Pediatric emergency pre-examination triage method based on crying emotion recognition

Abstract

The invention discloses a pediatric emergency treatment pre-examination triage method based on cry emotion recognition, and belongs to the technical field of emergency treatment triage, and the method specifically comprises the steps: constructing a child patient cry and health information data set; extracting frequency, intensity and rhythm features in the audio to form standardized audio feature data; feature categories are divided according to the age groups of the child patients, standardized audio features of the same age group are associated with corresponding emotion tags, and an age-divided emotion feature library is established; training an emotion recognition model based on the age-divided emotion feature library, and determining a corresponding relationship between different emotion types and the emergency degrees of the pediatric emergency treatment conditions; acquiring crying audio of a new hospital child in real time, inputting the trained emotion recognition model, and outputting an emotion type and an emergency degree corresponding to crying of the child; and calling the basic health information of the new hospital child patient, combining the basic health information with the emergency degree obtained by the emotion recognition model to generate a targeted pre-examination triage scheme, and synchronizing the pre-examination triage scheme to the pediatric emergency triage management system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of emergency triage, in particular to a pediatric emergency pre-examination triage method based on cry emotion recognition. BACKGROUND

[0002] Pediatric emergency is a high-demand scenario in medical services, with rapid changes in the condition of sick children and anxious emotions of their families. Efficient and accurate pre-examination triage is a key link to ensure the order of diagnosis and treatment and the safety of sick children. The existing pediatric emergency pre-examination triage method mainly relies on the clinical experience of medical staff, combined with the description of the symptoms of sick children by their families and basic physiological signs such as body temperature and heart rate for judgment. Some medical institutions may use standardized triage scales to assist in assessment, but the core is still based on subjective judgment and single-dimensional objective signs, and the specific non-verbal expression information of sick children has not been fully integrated into the triage decision-making.

[0003] The core problem of the existing pediatric emergency pre-examination triage technology is that it fails to effectively integrate the key information of the cries of sick children, which directly reflects the emotions and condition of the children, and lacks targeted consideration of the physiological differences of children of different ages, resulting in limitations such as strong subjectivity and incomplete judgment dimensions in triage decision-making. The description of symptoms by families is easily influenced by emotions, and a unified assessment standard cannot adapt to the differences in cries and condition of children of different ages, ultimately resulting in insufficient accuracy in judging the emergency level of the condition, which may either delay the disposal of emergency cases or occupy high-quality medical resources for non-emergency cases, affecting the overall diagnosis and treatment efficiency and service quality of pediatric emergency. SUMMARY

[0004] The purpose of the present application is to provide a pediatric emergency pre-examination triage method based on cry emotion recognition, which solves the problems in the background art: The purpose of the present application can be achieved by the following technical solutions: A pediatric emergency pre-examination triage method based on cry emotion recognition, comprising the following steps: S1, collecting the cry audio data and basic health information of the pediatric emergency sick children to be triaged, and associating the two types of information, to construct a sick child cry and health information dataset; S2, performing noise removal processing on the cry audio in the dataset, extracting the frequency, intensity and rhythm characteristics in the audio, and forming standardized audio feature data; S3, dividing the features into categories according to the age of the children, associating the standardized audio features of the same age group with the corresponding emotion labels, and establishing an age-specific emotion feature library; S4, training an emotion recognition model based on the age-specific emotion feature library to determine the corresponding relationship between different emotion types and the emergency level of pediatric emergency; S5, real-time collection of newly admitted children's crying audio, input of the trained emotion recognition model, and output of the corresponding emotion type and emergency degree of the children's crying; S6, calling the basic health information of the newly admitted children, combining the emergency degree obtained by the emotion recognition model, generating a targeted pre-examination triage scheme, and synchronizing the pre-examination triage scheme to the pediatric emergency triage management system.

[0005] As a further scheme of the present application: in step S2, the process of extracting the frequency, intensity and rhythm characteristics in the audio to form standardized audio feature data is: The noise-removed crying audio is cut into continuous audio segments according to a fixed time length, ensuring that each segment contains a complete crying rhythm, and defining a uniform analysis unit for feature extraction; Perform feature extraction on each audio segment, obtain frequency characteristics through segmented spectrum analysis, calculate the ratio of peak value to average amplitude in the segment to obtain intensity characteristics, and record the time interval sequence of adjacent peaks as rhythm characteristics; Integrate the extracted frequency, intensity and rhythm characteristics into a feature vector in a predetermined order, adjust the value range of each index in the feature vector through a unified numerical conversion rule, and form standardized audio feature data.

[0006] As a further scheme of the present application: in step S3, the process of dividing the feature categories according to the age of the children, associating the standardized audio features of the same age group with the corresponding emotion labels, and establishing an age-based emotion feature library is: Preprocess the standardized audio features, use an unsupervised clustering algorithm, and preliminarily group them according to the similarity between feature vectors to form several basic feature clusters; For each basic feature cluster, analyze the age distribution of the children in it, determine the main age range corresponding to each cluster, and use this range as the age identification information of the cluster; Associate the basic feature clusters with age identification information with the corresponding emotion labels, classify and integrate the associated feature clusters according to the age identification, and construct an age-based emotion feature library.

[0007] As a further scheme of the present application: the specific way of preprocessing the standardized audio features, using an unsupervised clustering algorithm, and preliminarily grouping them according to the similarity between feature vectors to form several basic feature clusters is: For each feature vector in the standardized audio features, calculate the Euclidean distance between it and all other feature vectors in the data set to generate a distance matrix as the basis for feature enhancement; According to the distance matrix, weight and adjust the elements of each feature vector, the smaller the distance, the greater the weight of the corresponding feature vector, highlighting the common information of similar features, and obtaining the enhanced feature vector. Adopt the density-based clustering algorithm, take the enhanced feature vector as the input, set the density threshold and the neighborhood radius parameter, and classify the feature vectors connected in density in the feature space into a class to form the basic feature cluster.

[0008] As a further scheme of the present application: in the step S4, the process of training the emotion recognition model based on the age-based emotion feature library and determining the corresponding relationship between different emotion types and the emergency degree of the pediatric emergency condition is: The age-based emotion feature library is split into independent training sets and test sets according to age groups, ensuring that the distribution of emotion labels in each set is consistent with the original library; A multi-branch neural network is constructed, the basic layer shares the extraction of general audio features, each age group corresponds to an independent branch layer, and the emotion type of the age group is output; The corresponding branch is trained with each age group training set, the model recognition accuracy is verified through the test set, and the network parameters are adjusted until the model performance is stable; The actual priority data of the emergency treatment of children corresponding to each emotion type is collected, and a fixed corresponding relationship between the emotion type and the emergency degree is established by using statistical analysis method.

[0009] As a further scheme of the present application: the specific way of constructing a multi-branch neural network, the basic layer shares the extraction of general audio features, each age group corresponds to an independent branch layer, and the emotion type of the age group is output is: Standardized audio features are used as input, a convolution layer is constructed as the basic layer, and general audio features are extracted through convolution operation; An independent branch is constructed for each age group, the general features output by the basic layer are input into the fully connected layer of the branch together with the numerical coding of the age group, and feature adaptation is performed; A multi-classification output layer is set at the end of each branch, a multi-classification activation function is used to output the probability of each emotion type under the age group, and the emotion type output is realized.

[0010] As a further scheme of the present application: in the step S6, the process of retrieving the basic health information of the newly admitted children and combining the emergency degree obtained by the emotion recognition model to generate a targeted pre-examination triage scheme is: The unique identifier of the newly admitted children is used as the retrieval basis to retrieve the corresponding basic health information from the children's crying sound and health information data set, and accurate information matching is completed; The key items in the basic health information are extracted, and the emergency degree output by the emotion recognition model is input into the feature fusion module for correlation analysis to obtain a comprehensive evaluation result; According to the comprehensive evaluation result, the preset triage rule library of the pediatric emergency is matched to determine the treatment order, the corresponding consultation room and the preliminary nursing suggestion, and a targeted pre-examination triage scheme is formed.

[0011] As a further scheme of the present application: the key items in the extracted basic health information are input into a feature fusion module together with the emergency degree output by the emotion recognition model for correlation analysis to obtain a specific manner of comprehensive evaluation result: Extracting the past medical history, current body temperature and allergy history in the basic health information as key items, and converting each key item into a standardized numerical code; Assigning a preset weight to the coded key items and the emergency degree output by the emotion recognition model, and integrating them into a fusion feature vector input module according to the weight ratio; The feature fusion module performs splicing and logical judgment on the fusion feature vector, and outputs a comprehensive evaluation result containing health risk and emergency level.

[0012] The beneficial effects of the present application are: The present application significantly improves the accuracy and objectivity of the triage decision by deeply combining the cry sound emotion recognition of sick children with pediatric emergency pre-examination triage. By collecting cry sound audio data of sick children, extracting frequency, intensity and rhythm features and standardizing the processing, and constructing an age-based emotion feature library according to age, the physiological development differences of sick children of different ages are targeted and adapted, avoiding the problem of insufficient adaptability caused by uniform evaluation standards. The construction of multi-branch neural network enables the model to accurately identify the emotion type corresponding to the cry sound of children of different ages, and then performs multi-dimensional fusion analysis on the basis health information such as past medical history and body temperature, breaking the limitations of traditional triage relying on subjective judgment and single physiological indicators, effectively reducing the triage errors caused by family description bias or symptom misjudgment, and providing a more comprehensive and reliable basis for the determination of the emergency degree, ensuring that emergency cases can be identified and disposed of in time.

[0013] The present application significantly shortens the time cost of pre-examination triage by collecting real-time cry sound audio of newly admitted children, outputting the emotion type and emergency degree quickly by the trained model, and automatically generating a targeted pre-examination triage scheme combined with the basic health information and synchronizing it to the management system. The overall realization of intelligent and standardized triage decision reduces the dependence on individual experience of medical staff, helps to improve the overall diagnosis and treatment order and service quality of pediatric emergency, and provides more efficient and accurate medical care for sick children. BRIEF DESCRIPTION OF DRAWINGS

[0014] The present application will be further described below with reference to the accompanying drawings.

[0015] Figure 1 is a flowchart of a pediatric emergency pre-examination triage method based on cry sound emotion recognition. DETAILED DESCRIPTION

[0016] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative work are within the protection scope of the present application.

[0017] Please refer to Figure 1 The present application is a pediatric emergency pre-examination triage method based on crying sound emotion recognition, comprising the following steps: S1, collecting the crying sound audio data and basic health information of the pediatric emergency patients to be triaged, corresponding association of the two types of information, and constructing the crying sound and health information data set of the patients; S2, noise removal processing is performed on the crying sound audio in the data set, the frequency, intensity and rhythm characteristics in the audio are extracted, and standardized audio feature data is formed; S3, classifying the feature categories according to the age of the patients, associating the standardized audio features of the same age group with the corresponding emotion labels, and establishing an age-based emotion feature library; S4, training an emotion recognition model based on the age-based emotion feature library, and determining the corresponding relationship between different emotion types and the emergency degree of pediatric emergency; S5, real-time collection of the crying sound audio of the newly admitted patients, inputting the trained emotion recognition model, and outputting the corresponding emotion type and emergency degree of the crying sound of the patients; S6, calling the basic health information of the newly admitted patients, combining the emergency degree obtained by the emotion recognition model, generating a targeted pre-examination triage scheme, and synchronizing the pre-examination triage scheme to the pediatric emergency triage management system.

[0018] In a preferred embodiment of the present application, in step S1, the crying sound audio data and basic health information of the pediatric emergency patients to be triaged are collected, the two types of information are correspondingly associated, and the specific content of constructing the crying sound and health information data set of the patients is: Deploy the device adapted to collect the crying sound of children in the pediatric emergency triage area. When the child to be triaged cries, the medical staff starts the device to record the crying sound immediately. In the recording process, environmental interference is avoided to ensure that the audio is clear and identifiable. The basic health information is obtained by the medical staff through communication with the parents and synchronous checking of the records already recorded in the hospital emergency pre-examination registration system. The key contents such as the age, gender, current temperature, medical history, allergy and current main symptoms of the child are collected, and then accurately entered into the system. Taking the unique medical identification of the child as the association basis, the recorded crying sound is matched with the basic health information entered into the system one by one to ensure that each audio data can be accurately associated with the complete health information of the corresponding child. After the matching is correct, all the associated data is sorted and summarized according to the unified rules, and finally the crying sound and health information data set of the child is formed.

[0019] In another preferred embodiment of the present application, in the step S2, the process of extracting the frequency, intensity and rhythm characteristics in the audio to form the standardized audio feature data is: In the audio feature extraction stage, the crying sound audio after noise removal is first divided into segments. The complete audio is divided into continuous segments according to a fixed time length. The setting of this time length is based on the principle of ensuring that each segment contains a complete crying sound syllable. For example, if the crying sound syllable of the child usually lasts about 1.5 seconds, the segmentation time can be set to 2 seconds, which can completely cover the syllable and avoid feature redundancy caused by too long segments. In this way, a unified and standardized analysis unit is defined for subsequent feature extraction, so that each segment is comparable.

[0020] Then, specific feature extraction operations are performed on each audio segment. For frequency characteristics, a segmented spectrum analysis method is used to convert the audio segment into a spectrum graph through specific signal processing means. The distribution of different frequency components can be observed directly from the spectrum graph, and then the key information reflecting the frequency characteristics of the crying sound can be extracted. Taking the intensity feature extraction as an example, first find the maximum amplitude of the sound wave in the segment, then calculate the average amplitude of the entire segment, and the ratio of the two is the intensity feature value, which can reflect the strength change of the crying sound. In the rhythm feature extraction, the positions of the sound wave peaks are detected, and the time intervals between adjacent two peaks are recorded. The sequence formed by these intervals constitutes the rhythm feature. For example, the interval between the peaks of the fast and continuous crying sound is short, and the rhythm feature value will show the corresponding rule.

[0021] Finally, the integration and standardization of the features are performed. The extracted frequency, intensity, and rhythm features are combined into a multi-dimensional feature vector in a predetermined order, such as frequency features first, then intensity features, and finally rhythm features. Since the value ranges of different features can differ greatly, for example, the frequency values can range from a few hundred to a few thousand hertz, and the intensity values can range from a few times to a few dozen times, this can affect the training effect of the subsequent model. Therefore, a unified numerical conversion rule is needed to adjust the values of all feature indicators to a same reasonable range, such as between 0 and 1, thereby forming standardized audio feature data.

[0022] In another preferred embodiment of the present application, in step S3, the feature categories are divided according to the age of the children, the standardized audio features of the same age group are associated with the corresponding emotional labels, and the process of establishing an age-based emotional feature library is as follows: In the initial stage of constructing the age-based emotional feature library, the standardized audio feature data is first preprocessed to ensure that the data quality meets the clustering requirements. These standardized features have adjusted the value range through a unified rule, eliminating the dimensional differences. Next, an unsupervised clustering algorithm is used to preliminarily group the data based on the similarity between feature vectors, forming several basic feature clusters, the specific process is as follows: First, the Euclidean distance between each feature vector and all other feature vectors in the data set is calculated. The Euclidean distance is a common way to measure the similarity of two multi-dimensional feature vectors, and the smaller the distance, the closer the features of the two feature vectors corresponding to the crying audio in the frequency, intensity, and rhythm dimensions. For example, if feature vector A corresponds to a crying audio of an infant due to abdominal pain, and feature vector B corresponds to a crying audio of another infant due to a fever, there are differences in frequency peak value and rhythm interval between the two, and the calculated Euclidean distance will be larger. If feature vector C also corresponds to a crying audio of an infant due to abdominal pain, its Euclidean distance with vector A will be smaller. By calculating the distance between all feature vectors, a complete distance matrix is generated, which clearly presents the similarity relationship between any two feature vectors, serving as the basis data for subsequent feature enhancement.

[0023] Subsequently, the elements of each feature vector are adjusted by weighting according to the distance matrix. The adjustment rule is that the smaller the distance, the greater the weight of the corresponding feature vector. The core purpose of this design is to highlight the common information of similar features. For example, in the distance matrix, the k feature vectors closest to feature vector D often represent crying audio with highly similar emotional expressions, such as both being intense and painful crying. By giving these similar vectors a higher weight, the feature elements of D can be adjusted to incorporate more of these common features, resulting in an enhanced feature vector. This enhancement process can effectively reduce the interference of individual differences on feature clustering, making the crying features of the same type of emotion more concentrated.

[0024] Finally, the enhanced feature vectors are used as input data for a density-based clustering algorithm. Two key parameters need to be set during the clustering process: the density threshold and the neighborhood radius. The neighborhood radius is used to define the neighborhood range of a certain feature vector, i.e., other vectors that are within the neighborhood radius of the vector are considered as its neighbors. The density threshold is the criterion for determining whether a region forms a cluster. If the number of neighbors of a feature vector reaches or exceeds the density threshold, the region is identified as a core region, and all density-connected core regions and peripheral neighbor vectors are classified into a class. For example, if the neighborhood radius is set to r and the density threshold is set to m, when the number of neighbors of a feature vector E reaches m, E becomes a core vector, and its neighbor vectors, including the neighbors of other core vectors, will gradually aggregate to form a basic feature cluster. Through this process, all feature vectors are divided into several non-overlapping basic feature clusters, and the feature vectors in each cluster have a high degree of similarity, corresponding to a certain type of emotional expression of crying audio.

[0025] After completing the division of the basic feature clusters, age distribution analysis needs to be performed on each cluster to determine its corresponding main age range, which is used as the age identification information of the cluster. Specifically, first, the age information of all children in each basic feature cluster is extracted, which comes from the previously constructed children's crying and health information dataset and is accurately associated with the audio feature data.

[0026] Next, statistical analysis is performed on the age data in each cluster, such as calculating the proportion of children in different age groups (e.g., 0-1 years old, 1-3 years old, 3-6 years old, etc.) in the cluster. For example, in a certain basic feature cluster, there are 100 children, of which 65 are 0-1 years old, accounting for 65%; 25 are 1-3 years old, accounting for 25%; and 10 are 3-6 years old, accounting for 10%. Through this statistical analysis, it can be clearly seen that the age distribution of children in this cluster is mainly 0-1 years old, so 0-1 years old is determined as the main age range of the cluster.

[0027] If the age distribution of a certain cluster is relatively scattered, such as 0-1 years old accounting for 40%, 1-3 years old accounting for 35%, and 3-6 years old accounting for 25%, further analysis of the feature commonality of the cluster is needed, combined with clinical experience to determine which age group's emotional expression characteristics the cluster is more inclined to. For example, if the feature vectors of the cluster exhibit the typical high-frequency characteristics of infant crying in the frequency feature, even if the proportion of 1-3 years old children is close, the main age range of the cluster can still be determined as 0-1 years old. Finally, each basic feature cluster is assigned a unique age identification information, establishing a clear correspondence between the cluster and the age range of the children.

[0028] After adding age labels to the basic feature clusters, the next step is to associate these age-labeled clusters with corresponding emotional labels. Emotional labels are used to describe the type of emotion expressed by the crying audio, such as pain, hunger, fear, and irritability, and are determined based on clinical observations and professional judgments of medical staff. For example, by analyzing the medical records and treatment scene of a child corresponding to a basic feature cluster, if most children in the cluster show obvious symptoms of pain (such as severe abdominal pain, high fever, and convulsions) at that time, and the intensity and rhythm features of their crying audio are highly consistent with the typical performance of pain emotion, then the pain emotional label is associated with the cluster.

[0029] After completing the association of feature clusters and emotional labels, all associated feature clusters are classified and integrated according to age labels. For example, all feature clusters with age labels of 0-1 years old are classified into one category and integrated into the 0-1 year old emotional feature set; feature clusters with age labels of 1-3 years old are classified into another category and integrated into the 1-3 year old emotional feature set, and so on. During the integration process, each age group of feature clusters also needs to be reorganized to ensure that clusters of the same emotional type have consistency in features, and clusters of different emotional types have obvious distinguishing features. Finally, these classified and integrated feature sets form the age-based emotional feature library.

[0030] In another preferred embodiment of the present application, the process of determining the corresponding relationship between different emotional types and the emergency degree of pediatric emergency conditions based on the age-based emotional feature library in step S4 is as follows: Before developing the emotional recognition model, the constructed age-based emotional feature library is first split into data, and the data is divided into independent training set and test set according to age. The age-based emotional feature library is classified by age, and each age group contains feature data corresponding to multiple emotional types. The splitting process must strictly follow the principle of independent splitting of data within the same age group to avoid cross-mixing of data from different age groups into the same set.

[0031] The distribution of emotional labels in the training set and test set is ensured to be consistent with the original age-based feature library during splitting. For example, in the original feature library of a certain age group, the pain emotional features have the highest proportion, followed by hunger, irritability, and fear emotional features. During splitting, the proportion of each type of emotional feature in the training set and test set should be matched with the original library through random sampling. The purpose of this is to avoid the model being biased towards a certain type of emotion due to unbalanced data distribution, and to ensure that the model can learn all emotional features of that age group uniformly. After splitting, each age group will have its own training set and test set.

[0032] The model construction stage adopts a multi-branch neural network structure. The basic layer extracts general features, and the independent branch layer adapts to the feature differences of different age groups, finally realizing accurate emotion type output. The specific process is as follows: First, standardized audio features are taken as input, and a convolutional layer is constructed as the basic layer of the neural network. The core role of the convolutional layer is to extract general audio features. These features are the basic attributes shared by crying audio of different age groups, such as the basic frequency spectrum pattern of crying sound and the common law of sound wave vibration. Through convolution operation, the basic layer will filter and refine the input standardized features layer by layer, filtering out irrelevant minor differences and retaining core common information that reflects emotional expression, laying a foundation for subsequent feature adaptation of different age groups. This step is like extracting the essential features of crying from all crying sounds, and then optimizing them for different age groups.

[0033] Then, an independent branch layer is constructed for each age group to ensure that the model can accurately adapt to the feature differences of crying sounds of different age groups. First, each age group is converted into a corresponding numerical code. This code only identifies age information and does not participate in feature operation, but only serves as a basis for branch layer identification of corresponding age groups. Then, the general audio features output by the basic layer are input into the fully connected layer of the branch along with the numerical code of the age group. The fully connected layer will perform deep fusion and feature adaptation on these two types of information. For example, the crying frequency of 0-1 year old infants is generally high, and the fully connected layer will strengthen the weight of high frequency related features based on general features and weaken features that do not conform to the characteristics of this age group. The crying frequency of 3-6 year old children is relatively low, and the rhythm is more regular, so the fully connected layer will adjust the feature adaptation direction accordingly to make the features more suitable for the crying characteristics of this age group. In this way, each branch layer can form a feature processing logic that adapts to the corresponding age group.

[0034] Finally, a multi-classification output layer is set at the end of each branch to complete the emotion type output using a multi-classification activation function. The multi-classification output layer receives the feature data adapted by the fully connected layer, calculates the matching degree of each emotion type through the activation function, and finally outputs the corresponding probability of all preset emotion types for this age group. For example, the output layer of the 0-1 year old branch will output the probability values of pain, hunger, irritability, and fear, and the probability values represent the matching degree of the current input audio with the emotion type. The model will determine the most likely emotion type corresponding to the current crying sound according to the distribution of probability values, thereby realizing the emotion recognition function for a specific age group. The entire neural network structure not only ensures the efficient reuse of general features, but also realizes the individual adaptation of age groups through independent branches, balancing the training efficiency and recognition accuracy of the model.

[0035] The model training stage adopts the method of "age training and age verification" to ensure that each age branch can achieve stable recognition performance. For each age group, input its exclusive training set into the corresponding branch layer, and let the branch layer gradually learn the feature rules of different emotion types in this age group through continuous iteration. During the training process, the model will continuously adjust the internal parameters to optimize the correspondence between features and emotion types, such as making the high-frequency and high-intensity features of the "pain" emotion type form a more stable association with the "pain" label.

[0036] After a certain stage of training, the test set of this age group is introduced to verify the model performance. Input the feature data in the test set into the trained model to obtain the emotion type recognition result, and then compare it with the real emotion label in the test set to judge the accuracy of the model recognition. If the verification finds that the recognition result of a certain emotion type deviates greatly from the real label, such as frequently identifying "fear" type crying as "irritation", it needs to adjust the network parameters, such as optimizing the feature adaptation logic of the fully connected layer or adjusting the feature extraction granularity of the convolution layer. Through the cycle of training-verification-adjustment, repeatedly optimize the network parameters until the recognition result of the model on the test set tends to be stable and no longer fluctuates greatly. At this time, it is considered that the branch training of this age group is completed. After all age branches complete the training, the whole multi-branch emotion recognition model can be put into subsequent use.

[0037] After the model training is completed, a fixed correspondence between different emotion types and the emergency degree of pediatric emergency conditions needs to be established to provide a basis for pre-examination triage. First, collect the actual handling priority data of children corresponding to each emotion type. These data come from the clinical diagnosis and treatment records of pediatric emergency, including the final diagnosis of children corresponding to different emotion types, the arrangement of treatment order, the allocation of medical resources, and other information. For example, collect the emergency handling records of all children identified by the model as "pain" emotion, and collect the handling records of other emotion types such as "hunger", "irritation", "fear", etc. to ensure that the data covers all preset emotion types.

[0038] Subsequently, statistical analysis methods are used to organize and analyze the collected data. For each emotion type, summarize the actual handling priority of all children corresponding to it, and analyze the distribution rules of the emergency degree of children under this emotion type. For example, statistics show that among the children corresponding to the "pain" emotion, most have high fever convulsions, severe abdominal pain, trauma, and other urgent conditions that need to be treated immediately, and their handling priority is generally high. Children corresponding to the "hunger" emotion mostly have unmet physiological needs and no urgent conditions, and their handling priority is low. Children corresponding to the "fear" emotion have mild trauma or sudden discomfort, and their handling priority is between the two. Through this statistical analysis, the correspondence between each emotion type and the emergency degree of the condition is clear, and a fixed correspondence is finally established.

[0039] In a preferred embodiment of the present application, in step S6, the process of combining the basic health information of the newly admitted child with the emergency level obtained from the emotion recognition model to generate a targeted pre-examination triage plan is as follows: After the newly admitted child completes the crying audio collection and emotion recognition, the process of retrieving and matching the basic health information is first started. The newly admitted child will obtain a unique identifier when registering for emergency treatment, which can be a treatment registration number, an electronic treatment card number, etc. This identifier runs through the entire emergency treatment process, ensuring the uniqueness and traceability of the child's information. Taking this unique identifier as the core retrieval basis, the system will automatically associate to the pre-constructed child crying and health information dataset and initiate a precise retrieval request. During the retrieval process, the system will traverse all associated records in the dataset according to the unique identifier to locate the health information item corresponding to the child. To avoid matching errors caused by identifier input errors or data duplication, the system will automatically check the key information after retrieval, such as the child's age, gender, and other basic information recorded in the dataset, and the information entered by the newly admitted child during registration. Only when the two pieces of information are completely consistent, the corresponding basic health information is completely retrieved to the current triage process; if the information is inconsistent, the system will prompt the medical staff to manually check and confirm to ensure that the information used for subsequent triage is accurate.

[0040] After completing the retrieval of basic health information, the key items need to be extracted and combined with the emergency level output by the emotion recognition model to construct a fusion feature vector. The specific process is as follows: First, the key items are extracted. From the retrieved basic health information, three items that have a core impact on triage decision are selected, which are medical history, current body temperature, and allergy history. When extracting medical history, the information related to emergency conditions is focused on, such as whether there are repeated respiratory infections, gastrointestinal discomfort, and other past emergency records, to ensure that the extracted information reflects the child's basic health status and potential risks. The current body temperature information is directly taken from the real-time measurement results after the child is admitted to the hospital, without the need for additional processing, only to ensure the authenticity and effectiveness of the data. The extraction of allergy history focuses on clear drug allergies, food allergies, or contact allergies. If the child has no relevant allergy records, it should also be extracted as clear information.

[0041] Next, the extracted key items are standardized numerical encoding. The core principle of encoding is to convert non-numerical information into a unified format of numerical value, which is convenient for subsequent weight allocation and feature integration. For the past medical history, according to its influence on the emergency condition, it is encoded, such as a serious chronic disease history is encoded as a numerical value, an ordinary past medical history is encoded as another numerical value, and no past medical history is encoded as a third numerical value. The current body temperature is encoded according to the clinical body temperature division standard, such as a normal body temperature range corresponds to a numerical value, mild fever corresponds to a numerical value, and moderate and above fever corresponds to a higher numerical value. The encoding logic of the allergy history is more simple, and the definite allergy record is encoded as a numerical value, and the non-allergy record is encoded as another numerical value. In this way, all key items are converted into standardized numerical values that can participate in subsequent calculations.

[0042] Then the encoded key items and the emergency degree output by the emotion recognition model are allocated with preset weights. The basis of weight allocation comes from the clinical diagnosis and treatment experience of pediatric emergency, which gives priority to indicators that have greater impact on the emergency degree. For example, the current body temperature as a real-time physiological indicator directly reflects the current physical condition of the child, and the weight allocation is relatively high; the emergency degree output by the emotion recognition model is the core judgment basis based on the crying sound emotion features, and also allocates a high weight; the past medical history as the basic health background, the weight is slightly lower than the first two; the allergy history mainly affects the safety of the subsequent treatment and nursing plan, and the weight is reasonably set according to the clinical importance. After the allocation is completed, all indicators are integrated according to the weight proportion, such as multiplying the encoding numerical value of each indicator with the corresponding weight, and then combining all the results in order to form a fusion feature vector containing multi-dimensional information, and finally inputting the vector into the feature fusion module.

[0043] After receiving the input fusion feature vector, the feature fusion module first performs a splicing operation. The splicing process is to combine the past medical history code, current body temperature code, allergy history code, and emergency level value contained in the fusion feature vector into a continuous comprehensive feature sequence in a predetermined order. The purpose of this step is to break the independence between indicators, so that the module can consider all relevant factors at the same time, and avoid decision bias caused by single indicator analysis. After splicing is completed, the module starts the logical judgment process, which is based on the clinical diagnosis and treatment specifications and triage experience of pediatric emergency department. For example, if the fusion feature vector shows that the current body temperature code corresponds to moderate and above fever, the emotional recognition emergency level value is high, and the past medical history code shows that the child has a history of epilepsy, the module will combine the medical knowledge that high fever can induce epilepsy to judge that the child has a high health risk; if the allergy history code shows that the child is allergic to certain common antipyretics, the module will take this factor into account and mark the risk points that need to be avoided in subsequent treatment. In the logical judgment process, the module will check the value combination of each indicator one by one, such as the combination of high emergency level and normal body temperature, no special past medical history, and the combination of high emergency level and high fever, chronic disease history, which will be judged as different health risk levels. Finally, the module outputs two core results, one is the health risk assessment, which clearly shows the possible disease risk and potential hazards of the child; the other is the emergency level judgment, which determines the priority of the child in emergency department, and the two together constitute the comprehensive evaluation result, which provides direct basis for the generation of subsequent triage plan.

[0044] After getting the comprehensive evaluation result, the system will automatically match the pediatric emergency preset triage rule library and gradually generate a targeted pre-examination triage plan. The triage rule library is based on the diagnosis and treatment process of pediatric emergency department, division of department functions and clinical nursing specifications, and contains standardized processing rules corresponding to different health risks and different emergency levels, covering the core content of visit order, examination room allocation, preliminary nursing suggestion, etc.

[0045] When determining the visit order, the system will match the corresponding priority standard in the rule library according to the emergency level in the comprehensive evaluation result. For example, children with the highest emergency level will be included in the "priority visit" sequence and will be arranged in the frontmost position of the available diagnosis and treatment resources; children with medium emergency level will be sorted according to the registration order and disease severity; children with lower emergency level will wait for examination in the regular order. At the same time, the rule library will consider the type of health risk of the child, such as children with shortness of breath risk, even if the emergency level is the same as other children, the priority of examination will be appropriately improved to ensure timely intervention.

[0046] In the clinic allocation link, the system matches the health risk direction in the comprehensive evaluation result with the diagnosis and treatment range of each clinic. For example, if the comprehensive evaluation result shows that the child patient may have a respiratory infection risk and is accompanied by high fever symptoms, the child patient is preferentially allocated to the pediatric emergency internal medicine clinic; if the evaluation result shows that the child patient may have a trauma or surgery-related condition, the child patient is matched to the surgery clinic; for a child patient with a high health risk that requires multidisciplinary collaborative diagnosis and treatment, the child patient is directly allocated to the emergency critical observation room, and the medical staff of the related departments are simultaneously notified to prepare.

[0047] The generation of the preliminary nursing suggestion focuses on relieving the discomfort of the child patient at the moment and avoiding potential risks. The system extracts corresponding rules according to the key health information and the comprehensive evaluation result. For example, for a child patient with high fever, it is suggested to perform physical cooling and keep the environment ventilated; for a child patient with a history of allergy, it is clearly suggested to avoid contact with the relevant allergens during the nursing process; for a child patient with a history of heart disease, it is suggested to monitor the heart rate and respiratory status and avoid crying to increase the heart burden.

[0048] The determined order of treatment, the corresponding clinic and the preliminary nursing suggestion are integrated and summarized to form a complete and targeted pre-examination triage plan. After the plan is generated, it is simultaneously displayed on the work terminal of the medical staff and pushed to the pediatric emergency triage management system to ensure that the triage information is shared in real time in the entire diagnosis and treatment process, provide clear work guidance for the medical staff, and let the parents understand the treatment arrangement and matters needing attention of the child patient.

[0049] The above describes one embodiment of the present application in detail, but the content described is only the preferred embodiment of the present application and cannot be considered to limit the implementation range of the present application. Any equivalent changes and improvements made according to the scope of the present application should still belong to the patent coverage range of the present application.

Claims

1. A pediatric emergency pre-examination triage method based on crying emotional recognition, characterized in that, The method comprises the following steps: S1, collecting pediatric emergency waiting triage children's crying audio data and basic health information, corresponding association of the two types of information, and constructing children's crying and health information dataset; S2, noise removal processing of the crying audio in the dataset, extracting the frequency, intensity and rhythm characteristics of the audio, and forming standardized audio feature data; S3, dividing the feature categories according to the age of the children, associating the standardized audio features of the same age group with the corresponding emotional labels, and establishing an age-based emotional feature library; S4, training an emotional recognition model based on the age-based emotional feature library, and determining the corresponding relationship between different emotional types and the emergency degree of pediatric emergency; S5, real-time collection of new children's crying audio, inputting the trained emotional recognition model, and outputting the emotional type and emergency degree corresponding to the children's crying; S6, calling the basic health information of the new children, combining it with the emergency degree obtained by the emotional recognition model, generating a targeted pre-examination and triage scheme, and synchronizing the pre-examination and triage scheme to the pediatric emergency triage management system.

2. The pediatric emergency pre-check triage method based on cry emotion recognition according to claim 1, characterized in that, In the step S2, the process of extracting the frequency, intensity and rhythm characteristics of the audio and forming standardized audio feature data is as follows: The noise-removed crying audio is divided into continuous audio segments according to a fixed time length, ensuring that each segment contains a complete crying rhythm, and defining a unified analysis unit for feature extraction; Perform feature extraction on each audio segment, obtain frequency characteristics through segmented spectrum analysis, calculate the ratio of sound wave peak value to average amplitude in the segment to obtain intensity characteristics, and record the time interval sequence of adjacent peaks as rhythm characteristics; Integrate the extracted frequency, intensity and rhythm characteristics into a feature vector in a predetermined order, adjust the value range of each index in the feature vector through a unified numerical conversion rule, and form standardized audio feature data.

3. The pediatric emergency pre-check triage method based on cry emotion recognition according to claim 1, characterized in that, In the step S3, the process of dividing the feature categories according to the age of the children, associating the standardized audio features of the same age group with the corresponding emotional labels, and establishing an age-based emotional feature library is as follows: Pretreat the standardized audio features, use an unsupervised clustering algorithm, preliminarily group them according to the similarity between feature vectors, and form several basic feature clusters; For each basic feature cluster, analyze the age distribution of the children in it, determine the main age range corresponding to each cluster, and take this range as the age identification information of the cluster; Associate the basic feature clusters with age identification information with the corresponding emotional labels, classify and integrate the associated feature clusters according to the age identification, and construct an age-based emotional feature library.

4. The pediatric emergency pre-check triage method based on cry emotion recognition according to claim 3, characterized in that, The specific way of pretreating the standardized audio features, using an unsupervised clustering algorithm, and preliminarily grouping them according to the similarity between feature vectors to form several basic feature clusters is as follows: For each feature vector in the standardized audio features, calculate the Euclidean distance between it and all other feature vectors in the dataset to generate a distance matrix as the basic data for feature enhancement; According to the distance matrix, weight and adjust the elements of each feature vector, the smaller the distance, the greater the weight of the feature vector, highlighting the common information of similar features, and obtaining the enhanced feature vector; The density-based clustering algorithm is adopted to take the enhanced feature vector as input, set the density threshold and neighborhood radius parameters, and classify the density-connected feature vectors in the feature space into a class to form the basic feature cluster.

5. The pediatric emergency pre-check triage method based on cry emotion recognition according to claim 1, characterized in that, In the step S4, the process of training the emotion recognition model based on the age-based emotion feature library and determining the corresponding relationship between different emotion types and the emergency degree of pediatric emergency conditions is as follows: The age-based emotion feature library is split into independent training set and test set according to age, ensuring that the distribution of emotion labels in each set is consistent with the original library; A multi-branch neural network is constructed, the basic layer shares the extraction of general audio features, each age corresponds to an independent branch layer, and the emotion type of the age is output; The corresponding branch is trained with the training set of each age, the model recognition accuracy is verified through the test set, and the network parameters are adjusted until the model performance is stable; The actual priority data of the emergency treatment of children corresponding to each emotion type is collected, and a fixed corresponding relationship between emotion type and emergency degree is established by statistical analysis method.

6. The pediatric emergency pre-check triage method based on cry emotion recognition according to claim 5, characterized in that, The specific way of constructing the multi-branch neural network, the basic layer sharing the extraction of general audio features, each age corresponding to an independent branch layer, and outputting the emotion type of the age is as follows: Take the standardized audio features as input, construct a convolution layer as the basic layer, and extract general audio features through convolution operation; An independent branch is constructed for each age, and the general features output by the basic layer are input into the fully connected layer of the branch together with the numerical coding of the age, and the feature adaptation is performed; A multi-class output layer is set at the end of each branch, and a multi-class activation function is used to output the probability of each emotion type under the age, realizing the output of emotion type.

7. The pediatric emergency pre-check triage method based on cry emotion recognition according to claim 1, characterized in that, In the step S6, the process of retrieving the basic health information of the newly admitted children and combining it with the emergency degree obtained by the emotion recognition model to generate a targeted pre-examination triage plan is as follows: Take the unique identifier of the newly admitted children as the retrieval basis to retrieve the corresponding basic health information from the children's crying sound and health information dataset, and complete the accurate matching of information; Extract the key items in the basic health information and input them into the feature fusion module together with the emergency degree output by the emotion recognition model for correlation analysis to obtain a comprehensive evaluation result; According to the comprehensive evaluation result, match the preset triage rule library of pediatric emergency to determine the treatment order, corresponding examination room and preliminary nursing suggestion, and form a targeted pre-examination triage plan.

8. The pediatric emergency pre-check triage method based on cry emotion recognition according to claim 7, characterized in that, The specific way of extracting the key items in the basic health information and inputting them into the feature fusion module together with the emergency degree output by the emotion recognition model for correlation analysis to obtain a comprehensive evaluation result is as follows: Extract the medical history, current temperature and allergy history in the basic health information as key items, and convert each key item into standardized numerical coding; Assign a preset weight to the coded key items and the emergency degree output by the emotion recognition model, and integrate them into a fusion feature vector input module according to the weight proportion; The feature fusion module splices and logically judges the fusion feature vector to output a comprehensive evaluation result containing health risk and emergency level.

Images