Operating bed angle adjusting method based on patient posture recognition

Abstract

The invention relates to the technical field of medical equipment, and discloses an operating bed angle adjusting method based on patient pose recognition, which comprises the following steps of: constructing a pose adjusting database based on an angle adjusting system, extracting a reference target pose set from the pose adjusting database, acquiring a target selection pose and an initial pose, the method comprises the steps of extracting a reference initial pose set from a pose adjustment database, recognizing a target retrieval pose in the reference initial pose set by utilizing an initial pose, retrieving a target pose adjustment scheme in the pose adjustment database based on a target selection pose and the target retrieval pose, and driving a target operating bed by utilizing the target pose adjustment scheme, and obtaining a detected vital sign based on the sign monitoring signal, and after determining that the detected vital sign is a preset normal vital sign, generating a visual adjustment result based on the driven target operating bed and the result presentation unit. The main purpose of the invention is to improve the accuracy and the intelligent degree of angle adjustment of the operating bed.

Description

Technical Field

[0001] The present invention relates to a method for adjusting the angle of an operating table based on patient pose recognition, belonging to the technical field of medical equipment. Background Art

[0002] During a surgical procedure, the adjustment of the angle of the operating table is crucial for the smooth progress of the surgery and ensuring the comfort of the patient. Correspondingly, how to achieve the accuracy and intelligence of the adjustment of the angle of the operating table has become an urgent problem to be solved.

[0003] Currently, the adjustment of the angle of the operating table mostly relies on manual adjustment by humans.

[0004] Although the above method can achieve the adjustment of the angle of the operating table, when adjusting the angle of the operating table, it relies too much on personal experience, which may lead to inaccurate adjustment of the angle of the operating table. Moreover, due to the lack of a visualization unit for the operating table after adjustment, it may be impossible to know whether the patient is comfortable, resulting in inaccurate and unintelligent problems when adjusting the angle of the current operating table. Summary of the Invention

[0005] The present invention provides a method, device and computer-readable storage medium for adjusting the angle of an operating table based on patient pose recognition, and its main purpose is to improve the accuracy and intelligence of adjusting the angle of the operating table.

[0006] To achieve the above object, a method for adjusting the angle of an operating table based on patient pose recognition provided by the present invention includes:

[0007] Receiving an angle adjustment instruction, and confirming an angle adjustment environment based on the angle adjustment instruction, wherein the angle adjustment environment includes an angle adjustment system and a target operating table. The angle adjustment system includes a pose selection unit, a result presentation unit, a pose recognition unit and a physical sign monitoring unit. The target operating table includes a plurality of first adjustment units, and the first adjustment unit includes an angle adjustment unit, a height adjustment unit and a pressure monitoring unit;

[0008] Constructing a pose adjustment database based on the angle adjustment system, wherein the pose adjustment database stores a plurality of pose adjustment plan nodes, and the pose adjustment plan node includes a reference initial pose, a reference target pose and a pose adjustment plan;

[0009] Extract the reference target pose set from the pose adjustment database. Use the pose selection unit to receive the target selection pose selected by the user according to the reference target pose set, confirm the receipt of the pose recognition instruction from the pose recognition unit, confirm the initial pose of the patient based on the pose recognition instruction, extract the reference initial pose set from the pose adjustment database, and use the initial pose to identify the target retrieval pose in the reference initial pose set;

[0010] Based on the target selection pose and the target retrieval pose, retrieve the target pose adjustment scheme from the pose adjustment database, and use the target pose adjustment scheme to drive the target operating bed;

[0011] Confirm the receipt of the physical sign monitoring instruction from the physical sign monitoring unit, parse the physical sign monitoring instruction to obtain the physical sign monitoring signal, obtain the detected vital signs based on the physical sign monitoring signal, and after confirming that the detected vital signs are the preset normal vital signs, generate a visual adjustment result based on the driven target operating bed and the result presentation unit to realize the adjustment of the angle of the target operating bed.

[0012] Optionally, constructing the pose adjustment database based on the angle adjustment system includes:

[0013] Obtain a set of simulation models for simulating patients and a set of fitting poses for characterizing the poses of patients. Among them, the set of simulation models includes multiple simulation models, and the set of fitting poses includes multiple fitting poses. In a combined form, use each simulation model in the multiple simulation models and each fitting pose in the multiple fitting poses to obtain multiple fitting adjustment nodes. Among them, the fitting adjustment node includes a simulation model and a fitting pose;

[0014] Perform the following operations on each fitting adjustment node in the multiple fitting adjustment nodes:

[0015] Based on the pre-confirmed target adjustment pose and the fitting adjustment node, obtain multiple fitting adjustment schemes, and perform the following operations on each fitting adjustment scheme in the multiple fitting adjustment schemes:

[0016] Drive the target operating bed based on the fitting adjustment scheme, and use the pressure monitoring unit corresponding to each first adjustment unit among the multiple first adjustment units corresponding to the target operating bed and the target operating bed during driving to obtain the monitored pressure time series;

[0017] Summarize the monitored pressure time series to obtain a set of monitored pressure time series, and obtain the pose adjustment database based on the set of monitored pressure time series.

[0018] Optionally, obtaining the pose adjustment database based on the set of monitored pressure time series includes:

[0019] Obtain an evaluation index set for evaluating the fitting adjustment scheme, and obtain an initial evaluation value based on the evaluation index set, the monitored pressure time series set, and the pre-constructed analytic hierarchy process, where the initial evaluation value corresponds one-to-one with the fitting adjustment scheme;

[0020] Summarize the initial evaluation values to obtain an initial evaluation value set, and use a preset screening evaluation threshold to extract a target evaluation value set from the initial evaluation value set, where the target evaluation value set includes multiple target evaluation values, and the target evaluation values are all greater than or equal to the screening evaluation threshold;

[0021] Perform the following operations on each target evaluation value in the target evaluation value set:

[0022] Calculate a comprehensive evaluation value based on the target evaluation value, and the calculation formula is as follows:

[0023]

[0024] Where Z represents the comprehensive evaluation value, α, β, and γ are all preset coefficients, p represents the target evaluation value, t represents the time required when adopting the fitting adjustment scheme corresponding to the target evaluation value, h represents the height that the first adjustment unit needs to adjust, j represents the angle that the first adjustment unit needs to adjust, n represents the monitored pressure when the first adjustment unit is adjusting, m represents that a total of m first adjustment units in the fitting adjustment scheme corresponding to the target evaluation value need to adjust the pose of the simulation model, and f(h, j, n) i represents the energy consumption function of the i-th first adjustment unit among the m first adjustment units when adjusting the pose;

[0025] Summarize the comprehensive evaluation values to obtain a comprehensive evaluation value set, and use the comprehensive evaluation value set to confirm a target adjustment scheme, where the target adjustment scheme is the fitting adjustment scheme corresponding to the smallest comprehensive evaluation value in the comprehensive evaluation value set;

[0026] Confirm a pose adjustment database based on the target adjustment scheme.

[0027] Optionally, the confirming the pose adjustment database based on the target adjustment scheme includes:

[0028] Obtain a pose image and a fitting pose vector based on the fitting pose corresponding to the target adjustment scheme, and identify pose features in the pose image, where the pose features include pose length and pose width;

[0029] Obtain an initial monitored pressure set by using the monitored pressure time series set corresponding to the target adjustment scheme, where the initial monitored pressure set is a set of the first monitored pressure in each monitored pressure time series in the monitored pressure time series set;

[0030] Associate the fitting pose, target adjustment pose, fitting pose vector, pose feature, initial monitoring pressure set, and target adjustment plan to obtain a pose adjustment node;

[0031] Summarize the pose adjustment nodes to obtain a pose adjustment database.

[0032] Optionally, the identifying the target retrieval pose from the reference initial pose set by using the initial pose includes:

[0033] Obtain an initial pose vector based on the initial pose, obtain the initial features of the patient and a reference monitoring pressure set, where the initial features include a feature length and a feature width, and the reference monitoring pressure set includes multiple reference monitoring pressures. Sort the reference monitoring pressures in the reference monitoring pressure set in descending order of the reference monitoring pressure to obtain a reference monitoring pressure sequence;

[0034] Associate the initial pose vector, initial features, and reference monitoring pressure sequence to obtain a retrieval pose node;

[0035] Perform the following operations on each reference initial pose in the reference initial pose set:

[0036] Identify the fitting pose vector, pose feature, and initial monitoring pressure set corresponding to the reference initial pose in the pose adjustment database to obtain an identified pose node. Obtain an initial monitoring pressure sequence based on the initial monitoring pressure set, update the identified pose node by using the initial monitoring pressure sequence to obtain a matching pose node, and calculate the node similarity by using a pre-constructed pose similarity formula, the matching pose node, and the retrieval pose node;

[0037] Summarize the node similarities to obtain a node similarity set, and confirm the target retrieval pose based on the node similarity set, where the target retrieval pose is the reference initial pose corresponding to the maximum node similarity in the node similarity set.

[0038] Optionally, the pose similarity formula is as follows:

[0039]

[0040] Where X represents the node similarity, ω1, ω2, ω3 are all preset coefficients, CS() represents calculating the cosine similarity, DS() represents calculating the Euclidean distance, W0 and W1 respectively represent the initial pose vector corresponding to the retrieval pose node and the fitting pose vector corresponding to the matching pose node, p0 and p1 respectively represent the reference monitoring pressure sequence corresponding to the retrieval pose node and the initial monitoring pressure sequence corresponding to the matching pose node, and z0 and z1 respectively represent the initial features corresponding to the retrieval pose node and the pose features corresponding to the matching pose node.

[0041] Optionally, obtaining the detected vital signs based on the physical sign monitoring signal includes:

[0042] Obtaining a physical sign echo signal based on the physical sign monitoring signal, obtaining an analysis intermediate frequency signal by using the physical sign monitoring signal and the physical sign echo signal, obtaining a set of frequency recognition models for frequency recognition, where the set of frequency recognition models includes multiple frequency recognition models, and performing the following operations on each frequency recognition model in the set of frequency recognition models:

[0043] Obtaining initial vital signs by using the frequency recognition model and the analysis intermediate frequency signal, where the initial vital signs include an initial respiration rate and an initial heart rate, respectively summarizing the initial respiration rate in the initial vital signs and the initial heart rate in the initial vital signs to obtain an initial respiration rate set and an initial heart rate set, where the initial respiration rate set includes multiple initial respiration rates, and the initial respiration rate corresponds to the frequency recognition model one by one;

[0044] Obtaining a respiration rate variance based on the initial respiration rate set, where the respiration rate variance is the variance of multiple initial respiration rates in the initial respiration rate set, and comparing the respiration rate variance and a preset frequency variance threshold;

[0045] If the respiration rate variance is greater than or equal to the frequency variance threshold, obtaining a respiration rate mean based on the initial respiration rate set, where the respiration rate mean is the mean of multiple initial respiration rates in the initial respiration rate set, and performing the following operations on each initial respiration rate in the initial respiration rate set:

[0046] Calculating the absolute difference between the initial respiration rate and the respiration rate mean to obtain a screening difference, summarizing the screening differences to obtain a screening difference set, performing a sorting operation on the screening differences in the screening difference set in descending order of the screening differences to obtain a screening difference sequence, and using the screening difference sequence to confirm a target respiration rate, where the target respiration rate is the initial respiration rate corresponding to the first screening difference in the screening difference sequence, removing the target respiration rate from the initial respiration rate set to obtain an updated respiration rate set, using the updated respiration rate set as the initial respiration rate set, and returning to the step of obtaining the respiration rate variance based on the initial respiration rate set until the respiration rate variance is less than the frequency variance threshold;

[0047] If the respiration rate variance is less than the frequency variance threshold, obtaining a detected respiration rate based on the initial respiration rate set, where the detected respiration rate is the average of multiple initial respiration rate sets in the initial respiration rate set;

[0048] Obtaining a detected heart rate based on the initial heart rate set, and associating the detected respiration rate and the detected heart rate to obtain the detected vital signs.

[0049] Optionally, obtaining the initial pose vector based on the initial pose includes:

[0050] Identifying a set of joint nodes in the initial pose, where the set of joint nodes includes a plurality of joint nodes, and performing the following operations on each joint node in the set of joint nodes:

[0051] Obtaining the three-dimensional coordinates and identification ordinal numbers of the joints based on the joint nodes, and using the three-dimensional coordinates and identification ordinal numbers of the joints to identify the joint nodes, so as to obtain the identified joint nodes;

[0052] Summarizing the identified joint nodes to obtain a set of identified joint nodes, sorting the identified joint nodes in the set of identified joint nodes in ascending order of the identification ordinal numbers to obtain an identified joint node sequence;

[0053] Successively extracting initial joint nodes from the identified joint node sequence, and performing the following operations on the extracted initial joint nodes:

[0054] Using the initial joint nodes to confirm target joint nodes in the identified joint node sequence, where the target joint nodes are adjacent to the initial joint nodes and lag behind the initial joint nodes;

[0055] Calculating the Euclidean distance between the three-dimensional coordinates of the joints corresponding to the initial joint nodes and the three-dimensional coordinates of the joints corresponding to the target joint nodes to obtain joint spacings, summarizing the joint spacings to obtain a set of joint spacings, sorting the joint spacings in the set of joint spacings in the order from the earliest to the latest time when the joint spacings are obtained to obtain a joint spacing sequence, and fitting the joint spacing sequence into the initial pose vector, where the initial pose vector is as follows:

[0056] W0 = {j1, j2, j3…, j a ,…j b}

[0057] Wherein, j1, j2, j3, j a respectively represent the first, second, third and the a-th joint spacings in the joint spacing sequence, and b represents that there are b joint spacings in the joint spacing sequence.

[0058] Optionally, confirming that the detected vital signs are preset normal vital signs includes:

[0059] Obtaining a reference heart rate range and a reference breathing rate range. When the detected breathing rate corresponding to the detected vital signs does not belong to the reference breathing rate range and the detected heart rate corresponding to the detected vital signs does not belong to the reference heart rate range, a pre-constructed sign warning signal is sent to the initiator of the angle adjustment instruction;

[0060] Otherwise, confirm that the detected vital signs are the normal vital signs.

[0061] Optionally, generating a visual adjustment result based on the driven target operating bed and the result presentation unit includes:

[0062] Obtain the visual parameters of each first adjustment unit in the multiple first adjustment units corresponding to the driven target operating bed. Among them, the visual parameters include adjustment height, initial size, initial position, adjustment angle, and monitoring pressure, and summarize the visual parameters to obtain a set of visual parameters;

[0063] Confirm to receive a visual instruction from the result presentation unit, obtain a patient representation model based on the visual instruction, and generate a set of visual models using the set of visual parameters. Among them, the set of visual models includes multiple visual models marked with monitoring pressure, and the visual models marked with monitoring pressure correspond one-to-one with the first adjustment units;

[0064] Confirm a set of constraint conditions according to the target selection pose, and construct a visual adjustment result using the set of constraint conditions, the set of visual models, and the patient representation model.

[0065] To solve the above problems, the present invention also provides an electronic device, which includes:

[0066] At least one processor; and,

[0067] A memory communicatively connected to the at least one processor; wherein,

[0068] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement the above-mentioned operating bed angle adjustment method based on patient pose recognition.

[0069] To solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned operating bed angle adjustment method based on patient pose recognition.

[0070] Compared with the problems described in the background art, the present invention first receives an angle adjustment instruction, and based on the angle adjustment instruction, determines an angle adjustment environment. Among them, the angle adjustment environment includes an angle adjustment system and a target operating bed. The angle adjustment system includes a pose selection unit, a result presentation unit, a pose recognition unit, and a vital sign monitoring unit. The target operating bed includes a plurality of first adjustment units, and the first adjustment unit includes an angle adjustment unit, a height adjustment unit, and a pressure monitoring unit. It can be seen that in the embodiment of the present invention, the target operating bed is set as a plurality of first adjustment units that can be individually adjusted in height and angle. Furthermore, it lays a foundation for improving the accuracy of the angle adjustment of the operating bed. And each first adjustment unit is equipped with a pressure monitoring unit, which can monitor the pressure borne by the first adjustment unit in real time through the pressure monitoring unit. Furthermore, it can timely feedback the force conditions of different parts of the patient. Furthermore, it improves the intelligent level of the target operating bed in the present invention when performing angle adjustment. The present invention constructs a pose adjustment database based on the angle adjustment system. Among them, the pose adjustment database stores a plurality of pose adjustment plan nodes, and the pose adjustment plan node includes a reference initial pose, a reference target pose, and a pose adjustment plan. It can be seen that before adjusting the angle of the target operating bed, the present invention also formulates a variety of pose adjustment plan nodes, and each pose adjustment plan takes into account the relevant characteristics of the patient, so that the formulated pose adjustment plan not only meets the requirement of accurate angle adjustment, but also considers the comfort of the patient, the time and energy consumption required for angle adjustment. Furthermore, it improves the intelligent level of the angle adjustment of the target operating bed. The present invention confirms to receive a vital sign monitoring instruction from the vital sign monitoring unit, analyzes the vital sign monitoring instruction to obtain a vital sign monitoring signal, obtains a detected vital sign based on the vital sign monitoring signal, and after confirming that the detected vital sign is a preset normal vital sign, generates a visual adjustment result based on the driven target operating bed and the result presentation unit to realize the adjustment of the angle of the target operating bed. It can be seen that in the embodiment of the present invention, when adjusting the angle of the target operating bed, it also considers the vital signs of the patient. When the vital signs of the patient are dangerous, it can give an early warning in time. Furthermore, it improves the intelligent level of the angle adjustment of the target operating bed, and can combine the actual situation of the patient to visually feedback the result after angle adjustment in a visual form. Furthermore, it is beneficial to read the force conditions of each part of the patient, thereby improving the intelligent level of the angle adjustment of the target operating bed. Therefore, the main purpose of the method, device, electronic device, and computer-readable storage medium for adjusting the angle of the operating bed based on patient pose recognition proposed by the present invention is to improve the accuracy and intelligent level of the angle adjustment of the operating bed. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 It is a schematic flowchart of a method for adjusting the angle of an operating bed based on patient pose recognition provided by an embodiment of the present invention;

[0072] Figure 2 A structural schematic diagram of an electronic device for implementing the surgical bed angle adjustment method based on patient pose recognition provided by an embodiment of the present invention.

[0073] The implementation, functional features and advantages of the present invention will be further described in conjunction with the embodiments and with reference to the accompanying drawings. Detailed implementation manners

[0074] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0075] An embodiment of the present application provides a surgical bed angle adjustment method based on patient pose recognition. The execution subject of the surgical bed angle adjustment method based on patient pose recognition includes, but is not limited to, at least one of an electronic device such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the surgical bed angle adjustment method based on patient pose recognition can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0076] Embodiment 1:

[0077] Refer to Figure 1 As shown, it is a flowchart of a surgical bed angle adjustment method based on patient pose recognition provided by an embodiment of the present invention. In this embodiment, the surgical bed angle adjustment method based on patient pose recognition includes:

[0078] S1. Receive an angle adjustment instruction, and confirm an angle adjustment environment based on the angle adjustment instruction. Among them, the angle adjustment environment includes an angle adjustment system and a target surgical bed. The angle adjustment system includes a pose selection unit, a result presentation unit, a pose recognition unit, and a physical sign monitoring unit. The target surgical bed includes a plurality of first adjustment units, and the first adjustment unit includes an angle adjustment unit, a height adjustment unit, and a pressure monitoring unit.

[0079] It should be explained that the angle adjustment instruction is an instruction for adjusting the angle of the target operating bed. The angle adjustment environment refers to the necessary environment for adjusting the angle of the target operating bed. The angle adjustment system includes a pose selection unit, a result presentation unit, a pose recognition unit, and a physical sign monitoring unit. The target operating bed includes a plurality of first adjustment units, and the first adjustment unit includes an angle adjustment unit, a height adjustment unit, and a pressure monitoring unit. For the specific applications of the units, please refer to the subsequent embodiments. Generally, before confirming the size and position of each first adjustment unit in the target operating bed, multiple medical staff can participate in setting the adjustable height, adjustable angle, and size of the first adjustment unit in combination with actual clinical experience. Optionally, a lifting bracket with a self-locking function is used as the height adjustment unit, and a screw-nut mechanism is used as the angle adjustment unit. The same effect can be achieved by using other technologies, which will not be elaborated here. The height adjustment unit and the angle adjustment unit can respectively adjust the height and inclination angle of the first adjustment unit, and the pressure monitoring unit is used to monitor the pressure received by the first adjustment unit. Optionally, a pressure sensor is used as the pressure monitoring unit, and the same effect can be achieved by using other technologies.

[0080] It can be understood that the embodiments of the present invention mainly aim to adjust the pose of the patient in combination with the actual situation of the patient, and the embodiments of the present invention aim to improve the accuracy and intelligence of adjusting the angle of the operating bed.

[0081] Exemplarily, before the operation on the patient, the attending doctor Zhang of the patient issues the angle adjustment instruction, and Zhang confirms the angle adjustment environment. Zhang selects the corresponding pose in the angle adjustment system in combination with the pose required for the operation, and uses the target operating bed to adjust the pose of the patient, so as to improve the intelligence of the operation on the patient. And Zhang considers that the pose of the patient may need to be adjusted during the operation due to surgical needs. Therefore, on the premise of not affecting the normal progress of the operation, Zhang can dynamically adjust the pose of the patient through the target operating bed.

[0082] S2. Construct a pose adjustment database based on the angle adjustment system, wherein the pose adjustment database stores a plurality of pose adjustment scheme nodes, and the pose adjustment scheme node includes a reference initial pose, a reference target pose, and a pose adjustment scheme.

[0083] It should be explained that constructing the pose adjustment database based on the angle adjustment system includes:

[0084] Obtain a set of simulation models for simulating a patient and a set of fitted poses for characterizing the patient's pose, where the set of simulation models includes multiple simulation models, and the set of fitted poses includes multiple fitted poses. In a combined form, use each simulation model in the multiple simulation models and each fitted pose in the multiple fitted poses to obtain multiple fitted adjustment nodes, where a fitted adjustment node includes a simulation model and a fitted pose;

[0085] Perform the following operations on each fitted adjustment node in the multiple fitted adjustment nodes:

[0086] Based on a pre-confirmed target adjustment pose and the fitted adjustment nodes, obtain multiple fitted adjustment schemes, and perform the following operations on each fitted adjustment scheme in the multiple fitted adjustment schemes:

[0087] Drive the target operating bed based on the fitted adjustment scheme, and use the pressure monitoring unit corresponding to each of the multiple first adjustment units corresponding to the target operating bed and the target operating bed in the drive to obtain a monitored pressure time series;

[0088] Summarize the monitored pressure time series to obtain a set of monitored pressure time series, and obtain a pose adjustment database based on the set of monitored pressure time series.

[0089] It should be understood that the simulation model refers to a model used to simulate the weight and height of a patient. Optionally, a biomechanical entity model is used as the simulation model, and the same effect can be achieved by using other technologies, which will not be elaborated here. The fitted pose is used to characterize the pose of the patient in the initial state. Here, the initial state refers to the body position of the patient on the target operating bed, and the fitted pose can also characterize the local characteristics of the patient. Generally, in practical applications, it is impossible to ensure that the positions where each patient lies on the operating bed are the same. Therefore, the fitted pose can also characterize the position where the patient or the simulation model lies on the operating bed. For example, models with the same height and weight may express different fitted poses when representing the same body position due to different local characteristics of the models during model construction. Here, the local characteristics are characteristics used to characterize different diseased states of the patient. The fitted adjustment scheme refers to a scheme composed of the relevant parameters of the first adjustment unit that need to be adjusted when adjusting the fitted pose corresponding to the simulation model to the target adjustment pose. Here, when adjusting the first adjustment unit, the adjustable parameters include: height and angle. For example, when the body position is lying flat, but this body position is represented by people with different heights or different weights, different poses can be obtained through this body position. The purpose of considering the pose in the present invention is: to improve the accuracy of angle adjustment of the target operating bed.

[0090] It is understandable that the acquisition method of the multiple fitting adjustment schemes can be obtained by using a pre-trained neural network model, a target adjustment pose, and fitting adjustment nodes. The same effect can be achieved by using other technologies, which will not be elaborated here. For example, taking whether the pose after adjustment of the patient is the target pose as the goal, the neural network model is trained. Furthermore, through the trained neural network model, the adjustment order for different first adjustment units among the multiple first adjustment units can be obtained, and it includes the height and angle required for adjusting the first adjustment unit. Generally, when adjusting with different fitting adjustment schemes, there may be a large difference between the fitting pose after adjustment and the target adjustment pose due to different adjustment schemes. Therefore, it is necessary to screen out the fitting adjustment scheme that can accurately and comfortably fit from multiple fitting adjustment schemes. For the specific screening process, please refer to the following embodiments.

[0091] Further, monitoring the pressure time series means the pressure time series obtained after using the pressure monitoring unit to monitor the pressure in the target operating bed during driving. Here, only one pressure monitoring unit is taken as an example, and the same effect can be achieved by the other pressure monitoring units, which will not be elaborated here. For example, a monitoring pressure set is obtained by using a preset monitoring frequency and the pressure monitoring unit. Among them, the monitoring pressure set includes multiple monitoring pressures. The monitoring pressures are sorted in the order of the time corresponding to the acquisition of the monitoring pressures from the earliest to the latest to obtain the monitoring pressure time series.

[0092] Further, obtaining the pose adjustment database based on the monitoring pressure time series set includes:

[0093] Obtain an evaluation index set for evaluating the fitting adjustment scheme. Based on the evaluation index set, the monitoring pressure time series set, and the pre-constructed analytic hierarchy process, obtain an initial evaluation value, where the initial evaluation value corresponds to the fitting adjustment scheme one by one;

[0094] Summarize the initial evaluation values to obtain an initial evaluation value set. Use a preset screening evaluation threshold to extract a target evaluation value set from the initial evaluation value set. Among them, the target evaluation value set includes multiple target evaluation values, and the target evaluation values are all greater than or equal to the screening evaluation threshold;

[0095] Perform the following operations on each target evaluation value in the target evaluation value set:

[0096] Calculate a comprehensive evaluation value based on the target evaluation value. The calculation formula is as follows:

[0097]

[0098] Among them, Z represents the comprehensive evaluation value, α, β, and γ are all preset coefficients, p represents the target evaluation value, t represents the time required when adopting the fitting adjustment scheme corresponding to the target evaluation value, h represents the height that the first adjustment unit needs to adjust, j represents the angle that the first adjustment unit needs to adjust, n represents the monitoring pressure during the adjustment of the first adjustment unit, m represents that a total of m first adjustment units are required in the fitting adjustment scheme corresponding to the target evaluation value to adjust the pose of the simulation model, and f(h, j, n) i represents the energy consumption function of the i-th first adjustment unit among the m first adjustment units during pose adjustment;

[0099] Summarize the comprehensive evaluation values to obtain a comprehensive evaluation value set, and use the comprehensive evaluation value set to confirm the target adjustment scheme. Among them, the target adjustment scheme is the fitting adjustment scheme corresponding to the smallest comprehensive evaluation value in the comprehensive evaluation value set;

[0100] Confirm the pose adjustment database based on the target adjustment scheme.

[0101] It should be explained that the evaluation indicators are a set of indicators used to evaluate the fitting adjustment scheme in combination with the monitoring pressure time series set. Optionally, the evaluation indicator set includes: safety indicators and reliability indicators, and the safety indicators include: posture naturalness and joint pressure distribution, and the reliability indicators include pose accuracy and joint angle. Among them, the joint pressure distribution and joint angle are both related to the monitoring pressure time series. Posture naturalness refers to whether the adjusted fitting pose conforms to the natural human posture. For example, whether there are joints with excessive torsion or bending. The joint pressure distribution is obtained by analyzing the monitoring pressure in the monitoring pressure time series. For example, when the change trend of the monitoring pressure time series is slow and the pressure distribution is uniform, it is considered that the joint pressure distribution is good. Therefore, a higher score is given to the joint pressure distribution in this case. Pose accuracy is used to characterize the accuracy between the adjusted fitting pose and the target adjustment pose. Optionally, after converting the adjusted fitting pose and the target adjustment pose into vectors, the Euclidean distance between the two vectors is solved for characterization. The same effect can be achieved by using other technologies, which will not be elaborated here. The joint angle refers to the angle of the simulation model at the target joint after adjustment, and is used to evaluate the stability of the simulation model maintaining this pose. Here, the target joint refers to the joint that needs to ensure the pose remains unchanged, and the target joint may be composed of more than one joint. For example, if the pose corresponding to the target joint is to ensure that the simulation model is in a lying flat position, the joint angle can be represented by the angle between the back of the simulation model and the operating table. When this angle is 0 degrees, it indicates that the simulation model is in a lying flat position, and when the simulation model is at 90 degrees, it indicates that the simulation model is in a side-lying position.

[0102] It is understandable that the technology of obtaining the initial evaluation value by using the analytic hierarchy process, the monitoring pressure time series set and the evaluation index set is the prior art and will not be elaborated here. Using the screening evaluation threshold to confirm the target evaluation value set in the initial evaluation value set is to eliminate the fitting adjustment solutions that do not meet the expected results when adjusting the pose of the simulation model. Thus, the fitting adjustment solutions that meet the expected results are retained. Generally speaking, when wanting to adjust the fitting pose to the target adjustment pose, there may be more than one fitting adjustment solution. Therefore, it is necessary to confirm the best fitting adjustment solution among multiple fitting adjustment solutions that meet the requirements. Here, the best adjustment solution refers to the target adjustment solution. In the embodiments of the present invention, the time and energy consumption required for pose adjustment are also considered when calculating the comprehensive evaluation value. Furthermore, the timeliness and intelligence degree of the target adjustment solution in response can be improved. Optionally, a support vector regression algorithm is used to construct an energy consumption function for monitoring pressure, height and angle. The same effect can be achieved by using other technologies and will not be elaborated here.

[0103] It should be explained that the pose adjustment database confirmed based on the target adjustment solution includes:

[0104] Obtain a pose image and a fitting pose vector based on the fitting pose corresponding to the target adjustment solution, and identify pose features in the pose image, where the pose features include pose length and pose width;

[0105] Obtain an initial monitoring pressure set by using the monitoring pressure time series set corresponding to the target adjustment solution, where the initial monitoring pressure set is a set of the first monitoring pressures in each monitoring pressure time series in the monitoring pressure time series set;

[0106] Associate the fitting pose, the target adjustment pose, the fitting pose vector, the pose features, the initial monitoring pressure set and the target adjustment solution to obtain pose adjustment nodes;

[0107] Summarize the pose adjustment nodes to obtain a pose adjustment database.

[0108] It is understandable that the pose image refers to the image of the fitting pose. The fitting pose vector refers to the vector corresponding to the fitting pose. The pose length and pose width express the characteristics of the simulation model in terms of body shape. Optionally, a target recognition algorithm and the pose image are used to obtain a recognition target box, and the length of the recognition target box is used as the pose length, and the width of the recognition target box is used as the pose width. The recognition target box refers to the smallest rectangular box containing the simulation model in the pose image, and the technology of obtaining the recognition target box by using the target recognition algorithm is the prior art and will not be elaborated here. The acquisition method of the fitting pose vector is the same as that of the initial pose vector and will not be elaborated here.

[0109] Exemplarily, there are 5 monitored pressure time series in the monitored pressure time series set, and the first monitored pressures in each of the 5 monitored pressure time series are: 230N, 240N, 250N, 245N, and 300N respectively. Then the initial monitored pressure set includes 230N, 240N, 250N, 245N, and 300N.

[0110] It should be explained that the definitions of the reference initial pose and the fitted pose are the same and will not be elaborated here. The definitions of the reference target pose and the target adjustment pose are the same and will not be elaborated here. The definition of the pose adjustment scheme is the same as the definition of the target adjustment scheme and will not be elaborated here.

[0111] S3. Extract the reference target pose set from the pose adjustment database, use the pose selection unit to receive the target selection pose selected by the user according to the reference target pose set, confirm the receipt of the pose recognition instruction from the pose recognition unit, confirm the initial pose of the patient based on the pose recognition instruction, extract the reference initial pose set from the pose adjustment database, and use the initial pose to identify the target retrieval pose in the reference initial pose set.

[0112] It should be explained that the step of using the initial pose to identify the target retrieval pose in the reference initial pose set includes:

[0113] Obtain the initial pose vector based on the initial pose, obtain the initial features of the patient and the reference monitored pressure set. Among them, the initial features include the feature length and the feature width, and the reference monitored pressure set includes multiple reference monitored pressures. Sort the reference monitored pressures in the reference monitored pressure set in descending order of the reference monitored pressure to obtain the reference monitored pressure sequence;

[0114] Associate the initial pose vector, the initial features, and the reference monitored pressure sequence to obtain the retrieval pose node;

[0115] Perform the following operations on each reference initial pose in the reference initial pose set:

[0116] Identify the fitted pose vector, pose features, and initial monitored pressure set corresponding to the reference initial pose in the pose adjustment database to obtain the identified pose node. Obtain the initial monitored pressure sequence based on the initial monitored pressure set, update the identified pose node using the initial monitored pressure sequence to obtain the matching pose node, and calculate the node similarity using the pre-constructed pose similarity formula, the matching pose node, and the retrieval pose node;

[0117] Summarize the node similarities to obtain the node similarity set, and confirm the target retrieval pose based on the node similarity set. Among them, the target retrieval pose is the reference initial pose corresponding to the maximum node similarity in the node similarity set.

[0118] Further, the acquisition method of the reference monitoring pressure set is the same as that of the initial monitoring pressure set, which will not be elaborated here. The method of obtaining the initial monitoring pressure sequence using the initial monitoring pressure set is the same as the method of obtaining the reference monitoring pressure sequence using the reference monitoring pressure set, which will not be elaborated here. Updating the recognition pose node using the initial monitoring pressure sequence means updating the initial monitoring pressure set in the recognition pose node to the initial monitoring pressure sequence.

[0119] It can be understood that the pose similarity formula is as follows:

[0120]

[0121] Among them, X represents the node similarity, ω1, ω2, ω3 are all preset coefficients, CS() represents calculating the cosine similarity, DS() represents calculating the Euclidean distance, W0 and W1 respectively represent the initial pose vector corresponding to the retrieved pose node and the fitted pose vector corresponding to the matching pose node, P0 and P1 respectively represent the reference monitoring pressure sequence corresponding to the retrieved pose node and the initial monitoring pressure sequence corresponding to the matching pose node, and z0 and z1 respectively represent the initial feature corresponding to the retrieved pose node and the pose feature corresponding to the matching pose node.

[0122] Further, the reference monitoring pressure sequence or the initial monitoring pressure sequence is not only related to the patient's pose, but may also be related to factors such as the patient's habits and physical characteristics. Therefore, the number of reference monitoring pressures in the reference monitoring pressure sequence may not be the same as the number of initial monitoring pressures in the initial monitoring pressure sequence. Here, by adopting the method of setting different coefficients, the accuracy of calculating the node similarity is improved. Generally, when the dimensions of two vectors are different, they cannot be calculated. Therefore, before calculating two vectors with different dimensions, it is necessary to unify the dimensions of the two vectors. In the embodiments of the present invention, the dimensions of the two vectors are unified in the form of filling 0. The same effect can be achieved by using other technologies, which will not be elaborated here. The definitions of the initial feature and the pose feature are the same, which will not be elaborated here. The definition of the initial pose is the same as the definition of the reference initial pose, which will not be elaborated here.

[0123] S4. Based on the target selection pose and the target retrieval pose, retrieve the target pose adjustment scheme in the pose adjustment database, and use the target pose adjustment scheme to drive the target operating bed.

[0124] It is understandable that the target selection pose and the target retrieval pose are the initial pose of the patient and the pose that the patient needs to maintain, respectively. Generally, the target retrieval pose also considers factors such as the patient's body shape. Therefore, through the target retrieval pose and the target selection pose, a target pose adjustment plan that better meets the adjustment requirements can be retrieved from the pose adjustment database. For example, when the patient has a disability, the patient's initial pose may not be able to represent the characteristics of the patient's body shape. Therefore, by combining the initial monitoring pressure sequence and the initial features used to represent the patient's body shape distribution, a target pose adjustment plan that better suits the patient's body shape can be accurately retrieved from the pose adjustment database, thereby improving the accuracy and intelligence of the angle adjustment of the operating table. Driving the target operating table using the target pose adjustment plan means adjusting the height and angle required for the first adjustment unit in the target operating table to the height and angle required according to each first adjustment unit to be adjusted in the target pose adjustment plan.

[0125] S5. Confirm the receipt of the physical sign monitoring instruction from the physical sign monitoring unit, parse the physical sign monitoring instruction to obtain a physical sign monitoring signal, obtain the detected vital signs based on the physical sign monitoring signal, and after confirming that the detected vital signs are the preset normal vital signs, generate a visual adjustment result based on the driven target operating table and the result presentation unit to achieve the adjustment of the angle of the target operating table.

[0126] Further, the obtaining of the detected vital signs based on the physical sign monitoring signal includes:

[0127] Obtain a physical sign echo signal based on the physical sign monitoring signal, obtain an analysis intermediate frequency signal using the physical sign monitoring signal and the physical sign echo signal, and obtain a frequency recognition model set for frequency recognition, where the frequency recognition model set includes multiple frequency recognition models, and perform the following operations on each frequency recognition model in the frequency recognition model set:

[0128] Obtain the initial vital signs using the frequency recognition model and the analysis intermediate frequency signal, where the initial vital signs include the initial respiratory rate and the initial heart rate. Summarize the initial respiratory rate in the initial vital signs and the initial heart rate in the initial vital signs respectively to obtain an initial respiratory rate set and an initial heart rate set, where the initial respiratory rate set includes multiple initial respiratory rates, and the initial respiratory rate corresponds to the frequency recognition model one by one;

[0129] Obtain the respiratory rate variance based on the initial respiratory rate set, where the respiratory rate variance is the variance of multiple initial respiratory rates in the initial respiratory rate set, and compare the respiratory rate variance with a preset frequency variance threshold;

[0130] If the variance of the respiration frequency is greater than or equal to the frequency variance threshold, obtain the mean respiration frequency based on the initial respiration frequency set, where the mean respiration frequency is the mean of multiple initial respiration frequencies in the initial respiration frequency set. Perform the following operations on each initial respiration frequency in the initial respiration frequency set:

[0131] Calculate the absolute difference between the initial respiration frequency and the mean respiration frequency to obtain a screening difference. Aggregate the screening differences to obtain a screening difference set. Perform a sorting operation on the screening differences in the screening difference set in descending order of the screening differences to obtain a screening difference sequence. Use the screening difference sequence to identify the target respiration frequency, where the target respiration frequency is the initial respiration frequency corresponding to the first screening difference in the screening difference sequence. Remove the target respiration frequency from the initial respiration frequency set to obtain an updated respiration frequency set. Use the updated respiration frequency set as the initial respiration frequency set, and return to the step of obtaining the respiration frequency variance based on the initial respiration frequency set until the respiration frequency variance is less than the frequency variance threshold;

[0132] If the respiration frequency variance is less than the frequency variance threshold, obtain the detected respiration frequency based on the initial respiration frequency set, where the detected respiration frequency is the average of multiple initial respiration frequencies in the initial respiration frequency set;

[0133] Obtain the detected heart rate based on the initial heart rate set, and associate the detected respiration frequency and the detected heart rate to obtain the detected vital signs.

[0134] It should be explained that the vital sign monitoring signal refers to the signal used to monitor the vital signs of a patient. Optionally, the vital sign monitoring signal is the transmission signal of a millimeter radar. The vital sign echo signal refers to the echo signal corresponding to the vital sign monitoring signal. The analysis intermediate frequency signal refers to the intermediate frequency signal of the vital sign monitoring signal and the vital sign echo signal. The methods of obtaining the vital sign echo signal using the vital sign monitoring signal and obtaining the analysis intermediate frequency signal using the vital sign monitoring signal and the vital sign echo signal are all prior arts and will not be elaborated here. The frequency recognition model refers to the model or algorithm used to recognize the heart rate and respiration frequency of a patient. Optionally, the variational mode decomposition algorithm is used as the frequency recognition model. The same effect can be achieved using other technologies and will not be elaborated here. The target operating bed after driving refers to the target operating bed that has completed the angle adjustment.

[0135] Generally, since the probability that the frequency recognition model correctly recognizes the heartbeat frequency and the breathing frequency is not 100%, analyzing the results recognized by multiple frequency recognition models can improve the accuracy of the obtained patient's heartbeat frequency and patient's breathing frequency. When the variance of the breathing frequency is greater than or equal to the frequency variance threshold, it indicates that there are relatively large errors in some of the initial breathing frequencies in the initial breathing frequency set obtained by using the frequency recognition model set, and this error may be caused by the misrecognition of the frequency recognition model.

[0136] Furthermore, the larger the screening difference, the greater the difference between the initial breathing frequency corresponding to the screening difference and the remaining initial breathing frequencies in the initial breathing frequency set. Therefore, it is determined that the initial breathing frequency corresponding to the screening difference is the misrecognized initial breathing frequency. When the variance of the breathing frequency is less than the frequency variance threshold, it indicates that the initial breathing frequencies in the initial breathing frequency set are relatively consistent. Therefore, obtaining the detected breathing frequency at this time can improve the accuracy of the obtained detected breathing frequency. The obtaining method of the detected heartbeat frequency is the same as that of the detected breathing frequency and will not be elaborated here.

[0137] It can be understood that obtaining the initial pose vector based on the initial pose includes:

[0138] Identifying a set of joint nodes in the initial pose, where the set of joint nodes includes multiple joint nodes, and performing the following operations on each joint node in the set of joint nodes:

[0139] Obtaining the three-dimensional joint coordinates and the identification ordinal number based on the joint node, and using the three-dimensional joint coordinates and the identification ordinal number to label the joint node to obtain the labeled joint node;

[0140] Summarizing the labeled joint nodes to obtain a set of labeled joint nodes, and sorting the labeled joint nodes in the set of labeled joint nodes in ascending order of the identification ordinal number to obtain a sequence of labeled joint nodes;

[0141] Successively extracting initial joint nodes from the sequence of labeled joint nodes, and performing the following operations on the extracted initial joint nodes:

[0142] Using the initial joint node to confirm a target joint node in the sequence of labeled joint nodes, where the target joint node is adjacent to the initial joint node and lags behind the initial joint node;

[0143] Calculate the Euclidean distance between the three-dimensional joint coordinates corresponding to the initial joint nodes and the three-dimensional joint coordinates corresponding to the target joint nodes to obtain the joint spacing. Aggregate the joint spacings to obtain a set of joint spacings. Sort the joint spacings in the set of joint spacings in the order of the time corresponding to obtaining the joint spacings to obtain a joint spacing sequence. Fit the joint spacing sequence to the initial pose vector, where the initial pose vector is as follows:

[0144] W0 = {j1, j2, j3…, j a ,…j b}

[0145] where j1, j2, j3, j a respectively represent the first, second, third, and the a-th joint spacings in the joint spacing sequence, and b represents that there are b joint spacings in the joint spacing sequence.

[0146] It should be understood that a joint node refers to a node used to represent the position of a patient's joint. For example, the patient's knee, head, etc. are all the joint nodes. Optionally, a set of joint nodes is identified in the initial pose through a pre-trained neural network model. The three-dimensional joint coordinates refer to the three-dimensional coordinates used to represent the joint nodes. The acquisition method of the three-dimensional joint coordinates is the same as the acquisition method of the joint nodes, which will not be elaborated here. The identification ordinal number refers to a value used to represent the order of each joint node in the set of joint nodes. For example, when three different joint nodes are identified in the initial pose, the identification ordinal numbers can be obtained according to the order from top to bottom and from left to right. The identification ordinal number corresponding to the joint node in the upper left corner among the three different joint nodes is 1, and the identification ordinal number corresponding to the joint node in the lower right corner among the three different joint nodes is 3.

[0147] Exemplarily, if the identified joint node sequence includes 4 identified joint nodes, the first initial joint node extracted is the first identified joint node in the identified joint node sequence. The target joint node confirmed using the initial joint node is the second identified joint node in the identified joint node sequence. The first joint spacing in the joint spacing sequence is the Euclidean distance between the three-dimensional joint coordinates corresponding to the first identified joint node and the three-dimensional joint coordinates corresponding to the second identified joint node.

[0148] Further, the confirmation that the detected vital signs are preset normal vital signs includes:

[0149] Obtain the reference heart rate range and the reference breathing rate range. When the detected breathing rate corresponding to the detected vital signs does not belong to the reference breathing rate range and the detected heart rate corresponding to the detected vital signs does not belong to the reference heart rate range, a pre-constructed sign warning signal is sent to the initiator of the angle adjustment instruction;

[0150] Otherwise, confirm that the detected vital signs are the normal vital signs.

[0151] It should be explained that the reference heart rate range refers to the heart rate range of normal people, and the reference breathing rate range refers to the breathing rate range of normal people. The sign warning signal is a signal used to prompt the abnormal signs of the patient on the target operating bed. The normal vital signs are to confirm the normal signs of the patient on the target operating bed.

[0152] It can be understood that the generation of the visual adjustment result based on the driven target operating bed and the result presentation unit includes:

[0153] Obtain the visual parameters of each of the multiple first adjustment units corresponding to the driven target operating bed, where the visual parameters include the adjustment height, initial size, initial position, adjustment angle, and monitoring pressure, and summarize the visual parameters to obtain a visual parameter set;

[0154] Confirm that a visual instruction is received from the result presentation unit, obtain a patient representation model based on the visual instruction, and generate a visual model set using the visual parameter set, where the visual model set includes multiple visual models marked with monitoring pressure, and the visual models marked with monitoring pressure correspond one-to-one with the first adjustment units;

[0155] Confirm a set of constraint conditions according to the target selection pose, and construct a visual adjustment result using the set of constraint conditions, the visual model set, and the patient representation model.

[0156] It should be noted that the adjusted height and adjusted angle respectively refer to the height and angle adjusted when adjusting the height and angle of the first adjustment unit. The initial size refers to the size of the first adjustment unit, and the initial size includes but is not limited to the length, width, and height of the first adjustment unit. The initial position refers to the position of the first adjustment unit on the target operating bed, and this initial position can be represented by three-dimensional coordinates. The same effect can be achieved using other technologies, which will not be elaborated here. The monitored pressure refers to the pressure monitored by the pressure monitoring unit in the first adjustment unit. The patient representation model refers to a model used to represent the patient's pose. Optionally, the patient representation model is obtained through three-dimensional reconstruction technology. The visualization model refers to a model generated using the adjusted height, adjusted angle, initial position, and initial size, and this model is used to represent the first adjustment unit. The purpose of marking the monitored pressure on the visualization model is to present the force-bearing conditions of different parts of the patient, and then, in combination with the actual feelings of the patient, adjust the angle of the target operating bed. For example, if the monitored pressure corresponding to the visualization model is 200 N, then this visualization model is marked as the 200-visualization model. The same effect can be achieved using other technologies, which will not be elaborated here. The constraint condition set refers to a set of constraint conditions used to constrain the visualization model and the patient representation model. The constraint condition set includes but is not limited to: fixation, parallelism. Generally, each first adjustment unit corresponds to a visualization model, and the positions where different first adjustment units contact the patient are different. For example, different first adjustment units may respectively contact the patient's back and buttocks. The construction of the visualization adjustment result using the constraint condition set, the visualization model set, and the patient representation model refers to assembling the visualization models in the visualization model set and the patient representation model using the constraint condition set to generate a three-dimensional model that can represent the patient's pose on the target operating bed, the contact situation between the first adjustment unit and the patient, and the force-bearing situation of the first adjustment unit. This three-dimensional model is the visualization adjustment result. Here, the three-dimensional model of the contact situation between the first adjustment unit and the patient and the force-bearing situation of the first adjustment unit are represented by the height, angle, and monitored pressure of the first adjustment unit.

[0157] Compared with the problems described in the background art, the present invention first receives an angle adjustment instruction, and based on the angle adjustment instruction, an angle adjustment environment is confirmed. Among them, the angle adjustment environment includes an angle adjustment system and a target operating bed. The angle adjustment system includes a pose selection unit, a result presentation unit, a pose recognition unit, and a vital sign monitoring unit. The target operating bed includes a plurality of first adjustment units, and the first adjustment unit includes an angle adjustment unit, a height adjustment unit, and a pressure monitoring unit. It can be seen that in the embodiment of the present invention, the target operating bed is set as a plurality of first adjustment units that can be individually adjusted in height and angle. Furthermore, it lays a foundation for improving the accuracy of the angle adjustment of the operating bed. Moreover, each first adjustment unit is equipped with a pressure monitoring unit, which can monitor the pressure borne by the first adjustment unit in real time through the pressure monitoring unit. Furthermore, it can timely feedback the force-bearing conditions of different parts of the patient. Furthermore, it improves the intelligence level of the target operating bed during angle adjustment in the embodiment of the present invention. The present invention constructs a pose adjustment database based on the angle adjustment system. Among them, the pose adjustment database stores a plurality of pose adjustment plan nodes, and the pose adjustment plan node includes a reference initial pose, a reference target pose, and a pose adjustment plan. It can be seen that before the angle adjustment of the target operating bed, the present invention also formulates a variety of pose adjustment plan nodes, and each pose adjustment plan takes into account the relevant characteristics of the patient, so that the formulated pose adjustment plan not only meets the requirement of accurate angle adjustment, but also takes into account the comfort of the patient, the time and energy consumption required for angle adjustment. Furthermore, it improves the intelligence level of the angle adjustment of the target operating bed. The present invention confirms to receive a vital sign monitoring instruction from the vital sign monitoring unit, analyzes the vital sign monitoring instruction to obtain a vital sign monitoring signal, obtains a detected vital sign based on the vital sign monitoring signal, and after confirming that the detected vital sign is a preset normal vital sign, generates a visual adjustment result based on the driven target operating bed and the result presentation unit to realize the adjustment of the angle of the target operating bed. It can be seen that in the embodiment of the present invention, when adjusting the angle of the target operating bed, the vital signs of the patient are also considered. When the vital signs of the patient are dangerous, an early warning can be given in time. Furthermore, it improves the intelligence level of the angle adjustment of the target operating bed, and can combine the actual situation of the patient to intuitively feedback the result after angle adjustment in a visual form. Furthermore, it is beneficial to read the force-bearing conditions of each part of the patient, thereby improving the intelligence level of the angle adjustment of the target operating bed. Therefore, the method, device, electronic device, and computer-readable storage medium for adjusting the angle of the operating bed based on patient pose recognition proposed by the present invention mainly aim to improve the accuracy and intelligence level of the angle adjustment of the operating bed.

[0158] Embodiment 2:

[0159] Such as Figure 2As shown, it is a schematic structural diagram of an electronic device for implementing a surgical bed angle adjustment method based on patient pose recognition provided by an embodiment of the present invention.

[0160] The electronic device 1 may include a processor 10, a memory 11, a bus 12, and a communication interface 13, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a surgical bed angle adjustment program based on patient pose recognition.

[0161] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as the mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 may include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 can be used not only to store application software installed on the electronic device 1 and various types of data, such as the code of a surgical bed angle adjustment program based on patient pose recognition, but also to temporarily store data that has been output or will be output.

[0162] The processor 10 may be composed of integrated circuits in some embodiments. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same or different functions, including a combination of one or more Central Processing Units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and lines, and by running or executing programs or modules stored in the memory 11 (such as a surgical bed angle adjustment program based on patient pose recognition, etc.), and calling data stored in the memory 11, to execute various functions of the electronic device 1 and process data.

[0163] The bus can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable connection and communication between the memory 11 and at least one processor 10, etc.

[0164] Figure 2 Only the electronic device with components is shown. Those skilled in the art can understand that Figure 2 the shown structure does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have a different component arrangement.

[0165] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charge management, discharge management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may further include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0166] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0167] Optionally, the electronic device 1 may further include a user interface. The user interface may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0168] It should be understood that the above embodiments are only for illustration purposes and are not limited by this structure in the scope of the patent application.

[0169] The surgical bed angle adjustment program based on patient pose recognition stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve the following:

[0170] Receive an angle adjustment instruction, and confirm an angle adjustment environment based on the angle adjustment instruction. Among them, the angle adjustment environment includes an angle adjustment system and a target surgical bed. The angle adjustment system includes a pose selection unit, a result presentation unit, a pose recognition unit, and a vital sign monitoring unit. The target surgical bed includes multiple first adjustment units, and the first adjustment unit includes an angle adjustment unit, a height adjustment unit, and a pressure monitoring unit;

[0171] Construct a pose adjustment database based on the angle adjustment system. The pose adjustment database stores multiple pose adjustment plan nodes, and the pose adjustment plan node includes a reference initial pose, a reference target pose, and a pose adjustment plan;

[0172] Extract a set of reference target poses from the pose adjustment database. Use the pose selection unit to receive the target selection pose selected by the user according to the set of reference target poses, confirm the receipt of the pose recognition instruction from the pose recognition unit, confirm the initial pose of the patient based on the pose recognition instruction, extract a set of reference initial poses from the pose adjustment database, and use the initial pose to identify the target retrieval pose in the set of reference initial poses;

[0173] Retrieve a target pose adjustment plan from the pose adjustment database based on the target selection pose and the target retrieval pose, and drive the target surgical bed using the target pose adjustment plan;

[0174] Confirm the receipt of the vital sign monitoring instruction from the vital sign monitoring unit, parse the vital sign monitoring instruction to obtain a vital sign monitoring signal, obtain the detected vital signs based on the vital sign monitoring signal, and after confirming that the detected vital signs are preset normal vital signs, generate a visual adjustment result based on the driven target surgical bed and the result presentation unit to achieve the adjustment of the angle of the target surgical bed.

[0175] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 2 The description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0176] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM, Read-Only Memory).

[0177] The present invention also provides a computer-readable storage medium storing a computer program, which when executed by a processor of an electronic device, can implement:

[0178] Receiving an angle adjustment instruction, and confirming an angle adjustment environment based on the angle adjustment instruction, where the angle adjustment environment includes an angle adjustment system and a target operating bed. The angle adjustment system includes a pose selection unit, a result presentation unit, a pose recognition unit, and a vital sign monitoring unit. The target operating bed includes a plurality of first adjustment units, and the first adjustment unit includes an angle adjustment unit, a height adjustment unit, and a pressure monitoring unit;

[0179] Constructing a pose adjustment database based on the angle adjustment system, where the pose adjustment database stores a plurality of pose adjustment plan nodes, and the pose adjustment plan node includes a reference initial pose, a reference target pose, and a pose adjustment plan;

[0180] Extracting a reference target pose set from the pose adjustment database, using the pose selection unit to receive a target selection pose selected by the user according to the reference target pose set, confirming to receive a pose recognition instruction from the pose recognition unit, confirming the initial pose of the patient based on the pose recognition instruction, extracting a reference initial pose set from the pose adjustment database, and using the initial pose to identify a target retrieval pose in the reference initial pose set;

[0181] Retrieving a target pose adjustment plan in the pose adjustment database based on the target selection pose and the target retrieval pose, and driving the target operating bed using the target pose adjustment plan;

[0182] Confirming to receive a vital sign monitoring instruction from the vital sign monitoring unit, parsing the vital sign monitoring instruction to obtain a vital sign monitoring signal, obtaining a detected vital sign based on the vital sign monitoring signal, and after confirming that the detected vital sign is a preset normal vital sign, generating a visual adjustment result based on the driven target operating bed and the result presentation unit to realize the adjustment of the angle of the target operating bed.

[0183] The module described as a separation component may or may not be physically separated. The component shown as a module may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0184] In addition, in each embodiment of the present invention, each functional module may be integrated in a processing unit, may be physically present individually in each unit, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0185] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for adjusting the angle of an operating table based on patient posture recognition, characterized in that: The method comprises: receiving an angle adjustment instruction, and confirming an angle adjustment environment based on the angle adjustment instruction, wherein the angle adjustment environment includes an angle adjustment system and a target operating table, wherein the angle adjustment system includes a posture selection unit, a result presentation unit, a posture recognition unit, and a vital sign monitoring unit, and the target operating table includes a plurality of first adjustment units, and the first adjustment units include an angle adjustment unit, a height adjustment unit, and a pressure monitoring unit; Building a posture adjustment database based on the angle adjustment system, wherein the posture adjustment database stores a plurality of posture adjustment solution nodes, and the posture adjustment solution nodes include a reference initial posture, a reference target posture, and a posture adjustment solution; Extracting a reference target posture set from the posture adjustment database, using a posture selection unit to receive a target selection posture selected by a user according to the reference target posture set, confirming receipt of a posture recognition instruction from a posture recognition unit, confirming an initial posture of the patient based on the posture recognition instruction, extracting a reference initial posture set from the posture adjustment database, and using the initial posture to identify a target retrieval posture in the reference initial posture set; Based on the target selection posture and the target retrieval posture, a target posture adjustment scheme is retrieved from a posture adjustment database, and the target operating table is driven by using the target posture adjustment scheme; Confirm receipt of a vital sign monitoring instruction from a vital sign monitoring unit, parse the vital sign monitoring instruction, obtain a vital sign monitoring signal, acquire detected vital signs based on the vital sign monitoring signal, and after confirming that the detected vital signs are preset normal vital signs, generate a visualized adjustment result based on the driven target operating bed and the result presentation unit, so as to achieve adjustment of the angle of the target operating bed.

2. The method for adjusting the angle of an operating table based on patient posture recognition according to claim 1, characterized in that: The constructing of a posture adjustment database based on the angle adjustment system comprises: Acquire a simulation model set for simulating a patient and a fitting pose set for characterizing a patient's posture, wherein the simulation model set includes a plurality of simulation models, and the fitting pose set includes a plurality of fitting poses, and acquire a plurality of fitting adjustment nodes in a combined form by using each simulation model in the plurality of simulation models and each fitting pose in the plurality of fitting poses, wherein the fitting adjustment node includes a simulation model and a fitting pose; The following operations are performed on each of the multiple fitting adjustment nodes: Based on the pre-confirmed target adjustment posture and the fitting adjustment node, multiple fitting adjustment schemes are obtained, and the following operations are performed on each of the multiple fitting adjustment schemes: The target operating table is driven based on the fitting adjustment scheme, and a pressure monitoring time sequence is acquired by using a pressure monitoring unit corresponding to each of a plurality of first adjustment units corresponding to the target operating table and the target operating table being driven; The monitoring pressure time series are summarized to obtain a monitoring pressure time series set, and a posture adjustment database is obtained based on the monitoring pressure time series set.

3. The method for adjusting the angle of an operating table based on patient posture recognition according to claim 2, characterized in that: The acquiring of a posture adjustment database based on the monitored pressure time series set includes: Acquire an evaluation indicator set for evaluating the fitting adjustment scheme, and acquire an initial evaluation value based on the evaluation indicator set, the monitoring pressure time series set, and a pre-built hierarchical analysis method, wherein the initial evaluation value corresponds to the fitting adjustment scheme one by one; Summarizing the initial evaluation values ​​to obtain an initial evaluation value set, and using a preset screening evaluation threshold to extract a target evaluation value set from the initial evaluation value set, wherein the target evaluation value set includes multiple target evaluation values, and all target evaluation values ​​are greater than or equal to the screening evaluation threshold; For each target evaluation value in the target evaluation value set, the following operations are performed: The comprehensive evaluation value is calculated based on the target evaluation value, and the calculation formula is as follows: Wherein, Z represents the comprehensive evaluation value, α, β, and γ are all preset coefficients, p represents the target evaluation value, t represents the time required for adopting the fitting adjustment scheme corresponding to the target evaluation value, h represents the height that the first adjustment unit needs to adjust, j represents the angle that the first adjustment unit needs to adjust, n represents the monitoring pressure of the first adjustment unit when adjusting, m represents that a total of m first adjustment units are required in the fitting adjustment scheme corresponding to the target evaluation value to adjust the posture of the simulation model, and f(h,j,n) i represents the energy consumption function of the i-th first adjustment unit among the m first adjustment units when performing posture adjustment; Summarizing the comprehensive evaluation values ​​to obtain a comprehensive evaluation value set, and using the comprehensive evaluation value set to determine a target adjustment scheme, wherein the target adjustment scheme is a fitting adjustment scheme corresponding to the smallest comprehensive evaluation value in the comprehensive evaluation value set; A posture adjustment database is identified based on the target adjustment solution.

4. The method for adjusting the angle of an operating table based on patient posture recognition according to claim 3, characterized in that: The step of confirming a posture adjustment database based on the target adjustment scheme includes: Acquire a posture image and a fitting posture vector based on the fitting posture corresponding to the target adjustment scheme, and identify posture features in the posture image, wherein the posture features include posture length and posture width; Using the monitoring pressure time series set corresponding to the target adjustment scheme to obtain an initial monitoring pressure set, wherein the initial monitoring pressure set is a set of the first monitoring pressure in each monitoring pressure time series in the monitoring pressure time series set; Associating the fitting posture, the target adjustment posture, the fitting posture vector, the posture feature, the initial monitoring pressure set and the target adjustment scheme to obtain a posture adjustment node; The posture adjustment nodes are aggregated to obtain a posture adjustment database.

5. The method for adjusting the angle of an operating table based on patient posture recognition according to claim 4, characterized in that: The method of using the initial pose to identify the target retrieval pose in the reference initial pose set includes: Based on the initial posture, an initial posture vector is obtained, and an initial feature and a reference monitoring pressure set of the patient are obtained, wherein the initial feature includes a feature length and a feature width, and the reference monitoring pressure set includes a plurality of reference monitoring pressures, and the reference monitoring pressures in the reference monitoring pressure set are sorted in descending order to obtain a reference monitoring pressure sequence; Associating the initial posture vector, the initial feature and the reference monitoring pressure sequence to obtain a retrieval posture node; For each reference initial pose in the reference initial pose set, perform the following operations: Identify the fitting posture vector, posture feature and initial monitoring pressure set corresponding to the reference initial posture in the posture adjustment database to obtain the identification posture node, obtain the initial monitoring pressure sequence based on the initial monitoring pressure set, update the identification posture node using the initial monitoring pressure sequence to obtain the matching posture node, and calculate the node similarity using the pre-constructed posture similarity formula, matching posture node and retrieval posture node; The node similarities are summarized to obtain a node similarity set, and a target retrieval pose is determined based on the node similarity set, wherein the target retrieval pose is a reference initial pose corresponding to the largest node similarity in the node similarity set.

6. The method for adjusting the angle of an operating table based on patient posture recognition according to claim 5, characterized in that: The posture similarity formula is as follows: Among them, X represents the node similarity, ω1, ω2, ω3 are all preset coefficients, CS() represents the calculation of cosine similarity, DS() represents the calculation of Euclidean distance, W0 and W1 represent the initial pose vector corresponding to the retrieval pose node and the fitting pose vector corresponding to the matching pose node, respectively, p0 and p1 represent the reference monitoring pressure sequence corresponding to the retrieval pose node and the initial monitoring pressure sequence corresponding to the matching pose node, respectively, z0 and z1 represent the initial features corresponding to the retrieval pose node and the pose features corresponding to the matching pose node, respectively.

7. The method for adjusting the angle of an operating table based on patient posture recognition according to claim 6, characterized in that: The acquiring and detecting vital signs based on the vital sign monitoring signal comprises: A vital sign echo signal is obtained based on the vital sign monitoring signal, and an intermediate frequency signal is obtained and analyzed using the vital sign monitoring signal and the vital sign echo signal to obtain a frequency recognition model set for realizing frequency recognition, wherein the frequency recognition model set includes multiple frequency recognition models, and the following operations are performed on each frequency recognition model in the frequency recognition model set: The frequency recognition model is used to analyze the intermediate frequency signal to obtain initial vital signs, wherein the initial vital signs include initial respiratory frequency and initial heart rate, and the initial respiratory frequency in the initial vital signs and the initial heart rate in the initial vital signs are respectively summarized to obtain an initial respiratory frequency set and an initial heart rate set, wherein the initial respiratory frequency set includes multiple initial respiratory frequencies, and the initial respiratory frequencies correspond to the frequency recognition model one by one; Acquire a respiratory frequency variance based on the initial respiratory frequency set, wherein the respiratory frequency variance is the variance of multiple initial respiratory frequencies in the initial respiratory frequency set, and compare the respiratory frequency variance with a preset frequency variance threshold; If the respiratory frequency variance is greater than or equal to the frequency variance threshold, a respiratory frequency mean is obtained based on the initial respiratory frequency set, wherein the respiratory frequency mean is the mean of multiple initial respiratory frequencies in the initial respiratory frequency set, and the following operations are performed on the initial respiratory frequencies in the initial respiratory frequency set: Calculate the absolute difference between the initial respiratory frequency and the mean respiratory frequency to obtain a screening difference, summarize the screening differences to obtain a screening difference set, perform a sorting operation on the screening differences in the screening difference set in descending order to obtain a screening difference sequence, and use the screening difference sequence to confirm the target respiratory frequency, wherein the target respiratory frequency is the initial respiratory frequency corresponding to the first screening difference in the screening difference sequence, remove the target respiratory frequency from the initial respiratory frequency set to obtain an updated respiratory frequency set, use the updated respiratory frequency set as the initial respiratory frequency set, and return to the step of obtaining the respiratory frequency variance based on the initial respiratory frequency set until the respiratory frequency variance is less than the frequency variance threshold; If the respiratory frequency variance is less than the frequency variance threshold, acquiring a detected respiratory frequency based on the initial respiratory frequency set, wherein the detected respiratory frequency is an average value of multiple initial respiratory frequency sets in the initial respiratory frequency set; The detected heart rate is acquired based on the initial heart rate set, and the detected respiratory rate and the detected heart rate are associated to obtain the detected vital signs.

8. The method for adjusting the angle of an operating table based on patient posture recognition according to claim 7, characterized in that: The obtaining of an initial posture vector based on the initial posture comprises: A joint node set is identified in the initial pose, wherein the joint node set includes a plurality of joint nodes, and the following operations are performed on each joint node in the joint node set: Acquire a joint three-dimensional coordinate and an identification ordinal number based on the joint node, identify the joint node using the joint three-dimensional coordinate and the identification ordinal number, and obtain an identified joint node; Summarize the identified joint nodes to obtain an identified joint node set, and sort the identified joint nodes in the identified joint node set in ascending order of the identification ordinal numbers to obtain an identified joint node sequence; The initial joint nodes are extracted in sequence from the identified joint node sequence, and the following operations are performed on the extracted initial joint nodes: Using the initial joint node, identifying a target joint node in the identified joint node sequence, wherein the target joint node is adjacent to the initial joint node and lags behind the initial joint node; The Euclidean distance between the three-dimensional coordinates of the joint corresponding to the initial joint node and the three-dimensional coordinates of the joint corresponding to the target joint node is calculated to obtain the joint spacing, and the joint spacing is summarized to obtain a joint spacing set. The joint spacings in the joint spacing set are sorted in the order of the time corresponding to the acquisition of the joint spacing from the earliest to the latest, to obtain a joint spacing sequence, and the joint spacing sequence is fitted to the initial pose vector, wherein the initial pose vector is as follows: W0={j1,j2,j3…,j a ,…j b } Among them, j1, j2, j3, j a They represent the first, second, third and ath joint spacings in the joint spacing sequence respectively, and b means there are b joint spacings in the joint spacing sequence.

9. The method for adjusting the angle of an operating table based on patient posture recognition according to claim 8, characterized in that: The step of confirming that the detected vital signs are preset normal vital signs includes: Obtaining a reference heart rate range and a reference respiratory rate range, when the detected respiratory rate corresponding to the detected vital sign does not belong to the reference respiratory rate range and the detected heart rate corresponding to the detected vital sign does not belong to the reference heart rate range, sending a pre-constructed vital sign warning signal to the initiator of the angle adjustment instruction; Otherwise, confirm that the detected vital signs are the normal vital signs.

10. The method for adjusting the angle of an operating table based on patient posture recognition according to claim 9, characterized in that: The generated visual adjustment result based on the driven target operating table and the result presentation unit includes: Obtaining visualization parameters of each of the multiple first adjustment units corresponding to the driven target operating table, wherein the visualization parameters include adjustment height, initial size, initial position, adjustment angle and monitoring pressure, and summarizing the visualization parameters to obtain a visualization parameter set; Confirming receipt of a visualization instruction from a result presentation unit, acquiring a patient representation model based on the visualization instruction, and generating a visualization model set using the visualization parameter set, wherein the visualization model set includes a plurality of visualization models marked with monitoring pressure, and the visualization models marked with monitoring pressure correspond one to one with the first adjustment unit; A constraint set is determined according to the target selected posture, and a visualization adjustment result is constructed using the constraint set, the visualization model set and the patient representation model.

Images