Real-time data interaction processing method and system based on parent-child education
By acquiring user identification data and real-time parent-child interaction data, family education ability assessment data is generated, which solves the problem of the single assessment dimension in the existing system and realizes a comprehensive and accurate assessment of family education ability.
Patent Information
- Application Number
- CN202511554961.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-29
- Publication Date
- 2026-02-10
AI Technical Summary
Current assessments of family education capabilities suffer from a lack of simplistic dimensions, focusing primarily on academic performance while neglecting the quality of parent-child interaction and emotional management skills, leading to reduced accuracy.
By acquiring user identification data and real-time parent-child interaction data, key indicators are identified, family education ability assessment data is generated and visualized, and the comprehensive assessment is updated in combination with historical assessment data.
It improves the accuracy of family education ability assessment, provides a comprehensive assessment of the quality of parent-child interaction and emotional management, and helps parents improve their parenting methods.
Smart Images
Figure CN121504239A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, and in particular to a real-time data interaction processing method and system based on parent-child education. Background Technology
[0002] With technological advancements, the application of artificial intelligence (AI) in education has spurred profound changes in family education models. Traditional family education focuses on knowledge transmission, while the current technological environment requires parents to assume a new role as "learning technology partners," mastering AI tools to support their children's learning. For example, parents need to participate in the learning process with their children through tools such as programming learning platforms and AI-powered English learning apps, which places new demands on parents' technological application skills.
[0003] Current assessments of family education capabilities suffer from a lack of dimensionality. Existing assessments often focus on academic performance, neglecting key indicators such as the quality of parent-child interaction and emotional management skills, thus reducing the accuracy of these assessments. Therefore, it is essential to propose a real-time data interaction processing method and system that can improve the accuracy of family education capability assessments. Summary of the Invention
[0004] The purpose of this invention is to provide a real-time data interaction processing method and system based on parent-child education, aiming to solve the technical problem that the existing technology has the deficiency of a single dimension in the assessment of family education ability. Existing assessments mostly focus on academic performance and ignore key indicators such as the quality of parent-child interaction and emotional management ability, thereby reducing the accuracy of the assessment of family education ability.
[0005] To achieve the above objectives, the present invention employs a real-time data interaction processing method based on parent-child education, comprising the following steps: Acquire user identification data, identify the current role, and output role data; Acquire real-time parent-child interaction data, update the current role, and identify key metrics; Data on family education capabilities is generated based on key indicators and then visualized. Obtain historical assessment data and update the comprehensive assessment data.
[0006] Among the steps of acquiring user identification data, identifying the current role, and outputting role data: Divide the recognition area, acquire image data of the recognition area, and acquire the paired device in the recognition area; It identifies the current role data from image data and receives data from paired devices.
[0007] After the steps of identifying the current role data from the image data and receiving data from the paired device: Based on the current role data, request the data transmission channel for the paired device.
[0008] Among the steps involved in acquiring real-time parent-child interaction data, updating the current role, and identifying key metrics: Acquire character interaction data in real time and update the current character data; Based on the character interaction data, key indicator data is obtained and stored; the key indicator data includes interaction frequency, interaction duration, emotional state, and physiological reaction.
[0009] Among the steps, in acquiring character interaction data in real time and updating the current character data: The system acquires video stream data, audio data, and physiological indicator data respectively, and identifies each role in the video stream data. Update the current role data based on the identified role; The system associates characters with audio data and physiological indicators, and outputs the associated data.
[0010] In the step of generating family education capacity assessment data based on key indicators and then visualizing it: Determine the core dimensions of the evaluation and allocate indicator weights accordingly; Acquire key indicator data and conduct real-time and phased assessments respectively; Real-time and phased assessment data will be visualized.
[0011] Among the steps involved in acquiring key indicator data and conducting real-time and phased assessments: We perform weighted calculations on key indicator data to obtain real-time evaluation data. Set a prompt threshold, compare the real-time evaluation data with the prompt threshold, and trigger a prompt request.
[0012] Among the steps involved in acquiring key indicator data and conducting real-time and phased assessments: Identify the evaluation phase and summarize the real-time evaluation data for that phase to generate phase evaluation data.
[0013] Among the steps involved in acquiring historical assessment data and updating the comprehensive assessment data: Acquire historical assessment data; which includes real-time assessment data, phase assessment data, and historical comprehensive assessment data. The comprehensive assessment data is updated by combining real-time assessment data, phase assessment data, and historical comprehensive assessment data.
[0014] This invention also provides a real-time data interaction processing system based on parent-child education, including a current role recognition module, a key indicator recognition module, an evaluation data generation module, and a comprehensive evaluation update module; wherein: The current role recognition module is used to acquire user recognition data, identify the current role, and output role data; The key indicator identification module is used to acquire real-time parent-child interaction data, update the current role, and identify key indicators. The assessment data generation module is used to generate family education ability assessment data based on key indicators and to visualize the data. The comprehensive evaluation update module is used to obtain historical evaluation data and update the comprehensive evaluation data.
[0015] This invention discloses a real-time data interaction processing method and system based on parent-child education. The method comprises a current role identification module, a key indicator identification module, an evaluation data generation module, and a comprehensive evaluation update module, which perform the following steps: acquiring user identification data, identifying the current role, and outputting role data; acquiring real-time parent-child interaction data, updating the current role, and identifying key indicators; generating family education ability evaluation data based on the key indicators and visualizing it; acquiring historical evaluation data and updating the comprehensive evaluation data; and generating interactive scenarios by identifying roles in the data, recording key indicators, and then generating family education ability evaluation data to improve the accuracy of family education ability evaluation. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 This is a flowchart illustrating the real-time data interaction processing method based on parent-child education according to the present invention.
[0018] Figure 2 This is a flowchart of the steps of the real-time data interaction processing method based on parent-child education according to the present invention.
[0019] Figure 3 This is a flowchart of steps S100 of the present invention.
[0020] Figure 4 This is a flowchart of steps S200 of the present invention.
[0021] Figure 5 This is a flowchart of steps S300 of the present invention.
[0022] Figure 6 This is a flowchart of steps S400 of the present invention.
[0023] Figure 7 This is a schematic diagram of the real-time data interaction processing system based on parent-child education according to the present invention.
[0024] Figure 8 This is a schematic diagram of the electronic device of the present invention.
[0025] 501 - Current Role Recognition Module, 502 - Key Indicator Recognition Module, 503 - Evaluation Data Generation Module, 504 - Comprehensive Evaluation Update Module. Detailed Implementation
[0026] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.
[0027] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.
[0028] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."
[0029] Please see Figures 1-6 This invention provides a real-time data interaction processing method based on parent-child education, comprising the following steps: S100: Acquire user identification data, identify the current role, and output role data.
[0030] In this embodiment, user identification data is acquired, the current role is identified, and role data is output. The specific process is as follows: S101: Divide the recognition area, acquire image data of the recognition area, and acquire the paired device in the recognition area; the paired device includes a camera, a wristband, a recorder, etc. S102: Identify the current role data from the image data and receive data from the paired device; S103: Request the data transmission channel of the paired device based on the current role data.
[0031] In the above process, areas requiring role recognition are defined based on actual scenario needs, such as a family living room or a school classroom. Image data, including video streams or still images, is acquired using devices such as cameras installed within the recognition area. Simultaneously, information about paired devices within the recognition area is detected and acquired. These paired devices include cameras for recording images, wristbands for monitoring user physiological indicators, and recorders for recording sound; the cameras within the recognition area and the cameras in the paired devices used for recording images can be the same camera.
[0032] The acquired image data undergoes preprocessing to improve the accuracy and efficiency of subsequent processing. The preprocessing steps include: Grayscale conversion: Converting a color image to a grayscale image reduces computational complexity.
[0033] Normalization: Adjusting the image size and pixel value range to fit the algorithm input.
[0034] Denoising: Using filtering algorithms to remove noise from an image.
[0035] Face detection algorithms, such as the Haar cascade detector in OpenCV or the deep learning-based MTCNN, are used to locate face regions in images and output the bounding box coordinates of the faces. Detected faces are then aligned to ensure their position and orientation are consistent within the image, which helps improve the accuracy of subsequent recognition.
[0036] Convolutional Neural Networks (CNNs) are used to extract features from facial regions. CNNs extract high-level feature representations from images through multiple layers of convolution and pooling operations. A convolution operation can be represented as: in, Indicates the input image I and convolution kernel K After performing the convolution operation, at the location of the output feature map (i,j) The value at; I(i−m,j−n) Indicates the input image I In position (i−m,j−n) The pixel value at that location represents the convolution kernel. KA pixel in the currently processed image region when sliding on the image; K(m,n) Represents the convolution kernel K In position (m,n) The weights at each point are calculated using a small matrix called the convolution kernel, which is used to perform dot product and summation operations with local regions of the image to extract features.
[0037] Pooling operations are used to reduce the spatial dimensionality of feature maps, typically using max pooling or average pooling. Max pooling can be expressed as: P(i,j)=
[0038] in, P(i,j) This indicates the position of the feature map after pooling. (i,j) The purpose of max pooling is to select the largest pixel value from this region as the output. A(m,n) Represents the input feature map A The pixel value at position (m,n); s The pooling stride represents the step size by which the pooling window moves across the input feature map. Typically, the size of the pooling window and the stride are the same, but they can also be different. (i−1)×s+1≤m≤i×s Define the position of the pooling window in the vertical direction, where m It is the row index in the input feature map. n It is the column index in the input feature map; max This represents the maximum value function, used to find the largest pixel value within a specified window area.
[0039] The result of feature extraction is a feature vector, which represents the abstract features of the input face.
[0040] Face recognition is performed by comparing the extracted feature vectors with known face feature vectors pre-stored in a database. The comparison method uses Euclidean distance calculation, which measures the similarity between feature vectors, and is expressed as: in, x and y This represents two eigenvectors; n Indicates the dimension of the feature vector.
[0041] Based on the comparison results, the known roles to which the faces in the image belong are determined, such as child A, parent A, parent B, etc. The recognition results are output, including the identified roles and their location information in the image.
[0042] Simultaneously, it detects and acquires information about paired devices within the recognition area. These paired devices include cameras for recording images, wristbands for monitoring user physiological indicators, and recorders for recording sound. For example, it receives heart rate data from parent A, parent B, and child A transmitted via wristbands, audio data of parent-child conversations transmitted via recorders, and parent-child video data transmitted via cameras.
[0043] Data is segmented for each role, and all data is categorized and organized. For example, parent A's data, including image features, heart rate data, and possible voice data, is grouped into one category, while child A's data is grouped into another. The purpose of this is to allow for independent data transmission channel requests for each role in the future, ensuring the targeted and effective transmission of data.
[0044] Depending on the type and communication capabilities of the paired device, select the appropriate communication protocol to request a data transmission channel. For example, for devices that support Wi-Fi or Bluetooth communication, the corresponding communication protocol can be selected to establish a connection; for devices that require higher bandwidth or lower latency (such as high-definition cameras), a more specialized communication protocol or network architecture needs to be selected.
[0045] For each role, a data transmission channel request is sent to the corresponding paired device. The request typically includes the role's identity information, the required data type and amount, priority information, and communication protocol requirements. For example, the system might send a request to the wristband worn by parent A, requesting the establishment of a real-time heart rate data transmission channel and specifying Bluetooth Low Energy (BLE) as the communication protocol.
[0046] Upon receiving a request, the paired device determines whether to establish a data transmission channel based on its communication capabilities and current status. If the device agrees to establish a channel, it sends an acknowledgment message and begins transmitting data as requested. Upon receiving the acknowledgment message, the paired device records the channel establishment status and begins receiving data from the paired device.
[0047] Once the data transmission channel is successfully established, the paired devices will begin transmitting data as requested. This data is received and processed in real time to ensure its integrity and accuracy.
[0048] During data transmission, the transmission status is continuously monitored, including metrics such as data transmission rate, error rate, and latency. If transmission anomalies or data quality issues are detected, only adjustments or re-requesting the data transmission channel are required. Received data is stored in appropriate databases or files for subsequent analysis and processing. For example, parents' heart rate data and audio recordings of parent-child conversations can be stored in a health monitoring database for health analysis and parent-child relationship assessment.
[0049] S200: Acquire real-time parent-child interaction data, update the current role, and identify key metrics.
[0050] In this implementation, real-time parent-child interaction data is acquired, the current role is updated, and key indicators are identified. The specific process is as follows: S201: Acquire character interaction data in real time and update the current character data; S202: Based on the character interaction data, obtain key indicator data and store it; the key indicator data includes interaction frequency, interaction duration, emotional state, and physiological reaction.
[0051] During the above process, character interaction data is acquired in real time. Using the image data recognition method described in step S100, the video stream data is analyzed to identify each character in the scene. The identified character information is then compared and updated with the stored character data. If a character is appearing for the first time, it is added to the character database; if the character already exists, its latest interaction time and status information are updated.
[0052] Based on the identified roles, video stream data, audio data, and physiological indicator data are correlated. For example, video clips, voice recordings, and physiological indicator data of a specific role within a specific time period can be linked together to form a complete record of role interaction data.
[0053] Based on character interaction data, key performance indicator (KPI) data is obtained, including the definition and calculation of KPIs: Interaction frequency: The number of interactions between parents and children per unit of time (e.g., per minute). This can be achieved by analyzing voice activity in audio data or action interaction in video data. Example formula: For example, if 5 voice or motion interactions are detected within 1 minute, the interaction frequency is 5 times / minute.
[0054] Interaction Duration: Calculates the duration of each interaction. This can be achieved by analyzing the start and end times of video or audio data. Example Formula: For example, if an interaction starts at 10:00 and ends at 10:05, the interaction duration is 5 minutes.
[0055] Emotional state: Using facial expression recognition and voice emotion analysis technology, the emotional state between parents and children is quantitatively assessed.
[0056] In facial expression recognition, the acquired images undergo preprocessing, including denoising, grayscale conversion, and normalization. Denoising removes noise interference from the image, grayscale conversion converts a color image to a grayscale image, reducing computational load, and normalization standardizes the image size and pixel value range, facilitating subsequent processing.
[0057] Computer vision algorithms are used to extract facial feature points, such as the coordinates of key points in areas like the eyes, eyebrows, and mouth. Commonly used algorithms include Active Shape Model (ASM) and Active Appearance Model (AAM).
[0058] The intensity of facial action units (AUs) is calculated based on the extracted facial feature points. AUs are the basic units that describe facial muscle movements; different AU combinations correspond to different facial expressions. For example, the combination of AU1 (raised inner eyebrows) and AU4 (lowered eyebrows) typically indicates sadness.
[0059] The extracted facial features and AU (Aspect Ratio) intensity are input into a pre-trained emotion classification model. This model is typically based on deep learning algorithms, such as convolutional neural networks (CNNs), and is trained using a large amount of labeled facial expression data.
[0060] The model outputs emotion classification results, such as happiness, sadness, anger, surprise, fear, disgust, and neutrality. Furthermore, to achieve quantitative evaluation, a probability value can be assigned to each emotion category, representing the proportion of that emotion in the current facial expression.
[0061] Formula examples, such as emotion probability calculation: Assume the model outputs an emotion category. C The probability is P(C) ,for n Possible emotion categories: For example, if the model outputs a probability of 0.7 for happiness, 0.2 for sadness, and a total probability of 0.1 for other emotions, it indicates that happiness accounts for the highest proportion of the current facial expression.
[0062] Beyond the probability of emotion classification, the intensity of emotions can be further quantified. For example, for the emotion of happiness, an emotion intensity index can be defined based on the degree of change in facial features (such as the extent of mouth opening, the degree of eye squinting, etc.). I .
[0063] Formula example, such as calculating the emotion intensity index: Assume the facial feature parameters related to happiness are... F 1 ,F 2 ,⋯, F kThe weight of each parameter's contribution to the intensity of emotion is: w 1 ,w 2 ,⋯,w k Then the emotional intensity index I It can be represented as: in, For feature parameters The normalized function maps the feature parameters to a certain numerical range for comprehensive calculation.
[0064] In speech emotion analysis, the collected speech data undergoes preprocessing, including noise reduction, endpoint detection, and framing. Noise reduction removes background noise from the speech, endpoint detection determines the start and end points of the speech, and framing divides the continuous speech signal into short frames for easier subsequent processing.
[0065] Various features are extracted from the framed speech signal, such as fundamental frequency (F0), energy, speech rate, and formants. The fundamental frequency reflects the pitch of the speech, the energy is related to the loudness of the speech, the speech rate indicates the speed of speaking, and the formants are related to the timbre of the speech.
[0066] It can also extract advanced features such as Mel frequency cepstral coefficients (MFCC). MFCC can better simulate the auditory characteristics of the human ear and plays an important role in speech emotion analysis.
[0067] The extracted speech features are input into a pre-trained speech emotion classification model. This model is typically based on machine learning algorithms, such as Support Vector Machine (SVM), Random Forest (RF), or deep learning algorithms, such as Recurrent Neural Network (RNN), Long Short-Term Memory Network (LSTM), and is trained using a large amount of labeled speech emotion data.
[0068] The model outputs emotion classification results, similar to facial expression recognition, assigning a probability value to each emotion category.
[0069] Formula examples, such as calculating the probability of voice emotion: assuming the model outputs a certain emotion category. E The probability is P(E) ,for m Possible emotion categories: Similarly, the intensity of emotions can be quantified in speech sentiment analysis. For example, for anger, an emotion intensity index can be defined based on the changes in speech energy, speed, and fundamental frequency. S .
[0070] Formula Example (Calculation of Voice Emotion Intensity Index): Assume the voice feature parameters related to anger are... V 1 ,V 2 , ⋯,V p The weight of each parameter's contribution to the intensity of emotion is: u 1 ,u 2 ,⋯,u p Then the emotional intensity index S It can be represented as: in, For feature parameters The function after normalization.
[0071] In practical applications, to more accurately assess the emotional state between parents and children, facial expression recognition and voice emotion analysis technologies are often integrated. Features extracted from facial expression recognition and voice emotion analysis are concatenated or combined to form a comprehensive feature vector.
[0072] The combined feature vectors are input into a fusion classification model for emotion classification and quantitative evaluation. The fusion classification model can employ deep learning algorithms, such as multilayer perceptrons (MLPs) or a combination of convolutional neural networks and recurrent neural networks (CNN-RNN).
[0073] Emotion classification results and probability values are obtained using facial expression recognition and voice emotion analysis models, respectively. Based on certain fusion rules, such as weighted average, maximum or minimum values, the results of the two techniques are fused to obtain the final emotion classification and quantitative evaluation results.
[0074] Formula examples, such as decision-level fusion weighted average: assuming facial expression recognition yields a certain emotion... Q The probability is P face (Q) The probability of obtaining this emotion through voice sentiment analysis is: P voice (Q) The weights of the two technologies are respectively w face and w voice （w face +w voice =1） The probability of the merged emotionP fusion (Q) for: P fusion (Q)=w face ×Pf ace (Q)+w voice ×P voice (Q) By using the above facial expression recognition and voice emotion analysis technologies, as well as multimodal fusion methods, a comprehensive and accurate quantitative assessment of the emotional state between parents and children can be conducted, providing valuable references for parent-child relationship research and educational guidance.
[0075] Physiological response: Analyze physiological data transmitted by wearable devices, such as heart rate variability. Indicators such as heart rate variability (HRV) can be calculated to assess physiological response.
[0076] Formula examples, such as RMSSD calculation in heart rate variability: in, and It is the interval between adjacent heartbeats (in milliseconds). It is the total number of heart rate intervals. The higher the RMSSD value, the higher the heart rate variability, reflecting better physiological adaptability and emotional stability.
[0077] The calculated key performance indicator (KPI) data is stored in a database, including interaction frequency, interaction duration, emotional state, and physiological responses. Simultaneously, independent data records are created for each role to facilitate subsequent querying and analysis.
[0078] S300: Generates family education capacity assessment data based on key indicators and displays it visually.
[0079] In this implementation, family education capacity assessment data is generated based on key indicators and then visualized. The specific process is as follows: S301: Determine the core dimensions of the evaluation and allocate indicator weights; S302: Obtain key indicator data and conduct real-time and phased assessments respectively; S303: Visualize real-time and phased assessment data.
[0080] In the above process, the core dimensions of the evaluation are determined, including: Interaction and participation: This includes the duration of parent-child conversations, the frequency of joint activities (such as reading together, playing games, and outdoor sports), and the frequency of physical interaction (such as hugs and high-fives). For example, it includes tracking the daily time spent reading books together and the number of times outdoor sports are conducted weekly.
[0081] Effectiveness of educational guidance: This includes the accuracy rate of answers to children's questions, the number of times children are guided to think independently, and the effectiveness of cultivating good habits in children (such as the formation of habits like completing homework on time and tidying up belongings). For example, record the ratio of the number of times parents correctly answer their children's learning questions to the total number of questions asked.
[0082] Emotional Management: Monitor the frequency of emotional fluctuations and emotional regulation abilities (such as the time it takes to recover from negative emotions to a normal state) of parents and children during interactions. For example, through voice tone analysis and facial expression recognition, count the number of times parents and children experience negative emotions (such as anger and anxiety).
[0083] Learning support: This involves the provision of learning resources for children (such as purchasing books, enrolling in extracurricular classes, etc.), the duration and quality of homework tutoring (such as the reduction in the child's homework error rate). For example, statistics on the monthly cost of purchasing learning materials for the child and the change in the child's homework accuracy rate after tutoring.
[0084] We assign weights to the indicators and construct a hierarchical model, with family education ability assessment as the target layer, core dimensions as the criteria layer, and specific indicators as the solution layer. We determine the relative importance of elements in each layer through pairwise comparisons and calculate the weight vector.
[0085] The standardized value of each indicator is multiplied by its corresponding weight, and then the weighted values of all indicators are summed to obtain a comprehensive score for family education ability. The formula is as follows: in, S For comprehensive scoring, for i The weight of each indicator, For the first i The standardized value of each indicator, n This refers to the number of indicators.
[0086] For key indicator data, weighted calculations are performed to obtain real-time evaluation data; for example, the weight of interaction participation is 0.3, the weight of educational guidance effectiveness is 0.4, the weight of emotion management is 0.2, and the weight of learning support is 0.1. The real-time data of each indicator is multiplied by the corresponding weight and then added together to obtain the real-time evaluation score.
[0087] Establish prompt thresholds and compare real-time assessment data with these thresholds to trigger prompt requests. Multiple prompt thresholds can be set, and the assessment data ranges corresponding to different assessment levels can be determined based on analysis of historical family education ability assessment data. For example, assessment levels can be divided into four levels: Excellent, Good, Average, and Poor. The assessment data range for Excellent is 0.8~1.0, Good is 0.6~0.8, Average is 0.4~0.6, and Poor is 0~0.4.
[0088] Real-time assessment data is compared with prompt thresholds to determine the current assessment level of family education ability. When the real-time assessment data reaches or falls below a certain threshold, a corresponding prompt mechanism is triggered. Prompt methods may include push notifications from a mobile app, voice reminders from a smart speaker, and SMS notifications. For example, when the real-time assessment data is below 0.6, the mobile app pushes a message: "The current family education ability is at an average level. It is recommended to increase parent-child interaction time and improve the effectiveness of educational guidance." When the real-time assessment data is below 0.4, the smart speaker voice prompts: "The current family education ability is poor. Parents should adjust their educational methods in a timely manner and pay attention to the child's emotions and learning needs." The prompts can also include specific improvement suggestions to help parents adjust their educational behaviors promptly.
[0089] In the phased assessment, the assessment period is determined, such as weekly, monthly, or quarterly. At the end of the phase, key indicator data for that phase are summarized. For example, the total weekly duration of parent-child activities and the total number of times parents answered children's questions each month are calculated. The summarized data is then further processed, such as calculating averages and growth rates. For instance, the average weekly duration of parent-child conversations and the monthly growth rate of children's homework accuracy can be calculated. A detailed phased assessment report can be generated using the same weighting method and data range as the real-time assessment data.
[0090] Visualize real-time and phased assessment data. Use charts (such as bar charts, line charts, radar charts, etc.) and dashboards to present the assessment data intuitively to parents. For example, use a radar chart to display parents' scores across various core dimensions, allowing them to fully understand their strengths and weaknesses.
[0091] S400: Obtain historical assessment data and update comprehensive assessment data.
[0092] In this embodiment, historical evaluation data is acquired and the comprehensive evaluation data is updated. The specific process is as follows: S401: Obtain historical assessment data; where historical assessment data includes real-time assessment data, phase assessment data, and historical comprehensive assessment data; S402: Update the comprehensive assessment data by combining real-time assessment data, phase assessment data, and historical comprehensive assessment data.
[0093] In the above process, historical evaluation data is obtained. Since the dimensions and ranges of real-time evaluation data, phase evaluation data, and historical comprehensive evaluation data may differ, standardization processing is required. For example, the Min-Max standardization method can be used to map all data to the range of 0 to 1 for subsequent weighted calculations.
[0094] Ensure that different types of data are aligned in terms of time. For example, if real-time assessment data is recorded by the minute and phase assessment data is recorded by the week, the real-time assessment data needs to be aggregated by week to make it consistent with the time granularity of the phase assessment data.
[0095] Data analysis methods (such as correlation analysis and principal component analysis) are used to analyze the relationship between different data types and the overall performance of family education ability, and objective weights are determined. Based on the results of subjective evaluation and objective analysis, reasonable weights are assigned to real-time evaluation data, stage evaluation data, and historical comprehensive evaluation data. For example, stage evaluation data may be considered to better reflect the long-term effects of family education, and therefore given a higher weight (e.g., 0.5); real-time evaluation data reflects the current state and is given a weight of 0.3; and historical comprehensive evaluation data is used as a reference and is given a weight of 0.2.
[0096] The standardized real-time evaluation data, phase evaluation data, and historical comprehensive evaluation data are each multiplied by their respective weights to obtain their weighted values. For example, the weighted value of real-time evaluation data is 0.3 × the standardized real-time evaluation score, the weighted value of phase evaluation data is 0.5 × the standardized phase evaluation score, and the weighted value of historical comprehensive evaluation data is 0.2 × the standardized historical comprehensive evaluation score.
[0097] The three weighted values are added together to obtain the new comprehensive evaluation data. The formula is as follows: in, For the new comprehensive assessment data, , , The weights are respectively for real-time evaluation data, phase evaluation data, and historical comprehensive evaluation data. , , These are standardized real-time evaluation data, phase evaluation data, and historical comprehensive evaluation data, respectively.
[0098] Store comprehensive evaluation data: Store the updated comprehensive evaluation data in the corresponding table of the relational database, recording information such as evaluation time, comprehensive evaluation score, and the data range on which it is based, so as to facilitate subsequent querying and analysis.
[0099] Data Feedback: Updated comprehensive assessment results will be provided to parents via mobile app, SMS, email, etc. Feedback may include the comprehensive assessment score, assessment level (e.g., Excellent, Good, Average, Poor), comparison with the previous comprehensive assessment, and targeted improvement suggestions. For example, if the comprehensive assessment results show a decline in parenting skills, it is recommended that parents increase interaction time with their children and improve their parenting methods.
[0100] Corresponding to the aforementioned embodiments of the real-time data interaction processing method based on parent-child education, this application also provides embodiments of a real-time data interaction processing system based on parent-child education.
[0101] Figure 7 This is a block diagram illustrating a real-time data interaction processing system based on parent-child education, according to an exemplary embodiment. (Refer to...) Figure 7 The system may include: a current role recognition module 501, a key indicator recognition module 502, an evaluation data generation module 503, and a comprehensive evaluation update module 504; wherein: The current role recognition module 501 is used to acquire user recognition data, identify the current role, and output role data; The key indicator identification module 502 is used to acquire real-time parent-child interaction data, update the current role, and identify key indicators. The assessment data generation module 503 is used to generate family education ability assessment data based on key indicators and to visualize the data. The comprehensive evaluation update module 504 is used to obtain historical evaluation data and update the comprehensive evaluation data.
[0102] In this embodiment, the current role recognition module 501 acquires user identification data, identifies the current role, and outputs role data; the key indicator recognition module 502 acquires real-time parent-child interaction data, updates the current role, and identifies key indicators; the evaluation data generation module 503 generates family education ability evaluation data based on key indicators and displays it visually; the comprehensive evaluation update module 504 acquires historical evaluation data and updates the comprehensive evaluation data; by generating interactive scenarios after role recognition of the data and recording key indicators, family education ability evaluation data is generated, thereby improving the accuracy of family education ability evaluation.
[0103] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.
[0104] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.
[0105] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the real-time data interaction processing method based on parent-child education as described above. Figure 8 The diagram shown is a hardware structure diagram of any device with data processing capabilities, which is part of a real-time data interaction processing system based on parent-child education provided in an embodiment of the present invention. (Except for...) Figure 8 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.
[0106] Accordingly, this application also provides a computer-readable storage medium storing computer instructions thereon, which, when executed by a processor, implement the real-time data interaction processing method based on parent-child education as described above. The computer-readable storage medium can be an internal storage unit of any device with data processing capabilities as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any device with data processing capabilities and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the device with data processing capabilities, and can also be used to temporarily store data that has been output or will be output.
[0107] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.
[0108] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.
Claims
1. A real-time data interaction processing method based on parent-child education, characterized in that, Includes the following steps: Acquire user identification data, identify the current role, and output role data; Acquire real-time parent-child interaction data, update the current role, and identify key metrics; Data on family education capabilities is generated based on key indicators and then visualized. Obtain historical assessment data and update the comprehensive assessment data.
2. The real-time data interaction processing method based on parent-child education as described in claim 1, characterized in that, In the steps of acquiring user identification data, identifying the current role, and outputting role data: Divide the recognition area, acquire image data of the recognition area, and acquire the paired device in the recognition area; It identifies the current role data from image data and receives data from paired devices.
3. The real-time data interaction processing method based on parent-child education as described in claim 2, characterized in that, After the steps of identifying the current role data from the image data and receiving data from the paired device: Based on the current role data, request the data transmission channel for the paired device.
4. The real-time data interaction processing method based on parent-child education as described in claim 1, characterized in that, In the steps of acquiring real-time parent-child interaction data, updating the current role, and identifying key metrics: Acquire character interaction data in real time and update the current character data; Based on the character interaction data, key indicator data is obtained and stored; the key indicator data includes interaction frequency, interaction duration, emotional state, and physiological reaction.
5. The real-time data interaction processing method based on parent-child education as described in claim 3, characterized in that, In the steps of acquiring character interaction data in real time and updating the current character data: The system acquires video stream data, audio data, and physiological indicator data respectively, and identifies each role in the video stream data. Update the current role data based on the identified role; The system associates characters with audio data and physiological indicators, and outputs the associated data.
6. The real-time data interaction processing method based on parent-child education as described in claim 1, characterized in that, In the steps of generating family education capacity assessment data based on key indicators and visualizing it: Determine the core dimensions of the evaluation and allocate indicator weights accordingly; Acquire key indicator data and conduct real-time and phased assessments respectively; Real-time and phased assessment data will be visualized.
7. The real-time data interaction processing method based on parent-child education as described in claim 6, characterized in that, In the steps of acquiring key indicator data and conducting real-time and phased assessments: We perform weighted calculations on key indicator data to obtain real-time evaluation data. Set a prompt threshold, compare the real-time evaluation data with the prompt threshold, and trigger a prompt request.
8. The real-time data interaction processing method based on parent-child education as described in claim 7, characterized in that, In the steps of acquiring key indicator data and conducting real-time and phased assessments: Identify the evaluation phase and summarize the real-time evaluation data for that phase to generate phase evaluation data.
9. The real-time data interaction processing method based on parent-child education as described in claim 8, characterized in that, In the steps of acquiring historical assessment data and updating the comprehensive assessment data: Acquire historical assessment data; which includes real-time assessment data, phase assessment data, and historical comprehensive assessment data. The comprehensive assessment data is updated by combining real-time assessment data, phase assessment data, and historical comprehensive assessment data.
10. A real-time data interaction processing system based on parent-child education, applied to the real-time data interaction processing method based on parent-child education as described in claim 1, characterized in that, This includes a current role identification module, a key indicator identification module, an evaluation data generation module, and a comprehensive evaluation update module; among which: The current role recognition module is used to acquire user recognition data, identify the current role, and output role data; The key indicator identification module is used to acquire real-time parent-child interaction data, update the current role, and identify key indicators. The assessment data generation module is used to generate family education ability assessment data based on key indicators and to visualize the data. The comprehensive evaluation update module is used to obtain historical evaluation data and update the comprehensive evaluation data.