Swallowing behavior monitoring data processing method and system
Through the combination of monitoring sensors and processors, automatic monitoring and abnormal identification of swallowing behavior is achieved, solving the problem of time-consuming, labor-intensive and limited accuracy of manual observation in the prior art, and improving the accuracy of swallowing behavior detection and system reliability sex.
Patent Information
- Application Number
- CN202411016474.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-28
- Publication Date
- 2024-11-08
AI Technical Summary
The existing swallowing behavior monitoring methods rely on manual observation, are time-consuming and labor-intensive, and are limited in accuracy. They lack efficient real-time data processing and feedback mechanisms, and cannot identify and prompt abnormal eating behaviors in a timely manner.
A swallowing behavior monitoring data processing method and system is designed to obtain physiological characteristic signals through monitoring sensors. The processor analyzes signal characteristics based on preset models, recognizes swallowing behavior and triggers prompts when abnormalities are found, so as to realize automated monitoring and timely identification.
It improves the accuracy and sensitivity of swallowing behavior detection, reduces false alarms and missed reports, ensures the reliability of the monitoring system, and promptly detects potential health problems through automated identification and prompts, and improves the quality of life of patients.
Smart Images

Figure CN118902393A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to data processing technology, and in particular to a swallowing behavior monitoring data processing method and system. Background Art
[0002] Swallowing behavior monitoring has important applications in the field of medical health, especially in swallowing disorders, choking risk assessment, and dietary habit monitoring for the elderly and patients with chronic diseases.
[0003] Traditional swallowing behavior monitoring methods rely on manual observation and recording, which is not only time-consuming and laborious, but also limited in accuracy by the subjective judgment of the observer. In recent years, with the development of sensor technology, signal processing technology and data analysis technology, automated swallowing behavior monitoring systems have begun to appear, which can provide continuous and objective monitoring data. However, the current system is not capable of early warning of abnormal eating behaviors such as swallowing disorders and choking risks, lacks efficient real-time data processing and feedback mechanisms, and cannot instantly analyze monitoring data and give prompts for abnormal eating behaviors. Summary of the invention
[0004] The present application provides a swallowing behavior monitoring data processing method and system for realizing automatic monitoring of swallowing behavior, timely identifying abnormal eating behavior, and being able to provide prompts for abnormal eating behavior in real time.
[0005] In a first aspect, the present application provides a swallowing behavior monitoring data processing method, which is applied to a swallowing behavior monitoring system, wherein the swallowing behavior monitoring system includes a monitoring sensor set, a processor, and a prompt device, wherein each monitoring sensor in the monitoring sensor set is communicatively connected to the processor, and the prompt device is communicatively connected to the processor; the method includes:
[0006] Acquire physiological characteristic signals through monitoring sensors in the monitoring sensor set, and transmit the physiological characteristic signals to the processor;
[0007] The processor determines swallowing behavior information within a preset time period according to a preset swallowing behavior monitoring model and the physiological characteristic signal, wherein the swallowing behavior information includes a swallowing behavior sequence and a time node corresponding to each swallowing behavior in the swallowing behavior sequence;
[0008] If the processor determines that the eating behavior is abnormal according to the preset eating behavior monitoring model and the swallowing behavior information, the processor controls the prompting device to provide an abnormal eating behavior prompt.
[0009] In the above scheme, physiological characteristic signals are obtained by monitoring sensors, and the processor determines the swallowing behavior information based on the swallowing behavior monitoring model, and triggers a prompt when abnormal eating behavior is found, so as to realize automatic monitoring of swallowing behavior and timely identify abnormal eating behavior. It is suitable for medical monitoring, eating habit analysis and other fields, helping to prevent choking, swallowing disorders and other problems, and improving the quality of life of patients.
[0010] Optionally, the processor determines swallowing behavior information within a preset period of time according to a preset swallowing behavior monitoring model and the physiological characteristic signal, including:
[0011] The processor determines a peak value of the physiological characteristic signal and a valley value of the physiological characteristic signal according to the physiological characteristic signal monitored within a preset monitoring period, wherein the preset period includes a plurality of the preset monitoring periods;
[0012] The processor determines the swallowing behavior characteristic value of the preset monitoring period according to the physiological characteristic signal, the peak value of the physiological characteristic signal and the valley value of the physiological characteristic signal;
[0013] The processor calculates the swallowing behavior characteristic value of each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior characteristic value is greater than a preset characteristic value, the processor determines that there is swallowing behavior in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0014] In the above scheme, the processor calculates the swallowing behavior characteristic value based on the peak and valley values of the physiological characteristic signal during the monitoring period to determine the presence of swallowing behavior. Then, by analyzing the peak and valley values of the signal, the accuracy and sensitivity of swallowing behavior detection are improved, false positives and false negatives are reduced, and the reliability of the monitoring system is ensured.
[0015] Optionally, the processor determines swallowing behavior information within a preset period of time according to a preset swallowing behavior monitoring model and the physiological characteristic signal, including:
[0016] The processor uses Formula 1 and determines the swallowing behavior characteristic value according to the physiological characteristic signal monitored within a preset monitoring period. , the preset time period includes a plurality of the preset monitoring cycles, and the formula 1 is:
[0017]
[0018] in, is the starting time node of the preset monitoring period, is the end time node of the preset monitoring period, For The physiological characteristic signal at the moment, is the peak value of the physiological characteristic signal within the preset monitoring period, is the valley value of the physiological characteristic signal within the preset monitoring period, is the preset signal strength weight value, is the preset signal fluctuation weight value, is the standard deviation of the physiological characteristic signal within the preset monitoring period;
[0019] The processor calculates the swallowing behavior characteristic value of each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior characteristic value If the swallowing behavior is greater than a preset swallowing behavior characteristic value, the processor determines that swallowing behavior exists in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0020] In the above scheme, the swallowing behavior characteristic value is calculated using Formula 1, which comprehensively considers signal strength, fluctuation and standard deviation. Then, by quantitatively analyzing the physiological characteristic signals, the identification of swallowing behavior is made more objective and standardized, and the consistency and stability of the monitoring results are enhanced.
[0021] Optionally, the processor determines a peak value of the physiological characteristic signal and a valley value of the physiological characteristic signal according to the physiological characteristic signal monitored within a preset monitoring period, including:
[0022] The processor determines the peak values and valley values of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal according to the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal monitored within a preset monitoring period, wherein the physiological characteristic signal includes the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal;
[0023] Correspondingly, the processor determines the swallowing behavior characteristic value of the preset monitoring period according to the physiological characteristic signal, the peak value of the physiological characteristic signal, and the valley value of the physiological characteristic signal, including:
[0024] The processor determines a first swallowing behavior characteristic value, a second swallowing behavior characteristic value, and a third swallowing behavior characteristic value according to peak values and valley values of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal;
[0025] Correspondingly, the processor calculates the swallowing behavior characteristic value of each preset monitoring period within the preset time period. Determining the swallowing behavior information includes:
[0026] The processor determines a swallowing behavior feature probability according to the first swallowing behavior feature value, the second swallowing behavior feature value, and the third swallowing behavior feature value;
[0027] The processor determines the swallowing behavior information based on the swallowing behavior feature probability of each preset monitoring period within the preset time period, wherein if the swallowing behavior feature probability is greater than the preset swallowing behavior feature probability value, the processor determines that there is swallowing behavior in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0028] In the above scheme, the processor determines the swallowing behavior characteristic probability based on the peak and valley values of three different types of physiological characteristic signals (electromyographic characteristic signals, glottal vibration signals, and acceleration signals). The use of multimodal signal fusion improves the comprehensiveness and robustness of swallowing behavior monitoring, can more accurately capture swallowing events, and maintain high detection performance even in complex environments.
[0029] Optionally, the swallowing behavior information includes:
[0030] The processor uses Formula 2 and determines the swallowing behavior characteristic probability according to the physiological characteristic signal monitored within a preset monitoring period. , the formula 2 is:
[0031]
[0032] in, is the starting time node of the preset monitoring period, is the end time node of the preset monitoring period, , , are respectively the first swallowing behavior characteristic value, the second swallowing behavior characteristic value and the third swallowing behavior characteristic value of the preset monitoring period, , , Respectively in a first physiological characteristic signal, a second physiological characteristic signal, and a third physiological characteristic signal at a given moment, wherein the physiological characteristic signal includes the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal, , , are respectively the peak values of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal within the preset monitoring period, , , are valley values of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal, respectively, , , are respectively a first preset signal strength weight value, a second preset signal strength weight value, and a third preset signal strength weight value, , , are respectively a first preset signal fluctuation weight value, a second preset signal fluctuation weight value, and a third preset signal fluctuation weight value, , , are respectively the standard deviations of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal within the preset monitoring period;
[0033] The processor calculates the swallowing behavior characteristic probability of each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior feature probability If the swallowing behavior probability value is greater than a preset swallowing behavior characteristic probability value, the processor determines that swallowing behavior exists in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0034] In the above scheme, the swallowing behavior characteristic probability is calculated using Formula 2, which takes into account the characteristic values, intensity weights, and fluctuation weights of the three signals. By calculating weighted multi-characteristic values, swallowing behavior recognition is made more intelligent and refined, which can adapt to the physiological differences of different individuals and improve the adaptability and accuracy of the monitoring system.
[0035] Optionally, the first physiological characteristic signal is a pharyngeal electromyographic characteristic signal obtained by an electromyographic sensor, the second physiological characteristic signal is a glottal vibration signal obtained by a glottal sensor, and the third physiological characteristic signal is an acceleration signal obtained by an acceleration sensor.
[0036] In the above scheme, the first physiological characteristic signal is the pharyngeal electromyographic characteristic signal, the second physiological characteristic signal is the glottis vibration signal, and the third physiological characteristic signal is the acceleration signal. By directly monitoring the pharyngeal muscle activity, glottis vibration and head movement, multi-angle monitoring of the swallowing process is achieved, which can more comprehensively capture the biomechanical characteristics of swallowing behavior.
[0037] Optionally, the processor determines that the eating behavior is abnormal according to a preset eating behavior monitoring model and the swallowing behavior information, including:
[0038] The processor determines the average time interval of swallowing behavior, the standard deviation of swallowing behavior time, and the time difference between the first and last swallowing behaviors according to the swallowing behavior information within the preset time period;
[0039] The processor determines an abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference;
[0040] If the processor determines that the abnormal eating behavior index is greater than a preset abnormal eating behavior index threshold, it is determined that the eating behavior is abnormal.
[0041] In the above scheme, the processor determines the average time interval, time standard deviation and time difference between the first and last swallowing behaviors based on the swallowing behavior information, and calculates the abnormal eating behavior index. By statistically analyzing the time characteristics of swallowing behavior, abnormal eating patterns, such as overeating and dysphagia, can be effectively identified, which is helpful for early warning and intervention.
[0042] Optionally, the processor determines the abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference, including:
[0043] The processor determines a first characteristic difference value according to an absolute value of a difference between the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior;
[0044] The processor determines a second characteristic difference value according to an absolute value of a difference between the swallowing behavior time standard deviation and the reference swallowing behavior time standard deviation;
[0045] The processor determines a third characteristic difference value according to an absolute value of a difference between the first and last swallowing behavior time differences and the reference swallowing behavior time difference;
[0046] The processor determines the abnormal eating behavior index according to the sum of the first feature difference value, the second feature difference value and the third feature difference value.
[0047] In the above scheme, the processor calculates the abnormal index of eating behavior based on the difference in time characteristics between swallowing behavior and reference swallowing behavior. Through comparative analysis, the deviation degree of eating behavior is quantified, which improves the objectivity and scientificity of abnormal detection, and is conducive to precision medicine and personalized health management.
[0048] Optionally, the processor determines the abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference, including:
[0049] The processor uses Formula 3 and the swallowing behavior average time interval Average time interval with the reference swallowing behavior , the standard deviation of the swallowing behavior time Standard deviation of swallowing behavior time from the reference , and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference Determine the abnormal eating behavior index , the formula 3 is:
[0050]
[0051] in, , , They are respectively the first weight value, the second weight value and the third weight value.
[0052] In the above scheme, the abnormal eating behavior index is calculated using Formula 3, which takes into account the weights of the time interval, time standard deviation, and time difference. Through weight distribution, differentiated consideration of different time features is achieved, making abnormal detection more intelligent and able to adapt to the swallowing behavior monitoring needs in different scenarios.
[0053] Optionally, the swallowing behavior monitoring system further includes a cloud server and a monitoring terminal, and the processor and the monitoring terminal respectively preset a communication connection with the cloud server; after the processor determines the swallowing behavior information within a preset time period according to a preset swallowing behavior monitoring model and the physiological characteristic signal, it further includes:
[0054] The processor sends the swallowing behavior information to the cloud server, so that the cloud server generates a swallowing behavior monitoring curve according to the swallowing behavior information, and displays the swallowing behavior monitoring curve through the monitoring terminal.
[0055] In the above solution, swallowing behavior information is sent to the cloud server, and swallowing behavior monitoring curves are generated and displayed on the monitoring terminal. Remote storage and analysis of data are realized, which facilitates users and medical personnel to view swallowing behavior trends in real time, promotes remote medical monitoring and data analysis, and supports long-term health management and disease monitoring.
[0056] In a second aspect, the present application provides a swallowing behavior monitoring system, comprising: a monitoring sensor set, a processor, and a prompt device, wherein each monitoring sensor in the monitoring sensor set is communicatively connected to the processor, and the prompt device is communicatively connected to the processor;
[0057] Acquire physiological characteristic signals through monitoring sensors in the monitoring sensor set, and transmit the physiological characteristic signals to the processor;
[0058] The processor determines swallowing behavior information within a preset time period according to a preset swallowing behavior monitoring model and the physiological characteristic signal, wherein the swallowing behavior information includes a swallowing behavior sequence and a time node corresponding to each swallowing behavior in the swallowing behavior sequence;
[0059] If the processor determines that the eating behavior is abnormal according to the preset eating behavior monitoring model and the swallowing behavior information, the processor controls the prompting device to provide an abnormal eating behavior prompt.
[0060] Optionally, the processor determines swallowing behavior information within a preset period of time according to a preset swallowing behavior monitoring model and the physiological characteristic signal, including:
[0061] The processor determines a peak value of the physiological characteristic signal and a valley value of the physiological characteristic signal according to the physiological characteristic signal monitored within a preset monitoring period, wherein the preset period includes a plurality of the preset monitoring periods;
[0062] The processor determines the swallowing behavior characteristic value of the preset monitoring period according to the physiological characteristic signal, the peak value of the physiological characteristic signal and the valley value of the physiological characteristic signal;
[0063] The processor calculates the swallowing behavior characteristic value of each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior characteristic value is greater than a preset characteristic value, the processor determines that there is swallowing behavior in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0064] Optionally, the processor determines swallowing behavior information within a preset period of time according to a preset swallowing behavior monitoring model and the physiological characteristic signal, including:
[0065] The processor uses Formula 1 and determines the swallowing behavior characteristic value according to the physiological characteristic signal monitored within a preset monitoring period. , the preset time period includes a plurality of the preset monitoring cycles, and the formula 1 is:
[0066]
[0067] in, is the starting time node of the preset monitoring period, is the end time node of the preset monitoring period, For The physiological characteristic signal at the moment, is the peak value of the physiological characteristic signal within the preset monitoring period, is the valley value of the physiological characteristic signal within the preset monitoring period, is the preset signal strength weight value, is the preset signal fluctuation weight value, is the standard deviation of the physiological characteristic signal within the preset monitoring period;
[0068] The processor calculates the swallowing behavior characteristic value of each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior characteristic value If the swallowing behavior is greater than a preset swallowing behavior characteristic value, the processor determines that swallowing behavior exists in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0069] Optionally, the processor determines a peak value of the physiological characteristic signal and a valley value of the physiological characteristic signal according to the physiological characteristic signal monitored within a preset monitoring period, including:
[0070] The processor determines the peak values and valley values of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal according to the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal monitored within a preset monitoring period, wherein the physiological characteristic signal includes the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal;
[0071] Correspondingly, the processor determines the swallowing behavior characteristic value of the preset monitoring period according to the physiological characteristic signal, the peak value of the physiological characteristic signal, and the valley value of the physiological characteristic signal, including:
[0072] The processor determines a first swallowing behavior characteristic value, a second swallowing behavior characteristic value, and a third swallowing behavior characteristic value according to peak values and valley values of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal;
[0073] Correspondingly, the processor calculates the swallowing behavior characteristic value of each preset monitoring period within the preset time period. Determining the swallowing behavior information includes:
[0074] The processor determines a swallowing behavior feature probability according to the first swallowing behavior feature value, the second swallowing behavior feature value, and the third swallowing behavior feature value;
[0075] The processor determines the swallowing behavior information based on the swallowing behavior feature probability of each preset monitoring period within the preset time period, wherein if the swallowing behavior feature probability is greater than the preset swallowing behavior feature probability value, the processor determines that there is swallowing behavior in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0076] Optionally, the swallowing behavior information includes:
[0077] The processor uses Formula 2 and determines the swallowing behavior characteristic probability according to the physiological characteristic signal monitored within a preset monitoring period. , the formula 2 is:
[0078]
[0079] in, is the starting time node of the preset monitoring period, is the end time node of the preset monitoring period, , , are respectively the first swallowing behavior characteristic value, the second swallowing behavior characteristic value and the third swallowing behavior characteristic value of the preset monitoring period, , , Respectively in a first physiological characteristic signal, a second physiological characteristic signal, and a third physiological characteristic signal at a given moment, wherein the physiological characteristic signal includes the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal, , , are respectively the peak values of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal within the preset monitoring period, , , are valley values of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal, respectively, , , are respectively a first preset signal strength weight value, a second preset signal strength weight value, and a third preset signal strength weight value, , , are respectively a first preset signal fluctuation weight value, a second preset signal fluctuation weight value, and a third preset signal fluctuation weight value, , , are respectively the standard deviations of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal within the preset monitoring period;
[0080] The processor calculates the swallowing behavior characteristic probability of each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior feature probability If the swallowing behavior probability value is greater than a preset swallowing behavior characteristic probability value, the processor determines that swallowing behavior exists in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0081] Optionally, the first physiological characteristic signal is a pharyngeal electromyographic characteristic signal obtained by an electromyographic sensor, the second physiological characteristic signal is a glottal vibration signal obtained by a glottal sensor, and the third physiological characteristic signal is an acceleration signal obtained by an acceleration sensor.
[0082] Optionally, the processor determines that the eating behavior is abnormal according to a preset eating behavior monitoring model and the swallowing behavior information, including:
[0083] The processor determines the average time interval of swallowing behavior, the standard deviation of swallowing behavior time, and the time difference between the first and last swallowing behaviors according to the swallowing behavior information within the preset time period;
[0084] The processor determines an abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference;
[0085] If the processor determines that the abnormal eating behavior index is greater than a preset abnormal eating behavior index threshold, it is determined that the eating behavior is abnormal.
[0086] Optionally, the processor determines the abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference, including:
[0087] The processor determines a first characteristic difference value according to an absolute value of a difference between the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior;
[0088] The processor determines a second characteristic difference value according to an absolute value of a difference between the swallowing behavior time standard deviation and the reference swallowing behavior time standard deviation;
[0089] The processor determines a third characteristic difference value according to an absolute value of a difference between the first and last swallowing behavior time differences and the reference swallowing behavior time difference;
[0090] The processor determines the abnormal eating behavior index according to the sum of the first feature difference value, the second feature difference value and the third feature difference value.
[0091] Optionally, the processor determines the abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference, including:
[0092] The processor uses Formula 3 and calculates the swallowing behavior average time interval according to the swallowing behavior average time interval. Average time interval with the reference swallowing behavior , the standard deviation of the swallowing behavior time Standard deviation of swallowing behavior time from the reference , and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference Determine the abnormal eating behavior index , the formula 3 is:
[0093]
[0094] in, , , They are respectively the first weight value, the second weight value and the third weight value.
[0095] Optionally, the swallowing behavior monitoring system further includes a cloud server and a monitoring terminal, and the processor and the monitoring terminal respectively preset a communication connection with the cloud server; after the processor determines the swallowing behavior information within a preset time period according to a preset swallowing behavior monitoring model and the physiological characteristic signal, it further includes:
[0096] The processor sends the swallowing behavior information to the cloud server, so that the cloud server generates a swallowing behavior monitoring curve according to the swallowing behavior information, and displays the swallowing behavior monitoring curve through the monitoring terminal.
[0097] In a third aspect, the present application provides an electronic device, including:
[0098] processor; and,
[0099] A memory, configured to store executable instructions of the processor;
[0100] The processor is configured to perform any possible method described in the first aspect by executing the executable instructions.
[0101] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement any possible method described in the first aspect.
[0102] The swallowing behavior monitoring data processing method and system provided in the present application obtain physiological characteristic signals through monitoring sensors in a monitoring sensor set, and transmit the physiological characteristic signals to a processor. Then, the processor determines the swallowing behavior information within a preset time period according to a preset swallowing behavior monitoring model and the physiological characteristic signals. When the processor determines that the eating behavior is abnormal according to the preset eating behavior monitoring model and the swallowing behavior information, the processor controls the prompt device to provide an abnormal eating behavior prompt, thereby realizing automatic monitoring of swallowing behavior and timely identifying abnormal eating behavior. BRIEF DESCRIPTION OF THE DRAWINGS
[0103] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0104] Figure 1 is a flowchart of a swallowing behavior monitoring data processing method according to an exemplary embodiment of the present application;
[0105] Figure 2 is a flowchart of a swallowing behavior monitoring data processing method according to another exemplary embodiment of the present application;
[0106] Figure 3is a structural schematic diagram of a swallowing behavior monitoring system according to an exemplary embodiment of the present application;
[0107] Figure 4 It is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application.
[0108] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0109] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0110] In order to solve the above problems, the embodiments provided in this application aim to automatically identify and record swallowing behavior by monitoring and analyzing physiological characteristic signals, and at the same time evaluate whether the eating behavior is abnormal, so as to assist medical diagnosis, health monitoring and improvement of personal living habits. The method uses sensors to collect physiological characteristic signals, and analyzes the signal characteristics through a processor and combines them with a preset monitoring model. It can not only detect the occurrence of swallowing movements, but also determine whether the swallowing behavior conforms to the normal mode, so as to timely discover potential health problems. Specifically, it can be a monitoring sensor set including an electromyographic sensor, a glottal sensor and an acceleration sensor to continuously monitor the physiological characteristic signals related to the swallowing behavior. The processor receives the sensor data, analyzes the peak value, valley value and standard deviation of the signal according to the preset model, and determines the characteristic value of the swallowing behavior. Through the set algorithm and threshold, the processor can identify the time point when the swallowing behavior occurs and form a swallowing behavior sequence. The processor further analyzes the swallowing behavior sequence. If it is found that the average time interval, time standard deviation or time difference between the first and last swallowing behaviors of the swallowing behavior deviates from the normal range, it is determined as abnormal eating behavior. Once abnormal eating behavior is detected, the system will warn the user through a prompt device so that timely measures can be taken or medical advice can be sought.
[0111] By simultaneously monitoring electromyographic signals, glottal vibrations, and acceleration signals, the system can more comprehensively capture the dynamic characteristics of swallowing behavior and improve recognition accuracy. Using a specific mathematical model, the system can quantify the intensity and fluctuation characteristics of swallowing behavior, providing an objective basis for the identification of swallowing behavior. By comparing the temporal characteristics of swallowing behavior with reference values, the system can evaluate the normality of eating behavior and promptly detect potential swallowing disorders or other health problems. The system design takes into account interaction with cloud servers, allowing remote data storage, analysis, and monitoring curve display, making it easier for users and medical staff to monitor changes in swallowing behavior in real time.
[0112] The embodiments provided in this application can be used to assist in the diagnosis of swallowing disorders, choking risk assessment, etc. For example, it can be applied to personal health monitoring, especially the tracking of eating habits of the elderly and patients with chronic diseases. For another example, it can also be applied to the quantitative analysis of eating behavior in scientific research.
[0113] It can be seen that the concept of the technical solution of this application is to provide an efficient and accurate swallowing behavior monitoring method, which can realize real-time monitoring of swallowing behavior and early warning of abnormal eating behavior by analyzing multiple physiological signals, and has broad application prospects and practical value.
[0114] Figure 1 FIG. 1 is a flow chart of a swallowing behavior monitoring data processing method according to an exemplary embodiment of the present application. Figure 1 As shown, the method provided in this embodiment includes:
[0115] S101. Acquire physiological characteristic signals through monitoring sensors in a monitoring sensor set.
[0116] The method provided in the present application can be applied to a swallowing behavior monitoring system, which includes a monitoring sensor set, a processor, and a prompt device. Each monitoring sensor in the monitoring sensor set is communicatively connected to the processor, and the prompt device is communicatively connected to the processor.
[0117] In this step, the physiological characteristic signal is obtained by the monitoring sensor in the monitoring sensor set, and the physiological characteristic signal is transmitted to the processor. Specifically, the monitoring sensor set includes but is not limited to electromyographic sensors, glottal sensors and acceleration sensors. These sensors are designed to fit or be worn on corresponding parts of the human body, such as the neck, to capture physiological signals closely related to swallowing behavior. The sensor digitizes the collected raw signal and transmits it to the processor wirelessly or wiredly, and the processor is located in a computing unit inside or outside the portable monitoring device.
[0118] S102: The processor determines swallowing behavior information within a preset time period according to a preset swallowing behavior monitoring model and a physiological characteristic signal.
[0119] In this step, the processor determines the swallowing behavior information within a preset time period based on the preset swallowing behavior monitoring model and the physiological characteristic signal. The swallowing behavior information includes the swallowing behavior sequence and the time node corresponding to each swallowing behavior in the swallowing behavior sequence. Specifically, the processor runs the swallowing behavior monitoring software, which has a built-in swallowing behavior monitoring model. The model presets the signal characteristic thresholds and algorithms related to the swallowing behavior. The processor receives the physiological characteristic signal from the sensor and applies signal processing techniques such as filtering, noise reduction and feature extraction to determine key indicators such as peak values, valley values and standard deviations in the signal. Subsequently, based on these indicators and the preset model, the processor calculates the swallowing behavior characteristic value. When the characteristic value exceeds the set threshold, it identifies the occurrence of the swallowing behavior and records the time node of each swallowing behavior to form a swallowing behavior sequence.
[0120] In one possible implementation, the processor may determine the peak value of the physiological characteristic signal and the valley value of the physiological characteristic signal according to the physiological characteristic signal monitored in a preset monitoring period, and the preset period includes multiple preset monitoring periods. The processor determines the swallowing behavior characteristic value of the preset monitoring period according to the physiological characteristic signal, the peak value of the physiological characteristic signal, and the valley value of the physiological characteristic signal. The processor determines the swallowing behavior characteristic value of each preset monitoring period in the preset period according to the physiological characteristic signal, the peak value of the physiological characteristic signal, and the valley value of the physiological characteristic signal. Determine swallowing behavior information, wherein if the swallowing behavior characteristic value is greater than the preset characteristic value, the processor determines that there is swallowing behavior in the corresponding preset monitoring period, and the time node corresponding to each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0121] Specifically, the processor receives continuous physiological characteristic signal data from the sensor collection. These signal data are segmented according to preset monitoring cycles. For example, each cycle may range from a few seconds to a few minutes, depending on the monitoring accuracy requirements. The processor analyzes the signal within each cycle to find the maximum value (peak value) and minimum value (valley value) of the signal within the cycle. These values reflect the range of variation of the signal strength. The processor analyzes the swallowing behavior characteristic values of all monitoring cycles within the entire preset period. If the characteristic value of a monitoring cycle exceeds the preset threshold (preset characteristic value), it is determined that swallowing behavior has occurred within the cycle. The processor records the start time of this cycle, regards it as the time node of the swallowing behavior, and integrates this information into the swallowing behavior sequence to form a time series that records the occurrence time of each swallowing behavior within the monitoring period.
[0122] Furthermore, the processor may use Formula 1 to determine the swallowing behavior characteristic value according to the physiological characteristic signal monitored within a preset monitoring period. , the preset period includes multiple preset monitoring cycles, and formula 1 is:
[0123]
[0124] in, is the starting time node of the preset monitoring period, is the end time node of the preset monitoring cycle. For Physiological characteristic signals at all times, is the peak value of the physiological characteristic signal within the preset monitoring period. is the valley value of the physiological characteristic signal within the preset monitoring period. is the preset signal strength weight value, is the preset signal fluctuation weight value, It is the standard deviation of the physiological characteristic signal within the preset monitoring period.
[0125] The processor calculates the swallowing behavior characteristic values of each preset monitoring period within the preset time period. Determine swallowing behavior information, where if the swallowing behavior characteristic value If the swallowing behavior is greater than the preset swallowing behavior characteristic value, the processor determines that swallowing behavior exists in the corresponding preset monitoring period, and the time node corresponding to each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0126] Specifically, the processor compares the swallowing behavior characteristic value of each monitoring cycle with the preset swallowing behavior characteristic value threshold. If the characteristic value of a monitoring cycle is higher than this threshold, the processor considers that swallowing behavior has occurred in the monitoring cycle, and records the start time of the cycle as the time point of occurrence of a swallowing behavior. In this way, by traversing all monitoring cycles within the entire preset time period, the processor can construct a swallowing behavior sequence, and each element in the sequence represents a time node of a swallowing behavior.
[0127] Furthermore, the processor determines the peak value of the physiological characteristic signal and the valley value of the physiological characteristic signal based on the physiological characteristic signal monitored within a preset monitoring period. Specifically, the processor may determine the peak value and valley value of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal based on the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal monitored within the preset monitoring period, and the physiological characteristic signal includes the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal.
[0128] Specifically, the processor first receives three types of physiological characteristic signals from the monitoring sensor set: a first physiological characteristic signal (e.g., an electromyogram signal, reflecting the intensity of muscle activity), a second physiological characteristic signal (e.g., a glottal vibration signal, reflecting glottal activity), and a third physiological characteristic signal (e.g., an acceleration signal, reflecting the movement of the head or body). For each signal, the processor analyzes the data within a preset monitoring period and calculates the maximum value (peak value) and minimum value (valley value) within the period, which reflect the signal strength and variation range.
[0129] Correspondingly, the processor determines the swallowing behavior characteristic value of a preset monitoring period based on the physiological characteristic signal, the peak value of the physiological characteristic signal, and the valley value of the physiological characteristic signal. The processor may determine the first swallowing behavior characteristic value, the second swallowing behavior characteristic value, and the third swallowing behavior characteristic value based on the peak value and valley value of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal.
[0130] Specifically, the processor uses the peak and valley values of the first physiological characteristic signal to calculate the first swallowing behavior characteristic value, and similarly uses the peak and valley values of the second and third physiological characteristic signals to respectively calculate the second and third swallowing behavior characteristic values. These characteristic values reflect the performance of swallowing behavior in different physiological signals.
[0131] Correspondingly, the processor determines the swallowing behavior characteristic values of each preset monitoring period within the preset time period. Determining the swallowing behavior information may be that the processor determines the swallowing behavior characteristic probability according to the first swallowing behavior characteristic value, the second swallowing behavior characteristic value, and the third swallowing behavior characteristic value. The processor determines the swallowing behavior information according to the swallowing behavior characteristic probability of each preset monitoring period within the preset time period, wherein if the swallowing behavior characteristic probability is greater than the preset swallowing behavior characteristic probability value, the processor determines that there is a swallowing behavior in the corresponding preset monitoring period, and the time node corresponding to each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0132] Specifically, the processor combines the first, second, and third swallowing behavior feature values and uses statistical or machine learning methods to calculate a swallowing behavior feature probability. This probability value reflects the possibility of swallowing behavior occurring in the current monitoring cycle. The processor analyzes the swallowing behavior feature probabilities of all monitoring cycles within the entire preset period. If the feature probability of a monitoring cycle exceeds a preset threshold, then this cycle is marked as having swallowing behavior. The time node of the swallowing behavior is recorded as the start time of the monitoring cycle, thereby constructing a time series of the swallowing behavior.
[0133] S103: The processor determines that the eating behavior is abnormal according to a preset eating behavior monitoring model and swallowing behavior information.
[0134] If the processor determines that the eating behavior is abnormal based on the preset eating behavior monitoring model and swallowing behavior information, the processor controls the prompt device to prompt the abnormal eating behavior. Specifically, the processor further analyzes the swallowing behavior sequence and uses the eating behavior monitoring model to check the regularity and time distribution of the swallowing behavior. The model may be based on statistical analysis, such as the average time interval of the swallowing behavior, the time standard deviation, and the time difference between the first and last swallowing behaviors, and compared with the normal pattern. If an abnormality is found, such as a swallowing frequency that is too high, a time interval that is too short or irregular, the processor will trigger a preset prompt device, such as an alarm, vibration, or mobile phone application notification, to warn the user or guardian, indicating possible abnormal eating behavior.
[0135] In a possible implementation, the processor determines the average time interval of swallowing behavior, the standard deviation of swallowing behavior time, and the time difference between the first and last swallowing behaviors according to the swallowing behavior information in a preset time period. The processor determines the abnormal eating behavior index according to the average time interval of swallowing behavior and the average time interval of reference swallowing behavior, the standard deviation of swallowing behavior time and the standard deviation of reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference. If the processor determines that the abnormal eating behavior index is greater than a preset abnormal eating behavior index threshold, it is determined to be abnormal eating behavior.
[0136] Specifically, the processor first summarizes the time nodes of all swallowing behaviors within a preset period, and then calculates the average time interval between swallowing behaviors, that is, the average time difference between two swallowing behaviors; then, the standard deviation of the time interval between swallowing behaviors is calculated to measure the stability of the time interval between swallowing behaviors; finally, the time difference between the first and last swallowing behaviors, that is, the duration of the entire eating behavior, is determined. The processor compares the average time interval between swallowing behaviors, the time standard deviation, and the time difference between the first and last swallowing behaviors calculated above with a set of preset reference values. These reference values are obtained based on statistical data analysis of healthy people and represent normal swallowing behavior patterns. The processor calculates the difference between the actual value and the reference value and quantifies it into a characteristic difference, including the difference in the average time interval between swallowing behaviors, the difference in the time standard deviation, and the difference in the time difference between the first and last swallowing behaviors. The processor adds the three characteristic differences to determine the abnormal eating behavior index. If the index exceeds the preset abnormal threshold, it means that the actual swallowing behavior pattern is significantly different from the healthy reference pattern, which may indicate abnormal eating behavior, such as eating too fast, dysphagia, or irregular eating habits. At this point, the processor will mark the eating behavior as abnormal and may trigger an abnormal eating behavior prompt in the system.
[0137] In a possible implementation, the processor determines the abnormal eating behavior index according to the average time interval of swallowing behavior and the average time interval of reference swallowing behavior, the standard deviation of swallowing behavior time and the standard deviation of reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference, which may include:
[0138] The processor determines a first characteristic difference value according to the absolute value of the difference between the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior. The processor determines a second characteristic difference value according to the absolute value of the difference between the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time. The processor determines a third characteristic difference value according to the absolute value of the difference between the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference. The processor determines an abnormal eating behavior index according to the sum of the first characteristic difference value, the second characteristic difference value, and the third characteristic difference value.
[0139] In this embodiment, physiological characteristic signals are acquired by monitoring sensors in the monitoring sensor set, and the physiological characteristic signals are transmitted to the processor. Then, the processor determines the swallowing behavior information within a preset time period according to the preset swallowing behavior monitoring model and the physiological characteristic signals. When the processor determines that the eating behavior is abnormal according to the preset eating behavior monitoring model and the swallowing behavior information, the processor controls the prompt device to provide an abnormal eating behavior prompt, thereby realizing automatic monitoring of the swallowing behavior, timely identifying abnormal eating behavior, and being able to provide instant prompts for abnormal eating behavior.
[0140] Figure 2 FIG. 1 is a flow chart of a swallowing behavior monitoring data processing method according to another exemplary embodiment of the present application. Figure 2 As shown, the swallowing behavior monitoring data processing method provided in this embodiment includes:
[0141] S201. Acquire physiological characteristic signals through monitoring sensors in the monitoring sensor set.
[0142] In this step, the physiological characteristic signal is obtained by the monitoring sensor in the monitoring sensor set, and the physiological characteristic signal is transmitted to the processor. Specifically, the monitoring sensor set includes but is not limited to electromyographic sensors, glottal sensors and acceleration sensors. These sensors are designed to fit or be worn on corresponding parts of the human body, such as the neck, to capture physiological signals closely related to swallowing behavior. The sensor digitizes the collected raw signal and transmits it to the processor wirelessly or wiredly, and the processor is located in a computing unit inside or outside the portable monitoring device.
[0143] S202: The processor determines swallowing behavior information within a preset time period according to a preset swallowing behavior monitoring model and a physiological characteristic signal.
[0144] In this step, the processor determines the swallowing behavior information within a preset time period based on the preset swallowing behavior monitoring model and the physiological characteristic signal. The swallowing behavior information includes the swallowing behavior sequence and the time node corresponding to each swallowing behavior in the swallowing behavior sequence. Specifically, the processor runs the swallowing behavior monitoring software, which has a built-in swallowing behavior monitoring model. The model presets the signal characteristic thresholds and algorithms related to the swallowing behavior. The processor receives the physiological characteristic signal from the sensor and applies signal processing techniques such as filtering, noise reduction and feature extraction to determine key indicators such as peak values, valley values and standard deviations in the signal. Subsequently, based on these indicators and the preset model, the processor calculates the swallowing behavior characteristic value. When the characteristic value exceeds the set threshold, it identifies the occurrence of the swallowing behavior and records the time node of each swallowing behavior to form a swallowing behavior sequence.
[0145] Specifically, the processor uses Formula 2 and determines the swallowing behavior characteristic probability according to the physiological characteristic signal monitored within a preset monitoring period. , the above formula 2 is:
[0146]
[0147] in, is the starting time node of the preset monitoring period, is the end time node of the preset monitoring cycle. , , are respectively the first swallowing behavior characteristic value, the second swallowing behavior characteristic value and the third swallowing behavior characteristic value of the preset monitoring period, , , Respectively in The first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal at the moment, the physiological characteristic signal including the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal, , , are respectively the peak values of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal within the preset monitoring period, , , are the valley values of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal, respectively. , , are respectively a first preset signal strength weight value, a second preset signal strength weight value, and a third preset signal strength weight value, , , are respectively a first preset signal fluctuation weight value, a second preset signal fluctuation weight value, and a third preset signal fluctuation weight value, , , They are respectively the standard deviations of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal within the preset monitoring period.
[0148] Among them, the first physiological characteristic signal is a pharyngeal electromyographic characteristic signal obtained by an electromyographic sensor, the second physiological characteristic signal is a glottal vibration signal obtained by a glottal sensor, and the third physiological characteristic signal is an acceleration signal obtained by an acceleration sensor.
[0149] Then, the processor calculates the swallowing behavior characteristic probability of each preset monitoring period within the preset time period. Determine swallowing behavior information, where if the swallowing behavior feature probability If the swallowing behavior probability is greater than the preset swallowing behavior characteristic probability value, the processor determines that swallowing behavior exists in the corresponding preset monitoring period, and the time node corresponding to each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0150] Specifically, within a preset monitoring period, the processor collects a first physiological characteristic signal (such as a pharyngeal electromyography characteristic signal), a second physiological characteristic signal (such as a glottal vibration signal), and a third physiological characteristic signal (such as an acceleration signal). For each signal, the processor first calculates its characteristic value, that is, the swallowing behavior characteristic value, which may come from the peak value, valley value, average value or standard deviation of the signal. Then, the processor repeats the above steps for all monitoring periods within the entire preset time period, and calculates that the swallowing behavior characteristic probability of each period is greater than the preset swallowing behavior characteristic probability threshold. Then, the processor determines that swallowing behavior has occurred within the period. The identification time point of the swallowing behavior is marked as the start time of the monitoring period, thereby constructing a swallowing behavior sequence, and each element in the sequence represents a time node of a swallowing behavior.
[0151] S203: The processor determines that the eating behavior is abnormal according to a preset eating behavior monitoring model and swallowing behavior information.
[0152] If the processor determines that the eating behavior is abnormal based on the preset eating behavior monitoring model and swallowing behavior information, the processor controls the prompt device to prompt the abnormal eating behavior. Specifically, the processor further analyzes the swallowing behavior sequence and uses the eating behavior monitoring model to check the regularity and time distribution of the swallowing behavior. The model may be based on statistical analysis, such as the average time interval of the swallowing behavior, the time standard deviation, and the time difference between the first and last swallowing behaviors, and compared with the normal pattern. If an abnormality is found, such as a swallowing frequency that is too high, a time interval that is too short or irregular, the processor will trigger a preset prompt device, such as an alarm, vibration, or mobile phone application notification, to warn the user or guardian, indicating possible abnormal eating behavior.
[0153] In a possible implementation, the processor determines the average time interval of swallowing behavior, the standard deviation of swallowing behavior time, and the time difference between the first and last swallowing behaviors according to the swallowing behavior information in a preset time period. The processor determines the abnormal eating behavior index according to the average time interval of swallowing behavior and the average time interval of reference swallowing behavior, the standard deviation of swallowing behavior time and the standard deviation of reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference. If the processor determines that the abnormal eating behavior index is greater than a preset abnormal eating behavior index threshold, it is determined to be abnormal eating behavior.
[0154] Specifically, the processor may use Formula 3 and calculate the average time interval of the swallowing behavior according to Average time interval with reference swallowing behavior , swallowing behavior time standard deviation Standard deviation of swallowing behavior time from reference , and the time difference between the first and last swallowing behaviors And the reference swallowing behavior time difference Determine the abnormal eating behavior index , Formula 3 is:
[0155]
[0156] in, , , They are respectively the first weight value, the second weight value and the third weight value.
[0157] S204: The processor sends the swallowing behavior information to the cloud server.
[0158] Optionally, the swallowing behavior monitoring system in this embodiment may further include a cloud server and a monitoring terminal. The processor and the monitoring terminal respectively preset a communication connection with the cloud server. The processor sends the swallowing behavior information to the cloud server, so that the cloud server generates a swallowing behavior monitoring curve according to the swallowing behavior information, and displays the swallowing behavior monitoring curve through the monitoring terminal.
[0159] Specifically, after the processor completes the analysis of the swallowing behavior information, the swallowing behavior information will be uploaded to the cloud server. After receiving this information, the cloud server uses data analysis and visualization tools to convert the swallowing behavior information into an intuitive swallowing behavior monitoring curve. The monitoring curve can show the frequency, time distribution and other relevant statistical information of swallowing behavior, which helps users and medical professionals have a deeper understanding of swallowing behavior patterns. The monitoring curve generated by the cloud server is then sent to the user's monitoring terminal, such as a smartphone, tablet or dedicated health monitoring device, via a secure network connection. The application or software on the monitoring terminal is responsible for receiving and displaying these curves. Users can view their swallowing behavior monitoring results at any time. The monitoring terminal may also provide functions such as data synchronization, history query, and abnormal behavior warning to enhance the user experience and the effectiveness of monitoring.
[0160] Figure 3 FIG. 1 is a schematic diagram of a swallowing behavior monitoring system according to an exemplary embodiment of the present application. Figure 3 As shown, the swallowing behavior monitoring system 300 provided in this embodiment includes: a monitoring sensor set 310, a processor 320 and a prompt device 330, each monitoring sensor in the monitoring sensor set 310 is communicatively connected to the processor 320, and the prompt device 330 is communicatively connected to the processor 320;
[0161] Acquire physiological characteristic signals through the monitoring sensors in the monitoring sensor set 310, and transmit the physiological characteristic signals to the processor 320;
[0162] The processor 320 determines swallowing behavior information within a preset period of time according to a preset swallowing behavior monitoring model and the physiological characteristic signal, wherein the swallowing behavior information includes a swallowing behavior sequence and a time node corresponding to each swallowing behavior in the swallowing behavior sequence;
[0163] If the processor 320 determines that the eating behavior is abnormal according to the preset eating behavior monitoring model and the swallowing behavior information, the processor 320 controls the prompt device 330 to provide an abnormal eating behavior prompt.
[0164] Optionally, the processor 320 determines the swallowing behavior information within a preset period of time according to a preset swallowing behavior monitoring model and the physiological characteristic signal, including:
[0165] The processor 320 determines the peak value of the physiological characteristic signal and the valley value of the physiological characteristic signal according to the physiological characteristic signal monitored in a preset monitoring period, and the preset period includes a plurality of the preset monitoring periods;
[0166] The processor 320 determines the swallowing behavior characteristic value of the preset monitoring period according to the physiological characteristic signal, the peak value of the physiological characteristic signal and the valley value of the physiological characteristic signal;
[0167] The processor 320 generates a swallowing behavior characteristic value according to each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior characteristic value is greater than the preset characteristic value, the processor 320 determines that there is swallowing behavior in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0168] Optionally, the processor 320 determines the swallowing behavior information within a preset period of time according to a preset swallowing behavior monitoring model and the physiological characteristic signal, including:
[0169] The processor 320 uses Formula 1 and determines the swallowing behavior characteristic value according to the physiological characteristic signal monitored within a preset monitoring period. , the preset time period includes a plurality of the preset monitoring cycles, and the formula 1 is:
[0170]
[0171] in, is the starting time node of the preset monitoring period, is the end time node of the preset monitoring period, For The physiological characteristic signal at the moment, is the peak value of the physiological characteristic signal within the preset monitoring period, is the valley value of the physiological characteristic signal within the preset monitoring period, is the preset signal strength weight value, is the preset signal fluctuation weight value, is the standard deviation of the physiological characteristic signal within the preset monitoring period;
[0172] The processor 320 generates a swallowing behavior characteristic value according to each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior characteristic value If the swallowing behavior is greater than the preset swallowing behavior characteristic value, the processor 320 determines that there is swallowing behavior in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0173] Optionally, the processor 320 determines a peak value of the physiological characteristic signal and a valley value of the physiological characteristic signal according to the physiological characteristic signal monitored within a preset monitoring period, including:
[0174] The processor 320 determines the peak values and valley values of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal according to the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal monitored within a preset monitoring period, wherein the physiological characteristic signal includes the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal;
[0175] Correspondingly, the processor 320 determines the swallowing behavior characteristic value of the preset monitoring period according to the physiological characteristic signal, the peak value of the physiological characteristic signal, and the valley value of the physiological characteristic signal, including:
[0176] The processor 320 determines a first swallowing behavior characteristic value, a second swallowing behavior characteristic value, and a third swallowing behavior characteristic value according to the peak values and valley values of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal;
[0177] Correspondingly, the processor 320 processes the swallowing behavior characteristic values of each preset monitoring period within the preset time period. Determining the swallowing behavior information includes:
[0178] The processor 320 determines a swallowing behavior feature probability according to the first swallowing behavior feature value, the second swallowing behavior feature value, and the third swallowing behavior feature value;
[0179] The processor 320 determines the swallowing behavior information based on the swallowing behavior feature probability of each preset monitoring period within the preset time period, wherein if the swallowing behavior feature probability is greater than the preset swallowing behavior feature probability value, the processor 320 determines that there is swallowing behavior in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0180] Optionally, the swallowing behavior information includes:
[0181] The processor 320 uses Formula 2 and determines the swallowing behavior characteristic probability according to the physiological characteristic signal monitored within a preset monitoring period. , the formula 2 is:
[0182]
[0183] in, is the starting time node of the preset monitoring period, is the end time node of the preset monitoring period, , , are respectively the first swallowing behavior characteristic value, the second swallowing behavior characteristic value and the third swallowing behavior characteristic value of the preset monitoring period, , , Respectively in a first physiological characteristic signal, a second physiological characteristic signal, and a third physiological characteristic signal at a given moment, wherein the physiological characteristic signal includes the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal, , , are respectively the peak values of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal within the preset monitoring period, , , are valley values of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal, respectively, , , are respectively a first preset signal strength weight value, a second preset signal strength weight value, and a third preset signal strength weight value, , , are respectively a first preset signal fluctuation weight value, a second preset signal fluctuation weight value, and a third preset signal fluctuation weight value, , , are respectively the standard deviations of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal within the preset monitoring period;
[0184] The processor 320 determines the swallowing behavior characteristic probability of each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior feature probability If the swallowing behavior probability value is greater than a preset swallowing behavior characteristic probability value, the processor 320 determines that a swallowing behavior exists in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
[0185] Optionally, the first physiological characteristic signal is a pharyngeal electromyographic characteristic signal obtained by an electromyographic sensor, the second physiological characteristic signal is a glottal vibration signal obtained by a glottal sensor, and the third physiological characteristic signal is an acceleration signal obtained by an acceleration sensor.
[0186] Optionally, the processor 320 determines that the eating behavior is abnormal according to a preset eating behavior monitoring model and the swallowing behavior information, including:
[0187] The processor 320 determines the average time interval of swallowing behavior, the standard deviation of swallowing behavior time, and the time difference between the first and last swallowing behaviors according to the swallowing behavior information within the preset time period;
[0188] The processor 320 determines an abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference;
[0189] If the processor 320 determines that the abnormal eating behavior index is greater than a preset abnormal eating behavior index threshold, it is determined that the eating behavior is abnormal.
[0190] Optionally, the processor 320 determines the abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference, including:
[0191] The processor 320 determines a first characteristic difference value according to an absolute value of a difference between the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior;
[0192] The processor 320 determines a second characteristic difference value according to an absolute value of a difference between the swallowing behavior time standard deviation and the reference swallowing behavior time standard deviation;
[0193] The processor 320 determines a third characteristic difference value according to the absolute value of the difference between the first and last swallowing behavior time differences and the reference swallowing behavior time difference;
[0194] The processor 320 determines the abnormal eating behavior index according to the sum of the first feature difference value, the second feature difference value, and the third feature difference value.
[0195] Optionally, the processor 320 determines the abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference, including:
[0196] The processor 320 uses Formula 3 and calculates the swallowing behavior average time interval. Average time interval with the reference swallowing behavior , the standard deviation of the swallowing behavior time Standard deviation of swallowing behavior time from the reference , and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference Determine the abnormal eating behavior index , the formula 3 is:
[0197]
[0198] in, , , They are respectively the first weight value, the second weight value and the third weight value.
[0199] Optionally, the swallowing behavior monitoring system further includes a cloud server and a monitoring terminal, and the processor 320 and the monitoring terminal are respectively preset to communicate with the cloud server; after the processor 320 determines the swallowing behavior information within a preset time period according to the preset swallowing behavior monitoring model and the physiological characteristic signal, it also includes:
[0200] The processor 320 sends the swallowing behavior information to the cloud server, so that the cloud server generates a swallowing behavior monitoring curve according to the swallowing behavior information, and displays the swallowing behavior monitoring curve through the monitoring terminal.
[0201] Figure 4 is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. Figure 4 As shown, an electronic device 400 provided in this embodiment includes: a processor 401 and a memory 402; wherein:
[0202] The memory 402 is used to store computer programs, and the memory may also be a flash memory.
[0203] The processor 401 is used to execute the execution instructions stored in the memory to implement each step in the above method. For details, please refer to the relevant description in the above method embodiment.
[0204] Optionally, the memory 402 may be independent or integrated with the processor 401 .
[0205] When the memory 402 is a device independent of the processor 401, the electronic device 400 may further include:
[0206] The bus 403 is used to connect the memory 402 and the processor 401 .
[0207] This embodiment further provides a readable storage medium, in which a computer program is stored. When at least one processor of an electronic device executes the computer program, the electronic device executes the methods provided in the above-mentioned various implementation modes.
[0208] This embodiment also provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device implements the methods provided in the above various embodiments.
[0209] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.
[0210] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A swallowing behavior monitoring data processing method, It is characterized in that Applied to a swallowing behavior monitoring system, the swallowing behavior monitoring system includes a monitoring sensor set, a processor, and a prompting device, each monitoring sensor in the monitoring sensor set is communicatively connected to the processor, and the prompting device is communicatively connected to the processor; the method includes: Acquire physiological characteristic signals through monitoring sensors in the monitoring sensor set, and transmit the physiological characteristic signals to the processor; The processor determines swallowing behavior information within a preset time period according to a preset swallowing behavior monitoring model and the physiological characteristic signal, wherein the swallowing behavior information includes a swallowing behavior sequence and a time node corresponding to each swallowing behavior in the swallowing behavior sequence; If the processor determines that the eating behavior is abnormal according to the preset eating behavior monitoring model and the swallowing behavior information, the processor controls the prompting device to provide an abnormal eating behavior prompt.
2. The swallowing behavior monitoring data processing method according to claim 1, It is characterized in that The processor determines swallowing behavior information within a preset period of time according to a preset swallowing behavior monitoring model and the physiological characteristic signal, including: The processor determines a peak value of the physiological characteristic signal and a valley value of the physiological characteristic signal according to the physiological characteristic signal monitored within a preset monitoring period, wherein the preset period includes a plurality of the preset monitoring periods; The processor determines the swallowing behavior characteristic value of the preset monitoring period according to the physiological characteristic signal, the peak value of the physiological characteristic signal and the valley value of the physiological characteristic signal; The processor calculates the swallowing behavior characteristic value of each preset monitoring period within the preset time period. Determine the swallowing behavior information, wherein if the swallowing behavior characteristic value is greater than a preset characteristic value, the processor determines that there is swallowing behavior in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
3. The swallowing behavior monitoring data processing method according to claim 2, It is characterized in that The processor determines the peak value of the physiological characteristic signal and the valley value of the physiological characteristic signal according to the physiological characteristic signal monitored within a preset monitoring period, including: The processor determines the peak values and valley values of the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal according to the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal monitored within a preset monitoring period, wherein the physiological characteristic signal includes the first physiological characteristic signal, the second physiological characteristic signal and the third physiological characteristic signal; Correspondingly, the processor determines the swallowing behavior characteristic value of the preset monitoring period according to the physiological characteristic signal, the peak value of the physiological characteristic signal, and the valley value of the physiological characteristic signal, including: The processor determines a first swallowing behavior characteristic value, a second swallowing behavior characteristic value, and a third swallowing behavior characteristic value according to peak values and valley values of the first physiological characteristic signal, the second physiological characteristic signal, and the third physiological characteristic signal; Correspondingly, the processor calculates the swallowing behavior characteristic value of each preset monitoring period within the preset time period. Determining the swallowing behavior information includes: The processor determines a swallowing behavior feature probability according to the first swallowing behavior feature value, the second swallowing behavior feature value, and the third swallowing behavior feature value; The processor determines the swallowing behavior information based on the swallowing behavior feature probability of each preset monitoring period within the preset time period, wherein if the swallowing behavior feature probability is greater than the preset swallowing behavior feature probability value, the processor determines that there is swallowing behavior in the corresponding preset monitoring period, and the corresponding time node of each swallowing behavior in the swallowing behavior sequence is the starting time node of the corresponding preset monitoring period.
4. The swallowing behavior monitoring data processing method according to claim 3, It is characterized in that The first physiological characteristic signal is a pharyngeal electromyographic characteristic signal obtained by an electromyographic sensor, the second physiological characteristic signal is a glottal vibration signal obtained by a glottal sensor, and the third physiological characteristic signal is an acceleration signal obtained by an acceleration sensor.
5. The swallowing behavior monitoring data processing method according to any one of claims 1 to 4, It is characterized in that The processor determines that the eating behavior is abnormal according to a preset eating behavior monitoring model and the swallowing behavior information, including: The processor determines the average time interval of swallowing behavior, the standard deviation of swallowing behavior time, and the time difference between the first and last swallowing behaviors according to the swallowing behavior information within the preset time period; The processor determines an abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference; If the processor determines that the abnormal eating behavior index is greater than a preset abnormal eating behavior index threshold, it is determined that the eating behavior is abnormal.
6. The swallowing behavior monitoring data processing method according to claim 5, It is characterized in that The processor determines the abnormal eating behavior index according to the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior, the standard deviation of the swallowing behavior time and the standard deviation of the reference swallowing behavior time, and the time difference between the first and last swallowing behaviors and the reference swallowing behavior time difference, including: The processor determines a first characteristic difference value according to an absolute value of a difference between the average time interval of the swallowing behavior and the average time interval of the reference swallowing behavior; The processor determines a second characteristic difference value according to an absolute value of a difference between the swallowing behavior time standard deviation and the reference swallowing behavior time standard deviation; The processor determines a third characteristic difference value according to an absolute value of a difference between the first and last swallowing behavior time differences and the reference swallowing behavior time difference; The processor determines the abnormal eating behavior index according to the sum of the first feature difference value, the second feature difference value and the third feature difference value.
7. The swallowing behavior monitoring data processing method according to claim 6, It is characterized in that The swallowing behavior monitoring system further includes a cloud server and a monitoring terminal, and the processor and the monitoring terminal are respectively preset with the cloud server for communication connection; After the processor determines the swallowing behavior information within a preset period of time according to the preset swallowing behavior monitoring model and the physiological characteristic signal, the method further includes: The processor sends the swallowing behavior information to the cloud server, so that the cloud server generates a swallowing behavior monitoring curve according to the swallowing behavior information, and displays the swallowing behavior monitoring curve through the monitoring terminal.
8. A swallowing behavior monitoring data processing method and system, It is characterized in that include: A monitoring sensor set, a processor, and a prompting device, wherein each monitoring sensor in the monitoring sensor set is communicatively connected to the processor, and the prompting device is communicatively connected to the processor; Acquire physiological characteristic signals through monitoring sensors in the monitoring sensor set, and transmit the physiological characteristic signals to the processor; The processor determines swallowing behavior information within a preset time period according to a preset swallowing behavior monitoring model and the physiological characteristic signal, wherein the swallowing behavior information includes a swallowing behavior sequence and a time node corresponding to each swallowing behavior in the swallowing behavior sequence; If the processor determines that the eating behavior is abnormal according to the preset eating behavior monitoring model and the swallowing behavior information, the processor controls the prompting device to provide an abnormal eating behavior prompt.
9. An electronic device, It is characterized in that include: processor; as well as, A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.
Citation Information
Patent Citations
Eating and drinking action detection apparatus and eating and drinking action detection method
CN106859653A
Augmented reality systems and methods for user health analysis
CN109414164A
Wireless medical sensors and methods
CN111867672A
Deep learning-based function prediction model establishment method after early rehabilitation of cerebral apoplexy
CN115019919A
Swallowing monitoring system and method based on myoelectricity and pressure sensing
CN116942099A
Cited By
Swallowing monitoring system based on data analysis
CN120549445A
Human body state detection method and device, nose pad module and wearable equipment
CN121489502A
