requirements of readers, calling a book set to be analyzed from a book database, respectively obtaining the book subject and the book abstract of each reading book in the book set to be analyzed, and determining the book reading difficulty of each reading book;
and 4, step 4: establishing reading characteristics related to the readers based on the reading capacity and the book reading difficulty, dividing the reading characteristics into a plurality of reading dimensions, and matching the book grading mode of each reading dimension;
and 5: and carrying out multi-dimensional grading on the book sets to be graded according to a multi-dimensional book grading mode, so as to realize difficulty advanced reading.
In this embodiment, the historical reading information refers to historical reading records of readers, such as parameters of reading categories, progress, time, and the like, the preset database is pre-constructed and includes more than one test question included in different columns, and as the test questions are more than one, a test vector is obtained by constructing a test response, i.e., a test feedback, for each test question of the reader with respect to the test question, and is further constructed as a feedback matrix, where, for example, the test vector 1 is: {1002}, test vector 2 is: {2001}, the corresponding feedback matrix is
In an embodiment, the predetermined analysis model is obtained by training a sample with test vectors of various combinations and corresponding capabilities.
In this embodiment, the book set to be analyzed is determined according to reading requirements, and then the book category that the reader wants to read can be determined.
In this embodiment, the book theme refers to the general abstract of the book to be read, and the book abstract refers to the abstract of each chapter in the book, so as to determine the reading difficulty, and the reading difficulty is determined according to the abstract of the book itself.
In this embodiment, the reading ability and the book reading difficulty are determined based on the consideration of the reader and the consideration of the book reading itself, that is, the reading difficulty of the reader for different types of books, so as to obtain different reading dimensions.
For example, the reading comprehension degrees of the reader on the category book 1 and the category book 2 are the same, at this time, a grading mode with the same reading comprehension degree and consistent with the two categories can be obtained, and the grading mode is mainly used for analyzing the difficulty, and the comprehension degree of each reading dimension is sequentially decreased, for example: the comprehension degree is decreased to perform a hierarchical division, and the book grading mode is to grade all books corresponding to the reading dimension, such as: the easily understood range corresponding to the easily understood reading dimension is marked between [0,1], and the not easily understood range corresponding to the not easily understood reading dimension is marked between [1,2], in this case, although the upper category book 1 and the category book 2 are both in the easily understood reading dimension, the specific reading understanding degree still varies, if, according to the corresponding book grading manner, the category book 1 can be in one grade, the category book 2 is in one grade, and the grade corresponding to the category book 1 is more easily understood than the grade corresponding to the category book 2, in this case, the difficulty level reading is: category book 1, category book 2.
In this embodiment, the multi-dimensional book classification mode is that each reading dimension corresponds to a classification mode, and the books included in the reading dimension are classified according to the classification mode in a difficulty-comprehension degree, so as to realize difficulty-level reading.
The beneficial effects of the above technical scheme are: the reading ability is determined based on the preset analysis model by obtaining the test questions of the reader, and the multi-dimensional grading mode is matched according to the reading difficulty and the reading characteristics constructed by the reading ability, so that the difficulty advanced reading is realized, the reading experience can be improved for the reader, and the reading requirement can be met.
In one embodiment, obtaining the historical reading information of a reader, and calling a reading test topic from a preset database according to the historical reading information includes:
based on the historical reading information, acquiring the book type read by the reader, the reading time of each historical book, the reading progress of each historical book and the understanding degree of each chapter in each historical book;
classifying all historical books based on the book categories, determining the number of list rows according to the classified number, and establishing the number of cells of corresponding rows according to the number of the historical books contained in the same category;
determining the reading absorption condition of the reader on the corresponding history book based on the reading time, the reading progress and the understanding degree;
acquiring historical reading validity of the corresponding historical book based on an absorption-validity database;
sorting all the historical reading effectiveness corresponding to the historical books of the same category, and sequentially placing the historical reading effectiveness in corresponding cells from large to small;
acquiring elements in a first column of cells in the list, constructing a first column vector based on the row attribute of each row in the list, acquiring elements in a last full element column of cells in the list, and constructing a tail column vector based on the row attribute of each row in the list;
dividing elements at the same level in the first column vector, respectively acquiring a maximum element and a minimum element in each level, and simultaneously dividing elements at the same level in the tail column vector, respectively acquiring a first element and a second element in each level;
determining the book types of the history books corresponding to the positions of the maximum element and the minimum element, determining the book types of the history books corresponding to the positions of the first element and the second element, and calling reading test titles consistent with each type from a preset database based on the type determination result for the test of the reader.
In this embodiment, the element is the historical reading validity, and the first column vector is constructed by the historical reading validity as the element.
In this embodiment, the elements at the same level refer to the historical reading validity at the same reading validity level, and further, the maximum element and the minimum element in the level are determined, that is, the maximum historical reading validity and the minimum historical reading validity in the level, and further, the position of the validity in the list is determined, that is, the book category corresponding to the position.
The element in the last full element column cell in the list means that each cell in the column has an element which can represent validity, but an element which can represent validity does not exist in a certain cell in the next column of the column, and the column is the last full element column, for the last first element, the largest element in the same level is referred to, and the second element, the smallest element in the same level is referred to.
In this embodiment, book classification means that books of the same category are classified into one category, for example, the number of classifications is 20, and the corresponding number of rows in the list is 20, at this time, if 5 books of the same category exist in the first row, at this time, 10 cells exist in the row, the number of rows in the list is greater than 10, and the number of cells in each row is greater than 3.
In this embodiment, the higher the reading progress and understanding degree, and the shorter the reading time, the better the corresponding reading absorption condition, and the absorption-effectiveness database includes the absorption condition and the standard value of the absorption condition is converted into the effectiveness data.
In this embodiment, the validity sizes are sorted to be sequentially placed in the cells, and the elements in the cells are the validity.
In this embodiment, the predetermined database includes the category and the test topic for the category.
The beneficial effects of the above technical scheme are: through books category and the books quantity of the same category, establish the list, and place the cell in proper order through the validity size sequencing in listing, and then through drawing the first rank and the tail in the element, and through drawing with the element of rank, obtain last test topic, guarantee can carry out effective test to reader's reading ability, improve follow-up book classification efficiency, improve indirectly and read experience sense.
In one embodiment, receiving the test feedback of the reader on the reading test question, and constructing a feedback matrix, includes:
performing picture scanning on a reading screen of the reader, and judging whether the current reading test question is received within a first preset time after the current reading test question is issued to a reading end of the reader;
if so, judging that a transmission interface for transmitting the current reading test question is normal, and counting a first response time of the reader to the current reading test question and corresponding first response content;
if the answer is not received, the current reading test question is received within a second preset time, and second answer time of the reader to the current reading test question and corresponding second answer content are counted;
collecting a current log of a transmission interface corresponding to the current reading test subject and a historical log of the same reading test subject in normal transmission;
performing first analysis on the current log to obtain first operation data, and performing second analysis on the historical log to obtain second operation data;
comparing the first operating data with the second operating data with the same timestamp to obtain difference data, and extracting difference parameters at the same comparison time point;
drawing corresponding difference discrete points based on the difference parameters to obtain a difference discrete graph;
performing same-parameter outermost edge envelope drawing and innermost edge envelope drawing on the difference discrete graph;
determining a difference area corresponding to the same parameter based on the same parameter envelope drawing result;
determining the delay proportion corresponding to the same parameter from the parameter-area-proportion list according to the difference area of each same parameter;
acquiring a time delay adjustment factor based on all delay proportions;
determining a current receiving time point based on the second preset time and a normal receiving time point within the first preset time to obtain initial delay time;
adjusting the initial delay time based on the time delay adjusting factor to obtain the current delay time;
based on the current delay time, correcting the second response time of the current reading test question of the reader to obtain a third response time;
taking the first reply time and first reply content as test feedback and the third reply time and second reply content as test feedback;
and acquiring a feedback vector of each test feedback, and sequentially inputting the feedback vector into the blank matrix to obtain a feedback matrix.
In this embodiment, after the reading test question is issued to the reader, and when the reader receives the reading test question and starts to answer, the reader calculates the answer time and starts to count the answer time, however, in the counting process, there may be a situation that the interface delays receiving the test question, so that by comparing the log of the test question received by the interface with the log in the normal case (in the case that no delay occurs), a delay adjustment factor is obtained.
In this embodiment, the frame scan is mainly used to capture whether the reading screen receives a reading test question, and the transmission interface refers to a receiving port through which the reading screen can receive the test question.
In this embodiment, the log is analyzed mainly to obtain the operation data, and the history log refers to a log generated when the test title can be normally received within the first preset time.
In this embodiment, the timestamp comparison is mainly to determine existing difference data, such as network difference data, and further obtain network difference parameters of the timestamp at the same time point, because the network operation data exists in the whole log process, as shown in fig. 3, for example, difference parameter 1 exists, and then a difference discrete point is obtained after comparing with normal parameter 1, and further a difference discrete graph is obtained, where a1 represents an outermost edge envelope, and a2 represents an innermost edge envelope.
In this embodiment, the difference area is an area formed by an envelope determined by the same parameter, and the parameter-area-ratio list includes a parameter type, a difference area, and a delay ratio, and when the delay ratio is larger, the corresponding delay adjustment factor is larger, and the delay adjustment factor is mainly used for adjusting the initial delay time.
In this embodiment, for example, the initial delay time is 10s, the corresponding delay adjustment factor is 1.2, and the corresponding current delay time is 12s.
The beneficial effects of the above technical scheme are: the time for receiving the test questions by the reading end is judged, and then whether the transmission interface is normal or not is judged subsequently, so that a time delay adjusting factor is obtained, the second response time is repaired, the rationality of test feedback is guaranteed, the problem that the feedback efficiency is low due to the response time is effectively avoided, and reading experience is reduced.
In one embodiment, determining the reading ability of the reader based on a preset analysis model includes:
and acquiring the row vectors in the feedback matrix, and sequentially inputting the row vectors into a preset analysis model to obtain the reading capability of the reader.
In this embodiment, the row vector is also referred to as a feedback vector, and is obtained by training based on different combined feedback vectors and matching reading ability when the analysis model is preset.
The beneficial effects of the above technical scheme are: the matrix is analyzed through the preset analysis model, reading capacity is convenient to obtain, subsequent grading is convenient, and reading experience is indirectly improved.
In one embodiment, retrieving a book set to be analyzed from a book database, and respectively obtaining a book theme and a book abstract of each reading book in the book set to be analyzed, and determining a book reading difficulty of each reading book, includes:
extracting a primary theme and a secondary theme of each reading book in the book set to be analyzed, and respectively acquiring a first abstract corresponding to the primary theme and a second abstract corresponding to the secondary theme;
acquiring a content deployment framework of each reading book to determine a first framework weight of each primary theme and a second framework weight of each secondary theme contained in the primary theme;
determining the same chapter framework weight based on the first framework weight and the second framework weight;
matching corresponding feature extraction modes based on the same chapter framework weight, and extracting features of a first abstract and a second abstract contained in the same chapter according to the feature extraction modes;
all the extraction features of the books read by the same book are obtained, and the book reading difficulty of the books read by the same book is obtained based on the reading difficulty analysis model.
In this embodiment, the primary topic refers to the overall topic of the time section, and the secondary topic refers to the overall topic of the sections included in the section, so as to extract the corresponding abstract.
In this embodiment, the content deployment framework refers to the content layout of the corresponding book, and the framework weights corresponding to different chapters and subsections under different chapters are different, so that the framework weight of the same chapter needs to be determined.
In this embodiment, the feature extraction method refers to extracting features in a manner of matching with weights, and the larger the weight is, the more detailed the features that need to be extracted corresponding to the matched feature extraction method need to be.
In this embodiment, the reading difficulty analysis model is pre-trained.
The beneficial effects of the above technical scheme are: effective features can be extracted by determining the weights of the same chapter framework and matching the feature extraction mode, and then book reading difficulty is obtained based on the model, so that a foundation is provided for subsequently acquiring a grading mode.
In one embodiment, establishing a reading characteristic related to the reader based on the reading ability and the book reading difficulty, dividing the reading characteristic into a plurality of reading dimensions, and matching a book grading mode of each reading dimension, includes:
establishing a first relation between the reading capacity and the reading difficulty of each book and the book category of the corresponding reading book;
acquiring a preset capacity range and a preset difficulty range corresponding to each reading test subject, and further acquiring a corresponding comprehensive capacity range and a corresponding comprehensive difficulty range;
establishing a second relation between the comprehensive capacity range and the reading capacity and a third relation between the comprehensive difficulty range and the reading difficulty of each book and the book category of the reading book;
according to the relation constraint condition, carrying out preset constraint on the first relation, the second relation and the third relation, and establishing to obtain reading characteristics;
dividing the reading characteristics to obtain a plurality of reading dimensions;
and matching the unique dimension identification of each reading dimension from the identification-grading database to obtain a book grading mode corresponding to the unique dimension identification.
In this embodiment, the preset ability range and the preset difficulty range of the same reading test item are represented by numerical values, for example, the preset ability range corresponding to the test item 1 is [0,3] and the preset difficulty range is [5,6], at this time, the reading ability of the reader is 3, the book reading difficulty of the reading book 1 is 6, the book category of the reading book 1 is 01, and the first relationship is: 3- (1, 6) - (1, 01); the second relation is as follows: 3- (0, 3), the third relation is 6- (5, 6, 01), at this time, the reading state of the reader for the book in the category is judged through the relation constraint condition, since the reading capability 3 is the maximum capability value of the preset capability range, the reading difficulty 6 of the book is the maximum difficulty value of the preset difficulty range, and at this time, the book is in a completely relaxed state, that is, the reading book in the category 01 is set to be the easy-to-understand reading characteristic, and there are the more-to-understand reading characteristic, the difficult-to-understand reading characteristic and the difficult-to-understand reading characteristic, and the understanding of each degree can be regarded as one dimension, so as to obtain a plurality of reading dimensions.
In this embodiment, the identifier-hierarchy database includes different unique dimension identifiers and corresponding hierarchical manners, such as: the book 1 (easy to understand) and the book 2 (easy to understand) exist, at this time, the book 1 and the book 2 correspond to the same reading dimension, the unique dimension identification of the reading dimension at this time identifies the easily understood identification, and further, a grading mode is obtained from the identification-grading library, and the book 1 and the book 2 are taken as the same grading.
In this embodiment, the reading characteristics can be effectively divided according to the understanding degree by the first relationship, the second relationship, and the third relationship, so as to obtain reading books with different understanding degrees, and the unique identifier of the reading dimension may include: the degree of understanding and all categories corresponding to the same degree of understanding are identified.
For example, the unique identification of the reading dimension includes: the degree of understanding, category 01, 02, is included, and the corresponding book ranking can be obtained according to the identification.
The beneficial effects of the above technical scheme are: by establishing different first relation, second relation and third relation, a plurality of unique dimension identifications can be effectively determined and obtained, and then a book grading mode corresponding to the dimension is obtained, so that the reading pertinence of the reader is guaranteed.
In one embodiment, the book set to be graded is graded in multiple dimensions according to a multi-dimensional book grading mode, so as to realize difficulty-level reading, including:
after a book grading mode is obtained according to the unique dimension identification matching, a reading book subset of the category matched with the unique dimension identification is obtained;
determining a first reading difficulty of a first book in the reading book subset and a priority value of a first book category;
wherein, Y i A priority value indicating the ith first book; is a direct change i Indicating the first reading difficulty of the ith first book;
a conversion coefficient indicating a category of an ith book; e represents normal mature, and the value is 2.6; sigma i The historical priority recommendation coefficient of the ith first book is represented; s i The current value of the single reading dimension corresponding to the unique dimension identification of the ith first book is represented; s i,1 Representing a left boundary value of a single reading dimension corresponding to the corresponding unique dimension identification; s i,2 A right bound value representing a corresponding unique dimension identification single reading dimension, wherein S i,2 Greater than S i,1 And S is i ∈[S i,1 ，S i,2 ]；
And based on all book grading modes, grading all priority values corresponding to each grading mode in size, completing sub-grading of the same reading book subset, further completing multi-dimensional grading of the book set to be graded, and realizing difficulty advanced reading.
In this embodiment, the value range of the conversion coefficient is [0.9,1], the more frequent the history recommendation is, the higher the corresponding priority recommendation coefficient is, and the value range is [0,1].
In this embodiment, the calculation of the priority value is to determine the ranking of each reading book matched to the unique dimension identifier, for example, the reading book corresponding to the unique dimension identifier includes: the books 1,2, 3, 4, 5 and 6 are classified according to the priority value, so that the books 1, 3 and 4 are in one level, and the books 2, 5 and 6 are in one level, wherein the books 1, 3 and 4 are easier to understand than the books 2, 5 and 6.
At this time, the grading processing of the book subset corresponding to the unique dimension identification can be realized.
In this embodiment, the multidimensional ranking means that all the unique reading identifiers are completed in a corresponding ranking manner.
The beneficial effects of the above technical scheme are: the book subsets are read in a matching mode according to the unique dimension identification, the priority value is calculated through the difficulty and the category, multi-dimension grading is achieved through a book grading mode, difficulty advanced reading is achieved, and reading experience of readers is improved indirectly.
In one embodiment, the present invention provides a multi-dimensional book rating system, as shown in FIG. 2, comprising:
the question calling module is used for acquiring historical reading information of readers and calling reading test questions from a preset database according to the historical reading information;
the ability determining module is used for receiving test feedback of the reader on the reading test question, constructing a feedback matrix and determining the reading ability of the reader based on a preset analysis model;
the difficulty determining module is used for calling a book set to be analyzed from a book database, respectively obtaining the book theme and the book abstract of each read book in the book set to be analyzed, and determining the book reading difficulty of each read book;
the mode matching module is used for establishing reading characteristics related to the readers based on the reading capacity and the book reading difficulty, dividing the reading characteristics into a plurality of reading dimensions, and matching book grading modes of each reading dimension;
and the multidimensional grading module is used for carrying out multidimensional grading on the book sets to be graded according to a multidimensional book grading mode so as to realize difficulty advanced reading.
The beneficial effects of the above technical scheme are: the reading ability is determined based on the preset analysis model by obtaining the test questions of the reader, and the multi-dimensional grading mode is matched according to the reading difficulty and the reading characteristics constructed by the reading ability, so that the difficulty advanced reading is realized, the reading experience can be improved for the reader, and the reading requirement can be met.
In one embodiment, a computer device is proposed, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
step 1: obtaining historical reading information of a reader, and calling a reading test question from a preset database according to the historical reading information;
step 2: receiving test feedback of the reader on the reading test questions, constructing a feedback matrix, and determining the reading capacity of the reader based on a preset analysis model;
and 3, step 3: based on the reading requirements of readers, calling a book set to be analyzed from a book database, respectively obtaining the book subject and the book abstract of each reading book in the book set to be analyzed, and determining the book reading difficulty of each reading book;
and 4, step 4: establishing reading characteristics related to the readers based on the reading capacity and the book reading difficulty, dividing the reading characteristics into a plurality of reading dimensions, and matching the book grading mode of each reading dimension;
and 5: and carrying out multi-dimensional grading on the book sets to be graded according to a multi-dimensional book grading mode, so as to realize difficulty advanced reading.
In one embodiment, a computer-readable storage medium is proposed, in which a computer program is stored which, when executed by a processor, causes the processor to carry out the steps of:
step 1: obtaining historical reading information of a reader, and calling a reading test question from a preset database according to the historical reading information;
step 2: receiving test feedback of the reader on the reading test question, constructing a feedback matrix, and determining the reading capacity of the reader based on a preset analysis model;
and step 3: based on the reading requirements of readers, calling a book set to be analyzed from a book database, respectively obtaining the book subject and the book abstract of each reading book in the book set to be analyzed, and determining the book reading difficulty of each reading book;
and 4, step 4: establishing reading characteristics related to the readers based on the reading capacity and the book reading difficulty, dividing the reading characteristics into a plurality of reading dimensions, and matching the book grading mode of each reading dimension;
and 5: and carrying out multi-dimensional grading on the book sets to be graded according to a multi-dimensional book grading mode, so as to realize difficulty advanced reading.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims. Please enter the implementation content part.
Claims (9)
1. A multi-dimensional book grading method is characterized by comprising the following steps:
obtaining historical reading information of a reader, and calling a reading test question from a preset database according to the historical reading information;
receiving test feedback of the reader on the reading test question, constructing a feedback matrix, and determining the reading capacity of the reader based on a preset analysis model;
based on the reading requirements of readers, calling a book set to be analyzed from a book database, respectively obtaining the book subject and the book abstract of each reading book in the book set to be analyzed, and determining the book reading difficulty of each reading book;
establishing reading characteristics related to the readers based on the reading capacity and the book reading difficulty, dividing the reading characteristics into a plurality of reading dimensions, and matching the book grading mode of each reading dimension;
performing multi-dimensional grading on the book sets to be graded according to a multi-dimensional book grading mode to realize difficulty advanced reading;
the method includes the steps of obtaining historical reading information of readers, and calling reading test questions from a preset database according to the historical reading information, and includes:
based on the historical reading information, acquiring the book type read by the reader, the reading time of each historical book, the reading progress of each historical book and the understanding degree of each chapter in each historical book;
classifying all history books based on the book categories, determining the number of the rows in the list according to the classified number, and establishing the number of the cells of the corresponding rows according to the number of the history books contained in the same category;
determining the reading absorption condition of the reader on the corresponding history book based on the reading time, the reading progress and the understanding degree;
acquiring historical reading validity of the corresponding historical book based on an absorption-validity database;
sorting all the historical reading effectiveness corresponding to the historical books of the same category, and sequentially placing the historical reading effectiveness in corresponding cells from large to small;
acquiring elements in a first column of cells in the list, constructing a first column vector based on the row attribute of each row in the list, acquiring elements in a last full element column of cells in the list, and constructing a tail column vector based on the row attribute of each row in the list;
dividing elements at the same level in the first column vector, respectively acquiring a maximum element and a minimum element in each level, and simultaneously dividing elements at the same level in the tail column vector, respectively acquiring a first element and a second element in each level;
determining the book types of the history books corresponding to the positions of the maximum element and the minimum element, determining the book types of the history books corresponding to the positions of the first element and the second element, and calling reading test titles consistent with each type from a preset database based on the type determination result for the test of the reader.
2. The multi-dimensional book grading method of claim 1, wherein receiving the test feedback of the reader on the reading test question, and constructing a feedback matrix comprises:
performing picture scanning on a reading screen of the reader, and judging whether the current reading test question is received within a first preset time after the current reading test question is issued to a reading end of the reader;
if so, judging that a transmission interface for transmitting the current reading test question is normal, and counting a first response time of the reader to the current reading test question and corresponding first response content;
if the answer is not received, the current reading test question is received within a second preset time, and second answer time of the reader to the current reading test question and corresponding second answer content are counted;
collecting a current log of a transmission interface corresponding to the current reading test subject and a historical log of the same reading test subject in normal transmission;
performing first analysis on the current log to obtain first operation data, and performing second analysis on the historical log to obtain second operation data;
comparing the first operating data with the second operating data with the same timestamp to obtain difference data, and extracting difference parameters at the same comparison time point;
drawing corresponding difference discrete points based on the difference parameters to obtain a difference discrete graph;
performing the drawing of the outermost edge envelope and the drawing of the innermost edge envelope of the same parameter on the difference discrete graph;
determining the difference area corresponding to the same parameter based on the same parameter envelope drawing result;
determining the delay proportion corresponding to the same parameter from the parameter-area-proportion list according to the difference area of each same parameter;
acquiring a time delay adjustment factor based on all delay proportions;
determining a current receiving time point based on the second preset time and a normal receiving time point within the first preset time to obtain initial delay time;
adjusting the initial delay time based on the time delay adjusting factor to obtain the current delay time;
correcting the second response time of the current reading test question by the reader based on the current delay time to obtain a third response time;
taking the first reply time and first reply content as test feedback and the third reply time and second reply content as test feedback;
and acquiring a feedback vector of each test feedback, and sequentially inputting the feedback vector into the blank matrix to obtain a feedback matrix.
3. The multi-dimensional book rating method of claim 1, wherein determining the reading ability of the reader based on a predetermined analysis model comprises:
and acquiring the row vectors in the feedback matrix, and sequentially inputting the row vectors into a preset analysis model to obtain the reading capability of the reader.
4. The multi-dimensional book grading method according to claim 1, wherein the step of retrieving a book set to be analyzed from a book database, and respectively obtaining a book theme and a book abstract of each reading book in the book set to be analyzed, and determining the book reading difficulty of each reading book comprises the steps of:
extracting a primary theme and a secondary theme of each reading book in the book set to be analyzed, and respectively acquiring a first abstract corresponding to the primary theme and a second abstract corresponding to the secondary theme;
acquiring a content deployment framework of each reading book to determine a first framework weight of each primary theme and a second framework weight of each secondary theme contained in the primary theme;
determining the same chapter framework weight based on the first framework weight and the second framework weight;
matching corresponding feature extraction modes based on the same chapter framework weight, and extracting features of a first abstract and a second abstract contained in the same chapter according to the feature extraction modes;
all the extracted features of the books read by the same book are obtained, and the book reading difficulty of the books read by the same book is obtained based on the reading difficulty analysis model.
5. The multi-dimensional book grading method of claim 1, wherein based on the reading ability and the book reading difficulty, establishing a reading characteristic related to the reader, dividing the reading characteristic into a plurality of reading dimensions, and matching a book grading manner of each reading dimension, comprises:
establishing a first relation between the reading capacity and the reading difficulty of each book and the book category of the corresponding reading book;
acquiring a preset capacity range and a preset difficulty range corresponding to each reading test subject, and further acquiring a corresponding comprehensive capacity range and a corresponding comprehensive difficulty range;
establishing a second relation between the comprehensive capacity range and the reading capacity and a third relation between the comprehensive difficulty range and the reading difficulty of each book and the book category of the reading book;
according to the relation constraint condition, carrying out preset constraint on the first relation, the second relation and the third relation, and establishing to obtain reading characteristics;
dividing the reading characteristics to obtain a plurality of reading dimensions;
and matching the unique dimension identification of each reading dimension from the identification-grading database to obtain a book grading mode corresponding to the unique dimension identification.
6. The multi-dimensional book grading method of claim 1, wherein the book set to be graded is multi-dimensionally graded in a multi-dimensional book grading manner to achieve difficulty-advanced reading, comprising:
after a book grading mode is obtained according to the unique dimension identification matching, a reading book subset of the category matched with the unique dimension identification is obtained;
determining a first reading difficulty of a first book in the reading book subset and a priority value of a first book category;
wherein, Y i Denotes the ith bookA priority value of the first book; is a direct change i Indicating the first reading difficulty of the ith first book;
a conversion coefficient indicating a category of an ith book; e represents a constant, and the value is 2.6; sigma i The historical priority recommendation coefficient of the ith first book is represented; s. the i The current value of the single reading dimension corresponding to the unique dimension identification of the ith first book is represented; s i,1 Representing a left boundary value of a single reading dimension corresponding to the corresponding unique dimension identification; s i,2 A right bound value representing a corresponding unique dimension identification single reading dimension, wherein S i,2 Greater than S i,1 And S is i ∈[S i,1 ，S i,2 ]；
And based on all book grading modes, grading all priority values corresponding to each grading mode in size, completing sub-grading of the same reading book subset, further completing multi-dimensional grading of the book set to be graded, and realizing difficulty advanced reading.
7. A multi-dimensional book rating system, comprising:
the question calling module is used for acquiring historical reading information of a reader and calling a reading test question from a preset database according to the historical reading information;
the ability determining module is used for receiving test feedback of the reader on the reading test question, constructing a feedback matrix and determining the reading ability of the reader based on a preset analysis model;
the difficulty determining module is used for calling a book set to be analyzed from a book database, respectively obtaining the book theme and the book abstract of each read book in the book set to be analyzed, and determining the book reading difficulty of each read book;
the mode matching module is used for establishing reading characteristics related to the readers based on the reading capacity and the book reading difficulty, dividing the reading characteristics into a plurality of reading dimensions, and matching book grading modes of each reading dimension;
the multi-dimensional grading module is used for carrying out multi-dimensional grading on the book sets to be graded according to a multi-dimensional book grading mode so as to realize difficulty advanced reading;
wherein, the title calling module is used for:
based on the historical reading information, acquiring the book type read by the reader, the reading time of each historical book, the reading progress of each historical book and the understanding degree of each chapter in each historical book;
classifying all history books based on the book categories, determining the number of the rows in the list according to the classified number, and establishing the number of the cells of the corresponding rows according to the number of the history books contained in the same category;
determining the reading absorption condition of the reader on the corresponding history book based on the reading time, the reading progress and the understanding degree;
acquiring historical reading validity of the corresponding historical book based on an absorption-validity database;
sorting all the historical reading effectiveness corresponding to the historical books of the same category, and sequentially placing the historical reading effectiveness in corresponding cells from large to small;
acquiring elements in a first column of cells in the list, constructing a first column vector based on the row attribute of each row in the list, acquiring elements in a last full element column of cells in the list, and constructing a tail column vector based on the row attribute of each row in the list;
dividing elements at the same level in the first column vector, respectively acquiring a maximum element and a minimum element in each level, and simultaneously dividing elements at the same level in the tail column vector, respectively acquiring a first element and a second element in each level;
determining the book types of the history books corresponding to the positions of the maximum element and the minimum element, determining the book types of the history books corresponding to the positions of the first element and the second element, and calling reading test titles consistent with each type from a preset database based on the type determination result for the test of the reader.
8. A computer-readable medium, in which a computer program is stored which, when being executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 6.
9. A computer device comprising a memory and a processor, characterized in that the memory stores a computer program which, when executed by the processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210444525.9A CN114818921B (en) | 2022-04-26 | 2022-04-26 | Multi-dimensional book grading method, system, readable medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210444525.9A CN114818921B (en) | 2022-04-26 | 2022-04-26 | Multi-dimensional book grading method, system, readable medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114818921A CN114818921A (en) | 2022-07-29 |
| CN114818921B true CN114818921B (en) | 2023-04-07 |
Family
ID=82508087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210444525.9A Active CN114818921B (en) | 2022-04-26 | 2022-04-26 | Multi-dimensional book grading method, system, readable medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114818921B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114971976A (en) * | 2022-08-01 | 2022-08-30 | 北京思源智通科技有限责任公司 | Intelligent guide system and method for improving campus reading literacy |
| CN115577152B (en) * | 2022-09-29 | 2024-01-26 | 深圳市科图自动化新技术有限公司 | Online book borrowing management system based on data analysis |
| CN116796045B (en) * | 2023-08-23 | 2023-11-10 | 北京人天书店集团股份有限公司 | Multi-dimensional book grading method, system and readable medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107657559A (en) * | 2017-08-25 | 2018-02-02 | 北京享阅教育科技有限公司 | A kind of Chinese reading capability comparison method and system |
| CN112347239A (en) * | 2020-11-12 | 2021-02-09 | 方正株式(武汉)科技开发有限公司 | Book matching method, system, server and storage medium based on big data |
| CN112559866A (en) * | 2020-12-16 | 2021-03-26 | 郑州工程技术学院 | College book reading recommendation method, device, equipment and storage medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070292826A1 (en) * | 2006-05-18 | 2007-12-20 | Scholastic Inc. | System and method for matching readers with books |
| US10032208B2 (en) * | 2015-12-15 | 2018-07-24 | International Business Machines Corporation | Identifying recommended electronic books with detailed comparisons |
| CN109523194B (en) * | 2018-12-14 | 2021-06-01 | 深圳市小柠檬教育科技有限公司 | Chinese reading ability evaluation method and device and readable storage medium |
| CN109977408A (en) * | 2019-03-27 | 2019-07-05 | 西安电子科技大学 | The implementation method of English Reading classification and reading matter recommender system based on deep learning |
| CN110046304B (en) * | 2019-04-18 | 2022-12-13 | 腾讯科技（深圳）有限公司 | User recommendation method and device |
| CN110930275A (en) * | 2019-12-12 | 2020-03-27 | 周玉萍 | Reading training learning system based on mobile terminal |
| CN111667171A (en) * | 2020-06-04 | 2020-09-15 | 广州博高信息科技有限公司 | Big data-based group reading behavior analysis method, device, equipment and medium |
| CN112733059A (en) * | 2021-01-12 | 2021-04-30 | 深圳市小熊创新科技有限公司 | Intelligent reading tracking evaluation method, system, terminal and storage medium |
| CN113052730A (en) * | 2021-02-23 | 2021-06-29 | 杭州一亩教育科技有限公司 | Child grading reading assisting method and system for self-help reading ability acquisition |
-
2022
- 2022-04-26 CN CN202210444525.9A patent/CN114818921B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107657559A (en) * | 2017-08-25 | 2018-02-02 | 北京享阅教育科技有限公司 | A kind of Chinese reading capability comparison method and system |
| CN112347239A (en) * | 2020-11-12 | 2021-02-09 | 方正株式(武汉)科技开发有限公司 | Book matching method, system, server and storage medium based on big data |
| CN112559866A (en) * | 2020-12-16 | 2021-03-26 | 郑州工程技术学院 | College book reading recommendation method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114818921A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114818921B (en) | Multi-dimensional book grading method, system, readable medium and equipment | |
| CN109902753B (en) | User recommendation model training method and device, computer equipment and storage medium | |
| CN111783840A (en) | Visualization method and device for random forest model and storage medium | |
| CN111444952A (en) | Method and device for generating sample identification model, computer equipment and storage medium | |
| CN112700325A (en) | Method for predicting online credit return customers based on Stacking ensemble learning | |
| CN112396428B (en) | User portrait data-based customer group classification management method and device | |
| CN114282054A (en) | Video recommendation method and device, computer equipment and storage medium | |
| CN111126426A (en) | Feature selection method and device, computer equipment and storage medium | |
| CN112446441B (en) | Model training data screening method, device, equipment and storage medium | |
| WO2019223104A1 (en) | Method and apparatus for determining event influencing factors, terminal device, and readable storage medium | |
| CN112699923A (en) | Document classification prediction method and device, computer equipment and storage medium | |
| CN114663002A (en) | Method and equipment for automatically matching performance assessment indexes | |
| CN115881238A (en) | Model training method, transformer fault diagnosis method and related device | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| CN114648680A (en) | Training method, device, equipment, medium and program product of image recognition model | |
| CN110765351A (en) | Target user identification method and device, computer equipment and storage medium | |
| CN113822336A (en) | Cloud hard disk fault prediction method, device and system and readable storage medium | |
| CN111708810B (en) | Model optimization recommendation method and device and computer storage medium | |
| CN112883267A (en) | Data heat degree statistical method and device based on deep learning | |
| CN110888977B (en) | Text classification method, apparatus, computer device and storage medium | |
| CN112232951B (en) | Credit evaluation method, device, equipment and medium based on multi-dimensional cross feature | |
| CN114021716A (en) | Model training method and system and electronic equipment | |
| CN113590673A (en) | Data heat degree statistical method based on block chain deep learning | |
| CN114154548A (en) | Sales data sequence classification method and device, computer equipment and storage medium | |
| CN113221995A (en) | Data classification method, equipment and device based on semi-supervised deep classification algorithm |
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 |