A cardiopulmonary resuscitation chest compression intensity analysis method, device and computer equipment
By collecting and analyzing the user's body images and three-dimensional structural data, identifying the target pressing area and appropriate pressing pressure, the problem of uneven mastery of first aiders in CPR is solved, and the effect of CPR and patient survival rate is improved.
Patent Information
- Application Number
- CN202410422962.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-09
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-04-09
AI Technical Summary
During the cardiopulmonary resuscitation, the first aiders have uneven chest compression pressure due to misaligned posture, uneven strength, and insufficient physical strength for a long time, which affects the survival rate of patients with cardiac arrest.
By collecting user's body images and three-dimensional structural data, a three-dimensional structural model is generated, the body state and target pressing area are identified, appropriate pressing pressure level information is determined based on physiological information and bone density, and a pressing indication is provided to ensure the accuracy of pressing depth and force. sex.
It improves the quality of cardiopulmonary resuscitation and chest compression, reduces the risk of secondary trauma to patients, and improves the survival chances of patients with cardiac arrest.
Smart Images

Figure CN118470188B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device and computer equipment for analyzing the intensity of chest compression during cardiopulmonary resuscitation. Background Art
[0002] Cardiopulmonary resuscitation, or CPR for short, is the most effective emergency treatment technique for rescuing patients with cardiac arrest. It is designed to restore the patient's spontaneous breathing and circulation. Ordinary people can master CPR relatively well after simple training and a short practical operation process. It is currently the basic treatment method for patients in emergency situations when they encounter cardiac arrest. High-quality chest compression is a key component of CPR, which can maintain the blood circulation of patients with cardiac arrest and is crucial to improving the survival rate of patients with cardiac arrest. The American Heart Association (AHA) CPR guidelines recommend that the compression depth for adults is 5 to 6 cm, but for patients with special body shapes who are particularly thin or obese, the compression depth may be appropriately adjusted. However, in actual operations, due to incorrect compression posture, uneven strength control, and lack of physical strength for long-term compression, the first aid provider cannot reach the ideal compression depth or cause secondary trauma to the patient. Therefore, how to intelligently control the strength of chest compression in CPR is the current research focus.
[0003] Traditional CPR relies solely on personnel to perform CPR on patients by manually pressing the patient's sternum regularly and blowing air from mouth to mouth. However, this method often fails to reach the ideal compression depth or causes secondary trauma to the patient due to incorrect pressing posture, uneven force control, and lack of physical strength after long-term pressing by the first aider. This reduces the effectiveness of CPR and affects the survival chance of patients with cardiac arrest. Summary of the invention
[0004] Based on this, it is necessary to provide a cardiopulmonary resuscitation chest compression intensity analysis method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.
[0005] In a first aspect, the present application provides a method for analyzing the intensity of chest compression during cardiopulmonary resuscitation. The method comprises:
[0006] Collecting a body image of a user, three-dimensional body structure data of the user, and bone information of the user, and generating a three-dimensional structure model of the user based on the three-dimensional body structure data;
[0007] Based on the body image of the user and the bone information, identifying the user's physical condition, and based on the three-dimensional structure model of the user, locating the target pressing area of the user;
[0008] Based on the user's physical state, the user's pressing force information is determined through a pressing force analysis strategy, and the user's target pressing area and the user's pressing force information are used as the user's target pressing information.
[0009] Optionally, generating the three-dimensional structure model of the user based on the three-dimensional body structure data includes:
[0010] constructing a plane coordinate system of the plane on which the user lies, and generating an initial three-dimensional structure model of the user based on the three-dimensional body structure data;
[0011] The initial three-dimensional structure model of the user is mapped to the plane coordinate system to obtain the three-dimensional structure model of the user.
[0012] Optionally, the identifying the user's physical condition based on the user's body structure image and the bone information includes:
[0013] Based on the body structure image of the user, identifying the physiological information of the user and the body shape information of the user through an image detection and recognition network;
[0014] Based on the bone information of the user, the bone density of the user is identified, and the physiological information of the user, the body shape information of the user, and the bone density of the user are used as the physical state of the user.
[0015] Optionally, locating the target pressing area of the user based on the three-dimensional structure model of the user includes:
[0016] Based on the three-dimensional structure model of the user, identifying the chest area of the user through a three-dimensional recognition network;
[0017] Based on the three-dimensional structure range corresponding to the chest area of the user, the target pressing area of the user is located through a pressing area positioning strategy.
[0018] Optionally, determining the pressing force information of the user through a pressing force analysis strategy based on the user's physical state includes:
[0019] Based on the physiological information of the user and the body shape information of the user, query the pressing depth range of the user;
[0020] Based on the bone density of the user, querying the bone hardness corresponding to the bone density of the user in a bone database corresponding to the physiological information of the user, and identifying the corresponding relationship between the pressing force of the user and the pressing depth of the user based on the bone hardness;
[0021] Based on the pressing depth range of the user and the corresponding relationship, the pressing force range of the user is identified, and the pressing force range is used as the pressing force information of the user.
[0022] Optionally, in the absence of the pressing depth range of the user, determining the pressing force information of the user through a pressing force analysis strategy based on the user's physical state includes:
[0023] Based on the physiological information of the user, determine the initial compression depth range of the user, and scan the chest bone structure data of the user;
[0024] Based on the chest bone structure data of the user, a chest bone structure model of the user is constructed, and the chest bone structure model of the user is structurally spliced with the three-dimensional body data of the user to obtain a three-dimensional physical structure model of the user;
[0025] Based on the three-dimensional physical structure model of the user, identifying the in vivo sternum compression depth range corresponding to the initial compression depth range, and calculating the sternum pressure limit of the user through a bone pressure limit algorithm based on the bone density of the user;
[0026] In a bone database corresponding to the physiological information of the user, querying the bone hardness corresponding to the bone density of the user, and identifying the corresponding relationship between the pressing force of the user and the pressing depth of the user based on the bone hardness;
[0027] Based on the corresponding relationship, query the compression depth limit corresponding to the sternum pressure limit, and select a compression depth range that is not greater than the compression depth limit in the in vivo sternum compression depth range as the target sternum compression range;
[0028] Based on the corresponding relationship and the target sternum compression range, the user's compression force range is identified, and the compression force range is used as the user's compression force information.
[0029] Optionally, the identifying the user's pressing force range based on the corresponding relationship and the target sternum compression range includes:
[0030] In the initial compression depth range, a target compression depth range corresponding to the target sternum compression range is screened, and based on the corresponding relationship and the target compression depth range, a compression intensity range of the user is identified.
[0031] Optionally, after taking the target pressing area of the user and the pressing force information of the user as the target pressing information of the user, the method further includes:
[0032] Based on the target pressing area and the pressing force information, the pressing instruction information of the user is constructed through the pressing frequency information, and the pressing instruction information is transmitted to the client of the staff.
[0033] In a second aspect, the present application also provides a cardiopulmonary resuscitation chest compression intensity analysis device. The device comprises:
[0034] An acquisition module, used to acquire a body image of a user, three-dimensional body structure data of the user, and bone information of the user, and generate a three-dimensional structure model of the user based on the three-dimensional body structure data;
[0035] a positioning module, used to identify the user's physical state based on the user's body image and the bone information, and to locate the user's target pressing area based on the user's three-dimensional structure model;
[0036] A determination module is used to determine the user's pressing force information based on the user's physical state and through a pressing force analysis strategy, and use the user's target pressing area and the user's pressing force information as the user's target pressing information.
[0037] Optionally, the acquisition module is specifically used to:
[0038] constructing a plane coordinate system of the plane on which the user lies, and generating an initial three-dimensional structure model of the user based on the three-dimensional body structure data;
[0039] The initial three-dimensional structure model of the user is mapped to the plane coordinate system to obtain the three-dimensional structure model of the user.
[0040] Optionally, the positioning module is specifically used to:
[0041] Based on the body structure image of the user, identifying the physiological information of the user and the body shape information of the user through an image detection and recognition network;
[0042] Based on the bone information of the user, the bone density of the user is identified, and the physiological information of the user, the body shape information of the user, and the bone density of the user are used as the physical state of the user.
[0043] Optionally, the positioning module is specifically used to:
[0044] Based on the three-dimensional structure model of the user, identifying the chest area of the user through a three-dimensional recognition network;
[0045] Based on the three-dimensional structure range corresponding to the chest area of the user, the target pressing area of the user is located through a pressing area positioning strategy.
[0046] Optionally, the determining module is specifically used to:
[0047] Based on the physiological information of the user and the body shape information of the user, query the pressing depth range of the user;
[0048] Based on the bone density of the user, querying the bone hardness corresponding to the bone density of the user in a bone database corresponding to the physiological information of the user, and identifying the corresponding relationship between the pressing force of the user and the pressing depth of the user based on the bone hardness;
[0049] Based on the pressing depth range of the user and the corresponding relationship, the pressing force range of the user is identified, and the pressing force range is used as the pressing force information of the user.
[0050] Optionally, in the absence of the user's pressing depth range, the determining module is specifically configured to:
[0051] Based on the physiological information of the user, determine the initial compression depth range of the user, and scan the chest bone structure data of the user;
[0052] Based on the chest bone structure data of the user, a chest bone structure model of the user is constructed, and the chest bone structure model of the user is structurally spliced with the three-dimensional body data of the user to obtain a three-dimensional physical structure model of the user;
[0053] Based on the three-dimensional physical structure model of the user, identifying the in vivo sternum compression depth range corresponding to the initial compression depth range, and calculating the sternum pressure limit of the user through a bone pressure limit algorithm based on the bone density of the user;
[0054] In a bone database corresponding to the physiological information of the user, querying the bone hardness corresponding to the bone density of the user, and identifying the corresponding relationship between the pressing force of the user and the pressing depth of the user based on the bone hardness;
[0055] Based on the corresponding relationship, query the compression depth limit corresponding to the sternum pressure limit, and select a compression depth range that is not greater than the compression depth limit in the in vivo sternum compression depth range as the target sternum compression range;
[0056] Based on the corresponding relationship and the target sternum compression range, the user's compression force range is identified, and the compression force range is used as the user's compression force information.
[0057] Optionally, the determining module is specifically used to:
[0058] In the initial compression depth range, a target compression depth range corresponding to the target sternum compression range is screened, and based on the corresponding relationship and the target compression depth range, a compression intensity range of the user is identified.
[0059] Optionally, the device further comprises:
[0060] A transmission module is used to construct the user's pressing indication information based on the target pressing area and the pressing force information through the pressing frequency information, and transmit the pressing indication information to the client of the staff.
[0061] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.
[0062] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0063] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0064] The above-mentioned cardiopulmonary resuscitation chest compression force analysis method, device, computer equipment and storage medium collect the user's body image, the user's three-dimensional body structure data, and the user's bone information, and generate the user's three-dimensional structure model based on the body three-dimensional structure data; identify the user's body state based on the user's body image and the bone information, and locate the user's target compression area based on the user's three-dimensional structure model; determine the user's compression force information based on the user's body state through a compression force analysis strategy, and use the user's target compression area and the user's compression force information as the user's target compression information. This solution collects the user's body image, three-dimensional body structure data, and bone information to identify the user's physical condition and target compression area, and then determines the user's compression force information based on the physical condition, thereby avoiding secondary injury to the user caused by uneven force control. Then, the user's target compression information is generated based on the compression force information and the target compression area, thereby avoiding the problem of uneven force control caused by simple regular manual compression, thereby comprehensively improving the quality of cardiopulmonary resuscitation chest compression, and then increasing the survival chance of patients with cardiac arrest. BRIEF DESCRIPTION OF THE DRAWINGS
[0065] Figure 1 A schematic diagram of a flow chart of a method for analyzing chest compression intensity during cardiopulmonary resuscitation in one embodiment;
[0066] Figure 2 It is a structural block diagram of a cardiopulmonary resuscitation chest compression intensity analysis device in one embodiment;
[0067] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0069] The cardiopulmonary resuscitation chest compression intensity analysis method provided in the embodiment of the present application can be applied to the application environment corresponding to the cardiopulmonary resuscitation chest compression intensity analysis in the case of cardiopulmonary arrest. The method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. Among them, the terminal identifies the user's physical state and target compression area by collecting the user's body image, body three-dimensional structure data, and bone information, and then determines the user's compression intensity information based on the physical state, thereby avoiding secondary damage to the user caused by uneven force control, and then generates the user's target compression information through the compression intensity information and the target compression area, thereby avoiding the problem of uneven force control caused by simply regular manual compression, thereby comprehensively improving the quality of cardiopulmonary resuscitation chest compression, and then improving the survival chance of patients with cardiac arrest.
[0070] In one embodiment, Figure 1 As shown, a method for analyzing chest compression intensity of cardiopulmonary resuscitation is provided, and the method is applied to a terminal as an example for explanation, including the following steps:
[0071] Step S101 : collecting a user's body image, the user's three-dimensional body structure data, and the user's bone information, and generating a three-dimensional structure model of the user based on the three-dimensional body structure data.
[0072] In this embodiment, the terminal collects body image data of the user at different angles through the camera device in the acquisition unit to obtain the body image of the user. Then, the terminal collects the three-dimensional body structure data of the user through the scanning device based on infrared scanning technology in the acquisition unit. After that, the terminal collects the bone information of the user through the handheld scanning device based on X-ray scanning technology in the acquisition device, wherein the bone information is data information corresponding to the tightness of the bone structure of the user. Finally, the terminal generates a three-dimensional structure model of the user based on the acquired three-dimensional body structure data. The method of generating the three-dimensional structure model is the method of generating the model through a 3D modeling device. The specific generation process will be described in detail later.
[0073] Step S102, identifying the user's body state based on the user's body image and bone information, and locating the user's target pressing area based on the user's three-dimensional structure model.
[0074] In this embodiment, the terminal identifies the user's physical state based on the user's body image and bone information, and locates the user's target pressing area based on the user's three-dimensional structure model. The user's physical state is the user's tolerance to the pressing force, which includes the user's bone density and the user's body shape. The larger the body shape and the higher the bone density, the greater the user's tolerance to the pressing force, and the smaller the body shape and the lower the bone density, the smaller the user's tolerance to the pressing force. The larger the body shape, the deeper the single pressing depth, and the smaller the body shape, the shallower the single pressing depth. The specific identification process will be described in detail later. The user's target pressing area includes the user's mouth area, chest area, and neck area. The mouth area is used to perform air delivery lung resuscitation on the user, the neck area is used to adjust the direction of the user's mouth area, and the chest area is used to perform chest compression resuscitation on the user. The specific identification process will be described in detail later.
[0075] Step S103, based on the user's physical state, the user's pressing force information is determined through a pressing force analysis strategy, and the user's target pressing area, the user's pressing force information, and the three-dimensional structure model are combined to generate a resuscitation control instruction.
[0076] In this embodiment, the terminal determines the user's pressing force information based on the user's physical state through a pressing force analysis strategy, and generates a resuscitation control instruction based on the user's target pressing area, the user's pressing force information, and the three-dimensional structural model. The pressing force information includes pressing force and pressing depth, and the resuscitation control instruction includes a mouth orientation adjustment instruction, a breathing resuscitation instruction, a pulse resuscitation instruction, and a structural support instruction, wherein the mouth orientation adjustment instruction and the structural support instruction are used to control the structural support unit to adjust the user's mouth orientation and to perform adsorption support connection with the plane to which the user is attached. The breathing resuscitation instruction is used to control the mouth breathing resuscitation unit to perform air delivery lung resuscitation processing on the user's mouth area, and the pulse resuscitation instruction is used to control the chest compression resuscitation unit to perform compression resuscitation processing on the user's chest. The specific process of generating instructions will be described in detail later.
[0077] Based on the above scheme, the user's body state and target compression area are identified by collecting the user's body image, body three-dimensional structure data, and bone information. Then, the user's compression force information is determined based on the body state, thereby avoiding secondary injuries to the user caused by uneven force control. Then, the user's target compression information is generated based on the compression force information and the target compression area, thereby avoiding the problem of uneven force control caused by regular manual compression alone, thereby comprehensively improving the quality of cardiopulmonary resuscitation chest compression, and then increasing the survival chance of patients with cardiac arrest.
[0078] Optionally, a three-dimensional structural model of the user is generated based on the three-dimensional structure data of the body, including: constructing a plane coordinate system of the plane on which the user lies, and generating an initial three-dimensional structural model of the user based on the three-dimensional structure data of the body; mapping the initial three-dimensional structural model of the user to the plane coordinate system to obtain the three-dimensional structural model of the user.
[0079] In this embodiment, the terminal constructs a plane coordinate system of the plane on which the user lies, and generates an initial three-dimensional structure model of the user based on the three-dimensional structure data of the body. Then, the terminal maps the initial three-dimensional structure model of the user to the plane coordinate system to obtain the three-dimensional structure model of the user.
[0080] Based on the above scheme, after constructing the plane coordinate system of the plane on which the user lies, the three-dimensional structural model of the user is mapped, which improves the attention to the plane on which the user lies in the three-dimensional structural model and provides support data reference for subsequent structural support units to execute structural support instructions.
[0081] Optionally, the user's physical condition is identified based on the user's body structure image and bone information, including: based on the user's body structure image, identifying the user's physiological information and the user's body shape information through an image detection and recognition network; based on the user's bone information, identifying the user's bone density, and using the user's physiological information, the user's body shape information, and the user's bone density as the user's physical condition.
[0082] In this embodiment, the terminal identifies the user's physiological information and the user's body shape information based on the user's body structure image through an image detection and recognition network. The body shape information includes the user's height, the user's side width, the user's chest width, and the user's skeleton size. The user's physiological information includes the user's gender and the user's physiological age (the physiological age analyzed by image recognition may be different from the user's actual age). The image detection and recognition network can be, but is not limited to, a FasterRCNN (FasterRegion with CNN feature) target detection model.
[0083] Then, the terminal identifies the user's bone density based on the user's bone information, and uses the user's physiological information, the user's body shape information, and the user's bone density as the user's physical condition.
[0084] Based on the above solution, the user's physical condition is determined by comprehensively analyzing the user's physiological age, body shape, and bone density, thereby improving the accuracy and comprehensiveness of identifying the user's physical condition.
[0085] Optionally, locating the target pressing area of the user based on the three-dimensional structural model of the user, including: identifying the chest area of the user through a three-dimensional recognition network based on the three-dimensional structural model of the user; locating the target pressing area of the user through a pressing area positioning strategy based on the three-dimensional structure range corresponding to the chest area of the user.
[0086] In this embodiment, the terminal identifies the chest area of the user through a three-dimensional recognition network based on the three-dimensional structural model of the user. The three-dimensional recognition network may be a three-dimensional convolutional neural network (3D-CNN). Finally, the terminal locates the target pressing area of the user based on the pressing area range ratio preset in the terminal (i.e., the pressing area positioning strategy). The pressing area range ratio may be the range area corresponding to the middle and lower third of the sternum.
[0087] Based on the above solution, the compression accuracy of cardiac resuscitation is improved by locating the target compression area in the user's three-dimensional structure model.
[0088] Optionally, based on the user's physical state, the user's pressing force information is determined through a pressing force analysis strategy, including: based on the user's physiological information and the user's body shape information, querying the user's pressing depth range; based on the user's bone density, querying the bone hardness corresponding to the user's bone density in a bone database corresponding to the user's physiological information, and based on the bone hardness, identifying the correspondence between the user's pressing force and the user's pressing depth; based on the user's pressing depth range and the corresponding relationship, identifying the user's pressing force range, and using the pressing force range as the user's pressing force information.
[0089] In this embodiment, the terminal queries the user's pressing depth range in the user database based on the user's physiological information and the user's body shape information, wherein the user database includes a plurality of corresponding relationships between physiological information, body shape information and pressing depth ranges. Then, based on the user's bone density, the terminal queries the bone hardness corresponding to the user's bone density in the bone database corresponding to the user's physiological information, and identifies the corresponding relationship between the user's pressing force and the user's pressing depth based on the bone hardness. Specifically, the terminal queries the hardness database to identify the sinking depth of the sternum corresponding to different pressing forces when pressing on sternums of different bone hardnesses, and obtains the corresponding relationship between the pressing force of the user and the pressing depth of the user.
[0090] Finally, the terminal identifies the user's pressing force range based on the user's pressing depth range and the corresponding relationship, and uses the pressing force range as the user's pressing force information.
[0091] Based on the above solution, by determining the range of pressing force, the tolerance of pressing force is improved, thereby improving the control effect on the user's resuscitation strength.
[0092] Optionally, in the absence of a user's compression depth range, the user's compression force information is determined based on the user's physical state through a compression force analysis strategy, including: determining the user's initial compression depth range based on the user's physiological information, and scanning the user's chest bone structure data; constructing a chest bone structure model of the user based on the user's chest bone structure data, and performing structural splicing processing on the user's chest bone structure model and the user's body three-dimensional data to obtain the user's physical three-dimensional structure model; identifying the in vivo sternum compression depth range corresponding to the initial compression depth range based on the user's physical three-dimensional structure model, and Bone density, calculate the user's sternum pressure limit through the bone pressure limit algorithm; in the bone database corresponding to the user's physiological information, query the bone hardness corresponding to the user's bone density, and based on the bone hardness, identify the corresponding relationship between the user's pressing force and the user's pressing depth; based on the corresponding relationship, query the pressing depth limit corresponding to the sternum pressure limit, and in the body's sternum compression depth range, select the pressing depth range that is not greater than the pressing depth limit as the target sternum compression range; based on the corresponding relationship and the target sternum compression range, identify the user's pressing force range, and use the pressing force range as the user's pressing force information.
[0093] In this embodiment, the terminal determines the initial compression depth range of the user based on the user's physiological information, and scans the chest bone structure data of the user. The method of scanning the chest bone result data of the user is to scan the chest area of the user from multiple angles through a scanner carrying X-ray scanning technology to obtain three-dimensional scanning data of the chest bone of the user, and use the three-dimensional scanning data as the chest bone structure data of the user. Then, the terminal constructs a chest bone structure model of the user based on the chest bone structure data of the user. The method of constructing the chest bone structure model is to perform image modeling processing on the three-dimensional scanning data through a 3D modeling program to obtain the chest bone structure model of the user. The terminal performs structural splicing processing on the chest bone structure model of the user and the three-dimensional data of the user's body to obtain a three-dimensional structure model of the user's physique.
[0094] Then, the terminal identifies the in vivo sternum compression depth range corresponding to the initial compression depth range based on the user's physique three-dimensional structure model. Specifically, the terminal identifies the sternum compression depth value corresponding to each compression depth value in the initial compression depth range of the user in the physique three-dimensional structure model based on the user's physique three-dimensional structure model, and uses the range corresponding to all sternum compression depth values as the in vivo sternum compression depth range.
[0095] Among them, the process of identifying the depth value of each compression depth and the corresponding sternum compression depth value is that the terminal identifies the thickness value between the surface skin of the chest area and the sternum of the user based on the three-dimensional structure model of the body, and then identifies the sternum deformation domain value corresponding to the thickness value of the user based on the correspondence between the thickness value and the sternum deformation domain value preset in the terminal. Then, the terminal subtracts the sternum deformation domain value from the depth value in each initial compression depth range to obtain the sternum compression depth value corresponding to the depth value of each compression depth.
[0096] Specifically, the calculation formula for calculating the sternum compression depth value corresponding to each compression depth value is:
[0097] m i =M i -μ
[0098] In the above formula, m i is the ith sternum compression depth value, M i is the depth value of the i-th compression depth, μ is the sternum deformation domain value, and i is the virtual number of the depth value of each compression depth.
[0099] Then, the terminal calculates the user's sternum pressure limit value based on the user's bone density through a bone pressure limit algorithm, wherein the sternum pressure limit value is the maximum instantaneous pressure value that the user's sternum can withstand.
[0100] The calculation formula of the bone pressure limitation algorithm is:
[0101] F=g*S*γ
[0102] In the above formula, F is the sternum pressure limit of the user, g is the bone density of the user, S is the sternum compression area of the user (i.e., the area of the target compression area), and γ is the pressure bearing capacity corresponding to unit bone density.
[0103] The terminal queries the bone hardness corresponding to the user's bone density in the bone database corresponding to the user's physiological information, and identifies the corresponding relationship between the user's pressing force and the user's pressing depth based on the bone hardness. Then, based on the corresponding relationship, the terminal queries the pressing depth limit corresponding to the sternum pressure limit, and selects the pressing depth range that is not greater than the pressing depth limit in the sternum pressing depth range in the body as the target sternum pressing range. Finally, based on the corresponding relationship and the target sternum pressing range, the terminal identifies the user's pressing force range, and uses the pressing force range as the user's pressing force information.
[0104] Based on the above solution, by identifying the correspondence between the compression depth and the sternum compression depth, the user's compression force range is analyzed, thereby improving the accuracy of identifying the user's compression force.
[0105] Optionally, based on the correspondence and the target sternum compression range, the user's compression force range is identified, including: in the initial compression depth range, screening the target compression depth range corresponding to the target sternum compression range, and identifying the user's compression force range based on the correspondence and the target compression depth range.
[0106] In this embodiment, the terminal screens the target compression depth range corresponding to the target sternum compression range in the initial compression depth range, and identifies the user's compression intensity range based on the corresponding relationship and the target compression depth range.
[0107] Based on the above scheme, by converting the sternum compression range into the corresponding initial compression depth range, the target compression depth range is obtained, thereby identifying the compression force range, thereby improving the accuracy of identifying the actual compression force range.
[0108] Optionally, after taking the user's target pressing area and the user's pressing force information as the user's target pressing information, it also includes: based on the target pressing area and the pressing force information, through the pressing frequency information, constructing the user's pressing indication information, and transmitting the pressing indication information to the staff's client.
[0109] In this embodiment, the terminal constructs the user's pressing instruction information based on the target pressing area and the pressing force information through the pressing frequency information, and transmits the pressing instruction information to the client of the staff. The pressing frequency information is the standard pressing frequency of cardiopulmonary resuscitation, which is the frequency information preset by the staff and the terminal.
[0110] In another embodiment, the terminal generates a pressing frequency instruction, a target pressing area positioning instruction, and a pressing force control instruction through the pressing instruction information, and sends the pressing instruction information to the cardiopulmonary resuscitation machine. Then, the terminal controls the pressing device of the cardiopulmonary resuscitation machine to move to the target pressing area of the user through the target pressing area positioning instruction of the pressing instruction information, and controls the cardiopulmonary resuscitation machine to perform cardiopulmonary resuscitation on the user through the pressing frequency instruction and the pressing force control instruction of the pressing instruction information. Among them, the cardiopulmonary resuscitation machine includes a pressing device, a positioning device, a receiving device, and a control device, wherein the receiving device is used to receive each instruction and send each instruction to the control device, and the control device controls the positioning device through the target pressing area positioning instruction after splitting each instruction, locates the target pressing area of the user, and moves the pressing device to the target pressing area. Then the control device controls the pressing device to perform cardiopulmonary resuscitation on the user through the pressing frequency instruction and the pressing force control instruction. Among them, the control device is connected to the pressing device, the positioning device, and the receiving device respectively.
[0111] Based on the above solution, by constructing compression instruction information and transmitting it to the client of the staff, the auxiliary effect of the staff performing CPR compression is improved while avoiding the risk of secondary damage to the user's sternum.
[0112] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0113] Based on the same inventive concept, the embodiment of the present application also provides a cardiopulmonary resuscitation chest compression force analysis device for implementing the cardiopulmonary resuscitation chest compression force analysis method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more cardiopulmonary resuscitation chest compression force analysis device embodiments provided below can refer to the limitations of the cardiopulmonary resuscitation chest compression force analysis method above, and will not be repeated here.
[0114] In one embodiment, Figure 2 As shown, a cardiopulmonary resuscitation chest compression force analysis device is provided, comprising: a collection module 210, a positioning module 220 and a determination module 230, wherein:
[0115] The acquisition module 210 is used to acquire a body image of a user, three-dimensional body structure data of the user, and bone information of the user, and generate a three-dimensional structure model of the user based on the three-dimensional body structure data;
[0116] A positioning module 220, for identifying the user's physical state based on the user's body image and the bone information, and locating the user's target pressing area based on the user's three-dimensional structure model;
[0117] The determination module 230 is used to determine the user's pressing force information based on the user's physical state and through a pressing force analysis strategy, and use the user's target pressing area and the user's pressing force information as the user's target pressing information.
[0118] Optionally, the acquisition module 210 is specifically used for:
[0119] constructing a plane coordinate system of the plane on which the user lies, and generating an initial three-dimensional structure model of the user based on the three-dimensional body structure data;
[0120] The initial three-dimensional structure model of the user is mapped to the plane coordinate system to obtain the three-dimensional structure model of the user.
[0121] Optionally, the positioning module 220 is specifically used to:
[0122] Based on the body structure image of the user, identifying the physiological information of the user and the body shape information of the user through an image detection and recognition network;
[0123] Based on the bone information of the user, the bone density of the user is identified, and the physiological information of the user, the body shape information of the user, and the bone density of the user are used as the physical state of the user.
[0124] Optionally, the positioning module 220 is specifically used to:
[0125] Based on the three-dimensional structure model of the user, identifying the chest area of the user through a three-dimensional recognition network;
[0126] Based on the three-dimensional structure range corresponding to the chest area of the user, the target pressing area of the user is located through a pressing area positioning strategy.
[0127] Optionally, the determining module 230 is specifically configured to:
[0128] Based on the physiological information of the user and the body shape information of the user, query the pressing depth range of the user;
[0129] Based on the bone density of the user, querying the bone hardness corresponding to the bone density of the user in a bone database corresponding to the physiological information of the user, and identifying the corresponding relationship between the pressing force of the user and the pressing depth of the user based on the bone hardness;
[0130] Based on the pressing depth range of the user and the corresponding relationship, the pressing force range of the user is identified, and the pressing force range is used as the pressing force information of the user.
[0131] Optionally, when there is no pressing depth range of the user, the determining module 230 is specifically configured to:
[0132] Based on the physiological information of the user, determine the initial compression depth range of the user, and scan the chest bone structure data of the user;
[0133] Based on the chest bone structure data of the user, a chest bone structure model of the user is constructed, and the chest bone structure model of the user is structurally spliced with the three-dimensional body data of the user to obtain a three-dimensional physical structure model of the user;
[0134] Based on the three-dimensional physical structure model of the user, identifying the in vivo sternum compression depth range corresponding to the initial compression depth range, and calculating the sternum pressure limit of the user through a bone pressure limit algorithm based on the bone density of the user;
[0135] In a bone database corresponding to the physiological information of the user, querying the bone hardness corresponding to the bone density of the user, and identifying the corresponding relationship between the pressing force of the user and the pressing depth of the user based on the bone hardness;
[0136] Based on the corresponding relationship, query the compression depth limit corresponding to the sternum pressure limit, and select a compression depth range that is not greater than the compression depth limit in the in vivo sternum compression depth range as the target sternum compression range;
[0137] Based on the corresponding relationship and the target sternum compression range, the user's compression force range is identified, and the compression force range is used as the user's compression force information.
[0138] Optionally, the determining module 230 is specifically configured to:
[0139] In the initial compression depth range, a target compression depth range corresponding to the target sternum compression range is screened, and based on the corresponding relationship and the target compression depth range, a compression intensity range of the user is identified.
[0140] Optionally, the device further comprises:
[0141] A transmission module is used to construct the user's pressing indication information based on the target pressing area and the pressing force information through the pressing frequency information, and transmit the pressing indication information to the client of the staff.
[0142] Each module in the above-mentioned cardiopulmonary resuscitation chest compression intensity analysis device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0143] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a cardiopulmonary resuscitation chest compression intensity analysis method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.
[0144] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0145] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.
[0146] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0147] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.
[0148] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0149] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0150] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0151] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for analyzing chest compression intensity during cardiopulmonary resuscitation, characterized in that: The method comprises: Collecting a body image of a user, three-dimensional body structure data of the user, and bone information of the user, and generating a three-dimensional structure model of the user based on the three-dimensional body structure data; Based on the body image of the user and the bone information, identifying the user's physical condition, and based on the three-dimensional structure model of the user, locating the target pressing area of the user; Based on the user's physical state, determining the user's pressing force information through a pressing force analysis strategy, and using the user's target pressing area and the user's pressing force information as the user's target pressing information; The identifying the user's physical condition based on the user's body structure image and the bone information includes: Based on the body structure image of the user, identifying the physiological information of the user and the body shape information of the user through an image detection and recognition network; Based on the bone information of the user, identifying the bone density of the user, and using the physiological information of the user, the body shape information of the user, and the bone density of the user as the physical state of the user; The determining the pressing force information of the user based on the user's physical state through a pressing force analysis strategy includes: Based on the physiological information of the user and the body shape information of the user, query the pressing depth range of the user; Based on the bone density of the user, querying the bone hardness corresponding to the bone density of the user in a bone database corresponding to the physiological information of the user, and identifying the corresponding relationship between the pressing force of the user and the pressing depth of the user based on the bone hardness; Based on the pressing depth range of the user and the corresponding relationship, the pressing force range of the user is identified, and the pressing force range is used as the pressing force information of the user.
2. The method according to claim 1, characterized in that The step of generating the three-dimensional structure model of the user based on the three-dimensional body structure data comprises: constructing a plane coordinate system of the plane on which the user lies, and generating an initial three-dimensional structure model of the user based on the three-dimensional body structure data; The initial three-dimensional structure model of the user is mapped to the plane coordinate system to obtain the three-dimensional structure model of the user.
3. The method according to claim 1, characterized in that: The locating the target pressing area of the user based on the three-dimensional structure model of the user includes: Based on the three-dimensional structure model of the user, identifying the chest area of the user through a three-dimensional recognition network; Based on the three-dimensional structure range corresponding to the chest area of the user, the target pressing area of the user is located through a pressing area positioning strategy.
4. The method according to claim 1, characterized in that: In the absence of the pressing depth range of the user, determining the pressing force information of the user through a pressing force analysis strategy based on the user's physical state includes: Based on the physiological information of the user, determine the initial compression depth range of the user, and scan the chest bone structure data of the user; Based on the chest bone structure data of the user, a chest bone structure model of the user is constructed, and the chest bone structure model of the user is structurally spliced with the three-dimensional body data of the user to obtain a three-dimensional physical structure model of the user; Based on the three-dimensional physical structure model of the user, identifying the in vivo sternum compression depth range corresponding to the initial compression depth range, and calculating the sternum pressure limit of the user through a bone pressure limit algorithm based on the bone density of the user; In a bone database corresponding to the physiological information of the user, querying the bone hardness corresponding to the bone density of the user, and identifying the corresponding relationship between the pressing force of the user and the pressing depth of the user based on the bone hardness; Based on the corresponding relationship, query the compression depth limit corresponding to the sternum pressure limit, and select a compression depth range that is not greater than the compression depth limit in the in vivo sternum compression depth range as a target sternum compression range; Based on the corresponding relationship and the target sternum compression range, the user's compression force range is identified, and the compression force range is used as the user's compression force information.
5. The method according to claim 4, characterized in that The identifying the user's pressing force range based on the corresponding relationship and the target sternum pressing range includes: In the initial compression depth range, a target compression depth range corresponding to the target sternum compression range is screened, and based on the corresponding relationship and the target compression depth range, the user's compression intensity range is identified.
6. The method according to claim 1, characterized in that After the target pressing area of the user and the pressing force information of the user are used as the target pressing information of the user, the method further includes: Based on the target pressing area and the pressing force information, the pressing instruction information of the user is constructed through the pressing frequency information, and the pressing instruction information is transmitted to the client of the staff.
7. A cardiopulmonary resuscitation chest compression force analysis device, characterized in that: The device comprises: An acquisition module, used to acquire a body image of a user, three-dimensional body structure data of the user, and bone information of the user, and generate a three-dimensional structure model of the user based on the three-dimensional body structure data; a positioning module, used to identify the user's physical state based on the user's body image and the bone information, and to locate the user's target pressing area based on the user's three-dimensional structure model; a determination module, configured to determine the pressing force information of the user based on the user's physical state and through a pressing force analysis strategy, and use the user's target pressing area and the user's pressing force information as the user's target pressing information; The specific implementation of the positioning module identifying the user's physical state based on the user's body structure image and the bone information is as follows: Based on the body structure image of the user, identifying the physiological information of the user and the body shape information of the user through an image detection and recognition network; Based on the bone information of the user, identifying the bone density of the user, and using the physiological information of the user, the body shape information of the user, and the bone density of the user as the physical state of the user; The specific implementation of the determination module determining the user's pressing force information based on the user's physical state and through a pressing force analysis strategy is as follows: Based on the physiological information of the user and the body shape information of the user, query the pressing depth range of the user; Based on the bone density of the user, querying the bone hardness corresponding to the bone density of the user in a bone database corresponding to the physiological information of the user, and identifying the corresponding relationship between the pressing force of the user and the pressing depth of the user based on the bone hardness; Based on the pressing depth range of the user and the corresponding relationship, the pressing force range of the user is identified, and the pressing force range is used as the pressing force information of the user.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
