Online learning information recommendation method and related device

Abstract

An embodiment of the present application provides an online learning information recommendation method and related devices, the method comprising: obtaining learning posture information of a target learning user of online learning, and obtaining first core information input by the target learning user; determining reference learning material recommendation information corresponding to the target learning user according to the first core information; determining first preference information according to the learning posture information; determining target learning material recommendation information from the reference learning material recommendation information according to the first preference information; and displaying the target learning material recommendation information, which can automatically determine and display the learning material recommendation information based on the core information input by the student and the student's posture information, thereby improving the accuracy of learning material recommendation.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an online learning information recommendation method and related devices. Background Art

[0002] With the continuous improvement of the educational environment, online education has been increasingly accepted by users, and online education has also developed rapidly. However, in the existing online education, teachers usually give online lectures and students learn online. When using the above method for online learning, students can usually only accept the lecture knowledge taught by teachers, and their ability to learn independently cannot be mobilized in a timely manner. For example, when recommending learning materials, it is usually teachers who make recommendations. Since teachers usually recommend for student groups, the accuracy of recommending learning materials for individual students is low. Summary of the invention

[0003] The embodiment of the present application provides an online learning information recommendation method and related device, which can automatically determine and display learning material recommendation information based on core information input by students and students' posture information, thereby improving the accuracy of learning material recommendation.

[0004] A first aspect of an embodiment of the present application provides an online learning information recommendation method, which is applied to an online learning robot. The method includes:

[0005] Acquire learning posture information of a target learning user of online learning, and acquire first core information input by the target learning user;

[0006] Determine reference learning material recommendation information corresponding to the target learning user according to the first core information;

[0007] determining first preference information according to the learning posture information;

[0008] Determining target learning material recommendation information from the reference learning material recommendation information according to the first preference information;

[0009] The target learning material recommendation information is displayed.

[0010] In this example, by obtaining the learning posture information of the target learning user of online learning and the first core information input by the target learning user, the reference learning material recommendation information corresponding to the target learning user is determined according to the first core information, the first preference information is determined according to the learning posture information, the target learning material recommendation information is determined from the reference learning material recommendation information according to the first preference information, and the target learning material recommendation information is displayed. Therefore, the learning material recommendation information can be automatically determined and displayed based on the core information input by the student and the student's posture information, thereby improving the accuracy of learning material recommendations.

[0011] In a possible implementation, determining the reference learning material recommendation information corresponding to the target learning user according to the first core information includes:

[0012] Determine first sub-reference learning material recommendation information according to the first core information;

[0013] Determine the current learning association information of the target learning user according to the first core information;

[0014] Determine the associated learning material type information according to the current learning associated information;

[0015] The reference learning material recommendation information is determined from the first sub-reference learning material recommendation information according to the associated learning material type information.

[0016] In a possible implementation, determining the associated learning material type information according to the current learning associated information includes:

[0017] Perform keyword extraction on the current learning association information to obtain a first keyword set;

[0018] Constructing a keyword graph for the first keyword in the first keyword set to obtain a first keyword graph;

[0019] Determine association information between every two first keywords in the first keyword set according to the first keyword graph to obtain a first association information set, and determine group keyword tendency information of the first keyword set according to the first keyword graph;

[0020] Determining target associated information according to the group keyword tendency information and the first associated information set;

[0021] The associated learning material type information is determined according to the target associated information.

[0022] In a possible implementation, determining the group keyword tendency information of the first keyword set according to the first keyword graph includes:

[0023] Extracting core semantic information corresponding to each first keyword from the first keyword graph to obtain a first core semantic information set;

[0024] Determine, according to the first core semantic information set, a semantically associated keyword between every two first keywords to obtain a first semantically associated keyword set;

[0025] Acquire a target semantically associated keyword from the first semantically associated keyword set, where the target semantically associated keyword is a first semantically associated keyword with the largest number of occurrences corresponding to the first semantically associated keyword in the first semantically associated keyword set;

[0026] The tendency information corresponding to the target semantically associated keyword is determined as the group keyword tendency information.

[0027] In a possible implementation, determining the first preference information according to the learning posture information includes:

[0028] determining first attention information according to the learning posture information;

[0029] The first preference information is determined based on the first attention information.

[0030] A second aspect of an embodiment of the present application provides an online learning information recommendation device, which is applied to an online learning robot, and the device includes:

[0031] An acquisition unit, used to acquire learning posture information of a target learning user of online learning, and to acquire first core information input by the target learning user;

[0032] A first determining unit, configured to determine reference learning material recommendation information corresponding to the target learning user according to the first core information;

[0033] a second determining unit, configured to determine first preference information according to the learning posture information;

[0034] a third determining unit, configured to determine target learning material recommendation information from the reference learning material recommendation information according to the first preference information;

[0035] The display unit is used to display the target learning material recommendation information.

[0036] In a possible implementation manner, the first determining unit is configured to:

[0037] Determine first sub-reference learning material recommendation information according to the first core information;

[0038] Determine the current learning association information of the target learning user according to the first core information;

[0039] Determine the associated learning material type information according to the current learning associated information;

[0040] The reference learning material recommendation information is determined from the first sub-reference learning material recommendation information according to the associated learning material type information.

[0041] In a possible implementation, in determining the associated learning material type information according to the current learning associated information, the first determining unit is configured to:

[0042] Perform keyword extraction on the current learning association information to obtain a first keyword set;

[0043] Constructing a keyword graph for the first keyword in the first keyword set to obtain a first keyword graph;

[0044] Determine association information between every two first keywords in the first keyword set according to the first keyword graph to obtain a first association information set, and determine group keyword tendency information of the first keyword set according to the first keyword graph;

[0045] Determining target associated information according to the group keyword tendency information and the first associated information set;

[0046] The associated learning material type information is determined according to the target associated information.

[0047] In a possible implementation, in determining the group keyword tendency information of the first keyword set according to the first keyword graph, the first determining unit is used to:

[0048] Extracting core semantic information corresponding to each first keyword from the first keyword graph to obtain a first core semantic information set;

[0049] Determine, according to the first core semantic information set, a semantically associated keyword between every two first keywords to obtain a first semantically associated keyword set;

[0050] Acquire a target semantically associated keyword from the first semantically associated keyword set, where the target semantically associated keyword is a first semantically associated keyword with the largest number of occurrences corresponding to the first semantically associated keyword in the first semantically associated keyword set;

[0051] The tendency information corresponding to the target semantically associated keyword is determined as the group keyword tendency information.

[0052] In a possible implementation, the first preference information is determined according to the learning posture information, and the second determining unit is used to:

[0053] determining first attention information according to the learning posture information;

[0054] The first preference information is determined based on the first attention information.

[0055] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0056] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application.

[0057] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 A flowchart of an online learning information recommendation method is provided for an embodiment of the present application;

[0060] Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0061] Figure 3 A structural diagram of an online learning information recommendation device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0064] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0065] In order to better understand the online learning information recommendation method provided by the embodiment of the present application, the following first briefly introduces the scenario of applying the online learning information recommendation method. When the target learning user conducts online learning, it is usually conducted through a computer, mobile phone and other devices. The target learning user can be any user who needs to conduct online learning, such as a student, a teacher who needs training, a trainee, etc. The online learning robot can be an application installed on a computer or mobile device. When the target learning user is studying online, when the target learning user sees information that needs to be understood in detail, the information can be marked, for example, by marking it with a mouse, etc., so as to input the core information that needs to be understood in detail. In the existing scheme, after the marking process, the target learning user usually searches for relevant learning materials on the Internet by himself. Since the target learning user is in the learning stage, the understanding of the information may be somewhat insufficient, and it is not possible to better judge the learning materials that need to be used, resulting in the accuracy of the acquired learning material information being insufficient, which affects further learning. Therefore, in response to the above problems, the present application provides an online learning information recommendation method, which can combine the core information input by the target learning user and the collected learning posture information to determine the learning material recommendation information suitable for the target learning user and display it to the target learning user, so that the target learning user can obtain accurate learning material recommendation information and improve the efficiency of subsequent learning.

[0066] See also Figure 1 , Figure 1 The present invention provides a flowchart of an online learning information recommendation method. Figure 1 As shown, the method is applied to an online learning robot, and the method includes:

[0067] 101. Acquire learning posture information of a target learning user of online learning, and acquire first core information input by the target learning user.

[0068] The target learning user may be any user who needs to conduct online learning, such as a student, a teacher who needs training, a trainee, etc.

[0069] The learning posture information may include facial expression information, facial orientation information, sight direction information, sitting posture information, etc. The method for obtaining the learning posture information may be to obtain the online learning image of the target learning user through a camera, and extract the learning posture information from the online learning image. Specifically, for example, multiple continuous online learning images may be obtained, and the learning posture information may be extracted from the multiple continuous online learning images respectively, and then the sight direction information in the learning posture information may be clustered to obtain the sight direction information after clustering, and other learning posture information may be classified by the number of occurrences, and the one with the largest number of occurrences may be used as the corresponding learning posture information. For example, if two different facial expression information appear in multiple continuous images, and the number of images corresponding to each facial expression information is different, the facial expression information with the highest number of images may be determined as the facial expression information in the learning posture information, and the facial orientation information may also be obtained in the same way. When specifically determining the facial expression, facial orientation information, sight direction information, and sitting posture information of the target learning user, a general image processing method may be used to obtain the facial expression, facial orientation information, sight direction information, and sitting posture information of the target learning user.

[0070] The first core information input by the target learning user can be obtained through the target learning user using the online learning terminal. The target learning user can input the first core information through the input device of the terminal, and the input device can be, for example, a handwriting tablet, a mouse, etc. The first core information can be, for example, information that the target learning user needs to search for materials when learning, such as the "xx process" in the "basic principle of the xx process", and another example, "how to use the word xx".

[0071] 102. Determine reference learning material recommendation information corresponding to the target learning user according to the first core information.

[0072] Among them, the sub-reference learning material recommendation information corresponding to the target learning user can be determined according to the first core information, and the reference learning material recommendation information can be determined from the sub-reference learning material recommendation information according to the associated learning material type information determined according to the learning associated information corresponding to the first core information.

[0073] The sub-reference learning material recommendation information may be the name and introduction of a relevant learning paper corresponding to the first core information, the name and introduction of a public document, the name and introduction of a book, etc.

[0074] 103. Determine first preference information according to the learning posture information.

[0075] Among them, the learning attitude information can reflect the target learning user's learning attitude towards the current first core information, etc. For example, since the first core information may be recommended to the target learning user by other learning users, the target learning user's learning attitude towards the first core information may be positive or negative. Therefore, different learning attitudes can indicate the target learning user's preference for the first core information. For example, if the learning attitude is positive, the first preference information may be a preference for learning the learning materials corresponding to the first core information, and if the learning attitude is negative, the first preference information may be a dislike for learning the learning materials corresponding to the first core information. For different preference information, some learning material recommendation information suitable for the target learning user can be selected from the reference learning material recommendation information.

[0076] 104. Determine target learning material recommendation information from the reference learning material recommendation information according to the first preference information.

[0077] For a positive learning attitude, the first preference information may be a preference for learning the learning material corresponding to the first core information, and for a negative learning attitude, the first preference information may be a dislike for learning the learning material corresponding to the first core information. Therefore, for different first preference information, there is a method for determining the target learning material recommendation information from the reference learning material recommendation information, which is as follows:

[0078] If the first preference information is a preference for learning the learning material corresponding to the first core information, the reference learning material recommendation information can be used to determine the target learning material recommendation information. If the first preference information is a dislike for learning the learning material corresponding to the first core information, the reference learning material recommendation information with the highest matching degree with the first core information in the reference learning material recommendation information can be determined as the target learning material recommendation information. The degree of association can be obtained by obtaining the similarity between each learning material in the reference learning material recommendation information and the first core information, and determining the similarity as the matching degree.

[0079] 105. Display the target learning material recommendation information.

[0080] The target learning material recommendation information may be displayed at a specific location on the display screen of the terminal, for example, the target learning material recommendation information may be displayed in the lower left corner area.

[0081] In this example, by obtaining the learning posture information of the target learning user of online learning and the first core information input by the target learning user, the reference learning material recommendation information corresponding to the target learning user is determined according to the first core information, the first preference information is determined according to the learning posture information, the target learning material recommendation information is determined from the reference learning material recommendation information according to the first preference information, and the target learning material recommendation information is displayed. Therefore, the learning material recommendation information can be automatically determined and displayed based on the core information input by the student and the student's posture information, thereby improving the accuracy of learning material recommendations.

[0082] In a possible implementation, a method for determining reference learning material recommendation information corresponding to the target learning user according to the first core information includes:

[0083] A1. Determine first sub-reference learning material recommendation information according to the first core information;

[0084] A2. Determine the current learning association information of the target learning user according to the first core information;

[0085] A3. Determine the associated learning material type information according to the current learning associated information;

[0086] A4. Determine the reference learning material recommendation information from the first sub-reference learning material recommendation information according to the associated learning material type information.

[0087] The first core information can be searched in the database to obtain the first sub-reference learning material recommendation information corresponding to the first core information, and the first sub-reference learning material recommendation information can include the names of multiple learning materials and corresponding brief information. For example, the first core keyword can be extracted from the first core information, and the first core keyword can be searched in the database to obtain the first sub-reference learning material recommendation information corresponding to the first core information.

[0088] The method for determining the current learning-related information based on the first core information can be: determining the information associated with the first core information in the current online learning courseware, and determining the associated information as the current learning-related information. For example, in the current online learning courseware, a reference keyword corresponding to the first core keyword is determined, and the paragraph corresponding to the reference keyword is determined as the current learning-related information. The correspondence between the reference keyword and the first core keyword can be understood as the semantics of the reference keyword and the first core keyword being the same or similar. After obtaining the current learning-related information, the type of learning material information can be determined based on the current learning-related information. For example, keyword extraction can be performed on the current learning-related information to obtain a keyword set, and a keyword map can be constructed based on the keyword set, and finally the associated learning material type information can be determined based on the keyword map. Therefore, the associated learning material type information can be determined through the keyword map, which improves the accuracy of determining the associated learning material type information.

[0089] The sub-reference learning material recommendation information belonging to the associated learning material type corresponding to the associated learning material type information in the first sub-reference learning material recommendation information may be determined as the reference learning material recommendation information.

[0090] In this example, the first sub-reference learning material recommendation information is determined by the first core information, and the reference learning material recommendation information is determined from the first sub-reference learning material recommendation information based on the associated learning material type information determined according to the current learning associated information of the target learning user. Thus, the reference learning material recommendation information can be determined from multiple dimensions, thereby improving the accuracy of determining the reference learning material recommendation information.

[0091] In a possible implementation, a method for determining associated learning material type information according to the current learning associated information includes:

[0092] B1. extracting keywords from the current learning association information to obtain a first keyword set;

[0093] B2. constructing a keyword graph for the first keyword in the first keyword set to obtain a first keyword graph;

[0094] B3. Determine association information between every two first keywords in the first keyword set according to the first keyword graph to obtain a first association information set, and determine group keyword tendency information of the first keyword set according to the first keyword graph;

[0095] B4, determining target associated information according to the group keyword tendency information and the first associated information set;

[0096] B5. Determine the associated learning material type information according to the target associated information.

[0097] A general keyword extraction algorithm may be used to extract the first keyword from the current learning association information to obtain a first keyword set.

[0098] A keyword graph may be constructed for the first keyword in the first keyword set to obtain a first keyword graph. The construction method may be: taking the first keyword as a node, connecting every two keywords, the length of the connecting line represents the similarity between the two keywords, the higher the similarity, the shorter the connecting line, and the lower the similarity, the longer the connecting line. And the association information between the keywords is marked on the connecting line, the association information may be, for example, how the two keywords are associated, which may be specifically understood as the association point between the two keywords, and the association point may be, for example, semantic association, synonym association, formal association, etc.

[0099] The association information between every two first keywords can be directly extracted from the first keyword graph, thereby obtaining a first association information set.

[0100] The first keyword graph may be subjected to group keyword tendency clustering analysis, etc., to obtain group keyword tendency information of the first keyword set. Specifically, for example, the core semantic information corresponding to each first keyword may be extracted from the first keyword graph and clustered to obtain group keyword tendency information.

[0101] The matching degree between each first associated information and the group keyword tendency information is obtained from the first associated information set, and the first associated information with the highest matching degree is determined as the target associated information. The matching degree between the first associated information and the group keyword tendency information can be characterized by the similarity between the first associated information and the group keyword tendency information. The higher the similarity, the higher the matching degree, and the lower the similarity, the lower the matching degree.

[0102] The method for determining the associated learning material type information according to the target associated information may be: determining the associated learning material type information corresponding to the target associated information through a mapping relationship between preset associated information and associated learning material types.

[0103] In this example, a first keyword graph can be constructed, and the first associated information set and group keyword tendency information can be obtained based on the first keyword graph. Finally, the associated learning material type information can be determined based on the first associated information set and the group keyword tendency information, thereby improving the accuracy of determining the associated learning material type information.

[0104] In a possible implementation, a method for determining group keyword tendency information of the first keyword set according to the first keyword graph includes:

[0105] C1. Extracting core semantic information corresponding to each first keyword from the first keyword graph to obtain a first core semantic information set;

[0106] C2. Determine, according to the first core semantic information set, a semantically associated keyword between every two first keywords to obtain a first semantically associated keyword set;

[0107] C3. Acquire a target semantically associated keyword from the first semantically associated keyword set, where the target semantically associated keyword is a first semantically associated keyword with the largest number of occurrences corresponding to the first semantically associated keyword in the first semantically associated keyword set;

[0108] C4. Determine the tendency information corresponding to the target semantically associated keyword as the group keyword tendency information.

[0109] The method for extracting the core semantic information of each first keyword may be to use a general semantic extraction algorithm to perform semantic extraction to obtain initial semantic information, and then perform a de-cluttering process on the initial semantic information to obtain the core semantic information. The method for de-cluttering the initial semantic information may be to delete non-keywords in the initial semantic information, thereby determining the initial semantic information without the non-keywords as the core semantic information.

[0110] The first core semantic information can be subjected to semantically associated keyword analysis to obtain the first semantically associated keyword. Specifically, since the first core semantic information includes multiple semantic keywords, the first semantically associated keyword can be determined from the multiple semantic keywords. For example, a semantic keyword with an associated relationship among the multiple semantic keywords can be determined as the first semantically associated keyword. If there is no semantic keyword with an associated relationship among the multiple semantic keywords, a semantic keyword can be randomly selected from the multiple semantic keywords and determined as the first semantically associated keyword. By randomly selecting, it can be ensured that each semantic keyword has the same probability of being selected, thereby ensuring the balance of the subsequent overall semantically associated keywords when they appear, and improving the accuracy of the final determination of the group keyword tendency information.

[0111] The target semantically associated keyword can be obtained from the first semantically associated keyword set, and the target semantically associated keyword is the first semantically associated keyword with the largest number of occurrences corresponding to the first semantically associated keyword in the first semantically associated keyword set. The tendency information corresponding to the target semantically associated keyword is determined as the group keyword tendency information, so that the final clustering can be achieved, thereby determining the group keyword tendency information, and improving the accuracy of determining the group keyword tendency information.

[0112] In a possible implementation, a method for determining first preference information according to the learning posture information includes:

[0113] D1. determining first attention information according to the learning posture information;

[0114] D2. Determine the first preference information based on the first attention information.

[0115] Among them, the learning posture information includes facial expression information, facial orientation, etc., so the facial expression information, facial orientation, etc. can be analyzed and processed to obtain the first attention information, specifically: perform attention analysis on the facial expression information to obtain the first sub-attention information; perform attention analysis on the facial orientation to obtain the second sub-attention information; determine the first attention information based on the first sub-attention information and the second sub-attention information.

[0116] The method of performing attention analysis on facial expression information to obtain the first sub-attention information may be: different facial expression information has its corresponding facial expression, and the first sub-attention information may be obtained according to the facial expression. Specifically, for example, if the facial expression is a focused expression, the first sub-attention information may be highly focused attention, and highly focused attention indicates that the target learning user may have a high interest in the first core information; if the facial expression is a lazy expression, the first sub-attention information may be distracted, and distracted attention indicates that the target learning user has a low interest in the first core information; if the facial expression is an excited expression, the first sub-attention information may be moderately focused attention. Since the facial expression of the target learning user is an excited expression, it indicates that the target learning user has a moderate interest in the first core information, which is between a high interest and a low interest, and may have some understanding of the content. If the facial expression is a sleepy expression, the first sub-attention information may be distracted, indicating that the target learning user has a low interest in the first core information, etc.

[0117] Attention analysis can be performed based on the facial orientation information to obtain second sub-attention information, which can be specifically as follows: Here, taking a computer as an example for explanation, it is possible to determine whether there is an intersection between the facial orientation and the display plane of the computer's monitor. Whether there is an intersection between the facial orientation and the display plane can be understood as whether the facial orientation has an overlapping part with the display plane, and the display plane can be understood as the display interface of the monitor. For example, if the facial orientation has no intersection with the display interface (the face and the display interface tend to be parallel), then the second sub-attention information can be determined to be low concentration attention; if the facial orientation partially overlaps with the display interface (the angle of intersection between the face and the display interface is greater than zero degrees and less than ninety degrees), then the second sub-attention information can be determined to be moderate concentration attention; if the facial orientation is completely perpendicular to the display interface (the facial orientation is perpendicular to the display interface), then the second sub-attention information can be determined to be high concentration attention.

[0118] The first sub-attention information and the second sub-attention information may be fused to obtain the first attention information. The fusion processing method may be to perform a weight operation on the attention values ​​corresponding to the first sub-attention information and the second sub-attention information to obtain an operation result, and determine the attention information corresponding to the operation result as the first attention information.

[0119] Different attention information corresponds to different preference information. For example, if the attention is highly concentrated or moderately concentrated, the first preference information may be a preference for learning the learning materials corresponding to the first core information. If the attention is poorly concentrated, the first preference information may be a dislike for learning the learning materials corresponding to the first core information.

[0120] In this example, by performing attention analysis on the facial expression information, the first sub-attention information is obtained, and by performing attention analysis on the facial orientation information, the second sub-attention information is obtained. Therefore, the attention information can be acquired in multiple dimensions. Finally, the first attention information is determined based on the first sub-attention information and the second sub-attention information, and the first preference information is determined based on the first attention information, thereby improving the accuracy of acquiring the first preference information of the target learning user.

[0121] For the above embodiments, please refer to Figure 2 , Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application, as shown in the figure, includes a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0122] Acquire learning posture information of a target learning user of online learning, and acquire first core information input by the target learning user;

[0123] Determine reference learning material recommendation information corresponding to the target learning user according to the first core information;

[0124] determining first preference information according to the learning posture information;

[0125] Determining target learning material recommendation information from the reference learning material recommendation information according to the first preference information;

[0126] The target learning material recommendation information is displayed.

[0127] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the terminal includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0128] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0129] In line with the above, see Figure 3 , Figure 3 The present invention provides a schematic diagram of the structure of an online learning information recommendation device. Figure 3 As shown, the device is applied to an online learning robot, and includes:

[0130] An acquisition unit 301 is used to acquire learning posture information of a target learning user of online learning, and to acquire first core information input by the target learning user;

[0131] A first determining unit 302, configured to determine reference learning material recommendation information corresponding to the target learning user according to the first core information;

[0132] A second determining unit 303, configured to determine first preference information according to the learning posture information;

[0133] A third determining unit 304 is used to determine target learning material recommendation information from the reference learning material recommendation information according to the first preference information;

[0134] The display unit 305 is used to display the target learning material recommendation information.

[0135] In a possible implementation, the first determining unit 302 is configured to:

[0136] Determine first sub-reference learning material recommendation information according to the first core information;

[0137] Determine the current learning association information of the target learning user according to the first core information;

[0138] Determine the associated learning material type information according to the current learning associated information;

[0139] The reference learning material recommendation information is determined from the first sub-reference learning material recommendation information according to the associated learning material type information.

[0140] In a possible implementation, in determining the associated learning material type information according to the current learning associated information, the first determining unit 302 is used to:

[0141] Perform keyword extraction on the current learning association information to obtain a first keyword set;

[0142] Constructing a keyword graph for the first keyword in the first keyword set to obtain a first keyword graph;

[0143] Determine association information between every two first keywords in the first keyword set according to the first keyword graph to obtain a first association information set, and determine group keyword tendency information of the first keyword set according to the first keyword graph;

[0144] Determining target associated information according to the group keyword tendency information and the first associated information set;

[0145] The associated learning material type information is determined according to the target associated information.

[0146] In a possible implementation, in determining the group keyword tendency information of the first keyword set according to the first keyword graph, the first determining unit 302 is used to:

[0147] Extracting core semantic information corresponding to each first keyword from the first keyword graph to obtain a first core semantic information set;

[0148] Determine, according to the first core semantic information set, a semantically associated keyword between every two first keywords to obtain a first semantically associated keyword set;

[0149] Acquire a target semantically associated keyword from the first semantically associated keyword set, where the target semantically associated keyword is a first semantically associated keyword with the largest number of occurrences corresponding to the first semantically associated keyword in the first semantically associated keyword set;

[0150] The tendency information corresponding to the target semantically associated keyword is determined as the group keyword tendency information.

[0151] In a possible implementation, the first preference information is determined according to the learning posture information, and the second determining unit 303 is used to:

[0152] determining first attention information according to the learning posture information;

[0153] The first preference information is determined based on the first attention information.

[0154] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the online learning information recommendation methods recorded in the above method embodiments.

[0155] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any one of the online learning information recommendation methods recorded in the above method embodiments.

[0156] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0157] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0158] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0159] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0161] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0162] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0163] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for recommending online learning information, characterized in that: Applied to an online learning robot, the method comprises: Acquire learning posture information of a target learning user of online learning, and acquire first core information input by the target learning user; Determine reference learning material recommendation information corresponding to the target learning user according to the first core information; determining first preference information according to the learning posture information; Determining target learning material recommendation information from the reference learning material recommendation information according to the first preference information; Displaying the target learning material recommendation information; The determining, according to the first core information, the reference learning material recommendation information corresponding to the target learning user includes: Determine first sub-reference learning material recommendation information according to the first core information; Determine the current learning association information of the target learning user according to the first core information; Determine the associated learning material type information according to the current learning associated information; Determining the reference learning material recommendation information from the first sub-reference learning material recommendation information according to the associated learning material type information; The determining of the associated learning material type information according to the current learning associated information includes: Perform keyword extraction on the current learning association information to obtain a first keyword set; Constructing a keyword graph for the first keyword in the first keyword set to obtain a first keyword graph; Determine association information between every two first keywords in the first keyword set according to the first keyword graph to obtain a first association information set, and determine group keyword tendency information of the first keyword set according to the first keyword graph; Determining target associated information according to the group keyword tendency information and the first associated information set; The associated learning material type information is determined according to the target associated information.

2. The online learning information recommendation method according to claim 1, characterized in that: The determining the group keyword tendency information of the first keyword set according to the first keyword graph includes: Extracting core semantic information corresponding to each first keyword from the first keyword graph to obtain a first core semantic information set; Determine, according to the first core semantic information set, a semantically associated keyword between every two first keywords to obtain a first semantically associated keyword set; Acquire a target semantically associated keyword from the first semantically associated keyword set, where the target semantically associated keyword is a first semantically associated keyword with the largest number of occurrences corresponding to the first semantically associated keyword in the first semantically associated keyword set; The tendency information corresponding to the target semantically associated keyword is determined as the group keyword tendency information.

3. The online learning information recommendation method according to any one of claims 1-2, characterized in that: The determining the first preference information according to the learning posture information includes: determining first attention information according to the learning posture information; The first preference information is determined based on the first attention information.

4. An online learning information recommendation device, characterized in that: Applied to online learning robots, the device comprises: An acquisition unit, used to acquire learning posture information of a target learning user of online learning, and to acquire first core information input by the target learning user; A first determining unit, configured to determine reference learning material recommendation information corresponding to the target learning user according to the first core information; a second determining unit, configured to determine first preference information according to the learning posture information; a third determining unit, configured to determine target learning material recommendation information from the reference learning material recommendation information according to the first preference information; A display unit, used to display the target learning material recommendation information; The first determining unit is used for: Determine first sub-reference learning material recommendation information according to the first core information; Determine the current learning association information of the target learning user according to the first core information; Determine the associated learning material type information according to the current learning associated information; Determining the reference learning material recommendation information from the first sub-reference learning material recommendation information according to the associated learning material type information; In the aspect of determining the associated learning material type information according to the current learning associated information, the first determining unit is used to: Perform keyword extraction on the current learning association information to obtain a first keyword set; Constructing a keyword graph for the first keyword in the first keyword set to obtain a first keyword graph; Determine association information between every two first keywords in the first keyword set according to the first keyword graph to obtain a first association information set, and determine group keyword tendency information of the first keyword set according to the first keyword graph; Determining target associated information according to the group keyword tendency information and the first associated information set; The associated learning material type information is determined according to the target associated information.

5. A terminal, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 3.

Images