Science popularization education knowledge recommendation method and system

Abstract

The invention discloses a science popularization education knowledge recommendation method and system, and relates to the technical field of recommendation service, and the method comprises the following steps: building an emotion recognition mechanism, generating emotion feedback data through an algorithm, and collecting the emotion feedback data of a user in real time; establishing a self-adaptive learning path recommendation mechanism, and dynamically adjusting learning contents and paths according to the collected emotion feedback data of the user; and based on the adjusted learning path, collecting feedback data of the user in the learning process, and evaluating the validity of the learning path and the learning effect of the user. According to the emotion feedback data of the user, personalized learning paths and content recommendation can be dynamically generated, personalized requirements of different learners are met, the learning effect is improved, the emotion feedback data of the user are collected and analyzed in real time through facial expression recognition and voice emotion analysis technologies, and the user experience is improved. The learning content and path are dynamically adjusted according to the emotional state of the user, and more adaptive learning experience is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of recommendation services, and in particular to a method and system for recommending popular science education knowledge. Background Art

[0002] With the development of Internet technology and informatization, online education has become an important way of learning. Traditional online education systems usually rely on fixed course content and learning paths, and cannot be dynamically adjusted according to individual differences and real-time feedback. This single education model is difficult to meet the needs of different learners, especially in the field of popular science education, where learners' interests and emotional states have a significant impact on learning outcomes.

[0003] In the existing online education system, there are mainly the following technical problems:

[0004] Lack of personalized recommendations: Existing systems usually recommend content based on a preset course structure and fixed learning path, which is difficult to adapt to the personalized needs of different learners. Different learners have differences in knowledge base, learning interests, learning habits, etc., and fixed recommendation strategies cannot effectively improve learning outcomes.

[0005] Unable to respond to emotional feedback in real time: Learners may generate various emotional feedback during the learning process, such as interest, confusion, fatigue, etc. These emotional states have a direct impact on learning outcomes, but existing systems are unable to collect and analyze these emotional feedbacks in real time to adjust learning content and paths.

[0006] Recommendation algorithms are not smart enough: Existing recommendation algorithms usually rely on simple statistical models or predefined rules and lack dynamic optimization mechanisms based on real-time user data, resulting in poor recommendation results and difficulty in providing personalized and adaptive learning experiences. Summary of the invention

[0007] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0008] In view of the above problems existing in the existing popular science education knowledge recommendation method, the present invention is proposed.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0010] A method for recommending popular science education knowledge comprises the following steps:

[0011] Establish an emotion recognition mechanism, generate emotion feedback data through algorithms, and collect users’ emotion feedback data in real time;

[0012] Establish an adaptive learning path recommendation mechanism to dynamically adjust learning content and paths based on the collected user emotional feedback data;

[0013] Based on the adjusted learning path, collect user feedback data during the learning process to evaluate the effectiveness of the learning path and the user's learning effect.

[0014] As a preferred solution of the method for recommending popular science education knowledge described in the present invention, the emotion recognition algorithm of the emotion recognition mechanism includes:

[0015] Calculate the facial expression intensity score:

[0016]

[0017] Among them, E i (t) represents the intensity of the i-th facial expression at time t, ranging from [0,1], and w i is the weight coefficient of facial expression;

[0018] Then calculate the speech emotion intensity score:

[0019]

[0020] Among them, V j (t) represents the intensity of the j-th type of speech emotion at time t, ranging from [0,1], v j is the weight coefficient of speech emotion.

[0021] As a preferred solution of the method for recommending popular science education knowledge described in the present invention, wherein: the comprehensive emotion score S(t) is calculated according to the facial expression intensity and the voice expression intensity;

[0022]

[0023] Among them, E norm and V norm are the normalization factors of facial expressions and voice emotions, respectively, which are used to ensure the scale consistency of the integration results; α is the weight coefficient of the emotion feedback parameter, which is used to adjust the relative importance of facial expressions and voice emotions.

[0024] As a preferred solution of the popular science education knowledge recommendation method of the present invention, the adaptive learning path recommendation mechanism includes the following steps:

[0025] S1: Each recommended learning content is divided into a difficulty coefficient of 0-1, and the difficulty coefficient is recorded as L i ;

[0026] S2: Combine the comprehensive sentiment score S(t) at time t to calculate the dynamic adjustment factor δ of the learning content i (t);

[0027] γ is the sensitivity parameter of emotional feedback to the learning path adjustment

[0028] S3: Calculate the comprehensive adjustment weight R based on the dynamic adjustment factor i (t); Adjust the recommendation priority according to the comprehensive adjustment weight;

[0029] R i (t) = β i ·δ i (t);

[0030] Among them, β i is the basic recommendation weight of the i-th learning content, satisfying ∑β i =1.

[0031] As a preferred solution of the method for recommending popular science education knowledge described in the present invention, wherein: according to the comprehensive recommendation weight R i (t) and the difficulty coefficient L of the learning content i , calculate the final recommended learning path value L recommended (t);

[0032] but

[0033] Among them, through L recommended (t) Ensure that the recommended learning path can dynamically adapt to the user’s emotional state.

[0034] As a preferred solution of the method for recommending popular science education knowledge of the present invention, wherein: three threshold intervals are set to optimize the recommended content;

[0035] When L recommended When (t)≤the first threshold, the recommendation weight is considered low and simple content is recommended first;

[0036] When the first threshold <L recommended When (t)≤the second threshold, the recommendation weight is considered medium, and medium-difficulty content is recommended first;

[0037] When L recommended When (t)>the second threshold, the recommendation weight is considered to be high, and content with higher difficulty is recommended first.

[0038] As a preferred solution of the popular science education knowledge recommendation method of the present invention, wherein: the effectiveness of the learning path and the learning effect of the user are evaluated by calculating the effective value E;

[0039]

[0040] In the above formula, C(t) is the completion rate of the user at time t, E(t) is the accuracy rate of the user, T(t) is the learning time of the user, and E 有效值 The higher it is, the more effective the learning path is.

[0041] A popular science education knowledge recommendation system, based on the above-mentioned popular science education knowledge recommendation method, is characterized in that the system includes the following functional modules:

[0042] The user emotion collection module collects user facial expression data in real time through the camera, collects user voice data in real time through the microphone and performs emotion analysis, comprehensively processes facial expression and voice emotion data, and generates a comprehensive emotion score;

[0043] Learning content database: stores various popular science education resources, including basic videos, intermediate articles and advanced interactive exercises, and records the difficulty level of each learning content;

[0044] The learning path recommendation module calculates the dynamic adjustment factor based on the comprehensive emotional score and the difficulty coefficient of the learning content, multiplies the basic recommendation weight and the dynamic adjustment factor to obtain the comprehensive recommendation weight, and generates the final recommended learning path based on the comprehensive recommendation weight and the difficulty coefficient of the learning content;

[0045] Learning feedback collection module, real-time monitoring and recording of user learning behavior data, including learning completion rate, accuracy rate, and learning time;

[0046] The evaluation module evaluates the effectiveness of the learning path and the user's learning effect based on the user's feedback data during the learning process.

[0047] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for recommending popular science education knowledge when executing the computer program.

[0048] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for recommending popular science education knowledge.

[0049] Beneficial effects of the present invention:

[0050] 1. The present invention can dynamically generate personalized learning paths and content recommendations based on the user's emotional feedback data, meet the personalized needs of different learners, and improve learning effects;

[0051] 2. The present invention uses facial expression recognition and voice emotion analysis technology to collect and analyze users' emotional feedback data in real time, dynamically adjust learning content and paths according to the user's emotional state, and provide a more adaptive learning experience;

[0052] 3. The present invention adopts dynamic adjustment factors and comprehensive recommendation weight calculation methods to optimize the recommendation algorithm in real time, improve the recommendation accuracy and effect, and make the learning content more in line with the user's current emotional state and needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0054] Figure 1 This is a schematic diagram of the overall structure of a popular science education knowledge recommendation system proposed by the present invention;

[0055] Figure 2 A learning path recommendation schematic diagram of a popular science education knowledge recommendation method proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0059] Reference Figure 1-Figure 2, is an embodiment of the present invention, and provides a method and system for recommending popular science education knowledge, the method mainly comprising the following steps:

[0060] Step 1: Establish an emotion recognition mechanism, generate emotion feedback data through algorithms, and collect users’ emotion feedback data in real time.

[0061] Specifically, the emotion recognition algorithm of the emotion recognition mechanism includes:

[0062] Calculate the facial expression intensity score:

[0063]

[0064] Among them, E i (t) represents the intensity of the i-th facial expression at time t, ranging from [0,1], and w i is the weight coefficient of facial expression;

[0065] Then calculate the speech emotion intensity score:

[0066]

[0067] Among them, V j (t) represents the intensity of the j-th type of speech emotion at time t, ranging from [0,1], v j is the weight coefficient of speech emotion.

[0068] Finally, the comprehensive emotion score S(t) is calculated based on the facial expression intensity and the voice expression intensity;

[0069]

[0070] Among them, E norm and V norm are the normalization factors of facial expressions and voice emotions, respectively, which are used to ensure the scale consistency of the integration results; α is the weight coefficient of the emotion feedback parameter, which is used to adjust the relative importance of facial expressions and voice emotions.

[0071] Step 2: Establish an adaptive learning path recommendation mechanism to dynamically adjust the learning content and path based on the emotional feedback data collected from users. Real-time adjustment is an immediate response mechanism in the short term, which aims to immediately adjust the learning path according to the emotional state to ensure that users remain active in the current learning process.

[0072] Furthermore, the adaptive learning path recommendation mechanism includes the following steps:

[0073] S1: Each recommended learning content is divided into a difficulty coefficient of 0-1, and the difficulty coefficient is recorded as L i ;

[0074] S2: Combine the comprehensive sentiment score S(t) at time t to calculate the dynamic adjustment factor δ of the learning content i (t);

[0075] γ is the sensitivity parameter of emotional feedback to the adjustment of learning path;

[0076] S3: Calculate the comprehensive adjustment weight R based on the dynamic adjustment factor i (t); Adjust the recommendation priority according to the comprehensive adjustment weight;

[0077] R i (t) = β i ·δ i (t);

[0078] Among them, β i is the basic recommendation weight of the i-th learning content, satisfying ∑β i =1.

[0079] According to the comprehensive recommendation weight R i (t) and the difficulty coefficient L of the learning content i , calculate the final recommended learning path value L recommended (t);

[0080] but

[0081] Among them, through L recommended (t) Ensure that the recommended learning path can dynamically adapt to the user's emotional state, allowing the user to challenge more difficult content when the emotional state is good, and recommend simpler content when the emotional state is poor. Set three threshold intervals to optimize the recommended content;

[0082] When L recommended When (t)≤the first threshold, the recommendation weight is considered to be low, and simple content is recommended first, such as basic science videos.

[0083] When the first threshold <L recommended When (t)≤the second threshold, the recommendation weight is considered medium, and priority is given to content of medium difficulty, such as intermediate popular science articles.

[0084] When L recommended When (t)>the second threshold, the recommendation weight is considered to be high, and content with higher difficulty, such as advanced interactive exercises, is recommended first.

[0085] Specifically, assuming that the learning contents are: basic science videos, intermediate science articles, and advanced interactive exercises, the corresponding difficulty coefficients are L1 = 0.2, L2 = 0.5, and L3 = 0.8;

[0086] According to the formula, assuming γ = 1, the basic recommendation weights corresponding to the learning content are: β1 = 0.3, β2 = 0.4, β3 = 0.3;

[0087] The dynamic adjustment factors δ1(t)≈0.5, δ2(t)≈0.3, δ3(t≈0.2 are calculated;

[0088] Thus we can get, R1(t) = 0.3 × 0.5 = 0.15, R2(t) = 0.4 × 0.3 = 0.12, R3(t) = 0.3 × 0.2 = 0.06;

[0089] Finally, the recommended learning path L is calculated. recommended (t)≈0.15;

[0090] Further extension, assuming that the first threshold of this embodiment is 0.3 and the second threshold is 0.6, combined with the attached Figure 2 It can be seen that, in this implementation, based on the final calculation results, emphasis should be placed on recommending basic science videos with lower difficulty coefficients.

[0091] Step 3: Based on the adjusted learning path, collect user feedback data during the learning process to evaluate the effectiveness of the learning path and the user's learning effect.

[0092] The effectiveness of the learning path and the learning effect of the user are evaluated by calculating the effective value E;

[0093]

[0094] Among them, C(t) is the completion rate of the user at time t, E(t) is the accuracy rate of the user, T(t) is the learning time of the user, the integral term in the numerator represents the product of the cumulative sentiment score and the completion rate from time 0 to t, and the value of the accuracy rate adjusted by a nonlinear function, while the denominator combines the comprehensive recommendation weight, the difficulty coefficient of the learning content, and the logarithmic function of the learning time;

[0095] E 有效值 The higher it is, the more effective the learning path is.

[0096] A popular science education knowledge recommendation system, based on the above-mentioned popular science education knowledge recommendation method, is characterized in that the system includes the following functional modules:

[0097] The user emotion collection module collects user facial expression data in real time through the camera, collects user voice data in real time through the microphone and performs emotion analysis, comprehensively processes facial expression and voice emotion data, and generates a comprehensive emotion score; learning content database: stores various popular science education resources, including basic videos, intermediate articles and advanced interactive exercises, and records the difficulty coefficient of each learning content.

[0098] The learning path recommendation module calculates the dynamic adjustment factor based on the comprehensive emotional score and the difficulty coefficient of the learning content, multiplies the basic recommendation weight and the dynamic adjustment factor to obtain the comprehensive recommendation weight, and generates the final recommended learning path based on the comprehensive recommendation weight and the difficulty coefficient of the learning content;

[0099] The learning feedback collection module monitors and records the user's learning behavior data in real time, including learning completion rate, accuracy rate, and learning time; the evaluation module evaluates the effectiveness of the learning path and the user's learning effect based on the user's feedback data during the learning process.

[0100] This embodiment also provides a computer device, which is suitable for a method and system for recommending popular science education knowledge, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a method and system for recommending popular science education knowledge as proposed in the above embodiment.

[0101] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0102] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a method and a system for recommending popular science education knowledge are implemented as proposed in the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0103] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for recommending popular science education knowledge, characterized in that: The following steps are involved: Establish an emotion recognition mechanism, generate emotion feedback data through algorithms, and collect users’ emotion feedback data in real time; Establish an adaptive learning path recommendation mechanism to dynamically adjust learning content and paths based on the collected user emotional feedback data; Based on the adjusted learning path, collect user feedback data during the learning process to evaluate the effectiveness of the learning path and the user's learning effect.

2. A method for recommending popular science education knowledge according to claim 1, characterized in that: The emotion recognition algorithm of the emotion recognition mechanism includes: Calculate the facial expression intensity score: Among them, E i (t) represents the intensity of the i-th facial expression at time t, ranging from [0,1], and w i is the weight coefficient of facial expression; Then calculate the speech emotion intensity score: Among them, V j (t) represents the intensity of the j-th type of speech emotion at time t, ranging from [0,1], v j is the weight coefficient of speech emotion.

3. A method for recommending popular science education knowledge according to claim 1, characterized in that: The comprehensive emotion score S(t) is calculated based on the intensity of facial expression and voice expression; Among them, E norm and V norm are the normalization factors of facial expressions and voice emotions, respectively, which are used to ensure the scale consistency of the integration results; α is the weight coefficient of the emotion feedback parameter, which is used to adjust the relative importance of facial expressions and voice emotions.

4. A method for recommending popular science education knowledge according to claim 3, characterized in that: The adaptive learning path recommendation mechanism includes the following steps: S1: Each recommended learning content is divided into a difficulty coefficient of 0-1, and the difficulty coefficient is recorded as L i ; S2: Combine the comprehensive sentiment score S(t) at time t to calculate the dynamic adjustment factor δ of the learning content i (t); Where γ is the sensitivity parameter of emotional feedback to the adjustment of learning path; S3: Calculate the comprehensive adjustment weight R based on the dynamic adjustment factor i (t); Adjust the recommendation priority according to the comprehensive adjustment weight; R i (t)=β i ·d i (t); Among them, β i is the basic recommendation weight of the i-th learning content, satisfying ∑β i =1.

5. A method for recommending popular science education knowledge according to claim 4, characterized in that: According to the comprehensive recommendation weight R i (t) and the difficulty coefficient L of the learning content i , calculate the final recommended learning path value L recommended (t); but Among them, through L recommended (t) Ensure that the recommended learning path can dynamically adapt to the user’s emotional state.

6. A method for recommending popular science education knowledge according to claim 5, characterized in that: Set three threshold intervals to optimize recommended content; When L recommended When (t)≤the first threshold, the recommendation weight is considered low and simple content is recommended first; When the first threshold <L recommended When (t)≤the second threshold, the recommendation weight is considered medium, and medium-difficulty content is recommended first; When L recommended When (t)>the second threshold, the recommendation weight is considered to be high, and content with higher difficulty is recommended first.

7. A method for recommending popular science education knowledge according to claim 6, characterized in that: The effectiveness of the learning path and the learning effect of the user are evaluated by calculating the effective value E; Among them, C(t) in the above formula is the completion rate of the user at time t, E(t) is the accuracy rate of the user, and T(t) is the learning time of the user; E 有效值 The higher it is, the more effective the learning path is.

8. A popular science education knowledge recommendation system, based on the popular science education knowledge recommendation method according to claim 7, characterized in that: The system includes the following functional modules: The user emotion collection module collects user facial expression data in real time through the camera, collects user voice data in real time through the microphone and performs emotion analysis, comprehensively processes facial expression and voice emotion data, and generates a comprehensive emotion score; Learning content database: stores various popular science education resources, including basic videos, intermediate articles and advanced interactive exercises, and records the difficulty level of each learning content; The learning path recommendation module calculates the dynamic adjustment factor based on the comprehensive emotional score and the difficulty coefficient of the learning content, multiplies the basic recommendation weight and the dynamic adjustment factor to obtain the comprehensive recommendation weight, and generates the final recommended learning path based on the comprehensive recommendation weight and the difficulty coefficient of the learning content; Learning feedback collection module, real-time monitoring and recording of user learning behavior data, including learning completion rate, accuracy rate, and learning time; The evaluation module evaluates the effectiveness of the learning path and the user's learning effect based on the user's feedback data during the learning process.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for recommending popular science education knowledge as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for recommending popular science education knowledge as described in any one of claims 1 to 7 are implemented.

Images