CN106469427A - The choosing method of learning path and device - Google Patents
The choosing method of learning path and device Download PDFInfo
- Publication number
- CN106469427A CN106469427A CN201610793494.2A CN201610793494A CN106469427A CN 106469427 A CN106469427 A CN 106469427A CN 201610793494 A CN201610793494 A CN 201610793494A CN 106469427 A CN106469427 A CN 106469427A
- Authority
- CN
- China
- Prior art keywords
- defect
- ability
- learning path
- path
- follow
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000007547 defect Effects 0.000 claims abstract description 164
- 238000013459 approach Methods 0.000 claims description 5
- 239000011800 void material Substances 0.000 claims 1
- 241001251068 Formica fusca Species 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000003016 pheromone Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 235000001968 nicotinic acid Nutrition 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of choosing method of learning path and device.Methods described includes:Determine the defect rank of the ability of learner according to the history learning path in learning path model;According to determined by defect rank determine the influence degree to follow-up learning path for the described ability;According to the influence degree to described follow-up learning path for the described ability, continue the learning path choosing described learner next step in learning path in the rear.So, it is that the selection of next step learning path provides reliable foundation, be that learner chooses more suitably learning path so that the study of learner is more efficient.
Description
Technical field
It relates to computer realm, in particular it relates to a kind of choosing method of learning path and device.
Background technology
In the curricular system for giveing training to learner, including the training to polytype and ability.For example, children
The curricular system of youngster generally includes class of languages, Science, Arts, healthy class and social class.Wherein it is desired to the general character energy of culture
Power generally includes:Cognition Understanding ability, capacity for mood, social competence, self-care ability, absorbed ability, motor capacity.
At present, in the training scheme to learner, a kind of scheme is the course (example arranging fixation in a fixed order
As syllabus).In this scheme, learner is when by testting after class, then carries out next course;Another kind of scheme is root
Performance of the test before the class according to learner recommends course.
Because the individual variation ratio of learner is larger, in the scheme of above-mentioned fixing course, learner can not be had
Targetedly personalized culture.Even with the scheme of above-mentioned recommendation course, by generally be based on test overall scores,
The average level of namely above-mentioned multiple general character ability, there is larger defect in ability or the learner of advantage comes for certain aspects
Say, effect is not still good.
Content of the invention
The purpose of the disclosure is to provide a kind of personalized choosing method of learning path and device.
To achieve these goals, the disclosure provides a kind of choosing method of learning path.Methods described includes:According to
Practise the defect rank that the history learning path in path model determines the ability of learner;According to determined by defect rank determine
The influence degree to follow-up learning path for the described ability;According to the influence degree to described follow-up learning path for the described ability,
The learning path of described learner next step is chosen in described follow-up learning path.
Alternatively, the history learning path in the described model according to learning path determines the defect rank of the ability of learner
Step include:Determine the defect parameters of the described ability of learner described in described history learning path;Obtain each to learn
Practise the meansigma methodss of the actual value of ability of course node;The actual value of the defect parameters according to described ability and described ability flat
Average, determines the defect rank of described ability.
Alternatively, described learning path model is directed acyclic graph, including course node and directed edge, described defect parameters
Including:Defect path, defect number of paths and defect course number of nodes,
L=L0+m;N=N0+n;P=P0+q
Wherein, L represents defect path;L0Represent defect path initial length;M represents in described history learning path
Power gradient is 0 or the number of the directed edge of negative value;N represents defect number of paths;N0Represent defect path initial number;N table
Show that in described history learning path, continuous power gradient is 0 or the number of the directed edge of negative value;P represents defect course nodes
Amount;P0Represent defect course node initial number;Q represents the actual value of ability and desired value described in described history learning path
Difference be negative value course node number.
Alternatively, defect rank determined by described basis determines described ability to the influence degree of follow-up learning path
Step includes:According to determined by defect rank determine defect coefficient;Described follow-up study road is determined according to described defect coefficient
In footpath every directed edge up to weights,
Wherein, ViRepresent for i-th kind of ability up to weights, KiRepresent the defect coefficient of i-th kind of ability, GiUnder expression
The desired value of i-th kind of ability of one course node, CiRepresent the condition value of i-th kind of ability of next course node;According to described
The virtual length determining the expression influence degree to follow-up learning path for the described ability up to weights of every directed edge,
Wherein, dijRepresent the virtual length of j-th directed edge, M represents the number of ability.
Alternatively, described ability includes multi abilities, the described impact according to described ability to described follow-up learning path
Degree, the step continuing the learning path choosing described learner next step in learning path in the rear includes:According to described energy
The influence degree to described follow-up learning path for the power, by heuritic approach, continues in learning path in the rear and chooses described energy
The minimum follow-up learning path of the influence degree of power, as the learning path of described learner next step.
The disclosure also provides a kind of selecting device of learning path.Described device includes:Defect rank determining module, is used for
Determine the defect rank of the ability of learner according to the history learning path in learning path model;Influence degree determining module,
Determine the influence degree to follow-up learning path for the described ability for defect rank determined by basis;Choose module, for root
According to the influence degree to described follow-up learning path for the described ability, continue in the rear in learning path choose described learner next
The learning path of step.
By technique scheme, by the ability of learner determined by history learning path in learning path model
Defect rank, embodies in the training completing course, the obvious degree of certain capabilities defect of learner, the model of effect
Enclose, the order of severity etc..Impact when determining that the defect of this certain capabilities learns to re-service term accordingly, thus select next step
Learning path.So, it is that the selection of next step learning path provides reliable foundation, be that learner is chosen more suitably
Learning path is so that the study of learner is more efficient.
Other feature and advantage of the disclosure will be described in detail in subsequent specific embodiment part.
Brief description
Accompanying drawing is used to provide further understanding of the disclosure, and constitutes the part of description, with following tool
Body embodiment is used for explaining the disclosure together, but does not constitute restriction of this disclosure.In the accompanying drawings:
Fig. 1 is the flow chart of the choosing method of learning path that an exemplary embodiment provides;
Fig. 2 is the schematic diagram of the learning path model that an exemplary embodiment provides;
Fig. 3 is the flow chart of the determination defect rank that an exemplary embodiment provides;
Fig. 4 is the flow process of the influence degree to follow-up learning path for the ability described in determination that an exemplary embodiment provides
Figure;
Fig. 5 is the block diagram of the selecting device of learning path that an exemplary embodiment provides.
Specific embodiment
It is described in detail below in conjunction with accompanying drawing specific embodiment of this disclosure.It should be appreciated that this place is retouched
The specific embodiment stated is merely to illustrate and explains the disclosure, is not limited to the disclosure.
Fig. 1 is the flow chart of the choosing method of learning path that an exemplary embodiment provides.As shown in figure 1, described side
Method may comprise steps of.
In step s 11, defect of ability of learner etc. is determined according to the history learning path in learning path model
Level.
In step s 12, according to determined by defect rank determine the influence degree to follow-up learning path for the described ability.
In step s 13, the influence degree to follow-up learning path according to described ability, chooses in follow-up learning path
The learning path of learner next step.
By technique scheme, by the ability of learner determined by history learning path in learning path model
Defect rank, embodies in the training completing course, the obvious degree of certain capabilities defect of learner, the model of effect
Enclose, the order of severity etc..Impact when determining that the defect of this certain capabilities learns to re-service term accordingly, thus select next step
Learning path.So, it is that the selection of next step learning path provides reliable foundation, be that learner is chosen more suitably
Learning path is so that the study of learner is more efficient.
Specifically, learning path model can be pre-build.Learning path model can be directed acyclic graph (directed
Acycline praph, DAG scheme) model, including course node and directed edge.Fig. 2 is the study that an exemplary embodiment provides
The schematic diagram of path model.As shown in Fig. 2 the course node of the circular frame such as " tinting " " bouncing the ball " is to complete course node,
The oval course node of " brushing teeth after meal " is current course node, and the square course node such as " arrangement bookshelf " is re-service term section
Point.Directed line segment between two course nodes is directed edge.
Wherein it is possible to arrange multiple capabilities attributes for each course node.For example, in the culture scheme of child, described
Ability can include one or more of following:Cognition Understanding ability, capacity for mood, social competence, self-care ability, specially
Note ability and motor capacity.In the particular embodiment, can only consider wherein a certain ability it is also possible to consider multiple
Ability, to choose the learning path of next step, described in detail below.
History learning path can include all possible path that completed course node is formed.Exemplary one
In embodiment, the defect parameters embodying defect rank can be set, determine defect by quantitatively calculating defect parameters
Grade.Fig. 3 is the flow chart of the determination defect rank that an exemplary embodiment provides.As shown in figure 3, according to learning path model
In history learning path determine that the step of the defect rank (step S11) of ability of learner may comprise steps of.
In step S111, determine the defect parameters of the described ability of history learning path learning person.
Wherein it is possible to be every kind of capabilities setting condition value, actual value and desired value.Condition value is this course node institute of study
The ability value needing;Actual value is the ability value that actually reaches after learning this course of learner (for example, it is possible to according to teacher's
Evaluation obtains);The ability value that desired value should reach after completing this course for learner.Following table is the course section of " tinting "
The condition value of the corresponding above-mentioned six kinds of abilities of point, actual value and desired value.
And it is possible to arrange power gradient attribute for each directed edge in history learning path.Described power gradient is
The difference of the ability actual value of the ability actual value of next course node of directed edge and a upper course node.
For example, described defect parameters can include:Defect path, defect number of paths and defect course node
Quantity, and meet:L=L0+m;N=N0+n;P=P0+q.
Wherein, L represents defect path;L0Represent defect path initial length;M represents its energy in history learning path
Power gradient is 0 or the number of the directed edge of negative value.
N represents defect number of paths;N0Represent defect path initial number;N represents continuous in described history learning path
Power gradient be 0 or the number of the directed edge of negative value.
P represents defect course number of nodes;P0Represent defect course node initial number;Q represents described history learning road
The number of the course node that the actual value of ability described in footpath is negative value with the difference of desired value.
Wherein, power gradient is 0 or after negative value represents next the course node completing directed edge, and described ability is carried
Rise or reduce on the contrary.After the actual value of ability and the difference of desired value represent for negative value and complete this course node, the energy of learner
Power does not reach target.L0、N0、P0It can be the arbitrary value pre-setting.
Therefore, defect course number of nodes P embody be learner described ability in course deviation sum total, quantity
This capability defect tendency of more explanation learners is more obvious;What defect number of paths N embodied is the described ability of learner
Defect sphere of action, number of paths illustrates that the coverage of this capability defect is bigger;What defect path L embodied is to learn
The defect order of severity of this ability of habit person, path is longer, illustrates that the impact of this capability defect is more serious.
Thus, by search for upwards from current course node start most to learning path model course node (or
Reverse search), quantify the drawbacks described above parameter in history learning path.As described above, history learning path can be included
The all possible path that the course node completing is formed.It is, all determining that defect is joined for every possible path
Number.The defect parameters of every kind of ability in the case that described ability includes multi abilities, can be determined respectively.
In step S112, obtain the meansigma methodss of each actual value of the ability of learned lesson node.Described ability
The meansigma methodss of actual value reflect the average level that after multiple learners learn this course node, described ability reaches.This meansigma methods
Can be drawn according to Statistics.
In step S113, the defect parameters according to described ability and the meansigma methodss of the actual value of ability, determine described energy
The defect rank of power.
The defect rank of every kind of ability when described ability includes multi abilities, can be considered respectively.For example, it is possible to pass through
The neural network model training obtains defect rank.When training neural network model, can be with the actual value of input capability
Meansigma methodss, defect parameters and corresponding defect rank.Wherein, defect rank can be obtained by experience, or, each can be lacked
Sunken parameter gives certain weight respectively, by the weighted sum value of all defect parameter compared with the meansigma methodss of the actual value of ability
Relatively to determine defect rank.
Defect rank can be set as example including the multiple grades such as serious, general, slight.Defect rank determined above
Afterwards it is possible to carry out in step S12 the influence degree to follow-up learning path for the capability really.
Fig. 4 is the flow process of the influence degree to follow-up learning path for the ability described in determination that an exemplary embodiment provides
Figure.As shown in figure 4, according to determined by defect rank determine the influence degree (step to follow-up learning path for the described ability
S12 step) may comprise steps of.
In step S121, according to determined by defect rank determine defect coefficient.
Defect coefficient is used for quantitatively representing defect rank, is beneficial to the influence degree of ability described in subsequent quantizatiion.For example,
Defect rank is serious, general, slight can to use defect COEFFICIENT K respectively1、K2、K3Represent, wherein K1> K2> K3≥1.
In step S122, according to defect coefficient determine every directed edge in follow-up learning path up to weights.
Wherein, ViRepresent for i-th kind of ability up to weights, KiRepresent the defect coefficient of i-th kind of ability, GiUnder expression
The desired value of i-th kind of ability of one course node, CiRepresent the condition value of i-th kind of ability of next course node.
Described up to weights for the selected probability getting next step learning path of directed edge weight.Include many in ability
During the ability of kind, can be vectorial [V up to weights1, V2... Vi,…VM], M represents the number of ability.
In step S123, determined up to weights according to described every directed edge and represent described ability to follow-up study road
The virtual length of the influence degree in footpath.
Wherein, dijRepresent the virtual length of j-th directed edge, M represents the number of ability.So, virtual length embodies
The influence degree to next course node in directed edge for the defect rank of described ability.Herein, virtual length and influence degree are in
Positive correlation.It is, the virtual length of directed edge is longer, the defect rank of described ability is to next course node in this directed edge
Influence degree bigger.When affecting less due to the defect of ability to course node, the effect of study preferably, therefore, it can select
Select the minimum directed edge of the influence degree of the defect rank of described ability, as the learning path of learner next step, that is,
Optimum learning path.
In addition, often completing a course node, defect rank may will be varied from, and defect coefficient is likely to accordingly change
Become.In order to all select when often completing a course node optimum learning path, can when often completing a course node,
Recalculate defect rank, and the virtual length of directed edge.In such manner, it is possible to consider the change of learner competencies to follow-up class
The impact of Cheng Jiedian, dynamically carries out the selection of optimal path, makes the study of each course node more efficient.
In one embodiment, described ability includes multi abilities, according to the impact journey to follow-up learning path for the described ability
Degree, the step (step S13) choosing the learning path of learner next step in follow-up learning path can include:According to described
The influence degree to follow-up learning path for the ability, by heuritic approach, chooses the shadow of described ability in follow-up learning path
The minimum follow-up learning path of the degree of sound, as the learning path of learner next step.
Wherein, heuritic approach can include genetic algorithm or (for example, ant group algorithm, the population calculation of bionics algorithm
Method)., choose learning path and specifically may comprise steps of taking ant group algorithm as a example:
(1) by virtual length d of directed edgeijAs initialization algorithm parameter.Cycle-index N when arranging initialc=0, and
Setting maximum cycle Nmax, amount Q of configuration information element, the only different Formica fusca of z is placed on respective initial position, just
Pheromone on beginningization side (i, j);
(2) cycle-index increases certainly, i.e. Nc=Nc+1;
(3) initialize Formica fusca taboo list;
(4) Formica fusca number increases certainly, i.e. k=k+1;
(5) kth Formica fusca is calculated with the node of next step transfer corresponding with its path (directed edge), updates taboo list;
(6) the pheromone amount on the path that local updating Formica fusca is passed by;
(7) if node is not also all passed by, go to (5th) step and continue executing with, otherwise go to (8th) step;
(8) if Formica fusca number k>Z sets up, and that is, all Formica fuscas all complete to search for, then go to (9th) step, otherwise, go to the
(4) step;
(9) compare the virtual length in the path that each Formica fusca is each passed by, choose virtual length the shortest, simultaneously to it
Through path carry out the renewal of pheromone;
(10) if Nc≥NmaxThen end loop, exports to result in a manner, otherwise by among taboo list
Erasing of information fall after go to (2nd) step and continue executing with.
In this embodiment, apply ant algorithm, optimal path can be drawn in the case of considering multi abilities,
Simply easily implement.
The disclosure also provides a kind of selecting device of learning path.Fig. 5 is the learning path that an exemplary embodiment provides
Selecting device block diagram.As shown in figure 5, the selecting device 10 of described learning path can include defect rank determining module
11st, influence degree determining module 12 and selection module 13.
Defect rank determining module 11 is used for determining the energy of learner according to the history learning path in learning path model
The defect rank of power.
Influence degree determining module 12 is used for defect rank determined by basis and determines described ability to follow-up learning path
Influence degree.
Choose module 13 and be used for according to described ability the influence degree to described follow-up learning path, continue study in the rear
The learning path of described learner next step is chosen in path.
Alternatively, described defect rank determining module 11 can include defect parameters determination sub-module, meansigma methodss obtain son
Module and defect rank determination sub-module.
Defect parameters determination sub-module is used for determining lacking of the described ability of learner described in described history learning path
Sunken parameter.
Meansigma methodss acquisition submodule is used for obtaining the meansigma methodss of each actual value of the ability of learned lesson node.
Defect rank determination sub-module is average for the actual value of the defect parameters according to described ability and described ability
Value, determines the defect rank of described ability.
Alternatively, described learning path model is directed acyclic graph, including course node and directed edge, described defect parameters
Including:Defect path, defect number of paths and defect course number of nodes,
L=L0+m;N=N0+n;P=P0+q
Wherein, L represents defect path;L0Represent defect path initial length;M represents in described history learning path
Power gradient is 0 or the number of the directed edge of negative value.
N represents defect number of paths;N0Represent defect path initial number;N represents continuous in described history learning path
Power gradient be 0 or the number of the directed edge of negative value.
P represents defect course number of nodes;P0Represent defect course node initial number;Q represents described history learning road
The number of the course node that the actual value of ability described in footpath is negative value with the difference of desired value.
Alternatively, described influence degree determining module 12 can include defect coefficient determination sub-module, determine up to weights
Submodule and virtual length determination sub-module.
Defect coefficient determination sub-module is used for defect rank determined by basis and determines defect coefficient.
Up to weights determination sub-module be used for according to described defect coefficient determine in described follow-up learning path every oriented
Side up to weights,
Wherein, ViRepresent for i-th kind of ability up to weights, KiRepresent the defect coefficient of i-th kind of ability, GiUnder expression
The desired value of i-th kind of ability of one course node, CiRepresent the condition value of i-th kind of ability of next course node.
Virtual length determination sub-module, represents described ability pair for determining up to weights according to described every directed edge
The virtual length of the influence degree of follow-up learning path,
Wherein, dijRepresent the virtual length of j-th directed edge, M represents the number of ability.
Alternatively, described ability includes multi abilities, and described selection module 13 can include choosing submodule.
Choose submodule and be used for according to described ability the influence degree to described follow-up learning path, by heuristic calculation
Method, continues the follow-up learning path of the influence degree minimum choosing described ability in learning path, in the rear as described study
The learning path of person's next step.
With regard to the device in above-described embodiment, wherein the concrete mode of modules execution operation is in relevant the method
Embodiment in be described in detail, explanation will be not set forth in detail herein.
By technique scheme, by the ability of learner determined by history learning path in learning path model
Defect rank, embodies in the training completing course, the obvious degree of certain capabilities defect of learner, the model of effect
Enclose, the order of severity etc..Impact when determining that the defect of this certain capabilities learns to re-service term accordingly, thus select next step
Learning path.So, it is that the selection of next step learning path provides reliable foundation, be that learner is chosen more suitably
Learning path is so that the study of learner is more efficient.
Describe the preferred implementation of the disclosure above in association with accompanying drawing in detail, but, the disclosure is not limited to above-mentioned reality
Apply the detail in mode, in the range of the technology design of the disclosure, multiple letters can be carried out with technical scheme of this disclosure
Monotropic type, these simple variant belong to the protection domain of the disclosure.
It is further to note that each particular technique feature described in above-mentioned specific embodiment, in not lance
In the case of shield, can be combined by any suitable means.In order to avoid unnecessary repetition, the disclosure to various can
The compound mode of energy no longer separately illustrates.
Additionally, combination in any can also be carried out between the various different embodiment of the disclosure, as long as it is without prejudice to this
Disclosed thought, it equally should be considered as disclosure disclosure of that.
Claims (10)
1. a kind of choosing method of learning path is it is characterised in that methods described includes:
Determine the defect rank of the ability of learner according to the history learning path in learning path model;
According to determined by defect rank determine the influence degree to follow-up learning path for the described ability;
According to the influence degree to described follow-up learning path for the described ability, continue in learning path in the rear and choose described study
The learning path of person's next step.
2. method according to claim 1 is it is characterised in that history learning path in the described model according to learning path
Determine that the step of the defect rank of the ability of learner includes:
Determine the defect parameters of the described ability of learner described in described history learning path;
Obtain the meansigma methodss of each actual value of the ability of learned lesson node;
The meansigma methodss of the actual value of the defect parameters according to described ability and described ability, determine the defect rank of described ability.
3. method according to claim 2 is it is characterised in that described learning path model is directed acyclic graph, including class
Cheng Jiedian and directed edge, described defect parameters include:Defect path, defect number of paths and defect course number of nodes,
L=L0+m;N=N0+n;P=P0+q
Wherein, L represents defect path;L0Represent defect path initial length;M represents ability in described history learning path
Gradient is 0 or the number of the directed edge of negative value;
N represents defect number of paths;N0Represent defect path initial number;N represents continuous ability in described history learning path
Gradient is 0 or the number of the directed edge of negative value;
P represents defect course number of nodes;P0Represent defect course node initial number;Q represents institute in described history learning path
The difference of the actual value and desired value of stating ability is the number of the course node of negative value.
4. method according to claim 1 is it is characterised in that defect rank determined by described basis determines described ability
The step of the influence degree of follow-up learning path is included:
According to determined by defect rank determine defect coefficient;
According to described defect coefficient determine every directed edge in described follow-up learning path up to weights,
Wherein, ViRepresent for i-th kind of ability up to weights, KiRepresent the defect coefficient of i-th kind of ability, GiRepresent next class
The desired value of i-th kind of ability of Cheng Jiedian, CiRepresent the condition value of i-th kind of ability of next course node;
The void representing the influence degree to follow-up learning path for the described ability is determined according to described every directed edge up to weights
Quasi-length,
Wherein, dijRepresent the virtual length of j-th directed edge, M represents the number of ability.
5. method according to claim 1 is it is characterised in that described ability includes multi abilities, described according to described energy
The influence degree to described follow-up learning path for the power, continues the study choosing described learner next step in learning path in the rear
The step in path includes:
According to the influence degree to described follow-up learning path for the described ability, by heuritic approach, continue study road in the rear
The minimum follow-up learning path of the influence degree of described ability is chosen, as the learning path of described learner next step in footpath.
6. a kind of selecting device of learning path is it is characterised in that described device includes:
Defect rank determining module, for determined according to the history learning path in learning path model learner ability lack
Sunken grade;
Influence degree determining module, determines the impact to follow-up learning path for the described ability for defect rank determined by basis
Degree;
Choose module, for the influence degree to described follow-up learning path according to described ability, continue learning path in the rear
The middle learning path choosing described learner next step.
7. device according to claim 6 is it is characterised in that described defect rank determining module includes:
Defect parameters determination sub-module, the defect for determining the described ability of learner described in described history learning path is joined
Number;
Meansigma methodss acquisition submodule, for obtaining the meansigma methodss of each actual value of the ability of learned lesson node;
Defect rank determination sub-module, for the meansigma methodss of the defect parameters according to described ability and the actual value of described ability,
Determine the defect rank of described ability.
8. device according to claim 7 is it is characterised in that described learning path model is directed acyclic graph, including class
Cheng Jiedian and directed edge, described defect parameters include:Defect path, defect number of paths and defect course number of nodes,
L=L0+m;N=N0+n;P=P0+q
Wherein, L represents defect path;L0Represent defect path initial length;M represents ability in described history learning path
Gradient is 0 or the number of the directed edge of negative value;
N represents defect number of paths;N0Represent defect path initial number;N represents continuous ability in described history learning path
Gradient is 0 or the number of the directed edge of negative value;
P represents defect course number of nodes;P0Represent defect course node initial number;Q represents institute in described history learning path
The difference of the actual value and desired value of stating ability is the number of the course node of negative value.
9. device according to claim 6 is it is characterised in that described influence degree determining module includes:
Defect coefficient determination sub-module, determines defect coefficient for defect rank determined by basis;
Up to weights determination sub-module, for every directed edge in described follow-up learning path is determined according to described defect coefficient
Up to weights,
Wherein, ViRepresent for i-th kind of ability up to weights, KiRepresent the defect coefficient of i-th kind of ability, GiRepresent next class
The desired value of i-th kind of ability of Cheng Jiedian, CiRepresent the condition value of i-th kind of ability of next course node;
Virtual length determination sub-module, represents described ability to follow-up for being determined up to weights according to described every directed edge
The virtual length of the influence degree of learning path,
Wherein, dijRepresent the virtual length of j-th directed edge, M represents the number of ability.
10. device according to claim 6 is it is characterised in that described ability includes multi abilities, described selection module bag
Include:
Choose submodule, for the influence degree to described follow-up learning path according to described ability, by heuritic approach,
Choose the minimum follow-up learning path of the influence degree of described ability in described follow-up learning path, as described learner next
The learning path of step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610793494.2A CN106469427A (en) | 2016-08-31 | 2016-08-31 | The choosing method of learning path and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610793494.2A CN106469427A (en) | 2016-08-31 | 2016-08-31 | The choosing method of learning path and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106469427A true CN106469427A (en) | 2017-03-01 |
Family
ID=58230297
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610793494.2A Pending CN106469427A (en) | 2016-08-31 | 2016-08-31 | The choosing method of learning path and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106469427A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109360630A (en) * | 2018-10-24 | 2019-02-19 | 浙江师范大学 | Nonparametric cognitive diagnosis method and its equipment suitable for small sample |
CN111341157B (en) * | 2020-02-10 | 2022-04-01 | 武汉知童教育科技有限公司 | Training method for auditory cognitive ability |
-
2016
- 2016-08-31 CN CN201610793494.2A patent/CN106469427A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109360630A (en) * | 2018-10-24 | 2019-02-19 | 浙江师范大学 | Nonparametric cognitive diagnosis method and its equipment suitable for small sample |
CN111341157B (en) * | 2020-02-10 | 2022-04-01 | 武汉知童教育科技有限公司 | Training method for auditory cognitive ability |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Dasaprawira et al. | Developing mathematics questions of PISA type using Bangka context. | |
CN108806341B (en) | Optimal personalized learning path planning method | |
CN109903617B (en) | Personalized exercise method and system | |
CN109118861A (en) | A kind of individualized intelligent tutoring system | |
Prayitno et al. | Enhancing Students' Higher Order Thinking Skills in Science through INSTAD Strategy. | |
CN107544973A (en) | A kind of method and apparatus that data are handled | |
CN109903201A (en) | Personalized culture scheme generation method and system | |
CN110197340A (en) | A kind of learner's H-NTLA method towards online education platform | |
CN109300069A (en) | Acquisition methods, device and the electronic equipment of user's learning path model | |
CN106469427A (en) | The choosing method of learning path and device | |
Semet et al. | Artificial ant colonies and e-learning: An optimisation of pedagogical paths | |
CN107862911A (en) | A kind of teaching preparation system based on mobile Internet | |
Usra et al. | Improving critical thinking ability using teaching game for understanding | |
CN114065031A (en) | Personalized learning path recommendation method based on fuzzy cognitive map | |
Baker et al. | Expert benchmarks for student academic performance: The case for gifted children | |
EGITIM | The role of autonomy in critical thinking | |
Lee et al. | Constructing personal concept map automatically via Correlative Test-Items Structure | |
Calalb | The impact of inquiry based science education on the formation of lifelong learning skills | |
Sharma | Mathematical giftedness: A creative scenario | |
Robledo et al. | Teaching Beyond Borders: Effectiveness of Heuristic Approach in Teaching Science in Public Secondary Schools in Area IV, Division of Batangas, Philippines | |
Seridi et al. | Adaptive instructional planning in intelligent learning systems | |
Javadi et al. | Improving student's modeling framework in a tutorial-like system based on Pursuit learning automata and reinforcement learning | |
CN111815491A (en) | Adaptive learning plan making method and device, readable storage medium and terminal | |
CN109447865A (en) | A kind of learning Content recommended method and system | |
Fernandes et al. | Unleashing the Potential of Reinforcement Learning for Enhanced Personalized Education |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170301 |
|
RJ01 | Rejection of invention patent application after publication |