Ultrasonic probe data transmission method and system based on edge calculation

Abstract

The invention discloses an ultrasonic probe data transmission method and system based on edge computing, and the method comprises the steps: responding to a monitoring start instruction, and transmitting a plurality of synchronous beacons to a plurality of ultrasonic probes based on wireless broadcasting; acquiring ultrasonic echo data detected by the ultrasonic probe based on the synchronous beacon; processing the ultrasonic echo data by an edge computing node to obtain processing result data; and storing the processing result data to a memory of the edge computing node and sending the processing result data to a cloud computing node. Therefore, according to the invention, multi-probe high-synchronization and low-delay distributed ultrasonic data acquisition and edge processing can be realized, the time sequence consistency and data integrity of multi-point monitoring are improved, and the risk of monitoring data distortion caused by time desynchrony or transmission delay is reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for transmitting data from an ultrasound probe based on edge computing. Background Technology

[0002] With the rapid expansion of multi-probe ultrasound monitoring in the medical and industrial fields, medical institutions and equipment manufacturers are increasingly focusing on improving the temporal consistency and reliability of multi-point monitoring through highly synchronized, low-latency data acquisition and processing. Existing technologies typically control multiple ultrasound probes to acquire echo data via wired connections or independent triggering, using a central server for unified processing to support multi-point monitoring needs. However, existing solutions lack wireless broadcast synchronization beacon mechanisms, real-time fusion processing of multi-probe echo data at edge nodes, and parallel guarantees for local storage and cloud uploading. This makes it difficult to guarantee high-precision alignment of acquisition timestamps and low-latency result output. Commonly used asynchronous triggering or centralized processing strategies are unsuitable for the timing requirements of distributed scenarios, resulting in insufficient temporal consistency and integrity of monitoring data. Data distortion or loss due to time asynchrony or transmission delays is easily caused, limiting the accuracy and clinical value of multi-probe ultrasound systems in real-time diagnosis and dynamic monitoring. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an ultrasound probe data transmission method and system based on edge computing, which can realize distributed ultrasound data acquisition and edge processing with high synchronization and low latency of multiple probes, improve the temporal consistency and data integrity of multi-point monitoring, and reduce the risk of monitoring data distortion caused by time asynchrony or transmission delay.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses an ultrasound probe data transmission method based on edge computing, the method comprising: In response to the monitoring start command, multiple synchronization beacons are sent to multiple ultrasound probes via wireless broadcast; Acquire the ultrasonic echo data obtained by the ultrasonic probe based on the synchronization beacon; The ultrasonic echo data is processed by edge computing nodes to obtain the processing result data; The processing result data is saved to the storage of the edge computing node and sent to the cloud computing node.

[0005] As an alternative implementation, in a first aspect of the invention, the edge computing node is a processor disposed in at least one of the ultrasound probes.

[0006] As an optional implementation, in the first aspect of the invention, the step of transmitting multiple synchronization beacons to multiple ultrasound probes via wireless broadcast includes: The time point at which the monitoring start command was generated and the corresponding multiple monitoring locations are obtained; the monitoring locations are the neck, heart, wrist, spine, or head. The ultrasonic probe corresponding to the monitoring location is identified as the target ultrasonic probe; Calculate the time difference between the current time point and the time point at which the event occurred; Based on the time difference and the probe parameters of each ultrasound probe, a synchronization beacon corresponding to each ultrasound probe is generated; Each of the aforementioned synchronization beacons is transmitted to the corresponding ultrasound probe via wireless broadcast.

[0007] As an optional implementation, in the first aspect of the invention, generating a synchronization beacon corresponding to each ultrasound probe based on the time difference and the probe parameters of each ultrasound probe includes: For each of the ultrasound probes, the probe parameters of the ultrasound probe are obtained; the probe parameters include probe type, probe hardware information, probe software information and probe communication parameters; Match multiple historical probe beacon data that are similar to the probe parameters in a preset historical database; Calculate the average communication delay corresponding to all the historical probe beacon data to obtain the reference delay time; Calculate the weighted sum of the time difference and the reference delay time to obtain the target time; Calculate the sum of the current time and the target time to obtain the target operation start time; Generate a synchronization beacon corresponding to the ultrasound probe, including the target operation start time.

[0008] As an optional implementation, in the first aspect of the invention, the step of processing the ultrasonic echo data by the edge computing node to obtain the processing result data includes: Obtain the overall computing tasks sent by the cloud computing nodes; The overall computational task is analyzed to determine the front-end processing task corresponding to the edge computing node in each of the ultrasound probes; For each ultrasound echo data, the edge computing node in the ultrasound probe that acquires the ultrasound echo data performs the front-end processing task to process the ultrasound echo data to obtain the processing result data.

[0009] As an optional implementation, in a first aspect of the invention, analyzing the overall computational task to determine the front-end processing task corresponding to the edge computing node in each of the ultrasound probes includes: The overall computation task and the node processing capability parameters corresponding to the edge computing nodes in all the ultrasound probes are input into the trained task partitioning model to obtain the front-end computation task corresponding to each edge computing node. The task partitioning model is trained using a training dataset that includes multiple training computation tasks and corresponding front-end computation task annotations and edge computing node parameter annotations. Based on the remaining tasks in the overall computing task excluding the front-end computing task, determine the data compression task corresponding to each edge computing node; The front-end computing task and the data compression task are defined as the front-end processing tasks corresponding to the edge computing nodes in each ultrasound probe.

[0010] As an optional implementation, in a first aspect of the invention, the front-end computing task includes at least one of beamforming, filtering, envelope detection, image generation, and Doppler shift calculation.

[0011] As an optional implementation, in the first aspect of the invention, determining the data compression task corresponding to each edge computing node based on the remaining tasks in the overall computing task excluding the front-end computing task includes: Determine the task description data for the remaining tasks in the overall computing task, excluding the front-end computing task; The task description data is input into a trained minimum input data volume prediction model to obtain the output task input data volume; the input data volume prediction model is trained using a training dataset that includes multiple training task description data and minimum data input volume labels. For each edge computing node, the task description data of the front-end computing task corresponding to the edge computing node is input into the trained output data volume prediction model to obtain the task output data volume corresponding to the edge computing node; the output data volume prediction model is trained through a training dataset that includes multiple training task description data and data output volume annotations; The data compression ratio parameter corresponding to the edge computing node is obtained by multiplying the ratio of the task output data volume to the task input data volume with a preset ratio coefficient. Generate a data compression task corresponding to the edge computing node, including the data compression ratio parameter.

[0012] A second aspect of this invention discloses an ultrasound probe data transmission system based on edge computing, the system comprising: The broadcast module is used to send multiple synchronization beacons to multiple ultrasound probes via wireless broadcast in response to a monitoring start command; The acquisition module is used to acquire the ultrasonic echo data obtained by the ultrasonic probe based on the synchronization beacon. The processing module is used to process the ultrasonic echo data by the edge computing nodes to obtain the processing result data; The sending module is used to save the processing result data to the storage of the edge computing node and to send the processing result data to the cloud computing node.

[0013] As an alternative implementation, in a second aspect of the invention, the edge computing node is a processor disposed in at least one of the ultrasound probes.

[0014] As an optional implementation, in a second aspect of the invention, the specific method by which the broadcast module transmits multiple synchronization beacons to multiple ultrasound probes via wireless broadcast includes: The time point at which the monitoring start command was generated and the corresponding multiple monitoring locations are obtained; the monitoring locations are the neck, heart, wrist, spine, or head. The ultrasonic probe corresponding to the monitoring location is identified as the target ultrasonic probe; Calculate the time difference between the current time point and the time point at which the event occurred; Based on the time difference and the probe parameters of each ultrasound probe, a synchronization beacon corresponding to each ultrasound probe is generated; Each of the aforementioned synchronization beacons is transmitted to the corresponding ultrasound probe via wireless broadcast.

[0015] As an optional implementation, in a second aspect of the invention, the specific method by which the broadcast module generates a synchronization beacon corresponding to each ultrasound probe based on the time difference and the probe parameters of each ultrasound probe includes: For each of the ultrasound probes, the probe parameters of the ultrasound probe are obtained; the probe parameters include probe type, probe hardware information, probe software information and probe communication parameters; Match multiple historical probe beacon data that are similar to the probe parameters in a preset historical database; Calculate the average communication delay corresponding to all the historical probe beacon data to obtain the reference delay time; Calculate the weighted sum of the time difference and the reference delay time to obtain the target time; Calculate the sum of the current time and the target time to obtain the target operation start time; Generate a synchronization beacon corresponding to the ultrasound probe, including the target operation start time.

[0016] As an optional implementation, in a second aspect of the invention, the specific method by which the processing module processes the ultrasonic echo data using edge computing nodes to obtain the processed result data includes: Obtain the overall computing tasks sent by the cloud computing nodes; The overall computational task is analyzed to determine the front-end processing task corresponding to the edge computing node in each of the ultrasound probes; For each ultrasound echo data, the edge computing node in the ultrasound probe that acquires the ultrasound echo data performs the front-end processing task to process the ultrasound echo data to obtain the processing result data.

[0017] As an optional implementation, in a second aspect of the invention, the processing module analyzes the overall computational task to determine the specific method of the front-end processing task corresponding to the edge computing node in each of the ultrasound probes, including: The overall computation task and the node processing capability parameters corresponding to the edge computing nodes in all the ultrasound probes are input into the trained task partitioning model to obtain the front-end computation task corresponding to each edge computing node. The task partitioning model is trained using a training dataset that includes multiple training computation tasks and corresponding front-end computation task annotations and edge computing node parameter annotations. Based on the remaining tasks in the overall computing task excluding the front-end computing task, determine the data compression task corresponding to each edge computing node; The front-end computing task and the data compression task are defined as the front-end processing tasks corresponding to the edge computing nodes in each ultrasound probe.

[0018] As an optional implementation, in a second aspect of the invention, the front-end computing task includes at least one of beamforming, filtering, envelope detection, image generation, and Doppler shift calculation.

[0019] As an optional implementation, in a second aspect of the invention, the processing module determines the specific method of the data compression task corresponding to each edge computing node based on the remaining tasks in the overall computing task excluding the front-end computing task, including: Determine the task description data for the remaining tasks in the overall computing task, excluding the front-end computing task; The task description data is input into a trained minimum input data volume prediction model to obtain the output task input data volume; the input data volume prediction model is trained using a training dataset that includes multiple training task description data and minimum data input volume labels. For each edge computing node, the task description data of the front-end computing task corresponding to the edge computing node is input into the trained output data volume prediction model to obtain the task output data volume corresponding to the edge computing node; the output data volume prediction model is trained through a training dataset that includes multiple training task description data and data output volume annotations; The data compression ratio parameter corresponding to the edge computing node is obtained by multiplying the ratio of the task output data volume to the task input data volume with a preset ratio coefficient. Generate a data compression task corresponding to the edge computing node, including the data compression ratio parameter.

[0020] A third aspect of this invention discloses another edge computing-based ultrasound probe data transmission system, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the edge computing-based ultrasonic probe data transmission method disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the edge computing-based ultrasonic probe data transmission method disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention enables distributed ultrasound data acquisition and edge processing with high synchronization and low latency across multiple probes by sending multiple synchronization beacons to the ultrasound probes in response to a monitoring start command. This improves the temporal consistency and data integrity of multi-point monitoring and reduces the risk of data distortion caused by time asynchrony or transmission delay. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1This is a schematic flowchart of an ultrasound probe data transmission method based on edge computing disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of the structure of an ultrasound probe data transmission system based on edge computing disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another edge computing-based ultrasonic probe data transmission system disclosed in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] This invention discloses an ultrasound probe data transmission method and system based on edge computing. By responding to a monitoring start command, multiple synchronization beacons are wirelessly broadcast to the ultrasound probe, acquiring ultrasound echo data detected by the probe based on the beacons. The edge computing nodes process the data to obtain the results, which are simultaneously saved locally and uploaded to the cloud. This enables highly synchronized, low-latency distributed ultrasound data acquisition and edge processing across multiple probes, improving the temporal consistency and data integrity of multi-point monitoring, and reducing the risk of data distortion due to time asynchrony or transmission delays. Detailed explanations follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a schematic flowchart of an ultrasound probe data transmission method based on edge computing disclosed in an embodiment of the present invention. Wherein, Figure 1 The described edge computing-based ultrasound probe data transmission method can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 1 As shown, this edge computing-based ultrasound probe data transmission method may include the following operations: 101. In response to the monitoring start command, multiple synchronization beacons are sent to multiple ultrasound probes via wireless broadcast.

[0032] Optionally, the monitoring start command can be manually triggered by the user, automatically started at a set time, or triggered by an abnormal event; this invention does not impose any limitations.

[0033] Optionally, the wireless broadcast can employ Wi-Fi broadcast, Bluetooth Low Energy broadcast, or a dedicated 2.4 GHz wireless protocol; this invention does not impose any limitations.

[0034] 102. Obtain ultrasonic echo data obtained by the ultrasonic probe based on the synchronous beacon detection.

[0035] Optionally, the ultrasonic echo data can be the original radio frequency echo signal or A-mode / B-mode data after preliminary envelope detection; this invention does not impose any limitations.

[0036] 103. The edge computing nodes process the ultrasonic echo data to obtain the processing result data.

[0037] Optionally, the edge computing node is a processor located in at least one ultrasound probe.

[0038] Optionally, the edge computing node can be a microcontroller, edge gateway, or local server integrated into the probe; the present invention does not limit this.

[0039] 104. Save the processing results data to the storage of the edge computing node and send the processing results data to the cloud computing node.

[0040] Optionally, the storage device can be a solid-state drive or a flash memory card, and the cloud computing node can be a public cloud server or a private cloud cluster; this invention does not impose any limitations.

[0041] As can be seen, the above-described embodiments of the invention send multiple synchronization beacons to the ultrasound probe via wireless broadcast in response to the monitoring start command, acquire ultrasound echo data detected by the probe based on the beacons, process the result data by the edge computing node and save it locally and upload it to the cloud at the same time, thereby realizing distributed ultrasound data acquisition and edge processing with high synchronization and low latency of multiple probes, improving the temporal consistency and data integrity of multi-point monitoring, and reducing the risk of monitoring data distortion caused by time asynchrony or transmission delay.

[0042] As an optional embodiment, the step described above, which involves transmitting multiple synchronization beacons to multiple ultrasound probes via wireless broadcast, includes: Obtain the time point at which the monitoring start command was generated and the corresponding multiple monitoring locations; The ultrasonic probe that is used to identify the monitoring location is the target ultrasonic probe; Calculate the time difference between the current time point and the time point at which the event occurred; Based on the time difference and the probe parameters of each ultrasound probe, a synchronization beacon corresponding to each ultrasound probe is generated. Each synchronization beacon is transmitted to the corresponding ultrasound probe via wireless broadcast.

[0043] Optional monitoring locations include the neck, heart, wrist, spine, or head.

[0044] Optionally, the time point of generation can be accurate to the millisecond level, and this invention does not limit it.

[0045] Optionally, the ultrasound probe corresponding to the determined monitoring location can be based on a pre-bound mapping table between probe ID and location; this invention does not impose any limitations on this.

[0046] As can be seen, through the above optional embodiments, by determining the time point of the monitoring start command generation and the target ultrasound probe corresponding to the monitoring location, calculating the current time and the time difference between generation, and combining the probe parameters to generate a synchronization beacon, accurate beacon customization based on time difference and probe characteristics can be achieved, improving the accuracy and reliability of multi-probe start synchronization, and reducing the risk of beacon asynchrony caused by differences in probe parameters.

[0047] As an optional embodiment, the step above, generating a synchronization beacon corresponding to each ultrasound probe based on the time difference and the probe parameters of each ultrasound probe, includes: For each ultrasonic probe, obtain the probe parameters of that ultrasonic probe; Match multiple historical probe beacon data with similar probe parameters to the preset historical database; Calculate the average communication delay corresponding to all historical probe beacon data to obtain the reference delay time; Calculate the weighted sum of the time difference and the reference delay to obtain the target time; Calculate the sum of the current time and the target time to obtain the start time of the target operation; Generate a synchronization beacon corresponding to the ultrasound probe, including the target operation start time.

[0048] Optionally, probe parameters include probe type, probe hardware information, probe software information, and probe communication parameters.

[0049] Optionally, the probe type can be a linear array probe or a convex array probe; this invention does not limit the type.

[0050] Optionally, the probe parameters may also include probe clock offset, communication delay compensation value, or sampling rate; this invention does not impose any limitations.

[0051] Optionally, the matching of the historical probe beacon data can be achieved based on the calculation of parameter vector similarity between probe parameters and threshold filtering, which is not limited in this invention.

[0052] Optionally, the average communication delay corresponding to all historical probe beacon data can be a weighted average, with the weight proportional to the similarity of the parameter vectors. This invention does not impose any limitations on this.

[0053] Optionally, the synchronization beacon can be a broadcast packet containing a timestamp; this invention does not limit this.

[0054] As can be seen, through the above optional embodiments, by acquiring the ultrasonic probe parameters and matching historical similar probe beacon data to calculate the reference delay time, and combining the time difference weighted summation to obtain the target operation start time to generate a synchronization beacon, adaptive synchronization time calibration based on historical delay and current time difference is realized, improving the time accuracy of multi-probe collaborative detection and reducing the risk of signal acquisition misalignment caused by not considering historical delay.

[0055] As an optional embodiment, the step above, in which the edge computing node processes the ultrasonic echo data to obtain the processed result data, includes: Obtain the overall computing tasks sent by the cloud computing nodes; The overall computational task is analyzed to determine the front-end processing task corresponding to the edge computing node in each ultrasound probe. For each ultrasonic echo data, the edge computing node in the ultrasonic probe that acquires the ultrasonic echo data performs a front-end processing task to process the ultrasonic echo data and obtain the processing result data.

[0056] Optionally, the overall calculation task can be vascular elasticity analysis, cardiac output estimation, or hemodynamic parameter calculation, and the present invention does not limit it.

[0057] Optionally, the front-end computing tasks include at least one of beamforming, filtering, envelope detection, image generation, and Doppler shift calculation.

[0058] Optionally, the front-end processing task can be radio frequency data filtering, envelope detection, or preliminary image reconstruction; this invention does not limit the scope of the task.

[0059] Optionally, the processing result data can be a B-mode image, a blood flow velocity map, or a parameterized feature vector; this invention does not impose any limitations.

[0060] As can be seen, through the above optional embodiments, by acquiring the overall cloud computing task and analyzing and determining the front-end processing task of each ultrasound probe edge computing node, the corresponding edge node executes the processing to obtain the result data, thereby realizing distributed edge computing load balancing based on task decomposition, improving the real-time performance and system scalability of ultrasound echo data processing, and reducing the risk of latency and bandwidth pressure caused by centralized cloud computing.

[0061] As an optional embodiment, the step described above, analyzing the overall computational task to determine the front-end processing task corresponding to the edge computing node in each ultrasound probe, includes: The overall computational task and the node processing capability parameters corresponding to the edge computing nodes in all ultrasound probes are input into the trained task partitioning model to obtain the front-end computational task corresponding to each edge computing node. Based on the remaining tasks in the overall computing task excluding the front-end computing task, determine the data compression task corresponding to each edge computing node; The front-end computing task and data compression task are defined as the front-end processing tasks corresponding to the edge computing nodes in each ultrasound probe.

[0062] Optionally, the task partitioning model is trained using a training dataset that includes multiple training computation tasks and corresponding front-end computation task annotations and edge computation node parameter annotations.

[0063] Optionally, the task partitioning model can be a four-layer fully connected neural network with 324 neurons in the first layer, 162 neurons in the second layer, 81 neurons in the third layer, and a fourth layer that outputs a task assignment vector. The mean squared error loss function is used, and the model is trained for 120 training epochs on 150,000 task-node capability labeled data. This invention does not impose any limitations on this model.

[0064] Optionally, the data compression task can be JPEG compression, H.265 video compression, or feature quantization compression; this invention does not impose any limitations.

[0065] As can be seen, through the above optional embodiments, by inputting the overall computing task and the processing capability parameters of each edge computing node into the trained task partitioning model to output the front-end computing task, and generating a data compression task accordingly, intelligent task allocation and compression based on node capabilities and task descriptions can be achieved, thereby improving the utilization rate of edge computing resources and data transmission efficiency, and reducing the risk of node overload or data redundancy caused by uneven task allocation.

[0066] As an optional embodiment, the step above, determining the data compression task corresponding to each edge computing node based on the remaining tasks in the overall computing task excluding the front-end computing task, includes: Determine the task description data for the remaining tasks in the overall computing task, excluding the front-end computing task; Input the task description data into the trained minimum input data volume prediction model to obtain the output task input data volume; For each edge computing node, the task description data of the front-end computing task corresponding to the edge computing node is input into the trained output data volume prediction model to obtain the task output data volume corresponding to the edge computing node. The data compression ratio parameter corresponding to the edge computing node is obtained by multiplying the ratio of the task output data volume to the task input data volume with a preset ratio coefficient. Generate a data compression task corresponding to the edge computing node, including data compression ratio parameters.

[0067] Optionally, the minimum input data volume prediction model is trained using a training dataset that includes multiple training task description data and minimum data input volume labels.

[0068] Optionally, the minimum input data volume prediction model can be a three-layer fully connected neural network, with 256 neurons in the first layer, 128 neurons in the second layer, and the output data volume value in the third layer, trained on 100,000 task description labeled data. This invention does not limit the model.

[0069] Optionally, the output data volume prediction model is trained using a training dataset that includes description data for multiple training tasks and labeled data output volumes.

[0070] Optionally, the output data volume prediction model can be a three-layer fully connected neural network, with a structure and training details similar to the minimum input data volume prediction model, which is not limited in this invention.

[0071] Optionally, the task parameters for this data compression task may include compression ratio, compression algorithm type, and compression priority, which are not limited in this invention.

[0072] As can be seen, through the above optional embodiments, the remaining task description data is input into the minimum input data volume prediction model to predict the task input data volume, and the front-end calculation task description input and output data volume prediction model is used to predict the output data volume. The data compression ratio parameter is generated based on the product of the input-output ratio and the proportional coefficient. This enables accurate adaptive adjustment of compression parameters based on the prediction model, improves the targeting of data compression and transmission efficiency, and reduces the risk of data redundancy or quality loss caused by fixed compression parameters.

[0073] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an ultrasound probe data transmission system based on edge computing, as disclosed in an embodiment of the present invention. Figure 2 The described edge computing-based ultrasound probe data transmission system can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 2 As shown, the edge computing-based ultrasound probe data transmission system may include: Broadcast module 201 is used to send multiple synchronization beacons to multiple ultrasound probes via wireless broadcast in response to a monitoring start command.

[0074] The acquisition module 202 is used to acquire ultrasonic echo data obtained by the ultrasonic probe based on the synchronous beacon detection.

[0075] The processing module 203 is used to process the ultrasonic echo data by the edge computing node to obtain the processing result data.

[0076] The sending module 204 is used to save the processing result data to the storage of the edge computing node and to send the processing result data to the cloud computing node.

[0077] As can be seen, the above-described embodiments of the invention send multiple synchronization beacons to the ultrasound probe via wireless broadcast in response to the monitoring start command, acquire ultrasound echo data detected by the probe based on the beacons, process the result data by the edge computing node and save it locally and upload it to the cloud at the same time, thereby realizing distributed ultrasound data acquisition and edge processing with high synchronization and low latency of multiple probes, improving the temporal consistency and data integrity of multi-point monitoring, and reducing the risk of monitoring data distortion caused by time asynchrony or transmission delay.

[0078] As an optional embodiment, the edge computing node is a processor located in at least one ultrasound probe.

[0079] As can be seen, the above optional embodiments define the edge computing nodes set in the ultrasound probe for front-end data processing directly at the ultrasound probe, which helps to achieve distributed ultrasound data acquisition and edge processing with high synchronization and low latency of multiple probes, and improves the temporal consistency and data integrity of multi-point monitoring.

[0080] As an optional embodiment, the broadcast module transmits multiple synchronization beacons to multiple ultrasound probes via wireless broadcast in the following specific manner: The system obtains the time point at which the monitoring start command is generated and the corresponding multiple monitoring locations; optionally, the monitoring locations are the neck, heart, wrist, spine, or head. The ultrasonic probe that is used to identify the monitoring location is the target ultrasonic probe; Calculate the time difference between the current time point and the time point at which the event occurred; Based on the time difference and the probe parameters of each ultrasound probe, a synchronization beacon corresponding to each ultrasound probe is generated. Each synchronization beacon is transmitted to the corresponding ultrasound probe via wireless broadcast.

[0081] As can be seen, through the above optional embodiments, by determining the time point of the monitoring start command generation and the target ultrasound probe corresponding to the monitoring location, calculating the current time and the time difference between generation, and combining the probe parameters to generate a synchronization beacon, accurate beacon customization based on time difference and probe characteristics can be achieved, improving the accuracy and reliability of multi-probe start synchronization, and reducing the risk of beacon asynchrony caused by differences in probe parameters.

[0082] As an optional embodiment, the broadcast module generates a specific method for generating a synchronization beacon corresponding to each ultrasound probe based on the time difference and the probe parameters of each ultrasound probe, including: For each ultrasonic probe, obtain the probe parameters; optionally, the probe parameters include probe type, probe hardware information, probe software information and probe communication parameters. Match multiple historical probe beacon data with similar probe parameters to the preset historical database; Calculate the average communication delay corresponding to all historical probe beacon data to obtain the reference delay time; Calculate the weighted sum of the time difference and the reference delay to obtain the target time; Calculate the sum of the current time and the target time to obtain the start time of the target operation; Generate a synchronization beacon corresponding to the ultrasound probe, including the target operation start time.

[0083] As can be seen, through the above optional embodiments, by acquiring the ultrasonic probe parameters and matching historical similar probe beacon data to calculate the reference delay time, and combining the time difference weighted summation to obtain the target operation start time to generate a synchronization beacon, adaptive synchronization time calibration based on historical delay and current time difference is realized, improving the time accuracy of multi-probe collaborative detection and reducing the risk of signal acquisition misalignment caused by not considering historical delay.

[0084] As an optional embodiment, the specific method by which the processing module processes the ultrasonic echo data from the edge computing nodes to obtain the processed result data includes: Obtain the overall computing tasks sent by the cloud computing nodes; The overall computational task is analyzed to determine the front-end processing task corresponding to the edge computing node in each ultrasound probe. For each ultrasonic echo data, the edge computing node in the ultrasonic probe that acquires the ultrasonic echo data performs a front-end processing task to process the ultrasonic echo data and obtain the processing result data.

[0085] As can be seen, through the above optional embodiments, by acquiring the overall cloud computing task and analyzing and determining the front-end processing task of each ultrasound probe edge computing node, the corresponding edge node executes the processing to obtain the result data, thereby realizing distributed edge computing load balancing based on task decomposition, improving the real-time performance and system scalability of ultrasound echo data processing, and reducing the risk of latency and bandwidth pressure caused by centralized cloud computing.

[0086] As an optional embodiment, the processing module analyzes the overall computational task to determine the specific manner in which the front-end processing task corresponds to the edge computing node in each ultrasound probe is performed, including: The overall computational task and the node processing capability parameters corresponding to the edge computing nodes in all ultrasound probes are input into the trained task partitioning model to obtain the front-end computational task corresponding to each edge computing node. Optionally, the task partitioning model is trained using a training dataset that includes multiple training computational tasks and corresponding front-end computational task annotations and edge computing node parameter annotations. Based on the remaining tasks in the overall computing task excluding the front-end computing task, determine the data compression task corresponding to each edge computing node; The front-end computing task and data compression task are defined as the front-end processing tasks corresponding to the edge computing nodes in each ultrasound probe.

[0087] As can be seen, through the above optional embodiments, by inputting the overall computing task and the processing capability parameters of each edge computing node into the trained task partitioning model to output the front-end computing task, and generating a data compression task accordingly, intelligent task allocation and compression based on node capabilities and task descriptions can be achieved, thereby improving the utilization rate of edge computing resources and data transmission efficiency, and reducing the risk of node overload or data redundancy caused by uneven task allocation.

[0088] As an optional embodiment, the front-end computing task includes at least one of beamforming, filtering, envelope detection, image generation, and Doppler shift calculation.

[0089] As can be seen, the above optional embodiments define the task details of the front-end computing task to instruct the computing nodes of the ultrasound probe to perform front-end data processing, thereby assisting in the realization of distributed ultrasound data acquisition and edge processing with high synchronization and low latency of multiple probes, and improving the temporal consistency and data integrity of multi-point monitoring.

[0090] As an optional embodiment, the processing module determines the specific method of the data compression task corresponding to each edge computing node based on the remaining tasks in the overall computing task excluding the front-end computing tasks, including: Determine the task description data for the remaining tasks in the overall computing task, excluding the front-end computing task; The task description data is input into the trained minimum input data volume prediction model to obtain the output task input data volume; optionally, the input data volume prediction model is trained using a training dataset that includes multiple training task description data and minimum data input volume labels. For each edge computing node, the task description data of the front-end computing task corresponding to the edge computing node is input into the trained output data volume prediction model to obtain the task output data volume corresponding to the edge computing node; optionally, the output data volume prediction model is trained using a training dataset that includes multiple training task description data and data output volume annotations. The data compression ratio parameter corresponding to the edge computing node is obtained by multiplying the ratio of the task output data volume to the task input data volume with a preset ratio coefficient. Generate a data compression task corresponding to the edge computing node, including data compression ratio parameters.

[0091] As can be seen, through the above optional embodiments, the remaining task description data is input into the minimum input data volume prediction model to predict the task input data volume, and the front-end calculation task description input and output data volume prediction model is used to predict the output data volume. The data compression ratio parameter is generated based on the product of the input-output ratio and the proportional coefficient. This enables accurate adaptive adjustment of compression parameters based on the prediction model, improves the targeting of data compression and transmission efficiency, and reduces the risk of data redundancy or quality loss caused by fixed compression parameters.

[0092] Example 3 Please see Figure 3 , Figure 3 This is another edge computing-based ultrasonic probe data transmission system disclosed in the embodiments of the present invention. Figure 3 The described edge computing-based ultrasound probe data transmission system is applied in data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the edge computing-based ultrasound probe data transmission system may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the edge computing-based ultrasound probe data transmission method described in Embodiment 1.

[0093] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the edge computing-based ultrasonic probe data transmission method described in Embodiment 1.

[0094] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the edge computing-based ultrasonic probe data transmission method described in Embodiment 1.

[0095] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0097] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0098] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0103] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0104] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0105] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0106] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0107] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0108] Finally, it should be noted that the ultrasonic probe data transmission method and system based on edge computing disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for transmitting data from an ultrasonic probe based on edge computing, characterized in that, The method includes: In response to the monitoring start command, multiple synchronization beacons are sent to multiple ultrasound probes via wireless broadcast; Acquire the ultrasonic echo data obtained by the ultrasonic probe based on the synchronization beacon; The ultrasonic echo data is processed by edge computing nodes to obtain the processing result data; The processing result data is saved to the storage of the edge computing node and sent to the cloud computing node.

2. The ultrasonic probe data transmission method based on edge computing according to claim 1, characterized in that, The edge computing node is a processor located in at least one of the ultrasound probes.

3. The ultrasonic probe data transmission method based on edge computing according to claim 1, characterized in that, The method of transmitting multiple synchronization beacons to multiple ultrasound probes via wireless broadcast includes: The time point at which the monitoring start command was generated and the corresponding multiple monitoring locations are obtained; the monitoring locations are the neck, heart, wrist, spine, or head. The ultrasonic probe corresponding to the monitoring location is identified as the target ultrasonic probe; Calculate the time difference between the current time point and the time point at which the event occurred; Based on the time difference and the probe parameters of each ultrasound probe, a synchronization beacon corresponding to each ultrasound probe is generated; Each of the aforementioned synchronization beacons is transmitted to the corresponding ultrasound probe via wireless broadcast.

4. The ultrasonic probe data transmission method based on edge computing according to claim 3, characterized in that, The step of generating a synchronization beacon corresponding to each ultrasound probe based on the time difference and the probe parameters of each ultrasound probe includes: For each of the ultrasound probes, the probe parameters of the ultrasound probe are obtained; the probe parameters include probe type, probe hardware information, probe software information and probe communication parameters; Match multiple historical probe beacon data that are similar to the probe parameters in a preset historical database; Calculate the average communication delay corresponding to all the historical probe beacon data to obtain the reference delay time; Calculate the weighted sum of the time difference and the reference delay time to obtain the target time; Calculate the sum of the current time and the target time to obtain the target operation start time; Generate a synchronization beacon corresponding to the ultrasound probe, including the target operation start time.

5. The ultrasonic probe data transmission method based on edge computing according to claim 1, characterized in that, The processing result data obtained by processing the ultrasonic echo data by the edge computing node includes: Obtain the overall computing tasks sent by the cloud computing nodes; The overall computational task is analyzed to determine the front-end processing task corresponding to the edge computing node in each of the ultrasound probes; For each ultrasound echo data, the edge computing node in the ultrasound probe that acquires the ultrasound echo data performs the front-end processing task to process the ultrasound echo data to obtain the processing result data.

6. The ultrasonic probe data transmission method based on edge computing according to claim 5, characterized in that, The analysis of the overall computational task to determine the front-end processing task corresponding to the edge computing node in each ultrasound probe includes: The overall computation task and the node processing capability parameters corresponding to the edge computing nodes in all the ultrasound probes are input into the trained task partitioning model to obtain the front-end computation task corresponding to each edge computing node. The task partitioning model is trained using a training dataset that includes multiple training computation tasks and corresponding front-end computation task annotations and edge computing node parameter annotations. Based on the remaining tasks in the overall computing task excluding the front-end computing task, determine the data compression task corresponding to each edge computing node; The front-end computing task and the data compression task are defined as the front-end processing tasks corresponding to the edge computing nodes in each ultrasound probe.

7. The ultrasonic probe data transmission method based on edge computing according to claim 6, characterized in that, The front-end computing tasks include at least one of beamforming, filtering, envelope detection, image generation, and Doppler shift calculation.

8. The ultrasonic probe data transmission method based on edge computing according to claim 6, characterized in that, The step of determining the data compression task corresponding to each edge computing node based on the remaining tasks in the overall computing task excluding the front-end computing task includes: Determine the task description data for the remaining tasks in the overall computing task, excluding the front-end computing task; The task description data is input into the trained minimum input data volume prediction model to obtain the output task input data volume; the minimum input data volume prediction model is trained on a training dataset that includes multiple training task description data and minimum data input volume labels; For each edge computing node, the task description data of the front-end computing task corresponding to the edge computing node is input into the trained output data volume prediction model to obtain the task output data volume corresponding to the edge computing node; the output data volume prediction model is trained through a training dataset that includes multiple training task description data and data output volume annotations; The data compression ratio parameter corresponding to the edge computing node is obtained by multiplying the ratio of the task output data volume to the task input data volume with a preset ratio coefficient. Generate a data compression task corresponding to the edge computing node, including the data compression ratio parameter.

9. An ultrasonic probe data transmission system based on edge computing, characterized in that, The system includes: The broadcast module is used to send multiple synchronization beacons to multiple ultrasound probes via wireless broadcast in response to a monitoring start command; The acquisition module is used to acquire the ultrasonic echo data obtained by the ultrasonic probe based on the synchronization beacon. The processing module is used to process the ultrasonic echo data by the edge computing nodes to obtain the processing result data; The sending module is used to save the processing result data to the storage of the edge computing node and to send the processing result data to the cloud computing node.

10. An ultrasonic probe data transmission system based on edge computing, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the edge computing-based ultrasound probe data transmission method as described in any one of claims 1-8.

Images