Learning Path Display Method, Learning Path Generation Method, Device, and Storage Medium

Abstract

The present application relates to a learning path display method, a learning path generation method, an apparatus and a storage medium. The learning path display method includes: receiving first answer content input by a user for a first assessment exercise; when the user's weak knowledge meets a first preset condition, displaying a target learning path, where the target learning path is generated based on the weak knowledge points and the associated knowledge points on which the weak knowledge points depend, and the target learning path includes the weak knowledge points and the associated knowledge points. The present application can solve the problems in the prior art that students need to independently formulate learning plans and cannot promptly conduct consolidation learning when there are knowledge points with low student mastery.

Description

Technical Field

[0001] This application relates to the field of online education technology, and particularly relates to a learning path display method, a learning path generation method, a device and a storage medium. Background Art

[0002] As an important goal of evaluating teaching and learning, after-class exercises are an indispensable part of education. However, the traditional offline after-class exercise method can no longer meet the needs of modern education. With the development of the Internet, online answering systems have emerged. Students can actively conduct after-class exercises in the online answering system after class, and the background will count the students' answering situations to obtain the students' mastery levels of various knowledge points, that is, obtain the results of the students' cognitive abilities.

[0003] In the prior art, students can view their cognitive ability results through the online answering system and can independently formulate learning plans based on the cognitive ability results to study and consolidate weak knowledge points. However, this learning and consolidation method lacks scientificity. Moreover, if there are some knowledge points with relatively low mastery levels in the problem-solving course and students cannot promptly conduct consolidation learning, it may also affect the learning progress of subsequent knowledge points during the subsequent learning process. Summary of the Invention

[0004] The technical problem to be solved by this application is to provide a learning path display method, a learning path generation method, a device and a storage medium, which can solve the problems in the prior art that students need to independently formulate learning plans and cannot promptly conduct consolidation learning when there are knowledge points with low mastery levels among students.

[0005] To solve the above technical problems, on the one hand, the present application provides a learning path display method, the method comprising: receiving first answer content input by a user for a first assessment exercise; when the user's weak knowledge points meet a first preset condition, displaying a target learning path, the target learning path being generated based on the weak knowledge points and associated knowledge points on which the weak knowledge points depend, the target learning path including the weak knowledge points and the associated knowledge points. On the other hand, the present application provides a learning path generation method, the method comprising: obtaining first answer content of a user for a first assessment exercise, and determining at least one weak knowledge point of the user according to the first answer content; for each of the weak knowledge points, determining associated knowledge points on which the weak knowledge point depends based on a preset relationship, and forming at least one learning short path according to the weak knowledge point and the associated knowledge points, the learning short path including the weak knowledge point and the associated knowledge points; calculating the learning difficulty of each of the learning short paths, and taking the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point; and fusing the optimal learning short paths of at least one of the weak knowledge points to obtain a target learning path including each weak knowledge point.

[0006] On the other hand, the present application provides a learning path display device, the device comprising: a first answer content receiving module, configured to receive first answer content input by a user for a first assessment exercise; a target learning path display module, configured to display a target learning path when the user's weak knowledge points meet a first preset condition, the target learning path being generated based on the weak knowledge points and associated knowledge points on which the weak knowledge points depend, the target learning path including the weak knowledge points and the associated knowledge points.

[0007] On the other hand, the present application provides a learning path generation device, the device comprising: a weak knowledge point determination module, configured to obtain first answer content of a user for a first assessment exercise, and determine at least one weak knowledge point of the user according to the first answer content; a learning short path generation module, configured to, for each of the weak knowledge points, determine associated knowledge points on which the weak knowledge point depends based on a preset relationship, and form at least one learning short path according to the weak knowledge point and the associated knowledge points, the learning short path including the weak knowledge point and the associated knowledge points; an optimal learning short path generation module, configured to calculate the learning difficulty of each of the learning short paths, and take the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point; and a target learning path generation module, configured to fuse the optimal learning short paths of at least one of the weak knowledge points to obtain a target learning path including each weak knowledge point.

[0008] On the other hand, the present application provides a computer storage medium storing at least one instruction, at least one program, a code set or an instruction set, which is loaded and executed by a processor to perform the method as described above.

[0009] Implementing the embodiments of the present application has the following beneficial effects:

[0010] By receiving the first answer content input by the user for the first evaluation exercise and displaying a target learning path when the user's weak knowledge points meet the first preset condition, the target learning path is generated based on the weak knowledge points and the associated knowledge points on which the weak knowledge points depend, and the target learning path includes the weak knowledge points and the associated knowledge points. It is possible to automatically plan a personalized learning path according to the relationship between the weak knowledge points and the associated knowledge points of the student, avoiding the student independently formulating a learning plan according to the results of their own cognitive ability, improving the scientific nature of consolidated learning. Moreover, during the student's independent practice process, adopting an attitude of "detecting and treating early" for weak knowledge points can promptly consolidate learning when a certain number of knowledge points with low mastery degrees appear, avoiding affecting the learning progress of subsequent knowledge points. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 is a schematic diagram of the hardware environment provided by the embodiments of the present application;

[0013] Figure 2 is a flowchart of a learning display method provided by the embodiments of the present application;

[0014] Figure 3 is an operation schematic diagram of displaying a target learning path in a learning display method provided by the embodiments of the present application;

[0015] Figure 4 is a flowchart of displaying learning materials in a learning display method provided by the embodiments of the present application;

[0016] Figure 5 is a flowchart of displaying the latest mastery status of weak knowledge points in a learning display method provided by the embodiments of the present application;

[0017] Figure 6It is a flowchart of a learning display method provided by an embodiment of the present application;

[0018] Figure 7 It is a flowchart of forming a learning short path in a learning display method provided by an embodiment of the present application;

[0019] Figure 8 It is a flowchart of scoring a learning short path in a learning display method provided by an embodiment of the present application;

[0020] Figure 9 It is a flowchart of generating a target learning path in a learning display method provided by an embodiment of the present application;

[0021] Figure 10 It is a flowchart of the user's answering process provided by an embodiment of the present application;

[0022] Figure 11 It is a schematic structural diagram of a learning path display device provided by an embodiment of the present application;

[0023] Figure 12 It is a schematic structural diagram of a learning path generation device provided by an embodiment of the present application;

[0024] Figure 13 It is a schematic structural diagram of a learning path display device and a learning path generation device provided by an embodiment of the present application. Detailed implementation manners

[0025] To make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0027] This application involves the following key terms, and the meanings of each key term are as follows.

[0028] The forward and backward relationship in the knowledge graph: The forward and backward relationship is generated based on prior teaching and research knowledge. It represents the dependency relationship between knowledge points. For example, knowledge point a is a prerequisite knowledge point for knowledge point b, that is, knowledge point b depends on knowledge point a.

[0029] Knowledge tree: The knowledge tree is also generated based on prior teaching and research knowledge. It represents the organizational relationship of knowledge points in a subject system, similar to the table of contents structure of a book. In practical applications, knowledge points all refer to the leaf nodes in the knowledge tree, and the weak knowledge points to be diagnosed are also the leaf nodes in the knowledge tree. The internal nodes in the knowledge tree are used to represent the hierarchical organizational relationship.

[0030] Knowledge point: All knowledge points involved in this application refer to the leaf nodes of the knowledge tree, and by default, they do not cross academic disciplines or school levels. That is, all knowledge points involved in this application refer to knowledge points within a subject system, such as junior high school mathematics, high school physics, etc.

[0031] The embodiments of the present invention provide a learning path display method and a learning path generation method. Optionally, in the embodiments of the present invention, the above learning path display method and learning path generation method can be applied to Figure 1 the hardware environment composed of the server 102 and the terminal 104 as shown. As Figure 1 shown, the server 102 is connected to the terminal 104 through a network. The above network includes but is not limited to: wide area network, metropolitan area network or local area network. The terminal 104 is not limited to a PC, mobile phone, tablet computer, etc. The learning path display method and learning path generation method of the embodiments of the present invention can be executed by the server 102, or can be executed by the terminal 104, or can also be jointly executed by the server 102 and the terminal 104. Among them, when the terminal 104 executes the learning path display method of the embodiments of the present invention, it can also be executed by the client installed on it.

[0032] The following Figure 2 is used to illustrate a learning path display method provided by the embodiments of the present invention. This method is applied to the client. As Figure 2 shown, the method includes:

[0033] Step S201: Receive the first answer content input by the user for the first assessment exercise;

[0034] In an embodiment of the present invention, the first assessment exercise refers to an exercise used to test the user's mastery of one or several knowledge points. The first assessment exercise may be included in the first assessment exercise set, and the first assessment exercise set may include one or more of the first assessment exercises. The first answer content refers to the answer content fed back by the user for at least one of the first assessment exercises.

[0035] In practical applications, an input area for the user to perform text editing may be set on the display interface. For example, the input area may be a text box displayed on the display interface of the client, so that the user can input the first answer content corresponding to the first assessment exercise in the input area.

[0036] Step S203: When the user's weak knowledge points meet the first preset condition, display a target learning path, which is generated based on the weak knowledge points and the associated knowledge points on which the weak knowledge points depend. The target learning path includes the weak knowledge points and the associated knowledge points.

[0037] In an embodiment of the present invention, the weak knowledge point refers to a knowledge point whose mastery degree is less than the preset mastery degree. For example, when the mastery degree of a completely mastered knowledge point is 1, the preset mastery degree is set to 0.6. When the mastery degree of a certain knowledge point is less than 0.6, it means that this knowledge point is a weak knowledge point. On the contrary, when the mastery degree of a certain knowledge point is greater than or equal to 0.6, it means that this knowledge point is not a weak knowledge point.

[0038] Optionally, the first preset condition may be that the number of the user's weak knowledge points is greater than or equal to a preset value. That is, the step of displaying the target learning path when the user's weak knowledge points meet the first preset condition may include:

[0039] When the number of the user's weak knowledge points is greater than or equal to the preset value, display the target learning path.

[0040] It can be understood that as the user answers questions, the user's weak knowledge points will gradually emerge along with the first answer content. At this time, the client can monitor the cumulative number of the user's weak knowledge points.

[0041] For example, after the user completes the first exercise in the first assessment exercise set, the client determines that the user has a weak knowledge point a according to the answer content of the user for the first exercise. At this time, the client can monitor that the number of the user's weak knowledge points is 1; after the user completes the second exercise in the first assessment exercise set, the client determines that the user has weak knowledge points b and c according to the answer content of the user for the second exercise. At this time, the client can monitor that the number of the user's weak knowledge points is 3.

[0042] The preset value can be determined based on tests. For example, through user tests, it is determined that when the number of a user's weak knowledge points exceeds 3, it will affect the learning of subsequent knowledge points. At this time, the preset value can be determined as 3.

[0043] Optionally, the first preset condition can also be that a weak knowledge point is monitored, and the first instruction trigger control of the message prompt identifier corresponding to the weak knowledge point is triggered. That is, the step of displaying the target learning path when the user's weak knowledge point meets the first preset condition can include:

[0044] When each weak knowledge point is monitored, a message prompt identifier is displayed in a preset peripheral area of the answering area corresponding to the weak knowledge point, and the message prompt identifier includes a first instruction trigger control;

[0045] If the first instruction trigger control is triggered, the target learning path corresponding to the weak knowledge point is displayed.

[0046] For example, as Figure 3 shown, when each weak knowledge point of a user is monitored, a floating bubble can be displayed around the answering area corresponding to the weak knowledge point. After the user clicks on the floating bubble, the floating bubble breaks, and the target learning path corresponding to the weak knowledge point is displayed.

[0047] In practical applications, by displaying the message prompt identifier around the answering area, the user can be reminded in a timely manner to learn the weak knowledge points. Moreover, since the display of the target learning path responds to the user's operation on the message prompt identifier, the sudden pop-up of the target learning path can be reduced to disturb the user during the problem-solving process. The target display path is only displayed when the user himself triggers the message prompt identifier, thus being more in line with the actual needs of the user and improving the user experience.

[0048] Optionally, the first preset condition can also be that the weak knowledge point is an important knowledge point. That is, the step of displaying the target learning path when the user's weak knowledge point meets the first preset condition can include: when the weak knowledge point is an important knowledge point, the target learning path is displayed.

[0049] Specifically, the importance of each knowledge point can be marked in advance. If a knowledge point is marked as important, it means that the marked knowledge point is an important knowledge point.

[0050] The associated knowledge point refers to the knowledge point that the user needs to rely on to understand the weak knowledge point. The associated knowledge point can be a pre - knowledge point, or a sibling node of the weak knowledge point on the knowledge tree, that is, a node having the same parent node as the weak knowledge point.

[0051] Each knowledge point in the target learning path may be provided with a label. Through the labels of each knowledge point, the user can know the knowledge points that need to be learned.

[0052] In practical applications, the background server may analyze the first answer content to obtain the user's mastery of each knowledge point, and determine the knowledge points with a mastery less than the preset mastery as weak knowledge points. At the same time, the background server will also update the user's mastery of each knowledge point to the user's cognitive ability map in real time for subsequent query and invocation.

[0053] Of course, the process that can be executed by the background server above can also be executed by the terminal where the client is located, and the present application does not limit this.

[0054] In the embodiments of the present invention, by displaying the target learning path when the weak knowledge points meet the first preset condition, the target learning path is generated based on the weak knowledge points and the associated knowledge points on which the weak knowledge points depend. The target learning path includes the weak knowledge points and the associated knowledge points, so that a personalized learning path can be automatically planned according to the relationship between the user's weak knowledge points and the associated knowledge points, avoiding students formulating their own learning plans according to the results of their cognitive abilities, improving the scientific nature of consolidation learning, and, during the process of students' independent practice, taking an attitude of "detecting early and treating early" towards weak knowledge points, and can conduct consolidation learning in time when a certain number of knowledge points with low mastery appear, avoiding affecting the learning progress of subsequent knowledge points.

[0055] In some embodiments, as Figure 4 shown, both the weak knowledge points and the associated knowledge points include second instruction trigger controls, and the second instruction trigger controls are used to trigger learning materials associated with the corresponding knowledge points; correspondingly, the method may further include:

[0056] Step S401: If the second instruction trigger control is triggered, obtain the learning materials associated with the corresponding knowledge point;

[0057] Step S403: Display the learning materials on the display interface.

[0058] Specifically, the learning materials may be learning materials such as books, audio, or video.

[0059] In step S401, the obtaining of the learning materials associated with the corresponding knowledge point may include: sending a learning material acquisition request to the background server, where the learning material acquisition request includes the corresponding knowledge point; receiving the learning materials associated with the corresponding knowledge point returned by the background server in response to the learning material acquisition request.

[0060] In practical applications, when the user clicks on any second instruction trigger control, learning materials corresponding to the knowledge points of the second instruction trigger control will be displayed on the display interface. For example, when the user triggers the button corresponding to the knowledge point "Calculus", a learning video corresponding to the knowledge point "Calculus" will be played. It can be seen that the embodiment of the present invention provides a quick entry from knowledge points to learning materials. When the user needs to learn relevant materials, the user can quickly retrieve the learning materials without switching to other platforms, which is convenient for the user's learning.

[0061] In some embodiments, as Figure 5 shown, the method may further include:

[0062] Step S501: In response to the user's re-evaluation request, obtain a second evaluation exercise set, where the second evaluation exercise set is generated based on the weak knowledge points included in the target learning path, and the second evaluation exercise set includes second evaluation exercises;

[0063] Step S503: Display the second evaluation exercises on the display interface;

[0064] Step S505: Receive the second answer content of the user for the second evaluation exercises;

[0065] Step S507: Monitor the user's latest mastery status of the weak knowledge points, where the latest mastery status is determined based on the second answer content;

[0066] Step S509: Display the latest mastery status on the display interface.

[0067] In the embodiment of the present invention, the second evaluation exercise set may include one or more of the second evaluation exercises. The second evaluation exercise refers to an exercise used to test the user's mastery of one or several weak knowledge points in the target learning path, and the second answer content refers to the answer content fed back by the user for at least one of the second evaluation exercises.

[0068] The latest mastery status may be characterized as the latest mastery degree (for example, the latest mastery degree is 0.6), or may be characterized as not mastered or mastered.

[0069] In practical applications, the user can exit learning and apply for re-evaluation at any time. Since the second evaluation exercise set is generated based on the weak knowledge points included in the target learning path, therefore, the user's performance on the weak knowledge points can be evaluated with fewer questions. At the same time, after the evaluation, since the latest mastery status is displayed on the display interface, the user can intuitively see whether their cognitive level on the weak knowledge points has improved. The embodiment of the present invention also provides a learning path generation method, asFigure 6 As shown, the method includes:

[0070] Step S601: Obtain the first answering content of the user for the first assessment exercise, and determine at least one weak knowledge point of the user according to the first answering content;

[0071] Step S603: For each weak knowledge point, determine the associated knowledge points on which the weak knowledge point depends based on a preset relationship, and form at least one learning short path according to the weak knowledge point and the associated knowledge points, where the learning short path includes the weak knowledge point and the associated knowledge points;

[0072] In an embodiment of the present invention, the preset relationship may be a preset front - back relationship, or may be a preset acquisition order of knowledge points and a preset knowledge tree structure.

[0073] For example, for the weak knowledge point a, based on the preset front - back relationship, the pre - knowledge point b of a can be found, and the pre - knowledge point c of b can be found, then a learning short path of c -> b -> a can be formed.

[0074] Step S605: Calculate the learning difficulty of each learning short path, and use the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point;

[0075] Step S607: Integrate the optimal learning short paths of at least one weak knowledge point to obtain a target learning path including each weak knowledge point.

[0076] In an embodiment of the present invention, when a target learning path needs to be generated, the target learning path can be generated in time, meeting the requirement of real - time human - computer interaction. At the same time, by scoring each learning short path, the optimal learning short path can be selected for integration, thus facilitating the user's learning of weak knowledge points.

[0077] In some embodiments, as Figure 7 shown, determining the associated knowledge points on which the weak knowledge point depends based on the preset relationship, and forming at least one learning short path according to the weak knowledge point and the associated knowledge points may include:

[0078] Step S701: Determine whether the front - back relationship ratio is greater than or equal to a preset value, where the front - back relationship ratio is the ratio of the number of front - back relationship edges between leaf nodes in the same knowledge tree to the number of all leaf nodes;

[0079] In the embodiments of the present invention, the front-back relationship ratio is used to characterize the sparsity of the front-back relationship, and the preset value can be determined based on experiments. For example, when the preset value is set to 80%, and the current front-back relationship ratio is less than 80%, it indicates that the front-back relationship is relatively sparse. At this time, it is impossible to plan a learning short path by searching for the prerequisite knowledge points of the weak knowledge points.

[0080] Step S703: When the front-back relationship ratio is greater than or equal to the preset value, use the weak knowledge point as the current search node, and search for the prerequisite knowledge points of the current search node according to the pre-set front-back relationship.

[0081] For example, in the pre-set front-back relationship, it is set that the prerequisite knowledge point of knowledge point a is b, and the prerequisite knowledge point of knowledge point b is c. Then, for the weak knowledge point a, use it as the current search node, and according to the pre-set front-back relationship, the prerequisite knowledge point b of the weak knowledge point a can be found.

[0082] Step S705: Use the found prerequisite knowledge point as the current search node, and search for the prerequisite knowledge points of the current search node again according to the pre-set front-back relationship. Through multiple iterations, find the associated knowledge points relied on by the weak knowledge point one by one.

[0083] For example, use the found prerequisite knowledge point b as the current search node, and continue to search for the prerequisite knowledge point c of the prerequisite knowledge point b according to the pre-set front-back relationship, and keep iterating to find the associated knowledge points relied on by the weak knowledge point until the second preset condition is met and the iteration stops.

[0084] Step S707: When the second preset condition is met, stop the search, and form at least one learning short path according to the weak knowledge point and the found associated knowledge points.

[0085] In the embodiments of the present invention, the second preset condition may be that there are a preset number of knowledge points in the learning short path, there are no prerequisite knowledge points, or the mastery level of the prerequisite knowledge points is greater than or equal to the preset mastery threshold. When any of the second preset conditions is met, stop the iteration, and form at least one learning short path according to the weak knowledge point and the found associated knowledge points.

[0086] For example, when the second preset condition is that there are already 3 knowledge points in the learning short path, stop the iteration. Then, when the prerequisite knowledge point c of knowledge point b is found, there are 3 knowledge points in the learning short path. At this time, stop the iteration, and form the learning short path c->b->a of the weak knowledge point a according to these 3 knowledge points.

[0087] In some embodiments, such as Figure 7As shown, determining the associated knowledge points relied on by the weak knowledge points based on a preset relationship and forming at least one learning short path according to the weak knowledge points and the associated knowledge points may further include:

[0088] Step S702: When the front-to-back relationship ratio is less than a preset value, search for sibling nodes of the weak knowledge points according to the pre-set knowledge tree structure;

[0089] Step S704: Sort the weak knowledge points and the sibling nodes according to the pre-set acquisition order;

[0090] Step S706: Form at least one learning short path according to the sibling nodes located before the weak knowledge points and the weak knowledge points after sorting.

[0091] For example, according to Step S702, it is found that the weak knowledge point a has sibling nodes b, c, and e, and the sorting according to the acquisition order is c, e, a, b, then the learning short path c->e->a is obtained.

[0092] In practical applications, even if the front-to-back relationship of the knowledge points in the structure tree is relatively sparse, for each weak knowledge point, at least one learning short path can be found.

[0093] In some embodiments, as Figure 8 shown, calculating the learning difficulty of each of the learning short paths and taking the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point may include: Step S801: Obtain the index data of each learning short path under each path difficulty coefficient index, and the path difficulty coefficient index includes at least one of the following: the path length of the learning short path, the cumulative difference in the mastery of adjacent two knowledge points in the learning short path, and the number of times the knowledge points in the learning short path appear in the learning short paths of other weak knowledge points;

[0094] For example, there are two weak knowledge points a and b. Among them, the weak knowledge point a has two learning short paths c->b->a and c->d->a, the learning short path of the weak knowledge point b is f->e->d->b, the mastery of the weak knowledge point a is 0.2, the mastery of the knowledge point b is 0.5, the mastery of the knowledge point c is 0.7, and the mastery of the knowledge point d is 0.8.

[0095] Then, as shown in Table 1, the learning short path (c->b->a) of the weak knowledge point a has an index data of 3 in the index of the path difficulty coefficient index "the path length of the learning short path (Index 1)" (since the number of nodes can represent the path length, the number of nodes 3 is used as the index data). The learning short path (c->d->a) of the weak knowledge point a also has an index data of 3 under the index of the path difficulty coefficient index "the path length of the learning short path".

[0096] Table 1

[0097]

[0098] The learning short path (c->b->a) of the weak knowledge point a has an index data of 0.5 in the index of the path difficulty coefficient index "the cumulative difference in the mastery degrees of two adjacent knowledge points in the learning short path (Index 2)" (the difference between adjacent knowledge points a and b is 0.3, and the difference between adjacent knowledge points b and c is 0.2, and their cumulative difference is 0.5). The learning short path (c->d->a) of the weak knowledge point a has an index data of 0.7 under the index of the path difficulty coefficient index "the cumulative difference in the mastery degrees of two adjacent knowledge points in the learning short path" (the difference between adjacent knowledge points a and d is 0.6, and the difference between adjacent knowledge points d and c is 0.1, and their cumulative difference is 0.7).

[0099] The learning short path (c->b->a) of the weak knowledge point a has an index data of 1 in the index of the path difficulty coefficient index "the number of times the knowledge points in the learning short path appear in the learning short paths of other weak knowledge points (Index 3)" (only node b appears 1 time in the learning short path of other weak knowledge point b). The learning short path (c->d->a) of the weak knowledge point a has an index data of 1 under the index of the path difficulty coefficient index "the number of times the knowledge points in the learning short path appear in the learning short paths of other weak knowledge points" (only node d appears 1 time in the learning short path of other weak knowledge point b).

[0100] Step S803: Determine the difficulty value of each said learning short path under each path difficulty coefficient index according to the index data under each path difficulty coefficient index.

[0101] In the embodiment of the present invention, a difficulty value scoring table may be preset. The difficulty value scoring table may include the difficulty values corresponding to different index data under each path difficulty coefficient index; wherein,

[0102] Since the longer the learning short path is, the higher the learning cost of the user is. Therefore, for the path difficulty coefficient index "the path length of the learning short path", the difficulty value scoring table can stipulate that as the index data decreases, the corresponding difficulty value gradually decreases, so as to shorten the user's learning path as much as possible and save the user's learning cost. For example, in the difficulty value scoring table, it is stipulated that when the path length of the learning short path is 4, the corresponding difficulty value is 95; when the path length of the learning short path is 3, the corresponding difficulty value is 90; when the path length of the learning short path is 2, the corresponding difficulty value is 80.

[0103] Combined with the example in step S801, the index data of the learning short path (c->b->a) of the weak knowledge point a under the path difficulty coefficient index "the path length of the learning short path" is 3. Then, as shown in Table 1, the difficulty value of the learning short path (c->b->a) of the weak knowledge point a under the path difficulty coefficient index "the path length of the learning short path" is 90;

[0104] The index data of the learning short path (c->d->a) of the weak knowledge point a under the path difficulty coefficient index "the path length of the learning short path" is also 3. Then, as shown in Table 1, the difficulty value of the learning short path (c->d->a) of the weak knowledge point a under the path difficulty coefficient index "the path length of the learning short path" is also 90.

[0105] Since the greater the cumulative difference in the mastery degrees of two adjacent knowledge points in the learning short path, the greater the learning difficulty of the user. Therefore, for the path difficulty coefficient index "the cumulative difference in the mastery degrees of two adjacent knowledge points in the learning short path", the difficulty value scoring table can stipulate that as the index data decreases, the corresponding difficulty value gradually decreases, so as to make the learning process of the path more step by step and smoother as much as possible. For example, in the difficulty value scoring table, it is stipulated that when the cumulative difference is 0.7, the corresponding difficulty value is 90; when the cumulative difference is 0.6, the corresponding difficulty value is 80; when the cumulative difference is 0.5, the corresponding difficulty value is 70.

[0106] Combined with the example in step S801, the index data of the learning short path (c->b->a) of the weak knowledge point a under the path difficulty coefficient index "the cumulative difference in the mastery degrees of two adjacent knowledge points in the learning short path" is 0.5. Then, as shown in Table 1, the difficulty value of the learning short path (c->b->a) of the weak knowledge point a under the path difficulty coefficient index "the cumulative difference in the mastery degrees of two adjacent knowledge points in the learning short path" is 70;

[0107] The indicator data of the short learning path (c->d->a) of weak knowledge point a under the path difficulty coefficient indicator "the cumulative difference in the mastery of two adjacent knowledge points in the short learning path" is 0.7. As shown in Table 1, the difficulty value of the short learning path (c->d->a) of weak knowledge point a under the path difficulty coefficient indicator "the cumulative difference in the mastery of two adjacent knowledge points in the short learning path" is 90.

[0108] Since each subsequent short learning path will be integrated into the target learning path, the difficulty value scoring table can stipulate that as the indicator data increases, the corresponding difficulty value gradually decreases, so that knowledge points with higher centrality can be used in the path as much as possible. For example, the preset scoring rule stipulates that when the number of occurrences is 1, the corresponding indicator score is 30, when the number of occurrences is 2, the corresponding indicator score is 25, and when the number of occurrences is 3, the corresponding indicator score is 20.

[0109] Combined with the example in step S801, the index data of the learning short path (c->b->a) of the weak knowledge point a under the path difficulty coefficient indicator "the number of times the knowledge point in the learning short path appears in the learning short paths of other weak knowledge points" is 1. Then, as shown in Table 1, the difficulty value of the learning short path (c->b->a) of the weak knowledge point a under the path difficulty coefficient indicator "the number of times the knowledge point in the learning short path appears in the learning short paths of other weak knowledge points" is 30;

[0110] The indicator data of the learning short path of weak knowledge point a (c->d->a) under the path difficulty coefficient indicator "the number of times the knowledge points in the learning short path appear in the learning short paths of other weak knowledge points" is 1. Then, as shown in Table 1, the difficulty value of the learning short path of weak knowledge point a (c->d->a) under the path difficulty coefficient indicator "the number of times the knowledge points in the learning short path appear in the learning short paths of other weak knowledge points" is 30.

[0111] Step S805: Calculate the learning difficulty of each of the short learning paths according to the difficulty values under each path difficulty coefficient indicator.

[0112] For each short learning path, the sum of the difficulty values under each path difficulty coefficient indicator of the short learning path is taken as the learning difficulty of the short learning path.

[0113] For example, for the short learning path (c->b->a) of the weak knowledge point a, as shown in Table 1, the sum of its difficulty values is 190. For the short learning path (c->d->a) of the weak knowledge point a, the sum of its difficulty values is 210. Therefore, the short learning path (c->b->a) with the lowest learning difficulty can be used as the optimal learning path for the weak knowledge point a.

[0114] In practical applications, by scoring the short learning paths of each weak knowledge point, a short learning path with low learning cost and low learning difficulty can be selected from at least one short learning path of each weak knowledge point, thereby facilitating the user's learning of weak knowledge points.

[0115] In some embodiments, as Figure 9 described, fusing the optimal learning paths of at least one of the weak knowledge points to obtain a target learning path including each weak knowledge point may include:

[0116] Step S901: If the starting nodes in each of the optimal learning paths are different, sort each of the optimal learning paths according to the acquisition order of the starting nodes;

[0117] Step S903: If the starting nodes in each of the optimal learning paths are the same, sort the optimal learning paths according to the acquisition order of the next node of the starting node;

[0118] Step S905: Concatenate the head and tail of the sorted optimal learning paths to obtain an initial learning path;

[0119] Step S907: Delete the duplicate nodes that appear again in the initial learning path to obtain a target learning path including each weak knowledge point.

[0120] For example, the optimal learning short path for weak knowledge point a is c -> b -> a, and the learning short path for weak knowledge point b is f -> e -> d -> b. Obviously, the starting node c of the optimal learning short path for weak knowledge point a is different from the starting node f of the optimal learning short path for weak knowledge point b. At this time, the two optimal learning short paths are sorted according to the acquisition order of the starting node c and the starting node f. Assuming that the acquisition order of the starting node f is after the starting node c, at this time, the optimal learning short path f -> e -> d -> b is arranged after the optimal learning short path c -> b -> a, and the optimal learning short path is spliced after the optimal learning short path according to the method in step S905 to obtain the initial learning path c -> b -> a -> f -> e -> d -> b. Finally, according to the method in step S907, the nodes that appear repeatedly in the initial learning path c -> b -> a -> f -> e -> d -> b are deleted. Obviously, the node b appears repeatedly in the initial learning path. Therefore, the second occurrence of the node b in the path is deleted, and finally the target learning path c -> b -> a -> f -> e -> d is obtained.

[0121] In practical applications, by sorting and splicing each of the optimal learning short paths, and deleting the repeated nodes that appear again in the initial learning path, it can be ensured that the user can learn in the correct order and the user can be prevented from repeating the learning of the knowledge points that have already been learned, thereby improving the learning efficiency of the user.

[0122] For the technical details not described in detail in the above embodiments, reference may be made to the methods provided in any embodiment of the present application.

[0123] The method described in the above embodiments will be further described below in combination with the user's answering process.

[0124] The learning path display method in the above embodiments is specifically executed by the front-end module, and the learning path generation method in the above embodiments is specifically executed by the back-end module. As Figure 10 shown, the specific process of the user's answering process can be as follows:

[0125] The student independently practices after class, and the front-end module receives the first answering content input by the student for the first evaluation exercise;

[0126] The back-end module updates the student's cognitive ability map in real time according to the first answering content;

[0127] The front-end module monitors the number of the student's weak knowledge points;

[0128] When the number of the weak knowledge points is greater than or equal to a preset value, the back-end module generates a target learning path based on the weak knowledge points and the associated knowledge points on which the weak knowledge points depend;

[0129] The front - end module gives a page prompt to the student: Weak knowledge points XXX, XXX are found, and the target learning path has been planned;

[0130] The front - end module obtains the target learning path from the back - end module and displays the target learning path on the display interface, where each knowledge point in the path is a button;

[0131] If the button of a certain knowledge point is triggered, the front - end module enters the learning page, obtains the learning materials associated with the knowledge point whose button is triggered from the back - end module, and displays the learning materials on the display interface;

[0132] In response to the student's re - evaluation request, enter the evaluation page. The front - end module displays the second evaluation exercises in the second evaluation exercise set, receives the second answer content of the student for the second evaluation exercises, and monitors the latest mastery status of the weak knowledge points. The second evaluation exercise set is generated by the back - end module for intelligent test paper compilation based on the weak knowledge points in the target learning path;

[0133] The front - end module displays the latest mastery status of the student regarding the weak knowledge points on the display interface.

[0134] The embodiment of the present invention also provides a learning path display device. Please refer to Figure 11 , and the device includes:

[0135] The first answer content receiving module 1101 is used to receive the first answer content input by the user for the first evaluation exercises;

[0136] The target learning path display module 1102 is used to display the target learning path when the weak knowledge points of the user meet the first preset condition. The target learning path is generated based on the weak knowledge points and the associated knowledge points on which the weak knowledge points depend. The target learning path includes the weak knowledge points and the associated knowledge points.

[0137] In some embodiments, both the weak knowledge points and the associated knowledge points include a second instruction trigger control, and the second instruction trigger control is used to trigger the learning materials associated with the corresponding knowledge points; correspondingly, the device may further include:

[0138] The learning material acquisition module is used to obtain the learning materials associated with the corresponding knowledge points when the second instruction trigger control is triggered;

[0139] The learning material display module is used to display the learning materials on the display interface.

[0140] In some embodiments, the device may further include:

[0141] The second evaluation exercise set acquisition module is used to obtain a second evaluation exercise set in response to a user's re-evaluation request. The second evaluation exercise set is generated based on the weak knowledge points included in the target learning path, and the second evaluation exercise set includes second evaluation exercises;

[0142] The second evaluation exercise display module is used to display the second evaluation exercises on the display interface;

[0143] The second answer content receiving module is used to receive the second answer content of the user for the second evaluation exercises;

[0144] The latest mastery status acquisition module is used to monitor the user's latest mastery status of the weak knowledge points, and the latest mastery status is determined based on the second answer content;

[0145] The latest mastery status display module is used to display the latest mastery status on the display interface.

[0146] An embodiment of the present invention also provides a learning path generation device. Please refer to Figure 12 , and the device includes:

[0147] The weak knowledge point determination module 1201 is used to obtain the first answer content of the user for the first evaluation exercises, and determine at least one weak knowledge point of the user according to the first answer content;

[0148] The learning short path generation module 1202 is used to, for each of the weak knowledge points, determine the associated knowledge points on which the weak knowledge points depend based on a preset relationship, and form at least one learning short path according to the weak knowledge points and the associated knowledge points. The learning short path includes the weak knowledge points and the associated knowledge points;

[0149] The optimal learning short path generation module 1203 is used to calculate the learning difficulty of each of the learning short paths, and use the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point;

[0150] The target learning path generation module 1204 is used to fuse the optimal learning short paths of at least one of the weak knowledge points to obtain a target learning path including each weak knowledge point.

[0151] In some embodiments, the learning short path generation module may include:

[0152] The first search sub-module is used to, when the pre-post relationship ratio is greater than or equal to a preset value, use the weak knowledge point as the current search node, and search for the pre-knowledge points of the current search node according to the pre-set pre-post relationship. The pre-post relationship ratio is the ratio of the number of pre-post relationship edges between leaf nodes in the same knowledge tree to the number of all leaf nodes;

[0153] The second search sub-module is used to use the found pre-knowledge point as the current search node, and search for the pre-knowledge points of the current search node again according to the pre-set pre-post relationship. Through multiple iterations, the associated knowledge points relied on by the weak knowledge point are found one by one;

[0154] The learning short path generation sub-module is used to stop searching when the second preset condition is met, and form at least one of the learning short paths according to the weak knowledge point and the found associated knowledge points; and / or,

[0155] The third search sub-module is used to search for the sibling nodes of the weak knowledge point according to the pre-set knowledge tree structure when the pre-post relationship ratio is less than the preset value;

[0156] The node sorting sub-module is used to sort the weak knowledge point and the sibling nodes according to the pre-set acquisition order;

[0157] The learning short path generation sub-module is further used to form at least one learning short path according to the sibling nodes before the weak knowledge point and the weak knowledge point after sorting;

[0158] In some embodiments, the optimal learning short path generation module may include:

[0159] The index data acquisition sub-module is used to acquire the index data of each learning short path under each path difficulty coefficient index. The path difficulty coefficient index includes at least one of the following: the path length of the learning short path, the cumulative difference in the mastery degrees of two adjacent knowledge points in the learning short path, and the number of times the knowledge points in the learning short path appear in the learning short paths of other weak knowledge points;

[0160] The difficulty value determination sub-module is used to determine the difficulty value of each learning short path under each path difficulty coefficient index according to the index data under each path difficulty coefficient index;

[0161] The learning difficulty calculation sub-module is used to calculate the learning difficulty of each learning short path according to the difficulty values under each path difficulty coefficient index;

[0162] In some embodiments, the target learning path generation module may include:

[0163] The first optimal learning short-path sorting sub-module is used to sort each of the optimal learning short-paths according to the acquisition order of the starting nodes when the starting nodes in each of the optimal learning short-paths are different;

[0164] The second optimal learning short-path sorting sub-module is used to sort the optimal learning short-paths according to the acquisition order of the next nodes of the starting nodes when the starting nodes in each of the optimal learning short-paths are the same;

[0165] The initial learning path generation sub-module is used to splice the head and tail of the sorted optimal learning short-paths to obtain an initial learning path;

[0166] The target learning path generation sub-module is used to delete the repeated nodes that appear again in the initial learning path to obtain a target learning path including each weak knowledge point.

[0167] The device provided in the above embodiment can execute the method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects for executing the method. The technical details not described in detail in the above embodiment can be referred to the method provided in any embodiment of the present application.

[0168] This embodiment also provides a computer-readable storage medium, in which at least one instruction, at least one segment of program, code set or instruction set is stored, and the at least one instruction, at least one segment of program, code set or instruction set is loaded and executed by a processor to execute any one of the methods as described above in this embodiment.

[0169] This embodiment also provides a device, and the structure diagram can be seen in Figure 13, the device 1300 can vary significantly due to different configurations or performances. It may include one or more central processing units (CPUs) 1322 (e.g., one or more processors) and a memory 1332, and one or more storage media 1330 (e.g., one or more mass storage devices) for storing application programs 1342 or data 1344. Among them, the memory 1332 and the storage media 1330 can be transient storage or persistent storage. The programs stored in the storage media 1330 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the device. Further, the central processing unit 1322 can be configured to communicate with the storage media 1330 and execute a series of instruction operations in the storage media 1330 on the device 1300. The device 1300 may also include one or more power supplies 1326, one or more wired or wireless network interfaces 1350, one or more input / output interfaces 1358, and / or one or more operating systems 1341, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc. Any of the above methods in this embodiment can be based on Figure 13 the device shown.

[0170] This specification provides the method operation steps as described in the embodiments or flowcharts, but may include more or fewer operation steps based on routine or non-creative labor. The steps and sequences listed in the embodiments are only one way among many execution sequences of the steps and do not represent the only execution sequence. When the actual system or interrupt product is executed, it can be executed in the order of the methods shown in the embodiments or the drawings or in parallel (e.g., in an environment of parallel processors or multi-threaded processing).

[0171] The structure shown in this embodiment is only a part of the structure related to the solution of this application and does not constitute a limitation on the device to which the solution of this application is applied. The specific device may include more or fewer components than those shown, or combine some components, or have a different arrangement of components. It should be understood that the methods, devices, etc. disclosed in this embodiment can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, indirect coupling or communication connection of device or unit modules.

[0172] Based on such understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0173] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this specification can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0174] As mentioned above, the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of this application.

Claims

1. A learning path display method, characterized in that, The method includes: Receiving first answer content input by the user for the first assessment exercise; When the user's weak knowledge points meet the first preset condition, displaying a target learning path, where the weak knowledge points are determined based on the first answer content; The target learning path is generated based on the following method: For each of the weak knowledge points, determining associated knowledge points on which the weak knowledge point depends based on a preset relationship, and forming at least two learning short paths according to the weak knowledge point and the associated knowledge points, where the learning short paths include the weak knowledge point and the associated knowledge points; Calculating the learning difficulty of each of the learning short paths, and taking the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point; Fusing the optimal learning short paths of at least two weak knowledge points to obtain a target learning path including each weak knowledge point.

2. The learning path display method according to claim 1, wherein The step of displaying the target learning path when the user's weak knowledge points meet the first preset condition includes: When the number of the user's weak knowledge points is greater than or equal to a preset value, displaying the target learning path; or, When each weak knowledge point is detected, displaying a message prompt identifier in a preset peripheral area of the answer area corresponding to the weak knowledge point, where the message prompt identifier includes a first instruction trigger control; If the first instruction trigger control is triggered, displaying the target learning path corresponding to the weak knowledge point.

3. The learning path display method according to claim 1, characterized in that Both the weak knowledge point and the associated knowledge point include a second instruction trigger control, and the second instruction trigger control is used to trigger learning materials associated with the corresponding knowledge point; correspondingly, the method further includes: If the second instruction trigger control is triggered, obtaining the learning materials associated with the corresponding knowledge point; Displaying the learning materials on the display interface.

4. The learning path display method according to claim 1, wherein The method further includes: In response to the user's re-assessment request, obtaining a second assessment exercise set, where the second assessment exercise set is generated based on the weak knowledge points included in the target learning path, and the second assessment exercise set includes second assessment exercises; Displaying the second assessment exercises on the display interface; Receiving second answer content input by the user for the second assessment exercises; Monitoring the user's latest mastery status of the weak knowledge points, where the latest mastery status is determined based on the second answer content; Displaying the latest mastery status on the display interface.

5. A learning path generation method, characterized by The method includes: Obtaining the first answer content input by the user for the first assessment exercise, and determining at least two weak knowledge points of the user according to the first answer content; For each of the weak knowledge points, determining associated knowledge points on which the weak knowledge point depends based on a preset relationship, and forming at least two learning short paths according to the weak knowledge point and the associated knowledge points, where the learning short paths include the weak knowledge point and the associated knowledge points; Calculating the learning difficulty of each of the learning short paths, and taking the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point; Fusing the optimal learning short paths of at least two of the weak knowledge points to obtain a target learning path including each weak knowledge point.

6. The learning path generation method according to claim 5, wherein Calculating the learning difficulty of each of the learning short paths, and taking the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point includes: Obtaining the index data of each of the learning short paths under each path difficulty coefficient index, where the path difficulty coefficient index includes at least one of the following: the path length of the learning short path, the cumulative difference in the mastery degrees of two adjacent knowledge points in the learning short path, and the number of times the knowledge points in the learning short path appear in the learning short paths of other weak knowledge points; Determining the difficulty value of each of the learning short paths under each path difficulty coefficient index according to the index data under each path difficulty coefficient index; Calculating the learning difficulty of each of the learning short paths according to the difficulty values under each path difficulty coefficient index.

7. The learning path generation method according to claim 5, wherein Based on a preset relationship, determining the associated knowledge points on which the weak knowledge point depends, and forming at least two learning short paths according to the weak knowledge point and the associated knowledge points includes: When the front-to-back relationship ratio is greater than or equal to a preset value, taking the weak knowledge point as the current search node, and searching for the pre-knowledge point of the current search node according to the pre-set front-to-back relationship, where the front-to-back relationship ratio is the ratio of the number of front-to-back relationship edges between leaf nodes in the same knowledge tree to the number of all leaf nodes; Taking the found pre-knowledge point as the current search node, and searching for the pre-knowledge point of the current search node again according to the pre-set front-to-back relationship. Through multiple iterations, the associated knowledge points on which the weak knowledge point depends are searched for one by one; When a second preset condition is met, stop searching, and form at least one of the learning short paths according to the weak knowledge point and the found associated knowledge points; and / or, When the front-to-back relationship ratio is less than the preset value, searching for the sibling nodes of the weak knowledge point according to the pre-set knowledge tree structure; Sorting the weak knowledge point and the sibling nodes according to the pre-set acquisition order; Forming at least two learning short paths according to the sibling nodes located before the weak knowledge point and the weak knowledge point after sorting.

8. The learning path generation method according to claim 5, wherein Fusing the optimal learning short paths of at least two of the weak knowledge points to obtain a target learning path including each weak knowledge point includes: If the starting nodes in each of the optimal learning short paths are different, sorting each of the optimal learning short paths according to the acquisition order of the starting nodes; If the starting nodes in each of the optimal learning short paths are the same, sorting the optimal learning short paths according to the acquisition order of the next node of the starting node; Performing head-to-tail splicing on the sorted optimal learning short paths to obtain an initial learning path; Deleting the repeated nodes that appear again in the initial learning path to obtain a target learning path including each weak knowledge point.

9. A learning path display device, characterized in that, The device includes: A first answer content receiving module, configured to receive the first answer content input by the user for the first assessment exercise; A target learning path display module, configured to display a target learning path when the weak knowledge points of the user meet a first preset condition, where the weak knowledge points are determined based on the first answer content; The target learning path is generated based on the following method: For each of the weak knowledge points, based on a preset relationship, determine the associated knowledge points upon which the weak knowledge point depends, and form at least two learning short paths according to the weak knowledge point and the associated knowledge points, where the learning short paths include the weak knowledge point and the associated knowledge points; Calculate the learning difficulty of each of the learning short paths, and use the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point; Fuse the optimal learning short paths of at least two weak knowledge points to obtain a target learning path including each weak knowledge point.

10. A learning path generation device, characterized in that, The device includes: A weak knowledge point determination module, configured to obtain the first answering content of the user for the first evaluation exercise, and determine at least two weak knowledge points of the user according to the first answering content; A learning short path generation module, configured to, for each of the weak knowledge points, based on a preset relationship, determine the associated knowledge points upon which the weak knowledge point depends, and form at least two learning short paths according to the weak knowledge point and the associated knowledge points, where the learning short paths include the weak knowledge point and the associated knowledge points; An optimal learning short path generation module, configured to calculate the learning difficulty of each of the learning short paths, and use the learning short path with the lowest learning difficulty as the optimal learning short path of the weak knowledge point; A target learning path generation module, configured to fuse the optimal learning short paths of at least two weak knowledge points to obtain a target learning path including each weak knowledge point.

11. A computer-readable storage medium, characterized in that, At least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to perform the learning path display method according to any one of claims 1 to 4, or the learning path generation method according to any one of claims 5 to 8.

12. A learning path display device, characterized in that, The learning path display device implements the learning path display method according to any one of claims 1 to 4.

13. A learning path generation device, characterized in that, The learning path generation device implements the learning path generation method according to any one of claims 5 to 8.

Images