A method and system for monitoring resuscitation processes in a trauma resuscitation unit

Abstract

The embodiment of the application provides a kind of trauma resuscitation unit in the monitoring method and system of resuscitation process, and monitoring method includes: obtaining the trauma information of personnel to be resuscitated;Determine the corresponding preset resuscitation process based on trauma information, and preset resuscitation process includes multiple preset resuscitation sub-processes with preset time attribute;In the first field of vision video, the actual time attribute corresponding to actual resuscitation sub-process is extracted;Pre-set time attribute is compared with actual time attribute, and comparison result is obtained;In the first field of vision video, the actual time attribute corresponding to actual resuscitation sub-process is extracted, to determine the progress of actual resuscitation process according to the first field of vision video;Pre-set time attribute is compared with actual time attribute, and comparison result is obtained, to confirm whether actual resuscitation process exists deviation for preset resuscitation process;Resuscitation process in trauma resuscitation unit is monitored based on comparison result, actual resuscitation process is monitored.

Description

Technical Field

[0001] This invention relates to the field of medical treatment, specifically to a method and system for monitoring the resuscitation process in a trauma resuscitation unit. Background Technology

[0002] Trauma resuscitation units (CRUs) are typically located within the emergency medicine department and are dedicated to the early assessment and treatment of severely traumatized patients within the trauma center. The capacity building of CRUs is based on the core principles of advanced trauma life support and must meet the requirements or potential treatment measures outlined in the "ABCDE" systematic resuscitation process to achieve the desired therapeutic outcomes. Since the primary purpose of CRUs is to treat severe trauma, in addition to secondary assessment capabilities, they should also possess the capacity for treating severe trauma, especially controlling and resuscitating massive bleeding, managing the airway, and treating preventable fatal injuries such as tension pneumothorax.

[0003] The trauma resuscitation unit is a highly demanding and time-sensitive environment where work efficiency is of paramount importance. Within the trauma resuscitation unit, there are fixed time limits for the entire resuscitation process, as well as fixed start and end times for sub-resuscitation processes. In other words, each sub-resuscitation process has a fixed time limit, and there are also fixed time limits for the intervals between sub-processes.

[0004] In the resuscitation treatment of patients, if a resuscitation sub-process is not executed in a timely manner, or if the actual start time is later than the preset start time or the actual end time is later than the preset end time, it will affect the timeliness requirements of the resuscitation process and thus affect the resuscitation effect of the patients to be resuscitated. Therefore, it is necessary to monitor the execution of the resuscitation process in the trauma resuscitation unit.

[0005] Therefore, the lack of monitoring of the execution of resuscitation procedures within existing trauma resuscitation units may pose a technical problem that could affect the resuscitation outcomes of patients awaiting resuscitation. Summary of the Invention

[0006] This application provides a method and system for monitoring the resuscitation process in a trauma resuscitation unit, to at least solve the technical problem in the related art that existing trauma resuscitation units do not monitor the execution of the resuscitation process in the trauma resuscitation unit, which may affect the resuscitation effect of the patient to be resuscitated.

[0007] In this embodiment, a method for monitoring the resuscitation process in a trauma resuscitation unit is provided. The trauma resuscitation unit includes: a workspace, in which at least one first video acquisition device is provided for acquiring first field-of-view video information of at least one work area of ​​the workspace; and a server connected to the first video acquisition device. The monitoring method is applicable to the server and includes: acquiring trauma information of a person to be resuscitated; determining a corresponding preset resuscitation process based on the trauma information, the preset resuscitation process including multiple preset resuscitation sub-processes with preset time attributes; extracting the actual time attribute corresponding to the actual resuscitation sub-process from the first field-of-view video; comparing the preset time attribute with the actual time attribute to obtain a comparison result; and monitoring the resuscitation process in the trauma resuscitation unit based on the comparison result.

[0008] Optionally, extracting the actual time attribute of the actual resuscitation sub-process from the first visual field video includes: dividing the first visual field video into multiple first sub-video streams containing the actual resuscitation sub-process in real time based on preset action features in the preset resuscitation sub-process; and determining the actual time attribute of the actual resuscitation sub-process based on the first sub-video streams.

[0009] Optionally, the step of dividing the first visual field video into multiple first sub-video streams containing actual resuscitation sub-processes in real time based on preset action features in the preset resuscitation sub-process includes: identifying action features in video frames every N video frames in the first visual field video to obtain at least one actual action feature; comparing the actual action feature with at least one of preset start action features, preset key action features, and preset end action features in the preset resuscitation sub-process; when the similarity of at least one of the preset start action features, preset key action features, and preset end action features of the actual action feature is greater than a preset similarity, dividing the first visual field video based on the actual action feature to obtain the first sub-video stream corresponding to the actual resuscitation sub-process.

[0010] Optionally, the step of extracting the actual time attribute of the actual resuscitation sub-process from the first visual field video further includes: capturing the first visual field video in real time according to the preset time attribute of the preset resuscitation sub-process to obtain the second sub-video stream; extracting key frames for characterizing the actual time attribute from the second sub-video stream; and determining the actual time attribute based on the key frames characterizing the actual time attribute.

[0011] Optionally, extracting keyframes for characterizing actual time attributes in the second sub-video stream includes: identifying a second video frame in the first field-of-view video based on a preset start action, preset key action, and / or preset end action of a preset recovery process; when the similarity between the second video frame and the preset video frame is greater than a preset similarity, the second video frame is used as the keyframe characterizing actual time attributes.

[0012] Optionally, the preset resuscitation sub-process includes multiple sub-operations, and the monitoring of the resuscitation process in the trauma resuscitation unit based on the comparison results includes: determining whether the deviation between the actual time attribute and the preset time attribute of each sub-operation and / or multiple sub-operations is greater than a preset degree; when the deviation degree is greater than the preset deviation degree, it is confirmed that the actual resuscitation sub-process has an execution deviation.

[0013] Optionally, the trauma resuscitation unit includes a second video acquisition device for acquiring a second first field of view video; and upon confirming that the actual resuscitation sub-process has an execution deviation, it further includes: acquiring a first deviation video stream in the first field of view video where the deviation occurred and a second deviation video stream in the second first field of view video; identifying a first deviation event in the first deviation video stream and a second deviation event in the second deviation video stream respectively; and fusing the first deviation event and the second deviation event to obtain the actual deviation event.

[0014] Optionally, after fusing the first deviation event and the second deviation event to obtain the actual deviation event, the process includes: acquiring the vital signs data and changes in the vital signs data of the person to be resuscitated; verifying the actual deviation event based on the vital signs data and the changes in the vital signs data; determining the factors of the deviation based on the first field of view video and the second first field of view video; and determining the deviation factors based on the first field of view video stream between the sub-operations that have the deviation and / or between the sub-operations.

[0015] Optionally, after fusing the first deviation event and the second deviation event to obtain the actual deviation event, the process includes: acquiring the vital signs data and changes in the vital signs data of the person to be resuscitated; and verifying the actual deviation event based on the vital signs data and the changes in the vital signs data.

[0016] According to another aspect of this application, a monitoring system for the resuscitation process in a trauma resuscitation unit is provided. The monitoring system includes: a workspace, in which at least one first video acquisition device is provided for acquiring first field-of-view video information of at least one work area in the workspace; and a server connected to the first video acquisition device. The server is capable of executing the monitoring method for the resuscitation process in a trauma resuscitation unit as described in any of the preceding claims.

[0017] According to another aspect of this application, an electronic device is provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus, the memory is used to store a computer program, and the processor is used to execute a monitoring method for the recovery process as described in any of the preceding claims by running the computer program stored in the memory.

[0018] This application provides a method for monitoring the resuscitation process in a trauma resuscitation unit. The trauma resuscitation unit includes: a workspace, in which at least one first video acquisition device is installed to acquire first field-of-view video information of at least one work area; and a server connected to the first video acquisition device. The monitoring method is applicable to the server and includes: acquiring trauma information of a person to be resuscitated; determining a corresponding preset resuscitation process based on the trauma information, the preset resuscitation process including multiple preset resuscitation sub-processes with preset time attributes; extracting the actual time attribute corresponding to the actual resuscitation sub-process from the first field-of-view video; comparing the preset time attribute with the actual time attribute to obtain a comparison result; and monitoring the resuscitation process in the trauma resuscitation unit based on the comparison result. Through the above technical solution, the actual time attribute corresponding to the actual resuscitation sub-process is extracted from the first field-of-view video to determine the progress of the actual resuscitation process based on the first field-of-view video; the preset time attribute is compared with the actual time attribute to obtain a comparison result to confirm whether the actual resuscitation process deviates from the preset resuscitation process; and the resuscitation process in the trauma resuscitation unit is monitored based on the comparison result, thus achieving monitoring of the actual resuscitation process. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the hardware environment for a method for monitoring the resuscitation process in a trauma resuscitation unit according to an embodiment of the present invention;

[0022] Figure 2 This is a flowchart illustrating a method for monitoring the resuscitation process in a trauma resuscitation unit according to an embodiment of this application;

[0023] Figure 3 This is a structural block diagram of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] According to one aspect of the embodiments of this application, a method for monitoring the resuscitation process in a trauma resuscitation unit is provided. The trauma resuscitation unit includes: a workspace, in which at least one first video acquisition device is provided for acquiring first field-of-view video information of at least one work area of ​​the workspace; and a server connected to the first video acquisition device. The monitoring method is applicable to the server.

[0027] Optionally, in this embodiment, the above-described method for monitoring the resuscitation process in a trauma resuscitation unit can be applied to, for example... Figure 1 The hardware environment shown consists of terminal 102 and server 104.

[0028] like Figure 1As shown, server 104 is connected to terminal 102 via a network and can provide services to the terminal or clients installed on the terminal. It can set up a database on the server or independently of the server to provide data storage services for server 104, and can also be used to handle cloud services. The aforementioned network includes, but is not limited to, wide area networks (WANs), metropolitan area networks (MANs), or local area networks (LANs). Terminal 102 is not limited to PCs, mobile phones, tablets, etc. The method for monitoring the resuscitation process in a trauma resuscitation unit according to an embodiment of this application can be executed by server 104, by terminal 102, or by both server 104 and terminal 102. The terminal 102 can also execute the method for monitoring the resuscitation process in a trauma resuscitation unit according to an embodiment of this application using a client installed on it.

[0029] Taking a monitoring method for the resuscitation process in a trauma resuscitation unit as an example, which is executed by terminal 102 and / or server 104, Figure 2 This is a schematic flowchart of an optional monitoring method for the resuscitation process in a trauma resuscitation unit according to an embodiment of this application, as shown below. Figure 2 As shown, the process of this method may include the following steps:

[0030] S10. Obtain trauma information from individuals awaiting resuscitation.

[0031] For example, the trauma information of the person to be resuscitated can be determined by medical staff through questioning relevant personnel, visual observation and / or analysis of the vital signs of the person to be resuscitated as reflected by relevant instruments, or it can be determined by computer-automated questioning and answering, capturing corresponding video and image information based on the questioning and answering results and / or computer-captured and analyzed the vital signs of the person to be resuscitated as reflected by relevant instruments, etc. No specific limitation is made here.

[0032] S20. Determine the corresponding preset resuscitation process based on the trauma information. The preset resuscitation process includes multiple preset resuscitation sub-processes with preset time attributes.

[0033] A trauma resuscitation unit is a facility specifically designed for the early assessment and treatment of severely traumatized patients. It needs to meet the treatment measures required or that may be performed in the "ABCDE" systematic resuscitation process. Based on this, different trauma information can correspond to a fixed trauma resuscitation process in the trauma resuscitation unit. In this application, the fixed trauma resuscitation process is the preset resuscitation process.

[0034] It should be understood that a trauma resuscitation unit is a highly demanding and time-sensitive environment. Specifically, the resuscitation process within a trauma resuscitation unit has time-limited requirements. That is, the trauma resuscitation process includes multiple resuscitation sub-processes with at least start time requirements, end time requirements, key operation time requirements, and at least duration requirements. In this application, the multiple preset resuscitation sub-processes with preset time attributes are the aforementioned resuscitation sub-processes that include multiple start and end time node requirements and duration requirements.

[0035] In this application, the preset time attribute is a relative time attribute determined based on the start or end time of the preset resuscitation sub-process and the start time of the preset resuscitation process. That is, the preset time attribute of a certain preset resuscitation sub-process includes at least a time attribute determined by the time interval between the start time of the preset resuscitation sub-process and the start time of the resuscitation process, a time attribute determined by the time interval between the end time of the preset resuscitation sub-process and the start time of the resuscitation process, and a time attribute determined by the time interval between the critical operation time of the preset resuscitation sub-process and the start time of the resuscitation process.

[0036] S30. Extract the actual time attribute corresponding to the actual resuscitation sub-process from the first field of view video.

[0037] In order to monitor the actual recovery process, this application extracts the actual time attributes corresponding to the actual recovery sub-processes from the first-view video that can characterize the progress of the actual recovery process.

[0038] In this application, the actual time attribute is a relative time attribute determined based on the time represented by the keyframe of the actual resuscitation sub-process and the start time of the actual resuscitation process.

[0039] As one possible implementation, the first field-of-view video is divided into a first sub-video stream containing multiple actual resuscitation sub-processes in real time according to preset action features, and the actual time attributes of the actual resuscitation sub-processes are determined based on the first sub-video streams; the preset action features may be preset start action features, preset key action features and / or preset end action features.

[0040] For example, after dividing the first field-of-view video into a first sub-video stream containing multiple actual resuscitation sub-processes in real time according to the preset action features, the actual time attribute can be determined by the preset action features, which characterizes the start time, end time, or key action of the actual resuscitation sub-process. In this implementation, the actual time attribute is a relative time attribute determined by the start time, end time, or key action of the actual resuscitation sub-process and the start time of the actual resuscitation process. That is, the actual time attribute corresponding to a certain actual resuscitation sub-process includes at least the time attribute determined by the time interval between the start time of the actual resuscitation sub-process determined according to the preset start action and the start time of the actual resuscitation process, the time attribute determined by the time interval between the end time of the actual resuscitation sub-process determined according to the preset end action and the start time of the actual resuscitation process, or the time attribute determined by the time interval between the start time of the actual resuscitation sub-process determined according to the preset key action and the start time of the actual resuscitation process.

[0041] The preset time attribute is a relative time attribute determined by the start time, end time, or key action of the preset resuscitation sub-process and the start time of the preset resuscitation process. That is, the preset time attribute under the preset resuscitation sub-process corresponding to the actual resuscitation sub-process includes at least the time attribute determined by the time interval between the start time of the preset resuscitation sub-process corresponding to the actual resuscitation sub-process based on the preset start action and the start time of the preset resuscitation process, the time attribute determined by the time interval between the end time of the preset resuscitation sub-process corresponding to the actual resuscitation sub-process based on the preset end action and the start time of the preset resuscitation process, or the time attribute determined by the time interval between the start time of the preset resuscitation sub-process corresponding to the actual resuscitation sub-process based on the preset key action and the start time of the resuscitation process.

[0042] As another possible implementation, the actual time attribute is obtained by extracting the first field-of-view video according to the preset time attribute of the preset resuscitation sub-process, and then determining the second sub-video stream based on the second sub-video stream. In this implementation, the second sub-video stream is identified according to preset action features. The actual time attribute can be determined in the second sub-video stream based on the preset action features, which represent the start time, end time, or key action of the actual resuscitation sub-process.

[0043] Optionally, since staff need to sign in or prepare equipment at the start of the resuscitation process, as one possible implementation, in this application, feature recognition is performed on the staff's sign-in operation in the first field-of-view video. When all staff are identified as being in place, the time at that moment is recorded as the start time of the actual resuscitation process. As another possible implementation, feature recognition is performed on the staff's equipment preparation in the first field-of-view video. When the equipment is identified as being ready, the time at that moment is recorded as the start time of the actual resuscitation process. As yet another possible implementation, at the start of the resuscitation process, staff manually trigger the actual resuscitation process start signal. When the actual resuscitation process start signal is detected, the current moment is recorded as the start time of the actual resuscitation process.

[0044] In this application, the first video acquisition device is used to acquire first field-of-view video information of at least one working area of ​​the workspace. The first field-of-view video information can be understood as video information based on a third-person perspective, reflecting the overall progress of the resuscitation process. However, the video information may be obstructed by staff, making it difficult to accurately identify preset action features. To address this, as an exemplary embodiment, the trauma resuscitation unit further includes at least one second video acquisition device. The second video acquisition device is worn by the staff and is used to acquire second field-of-view video information of the current staff's operation information. The method for extracting actual time attributes applied to the first field-of-view video can also be applied to the second field-of-view video.

[0045] S40. Compare the preset time attribute with the actual time attribute to obtain the comparison result.

[0046] To confirm whether there is a deviation between the actual recovery process and the preset recovery process, this application compares the preset time attribute with the actual time attribute to obtain a comparison result. When the deviation between the preset time attribute and the actual time attribute is not greater than a preset level, it is confirmed that there is no execution deviation in the actual recovery process. When the deviation between the preset time attribute and the actual time attribute is greater than a preset level, it is confirmed that there is an execution deviation in the actual recovery process.

[0047] S50. Monitor the resuscitation process in the trauma resuscitation unit based on the comparison results.

[0048] In this application, when deviations occur in the actual resuscitation process, situations may arise such as staff operational errors, staff non-standard operations, and / or staff adding procedures to the resuscitation personnel. In order to achieve quality control analysis of staff in the resuscitation process based on the above situations, medical traceability of the resuscitation process, and / or further optimization of the resuscitation process, this application monitors the resuscitation process in the trauma resuscitation unit based on the comparison results.

[0049] Through steps S10 to S50, trauma information of the person to be resuscitated is obtained; based on the trauma information, a corresponding preset resuscitation procedure is determined, the preset resuscitation procedure including multiple preset resuscitation sub-procedures with preset time attributes; the actual time attribute corresponding to the actual resuscitation sub-procedure is extracted from the first field of view video to determine the progress of the actual resuscitation procedure based on the first field of view video; the preset time attribute is compared with the actual time attribute to obtain a comparison result to confirm whether there is a deviation between the actual resuscitation procedure and the preset resuscitation procedure; based on the comparison result, the resuscitation procedure in the trauma resuscitation unit is monitored, realizing the monitoring of the actual resuscitation procedure, solving the technical problem that existing trauma resuscitation units do not monitor the execution of the resuscitation procedure in the trauma resuscitation unit, which may affect the resuscitation effect of the patient to be resuscitated.

[0050] As an exemplary embodiment, the step of extracting the actual time attribute of the actual resuscitation sub-process from the visual field video includes: dividing the visual field video into multiple first sub-video streams containing the actual resuscitation sub-process in real time based on preset action features in the preset resuscitation sub-process; and determining the actual time attribute of the actual resuscitation sub-process based on the first sub-video streams.

[0051] For example, the visual field video is divided into multiple first sub-video streams containing actual resuscitation sub-processes in real time based on preset action features in the preset resuscitation sub-processes. The preset action features can be determined based on specific actions performed by the staff at the start, end, and / or key operations of the preset resuscitation sub-processes. For example, at the start of a preset resuscitation sub-process, the staff may place specific related equipment into position for the operation that is about to be performed in the preset resuscitation sub-process. The preset action feature for this preset resuscitation sub-process can be the action feature of the staff placing the specific related equipment into position. At the end of a preset resuscitation sub-process, the staff may place the specific related equipment back into its original position. The preset action feature for this preset resuscitation sub-process can be the action feature of the staff placing the specific related equipment back into its original position. At the key operation moment of a preset resuscitation sub-process, the staff may perform specific key actions for the key operation. The preset action feature for this preset resuscitation sub-process can be the action feature of the specific key action performed by the staff. In this application, the visual field video is divided into multiple first sub-video streams containing actual resuscitation sub-processes in real time based on the preset action features determined according to the preset resuscitation sub-processes.

[0052] For example, the actual time attribute of the actual resuscitation sub-process determined based on the first sub-video stream can be the actual time attribute determined according to the preset start action feature and / or preset end action in the preset action features mentioned above. For example, every N video frames in the first video stream, action features are identified to obtain at least one actual action feature. When the actual action feature satisfies the preset start action feature mentioned above, the time interval between the time of the video frame containing the actual action feature and the start time of the actual resuscitation process is determined as the actual time attribute of the actual resuscitation sub-process. At this time, the preset time attribute is the time interval between the preset time of the preset start action feature under the preset resuscitation process and the start time of the preset resuscitation process. When the actual action feature satisfies the preset end action feature mentioned above, the time interval between the time of the video frame containing the actual action feature and the end time of the actual resuscitation process is determined as the actual time attribute of the actual resuscitation sub-process. At this time, the preset time attribute is the time interval between the preset time of the preset end action feature under the preset resuscitation process and the end time of the preset resuscitation process.

[0053] For example, determining the actual time attribute of the actual resuscitation sub-process based on the first sub-video stream can be based on the actual time attribute determined according to the key actions under the first sub-video stream; for example, after dividing the actual action features into multiple first sub-video streams containing actual resuscitation sub-processes according to the actual action features satisfying preset start action features and preset end action features, the action features in the video frames are identified every N video frames in the first video stream to obtain at least one actual action feature; when the actual action feature satisfies the preset key action feature, the time interval between the time of the video frame containing the actual action feature and the start time of the actual resuscitation process is determined as the actual time attribute of the actual resuscitation sub-process, and at this time the preset time attribute is the time interval between the preset time of the preset key action feature under the preset resuscitation process and the start time of the preset resuscitation process;

[0054] For example, the actual time attribute of the actual resuscitation sub-process determined based on the first sub-video stream can be the actual time attribute determined according to other actions under the first sub-video stream; for example, after dividing the actual action features into multiple first sub-video streams containing actual resuscitation sub-processes according to the actual action features satisfying preset start action features and preset key actions, the action features in the video frames are identified every N video frames in the first video stream to obtain at least one actual action feature; when the actual action feature satisfies preset other action features, the time interval between the time of the video frame containing the actual action feature and the start time of the actual resuscitation process is determined as the actual time attribute of the actual resuscitation sub-process, and at this time the preset time attribute is the time interval between the preset time of the preset other action features under the preset resuscitation process and the start time of the preset resuscitation process.

[0055] As an exemplary embodiment, the step of dividing the visual field video into multiple first sub-video streams containing actual resuscitation sub-processes in real time based on preset action features in the preset resuscitation sub-process includes: identifying action features in video frames every N video frames in the first visual field video to obtain at least one actual action feature; comparing the actual action feature with at least one of preset start action features, preset key action features, and preset end action features in the preset resuscitation sub-process; when the similarity between the actual action feature and at least one of the preset start action features, preset key action features, and preset end action features is greater than a preset similarity, dividing the first visual field video based on the actual action feature to obtain the first sub-video stream corresponding to the actual resuscitation sub-process.

[0056] For example, after obtaining the first sub-video stream corresponding to the actual resuscitation sub-process, the actual time attribute can be determined by a preset action feature, representing the start time, end time, or key action of the actual resuscitation sub-process. In this implementation, the actual time attribute is a relative time attribute determined by the start time, end time, or key action of the actual resuscitation sub-process and the start time of the actual resuscitation process. That is, the actual time attribute corresponding to a certain actual resuscitation sub-process includes at least the time attribute determined by the time interval between the start time of the actual resuscitation sub-process determined by the preset start action and the start time of the actual resuscitation process, the time attribute determined by the time interval between the end time of the actual resuscitation sub-process determined by the preset end action and the start time of the actual resuscitation process, or the time attribute determined by the time interval between the start time of the actual resuscitation sub-process determined by the preset key action and the start time of the actual resuscitation process.

[0057] The preset time attribute is a relative time attribute determined by the start time, end time, or key action of the preset resuscitation sub-process and the start time of the preset resuscitation process. That is, the preset time attribute under the preset resuscitation sub-process corresponding to the actual resuscitation sub-process includes at least the time attribute determined by the time interval between the start time of the preset resuscitation sub-process corresponding to the actual resuscitation sub-process based on the preset start action and the start time of the preset resuscitation process, the time attribute determined by the time interval between the end time of the preset resuscitation sub-process corresponding to the actual resuscitation sub-process based on the preset end action and the start time of the preset resuscitation process, or the time attribute determined by the time interval between the start time of the preset resuscitation sub-process corresponding to the actual resuscitation sub-process based on the preset key action and the start time of the resuscitation process.

[0058] As an exemplary embodiment, the step of extracting the actual time attribute of the actual resuscitation sub-process from the visual field video further includes: real-time segmentation of the first visual field video according to the preset time attribute of the preset resuscitation sub-process to obtain the second sub-video stream; extracting key frames for characterizing the actual time attribute from the second sub-video stream; and determining the actual time attribute based on the key frames characterizing the actual time attribute.

[0059] As an exemplary embodiment, the step of extracting key frames for characterizing actual time attributes in the second sub-video stream includes: identifying a second video frame in the visual field video based on a preset start action, a preset key action, and / or a preset end action of a preset recovery process; when the similarity between the second video frame and the preset video frame is greater than a preset similarity, the second video frame is used as the key frame characterizing the actual time attributes.

[0060] Specifically, the first visual field video is captured in real time according to the preset time attribute of the preset recovery sub-process to obtain the second sub-video stream. Then, based on the preset start action, preset key action and / or preset end action of the preset recovery process, the second video frame is identified in the visual field video. When the similarity between the second video frame and the preset video frame is greater than the preset similarity, the second video frame is used as the key frame representing the actual time attribute.

[0061] In this implementation, the actual time attribute is the relative time attribute determined by the start time of the preset start action, the end time of the preset end action, or the time of the preset key action identified by the second sub-video stream, and the start time of the actual resuscitation process. That is, the actual time attribute corresponding to a certain second sub-video stream includes at least the time attribute determined by the time interval between the start time of the second sub-video stream determined by the preset start action and the start time of the actual resuscitation process, the time attribute determined by the time interval between the end time of the second sub-video stream determined by the preset end action and the start time of the actual resuscitation process, or the time attribute determined by the time interval between the time of the second sub-video stream determined by the preset key action and the start time of the actual resuscitation process.

[0062] As an exemplary embodiment, the preset resuscitation sub-process includes multiple sub-operations, and the monitoring of the resuscitation process in the trauma resuscitation unit based on the comparison results includes:

[0063] Determine whether the deviation between the actual time attribute and the preset time attribute of each sub-operation and / or multiple sub-operations is greater than the preset level; when the deviation is greater than the preset deviation level, confirm that the actual recovery sub-process has an execution deviation.

[0064] The resuscitation sub-process may include one or more sub-operations. Based on this, in order to detect the resuscitation process, it is determined whether the deviation between the actual time attribute and the preset time attribute of each sub-operation and / or multiple sub-operations is greater than the preset level.

[0065] Sub-operations in the resuscitation process typically include a start action, a key action, and an end action. Therefore, in this application, the start action, key action, and end action of a sub-operation can be used as preset operation features of the sub-operation. Then, based on the preset operation features, the actual time attribute of each actual sub-operation and the preset time attribute of the preset sub-operation can be determined. And based on the preset sub-operation corresponding to each actual sub-operation, the preset time attribute of the preset sub-operation can be determined.

[0066] For example, after identifying multiple sub-operations, the actual time attribute between the sub-operations is determined based on the actual time attribute of the preceding sub-operation determined by the end action and the start time of the following sub-operation determined by the start action, according to the timing sequence of any two consecutive sub-operations.

[0067] For example, the sub-operation can be endotracheal intubation. When starting endotracheal intubation, the staff first tilts the patient's head back while the doctor holds a laryngoscope. Then, the doctor inserts the laryngoscope into the oral cavity from the right corner of the mouth, inserts the trachea to the junction of the trachea and bronchus of the patient, and finally removes the laryngoscope. In this application, the starting action of tilting the patient's head back while the doctor holds the laryngoscope can be taken as the preset operation feature of the endotracheal intubation sub-operation, the key action of the doctor inserting the laryngoscope into the oral cavity from the right corner of the mouth or inserting the trachea to the junction of the trachea and bronchus of the patient can be taken as the key action feature of the endotracheal intubation sub-operation, and the key action of the doctor removing the laryngoscope can be taken as the ending action feature of the endotracheal intubation sub-operation.

[0068] For example, after determining the actual time attribute and the preset time attribute in the above manner, it is determined whether the deviation between the actual time attribute and the preset time attribute between each sub-operation and / or multiple sub-operations is greater than the preset degree; when the deviation degree is greater than the preset deviation degree, it is confirmed that the actual recovery sub-process has an execution deviation.

[0069] As an exemplary embodiment, the trauma resuscitation unit includes a second video acquisition device for acquiring a second visual field video; and upon confirming that the actual resuscitation sub-process has an execution deviation, it further includes: acquiring a first deviation video stream in the first visual field video where the deviation occurred and a second deviation video stream in the second visual field video; identifying a first deviation event in the first deviation video stream and a second deviation event in the second deviation video stream respectively; and fusing the first deviation event and the second deviation event to obtain the actual deviation event.

[0070] For example, the above fusion method can identify the first deviation event in the first deviation video stream and the second deviation event in the second deviation video stream according to preset action features, perform action matching, and fuse the first deviation event and the second deviation event into an actual deviation event in the deviation video stream that has the same time axis at the point where the deviation occurs based on the action matching result. For example, after fusing the first deviation event and the second deviation event to obtain the actual deviation event, the actual deviation event can be represented from multiple perspectives to realize the monitoring of the resuscitation process in the trauma resuscitation unit.

[0071] The aforementioned deviation events may be due to redundant or erroneous operations performed by staff, or they may be necessary operations performed based on changes in the condition of patients awaiting resuscitation. Therefore, it is necessary to verify these deviation events.

[0072] As an exemplary embodiment, after obtaining the deviation event, the process includes: acquiring the vital signs data of the person to be resuscitated and information on changes in the vital signs data; and verifying the actual deviation event based on the vital signs data and information on changes in the vital signs data.

[0073] For the above scheme, after a deviation event is obtained, if the vital signs data of the person to be resuscitated are outside the normal range and the change information is from vital signs data within the normal range to vital signs data outside the normal range, the deviation event is confirmed as an error operation performed by the staff; if the vital signs data of the person to be resuscitated are within the normal range and the change information is unchanged, the deviation event is confirmed as a redundant operation performed by the staff; if the vital signs data of the person to be resuscitated are within the normal range and the change information is from vital signs data outside the normal range to vital signs data within the normal range, the deviation event is confirmed as a necessary operation based on the change in the condition of the patient to be resuscitated.

[0074] When the vital signs data of a person awaiting resuscitation change, staff may need to perform operations that deviate from the preset resuscitation procedure. In this case, as an exemplary embodiment, after obtaining the vital signs data and information on changes in the vital signs data of the person awaiting resuscitation, the deviation events that occur in the resuscitation sub-procedure where deviations occur, as well as the probability of each deviation event, are predicted based on the actual vital signs data and information on changes.

[0075] For example, actual vital signs data and changes reflect the progression of a patient's condition, and these data can correspond to potential conditions that may arise. Staff will perform relevant procedures for any potential conditions that may occur, and adjustments to the resuscitation process may be necessary in response to these procedures.

[0076] In this embodiment, based on the actual vital signs data and changes of the patient to be resuscitated, a neural network model can be used to predict deviation events in or after the resuscitation sub-process where deviations occur; that is, to predict the possible condition of the resuscitated patient and the operations that the staff will perform.

[0077] Specifically, the neural network model is trained using pre-selected actual vital sign data and changes of patients to be resuscitated, as well as samples of deviation events corresponding to the actual vital sign data and changes of patients to be resuscitated. After obtaining a trained neural network model with actual prediction accuracy that meets the preset prediction accuracy, the actual vital sign data and changes are input into the trained neural network model to predict the deviation events that will occur in subsequent resuscitation sub-processes and the probability of the deviation events occurring.

[0078] For example, in a subsequent resuscitation sub-process, when the actual deviation event meets the predicted deviation event, the deviation event is confirmed as a necessary operation based on the changes in the patient's condition to be resuscitated.

[0079] As an exemplary embodiment, after obtaining the deviation event, the process includes: determining the degree of correlation between the deviation event and the vital signs data and change information; when the degree of correlation is greater than a preset degree of correlation, confirming that the deviation event is a necessary operation for the vital signs data and change information of the patient to be resuscitated, and updating the preset sub-process.

[0080] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0081] According to another aspect of this application, a monitoring system for the resuscitation process in a trauma resuscitation unit is provided. The monitoring system includes: a workspace, in which at least one first video acquisition device is provided for acquiring first field-of-view video information of at least one work area of ​​the workspace.

[0082] A server is connected to the first video acquisition device; the server is used to execute the monitoring method, the monitoring method including: acquiring trauma information of the person to be resuscitated;

[0083] Based on the trauma information, a corresponding preset resuscitation procedure is determined, which includes multiple preset resuscitation sub-procedures with preset time attributes.

[0084] Extract the actual time attribute corresponding to the actual resuscitation sub-process from the first field of view video;

[0085] The preset time attribute is compared with the actual time attribute to obtain the comparison result;

[0086] The resuscitation process in the trauma resuscitation unit is monitored based on the comparison results.

[0087] According to another aspect of the embodiments of this application, an electronic device for implementing the monitoring method of the resuscitation process in the above-described trauma resuscitation unit is also provided. The electronic device may be a server, a terminal, or a combination thereof.

[0088] Figure 3 This is a structural block diagram of an optional electronic device according to an embodiment of this application, such as... Figure 3 As shown, it includes a processor 402, a communication interface 404, a memory 406, and a communication bus 408. The processor 402, communication interface 404, and memory 406 communicate with each other via the communication bus 408.

[0089] Memory 406 is used to store computer programs;

[0090] When processor 402 executes a computer program stored in memory 406, it performs the following steps:

[0091] Based on the trauma information, a corresponding preset resuscitation procedure is determined, which includes multiple preset resuscitation sub-procedures with preset time attributes.

[0092] Extract the actual time attribute corresponding to the actual resuscitation sub-process from the first field of view video;

[0093] The preset time attribute is compared with the actual time attribute to obtain the comparison result;

[0094] The resuscitation process in the trauma resuscitation unit is monitored based on the comparison results.

[0095] Optionally, in this embodiment, the communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0096] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0097] The memory may include RAM, or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0098] The processor mentioned above can be a general-purpose processor, including but not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0099] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0100] Those skilled in the art will understand that Figure 3 The structure shown is for illustrative purposes only. The device used to implement the monitoring method of the resuscitation process in the above trauma resuscitation unit can be a terminal device, such as a smartphone (e.g., Android phone, iOS phone), tablet computer, handheld computer, mobile internet device (MID), PAD, etc. Figure 3 This does not limit the structure of the aforementioned electronic device. For example, the terminal device may also include components that are more... Figure 3 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 3 The different configurations shown.

[0101] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, ROM, RAM, disk or optical disk, etc.

[0102] According to another aspect of the embodiments of this application, a storage medium is also provided. Optionally, in this embodiment, the storage medium can be used to execute program code of the method described in any of the above embodiments.

[0103] Optionally, in this embodiment, the storage medium may be located on at least one of the network devices in the network shown in the above embodiment.

[0104] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps:

[0105] Based on the trauma information, a corresponding preset resuscitation procedure is determined, which includes multiple preset resuscitation sub-procedures with preset time attributes.

[0106] Extract the actual time attribute corresponding to the actual resuscitation sub-process from the first field of view video;

[0107] The preset time attribute is compared with the actual time attribute to obtain the comparison result;

[0108] The resuscitation process in the trauma resuscitation unit is monitored based on the comparison results.

[0109] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated in this embodiment.

[0110] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, ROMs, RAMs, portable hard drives, magnetic disks, or optical disks.

[0111] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0112] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more electronic devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0113] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0114] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0115] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the solution provided in this embodiment, depending on actual needs.

[0116] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0117] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of monitoring a resuscitation process in a trauma resuscitation unit, characterized by, The trauma recovery unit comprises a working space, at least one first video acquisition device is arranged in the working space, and is used for acquiring first visual field video information of at least one working area of the working space; a server connected with the first video acquisition device, the monitoring method is suitable for the server, and comprises the following steps: Obtaining trauma information of a person to be recovered; Determine the corresponding preset recovery process based on the trauma information, the preset recovery process comprises a plurality of preset recovery sub-processes with preset time attributes; Extracting an actual time attribute corresponding to an actual recovery sub-process in the first visual field video, comprising: real-time intercepting the first visual field video according to the preset time attribute of the preset recovery sub-process to obtain a second sub-video stream; extracting a key frame for representing an actual time attribute in the second sub-video stream; determining the actual time attribute based on the key frame representing the actual time attribute; wherein the step of extracting the key frame for representing the actual time attribute in the second sub-video stream comprises: identifying a second video frame in the first visual field video based on a preset starting action, a preset key action and / or a preset ending action of the preset recovery process; when the similarity between the second video frame and a preset video frame is greater than a preset similarity, the second video frame is taken as the key frame representing the actual time attribute; Comparing the preset time attribute with the actual time attribute to obtain a comparison result; Monitoring the recovery process in the trauma recovery unit based on the comparison result.

2. The method of claim 1, wherein the method further comprises: The step of extracting the actual time attribute of the actual recovery sub-process in the first visual field video comprises: Dividing the first visual field video into a plurality of first sub-video streams containing the actual recovery sub-process based on the preset action features in the preset recovery sub-process; Determining the actual time attribute of the actual recovery sub-process based on the first sub-video stream.

3. The method of claim 2, wherein the method further comprises: The step of dividing the first visual field video into a plurality of first sub-video streams containing the actual recovery sub-process based on the preset action features in the preset recovery sub-process comprises: Identifying action features in video frames every N video frames in the first visual field video to obtain at least one actual action feature; Comparing the actual action feature with at least one of the preset starting action feature, the preset key action feature and the preset ending action feature in the preset recovery sub-process; When the similarity between the actual action feature and at least one of the preset starting action feature, the preset key action feature and the preset ending action feature is greater than a preset similarity, dividing the first visual field video based on the actual action feature to obtain the first sub-video stream corresponding to the actual recovery sub-process.

4. The method of claim 1, wherein the method further comprises: The preset recovery sub-process comprises a plurality of sub-operations, and the step of monitoring the recovery process in the trauma recovery unit based on the comparison result comprises: Judging whether the deviation degree of the actual time attribute and the preset time attribute of each sub-operation and / or the plurality of sub-operations is greater than a preset degree; When the deviation degree is greater than the preset deviation degree, it is confirmed that the actual recovery sub-process has an execution deviation.

5. The method of claim 4, wherein the method further comprises: The trauma resuscitation unit comprises a second video acquisition device configured to acquire a second first-view video; The confirming that the actual resuscitation sub-process has an execution deviation further comprises: obtaining a first deviation video stream in the first-view video and a second deviation video stream in the second first-view video; identifying a first deviation event in the first deviation video stream and a second deviation event in the second deviation video stream, respectively; fusing the first deviation event and the second deviation event to obtain an actual deviation event.

6. The method of claim 5, wherein the method further comprises: The fusing the first deviation event and the second deviation event to obtain an actual deviation event further comprises: obtaining vital sign data of the person to be resuscitated and change information of the vital sign data; verifying the actual deviation event based on the vital sign data and the change information of the vital sign data.

7. A monitoring system of a resuscitation process in a trauma resuscitation unit, characterized by, The monitoring system comprises a working space, at least one first video acquisition device arranged in the working space and configured to acquire first-view video information of at least one working area in the working space, and a server connected with the first video acquisition device; the server is capable of executing the monitoring method of the resuscitation process in the trauma resuscitation unit according to any one of claims 1-6.

8. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein, The processor, the communication interface and the memory complete communication with each other through the communication bus, and the method comprises the following steps: The memory is configured to store a computer program; The processor is configured to execute the monitoring method of the resuscitation process according to any one of claims 1-6 by running the computer program stored in the memory.

Images