Evaluation method for cardio-pulmonary resuscitation field environment confirmation operation and related device thereof

Abstract

The invention discloses an evaluation method for cardio-pulmonary resuscitation field environment confirmation operation and a related device thereof, and relates to the technical field of computer vision. The method comprises the following steps: acquiring first body part data of a user in a target stage of cardio-pulmonary resuscitation; performing fitting operation according to a preset rule based on the time sequence position data of the hands, the arms and the shoulders in the first body part data of the user so as to determine whether the arm actions of the user are qualified or not; acquiring second body part data based on the first body part data of the user; the second body part data is the first body part data in a preset time period; and performing fitting operation based on the time sequence position data of the head in the second body part data of the user to determine whether the head action of the user is qualified or not. According to the method, whether the action of the user meets the action requirement of confirming the field environment in cardio-pulmonary resuscitation or not can be automatically judged, and dependence on manual judgment is avoided.

Description

Technical Field

[0001] The present application relates to the field of computer vision technology, and specifically to an evaluation method for confirming operations in a cardiopulmonary resuscitation scene environment and a related device thereof. Background Art

[0002] When emergency cardio-pulmonary resuscitation (CPR) is performed, the operation of "confirming the scene environment" can ensure the safety of the rescuer and avoid secondary injuries, thereby improving the success rate of cardio-pulmonary resuscitation. When the rescuer performs the "confirming the scene environment" operation, he usually needs to open his arms, turn his head left and right, and use his eyes to confirm the rescue environment.

[0003] There is no device or method in the prior art that can automatically capture and identify the recognition and judgment of the "confirming the on-site environment" operation of cardiopulmonary resuscitation. In the teaching and assessment environment, it can only be captured, identified and judged by the naked eye. In other words, the judgment of the operation of "confirming the on-site environment" in the cardiopulmonary resuscitation test in the prior art mainly depends on the experience of the examiner, and there is a certain degree of subjectivity and inconsistency. Since the examiner needs to observe the video and manually drag the progress bar, etc., not only is the accuracy low, but the assessment efficiency is also low. The method that relies on manual experience is difficult to promote and apply in an environment where there is a lack of cardiopulmonary resuscitation training experience, which also hinders the promotion and application of cardiopulmonary resuscitation, a key technology, to the vast number of inexperienced groups. Summary of the invention

[0004] The purpose of this application is to provide an evaluation method for cardiopulmonary resuscitation on-site environment confirmation operation and related devices, so as to solve the technical problems of inconsistent evaluation standards and low evaluation efficiency in the prior art of manual evaluation of the "confirmation of on-site environment" operation in cardiopulmonary resuscitation.

[0005] To achieve the above objectives, this application provides the following technical solutions:

[0006] In the first aspect, the present application proposes a technical solution for a method for evaluating a cardiopulmonary resuscitation on-site environment confirmation operation, the method comprising:

[0007] Acquire first body part data of the user at a target stage of cardiopulmonary resuscitation, the first body part data at least comprising time-series position data of the user's hands, arms, shoulders and head;

[0008] Performing a fitting operation according to a preset rule based on the time-series position data of the hand, arm and shoulder in the first body part data of the user to determine whether the arm movement of the user is qualified;

[0009] Based on the first body part data of the user, obtaining second body part data; the second body part data is the first body part data within a preset time period;

[0010] performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified;

[0011] If the user's arm movements and head movements are both qualified, then the user's cardiopulmonary resuscitation on-site environment confirmation operation is qualified.

[0012] As a specific solution in the technical solution of the present application, the fitting operation is performed according to a preset rule based on the time-series position data of the hand, arm and shoulder in the first body part data of the user to determine whether the arm movement of the user is qualified, including:

[0013] Fitting the position coordinates of the hand, arm and shoulder at the same time node to obtain multiple first fitting functions;

[0014] Based on each first fitting function, it is determined whether the user's arm movement is qualified.

[0015] As a specific solution in the technical solution of the present application, performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified includes:

[0016] The horizontal coordinate of the user's head and time form a position-time coordinate system;

[0017] Fitting the position coordinates of the eyes or ears of each user in the position-time coordinate system to form a second fitting function;

[0018] Based on the second fitting function, it is determined whether the user's head movement is qualified.

[0019] As a specific solution in the technical solution of the present application, the determining whether the user's arm movement is qualified based on each first fitting function includes:

[0020] Based on each first fitting function, each fitting straight line function is obtained; the fitting straight line function corresponds to the first fitting function one by one;

[0021] Based on the multiple first fitting functions and the corresponding fitting straight line functions, multiple first areas are obtained; the first area is the area enclosed by the first fitting function and the corresponding fitting straight line function; the first area, the first fitting function and the fitting straight line function correspond one to one;

[0022] If any of the first areas is smaller than the first threshold, the arm movement is determined to be qualified.

[0023] As a specific solution in the technical solution of the present application, if any of the first areas is smaller than the first threshold, determining that the arm movement is qualified includes:

[0024] If any first area is smaller than a first threshold, obtaining a fitting straight line function corresponding to the first area;

[0025] Based on the fitted straight line function, obtaining the horizontal angle of the fitted straight line function;

[0026] If the horizontal angle is smaller than the second threshold, the arm movement is determined to be qualified.

[0027] As a specific solution in the technical solution of the present application, the determining whether the user's head movement is qualified based on the second fitting function includes:

[0028] Based on the second fitting function, obtaining a mean straight line function;

[0029] Based on the second fitting function and the mean straight line function, a second area and a third area are obtained; the second area is the maximum area formed by the second fitting function and the mean straight line function, and the third area is the second largest area formed by the second fitting function and the mean straight line function;

[0030] If the second area and the third area are adjacent to each other and the absolute value of the difference between the second area and the third area is smaller than a third threshold, it is determined that the head movement is qualified.

[0031] As a specific solution in the technical solution of the present application, the preset time period includes a time period formed by a preset time length after a first time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified;

[0032] Or the preset time period includes a time period formed between a first time node and a second time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified; at the second time node, the arm movement is judged to be unqualified, and before the second time node, the arm movement is judged to be qualified.

[0033] In the second aspect, the present application proposes a technical solution of an evaluation device for confirming the operation of a cardiopulmonary resuscitation scene environment, the device comprising:

[0034] An acquisition module, configured to acquire first body part data of a user at a target stage of cardiopulmonary resuscitation, wherein the first body part data at least includes time-series position data of a hand, an arm, a shoulder and a head of the user;

[0035] A processing module, configured to perform a fitting operation according to a preset rule based on the time-series position data of the hand, arm and shoulder in the first body part data of the user, so as to determine whether the arm movement of the user is qualified;

[0036] And, based on the first body part data of the user, obtaining second body part data; the second body part data is the first body part data within a preset time period;

[0037] and performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified;

[0038] And, if the user's arm movements and head movements are both qualified, the user's cardiopulmonary resuscitation scene environment confirmation operation is qualified.

[0039] As a specific solution in the technical solution of the present application, the processing module is further used to fit the position coordinates of the hand, arm and shoulder at the same time node to obtain multiple first fitting functions;

[0040] And, based on each first fitting function, determining whether the user's arm movement is qualified.

[0041] As a specific solution in the technical solution of the present application, the processing module is further used to form a position-time coordinate system by combining the horizontal coordinate of the user's head and time;

[0042] and, fitting the position coordinates of the eyes or ears of each user in the position-time coordinate system to form a second fitting function;

[0043] And, based on the second fitting function, determining whether the user's head movement is qualified.

[0044] As a specific solution in the technical solution of the present application, the processing module is further used to obtain each fitted straight line function based on each first fitting function; the fitted straight line function corresponds to the first fitting function one by one;

[0045] And, based on the multiple first fitting functions and the corresponding fitting straight line functions, multiple first areas are obtained; the first area is the area enclosed by the first fitting function and the corresponding fitting straight line function; the first area, the first fitting function and the fitting straight line function correspond one to one;

[0046] And, if any one of the first areas is smaller than the first threshold, the arm movement is determined to be qualified.

[0047] As a specific solution in the technical solution of the present application, the processing module is further used to obtain a fitting straight line function corresponding to any first area if any first area is smaller than a first threshold;

[0048] And, based on the fitted straight line function, obtaining the horizontal angle of the fitted straight line function;

[0049] And, if the horizontal angle is smaller than a second threshold, the arm movement is determined to be qualified.

[0050] As a specific solution in the technical solution of the present application, the processing module is further used to obtain a mean straight line function based on the second fitting function;

[0051] And, based on the second fitting function and the mean straight line function, a second area and a third area are obtained; the second area is the maximum area formed by the second fitting function and the mean straight line function, and the third area is the second largest area formed by the second fitting function and the mean straight line function;

[0052] And, if the second area and the third area are adjacent, and the absolute value of the difference between the second area and the third area is less than a third threshold, it is determined that the head movement is qualified.

[0053] As a specific solution in the technical solution of the present application, the preset time period includes a time period formed by a preset time length after a first time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified;

[0054] Or the preset time period includes a time period formed between a first time node and a second time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified; at the second time node, the arm movement is judged to be unqualified, and before the second time node, the arm movement is judged to be qualified.

[0055] In a third aspect, the present application proposes a technical solution for an evaluation device for a cardiopulmonary resuscitation on-site environment confirmation operation, a data collector for obtaining first body part data of a user at a target stage of cardiopulmonary resuscitation, wherein the first body part data at least includes time-series position data of the user's hands, arms, shoulders, and head;

[0056] A processor, configured to perform a fitting operation according to a preset rule based on the time-series position data of the hand, arm, and shoulder in the first body part data of the user, so as to determine whether the arm movement of the user is qualified;

[0057] And, based on the first body part data of the user, obtaining second body part data; the second body part data is the first body part data within a preset time period;

[0058] and performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified;

[0059] And, if the user's arm movements and head movements are both qualified, the user's cardiopulmonary resuscitation scene environment confirmation operation is qualified.

[0060] As a specific solution in the technical solution of the present application, the processor is further used to fit the position coordinates of the hand, arm and shoulder at the same time node to obtain multiple first fitting functions;

[0061] And, based on each first fitting function, determining whether the user's arm movement is qualified.

[0062] As a specific solution in the technical solution of the present application, the processor is further used to form a position-time coordinate system by transforming the horizontal coordinate of the user's head and time;

[0063] and, fitting the position coordinates of the eyes or ears of each user in the position-time coordinate system to form a second fitting function;

[0064] And, based on the second fitting function, determining whether the user's head movement is qualified.

[0065] As a specific solution in the technical solution of the present application, the processor is further used to obtain each fitted straight line function based on each first fitting function; the fitted straight line function corresponds to the first fitting function one by one;

[0066] And, based on the multiple first fitting functions and the corresponding fitting straight line functions, multiple first areas are obtained; the first area is the area enclosed by the first fitting function and the corresponding fitting straight line function; the first area, the first fitting function and the fitting straight line function correspond one to one;

[0067] And, if any one of the first areas is smaller than the first threshold, the arm movement is determined to be qualified.

[0068] As a specific solution in the technical solution of the present application, the processor is further used to obtain a fitting straight line function corresponding to any first area if any first area is smaller than a first threshold;

[0069] And, based on the fitted straight line function, obtaining the horizontal angle of the fitted straight line function;

[0070] And, if the horizontal angle is smaller than a second threshold, the arm movement is determined to be qualified.

[0071] As a specific solution in the technical solution of the present application, the processor is further used to obtain a mean straight line function based on the second fitting function;

[0072] And, based on the second fitting function and the mean straight line function, a second area and a third area are obtained; the second area is the maximum area formed by the second fitting function and the mean straight line function, and the third area is the second largest area formed by the second fitting function and the mean straight line function;

[0073] And, if the second area and the third area are adjacent, and the absolute value of the difference between the second area and the third area is less than a third threshold, it is determined that the head movement is qualified.

[0074] As a specific solution in the technical solution of the present application, the preset time period includes a time period formed by a preset time length after a first time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified;

[0075] Or the preset time period includes a time period formed between a first time node and a second time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified; at the second time node, the arm movement is judged to be unqualified, and before the second time node, the arm movement is judged to be qualified.

[0076] In a fourth aspect, the present application further proposes a technical solution of a computer-readable storage medium. Specifically, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the evaluation method of the cardiopulmonary resuscitation scene environment confirmation operation as described in any one of the first aspects.

[0077] Compared with the prior art, the beneficial effects of this application are:

[0078] This application can automatically determine whether the user's actions meet the action requirements of "confirming the on-site environment" in cardiopulmonary resuscitation, avoiding reliance on manual judgment. And this automated evaluation method can improve response speed and accuracy, especially in the application scenario of batch automatic assessment. This application uses mathematical modeling and data processing based on human posture data. Its analysis of complex actions in "confirming the on-site environment" is more accurate, reliable and explainable, which is convenient for subsequent promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1A flowchart of a method for evaluating a cardiopulmonary resuscitation on-site environment confirmation operation proposed in an embodiment of the present application;

[0080] Figure 2 A schematic diagram of the normalized processing of the human body posture coordinate data proposed in the embodiment of the present application;

[0081] Figure 3 A schematic diagram of the position coordinates of a user's hand, arm, shoulder and head proposed in an embodiment of the present application (qualified);

[0082] Figure 4 The embodiments of this application are based on Figure 3 Schematic diagram of the first fitting function for data acquisition;

[0083] Figure 5 A schematic diagram of position coordinates of another user's hand, arm, shoulder and head proposed in an embodiment of the present application (unqualified);

[0084] Figure 6 The embodiments of this application are based on Figure 5 Schematic diagram of the first fitting function for data acquisition;

[0085] Figure 7 A schematic diagram of a position-time coordinate system formed by a user's eye horizontal coordinate and time according to an embodiment of the present application;

[0086] Figure 8 The embodiments of this application are based on Figure 7 Schematic diagram of the second fitting function for data acquisition;

[0087] Fig. 9 A schematic diagram of an evaluation device for confirming a cardiopulmonary resuscitation scene environment operation proposed in an embodiment of the present application;

[0088] Fig.10 A schematic diagram of an evaluation device for cardiopulmonary resuscitation on-site environment confirmation operation proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0089] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0090] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0091] The terms "first", "second", etc. in the specification and claims of the embodiments of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, such as the first body part data and the second body part data proposed below, which belong to different body part data. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The division of modules that appear in the embodiments of the present application is only a logical division. There may be other division methods when implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in the embodiments of the present application. In addition, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules, and some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0092] In order to solve the technical problems raised by the background technology, the embodiment of the present application proposes an evaluation method for confirming the operation of the cardiopulmonary resuscitation scene environment, specifically, Figure 1 As shown, the method includes steps S100 to S500:

[0093] Step S100: Acquire the first body part data of the user at the target stage of cardiopulmonary resuscitation.

[0094] It should be clear that the evaluation method for confirming the operation of the cardiopulmonary resuscitation site environment proposed in the embodiment of the present application has many application scenarios, which will not be described one by one in the following. For example, the evaluation method for confirming the operation of the cardiopulmonary resuscitation site environment proposed in the embodiment of the present application can not only be applied to the application scenario of the cardiopulmonary resuscitation test as described in the background technology, but also can be applied to the application scenario in which the user practices the cardiopulmonary resuscitation site environment confirmation operation, and evaluates whether the action practiced by the user is qualified, so that the user can adjust the action based on the evaluation result. Or it can also be applied to public places such as subway stations, shopping malls, schools, and restaurants, where the video cameras in the above public places shoot relevant action pictures, and the relevant action pictures are evaluated by remote or local computing devices, so as to timely warn or correct the cardiopulmonary resuscitation of critically ill users on the scene. In the subsequent embodiments of the present application, each application scenario is not listed one by one, and each embodiment is described with the application scenario of the cardiopulmonary resuscitation test.

[0095] As can be seen from the background technology, since the "confirming the on-site environment" operation in cardiopulmonary resuscitation only requires the evaluation of the user's arm and head movements, in the embodiment of the present application, the first body part data at least represents the time-series position data of the user's hands, arms, shoulders and head. That is to say, in the embodiment of the present application, it can be determined whether the user's "confirming the on-site environment" operation is qualified only by the data of the position changes of the user's hands, arms, shoulders and head over time. Of course, in other embodiments of the present application, other data can also be obtained, such as the time-series position data of the user's torso or legs.

[0096] Specifically, in the embodiments of the present application, the temporal position refers to the plane relative coordinate position and frame count of the user's body parts (for example, hands, arms, shoulders and head in the embodiments of the present application) in each frame of the image.

[0097] It should be clear that in the embodiment of the present application, the target stage of cardiopulmonary resuscitation can be the entire stage of cardiopulmonary resuscitation. That is to say, in the present embodiment, the first body part data of the user is the time-series position data of the user's hands, arms, shoulders and head in the entire stage of cardiopulmonary resuscitation. It should be noted that in the entire cardiopulmonary resuscitation process, there are many operations, such as: "confirming the scene environment", "assessing patient consciousness", "assessing patient vital signs" and "external chest compression". In the embodiment of the present application, since only the operation of the "confirming the scene environment" stage needs to be evaluated, in order to reduce the amount of data to be processed in the subsequent steps, the target stage of cardiopulmonary resuscitation can be the operation stage of "confirming the scene environment" in cardiopulmonary resuscitation. That is to say, in the present embodiment, the first body part data of the user can be the time-series position data of the user's hands, arms, shoulders and head in the "confirming the scene environment" stage.

[0098] Specifically, a stage refers to an interval in the process of development of things. In the embodiments of the present application, a stage refers to an interval from the beginning to the end of a certain operation in cardiopulmonary resuscitation. For example, the "confirming the scene environment" stage refers to the interval between the time node when "confirming the scene environment" starts and the time node when "confirming the scene environment" ends; the "assessing patient consciousness" stage refers to the interval between the time node when "assessing patient consciousness" starts and the time node when "assessing patient consciousness" ends.

[0099] In the embodiments of the present application, there is no restriction on the type of the first body part data, which may be video data, image data, or human body posture coordinate data that can be directly recognized or processed by a computer.

[0100] It should be clear that in most application scenarios, only the user's video data or picture data can be obtained. In the process of computer processing, these data need to be processed into human body posture coordinate data that can be recognized and processed by the computer. In one embodiment of the present application, the user's video data or picture data can be input into an artificial intelligence human body posture model to convert the user's video data or picture data into human body posture coordinate data that can be recognized and processed by the computer. Since this technology is a prior art, it is not described one by one. For example: Patent Publication No. CN111931701A, patent name is posture recognition method, device, terminal and storage medium based on artificial intelligence; and patent publication No. CN110781765A, patent name is a human body posture recognition method, device, equipment and storage medium patent application, both disclose similar artificial intelligence human body posture models.

[0101] Specifically, in an embodiment of the present application, the column name of the human body posture coordinate data storage can be: timestamp, node 1, the x-coordinate and y-coordinate corresponding to node 1, node 2, the x-coordinate and y-coordinate corresponding to node 2, ..., node n, the x-coordinate and y-coordinate corresponding to node n, where n is greater than or equal to 1; nodes 1 to n refer to various limbs of the user, for example: nodes 1 to n can represent the left hand, right shoulder, mouth, left eye, right elbow, etc., respectively, which will not be described one by one here. Of course, in other embodiments of the present application, the column name of the human body posture coordinate data storage can be set according to one's own needs.

[0102] It should be clear that in the embodiments of the present application, the x-coordinate and y-coordinate of each node may be the actual coordinate value of the node in the image. For example, in one embodiment of the present application, the pixels of an image are 1024*1024, that is, the height of the image is 1024 pixels and the width is also 1024 pixels. In the image, the actual coordinates of the user's left hand are (512,512), and in this embodiment, the coordinates of the node corresponding to the user's left hand are (512,512).

[0103] It should be clear that in image recognition, different evaluation indicators (i.e., different features in the feature vector, that is, the different evaluation indicators) often have different dimensions and dimensional units, which will affect the results of data analysis. In order to eliminate the dimensional influence between indicators, data standardization is required to solve the comparability between data indicators. After the original data is processed by data standardization, each indicator is in the same order of magnitude, which is suitable for comprehensive comparative evaluation. Among them, the most typical is the normalization of data. In short, the purpose of normalization is to limit the pre-processed data to a certain range (such as [0,1] or [-1,1]), so as to eliminate the adverse effects caused by singular sample data. For example, in an embodiment of the present application, even if the actions and postures of the users in the image are exactly the same, if the distances of different users from the camera are different, resulting in the inconsistent sizes occupied by the users themselves in the image, the coordinates of the same nodes will be inconsistent, which will cause the subsequent results to be greatly affected by the singular sample data and inaccurate.

[0104] In one embodiment of the present application, in order to improve the accuracy of subsequent processing results. In the embodiment, the x-coordinate and y-coordinate of each node can be the coordinates of the node in the image after the coordinates are standardized. Specifically, in the present embodiment, the x-coordinate and y-coordinate of the node can be (img_x, img_y), where img_x is the actual coordinate x of the current node divided by the width of the current image; img_y is the actual coordinate y of the current node divided by the height of the current image. From the above, it can be seen that if the actual coordinates of the user's left hand are (512, 512), the coordinates after standardized processing are (0.5, 0.5). In this embodiment, the coordinate format of each node after standardized processing is as follows Figure 2 shown.

[0105] Specifically, in the embodiments of the present application, the following is formed: Figure 2The method of directly recognizing or processing human body posture coordinate data in the format shown by a computer is as follows: after generating the human body posture timestamp and the coordinate points of different parts, the generated files are processed in batches within a time period through a timer. Among them, it is necessary to open the file, read the data of each line in the file, and obtain the total number of lines. Traverse the total number of lines of the file, obtain the data line of each line, and use regular expressions to extract the timestamp, x-axis and y-axis coordinate points. The expression corresponding to the file is:

[0106] (\d+:\d+\.\d+),x=([\d.]+)y=[\d.]+)

[0107] It should be clear that in this embodiment, if Figure 2 As shown, the correspondence between the joint point number no and the file in the known artificial intelligence human posture model is known. It is known that the first column is time t, and then each joint point coordinate is composed of "joint point number", "x-axis coordinate" and "y-axis coordinate".

[0108] As can be seen from the foregoing, in order to reduce the amount of data to be processed subsequently, the video data belonging to the stage of "confirming the on-site environment" can be selected in advance from the video data of the entire stage of cardiopulmonary resuscitation in the foregoing text, and processed by the artificial intelligence human posture model to obtain the human posture coordinate data of the user at the stage of "confirming the on-site environment", thereby reducing the amount of data to be processed in the subsequent steps. In some application scenarios, the human posture coordinate data of the user at each stage of cardiopulmonary resuscitation is required, then the video data of the entire stage of cardiopulmonary resuscitation can be input into the artificial intelligence human posture model to obtain the human posture coordinate data of the user at the entire stage of cardiopulmonary resuscitation. After obtaining the human posture coordinate data of the user at the entire stage of cardiopulmonary resuscitation, in order to reduce the amount of data to be processed in the subsequent steps, the human posture coordinate data of the user at the stage of "confirming the on-site environment" can be selected from the human posture coordinate data of the user at the entire stage of cardiopulmonary resuscitation. For example, in an embodiment of the present application, it can be determined which data belongs to the human posture coordinate data of the stage of "confirming the on-site environment" according to time division. Generally, it takes 5 to 10 seconds to complete the action of the stage of "confirming the on-site environment", so all the human body posture coordinate data between 0 seconds and m seconds can be defaulted to the human body posture coordinate data belonging to the stage of "confirming the on-site environment", where m can be any value greater than 0 and less than or equal to 10. Of course, in other embodiments of the present application, the time interval for selecting the human body posture coordinate data can be set according to the time period in which the action of the stage of "confirming the on-site environment" is completed. For example, during the examination process, the time period in which all users (that is, candidates) complete the action of the stage of "confirming the on-site environment" is between 1 hour 10 seconds and 1 hour 20 seconds, then only the human body posture coordinate data of users in this time period can be retrieved.

[0109] Specifically, in this embodiment, we will insert the start frame index ready into the human body posture coordinate data obtained in the "confirming the scene environment" stage above. bgn and end frame index ready end Finally, the coordinate point array of the "confirmation of the on-site environment" stage is obtained. arr , which is expressed as follows:

[0110] ready arr =lines arr [ready bgn :ready end ]

[0111] Step S200: performing a fitting operation according to preset rules based on the time-series position data of the hand, arm and shoulder in the first body part data of the user to determine whether the arm movement of the user is qualified.

[0112] It should be clear that in the process of "confirming the on-site environment", the user generally needs to raise the arm that is perpendicular to the horizontal plane to be parallel to the horizontal plane (that is, stretch the arms straight), rotate the head left and right to confirm whether the environment is safe, and then lower the arm that is parallel to the horizontal plane to be perpendicular to the horizontal plane. In the embodiment of the present application, if the user has the action of stretching both arms straight, it can be considered that the user's arm action is qualified. If the coordinate point array ready is traversed arr , and no arms straightening action is found, it can be considered that the user's arm action is unqualified.

[0113] It should be clear that in the embodiment of the present application, the main purpose of fitting the time-series position data of the user's hands, arms and shoulders is to determine whether the user has a double-arm straightening action. In the embodiment of the present application, any preset rule (i.e., any function, such as: the n-order polynomial function, the first straight line function and the second straight line function, the fitting straight line function hereinafter) can be used to fit the time-series position data of the user's hands, arms and shoulders to determine whether the user's arm action is qualified.

[0114] In one embodiment of the present application, an n-order polynomial function may be used to fit the time series position data of the user's hand, arm, and shoulder to obtain a first fitting function, wherein n is a positive integer greater than or equal to 2. Specifically, in this embodiment, step S200, based on the time series position data of the hand, arm, and shoulder in the first body part data of the user, performs a fitting operation according to a preset rule to determine whether the user's arm movement is qualified, includes steps S210 to S220:

[0115] Step S210: Fitting the position coordinates of the hand, arm and shoulder at the same time node to obtain a plurality of first fitting functions.

[0116] like Figure 3 As shown, Figure 3 Schematic diagram of the position coordinates of the user's hand, arm, shoulder and head at the time node 11:45:41:670 microseconds, where each star-shaped point represents a body part of the user. Figure 3 In order to clearly display the coordinates of each part of the user's body, Figures 4 to 6 In the present invention, each body part is no longer marked and described, and those skilled in the art can Figure 3 By performing a one-to-one comparison, the body part of the user represented by each point in other figures is determined.

[0117] It is easy to understand that in Figure 3In the embodiment of the present application, the hand position is the position of the middle of the user's hand (e.g., the palm); the arm position is the position of the user's elbow joint; and the shoulder position is the position of the user's shoulder joint. In other embodiments of the present application, the hand position may be one or more of the positions of the tip, middle, or wrist of the hand; the arm position may be one or more of the positions of the middle of the upper arm, middle of the forearm, or elbow. In actual applications, the appropriate hand position, arm position, shoulder position, and head position may be selected according to actual needs, which will not be described in detail later.

[0118] Depend on Figure 3 It can be seen that Figure 3 This is a schematic diagram of the position coordinates of the user's hand, arm, shoulder and head at the time node 11:45:41:670 microseconds. Figure 3 The position coordinates of the user's hands, arms, and shoulders in the , can show whether the user's arms are stretched out at the time point of 11:45:41:670 microseconds. It is easy to understand that if the user's arms are stretched out, the user's two arms can be regarded as an approximate straight line, that is, if Figure 3 If the line connecting the right hand position coordinates, right arm position coordinates, right shoulder position coordinates, left shoulder position coordinates, left arm position coordinates and left hand position coordinates in the figure can be approximated to a straight line, it can be determined that the user's arm movement is qualified. In the embodiment of the present application, we can adopt the method of obtaining the fitting function of each of the above points to determine whether the user's arm is straight (that is, whether the arm movement is qualified) through the fitting function.

[0119] It should be clear that the coordinate point array obtained in the "confirming the on-site environment" stage above is ready arr Each row of data represents the user's action posture at a time node, that is, through the coordinate point array ready arr Each row of data in can be obtained as follows Figure 3 A schematic diagram of the position coordinates of the user's hands, arms, shoulders and head is shown.

[0120] In the embodiment of the present application, based on the coordinate point array ready arr The actual steps to obtain multiple first fitting functions are as follows:

[0121] Traversing ready arr For all the rows in the ith loop, the ith group of data line=ready_arr[i] is obtained, where i is a positive integer greater than or equal to 1.

[0122] Create the coordinate array X of the torso and upper limbs (i.e. hands, arms, shoulders) arr and Y arr , traverse ready arr, and operate on each line, the process is as follows:

[0123] Take the x-axis coordinate of the left upper limb, the x-axis coordinate of the right upper limb, the x-axis coordinate of the left part of the torso, and the x-axis coordinate of the right part of the torso, and insert their tails into the array X arr , which is composed as follows:

[0124] X arr =LX arr +RX arr +BodyX arr [LS]+BodyX arr [RS]

[0125] Among them, LX arr An array of multiple joints on the x-axis of the left upper limb, RX arr An array of multiple joints on the x-axis of the right upper limb, BodyX arr [LS] is the array of multiple joint points on the x-axis of the left part of the torso, BodyX arr [RS] is an array of multiple joint points on the x-axis of the right part of the torso.

[0126] Take the y-axis coordinate of the left upper limb, the y-axis coordinate of the right upper limb, the y-axis coordinate of the left part of the torso, and the y-axis coordinate of the right part of the torso, and insert their tails into the array Y arr , which is composed as follows:

[0127] Y arr =LY arr +RY arr +BodyY arr [LS]+BodyY arr [RS]

[0128] Among them, LY arr is an array of multiple joints on the y axis of the left upper limb, RY arr BodyY is an array of multiple joints on the y axis of the right upper limb. arr [LS] is the array of multiple joint points on the y-axis of the left part of the torso, BodyY arr [RS] is an array of multiple joint points on the y-axis of the right part of the torso.

[0129] Specifically, in one embodiment of the present application, using X arr and Y arr Perform n-order polynomial fitting to obtain the fitting function. The process is as follows:

[0130] y fit1 =Polyfit(X arr , Y arr , n)

[0131] Among them, y fit1 Yes X arr and Y arr The nth-order fitting polynomial of is used to evaluate the standardness of the posture, where n is a positive integer greater than or equal to 2.

[0132] Specifically, Figure 4 As shown, through the n-order polynomial fitting function Figure 3 The coordinates of each upper limb of the user (that is, the position coordinates of the user's hand, arm, and shoulder) are fitted, and the first fitting function obtained is as follows: Figure 4 As shown by the green dashed line in Figure 6 As shown, through the n-order polynomial fitting function Figure 5 The first fitting function is obtained by fitting the coordinates of each upper limb of the user. Figure 6 As shown by the green dashed line in .

[0133] Step S220: Based on each first fitting function, determine whether the user's arm movement is qualified.

[0134] As we can see from the previous text, in "Confirming the on-site environment", the user generally needs to raise the arm that is perpendicular to the horizontal plane to be parallel to the horizontal plane, rotate the head left and right to confirm whether the environment is safe, and then lower the arm that is parallel to the horizontal plane to be perpendicular to the horizontal plane. This process is a dynamic process. If one of the user's actions meets the standard, it can be assumed that the user's arm action in the "Confirming the on-site environment" operation is qualified. In other words, the coordinate point array ready in the above text arr If the user's arms in any row of data (i.e., any time node) are in a straight state, that is, the arms are parallel to the horizontal plane, then the user's arm movement can be considered qualified. In other words, if any first fitting function among the multiple first fitting functions obtained represents that the user's arms are in a straight state, then the user's arm movement can be considered qualified.

[0135] It should be clear that in the embodiment of the present application, it is necessary to traverse each first fitting function in turn to determine whether the user's arm is in a straight state, that is, to determine whether the user's arm movement is qualified. arr Instead of enumerating and judging the multiple first fitting functions obtained in the embodiment of the present application one by one, an embodiment of judging the user's arm movement to be qualified based on the first fitting function is listed exemplarily in the embodiment of the present application. Figure 3 and Figure 4 As shown; and an embodiment of determining that the user's arm movement is unqualified based on the first fitting function is listed, the embodiment is as follows Figure 5 and Figure 6 shown.

[0136] In an embodiment of the present application, it is possible to use any method to determine whether the user's arm movement is qualified based on the first fitting function. For example, in one embodiment of the present application, it is possible to determine whether the user's arm movement is qualified based on the fit of the first fitting function. Specifically, the fit is the degree of fit between the predicted result of the characterization function model and the actual result. In the present embodiment, the function forming the first fitting function is an n-order polynomial function (i.e., a curve function), that is, in the present embodiment, the higher the fit of the first fitting function, the more the coordinates of each joint point of the user's upper limb (i.e., both arms) are in a curved state, that is, the higher the bending degree of the user's upper limb. In other words, the higher the fit, the more bent the user's upper limb is, that is, the more irregular the user's arm movement is; the lower the fit, the straighter the user's upper limb is, that is, the more standardized the user's arm movement is. In another embodiment of the present application, it is also possible to determine whether the user's arm movement is qualified based on the fit of the first fitting function by the following steps. Specifically, in the present embodiment, step S220, based on each first fitting function, determines whether the user's arm movement is qualified, including steps S221 to S223:

[0137] Step S221: Based on each first fitting function, each fitting straight line function is obtained, and the fitting straight line function corresponds to the first fitting function one by one.

[0138] Specifically, Figure 4 As shown, Figure 4 The position coordinates of the user's hand, arm, and shoulder are fitted with a straight line (also known as linear fitting), and the resulting straight line is as follows Figure 4 As shown by the red dotted line in Figure 6 As shown, Figure 6 The position coordinates of the user's hand, arm, and shoulder are fitted with a straight line. Figure 6 As shown by the red dotted line in FIG. In this embodiment, the expression of the fitting straight line function is as follows:

[0139] y fit2 =c 1 x+c 0

[0140] Among them, c 0 and c 1 is the coefficient obtained from the straight line fit, y fit2 It is a fitted straight line function formed by the upper limbs, which can be used to evaluate the horizontal angle between the user's arms and the horizontal plane (ie, the ground) after they are stretched out.

[0141] Step S222: Acquire a plurality of first areas based on a plurality of first fitting functions and corresponding fitting straight line functions.

[0142] Specifically, in this embodiment, the first area is the area enclosed by the first fitting function and the corresponding fitting straight line function, that is, Figure 4 and Figure 6 The area of ​​the middle gray area. The first area, the first fitting function and the fitting straight line function correspond one to one.

[0143] In this embodiment, the calculation method of the first area is as follows:

[0144] Calculate the x-axis coordinate value range of the first fitting function, and its expression is as follows:

[0145] X min =min(X arr ), X max =max(X arr )

[0146] Among them, X min refers to the array X arr The minimum value in X max refers to the array X arr The maximum value in .

[0147] Calculate y fit1 and fit2 In the specified interval [X min ,X max ], and we get the result x1 and result x2 , specifically, its expression is as follows:

[0148]

[0149]

[0150] Result x1 and result x2 Perform definite integral difference calculation to get the result integral diff (Also the first area):

[0151] integral diff =|result x1 -result x2 |

[0152] Specifically, in this application Figure 4 In the embodiment of the present invention, the first area is 0.0011. Figure 6 In the embodiment, the first area is 0.0134.

[0153] Step S223: If any one of the first areas is smaller than the first threshold, the arm movement is determined to be qualified.

[0154] As can be seen from the foregoing, in the embodiment of the present application, the "confirmation of the on-site environment" determines whether the arm movement is qualified based on whether the user's arms are straight when they are opened. In other words, if the user's arms are not straight, the arm movement is determined to be unqualified; if the user's arms are straight, the arm movement is determined to be qualified.

[0155] It is easy to understand that in this embodiment, the first area is the area formed by the first fitting function and the corresponding fitting straight line function. If the user's arms are stretched straighter, the first fitting function is closer to the straight line, that is, the first fitting function is closer to the corresponding fitting straight line function. In other words, if the user's arms are stretched straighter, the area formed by the first fitting function and the corresponding fitting straight line function (that is, the first area) is smaller. Therefore, in this embodiment, it can be determined based on the size of the first area whether the user's arms are stretched straight, that is, whether the arm movement is qualified.

[0156] Specifically, in an embodiment of the present application, the user posture corresponding to the first area being less than the first threshold value can be judged as a qualified arm movement. If each first area is greater than the first threshold value, it can be considered that the user's arm movement is unqualified during the entire "confirming the on-site environment" process. In the present embodiment, the first threshold value can be an empirical value obtained through a large number of experimental verifications. Of course, the first threshold value can be set based on the action standard. In the application scenario of the present application for teaching, the severity of the teaching can be controlled by adjusting the first threshold value (the second threshold value and the third threshold value below are similar), that is, the smaller the first threshold value, the straighter the user's arm is required to be stretched.

[0157] In a specific embodiment of the present application, the first threshold value may be greater than or equal to 0.001 and less than or equal to 0.005. Specifically, the first threshold value may be any value among 0.001, 0.002, 0.003, 0.004 and 0.005, or any value between two adjacent values ​​mentioned above.

[0158] It is easy to understand that in the embodiment of the present application, the first fitting function is mainly used to determine whether the user has the action of stretching and straightening both arms, so as to determine whether the user's arm action is qualified in the process of "confirming the on-site environment". That is to say, in the embodiment of the present application, the first fitting function can be any curve function that can implement the above method.

[0159] In one embodiment of the present application, the graph formed by the first fitting function can be formed by splicing a first broken line (i.e., formed by some line segments in the first straight line function) and a second broken line (i.e., formed by some line segments in the second straight line function) (not shown in the figure), that is, the fitting function can be composed of two straight line functions. Specifically, the first straight line function is a straight line function formed by fitting the coordinates of the user's right hand, right arm, and right shoulder; the second straight line function is a straight line function formed by fitting the coordinates of the user's left hand, left arm, and left shoulder. In this embodiment, the first broken line can be a straight line function in the first straight line function that is located in the interval [0, x m ) part; the second broken line can be located in the interval [x m , 1] part. Among them, the intersection point of the first straight line function and the second straight line function is (x m ,y m ). Based on the principle similar to the above, the first straight line function, the second straight line function and y fit2 (ie, the fitted straight line function) is the first area. In this embodiment, it is also possible to determine whether the user's arm is straight based on the size of the first area, that is, to determine whether the arm movement is qualified, which will not be described in detail here.

[0160] In another embodiment of the present application, y fit2 (i.e., the fitted straight line function) can be directly used as the first fitting function. It is easy to understand that the first fitting function is mainly used to determine whether the user's arm is straight. fit2 is a straight line, so we can fit2 The degree of fit directly determines whether the user's arm is straight, that is, whether the arm movement is qualified. It is easy to understand that the straighter the user's arm is stretched, the better the y fit2 The higher the fitting degree, the better. fit2 The lower the fit.

[0161] It should be clear that in most application scenarios, as long as the user has the action of straightening his arm, it can be assumed that the user's arm action is qualified in the process of "confirming the on-site environment". However, in order to further standardize the arm action, it is also necessary to determine whether the user keeps the arm horizontal during the process of straightening the arm, that is, whether the arm is parallel to the horizontal plane (that is, the ground).

[0162] In order to further standardize the evaluation of arm movements, in one embodiment of the present application, in step S223, if any of the first areas is smaller than the first threshold, determining that the arm movement is qualified includes:

[0163] Step S224: If any first area is smaller than the first threshold, a fitting straight line function corresponding to the first area is obtained.

[0164] Specifically, Figure 4 As shown, Figure 4 The first area in is less than the first threshold, then obtain Figure 4 Relative to the fitted straight line function (ie y fit2 , Figure 4 The red straight line).

[0165] Step S225: Based on the fitted straight line function, the horizontal angle of the fitted straight line function is obtained.

[0166] As can be seen from the above, the fitted straight line function itself can represent the state of the user's arm extension, and the horizontal angle of the fitted straight line function can be converted based on the slope of the fitted straight line function. Figure 4 As shown, Figure 4 The corresponding horizontal angle of the fitting straight line function is 0.75°.

[0167] In this embodiment, the fitting straight line function (ie, y fit2 ) is calculated as follows:

[0168] The horizontal angle of the fitted straight line function is its slope In X arr The arc tangent of the minimum value is expressed as follows:

[0169]

[0170] Step S226: If the horizontal angle is less than the second threshold, the arm movement is determined to be qualified.

[0171] It is easy to understand that in this embodiment, if the horizontal angle is smaller, it means that the user's outstretched arm is closer to the parallel horizontal plane. Specifically, in this embodiment, the second threshold value can be an empirical value obtained through a large number of experimental verifications. Of course, the second threshold value can also be set based on the action standard.

[0172] In a specific embodiment of the present application, the second threshold value may be greater than or equal to 7° and less than or equal to 15°. Specifically, the second threshold value may be any one of 7°, 8°, 9°, 10°, 11°, 12°, 13°, 14° and 15°, or any degree between two adjacent degrees.

[0173] As can be seen from the foregoing, the user usually needs to open his arms and rotate his head left and right to confirm the rescue environment by looking at his eyes when "confirming the on-site environment". That is to say, after completing the determination of the user's arm movement in this application, the user's head movement also needs to be determined. In the embodiment of this application, whether the user's movement of rotating his head left and right is qualified can be determined directly based on the user's first body part data.

[0174] As can be seen from the foregoing, "confirming the on-site environment" is a dynamic process. Generally, the dynamic process is that the user raises the arm that is perpendicular to the horizontal plane to be parallel to the horizontal plane, rotates the head left and right, confirms whether the environment is safe, and then lowers the arm that is parallel to the horizontal plane to be perpendicular to the horizontal plane. In other words, during the process of the user rotating his head left and right, the user's arm movement remains straight, that is, the user's arm movement is in a qualified state. In other words, in an embodiment of the present application, data for the time period in which the user's arm movement remains straight can be extracted from the user's first body part data to reduce the amount of data processing in subsequent steps. Therefore, in one embodiment of the present application, the method further includes step S300: based on the user's first body part data, obtaining second body part data; the second body part data is the first body part data within a preset time period.

[0175] As can be seen from the foregoing, in this embodiment, the preset time period is the time period in which the user's arm movement remains in a straight state. That is to say, the preset time period can be the time period formed between the first time node and the second time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified; at the second time node, the arm movement is judged to be unqualified, and before the second time node, the arm movement is judged to be qualified. It should be clear that in this embodiment, it is necessary to traverse the coordinate point array ready arr Only by checking all the data in the table can we get the first time node and the second time node.

[0176] In order to further reduce the amount of data processing, in one embodiment of the present application, the preset time period can be a time period formed by a preset time length after a first time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified. Or the preset time period can be a time period formed by a preset time length before a second time node; at the second time node, the arm movement is judged to be unqualified, and before the second time node, the arm movement is judged to be qualified. Since the action of rotating the head left and right can be completed within a fixed time period, the preset time period can be equal to the fixed time period. For example, the fixed time period can be any time period between greater than or equal to 2 seconds and less than or equal to 5 seconds. Since this method only needs to obtain the first time node or the second time node, there is no need to traverse the coordinate point array ready arr All the data in the system can reduce the amount of data processing.

[0177] Step S400: performing a fitting operation based on the temporal position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified.

[0178] It should be clear that in the head movement of "confirming the scene environment", since the head only needs to move left and right, and does not need to move up and down, it is only necessary to measure the x coordinate of the head to determine whether the user has performed the correct head movement. In this embodiment, the movement of the head can be determined based on any feature in the head, such as through the user's ears, eyes, or eyebrows. In the embodiments of the present application, it is impossible to describe all the above embodiments one by one, and the method proposed in the present application will be described later based on the change of the user's eye coordinates over time.

[0179] Specifically, in this embodiment, create an array time eye , array LEyeX and array REyeX. Among them, time eye Used to store the time nodes (frame counts) of the user's eye activities, LEyeX is used to store the x-axis coordinates of the user's left eye, and REyeX is used to store the x-axis coordinates of the user's right eye.

[0180] In this embodiment, the array time eye The representation is as follows:

[0181] time eye =[i 1 ,i 2 ...i k ],k∈[min(time eye ), max(time eye )]

[0182] Among them, min(time eye ) is the first time node in the above text, max(time eye ) The second time node in the above text, i k Array ready arr The corresponding frame number in .

[0183] In this embodiment, the array LEyeX is represented as follows:

[0184] LEyeX=[lx 1 , lx 2 ...lx k ],k∈[min(time eye ), max(time eye )]

[0185] Among them, lx k Array readyarr Corresponding to i k The x-axis coordinate value of the user's left eye in the frame.

[0186] In this embodiment, the array REyeX is represented as follows:

[0187] REyeX=[rx 1 , rx 2 ...rx k ],k∈[min(time eye ), max(time eye )]

[0188] Among them, rx k Array ready arr Corresponding to i k The x-axis coordinate value of the user's right eye in the frame.

[0189] In an embodiment of the present application, whether the user's head movement is qualified can be determined by any method based on the above data.

[0190] In a specific embodiment of the present application, step S400, performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified includes steps S410 to S430:

[0191] Step S410: The horizontal coordinate of the user's eye and time form a position-time coordinate system.

[0192] Specifically, in order to enable those skilled in the art to clearly understand the technical principles of the method of the embodiment of the present application, as follows Figure 7 As shown, through the array time eye , array LEyeX and array REyeX construct a new coordinate system, with array time eye The frame number in the array is used as the new x-axis, and the x-axis coordinate values ​​in the array LEyeX and array REyeX are used as the new y-axis. Among them, the new coordinate points corresponding to the array LEyeX are as follows: Figure 7 As shown by the red star in the figure; the coordinate points corresponding to the array REyeX are as follows Figure 7 As shown by the blue star in the figure.

[0193] It is easy to understand that in other embodiments of the present application, the array time eye The frame number in the array is used as the new y-axis, and the x-axis coordinate values ​​in the array LEyeX and the array REyeX are used as the new x-axis. No further details will be given later.

[0194] Step S420: Fit the coordinates of each eye position of the user in the position-time coordinate system to form a second fitting function. In other embodiments of the present application, the second fitting function can be obtained directly based on the array LEyeX or the array REyeX. Of course, other types of arrays can also be obtained to obtain the second fitting function. In the embodiment of the present application, other types of arrays can be the distance array between the left eye coordinates and the right eye coordinates of the user (the obtained second fitting function is as follows: Figure 8 ), an array of the distance between the user's left eye coordinates and the left ear coordinates, an array of the user's left ear coordinates, an array of the user's right ear coordinates, etc., which are not described one by one here.

[0195] In the embodiments of the present application, it is impossible to describe all embodiments that can form the second fitting function. The following describes the method of forming the second fitting function of the present application by taking the change of the mean values ​​of the left eye coordinates and the right eye coordinates of the user over time.

[0196] Specifically, in this embodiment, the mean array mean of the user's left eye coordinates and right eye coordinates is calculated. y , mean array mean y The expression is as follows:

[0197] mean y =(LEyeX+REyeX) / 2

[0198] Mean array mean y The coordinate points included are Figure 7 As shown at the intersection of each black broken line in the figure, the coordinate point represents the movement coordinate of the center position of the left eye and the right eye of the user's head.

[0199] In this embodiment, the mean array mean y The coordinate points contained in are fitted to obtain the second fitting function. The second fitting function is as follows: Figure 7 As shown by the green dashed line in .

[0200] Specifically, for the mean array mean y The process of fitting the coordinate points contained in is as follows:

[0201] Y fit (x) = Polyfit(time eye ,mean y , n)

[0202] The above formula uses the fitting function algorithm to calculate time eye and mean yPerform polynomial fitting, n represents the order of fitting, n can be any positive integer greater than or equal to 2, Y fit (x) is the fitted polynomial function, and the graph of this function is as follows: Figure 7 As shown by the green dashed line in fit (x) can also be written as follows:

[0203] Y fit (x) = a n x n +a n-1 x n-1 +...+a 2 x 2 +a 1 x+a 0

[0204] For function Y fit (x) performs a first-order derivative, and the effect is as follows:

[0205] Y′ fit (x) = n n x n-1 +(n-1)a n-1 x n-2 +...+2a 2 x+a 1

[0206] Let Y′ fit (x) = 0, that is:

[0207] na n x n-1 +(n-1)a n-1 x n-2 +...+2a 2 x+a 1 =0

[0208] Solving the equation, we can get the extreme point x-axis array XPS = [x 1 ,x 2 ,...,x t ], t is any positive integer greater than or equal to 2. Since the range of the above numerical solution is not necessarily within the specified time range, it is necessary to filter the solution results to obtain the array after the extreme point x-axis is filtered. The filtering method is as follows:

[0209] xPs=xPs[(max(time eye )>XPS) / \(XPS>min(time eye ))]

[0210] Substitute the filtered array XPS into the function Y fit(x), after solving, we can get the y-axis extreme value array YPS=[y 1 ,y 2 ,...,y z ], z is any positive integer greater than or equal to 2. Specifically, each coordinate point in the array YPS, such as Figure 7 As shown by the green star in the figure.

[0211] Step S430: Based on the second fitting function, determine whether the user's head movement is qualified.

[0212] Specifically, in an embodiment of the present application, any method can be used based on the second fitting function to determine whether the user's head movement is qualified. For example, the degree of fit of the second fitting function can be used as described below to determine whether the user's head movement is qualified. In one embodiment of the present application, a mean straight line function can also be introduced to determine whether the user's head movement is qualified.

[0213] Specifically, step S430, based on the second fitting function, determining whether the user's head movement is qualified includes steps S431 to S433:

[0214] Step S431: Based on the second fitting function, obtain a mean straight line function.

[0215] Specifically, the method for obtaining the mean straight line function is as follows:

[0216] Find the mean of the array YPS The results are as follows:

[0217]

[0218] Known and function Y fit (x), To move an item, the process is as follows:

[0219]

[0220] In the embodiment of the present application, it is known that the fitting function Y fit (x) is a high-order polynomial, then the function can be solved and finally the function is obtained. You can get multiple solutions (that is, multiple coordinate points), multiple coordinate points such as Figure 7 The intersection of the brown straight line and the green dotted line. The x-axis results of the above multiple coordinate points are formed into an array xxs, and the y-axis results of the above multiple coordinate points are formed into an array yys, where The length of the yys array is the same as that of the xxs array.

[0221] It is easy to understand that in the embodiment of the present application, the array mean y Find the mean to get the average I won’t go into details here.

[0222] Given arrays xxs and yys, for adjacent data points (x i ,y i ) and (x i+1 ,y i+1 ), construct the mean straight line function line(x), specifically, the mean straight line function formula is as follows:

[0223] line(x)=c 1 x+c 0

[0224] Step S432: Based on the second fitting function and the mean straight line function, obtain a second area and a third area; the second area is the maximum area formed by the second fitting function and the mean straight line function, and the third area is the second largest area formed by the second fitting function and the mean straight line function.

[0225] Specifically, in this embodiment, an area array areas is created, consisting of Figure 7 It can be seen that the second fitting function and the mean straight line function form a plurality of area regions. First, obtain the second fitting function and the mean straight line function in [min(time eye ), max(time eye )] within the range of all intersection points (x i ,y i ), where the intersection point (x i ,y i )like Figure 7 The red dots in the figure show that an area can be obtained between the adjacent intersection points of the second fitting function and the mean straight line function, as shown in Figure 7 As shown, the second fitting function and the mean straight line function form four intersection points, that is, the second fitting function and the mean straight line function form three area regions.

[0226] Assume that the area enclosed by the second fitting function and the mean straight line function is located at the data point (x i ,y i ) and data points (x i+1 ,y i+1 ), the area of ​​the region can be calculated as follows:

[0227] Calculate the function corresponding to the second fitting function and the function corresponding to the mean straight line function in the interval [x i ,x i+1], that is, to calculate the definite integral of the function Y fit The definite integral of (x) and the function line(x) is calculated as follows:

[0228]

[0229] Calculate the difference of two definite integrals:

[0230] diff=|result x 1-result x 2|

[0231] In the embodiment of the present application, the extreme value arrays XPS and YPS are obtained in the interval [x i ,x i+1 ][y i ,y i+1 ] The y-axis coordinate point ys at the extreme point of the range i , judge if ys i Greater than Then get the extreme value array YPS in the interval [y i ,y i+1 ]Maximum value of the range py ; Otherwise, get the extreme value array YPS in the interval [y i ,y i+1 ]Minimum value of the range py .

[0232] If max py Greater than Then judge that its symbol is positive; if min py Less than Then we judge that the symbol is a negative sign, and multiply it by diff, and we can get the following formula:

[0233] diff s =sign*diff

[0234] In this embodiment, diff s Represents Y fit The integral difference between the (x) function and the line(x) function within the interval range is inserted into the array areas to represent the space-time trajectory of moving the head left and right.

[0235] After this cycle is over, we can get the value of i ,y i ) and data points (x i+1 ,y i+1 ) is the space-time trajectory of the head moving left or right within the range. After all data points are traversed, the complete trajectory array areas can be obtained.

[0236] Step S433: If the second area and the third area are adjacent, and the absolute value of the difference between the second area and the third area is less than a third threshold, it is determined that the head movement is qualified.

[0237] It is easy to understand that if the user's head turns left and right significantly during the "confirmation of the scene environment" process, it will definitely form Figure 7 In other words, if the two fitting functions and the mean straight line function can form the above-mentioned features, that is, they have adjacent second and third areas, and the absolute value of the difference between the second and third areas is less than the third threshold value (that is, the amplitude and speed of the left and right rotation of the user's head are basically the same), then the head movement can be judged as qualified.

[0238] As can be seen from the previous text, the second fitting function and the mean straight line function may form multiple enclosed areas, and each enclosed area is located at the data point (x i ,y i ) and data points (x i+1 ,y i+1 ). In the present application, two areas are adjacent (i.e., the second area and the third area are adjacent) when the area forming the second area is located at the data point (x i ,y i ) and data points (x i+1 ,y i+1 ), and the area forming the third area is located between the data point (x i-1 ,y i-1 ) and data points (x i ,y i ) or between data points (x i+1 ,y i+1 ) and data points (x i+2 ,y i+2 ), it means that the two areas are adjacent; otherwise, the two areas are not adjacent. In this embodiment, the third threshold value can be an empirical value obtained through a large number of experimental verifications. Of course, the third threshold value can also be set based on the action standard.

[0239] In a specific embodiment of the present application, the third threshold value may be greater than or equal to 0.03 and less than or equal to 0.07. Specifically, the third threshold value may be any value among 0.03, 0.04, 0.05, 0.06 and 0.07, or any value between two adjacent values ​​mentioned above.

[0240] As can be seen from the previous text, in the process of "confirming the scene environment", even if the position of the user's head changes slightly, a corresponding enclosed area will be directly formed between the second fitting function and the mean straight line function. In order to filter out these noises, the areas in the array areas can be denoised in any way.

[0241] In one embodiment of the present application, the array areas may be subjected to denoising by median filtering before being judged. Specifically, the method is as follows:

[0242] Calculate the mean of the array areas mean , the process is as follows:

[0243]

[0244] Among them, N is the number of data in the array areas.

[0245] Traverse the array areas and delete the absolute value less than area mean Data, traverse all area values ​​in the array areas i , find the maximum area value area max , again traverse all the area values ​​in areas i , filter area value area max Then find the largest area value from the remaining area values minor .

[0246] Compare area max and area minor Whether it is adjacent and area max and area minor Whether the absolute value of the difference is less than the third threshold.

[0247] From the previous text, we can see that Figure 7 A second fitting function is obtained based on the average value of the left eye position coordinates and the right eye position coordinates of the user; Figure 8 is a second fitting function obtained based on the distance between the coordinates of the left eye position and the right eye position of the user. Figure 7 and Figure 8 As shown, if the user's head rotates left and right, the key point coordinate change curve based on the user's head is similar to a sine curve. That is to say, in the embodiment of the present application, the second fitting function can also be a sine curve, that is, the embodiment of the present application can also determine whether the user's head movement is qualified by forming a sine curve fit. It is easy to understand that if the obtained sine curve function (that is, the second fitting function) has a higher fit, it means that the user's head movement is more standard, which will not be elaborated here.

[0248] Step S500: If the user's arm movements and head movements are both qualified, the user's cardiopulmonary resuscitation on-site environment confirmation operation is qualified.

[0249] It should be clear that in the embodiment of the present application, there is no order in which the user's arm movement determination and the user's head movement determination are performed, that is, there is no order in which step S200 and step S400 are performed. The user's arm movement can be determined first (that is, step S200 is performed), and then the user's head movement is determined (that is, step S400 is performed); of course, the user's head movement can be determined first, and then the user's arm movement can be determined; the user's arm movement and the user's head movement can also be determined at the same time.

[0250] It should be clear that the method proposed in the embodiment of the present application can automatically determine whether the user's actions meet the action requirements of "confirming the on-site environment" in cardiopulmonary resuscitation, avoiding reliance on manual judgment. And this automated evaluation method can improve response speed and accuracy, especially in the application scenario of batch automatic assessment. The method proposed in the embodiment of the present application performs mathematical modeling and data processing through human posture data. Its analysis of complex actions in "confirming the on-site environment" is more accurate, reliable and explainable, which is convenient for subsequent promotion and application.

[0251] After introducing all the embodiments of the evaluation method for confirming the cardiopulmonary resuscitation scene environment proposed in this application, the following introduces an embodiment of the evaluation device for confirming the cardiopulmonary resuscitation scene environment proposed in this application. Fig. 9 As shown, the evaluation device 10 for confirming the cardiopulmonary resuscitation on-site environment comprises:

[0252] An acquisition module 12, configured to acquire first body part data of a user at a target stage of cardiopulmonary resuscitation, wherein the first body part data at least includes time-series position data of a hand, an arm, a shoulder and a head of the user;

[0253] A processing module 11 is used to perform a fitting operation according to a preset rule based on the time-series position data of the hand, arm and shoulder in the first body part data of the user to determine whether the arm movement of the user is qualified;

[0254] And, based on the first body part data of the user, obtaining second body part data; the second body part data is the first body part data within a preset time period;

[0255] and performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified;

[0256] And, if the user's arm movements and head movements are both qualified, the user's cardiopulmonary resuscitation scene environment confirmation operation is qualified.

[0257] As a specific embodiment of the present application, the processing module 11 is further used to fit the position coordinates of the hand, arm and shoulder at the same time node to obtain multiple first fitting functions;

[0258] And, based on each first fitting function, determining whether the user's arm movement is qualified.

[0259] As a specific embodiment of the present application, the processing module 11 is further used to form a position-time coordinate system by transforming the horizontal coordinate of the user's head and time;

[0260] and, fitting the position coordinates of the eyes or ears of each user in the position-time coordinate system to form a second fitting function;

[0261] And, based on the second fitting function, determining whether the user's head movement is qualified.

[0262] As a specific embodiment of the present application, the processing module 11 is further used to obtain each fitted straight line function based on each first fitting function; the fitted straight line function corresponds to the first fitting function one by one;

[0263] And, based on the multiple first fitting functions and the corresponding fitting straight line functions, multiple first areas are obtained; the first area is the area enclosed by the first fitting function and the corresponding fitting straight line function; the first area, the first fitting function and the fitting straight line function correspond one to one;

[0264] And, if any one of the first areas is smaller than the first threshold, the arm movement is determined to be qualified.

[0265] As a specific embodiment of the present application, the processing module 11 is further configured to obtain a fitting straight line function corresponding to any first area if any first area is smaller than a first threshold value;

[0266] And, based on the fitted straight line function, obtaining the horizontal angle of the fitted straight line function;

[0267] And, if the horizontal angle is smaller than a second threshold, the arm movement is determined to be qualified.

[0268] As a specific embodiment of the present application, the processing module 11 is further used to obtain a mean straight line function based on the second fitting function;

[0269] And, based on the second fitting function and the mean straight line function, a second area and a third area are obtained; the second area is the maximum area formed by the second fitting function and the mean straight line function, and the third area is the second largest area formed by the second fitting function and the mean straight line function;

[0270] And, if the second area and the third area are adjacent, and the absolute value of the difference between the second area and the third area is less than a third threshold, it is determined that the head movement is qualified.

[0271] As a specific embodiment of the present application, the preset time period includes a time period formed by a preset time length after a first time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified;

[0272] Or the preset time period includes a time period formed between a first time node and a second time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified; at the second time node, the arm movement is judged to be unqualified, and before the second time node, the arm movement is judged to be qualified.

[0273] It should be clear that the device proposed in the embodiment of the present application can automatically determine whether the user's actions meet the action requirements of "confirming the on-site environment" in cardiopulmonary resuscitation, avoiding reliance on manual judgment. And the automated evaluation device can improve the response speed and accuracy, especially in the application scenario of batch automatic assessment. The device proposed in the embodiment of the present application performs mathematical modeling and data processing through human posture data. Its analysis of complex actions in "confirming the on-site environment" is more accurate, reliable and explainable, which is convenient for subsequent promotion and application.

[0274] After introducing all the embodiments of the evaluation device for confirming the cardiopulmonary resuscitation scene environment proposed in this application, the following introduces an embodiment of the evaluation device for confirming the cardiopulmonary resuscitation scene environment proposed in this application, such as Fig.10 As shown, the evaluation device 20 for the cardiopulmonary resuscitation on-site environment confirmation operation includes:

[0275] A data collector 22, for acquiring first body part data of the user at a target stage of cardiopulmonary resuscitation, wherein the first body part data at least includes time-series position data of the user's hands, arms, shoulders and head;

[0276] The processor 21 is used to perform a fitting operation according to a preset rule based on the time-series position data of the hand, arm and shoulder in the first body part data of the user to determine whether the arm movement of the user is qualified;

[0277] And, based on the first body part data of the user, obtaining second body part data; the second body part data is the first body part data within a preset time period;

[0278] and performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified;

[0279] And, if the user's arm movements and head movements are both qualified, the user's cardiopulmonary resuscitation scene environment confirmation operation is qualified.

[0280] As a specific embodiment of the present application, the processor 21 is further used to fit the position coordinates of the hand, arm and shoulder at the same time node to obtain multiple first fitting functions;

[0281] And, based on each first fitting function, determining whether the user's arm movement is qualified.

[0282] As a specific embodiment of the present application, the processor 21 is further used to form a position-time coordinate system by transforming the horizontal coordinate of the user's head and time;

[0283] and, fitting the position coordinates of the eyes or ears of each user in the position-time coordinate system to form a second fitting function;

[0284] And, based on the second fitting function, determining whether the user's head movement is qualified.

[0285] As a specific embodiment of the present application, the processor 21 is further used to obtain each fitted straight line function based on each first fitting function; the fitted straight line function corresponds to the first fitting function one by one;

[0286] And, based on the multiple first fitting functions and the corresponding fitting straight line functions, multiple first areas are obtained; the first area is the area enclosed by the first fitting function and the corresponding fitting straight line function; the first area, the first fitting function and the fitting straight line function correspond one to one;

[0287] And, if any one of the first areas is smaller than the first threshold, the arm movement is determined to be qualified.

[0288] As a specific embodiment of the present application, the processor 21 is further configured to obtain a fitting straight line function corresponding to any first area if any first area is smaller than a first threshold;

[0289] And, based on the fitted straight line function, obtaining the horizontal angle of the fitted straight line function;

[0290] And, if the horizontal angle is smaller than a second threshold, the arm movement is determined to be qualified.

[0291] As a specific embodiment of the present application, the processor 21 is further configured to obtain a mean straight line function based on the second fitting function;

[0292] And, based on the second fitting function and the mean straight line function, a second area and a third area are obtained; the second area is the maximum area formed by the second fitting function and the mean straight line function, and the third area is the second largest area formed by the second fitting function and the mean straight line function;

[0293] And, if the second area and the third area are adjacent, and the absolute value of the difference between the second area and the third area is less than a third threshold, it is determined that the head movement is qualified.

[0294] As a specific embodiment of the present application, the preset time period includes a time period formed by a preset time length after a first time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified;

[0295] Or the preset time period includes a time period formed between a first time node and a second time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified; at the second time node, the arm movement is judged to be unqualified, and before the second time node, the arm movement is judged to be qualified.

[0296] It should be clear that the device proposed in the embodiment of the present application can automatically determine whether the user's actions meet the action requirements of "confirming the on-site environment" in cardiopulmonary resuscitation, avoiding reliance on manual judgment. And the automated evaluation device can improve the response speed and accuracy, especially in the application scenario of batch automatic assessment. The device proposed in the embodiment of the present application performs mathematical modeling and data processing through human posture data. Its analysis of complex actions in "confirming the on-site environment" is more accurate, reliable and explainable, which is convenient for subsequent promotion and application.

[0297] After introducing all the embodiments of the evaluation device for the cardiopulmonary resuscitation on-site environment confirmation operation proposed in the present application, an embodiment of a computer-readable storage medium proposed in the present application is introduced below. Specifically, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the evaluation method for the cardiopulmonary resuscitation on-site environment confirmation operation as described in any of the above embodiments.

[0298] It should be clear that the computer-readable storage media in this application include permanent and non-permanent, removable and non-removable media that can be used to store information by 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 technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0299] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0300] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the methods, devices and equipment described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0301] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0302] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0303] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0304] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0305] The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0306] Although the embodiments of the present application have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating a cardiopulmonary resuscitation on-site environment confirmation operation, characterized in that: The method comprises: Acquire first body part data of the user at a target stage of cardiopulmonary resuscitation, the first body part data at least comprising time-series position data of the user's hands, arms, shoulders and head; Performing a fitting operation according to a preset rule based on the time-series position data of the hand, arm and shoulder in the first body part data of the user to determine whether the arm movement of the user is qualified; Based on the first body part data of the user, obtaining second body part data; the second body part data is the first body part data within a preset time period; performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified; If the user's arm movements and head movements are both qualified, then the user's cardiopulmonary resuscitation on-site environment confirmation operation is qualified.

2. The evaluation method for confirming the cardiopulmonary resuscitation scene environment according to claim 1, characterized in that: The fitting operation is performed based on the time-series position data of the hand, arm and shoulder in the first body part data of the user according to a preset rule to determine whether the arm movement of the user is qualified, which includes: Fitting the position coordinates of the hand, arm and shoulder at the same time node to obtain multiple first fitting functions; Based on each first fitting function, it is determined whether the user's arm movement is qualified.

3. The evaluation method for confirming the cardiopulmonary resuscitation scene environment according to claim 2, characterized in that: Performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified includes: The horizontal coordinate of the user's head and time form a position-time coordinate system; Fitting the position coordinates of the eyes or ears of each user in the position-time coordinate system to form a second fitting function; Based on the second fitting function, it is determined whether the user's head movement is qualified.

4. The evaluation method for confirming the cardiopulmonary resuscitation scene environment according to claim 3, characterized in that: The determining whether the user's arm movement is qualified based on each first fitting function comprises: Based on each first fitting function, each fitting straight line function is obtained; the fitting straight line function corresponds to the first fitting function one by one; Based on the multiple first fitting functions and the corresponding fitting straight line functions, multiple first areas are obtained; the first area is the area enclosed by the first fitting function and the corresponding fitting straight line function; the first area, the first fitting function and the fitting straight line function correspond one to one; If any of the first areas is smaller than the first threshold, the arm movement is determined to be qualified.

5. The evaluation method for confirming the cardiopulmonary resuscitation scene environment according to claim 4, characterized in that: If any of the first areas is smaller than the first threshold, determining that the arm movement is qualified includes: If any first area is smaller than a first threshold, obtaining a fitting straight line function corresponding to the first area; Based on the fitted straight line function, obtaining the horizontal angle of the fitted straight line function; If the horizontal angle is smaller than the second threshold, the arm movement is determined to be qualified.

6. The method for evaluating the cardiopulmonary resuscitation scene environment confirmation operation according to any one of claims 3 to 5, characterized in that: The determining whether the user's head movement is qualified based on the second fitting function includes: Based on the second fitting function, obtaining a mean straight line function; Based on the second fitting function and the mean straight line function, a second area and a third area are obtained; the second area is the maximum area formed by the second fitting function and the mean straight line function, and the third area is the second largest area formed by the second fitting function and the mean straight line function; If the second area and the third area are adjacent to each other and the absolute value of the difference between the second area and the third area is smaller than a third threshold, it is determined that the head movement is qualified.

7. The method for evaluating the cardiopulmonary resuscitation scene environment confirmation operation according to any one of claims 1 to 5, characterized in that: The preset time period includes a time period formed by a preset time length after a first time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified; Or the preset time period includes a time period formed between a first time node and a second time node; at the first time node, the arm movement is judged to be qualified, and before the first time node, the arm movement is judged to be unqualified; at the second time node, the arm movement is judged to be unqualified, and before the second time node, the arm movement is judged to be qualified.

8. An evaluation device for confirming the operation of cardiopulmonary resuscitation scene environment, characterized in that: include: An acquisition module, configured to acquire first body part data of a user at a target stage of cardiopulmonary resuscitation, wherein the first body part data at least includes time-series position data of a hand, an arm, a shoulder and a head of the user; A processing module, configured to perform a fitting operation according to a preset rule based on the time-series position data of the hand, arm and shoulder in the first body part data of the user, so as to determine whether the arm movement of the user is qualified; And, based on the first body part data of the user, obtaining second body part data; the second body part data is the first body part data within a preset time period; and performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified; And, if the user's arm movements and head movements are both qualified, the user's cardiopulmonary resuscitation scene environment confirmation operation is qualified.

9. An evaluation device for confirming the operation of cardiopulmonary resuscitation on-site environment, characterized in that: A data collector, for acquiring first body part data of a user at a target stage of cardiopulmonary resuscitation, wherein the first body part data at least includes time-series position data of a hand, an arm, a shoulder and a head of the user; A processor, configured to perform a fitting operation according to a preset rule based on the time-series position data of the hand, arm, and shoulder in the first body part data of the user, so as to determine whether the arm movement of the user is qualified; And, based on the first body part data of the user, obtaining second body part data; the second body part data is the first body part data within a preset time period; and performing a fitting operation based on the time-series position data of the head in the second body part data of the user to determine whether the head movement of the user is qualified; And, if the user's arm movements and head movements are both qualified, the user's cardiopulmonary resuscitation scene environment confirmation operation is qualified.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the evaluation method for the cardiopulmonary resuscitation scene environment confirmation operation as described in any one of claims 1 to 7 is implemented.

Images