Pediatric psychological nursing interactive guidance and emotional state real-time monitoring analysis method

Abstract

The invention discloses a pediatric psychological nursing interactive guidance and emotional state real-time monitoring analysis method, which comprises the following steps of: synchronously acquiring facial expression related data, voice emotion related data and physiological signal related data of a pediatric patient in a non-invasive manner by deploying an emotional state real-time monitoring module to form a multi-dimensional emotion related data set; the emotional state information is encrypted and transmitted to the analysis layer through the transmission layer, and an emotional state result is output through a multi-modal data fusion algorithm and an emotional state recognition model by adopting an edge computing and cloud collaborative architecture; a personalized interaction guiding module of the application layer is combined with pediatric patient age information and character labels to push adaptive content; and the data management and effect evaluation module encrypts the stored data and comprehensively evaluates the stored data to form a'monitoring-intervention-evaluation-optimization 'closed loop. According to the invention, emotion monitoring accuracy and guiding suitability are improved, data safety is guaranteed, and pediatric psychological nursing is helped to develop to precision and individuation.

Description

Technical Field

[0001] This invention relates to the field of pediatric psychology, specifically to a method for interactive guidance and real-time monitoring and analysis of emotional states in pediatric psychological nursing. Background Technology

[0002] In the field of pediatric nursing, psychological care plays a vital role in improving patients' treatment compliance and rehabilitation outcomes. Due to their age and limited cognitive abilities, pediatric patients are prone to negative emotions such as anxiety and fear during treatment. However, traditional pediatric psychological care relies on the subjective observation and experience of medical staff, lacking objective quantitative monitoring of emotional states, resulting in delayed and inaccurate emotion recognition.

[0003] Existing emotion monitoring methods are mostly limited to single-dimensional data collection, making it difficult to comprehensively reflect the true emotional state of pediatric patients. Furthermore, some collection methods are invasive, easily triggering resistance from pediatric patients and reducing their cooperation in nursing care. At the same time, traditional interactive guidance content is highly homogenized and not tailored to the individual characteristics of pediatric patients, such as age range and personality tags, resulting in poor intervention effects.

[0004] Furthermore, existing technologies lack secure storage mechanisms for emotion-related data, posing a risk of privacy breaches. They also fail to establish a complete "monitoring-intervention-evaluation-optimization" closed-loop process, making it impossible to dynamically adjust treatment plans based on nursing outcomes, thus hindering the continuous improvement of nursing quality. These issues make traditional pediatric psychological nursing inadequate to meet the needs of precise, personalized, and real-time care, necessitating more scientific and efficient technological solutions. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the defects of the above-mentioned technologies and provide a method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing.

[0006] To solve the above-mentioned technical problems, the technical solution provided by this invention is a method for interactive guidance and real-time monitoring and analysis of emotional states in pediatric psychological nursing, comprising the following complete steps:

[0007] Step 1: Deploy a real-time emotional state monitoring module. Using a non-invasive acquisition method, it simultaneously collects facial expression data, voice emotion data, and physiological signal data of pediatric patients to form a multi-dimensional emotion-related data set.

[0008] Step two: The collected multi-dimensional emotion-related data set is encrypted and transmitted to the analysis layer through the wireless transmission module and data encryption module contained in the transmission layer, ensuring the security and integrity of the data transmission process.

[0009] Step 3: The analysis layer calls the preset multimodal data fusion algorithm to perform feature fusion processing on the multi-dimensional emotion-related data set, and then analyzes the fused feature data through the trained emotion state recognition model to output the emotion state result containing the emotion state type and emotion state degree.

[0010] Step four: The application layer receives the emotional state results output by the analysis layer, and through the personalized interactive guidance module, combines the pediatric patient's age information and personality tags to filter and push interactive guidance content that is suitable for the pediatric patient's emotional state and individual characteristics.

[0011] Step 5: Record multi-dimensional emotion-related data sets, emotion state results, interactive guidance content, and interactive feedback data of pediatric patients through the data management and effect evaluation module. Conduct a comprehensive evaluation of the nursing effect, and dynamically adjust the parameters of the emotion state recognition model and the interactive guidance content library based on the evaluation results to form a closed-loop nursing process of "monitoring-intervention-evaluation-optimization".

[0012] As an improvement, the real-time emotion state monitoring module's multi-dimensional emotion-related data acquisition includes three independent dimensions: facial expression data acquisition, voice emotion data acquisition, and physiological signal data acquisition. The acquisition processes of the three dimensions are carried out synchronously and do not interfere with each other.

[0013] As an improvement, the facial expression data acquisition is achieved through a low-power camera that meets the safety standards for use by pediatric patients. The low-power camera captures facial images of pediatric patients in real time, extracts feature points related to emotion expression in the facial images, and then extracts the corresponding facial expression features.

[0014] As an improvement, the voice emotion data acquisition is achieved through a noise-canceling microphone with environmental noise reduction function. The noise-canceling microphone acquires the voice signal of the pediatric patient, filters out environmental interference noise, and extracts relevant parameters such as tone change features, speech rate change features, and energy change features from the voice signal.

[0015] As an improvement, the physiological signal data acquisition is achieved through a non-invasive flexible wristband sensor made of flexible material. The flexible wristband sensor fits the skin of the pediatric patient's wrist and collects data on changes in the patient's heart rate and skin conductance response. The trend of these two types of data reflects the patient's emotional and physiological arousal level.

[0016] As an improvement, the analysis layer adopts an edge computing architecture that combines edge computing and cloud computing. The preprocessing unit deployed on the acquisition terminal performs feature extraction and preprocessing on the collected multi-dimensional emotion-related data. The preprocessed feature data is then transmitted to the cloud server, which completes the inference calculation process of the emotion state recognition model, thus shortening the output delay of the emotion state results.

[0017] As an improvement, the personalized interactive guidance module is divided into appropriate interactive guidance forms according to the age range of pediatric patients. The guidance forms for younger pediatric patients include augmented reality interactive games and sound and light soothing devices, while the guidance forms for school-aged pediatric patients include scenario simulation animations, emotional guidance interactive Q&A, and interest-customized popular science content.

[0018] As an improvement, the personalized interactive guidance module has a built-in guidance strategy recommendation engine. The guidance strategy recommendation engine simultaneously receives the emotional state results output by the emotional state recognition model, the age information of pediatric patients, and the personality tags obtained through the initial questionnaire survey. It dynamically adjusts the type, difficulty, and presentation format of the interactive guidance content pushed according to preset adaptation rules.

[0019] As an improvement, the data management unit in the data management and effect evaluation module adopts blockchain encryption storage technology to encrypt and store multi-dimensional emotion-related data, emotion state results, interactive guidance content records, and interactive feedback data. It also provides a historical data query interface, allowing medical staff to view the historical trend curves of pediatric patients' emotional changes over a specified time period.

[0020] As an improvement, the effect evaluation unit in the data management and effect evaluation module includes a quantitative indicator evaluation subunit and a qualitative indicator evaluation subunit. The quantitative indicator evaluation subunit evaluates based on the magnitude of changes in emotional state, the duration of interaction and cooperation, and the duration of negative emotions. The qualitative indicator evaluation subunit evaluates based on the nursing effect evaluation form filled out by medical staff and the parent feedback questionnaire. The evaluation results of the two subunits are summarized to form a comprehensive nursing effect report.

[0021] The advantages of this invention compared to existing technologies are as follows: It employs a non-invasive data acquisition method, utilizing a low-power camera that meets pediatric patient safety standards, a noise-canceling microphone with environmental noise reduction capabilities, and a non-invasive flexible wristband sensor made of flexible materials to simultaneously collect multi-dimensional emotion-related data. This avoids discomfort for pediatric patients and improves nursing acceptance and cooperation. The multi-dimensional data, combined with multimodal data fusion algorithms and an edge computing and cloud-based collaborative architecture, enables more comprehensive and accurate emotional state recognition, and allows for rapid result output and real-time monitoring and response. The personalized interactive guidance module pushes appropriate guidance content based on the pediatric patient's age range, personality tags, and emotional state results, specifically alleviating negative emotions and improving the effectiveness of psychological nursing interventions. The data management unit uses blockchain encryption storage technology to ensure data security and privacy, while providing a historical data query interface to offer objective data support for medical staff and assist in nursing decision-making. The effectiveness evaluation unit takes into account both quantitative and qualitative indicators, and the evaluation results are scientific and comprehensive. Combined with the closed-loop process of "monitoring-intervention-evaluation-optimization", the parameters of the emotional state recognition model and the interactive guidance content library can be dynamically adjusted to continuously optimize the quality of nursing care and promote the development of pediatric psychological nursing towards precision and personalization. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the pediatric psychological nursing interactive guidance and real-time monitoring and analysis method for emotional state in this invention. Detailed Implementation

[0023] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0025] It is understood that spatial relation terms such as "below," "under," "below," "below," "above," "over," etc., can be used here to describe the relationship between one element or feature shown in the figure and other elements or features. It should be understood that, in addition to the orientation shown in the figure, spatial relation terms also include different orientations of the device in use and operation. For example, if the device in the figure is flipped, the element or feature described as "below" or "under" or "below" of the other element or feature will be oriented "over" the other element or feature. Therefore, the exemplary terms "below" and "under" can include both upper and lower orientations. Furthermore, the device may also include other orientations, such as being rotated 90 degrees or other orientations, and the spatial descriptive terms used herein will be interpreted accordingly.

[0026] It should be noted that when one element is considered to be "connected" to another element, it can be directly connected to the other element or connected to the other element through an intermediary element. In the following embodiments, "connection" should be understood as "electrical connection," "communication connection," etc., if the connected circuits, modules, units, etc., have the transmission of electrical signals or data between them.

[0027] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising,” “including,” or “having,” etc., specify the presence of the stated feature, whole, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof.

[0028] Referring to the attached diagram, the method for interactive guidance and real-time monitoring and analysis of emotional states in pediatric psychological nursing includes the following complete steps:

[0029] Step 1: Deploy a real-time emotional state monitoring module. Using a non-invasive acquisition method, it simultaneously collects facial expression data, voice emotion data, and physiological signal data of pediatric patients to form a multi-dimensional emotion-related data set.

[0030] Step two: The collected multi-dimensional emotion-related data set is encrypted and transmitted to the analysis layer through the wireless transmission module and data encryption module contained in the transmission layer, ensuring the security and integrity of the data transmission process.

[0031] Step 3: The analysis layer calls the preset multimodal data fusion algorithm to perform feature fusion processing on the multi-dimensional emotion-related data set, and then analyzes the fused feature data through the trained emotion state recognition model to output the emotion state result containing the emotion state type and emotion state degree.

[0032] Step four: The application layer receives the emotional state results output by the analysis layer, and through the personalized interactive guidance module, combines the pediatric patient's age information and personality tags to filter and push interactive guidance content that is suitable for the pediatric patient's emotional state and individual characteristics.

[0033] Step 5: Record multi-dimensional emotion-related data sets, emotion state results, interactive guidance content, and interactive feedback data of pediatric patients through the data management and effect evaluation module. Conduct a comprehensive evaluation of the nursing effect, and dynamically adjust the parameters of the emotion state recognition model and the interactive guidance content library based on the evaluation results to form a closed-loop nursing process of "monitoring-intervention-evaluation-optimization".

[0034] The real-time emotion monitoring module collects multi-dimensional emotion-related data, including three independent dimensions: facial expression data collection, voice emotion data collection, and physiological signal data collection. The collection processes of the three dimensions are carried out synchronously and do not interfere with each other.

[0035] The facial expression data acquisition is achieved through a low-power camera that meets the safety standards for use by pediatric patients. The low-power camera captures facial images of pediatric patients in real time, extracts feature points related to emotion expression in the facial images, and then extracts the corresponding facial expression features.

[0036] The voice emotion data acquisition is achieved through a noise-canceling microphone with environmental noise reduction function. The noise-canceling microphone acquires the voice signal of the pediatric patient, filters out environmental interference noise, and extracts relevant parameters such as tone change features, speech rate change features, and energy change features from the voice signal.

[0037] The physiological signal data acquisition is achieved through a non-invasive flexible wristband sensor made of flexible material. The flexible wristband sensor fits the skin of the pediatric patient's wrist and collects data on changes in the patient's heart rate and skin conductance. The trend of these two types of data reflects the patient's emotional and physiological arousal level.

[0038] The analysis layer adopts an edge computing architecture that combines edge computing and cloud computing. The preprocessing unit deployed on the acquisition terminal performs feature extraction and preprocessing on the collected multi-dimensional emotion-related data. The preprocessed feature data is then transmitted to the cloud server, which completes the inference calculation process of the emotion state recognition model, thus shortening the output delay of the emotion state results.

[0039] The personalized interactive guidance module allocates appropriate interactive guidance forms according to the age range of pediatric patients. The guidance forms for younger pediatric patients include augmented reality interactive games and sound and light soothing devices, while the guidance forms for school-aged pediatric patients include scenario simulation animations, interactive Q&A for emotional guidance, and interest-customized popular science content.

[0040] The personalized interactive guidance module has a built-in guidance strategy recommendation engine. The guidance strategy recommendation engine simultaneously receives the emotional state results output by the emotional state recognition model, the age information of pediatric patients, and the personality tags obtained through the initial questionnaire survey. It dynamically adjusts the type, difficulty, and presentation format of the interactive guidance content pushed according to preset adaptation rules.

[0041] The data management and effect evaluation module uses blockchain encryption storage technology to encrypt and store multi-dimensional emotion-related data, emotion state results, interactive guidance content records, and interactive feedback data. It also provides a historical data query interface, allowing medical staff to view the historical trend curves of pediatric patients' emotional changes over a specified time period.

[0042] The data management and effectiveness evaluation module includes a quantitative indicator evaluation sub-unit and a qualitative indicator evaluation sub-unit. The quantitative indicator evaluation sub-unit evaluates based on the magnitude of changes in emotional state, the duration of interaction and cooperation, and the duration of negative emotions. The qualitative indicator evaluation sub-unit evaluates based on the nursing effectiveness evaluation form filled out by medical staff and the parent feedback questionnaire. The evaluation results of the two sub-units are combined to form a comprehensive nursing effectiveness report.

[0043] The pediatric psychological nursing interactive guidance and real-time monitoring and analysis method disclosed in this invention is applicable to ward care, outpatient treatment and other scenarios for pediatric patients aged 3-12 years. It aims to achieve precision and closed-loop optimization of pediatric psychological nursing through the synergistic operation of non-invasive monitoring, intelligent analysis and personalized guidance.

[0044] I. Overall Implementation Environment Setup:

[0045] This embodiment is set as an application scenario in a general pediatric ward of a hospital, providing psychological nursing services for hospitalized pediatric patients aged 3-12. The overall system hardware deployment includes: a low-power camera, conforming to pediatric patient safety standards, fixedly installed 1.5 meters above the bedside, ensuring the lens is directly facing the patient's face without obstruction; a noise-canceling microphone with environmental noise reduction function placed on the bedside table, 0.5-1 meter away from the patient's head to avoid environmental noise interference; and a non-invasive flexible wristband sensor made of flexible medical material, with the wristband's tightness adjusted to fit the skin without affecting blood circulation. The software system deployment includes: installing a data preprocessing program on the data acquisition terminal (e.g., a tablet computer); deploying an emotion state recognition model and guidance strategy recommendation engine in the cloud; equipping the medical staff with a monitoring platform terminal (e.g., a desktop computer); and having parents receive feedback information via a mobile application. All devices construct a communication network through a wireless LAN (wireless network) and Bluetooth (wireless transmission technology). The wireless transmission module and data encryption module of the transmission layer are integrated into the communication module to ensure the security and stability of data transmission.

[0046] II. Implementation process of the real-time emotional state monitoring module:

[0047] The core objective of the real-time emotional state monitoring module is to synchronously and non-invasively collect facial expression data, voice emotion data, and physiological signal data from pediatric patients, forming a complete multi-dimensional set of emotion-related data.

[0048] (I) Implementation of Facial Expression Data Collection:

[0049] After the low-power camera is activated, it captures facial images of pediatric patients in real time at a rate of 15 frames per second (the acquisition frequency is only for describing the implementation process and is not limiting data). During the acquisition process, it automatically avoids interference scenarios such as strong light and backlight, and optimizes the clarity of facial images through a built-in image correction algorithm. Subsequently, a facial feature point extraction algorithm is used to locate 68 facial feature points related to emotion expression (such as feature points at the corners of the eyes, mouth, and eyebrows), and extracts parameters such as displacement and angle changes for each feature point to form facial expression feature data. For example, when the corners of the patient's mouth turn up, the displacement change parameter of the corresponding corner of the mouth feature point will show a positive fluctuation, and this fluctuation parameter is an important component of the facial expression feature data.

[0050] (II) Implementation of Voice Emotion Data Collection:

[0051] The noise-canceling microphone is continuously activated, collecting real-time voice signals from pediatric patients (including crying, talking, and sighing). Simultaneously, environmental noise reduction is activated, using filtering algorithms to eliminate ambient noise such as equipment operation and conversations within the ward. From the filtered, clean voice signal, parameters related to pitch variation (e.g., fluctuations in voice frequency), speech rate variation (e.g., changes in the number of syllables per unit time), and energy variation (e.g., changes in voice signal strength) are extracted to form voice emotion feature data. For example, when a patient is anxious, the pitch frequency of the voice signal will increase, and the speech rate will accelerate, with corresponding changes in the feature parameters.

[0052] (III) Implementation of Physiological Signal Data Acquisition:

[0053] After being worn, the flexible wristband sensor continuously collects heart rate and skin conductance response (SCRR) data from pediatric patients via built-in heart rate and SCRR sensors. The heart rate sensor detects the pulse at the wrist, recording changes in the number of heartbeats per unit time; the SCRR sensor detects changes in the conductivity of the skin surface, reflecting the patient's emotional and physiological arousal level. During data collection, the sensor automatically adapts to the patient's wrist size to ensure data stability. The collected heart rate and SCRR data are transmitted in real time to the data acquisition terminal, forming physiological signal characteristic data.

[0054] The data collection processes for the three dimensions mentioned above are carried out simultaneously and without interference. The collection terminal integrates the feature data of the three dimensions to form a multi-dimensional emotion-related data set, providing a complete data foundation for subsequent analysis.

[0055] III. Implementation process of the transport layer:

[0056] After the data acquisition terminal generates a multi-dimensional emotion-related data set, the data is securely transmitted via the wireless transmission module and data encryption module in the transmission layer. First, the data encryption module uses a symmetric encryption algorithm to encrypt the multi-dimensional emotion-related data set, converting the original data into encrypted ciphertext data to prevent the data from being stolen or tampered with during transmission. Then, the wireless transmission module transmits the encrypted ciphertext data to the cloud server in the analysis layer via Wi-Fi or Bluetooth. During transmission, the transmission layer monitors the network connection status in real time. If a network interruption occurs, the data encryption module temporarily stores the encrypted ciphertext data in the local storage unit of the acquisition terminal and automatically retransmits it once the network is restored, ensuring the integrity of the data transmission.

[0057] IV. Implementation process of the analysis layer:

[0058] The analysis layer adopts an edge computing architecture that combines edge computing and cloud computing to achieve efficient analysis of multi-dimensional emotion-related data and rapid output of emotion state results.

[0059] (I) Data Preprocessing Implementation:

[0060] After receiving a multi-dimensional set of emotion-related data, the preprocessing unit deployed at the acquisition terminal standardizes the data to eliminate dimensional differences between different dimensions. For example, facial expression feature data, voice emotion feature data, and physiological signal feature data are mapped to the [0,1] interval to ensure comparability of data across dimensions. During preprocessing, abnormal data (such as invalid facial image data due to patient limb obstruction, abnormal voice data caused by sudden noise, etc.) are automatically removed to ensure data quality.

[0061] (II) Implementation of Multimodal Data Fusion:

[0062] After the preprocessed feature data is transmitted to the cloud server, the analysis layer calls a preset multimodal data fusion algorithm to perform feature fusion processing. This embodiment uses a weighted summation fusion method, and the fusion formula is as follows:

[0063] F = w1F1 + w2F2 + w3F3

[0064] Where F represents the fused comprehensive feature value; w1, w2, and w3 represent the fusion weights of facial expression feature data, voice emotion feature data, and physiological signal feature data, respectively, with values ​​ranging from [0,1] and satisfying w1+w2+w3=1. The weight values ​​are preset based on the individual characteristics of pediatric patients, such as age and gender, and can be dynamically adjusted through subsequent closed-loop optimization; F1 represents the standardized processing result of facial expression feature data, F2 represents the standardized processing result of voice emotion feature data, and F3 represents the standardized processing result of physiological signal feature data. The purpose of this formula is to organically integrate the feature data from three independent dimensions, fully utilize the emotional representation information of each dimension, and improve the accuracy of subsequent emotion recognition.

[0065] (III) Implementation of Emotional State Recognition:

[0066] The cloud server inputs the fused comprehensive feature values ​​into the trained emotion state recognition model. This model, built on a deep learning algorithm, has been trained and optimized using a large amount of emotion sample data from pediatric patients. The model analyzes the comprehensive feature values ​​and outputs emotion state results that include both the emotion state type and its intensity. The emotion state types include four categories: pleasure, calmness, anxiety, and fear. The intensity of the emotion state is determined by the interval division corresponding to the comprehensive feature value, and is positively correlated with the fused comprehensive feature value (the higher the comprehensive feature value, the more pleasure-oriented the emotion state; conversely, the lower the value, the more negative the emotion state). The analysis layer, through an edge computing and cloud-collaborative architecture, distributes simple computational tasks such as data preprocessing to the acquisition terminal, while only complex computational tasks such as fusion and inference are handled by the cloud server. This effectively shortens the output latency of the emotion state results and ensures real-time monitoring.

[0067] V. Implementation process of the personalized interactive guidance module:

[0068] After receiving the emotional state results output by the analysis layer, the application layer pushes appropriate interactive guidance content to pediatric patients through the personalized interactive guidance module to achieve targeted psychological nursing intervention.

[0069] (I) Guiding the implementation of appropriate methods:

[0070] The personalized interactive guidance module first determines the basic guidance format based on the age range of pediatric patients: For younger pediatric patients aged 3-6, a combination of augmented reality interactive games and sound and light soothing devices is used. Augmented reality interactive games are presented on the display screen of the data acquisition terminal, such as a "ward treasure hunt" game where patients touch the screen to control a virtual character to find virtual items in the ward and receive virtual rewards (such as cartoon stickers) upon completion. The sound and light soothing devices are integrated into the data acquisition terminal, outputting soft, warm-toned light and shadow and soothing nursery rhymes (such as lullabies) based on the patient's emotional state, alleviating negative emotions through visual and auditory stimulation. For school-aged pediatric patients aged 7-12, a combination of scenario-based animation, emotional guidance-oriented interactive Q&A, and interest-customized science popularization content is used. Scenario-based animated simulations are played on the screen, with content revolving around themes such as "hospital treatment process" and "bravely facing illness," conveying positive emotions in a storytelling format; interactive Q&A sessions for emotional support are presented in text or voice format, such as "Are you feeling nervous right now? You can tell me about it," guiding patients to express their inner feelings; and interest-based customized science popularization content is pushed based on patients' interests (such as drawing, animals, etc.) obtained from the initial questionnaire survey, pushing relevant health science popularization picture books or short videos to alleviate anxiety while popularizing health knowledge.

[0071] (II) Implementation of Dynamic Adjustment of Guiding Content:

[0072] The personalized interactive guidance module's built-in guidance strategy recommendation engine simultaneously receives the emotional state results output by the emotional state recognition model, the pediatric patient's age information, and personality tags (such as outgoing, introverted, etc.) obtained through the initial questionnaire. It dynamically adjusts the type, difficulty, and presentation of the interactive guidance content according to preset adaptation rules. For example, when the emotional state result is anxiety and the patient is an introverted young child, the guidance strategy recommendation engine prioritizes pushing sound and light soothing devices and low-difficulty augmented reality interactive games to reduce the stimulation of complex interactions. When the emotional state result is calm and the patient is an outgoing school-aged child, it pushes moderately difficult scenario simulation animations and interactive Q&A to increase the interactivity. Simultaneously, the module collects real-time interactive feedback data from pediatric patients (such as the frequency of screen touches, the duration of viewing content, and voice responses) as a basis for subsequent content adjustments.

[0073] VI. Implementation process of the data management and performance evaluation module:

[0074] The data management and effectiveness evaluation module is responsible for recording relevant data throughout the nursing process and comprehensively evaluating the nursing effectiveness, providing support for closed-loop optimization.

[0075] (I) Data Management Implementation:

[0076] The data management unit employs blockchain encryption storage technology to encrypt and store multi-dimensional emotion-related data sets, emotion state results, interactive guidance content records, and interactive feedback data. Blockchain technology stores data through distributed nodes, with each node maintaining a complete copy of the data to ensure its immutability. Simultaneously, all data is anonymized, retaining only information relevant to nursing analysis to protect patient privacy. The data management unit provides a historical data query interface. Medical staff can input patient identification information (such as medical record number) through the monitoring platform terminal to view the patient's historical emotion change trend curve over a specified time period. The curve, with time on the horizontal axis and emotion state severity on the vertical axis, visually presents the dynamic changes in the patient's emotions, providing data reference for medical staff to adjust nursing plans.

[0077] (II) Implementation of Nursing Effectiveness Evaluation:

[0078] The effectiveness evaluation unit includes a quantitative indicator evaluation subunit and a qualitative indicator evaluation subunit. The conclusion on nursing effectiveness is formed by combining the evaluation results of both types of indicators. The quantitative indicator evaluation subunit assesses three indicators: the magnitude of emotional state changes, the duration of interaction and cooperation, and the duration of negative emotions. First, each indicator is standardized (mapped to [0, 100] points). Then, the quantitative indicator score is calculated through a simple weighted summation, as shown in the following formula:

[0079] S q=c1S1+c2S2+c3S3

[0080] Among them, S q The formula represents the quantitative indicator score; c1, c2, and c3 represent the weights of the magnitude of change in emotional state, duration of interaction and cooperation, and duration of negative emotions, respectively, with values ​​ranging from [0,1] and satisfying c1+c2+c3=1. The weight values ​​are preset according to the nursing focus; S1 represents the standardized score of the magnitude of change in emotional state (higher score when emotional state changes from negative to pleasant), S2 represents the standardized score of the duration of interaction and cooperation (the longer the duration, the higher the score), and S3 represents the standardized score of the duration of negative emotions (the shorter the duration, the higher the score). The purpose of this formula is to convert the three quantitative indicators into a unified score, making it easier to intuitively measure the quantitative effect of nursing intervention.

[0081] The qualitative indicator assessment subunit was based on the nursing effectiveness evaluation forms completed by medical staff and the parent feedback questionnaires. Medical staff scored patients' emotional cooperation and behavioral performance (out of 100 points) based on daily nursing observations; parents completed a feedback questionnaire via a mobile application, scoring their satisfaction with the nursing effectiveness (out of 100 points). The qualitative indicator score S... z The average of the two (S) z =(S y +S j ) / 2, where S y Rate healthcare workers, S j (Rating for parents).

[0082] The effectiveness evaluation unit combines quantitative and qualitative indicator scores to obtain a comprehensive nursing effectiveness score:

[0083] S = aS q +bS z

[0084] Where S represents the overall nursing effectiveness score; a and b represent the weights of the quantitative and qualitative indicator scores, respectively, both ranging from [0,1] and satisfying a+b=1, which can be adjusted according to the needs of nursing assessment; S q S is a quantitative indicator score. z This is the score for qualitative indicators. The formula integrates quantitative and qualitative assessment results to comprehensively reflect nursing effectiveness. The assessment unit generates a comprehensive nursing effectiveness report based on the comprehensive nursing effectiveness score and pushes it to the medical staff monitoring platform and the parent application.

[0085] VII. Closed-loop optimization implementation process:

[0086] After the data management and effectiveness evaluation module generates a comprehensive nursing effectiveness report, if the comprehensive nursing effectiveness score does not reach a preset threshold (e.g., 80 points), the system automatically initiates a closed-loop optimization process: adjusting the parameters of the emotion state recognition model based on the evaluation results (e.g., optimizing the model's feature weight allocation) to improve the accuracy of emotion recognition; simultaneously updating the interactive guidance content library, adding more suitable guidance content, and adjusting the adaptation rules of the guidance strategy recommendation engine (e.g., optimizing weight allocation). If the comprehensive nursing effectiveness score reaches the preset threshold, the current model parameters and guidance content are maintained, and data is continuously collected for dynamic monitoring. Through this closed-loop process of "monitoring-intervention-evaluation-optimization," continuous optimization of pediatric psychological nursing services is achieved, constantly improving nursing effectiveness.

[0087] The beneficial effects of interactive guidance and real-time monitoring and analysis of emotional states in pediatric psychological nursing:

[0088] Improving the comfort and cooperation of pediatric patients: This technical solution uses a non-invasive data acquisition method through a real-time emotional state monitoring module, combined with a non-invasive flexible wristband sensor made of flexible materials, a low-power camera that meets the safety standards for pediatric patients, and a noise-canceling microphone with environmental noise reduction function. This avoids the physical discomfort and psychological resistance caused by invasive data acquisition to pediatric patients, adapts to the physiological characteristics of pediatric patients, and significantly improves their acceptance and cooperation in the nursing process.

[0089] Achieving comprehensive and accurate emotional state monitoring: The real-time emotional state monitoring module simultaneously collects information from three independent dimensions: facial expression data, voice emotion data, and physiological signal data, forming a complete multi-dimensional emotional data set, which overcomes the limitations of traditional single-dimensional monitoring. Then, the multi-modal data fusion algorithm in the analysis layer performs feature fusion processing on the multi-dimensional emotional data set, and analyzes it in conjunction with the trained emotional state recognition model, effectively improving the accuracy of identifying emotional state types and emotional state levels, and providing a reliable basis for subsequent nursing interventions.

[0090] Ensuring the security and integrity of data transmission and storage: The transmission layer encrypts the multi-dimensional emotion-related data set before transmission through a wireless transmission module and a data encryption module. The data management unit in the data management and effect evaluation module uses blockchain encryption storage technology to encrypt and store various types of data. This dual protection mechanism not only prevents data from being stolen or tampered with during transmission, but also ensures the security and immutability of data storage. At the same time, anonymization protects the privacy of pediatric patients and complies with medical data security standards.

[0091] Real-time response for emotion monitoring and nursing guidance: The analysis layer adopts an edge computing architecture that combines edge computing and cloud computing. Data preprocessing is completed by the preprocessing unit of the acquisition terminal, while the cloud server focuses on the inference calculation of the emotion state recognition model, which greatly shortens the output delay of emotion state results and ensures the effectiveness of real-time emotion state monitoring. The application layer quickly pushes appropriate interactive guidance content based on the real-time output of emotion state results, realizing a real-time response from emotion recognition to intervention guidance and timely alleviating the negative emotions of pediatric patients.

[0092] Enhancing the personalization and effectiveness of interactive guidance: The personalized interactive guidance module allocates appropriate guidance formats according to the age range of pediatric patients. Furthermore, through a guidance strategy recommendation engine that combines emotional state results, age information, and personality tags, it dynamically adjusts the type, difficulty, and presentation format of interactive guidance content. This avoids the limitations of traditional homogeneous guidance, making the interactive guidance content more aligned with the individual characteristics and emotional needs of pediatric patients, and significantly improving the pertinence and effectiveness of psychological nursing interventions.

[0093] Constructing a closed-loop nursing process to continuously optimize nursing quality: Through a closed-loop nursing process of "monitoring-intervention-evaluation-optimization", the data management and effect evaluation module records data throughout the process and conducts comprehensive evaluation. Based on the evaluation results, the parameters of the emotional state recognition model and the interactive guidance content library are dynamically adjusted, enabling the system to continuously adapt to the emotional change patterns and nursing needs of pediatric patients, achieve iterative optimization of nursing plans, and continuously improve the overall quality and level of pediatric psychological nursing.

[0094] Provide data support for medical staff and assist in nursing decision-making: The data management and effect evaluation module provides a historical data query interface, allowing medical staff to view the historical trend curves of pediatric patients' emotional changes within a specified time period. Combined with the comprehensive nursing effect report, this enables medical staff to intuitively grasp the emotional dynamics and nursing effects of pediatric patients, providing objective data support for adjusting personalized nursing plans and formulating subsequent nursing plans, and reducing subjective judgment bias.

[0095] Balancing quantitative and qualitative assessments to ensure the scientific rigor of nursing effectiveness evaluation: The effectiveness evaluation unit assesses nursing effectiveness from the perspectives of objective data and subjective feedback through quantitative and qualitative indicator assessment sub-units, respectively. The assessment results of the two sub-units are summarized to form a comprehensive nursing effectiveness report, which reflects quantifiable objective effects such as changes in emotional state and interaction and cooperation, while also taking into account the professional assessments of medical staff and the subjective feelings of parents, making the nursing effectiveness evaluation more comprehensive and scientific.

[0096] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A method for interactive guidance and real-time monitoring and analysis of emotional states in pediatric psychological nursing, characterized by: Includes the following complete steps: Step 1: Deploy a real-time emotional state monitoring module. Using a non-invasive acquisition method, it simultaneously collects facial expression data, voice emotion data, and physiological signal data of pediatric patients to form a multi-dimensional emotion-related data set. Step two: The collected multi-dimensional emotion-related data set is encrypted and transmitted to the analysis layer through the wireless transmission module and data encryption module contained in the transmission layer, ensuring the security and integrity of the data transmission process. Step 3: The analysis layer calls the preset multimodal data fusion algorithm to perform feature fusion processing on the multi-dimensional emotion-related data set, and then analyzes the fused feature data through the trained emotion state recognition model to output the emotion state result containing the emotion state type and emotion state degree. Step four: The application layer receives the emotional state results output by the analysis layer, and through the personalized interactive guidance module, combines the pediatric patient's age information and personality tags to filter and push interactive guidance content that is suitable for the pediatric patient's emotional state and individual characteristics. Step 5: Record multi-dimensional emotion-related data sets, emotion state results, interactive guidance content, and interactive feedback data of pediatric patients through the data management and effect evaluation module. Conduct a comprehensive evaluation of the nursing effect, and dynamically adjust the parameters of the emotion state recognition model and the interactive guidance content library based on the evaluation results to form a closed-loop nursing process of "monitoring-intervention-evaluation-optimization".

2. The method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing according to claim 1, characterized in that: The real-time emotion monitoring module collects multi-dimensional emotion-related data, including three independent dimensions: facial expression data collection, voice emotion data collection, and physiological signal data collection. The collection processes of the three dimensions are carried out synchronously and do not interfere with each other.

3. The method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing according to claim 2, characterized in that: The facial expression data acquisition is achieved through a low-power camera that meets the safety standards for use by pediatric patients. The low-power camera captures facial images of pediatric patients in real time, extracts feature points related to emotion expression in the facial images, and then extracts the corresponding facial expression features.

4. The method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing according to claim 2, characterized in that: The voice emotion data acquisition is achieved through a noise-canceling microphone with environmental noise reduction function. The noise-canceling microphone acquires the voice signal of the pediatric patient, filters out environmental interference noise, and extracts relevant parameters such as tone change features, speech rate change features, and energy change features from the voice signal.

5. The method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing according to claim 2, characterized in that: The physiological signal data acquisition is achieved through a non-invasive flexible wristband sensor made of flexible material. The flexible wristband sensor fits the skin of the pediatric patient's wrist and collects data on changes in the patient's heart rate and skin conductance. The trend of these two types of data reflects the patient's emotional and physiological arousal level.

6. The method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing according to claim 1, characterized in that: The analysis layer adopts an edge computing architecture that combines edge computing and cloud computing. The preprocessing unit deployed on the acquisition terminal performs feature extraction and preprocessing on the collected multi-dimensional emotion-related data. The preprocessed feature data is then transmitted to the cloud server, which completes the inference calculation process of the emotion state recognition model, thus shortening the output delay of the emotion state results.

7. The method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing according to claim 1, characterized in that: The personalized interactive guidance module allocates appropriate interactive guidance forms according to the age range of pediatric patients. The guidance forms for younger pediatric patients include augmented reality interactive games and sound and light soothing devices, while the guidance forms for school-aged pediatric patients include scenario simulation animations, interactive Q&A for emotional guidance, and interest-customized popular science content.

8. The method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing according to claim 7, characterized in that: The personalized interactive guidance module has a built-in guidance strategy recommendation engine. The guidance strategy recommendation engine simultaneously receives the emotional state results output by the emotional state recognition model, the age information of pediatric patients, and the personality tags obtained through the initial questionnaire survey. It dynamically adjusts the type, difficulty, and presentation format of the interactive guidance content pushed according to preset adaptation rules.

9. The method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing according to claim 1, characterized in that: The data management and effect evaluation module uses blockchain encryption storage technology to encrypt and store multi-dimensional emotion-related data, emotion state results, interactive guidance content records, and interactive feedback data. It also provides a historical data query interface, allowing medical staff to view the historical trend curves of pediatric patients' emotional changes over a specified time period.

10. The method for interactive guidance and real-time monitoring and analysis of emotional state in pediatric psychological nursing according to claim 1, characterized in that: The data management and effectiveness evaluation module includes a quantitative indicator evaluation sub-unit and a qualitative indicator evaluation sub-unit. The quantitative indicator evaluation sub-unit evaluates based on the magnitude of changes in emotional state, the duration of interaction and cooperation, and the duration of negative emotions. The qualitative indicator evaluation sub-unit evaluates based on the nursing effectiveness evaluation form filled out by medical staff and the parent feedback questionnaire. The evaluation results of the two sub-units are combined to form a comprehensive nursing effectiveness report.

Images