CN-122004919-A - Ultrasonic equipment control method and system based on event triggering mode

CN122004919ACN 122004919 ACN122004919 ACN 122004919ACN-122004919-A

Abstract

The invention discloses an ultrasonic equipment control method and system based on an event triggering mode, wherein the method comprises the steps of configuring ultrasonic equipment into a first working mode to obtain sensing data of a user, judging whether the current cardiovascular state of the user is abnormal according to the sensing data, triggering a corresponding working event when judging that the current cardiovascular state of the user is abnormal, configuring the ultrasonic equipment into a second working mode to obtain ultrasonic data of the user based on the working event, wherein the working power of the ultrasonic equipment in the second working mode is larger than that in the first working mode, and the data amount of the ultrasonic data is higher than that of the sensing data. Therefore, the invention can realize the intelligent mode switching of event classification based on low-power consumption primary screening and high-precision diagnosis, improve the real-time performance and accuracy of cardiovascular monitoring, and reduce the risk of overhigh equipment power consumption caused by continuous high-power scanning.

Inventors

CAI WEIZHONG
XU PEIDA
ZHANG YONGLONG
LIN YANJIE

Assignees

广州索诺星信息科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260128

Claims (10)

1. A method for controlling an ultrasonic device based on an event-triggered mode, the method comprising: configuring an ultrasonic device into a first working mode to acquire sensing data of a user; Judging whether the current cardiovascular state of the user is abnormal or not according to the sensing data; triggering a corresponding working event when judging that the current cardiovascular state of the user is abnormal; The ultrasonic equipment is configured into a second working mode based on the working event to acquire ultrasonic data of the user, the working power of the ultrasonic equipment in the second working mode is larger than that in the first working mode, and the data volume of the ultrasonic data is higher than that of the sensing data.
2. The method for controlling an ultrasonic device based on an event triggering mode according to claim 1, wherein the ultrasonic device is a hand-held ultrasonic device, and a sensor is provided to acquire the sensing data.
3. The method of claim 1, wherein the sensing data comprises one or more of acceleration data, image data, sound data, and ultrasound sensing data.
4. The method for controlling an ultrasonic device based on an event triggering mode according to claim 1, wherein the determining whether the current cardiovascular state of the user is abnormal according to the sensing data comprises: Inputting the sensing data of the latest historical time point into a trained preliminary cardiovascular abnormality prediction model to obtain an output preliminary predicted abnormal value; Judging whether the preliminary predicted abnormal value is larger than a preset first abnormal value or not to obtain a first judging result; when the first judgment result is yes, determining that the current cardiovascular state of the user is abnormal; judging whether the preliminary predicted abnormal value is larger than a preset second abnormal value or not when the first judging result is negative, and obtaining a second judging result, wherein the second abnormal value is larger than the u even first abnormal value; When the second judgment result is negative, determining that the current cardiovascular state of the user is not abnormal; and when the second judging result is yes, judging whether the current cardiovascular state of the user is abnormal or not based on the sensing data of a plurality of historical time points.
5. The method according to claim 4, wherein the determining whether the current cardiovascular state of the user is abnormal based on the sensing data of a plurality of historical time points comprises: inputting the sensing data of a plurality of historical time points into a trained accurate cardiovascular abnormality prediction model to obtain predicted abnormal values corresponding to the sensing data of each historical time point; Combining all the predicted abnormal values from the early to the late based on the historical time points to obtain a predicted abnormal time sequence vector; Inputting the predicted abnormal time sequence vector into a trained LSTM neural network to obtain an output cardiovascular state value, wherein the LSTM neural network is obtained by training based on a plurality of training sensing abnormal time sequence data and a training data set of corresponding cardiovascular state scoring labels; judging whether the cardiovascular state value is smaller than a preset state threshold value or not so as to judge whether the current cardiovascular state of the user is abnormal or not.
6. The method for controlling an ultrasonic device based on an event triggering mode according to claim 5, wherein the preliminary cardiovascular abnormality prediction model and the accurate cardiovascular abnormality prediction model are obtained by training: acquiring a plurality of historical user sensing data and cardiovascular diagnostic data, and determining the historical user sensing data and the cardiovascular diagnostic data as a labeling data set; Training a preset basic model according to the marking data set until convergence to obtain a basic prediction model; selecting a first number of first training data and a second number of second training data from the set of annotation data, respectively, the second number being greater than the first number; Performing data characteristic association analysis on any two of the historical user sensing data in the second training data to obtain higher-precision data annotation; Training the basic prediction model according to the first training data and the second training data respectively, and jointly optimizing the loss functions of the two training models in training to obtain the preliminary cardiovascular abnormality prediction model obtained based on the first training data and the accurate cardiovascular abnormality prediction model obtained based on the second training data, wherein the loss function is a weighted sum of a first loss function value of the preliminary cardiovascular abnormality prediction model and a second loss function value of the accurate cardiovascular abnormality prediction model during the joint optimization, and the weight of the second loss function value is larger than that of the first loss function value.
7. The method for controlling an ultrasonic device based on an event triggering mode according to claim 5, wherein triggering the corresponding working event comprises: When the cardiovascular state value exists, determining a working event corresponding to the cardiovascular state value based on the type of the working event corresponding to a plurality of preset state value thresholds so as to trigger; when the cardiovascular state value does not exist, based on the working event types corresponding to the preset abnormal value thresholds, determining the working event corresponding to the preliminary predicted abnormal value to trigger, wherein the working event is in a monitoring mode or a diagnosis mode.
8. The method of claim 7, wherein when the operation event is the diagnostic mode, the device operation parameters of the ultrasonic device in the second operation mode are determined by: acquiring motion sensing data and ultrasonic sensing data of the ultrasonic equipment in real time; Determining a detection movement track of the ultrasonic equipment based on a track recognition algorithm according to the motion sensing data; Determining a detection target parameter corresponding to the ultrasonic equipment based on an image recognition algorithm according to the ultrasonic sensing data, wherein the detection target parameter comprises at least one of a detection position, a detection depth and a detection time point; determining detection importance parameters corresponding to the ultrasonic equipment based on a preset classifier algorithm according to the detection movement track and the detection target parameters; setting the equipment working parameters of the ultrasonic equipment to be a numerical value proportional to the detection importance parameters, wherein the equipment working parameters are power parameters, voltage parameters, frame rate parameters or frequency parameters.
9. An ultrasonic device control system based on an event-triggered mode, the system comprising: the first configuration module is used for configuring the ultrasonic equipment into a first working mode to acquire sensing data of a user; The judging module is used for judging whether the current cardiovascular state of the user is abnormal or not according to the sensing data; The triggering module is used for triggering a corresponding working event when judging that the current cardiovascular state of the user is abnormal; The second configuration module is used for configuring the ultrasonic equipment into a second working mode based on the working event to acquire ultrasonic data of the user, the working power of the ultrasonic equipment in the second working mode is larger than that in the first working mode, and the data amount of the ultrasonic data is higher than that of the sensing data.
10. An ultrasonic device control system based on an event-triggered mode, the system comprising: a memory storing executable program code; a processor coupled to the memory; The processor invokes the executable program code stored in the memory to perform the event trigger mode based ultrasound device control method of any of claims 1-8.

Description

Ultrasonic equipment control method and system based on event triggering mode Technical Field The invention relates to the technical field of data processing, in particular to an ultrasonic equipment control method and system based on an event triggering mode. Background With the rapid growth of cardiovascular real-time monitoring and portable ultrasound equipment demands, medical institutions and users increasingly pay attention to achieving efficient, low-risk cardiovascular state assessment through intelligent hierarchical working modes, wherein how to reduce equipment power consumption and user radiation exposure becomes a key technical problem. The prior art generally sets the ultrasound device to a single high power scan mode for continuous data acquisition, relying on manual judgment or fixed cycle switching to complete cardiovascular state assessment. The existing solution is difficult to effectively control power consumption and radiation exposure in a normal state due to lack of a real-time abnormality judgment mechanism based on low-power consumption primary screening data and intelligent control for automatically switching to a high-power mode after abnormality triggering, so that the overall power consumption of the equipment is overhigh, the long-term radiation accumulation risk of a user is increased, or diagnosis accuracy and instantaneity in an abnormal state are insufficient, and the practicability, safety and clinical value of the portable ultrasonic cardiovascular monitoring equipment are limited. It can be seen that the prior art has defects and needs to be solved. Disclosure of Invention The invention aims to solve the technical problem of providing an ultrasonic equipment control method and system based on an event triggering mode, which can realize the intelligent mode switching of event classification based on low-power consumption primary screening and high-precision diagnosis, improve the real-time performance and accuracy of cardiovascular monitoring and reduce the risk of overhigh equipment power consumption caused by continuous high-power scanning. In order to solve the technical problem, a first aspect of the present invention discloses an ultrasonic device control method based on an event trigger mode, the method comprising: configuring an ultrasonic device into a first working mode to acquire sensing data of a user; Judging whether the current cardiovascular state of the user is abnormal or not according to the sensing data; triggering a corresponding working event when judging that the current cardiovascular state of the user is abnormal; The ultrasonic equipment is configured into a second working mode based on the working event to acquire ultrasonic data of the user, the working power of the ultrasonic equipment in the second working mode is larger than that in the first working mode, and the data volume of the ultrasonic data is higher than that of the sensing data. As an optional implementation manner, in the first aspect of the present invention, the ultrasonic device is a handheld ultrasonic device, and a sensor is provided to acquire the sensing data. As an optional implementation manner, in the first aspect of the present invention, the sensing data includes one or more of acceleration data, image data, sound data, and ultrasound sensing data. As an optional implementation manner, in the first aspect of the present invention, the determining, according to the sensing data, whether the current cardiovascular state of the user is abnormal includes: Inputting the sensing data of the latest historical time point into a trained preliminary cardiovascular abnormality prediction model to obtain an output preliminary predicted abnormal value; Judging whether the preliminary predicted abnormal value is larger than a preset first abnormal value or not to obtain a first judging result; when the first judgment result is yes, determining that the current cardiovascular state of the user is abnormal; judging whether the preliminary predicted abnormal value is larger than a preset second abnormal value or not when the first judging result is negative, and obtaining a second judging result, wherein the second abnormal value is larger than the u even first abnormal value; When the second judgment result is negative, determining that the current cardiovascular state of the user is not abnormal; and when the second judging result is yes, judging whether the current cardiovascular state of the user is abnormal or not based on the sensing data of a plurality of historical time points. As an optional implementation manner, in the first aspect of the present invention, the determining, based on the sensing data of a plurality of historical time points, whether the current cardiovascular state of the user is abnormal includes: inputting the sensing data of a plurality of historical time points into a trained accurate cardiovascular abnormality prediction model to obtain predicted abnormal