CN109684436A - A kind of correlating method of knowledge and application - Google Patents
A kind of correlating method of knowledge and application Download PDFInfo
- Publication number
- CN109684436A CN109684436A CN201811459521.8A CN201811459521A CN109684436A CN 109684436 A CN109684436 A CN 109684436A CN 201811459521 A CN201811459521 A CN 201811459521A CN 109684436 A CN109684436 A CN 109684436A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- relevance
- different
- learning
- tester
- 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.)
- Granted
Links
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The present invention discloses correlating method and the application of a kind of knowledge, wherein the correlating method of knowledge includes: to obtain two different knowledge in same knowledge hierarchy；Several testers are obtained in the test data of two different knowledge；According to test data, every tester is obtained to the learning performance of two different knowledge；According to every tester to the learning performance of two different knowledge, the relevance between two different knowledge is determined.The present invention is by several testers to the learning performance of two different knowledge in same knowledge hierarchy, the relevance between two different knowledge can be obtained, it realizes and the relevance of the two uncertain knowledge of incidence relation under same knowledge hierarchy is excavated, convenient for the learning management to different two knowledge.
Description
Technical field
The present invention relates to learning management fields, and in particular to a kind of correlating method of knowledge and application.
Background technique
With the gradual improvement of people's living standard, parent and teacher increasingly pay attention to the study situation of student, meanwhile,
The learning system and individualized content that can be interacted with learner are recommended or the service systems such as adaptive learning are also met the tendency of
And it gives birth to.Due between different a variety of knowledge there is mutual dependence and incidence relation, different knowledge are carried out
Association analysis is conducive to learner and improves learning ability, and enhancing learning efficiency, and can use it and recommend to learner
Other knowledge.
The correlating method of knowledge traditional at present mainly rule of thumb using education expert manually knows all kinds of differences
Know content to be associated.Obviously, rule of thumb carrying out manual association study largely will increase disappearing for human resources
Consumption, it is time-consuming and laborious.Alternatively, the different learning Contents that can also be independently selected according to user carry out knowledge connection.Autonomous selection is logical
It is often to be based on Frequent Pattern Mining in conjunction with Aporior algorithm, FP-Tree algorithm to be associated knowledge, so user carries out frequency
The relevance of the corresponding knowledge of the learning Content of numerous selection can be very high.Therefore, which, which is only applicable to user, independently to select
The case where learning Content.However, for the knowledge learning that user can not independently select, such as the study of teaching material, due to textbook content
Every partial knowledge require to learn, therefore every partial knowledge can all frequently occur, herein under the premise of, utilize above-mentioned by autonomous choosing
The association mode of learning selected just can not therefrom know the relevance between different knowledge.
Summary of the invention
Therefore, technical problems to be solved of the embodiment of the present invention are the correlating method of knowledge in the prior art by people
Power association causes human resources consumption big, time-consuming and laborious, or by it is traditional based on Frequent Pattern Mining knowledge connection in the way of
The problem of can not knowing the relevance between the identical different knowledge of the degree of being frequent.
For this purpose, the embodiment of the invention provides following technical solutions:
The embodiment of the present invention provides a kind of correlating method of knowledge, includes the following steps:
Obtain two different knowledge in same knowledge hierarchy；
Several testers are obtained in the test data of described two different knowledge；
According to the test data, every tester is obtained to the learning performance of described two different knowledge；
According to every tester to the learning performance of described two different knowledge, determine described two different knowledge it
Between relevance.
Optionally, after the step of relevance between described two different knowledge of the determination further include:
Relevance between described two different knowledge is corrected.
Optionally, the step of relevance between described two different knowledge being corrected further include:
Extract the text feature and semantic feature of each knowledge；
According to the text feature of each knowledge, the text relevant between described two different knowledge is calculated；With root
According to the semantic feature of each knowledge, the semantic dependency between described two different knowledge is calculated；
According to the text relevant and the semantic dependency, the content calculated between described two different knowledge is related
Property；
The relevance between described two different knowledge is corrected according to the content relevance.
Optionally, described according to the test data, every tester is obtained to the learning table of described two different knowledge
Existing step includes:
Obtain the power of test value that each described knowledge examination question is presented in every tester；
According to the power of test value, determine every tester to the learning performance of described two different knowledge.
Optionally, the power of test value is calculated by item response theory algorithm.
Optionally, the correlating method of the knowledge, further includes: the answer quantity of every tester constitutes data
Group, the data group include the first preset quantity threshold value and the second preset quantity threshold value.
Optionally, the correlating method of the knowledge, in the first preset quantity threshold value and second preset quantity
The several testers that answer quantity meets preset condition are filtered out between threshold value.
Optionally, the answer that the first preset quantity threshold value and the second preset quantity threshold value pass through the data group
The exceptional value point of cut-off of the formed box-shaped figure of the data distribution of quantity obtains.
Optionally, it is described according to every tester to the learning performance of two knowledge, determine that two differences are known
Relevance between knowledge is calculated by relevance algorithm.
Optionally, teaching material or course content or teaching of the described two different knowledge in the same knowledge hierarchy are big
Guiding principle.
Optionally, classroom work or homework or classroom test of the test data selected from the several testers is practised
Topic.
Optionally, the correlating method of the knowledge, further includes:
Obtain the successive learning sequence of described two different knowledge；
According to the successive learning sequence, by the preposition knowledge gained knowledge as after of first gaining knowledge, or, work of gaining knowledge by after
For the postposition knowledge first gained knowledge.
The embodiment of the present invention provides a kind of recommended method of knowledge learning, comprising:
Obtain current learning knowledge of the target learner in a knowledge hierarchy；
The pass in a knowledge hierarchy between multiple groups two different knowledge is obtained using the correlating method of the knowledge
Connection property；
According to the relevance between the multiple groups two different knowledge, there are the passes with the current learning knowledge for lookup
The postposition knowledge of connection property；
Recommend the postposition knowledge to the target learner.
Optionally, the knowledge learning recommended method, the institute between the postposition knowledge and the current learning knowledge
Relevance is stated greater than the first preset threshold.
The embodiment of the present invention provides a kind of intelligent Auto-generating Test Paper method, comprising:
Target learner is obtained in an architectonic nuclear know-how that needs checking；
The pass in a knowledge hierarchy between multiple groups two different knowledge is obtained using the correlating method of the knowledge
Connection property；
According to the relevance between the multiple groups two different knowledge, there are the associations with the nuclear know-how that needs checking for lookup
Property the first knowledge, first knowledge is the preposition knowledge of the nuclear know-how that needs checking；
The first default allocation proportion of need checking nuclear know-how and first knowledge is respectively set；
Intelligent Auto-generating Test Paper is carried out according to the described first default allocation proportion.
Optionally, the intelligent Auto-generating Test Paper method, further includes:
According to the relevance between the multiple groups two different knowledge, there are the relevances with first knowledge for lookup
The second knowledge, second knowledge be first knowledge preposition knowledge；
The second default allocation proportion of need checking nuclear know-how, first knowledge and second knowledge is respectively set；
Intelligent Auto-generating Test Paper is carried out according to the described second default allocation proportion.
The embodiment of the present invention provides a kind of storage medium, is stored thereon with computer instruction, which is executed by processor
The step of association learning method of knowledge described in Shi Shixian；Or, the step of realizing the recommended method of the knowledge learning；
Or, the step of realizing the intelligent Auto-generating Test Paper method.
The embodiment of the present invention provides a kind of knowledge connection equipment, including memory, processor and storage are on a memory simultaneously
The computer program that can be run on a processor, the processor realize the correlating method of the knowledge when executing described program
The step of.
The embodiment of the present invention provides a kind of recommendation apparatus, including memory, processor and storage are on a memory and can be
The computer program run on processor, the processor realize the recommended method of the knowledge learning when executing described program
The step of.
The embodiment of the present invention provides a kind of group of volume equipment, including memory, processor and storage are on a memory and can be
The computer program run on processor, the processor realize the step of the intelligent Auto-generating Test Paper method when executing described program
Suddenly.
Technical solution of the embodiment of the present invention, has the advantages that
The present invention discloses correlating method and the application of a kind of knowledge, and wherein the correlating method of knowledge includes: and obtains same to know
Two different knowledge in knowledge system；Several testers are obtained in the test data of two different knowledge；According to test data, obtain
Learning performance of the every tester to two different knowledge；According to every tester to the learning performance of two different knowledge, really
Relevance between fixed two different knowledge.The present invention is by several testers to two different knowledge in same knowledge hierarchy
Learning performance, the relevance between two different knowledge can be obtained, realized to two incidence relations under same knowledge hierarchy not
Determining relevance is excavated, convenient for the learning management to different two knowledge.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is the first pass figure of the correlating method of knowledge in the embodiment of the present invention；
Fig. 2 is the second flow chart of the correlating method of knowledge in the embodiment of the present invention；
Fig. 3 is the third flow chart of the correlating method of knowledge in the embodiment of the present invention；
Fig. 4 is the 4th flow chart of the correlating method of knowledge in the embodiment of the present invention；
Fig. 5 is the box-shaped figure of the correlating method of knowledge in the embodiment of the present invention；
Fig. 6 is the first pass figure of the recommended method of knowledge learning in the embodiment of the present invention；
Fig. 7 is the first pass figure of intelligent Auto-generating Test Paper method in the embodiment of the present invention；
Fig. 8 is the second flow chart of intelligent Auto-generating Test Paper method in the embodiment of the present invention；
Fig. 9 is the hardware schematic of knowledge connection equipment in the embodiment of the present invention；
Figure 10 is the hardware schematic of recommendation apparatus in the embodiment of the present invention；
Figure 11 is the hardware schematic of intelligent Auto-generating Test Paper equipment in the embodiment of the present invention.
Specific embodiment
It is clearly and completely described below in conjunction with technical solution of the attached drawing to the embodiment of the present invention, it is clear that described
Embodiment be a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is general
Logical technical staff every other embodiment obtained without making creative work belongs to what the present invention protected
Range.
In the description of the embodiment of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right",
The orientation or positional relationship of the instructions such as "vertical", "horizontal", "inner", "outside" is to be based on the orientation or positional relationship shown in the drawings,
It is merely for convenience of the description embodiment of the present invention and simplifies description, rather than the device or element of indication or suggestion meaning must have
There is specific orientation, be constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " the
One ", " second ", " third " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
In the description of the embodiment of the present invention, it should be noted that unless otherwise clearly defined and limited, term " peace
Dress ", " connected ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integrally
Connection；It can be mechanical connection, be also possible to be electrically connected；Can be directly connected, can also indirectly connected through an intermediary,
It can also be the connection inside two elements, can be wireless connection, be also possible to wired connection.For the common skill of this field
For art personnel, the concrete meaning of above-mentioned term in the present invention can be understood with concrete condition.
As long as in addition, the non-structure each other of technical characteristic involved in invention described below different embodiments
It can be combined with each other at conflict.
Embodiment 1
The embodiment of the present invention provides a kind of correlating method of knowledge, as shown in Figure 1, including the following steps:
S11, two different knowledge in same knowledge hierarchy are obtained.Same knowledge hierarchy herein is same knowledge class
Type, such as: Mathematics Teaching Material or language teaching material or geography teaching material or English teaching material indicate that same knowledge type included knows
Know.Teaching material or course content or syllabus of herein the two different knowledge in same knowledge hierarchy, but the two it
Between relevance and do not know.Such as: a multiplication knowledge and a division knowledge are obtained in Mathematics Teaching Material.So two
Object of the different knowledge as knowledge connection.
S12, several testers are obtained in the test data of two different knowledge.Test data herein is selected from several tests
Exercise is tested in the classroom work of person or homework or classroom.Several testers can be learnt this two different knowledge one
Test crowd is criticized, and test data indicates that this several tester is presented in classroom work or homework or classroom test exercise
Learning performance.
Test data herein further include the identity ID of every tester, the examination question ID that answers, answer situation and each know
Know the ID number and its attribute information of examination question, which includes that discrimination parameter, the project in item response theory IRT are difficult
Spend parameter and conjecture degree parameter.
The test data of two different knowledge can be indicated by the following table 1 and table 2 among the above:
1 tester's answer table of table
| Tester ID | Topic ID | It is whether correct | |
| Answer record 1 | 1 | 10000001 | 0 |
| Answer record 2 | 2 | 10000002 | 1 |
2 topic information table of table
Above-mentioned Tables 1 and 2 all presents the test data of each knowledge, obtains the test data of each knowledge to confirm
It whether there is incidence relation between two uncertain knowledge.
S13, according to test data, obtain every tester to the learning performance of two different knowledge.Learning table herein
It is now every tester to this two mastery of knowledge degree.
Specifically, as shown in Fig. 2, it is above-mentioned according to test data, obtain study of the every tester to two different knowledge
The step S13 of performance includes:
S131, the power of test value that each knowledge examination question is presented in every tester is obtained.Power of test value herein is
Every tester can reflect every tester couple to each mastery of knowledge degree or degree of understanding, by the power of test value
The study situation of each knowledge, power of test value can also reflect that usual every tester is in each knowledge by test result
Test examination question in obtain score higher, illustrate that the power of test value of this tester is higher, usual every tester is at each
It is lower that score is obtained in the test examination question of knowledge, illustrates that the power of test value of the tester is lower.Pass through the survey of power of test value
Examination data whether there is certain incidence relation mainly for obtaining two different knowledge.
Power of test value among the above is calculated by item response theory algorithm.Specific formula is as follows:
Wherein, P (θ) is to answer questions examination question probability, and a is discrimination parameter, and b is item difficulty parameter, and c is conjecture degree parameter, θ
For power of test value, D is constant 1.7.
When whether correct the practical answer situation () and the discrimination parameter a of corresponding topic, project of every tester be difficult
When degree parameter b, conjecture degree parameter c are datum, every tester can be calculated according to maximum likelihood estimation algorithm in each knowledge
On the power of test value that is shown.
Specifically, the conjecture degree parameter in above-mentioned formula (1) can be determined directly by answer type, such as: True-False
Conjecture degree parameter is 1/2, and the conjecture degree parameter of single choice is 1/ number of options.Multinomial selection for four options, all works
Answer possibility are as follows:
(A/B/C/D/AB/AC/AD/BC/BD/CD/ABC/ABD/BCD/ABCD) totally 14 kinds, this 14 kinds conjecture degree parameter
It is 1/14, the conjecture degree parameter of question-and-answer problem is 0.
Item difficulty parameter, discrimination parameter, power of test value in above-mentioned formula (1), according to item item response theory
IRT algorithm, one or more vacancies in this three, then be set as default value 0.
Above-mentioned formula (1) can also by iterative algorithm estimate discrimination parameter, item difficulty parameter, iteration until
As a result convergence obtains final result.Such as: 5000 testers of examination question to be measured of answering carry out for this 5000 testers
Independent test, if the power of test value of 95% or more tester/item difficulty parameter/discrimination parameter is in nth iteration
And the absolute value changed between (n+1)th time is respectively less than a certain threshold value, such as 0.01, then it is assumed that n+1 iteration result convergence.Such as:
If the power of test value of tester is unknown, the data of answering for all examination questions that this tester answered are obtained, and are thus estimated
Calculate the power of test value of tester；If item difficulty unknown parameters, every tester for obtaining the examination question of answering makees answer
According to the discrimination parameter, and thus estimate item difficulty parameter.
S132, according to power of test value, determine every tester to the learning performance of two different knowledge.Due to testing energy
Force value is higher, the learning performance of this tester is better, and power of test value is lower, the learning performance of this tester is poorer, institute
Every tester can be characterized to the learning performance of two different knowledge by power of test value.Such as: pass through above-mentioned formula
(1) the power of test value for calculating the first item knowledge of every tester is A, and the power of test value of Section 2 knowledge is B, be can be obtained
Learning performance of the several testers to this two knowledge.
S14, according to every tester to the learning performance of two different knowledge, can be calculated this two different knowledge it
Between relevance.
Specifically, by above-mentioned according to every tester in the learning performance of two different knowledge, determine that two differences are known
The step S14 of relevance between knowledge is calculated by relevance algorithm.The relevance algorithm includes Pearson correlation coefficient
Algorithm, Spearman algorithm.Wherein, the formula of Pearson correlation coefficient is as follows:
Wherein, r is that the Pearson between two different knowledge is associated with property coefficient, XiKnow for i-th tester in first item
Learning performance in knowledge, YiIt is i-th tester in the intellectual learning performance of Section 2,Several testers know in first item
Learning performance mean value in knowledge,For several testers in the intellectual learning performance mean value of Section 2, n is the number of several testers
Amount.
Wherein, Spearman algorithm is calculated by the following formula,
Wherein, ρ is the association property coefficient of the Spearman between two different knowledge, and n is the quantity of several testers, di
The difference of learning performance ranking is presented in two different knowledge by every tester.Such as: 100 testers are surveyed
It tries, then n=100, i-th tester is 3 in the intellectual learning performance ranking of first item, in the intellectual learning table of Section 2
Existing ranking is 5, then di=3-5=-2.
The correlating method of knowledge in the embodiment of the present invention, as shown in figure 3, determining the association between two different knowledge
After the step S14 of property further include:
S15, the relevance between two different knowledge is corrected.So-called correction is exactly to be calculated step S14
Relevance between the different knowledge of two out is adjusted, and keeps the estimation of the two relevance more accurate.
Specifically, as shown in figure 4, the correlating method of the knowledge in the embodiment of the present invention, between two different knowledge
The step S15 that relevance is corrected further include:
S151, the text feature and semantic feature for extracting each knowledge.Text feature passes through the verbal description of each knowledge
Content carries out feature extraction, and semantic feature carries out feature extraction by the semantic content of each knowledge, which can lead to
It crosses Word2vec algorithm the verbal description of each knowledge is extracted to obtain, as a result be indicated in the form of term vector.
S152, the text feature according to each knowledge calculate the text relevant between two different knowledge；With, according to
The semantic feature of each knowledge calculates the semantic dependency between two different knowledge.
Specifically, the text relevant calculated between two different knowledge is calculated by the following formula,
T (x, y)=1-d (x, y)/maxLen (x, y) (4)
Wherein, T (x, y) is text relevant, and x is the text feature of the first knowledge, and y is that the text of Section 2 knowledge is special
Sign, editing distance of the d (x, y) for first item knowledge and the second knowledge between, maxLen (x, y) is in first item knowledge x and the
Word length length value corresponding compared with elder in binomial knowledge y.Such as: the text feature of first item knowledge x is the " meter of area
Calculate ", the text feature of the second knowledge y is " calculating of volume ", and the editing distance d (x, y) of x and y are that 1, maxLen (x, y) is 5,
Therefore T (x, y)=4/5 is calculated by above-mentioned formula (4).
The semantic dependency calculated between two different knowledge is calculated by the following formula,
Wherein, cos (X, Y) is the semantic dependency of two different knowledge, XjFor in the corresponding term vector of first item knowledge
The value of jth dimension, XjFor the value that jth in the corresponding term vector of Section 2 knowledge is tieed up, m is the dimension of term vector.
S153, according to text relevant and semantic dependency, calculate the content relevance between two different knowledge.
Specifically, the calculation formula of content relevance is as follows:
Content relevance=W1 × T (x, y)+(1-W1) × cos (X, Y)； (6)
It wherein, is text relevant, cos (X, Y) is the semantic dependency of two different knowledge, and W1 is text relevant pair
The weight answered, (1-W1) are the corresponding weight of semantic dependency, and the proportion range of W1 is 0-1.
S154, the relevance between two different knowledge is corrected according to content relevance.Pass through text relevant and semanteme
The content relevance that correlation calculations go out adjusts the relevance between two different knowledge.
Specifically, final correction relevance formula is as follows:
Final relevance=max (g, (W2 × g+ (1-W2) × h)； (7)
Wherein, g is the relevance between two different knowledge, and h is content relevance, and W2 is between two different knowledge
The corresponding weight of relevance, the proportion range are 0-1.
The correlating method of knowledge in the embodiment of the present invention, further includes: the answer quantity of every tester constitutes data group, should
Data group includes the first preset quantity threshold value and the second preset quantity threshold value.Such as: the answer quantity of every tester constitutes number
According to group be [55,70,75,76,77,78,150], in this data group include this group of data upper limit threshold and lower threshold,
And lower threshold can be the first preset quantity threshold value, upper limit threshold can be the second preset quantity threshold value.
Specifically, filtered out between the first preset quantity threshold value and the second preset quantity threshold value answer quantity meet it is default
The several testers of condition.Such as: the first preset quantity threshold value of above-mentioned data group is 58, the second preset quantity threshold value of the group
It is 90, filters out answer quantity between 58 and 90 just to meet the several testers of preset condition, so, it can be by above-mentioned data
Exceptional value 55 and 150 in group is rejected.The purpose of the present embodiment acquisition the first preset quantity threshold value and the second preset quantity threshold value
It is in order to reject and not meet preset condition answer data, to retain the answer data of needs.
Specifically, the first preset quantity threshold value and the second preset quantity threshold value pass through the formed case of data distribution of data group
The exceptional value point of cut-off of shape figure obtains.Box-shaped figure herein be also known as box must scheme, boxlike figure or box traction substation, be a kind of to be used as display
The statistical chart of one group of data dispersion data.Box-shaped figure generally includes quartile point, lower quartile point, the truncation of upper exceptional value
Point and lower exceptional value point of cut-off.As shown in figure 5, Q1 is lower quartile point, Q3 is upper quartile point, and P1 is the truncation of lower exceptional value
Point, P2 are upper exceptional value point of cut-off, and Q3 indicates the upper quartile of all data, and Q1 indicates the lower quartile of all data.
Wherein, the interquartile-range IQR of IQR=Q3-Q1, IQR for box-shaped figure, P1=Q1-1.5IQR,
P2=Q3+1.5IQR.Such as: answer quantity in data group is [55,70,75,76,77,78,150], the one or four
Quantile Q1 is the 2nd number 70 of this group of answer quantity, and the second quartile point Q3 is the 6th number 78 of this group of answer quantity.Institute
With IQR=Q3-Q1=78-70=8.First exceptional value point of cut-off P1=Q1-1.5IQR=70-1.5*8=58；Second is abnormal
It is worth point of cut-off
P2=Q3+1.5IQR=78+1.5*8=90.Box-shaped figure is generated by the quantity of answering of several testers, utilizes case
The upper exceptional value point of cut-off and lower exceptional value point of cut-off of shape figure screen several testers as answer amount threshold, from
And avoid because several tester's answer quantity very little caused by power of test value estimation precision decline or several testers because of answer
The problems such as similar brush that quantity excessively reflects is inscribed, machine is answered.By the way that the first preset quantity threshold value is respectively set as answer
The upper limit threshold of quantity and the second preset quantity threshold value filter out several testers as lower threshold, so that it is several to control this
The computational accuracy error of the power of test value of tester.
The correlating method of knowledge in the embodiment of the present invention, further includes:
Firstly, obtaining the successive learning sequence of two different knowledge.Successive learning sequence herein refers to target learner
In the sequencing of each study level-learning knowledge, such as: first-year student needs first to learn one grade textbook content,
It can learn sophomoric textbook content, such as: learn content of the content of multiplication prior to learning division.Successive learning sequence can
Which knowledge content for determining two knowledge contents is preposition knowledge, which knowledge content is postposition knowledge.Usual feelings
Under condition, postposition knowledge is to rely on preposition knowledge, such as: division is that multiplication is postposition knowledge, i.e., division depends on multiplication knowledge.
Then, according to successive learning sequence, by the preposition knowledge gained knowledge as after of first gaining knowledge, or, gaining knowledge by after
As the postposition knowledge first gained knowledge.Successive learning sequence once it is determined that, so that it may between two different knowledge, before determining
Set knowledge and postposition knowledge.
Knowledge connection method in the embodiment of the present invention, for several testers to two differences in same knowledge hierarchy
The learning performance of knowledge can obtain the relevance between two different knowledge, realize and close to two associations under same knowledge hierarchy
It is the relevance excavation of uncertain knowledge, convenient for the learning management to different two knowledge.
Embodiment 2
The embodiment of the present invention provides a kind of recommended method of knowledge learning, as shown in Figure 6, comprising:
S61, current learning knowledge of the target learner in a knowledge hierarchy is obtained.A knowledge hierarchy herein is one kind
Knowledge type, such as: Mathematics Teaching Material or language teaching material or geography teaching material or English teaching material indicate that a kind of knowledge type is included
Knowledge.Current learning knowledge is the knowledge that target learner is learning.Such as: the knowledge that target learner is learning
It is calculated for the periphery product in six grade mathematics teaching material knowledge.
S62, it is obtained using the correlating method of knowledge in the relevance in a knowledge hierarchy between multiple groups two different knowledge.
The relevance in same knowledge hierarchy between multiple groups difference knowledge is obtained using the knowledge connection method in embodiment 1.Such as: A,
B,C,D,E,F,G,H.There are relevance between knowledge A and knowledge B, there are relevances also between knowledge C by knowledge A, and knowledge A is also
There are relevances between knowledge D, and there are relevance between knowledge C and knowledge D, knowledge C exists also between knowledge E to be associated with
Property, there are relevances between knowledge E and knowledge F, and there are relevances between knowledge G and knowledge H.Same know so available
Relevance in knowledge system between multiple groups difference knowledge.
S63, according to the relevance between the different knowledge of multiple groups two, search that there are after relevance with current learning knowledge
Set knowledge.Such as: current learning knowledge is C, there are multiple groups relevance data AB, AC, AD, CD, CE, EF, GH of relevance
There are the postposition knowledge of relevance with C for middle lookup.Such as: know that knowledge C's is current using the knowledge connection method in embodiment 1
The postposition knowledge of learning knowledge is E, then postposition knowledge of the E as current learning knowledge can be obtained by searching for this multi-group data.
S64, recommend postposition knowledge to target learner.Target learner herein is under a certain knowledge hierarchy of study
Habit person, such as: learn some consistent class of the individual or study schedule that are learnt under a certain knowledge hierarchy.When postposition knowledge
After acquisition, in order to help target learner to preview new knowledge, makes its fast understanding new content in learning process, enhance target
The learning efficiency and learning initiative of habit person, can to target scholar recommend with its current learning knowledge there are the postpositions of relevance
Knowledge.
Knowledge learning recommended method in the embodiment of the present invention, the relevance between postposition knowledge and current learning knowledge are big
In the first preset threshold.The first preset threshold herein indicates the relevance degree between postposition knowledge and current learning knowledge most
A big relevance value.
Using the knowledge connection method in the embodiment of the present invention, it can be achieved that when target learner study is a certain architectonic
When knowledge, according to the relevance between two different knowledge, the relation of interdependence between two different knowledge is known, thus to
Target learner recommends the postposition knowledge of its current learning knowledge.Largely, target learner can be improved to know a certain
The learning efficiency of knowledge system, while enhancing the learning interest of target learner, and the good study habit of training objective learner.
Embodiment 4
The embodiment of the present invention provides a kind of intelligent Auto-generating Test Paper method, as shown in fig. 7, comprises:
S71, target learner is obtained in an architectonic nuclear know-how that needs checking.A knowledge hierarchy herein is a kind of knowledge
Type, such as: Mathematics Teaching Material or language teaching material or geography teaching material or English teaching material indicate that a kind of knowledge type included knows
Know.The knowledge that the nuclear know-how that needs checking had learnt for target learner, the knowledge examined, such as: target learner
The nuclear know-how that needs checking learnt is that the periphery product in six grade mathematics teaching material knowledge calculates.
S72, the relevance in same knowledge hierarchy between multiple groups two different knowledge is obtained using the correlating method of knowledge.
The relevance in same knowledge hierarchy between multiple groups difference knowledge is obtained using the knowledge connection method in embodiment 1.Such as: A,
B,C,D,E,F,G,H.There are relevance between knowledge A and knowledge B, there are relevances also between knowledge C by knowledge A, and knowledge A is also
There are relevances between knowledge D, and there are relevance between knowledge C and knowledge D, knowledge C exists also between knowledge E to be associated with
Property, there are relevances between knowledge E and knowledge F, and there are relevances between knowledge G and knowledge H.Same know so available
Relevance in knowledge system between multiple groups difference knowledge.
S73, according to the relevance between the different knowledge of multiple groups two, there are the first of relevance for nuclear know-how of searching and need checking
Knowledge, the first knowledge are the preposition knowledge of nuclear know-how of needing checking.The correlating method of knowledge in preposition knowledge utilization embodiment 1 herein
Know the preposition knowledge for the nuclear know-how that needs checking, i.e. the first knowledge.
S74, the first default allocation proportion that need checking nuclear know-how and the first knowledge is respectively set.The default distribution of first herein
Ratio is need checking proportion, the proportion of the first knowledge of nuclear know-how.Such as: the nuclear know-how that needs checking is C, and the first knowledge is A,
The first default allocation proportion of default A is 30%, and the first default allocation proportion for presetting C is 70%.
S75, intelligent Auto-generating Test Paper is carried out according to the first default allocation proportion.According to the first default allocation proportion of the nuclear know-how that needs checking
70%, the first of the first knowledge the default allocation proportion is 30%, carries out intelligent Auto-generating Test Paper, i.e., nuclear know-how institute accounting of needing checking in paper
Example is 70%, and the first knowledge proportion is 30%.Intelligent Auto-generating Test Paper is carried out according to 30%, 70% ratio.
The relevance needed checking between nuclear know-how and the first knowledge in the embodiment of the present invention is greater than the second preset threshold, and second
Preset threshold indicates maximum relevance value between nuclear know-how and its preposition knowledge of needing checking.
Intelligent Auto-generating Test Paper method in the embodiment of the present invention, can in conjunction with the correlating method of knowledge, to target learner to
It examines knowledge and above-mentioned first knowledge to carry out intelligent Auto-generating Test Paper according to different proportion, facilitates the knowledge test of target learner,
And then facilitate analysis target learner in the Grasping level of current learning knowledge and positioning target learners' knowledge study
Weak link.
Embodiment 5
Intelligent Auto-generating Test Paper method in the embodiment of the present invention, as shown in Figure 8, further includes:
S81, target learner is obtained in an architectonic nuclear know-how that needs checking.Knowledge hierarchy herein is a kind of knowledge class
Type, such as: Mathematics Teaching Material or language teaching material or geography teaching material or English teaching material indicate that a kind of knowledge type included knows
Know.The nuclear know-how that needs checking is the knowledge that target learner had learnt, and needs to carry out knowledge to be examined.Such as: target study
What person had learnt needs checking nuclear know-how as the periphery product calculating in six grade mathematics teaching material knowledge.
S82, the relevance in same knowledge hierarchy between multiple groups two different knowledge is obtained using the correlating method of knowledge.
The relevance in same knowledge hierarchy between multiple groups difference knowledge is obtained using the knowledge connection method in embodiment 1.Such as: A,
B,C,D,E,F,G,H.There are relevance between knowledge A and knowledge B, there are relevances also between knowledge C by knowledge A, and knowledge A is also
There are relevances between knowledge D, and there are relevance between knowledge C and knowledge D, knowledge C exists also between knowledge E to be associated with
Property, there are relevances between knowledge E and knowledge F, and there are relevances between knowledge G and knowledge H.Same know so available
Relevance in knowledge system between multiple groups difference knowledge.
S83, according to the relevance between the different knowledge of multiple groups two, search that there are the second of relevance to know with the first knowledge
Know, the second knowledge is the preposition knowledge of the first knowledge.It would know that the nuclear know-how that needs checking using the knowledge connection method in embodiment 1
Preposition knowledge, for example, the nuclear know-how that needs checking is C, the first knowledge is B, and B is the preposition knowledge of nuclear know-how of needing checking, and the second knowledge is A, A
For the preposition knowledge of the first knowledge B.
S84, the second default allocation proportion that the nuclear know-how that needs checking, the first knowledge and the second knowledge is respectively set.Herein
Two default allocation proportions are need checking proportion, the proportion of the first knowledge, the proportion of the second knowledge of nuclear know-how.Example
Such as: the nuclear know-how that needs checking be C, the first knowledge be B, the second knowledge be A, preset A the second default allocation proportion be 20%, preset B
The second default allocation proportion be 30%, the second default allocation proportion of the nuclear know-how that needs checking is 50%.
S85, intelligent Auto-generating Test Paper is carried out according to the second default allocation proportion.According to the second default allocation proportion of the nuclear know-how that needs checking
50%, the second of the first knowledge the default allocation proportion 30%, the second default allocation proportion 20% of the second knowledge carry out smart group
Volume, i.e., nuclear know-how proportion of needing checking in paper is institute's accounting that the 50%, first knowledge proportion is the 30%, second knowledge
Example is 20%.Intelligent Auto-generating Test Paper is carried out according to 50%, 30%, 20% ratio.
Intelligent Auto-generating Test Paper method in the embodiment of the present invention, the nuclear know-how that needs checking are known with the first knowledge and the first knowledge with second
Know existing relevance and is greater than the second preset threshold.The expression of second preset threshold needs checking maximum between nuclear know-how and its preposition knowledge
Relevance value.
Intelligent Auto-generating Test Paper method in the embodiment of the present invention, can in conjunction with the correlating method of knowledge, to target learner to
Examination knowledge and preposition knowledge, the preposition knowledge of the preceding knowledge for the nuclear know-how that needs checking of the nuclear know-how that needs checking are carried out according to different proportion
Intelligent Auto-generating Test Paper, facilitate target learner knowledge test, and then position its in knowledge learning the problem of showing.
By the method in embodiment 4 and embodiment 5, the preposition of the preposition knowledge for obtaining the nuclear know-how that needs checking can also be recycled
Then the preposition knowledge of knowledge carries out intelligent Auto-generating Test Paper according to different proportion, and then constitutes the nuclear know-how that needs checking of target learner, have
Help the knowledge test of target learner, and then facilitates analysis target learner to the Grasping level of current learning knowledge and determine
Weak link in the target learners' knowledge study of position.
Embodiment 6
The embodiment of the present invention provides a kind of storage medium, is stored thereon with computer instruction, which is executed by processor
The step of Shi Shixian embodiment 1, embodiment 2, embodiment 3, embodiment 4, method in embodiment 5.It is also deposited on the storage medium
Every tester is contained to the test datas of two different knowledge, every tester to the learning performance of two different knowledge, every
Text feature, semantic feature, text relevant, the semantic dependency etc. of item knowledge.
Wherein, storage medium can be magnetic disk, CD, read-only memory (Read-Only Memory, ROM), random
Storage memory (Random Access Memory, RAM), flash memory (FlashMemory), hard disk (Hard Disk
Drive, abbreviation: HDD) or solid state hard disk (Solid-StateDrive, SSD) etc.；The storage medium can also include above-mentioned
The combination of the memory of type.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of the process in above-described embodiment method
Computer program is crossed to instruct relevant hardware and complete, program can be stored in a computer-readable storage medium, the journey
Sequence is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium can for magnetic disk, CD, read-only deposit
Store up memory body (ROM) or random access memory (RAM) etc..
Embodiment 7
The embodiment of the present invention provides a kind of knowledge connection equipment, as shown in figure 9, include memory 920, processor 910 and
It is stored in the computer program that can be run on memory 920 and on processor 910, processor 910 is realized real when executing program
The step of applying method in example 1.
Fig. 9 is a kind of hardware knot of associate device of the processing method of execution list items operation provided in an embodiment of the present invention
Structure schematic diagram, as shown in figure 9, the knowledge connection equipment includes one or more processors 910 and memory 920, in Fig. 9 with
For one processor 910.
The equipment for executing the processing method of list items operation can also include: input unit 930 and output device 940.
Processor 910, memory 920, input unit 930 and output device 940 can pass through bus or other modes
It connects, in Fig. 9 for being connected by bus.
Processor 910 can be central processing unit (Central Processing Unit, CPU).Processor 910 may be used also
Think other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.General processor can be microprocessor or the processing
Device is also possible to any conventional processor etc..
Embodiment 8
The embodiment of the present invention provides a kind of recommendation apparatus, as shown in Figure 10, including memory 1020, processor 1010 and deposits
The computer program that can be run on memory 1020 and on processor 1010 is stored up, processor 1010 is realized real when executing program
The step of applying method in example 1.
Figure 10 is a kind of hardware of recommendation apparatus of the processing method of execution list items operation provided in an embodiment of the present invention
Schematic diagram, as shown in Figure 10, which includes one or more processors 1010 and memory 1020, with one in Figure 10
For a processor 1010.
The equipment for executing the processing method of list items operation can also include: input unit 1030 and output device 1040.
Processor 1010, memory 1020, input unit 1030 and output device 1040 can by bus or other
Mode connects, in Figure 10 for being connected by bus.
Processor 1010 can be central processing unit (Central Processing Unit, CPU).Processor 1010 is also
It can be other general processors, digital signal processor (Digital Signal Processor, DSP), dedicated integrated electricity
Road (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.General processor can be microprocessor or the processing
Device is also possible to any conventional processor etc..
Embodiment 9
The embodiment of the present invention provides a kind of intelligent Auto-generating Test Paper equipment, as shown in figure 11, including memory 120, processor 110 and
It is stored in the computer program that can be run on memory 120 and on processor 110, processor 110 is realized real when executing program
Apply example 4, in embodiment 5 the step of method.
Fig. 1 is a kind of the hard of intelligent Auto-generating Test Paper equipment of the processing method of execution list items operation provided in an embodiment of the present invention
Part schematic diagram, as shown in Figure 1, the intelligent Auto-generating Test Paper equipment includes one or more processors 110 and memory 120, in Fig. 1 with
For one processor 110.
The equipment for executing the processing method of list items operation can also include: input unit 130 and output device 140.
Processor 110, memory 120, input unit 130 and output device 140 can pass through bus or other modes
It connects, in Fig. 1 for being connected by bus.
Processor 110 can be central processing unit (Central Processing Unit, CPU).Processor 110 may be used also
Think other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.General processor can be microprocessor or the processing
Device is also possible to any conventional processor etc..
Obviously, the above embodiments are merely examples for clarifying the description, and does not limit the embodiments.It is right
For those of ordinary skill in the art, can also make on the basis of the above description it is other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And it is extended from this it is obvious variation or
It changes still within the protection scope of the invention.
Claims (21)
1. a kind of correlating method of knowledge, which comprises the steps of:
Obtain two different knowledge in same knowledge hierarchy；
Several testers are obtained in the test data of described two different knowledge；
According to the test data, every tester is obtained to the learning performance of described two different knowledge；
According to every tester to the learning performance of described two different knowledge, determine between described two different knowledge
Relevance.
2. the correlating method of knowledge according to claim 1, which is characterized in that in the determination described two different knowledge
Between relevance the step of after further include:
Relevance between described two different knowledge is corrected.
3. the correlating method of knowledge according to claim 2, which is characterized in that the pass between described two different knowledge
The step of connection property is corrected further include:
Extract the text feature and semantic feature of each knowledge；
According to the text feature of each knowledge, the text relevant between described two different knowledge is calculated；With, according to institute
The semantic feature of each knowledge is stated, the semantic dependency between described two different knowledge is calculated；
According to the text relevant and the semantic dependency, the content relevance between described two different knowledge is calculated；
The relevance between described two different knowledge is corrected according to the content relevance.
4. the correlating method of knowledge according to claim 3, which is characterized in that it is described according to the test data, it obtains
Every tester includes: to the step of learning performances of described two different knowledge
Obtain the power of test value that each described knowledge examination question is presented in every tester；
According to the power of test value, determine every tester to the learning performance of described two different knowledge.
5. the correlating method of knowledge according to claim 4, which is characterized in that the power of test value passes through Item Response Pattern
Theoretical algorithm is calculated.
6. the correlating method of knowledge according to claim 4, which is characterized in that further include: every tester's answers
It inscribes quantity and constitutes data group, which includes the first preset quantity threshold value and the second preset quantity threshold value.
7. the correlating method of knowledge according to claim 6, which is characterized in that in the first preset quantity threshold value and institute
It states and filters out the several testers that answer quantity meets preset condition between the second preset quantity threshold value.
8. the correlating method of knowledge according to claim 7, which is characterized in that the first preset quantity threshold value and described
The exceptional value point of cut-off that second preset quantity threshold value passes through the formed box-shaped figure of data distribution of the answer quantity of the data group
It obtains.
9. the correlating method of knowledge according to claim 1, which is characterized in that it is described according to every tester to two
The learning performance of item knowledge determines that the relevance between described two different knowledge is calculated by relevance algorithm.
10. the correlating method of knowledge according to claim 1, which is characterized in that described two different knowledge are selected from described
Teaching material or course content or syllabus in same knowledge hierarchy.
11. the correlating method of knowledge according to claim 1, which is characterized in that the test data is selected from described several
Exercise is tested in the classroom work of tester or homework or classroom.
12. the correlating method of knowledge according to claim 1, which is characterized in that further include:
Obtain the successive learning sequence of described two different knowledge；
According to the successive learning sequence, by the preposition knowledge gained knowledge as after of first gaining knowledge, or, being gained knowledge by after as institute
State the postposition knowledge first gained knowledge.
13. a kind of recommended method of knowledge learning characterized by comprising
Obtain current learning knowledge of the target learner in a knowledge hierarchy；
Multiple groups two are obtained in a knowledge hierarchy using the correlating method of the knowledge of any of claims 1-12
Relevance between different knowledge；
According to the relevance between the multiple groups two different knowledge, there are the relevances with the current learning knowledge for lookup
Postposition knowledge；
Recommend the postposition knowledge to the target learner.
14. knowledge learning recommended method according to claim 13, which is characterized in that the postposition knowledge and described current
The relevance between learning knowledge is greater than the first preset threshold.
15. a kind of intelligent Auto-generating Test Paper method characterized by comprising
Target learner is obtained in an architectonic nuclear know-how that needs checking；
Multiple groups two are obtained in a knowledge hierarchy using the correlating method of the knowledge of any of claims 1-12
Relevance between different knowledge；
According to the relevance between the multiple groups two different knowledge, there are the relevances with the nuclear know-how that needs checking for lookup
First knowledge, first knowledge are the preposition knowledge of the nuclear know-how that needs checking；
The first default allocation proportion of need checking nuclear know-how and first knowledge is respectively set；
Intelligent Auto-generating Test Paper is carried out according to the described first default allocation proportion.
16. intelligent Auto-generating Test Paper method according to claim 15, which is characterized in that further include:
According to the relevance between the different knowledge of multiple groups two, the with first knowledge there are the relevance is searched
Two knowledge, second knowledge are the preposition knowledge of first knowledge；
The second default allocation proportion of need checking nuclear know-how, first knowledge and second knowledge is respectively set；
Intelligent Auto-generating Test Paper is carried out according to the described second default allocation proportion.
17. intelligent Auto-generating Test Paper method according to claim 16, which is characterized in that the nuclear know-how that needs checking is known with described first
The relevance existing for knowledge and first knowledge and second knowledge is greater than the second preset threshold.
18. a kind of storage medium, is stored thereon with computer instruction, which is characterized in that the realization when instruction is executed by processor
The step of association learning method of knowledge of any of claims 1-12；Or, realizing any in claim 13-14
The step of recommended method of knowledge learning described in；Or, realizing intelligent Auto-generating Test Paper side described in any one of claim 15-17
The step of method.
19. a kind of knowledge connection equipment, can run on a memory and on a processor including memory, processor and storage
Computer program, which is characterized in that the processor is realized of any of claims 1-12 when executing described program
The step of correlating method of knowledge.
20. a kind of recommendation apparatus including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes knowledge described in any one of claim 13-14 when executing described program
The step of recommended method of study.
21. a kind of group of volume equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes intelligence described in any one of claim 15-17 when executing described program
The step of group volume method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811459521.8A CN109684436B (en) | 2018-11-30 | 2018-11-30 | Knowledge correlation method and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811459521.8A CN109684436B (en) | 2018-11-30 | 2018-11-30 | Knowledge correlation method and application |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109684436A true CN109684436A (en) | 2019-04-26 |
| CN109684436B CN109684436B (en) | 2021-08-03 |
Family
ID=66185616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811459521.8A Active CN109684436B (en) | 2018-11-30 | 2018-11-30 | Knowledge correlation method and application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109684436B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021213A (en) * | 2019-05-14 | 2019-07-16 | 上海乂学教育科技有限公司 | Mathematics preamble learning method in artificial intelligence study |
| CN110618390A (en) * | 2019-09-25 | 2019-12-27 | 深圳力维智联技术有限公司 | Method, device and equipment for identifying abnormal single battery of storage battery pack and storage medium thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512214A (en) * | 2015-11-28 | 2016-04-20 | 华中师范大学 | Knowledge database, construction method and learning situation diagnosis system |
| CN106599999A (en) * | 2016-12-09 | 2017-04-26 | 北京爱论答科技有限公司 | Evaluation method and system for using small amount of questions to accurately detect segmented weak knowledge points of student |
| CN107943940A (en) * | 2017-11-23 | 2018-04-20 | 网易（杭州）网络有限公司 | Data processing method, medium, system and electronic equipment |
| US20180151084A1 (en) * | 2016-11-30 | 2018-05-31 | Electronics And Telecommunications Research Institute | Apparatus and method for providing personalized adaptive e-learning |
-
2018
- 2018-11-30 CN CN201811459521.8A patent/CN109684436B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512214A (en) * | 2015-11-28 | 2016-04-20 | 华中师范大学 | Knowledge database, construction method and learning situation diagnosis system |
| US20180151084A1 (en) * | 2016-11-30 | 2018-05-31 | Electronics And Telecommunications Research Institute | Apparatus and method for providing personalized adaptive e-learning |
| CN106599999A (en) * | 2016-12-09 | 2017-04-26 | 北京爱论答科技有限公司 | Evaluation method and system for using small amount of questions to accurately detect segmented weak knowledge points of student |
| CN107943940A (en) * | 2017-11-23 | 2018-04-20 | 网易（杭州）网络有限公司 | Data processing method, medium, system and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110021213A (en) * | 2019-05-14 | 2019-07-16 | 上海乂学教育科技有限公司 | Mathematics preamble learning method in artificial intelligence study |
| CN110618390A (en) * | 2019-09-25 | 2019-12-27 | 深圳力维智联技术有限公司 | Method, device and equipment for identifying abnormal single battery of storage battery pack and storage medium thereof |
| CN110618390B (en) * | 2019-09-25 | 2021-08-31 | 深圳力维智联技术有限公司 | Method, device and equipment for identifying abnormal single battery of storage battery pack and storage medium thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109684436B (en) | 2021-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mao et al. | Validation of automated scoring for a formative assessment that employs scientific argumentation | |
| Lee et al. | Vlat: Development of a visualization literacy assessment test | |
| CN107273490B (en) | Combined wrong question recommendation method based on knowledge graph | |
| Tunas Bangsa Pematangsiantar | Comparison of weighted sum model and multi attribute decision making weighted product methods in selecting the best elementary school in Indonesia | |
| CN106599999A (en) | Evaluation method and system for using small amount of questions to accurately detect segmented weak knowledge points of student | |
| CN107657559A (en) | A kind of Chinese reading capability comparison method and system | |
| KR20190123105A (en) | System and method of providing customized education contents | |
| CN109242041A (en) | A kind of electric energy meter abnormal deviation data examination method, device, equipment and storage medium | |
| CN104166731A (en) | Discovering system for social network overlapped community and method thereof | |
| CN112699283B (en) | Test paper generation method and device | |
| CN111651677B (en) | Course content recommendation method, apparatus, computer device and storage medium | |
| CN112101828B (en) | Post skill evaluation method, system, electronic device and storage medium | |
| CN109345101A (en) | Evaluation in Education Quality analysis method based on comprehensive evaluation analysis method | |
| CN108763588A (en) | A kind of knowledge point quantitative analysis method and device | |
| CN116263782A (en) | Intelligent winding method, system and storage medium based on question bank | |
| Muratov et al. | Computer-assisted decision support for student admissions based on their predicted academic performance | |
| CN109684436A (en) | A kind of correlating method of knowledge and application | |
| CN113987019A (en) | Student learning condition analysis method and teaching system based on artificial intelligence | |
| CN108932593A (en) | A kind of cognition analysis of Influential Factors method and device | |
| Fotheringham et al. | Multiscale Geographically Weighted Regression: Theory and Practice | |
| CN115438152B (en) | Simple answer scoring method and system based on multi-neural network and knowledge graph | |
| Boyce et al. | Role of Representation in Prospective Teachers' Fractions Schemes. | |
| CN115544268A (en) | Construction and application method of teaching and employment auxiliary knowledge map | |
| CN113744101A (en) | Intelligent examinee volunteer filling method and device in new high-level examination mode and computer equipment | |
| Gnaldi | A multidimensional IRT approach for dimensionality assessment of standardised students’ tests in mathematics |
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 |