A cryoprobe control device based on sensing feedback

Abstract

The present invention discloses a control device for a cryoprobe based on sensing feedback. The processor in the device calls executable program code to execute a control method for the cryoprobe based on sensing feedback. The method includes: during the use of the cryoprobe, acquiring real-time image data obtained by an image sensing component and real-time pressing data obtained by a pressing sensing component in real time; based on the real-time image data and a preset image analysis algorithm, determining the moving speed data and moving direction data corresponding to the cryoprobe; according to the real-time pressing data, the moving speed data and the moving direction data, determining the gas outlet probability corresponding to the cryoprobe; according to the gas outlet probability and a preset probability threshold, controlling the gas outlet control component to enter a preparation state for opening in advance to respond to a gas outlet control instruction triggered by a gas outlet control button. It can be seen that the present invention can achieve more intelligent and efficient control of the cryoprobe.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to a freezing pen control device based on sensor feedback. Background Art

[0002] The freezing pen is designed based on the principle of cryo-cosmetology. Its main mechanism is to release cooling gas to suddenly cool down, forming ice crystals inside and outside the tissue cells, destroying the structure and causing lysis. At the same time, the low temperature causes cell dehydration, electrolyte concentration, pH change, protein denaturation, cell metabolism and death. Using this principle, the growths that hinder skin beauty, such as freckles, moles, pigmented spots, etc., are frozen to cause their tissue cells to degenerate, necrotize and fall off, so as to achieve the purpose of beauty treatment.

[0003] However, the existing freezing pen control technology generally only controls the freezing pen by the operator starting or stopping the air outlet control component, and does not consider combining image data and pressure sensor data to improve the intelligent degree and efficiency of control. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a cryopene control device and an intelligent cryopene based on sensor feedback, which can realize more intelligent and efficient control of the cryopene, so that the cryopene can quickly respond to the operator's actions and improve the operator's surgical efficiency and accuracy.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a freezing pen control method based on sensor feedback, wherein the freezing pen comprises a freezing pen body, an image sensor component and a pressure sensor component; the orientation of the image sensor component is the same as the orientation of the air outlet of the freezing pen body; the pressure sensor component is arranged near the air outlet control button of the freezing pen body; the method comprises:

[0006] When the freezing pen is in use, real-time image data acquired by the image sensing component and real-time pressing data acquired by the pressing sensing component are acquired in real time;

[0007] According to the real-time image data, based on a preset image analysis algorithm, determining the moving speed data and moving direction data corresponding to the freezing pen;

[0008] Determine the gas emission probability corresponding to the freezing pen according to the real-time pressing data, the moving speed data and the moving direction data;

[0009] Determine the component working strategy corresponding to the gas outlet control component of the cryoprobe according to the gas outlet probability and a preset probability threshold; the component working strategy is used to control the gas outlet control component to enter the open preparation state in advance to respond to a gas outlet control instruction triggered by the gas outlet control button.

[0010] The second aspect of the present invention discloses a cryoprobe control device based on sensing feedback. The cryoprobe includes a cryoprobe body, an image sensing component, and a pressing sensing component; the orientation of the image sensing component is the same as the orientation of the gas outlet of the cryoprobe body; the pressing sensing component is arranged at a position adjacent to the gas outlet control button of the cryoprobe body. The device includes:

[0011] An acquisition module, configured to, during the use of the cryoprobe, acquire in real time the real-time image data acquired by the image sensing component and the real-time pressing data acquired by the pressing sensing component.

[0012] A determination module, configured to determine the moving speed data and moving direction data corresponding to the cryoprobe based on a preset image analysis algorithm according to the real-time image data.

[0013] A prediction module, configured to determine the gas outlet probability corresponding to the cryoprobe according to the real-time pressing data, and the moving speed data and moving direction data.

[0014] A control module, configured to determine the component working strategy corresponding to the gas outlet control component of the cryoprobe according to the gas outlet probability and a preset probability threshold; the component working strategy is used to control the gas outlet control component to enter the open preparation state in advance to respond to a gas outlet control instruction triggered by the gas outlet control button.

[0015] The third aspect of the present invention discloses another cryoprobe control device based on sensing feedback. The device includes:

[0016] A memory storing executable program code.

[0017] A processor coupled to the memory.

[0018] The processor calls the executable program code stored in the memory and executes some or all of the steps in the cryoprobe control method based on sensing feedback disclosed in the first aspect of the present invention.

[0019] The fourth aspect of the present invention discloses an intelligent freezing pen, which includes a controller, a freezing pen body, an image sensing component, and a pressing sensing component; the orientation of the image sensing component is the same as that of the air outlet of the freezing pen body; the pressing sensing component is arranged at a position adjacent to the air outlet control button of the freezing pen body, and the controller executes some or all of the steps in the freezing pen control method based on sensing feedback disclosed in the first aspect of the present invention.

[0020] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0021] The embodiments of the present invention can comprehensively predict the air outlet probability of the freezing pen by means of image data and pressing sensing data during the use of the freezing pen, so as to make the freezing pen enter the open preparation state in advance, thereby realizing more intelligent and efficient control of the freezing pen, enabling the freezing pen to quickly respond to the operator's actions, and improving the operator's surgical efficiency and accuracy. Description of the Drawings

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 It is a schematic flowchart of a freezing pen control method based on sensing feedback disclosed in the embodiments of the present invention.

[0024] Figure 2 It is a schematic structural diagram of a freezing pen control device based on sensing feedback disclosed in the embodiments of the present invention.

[0025] Figure 3 It is a schematic structural diagram of another freezing pen control device based on sensing feedback disclosed in the embodiments of the present invention. Detailed Embodiments

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0027] In the description and claims of the present invention and the above-mentioned drawings, terms such as "second", "second", etc. are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0028] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0029] The present invention discloses a cryoprobe control device and an intelligent cryoprobe based on sensing feedback, which can comprehensively predict the gas outlet probability of the cryoprobe by means of image data and pressing sensing data during the use of the cryoprobe, so as to make the cryoprobe enter the open preparation state in advance, thereby realizing more intelligent and efficient control of the cryoprobe, enabling the cryoprobe to quickly respond to the operator's actions, and improving the operator's surgical efficiency and accuracy. The following will be described in detail respectively.

[0030] Embodiment 1

[0031] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a cryoprobe control method based on sensing feedback disclosed in an embodiment of the present invention. Among them, Figure 1The described freeze pen control method based on sensing feedback can be applied to a data processing chip, a processing terminal, or a processing server connected to an intelligent freeze pen (wherein the processing server can be a local server or a cloud server). Optionally, the freeze pen controlled by this method can include a freeze pen body, an image sensing component, and a pressing sensing component. Specifically, the orientation of the image sensing component is the same as that of the air outlet of the freeze pen body, and it can be used to obtain an image of the area pointed by the air outlet of the freeze pen for subsequent control and recognition. In one embodiment, a micro camera can be set on the side of the freeze pen body and the orientation of the camera can be adjusted to be the same as that of the air outlet of the freeze pen body to achieve the above purpose. Specifically, the pressing sensing component is set at a position adjacent to the air outlet control button of the freeze pen body. The definition of this adjacent position can be that the distance from the position of the air outlet control button is less than a preset distance threshold. Specifically, this pressing sensing component can be a pressure sensor, which is used to obtain the pressure of the user's hand on the freeze pen near the air outlet control button. This pressure sensing data can effectively represent the user's operation intention and can be used to predict the user's operation intention.

[0032] As Figure 1 shown, the freeze pen control method based on sensing feedback can include the following operations:

[0033] 101. During the use of the freeze pen, continuously obtain the real-time image data obtained by the image sensing component and the real-time pressing data obtained by the pressing sensing component.

[0034] 102. Based on the real-time image data and a preset image analysis algorithm, determine the moving speed data and moving direction data corresponding to the freeze pen.

[0035] 103. Based on the real-time pressing data, the moving speed data, and the moving direction data, determine the air outlet probability corresponding to the freeze pen.

[0036] 104. Based on the air outlet probability and a preset probability threshold, determine the component working strategy corresponding to the air outlet control component of the freeze pen.

[0037] Specifically, the component working strategy is used to control the air outlet control component to enter the open preparation state in advance to respond to the air outlet control instruction triggered by the air outlet control button.

[0038] Optionally, the gas outlet control component includes an intermediate valve component disposed on the gas outlet passage connecting the nitrogen storage component and the gas outlet of the freezing pen, and a gas outlet control valve disposed at the gas outlet of the freezing pen body, and the intermediate valve component and the gas outlet control valve are both connected to the gas outlet control button and are controlled by the gas outlet control button to open or close. Generally, when the control logic of the opening preparation state is not entered in advance, the operator needs to press the gas outlet control button to continuously open the intermediate valve component and the gas outlet control valve to achieve gas outlet.

[0039] Specifically, when the gas outlet control component receives the relevant command for instructing to enter the opening preparation state in advance, it opens the middle valve component to allow the refrigerated nitrogen to enter the gas outlet channel first. At this time, the gas outlet control valve waits for the control of the gas outlet control button. Once the control is received, it can be opened immediately for quick response.

[0040] Another advantage of the control technology of the present invention is that if the operator finds that there is no quick response when turning on the cryo-pen, he or she can immediately know that there is a problem with the timing of gas release, and can use this to check whether there is a problem during the operation to reduce surgical errors.

[0041] It can be seen that the above-mentioned embodiments of the invention can comprehensively predict the gas emission probability of the cryopen using the image data and pressure sensor data during the use of the cryopen, so as to enable the cryopen to enter the open preparation state in advance, thereby achieving more intelligent and efficient control of the cryopen, enabling the cryopen to quickly respond to the operator's actions, and improving the operator's surgical efficiency and accuracy.

[0042] In an optional embodiment, the real-time image data includes a plurality of real-time image data continuously acquired by the image sensing component. Accordingly, in the above steps, determining the movement speed data and the movement direction data corresponding to the freezing pen according to the real-time image data based on a preset image analysis algorithm includes:

[0043] According to the multiple real-time image data, based on the neural network algorithm and the image speed recognition algorithm, the moving speed data corresponding to the freezing pen is determined;

[0044] According to a plurality of real-time image data and a calibration object pre-set in the working area of ​​the freezing pen, based on a neural network algorithm and an image coordinate calibration algorithm, the moving direction data corresponding to the freezing pen is determined.

[0045] Through the above embodiments, it is possible to determine the moving speed data and moving direction data corresponding to the cryoprobe based on the neural network algorithm and the image recognition algorithm according to multiple real-time image data, so as to be able to analyze accurate moving speed data and moving direction data, so as to be able to achieve more intelligent and efficient control of the cryoprobe in the follow-up, enabling the cryoprobe to quickly respond to the operator's actions and improving the operator's surgical efficiency and accuracy.

[0046] In an alternative embodiment, in the above steps, determining the moving speed data corresponding to the cryoprobe based on the neural network algorithm and the image speed recognition algorithm according to multiple real-time image data includes:

[0047] Input the real-time image data with the acquisition time closest to the current time point into the trained speed recognition neural network model to obtain the predicted instantaneous speed corresponding to the real-time image data; the speed recognition neural network model is trained through a training data set including multiple training images and corresponding instantaneous speed annotations;

[0048] Based on the target recognition algorithm and the reference object distance estimation algorithm, calculate the moving distance of a specific recognition target in multiple real-time image data;

[0049] According to the moving distance and the acquisition time period corresponding to multiple real-time image data, calculate the average speed corresponding to multiple real-time image data;

[0050] Calculate the weighted summation average of the predicted instantaneous speed and the average speed to obtain the moving speed data corresponding to the cryoprobe.

[0051] Optionally, the neural network models in the present invention can all be neural network algorithm models with a CNN structure, an RNN structure or an LTSM structure, or a random forest algorithm model integrating multiple classifiers. The operator can select according to the specific implementation scenario and data characteristics, and the present invention does not make a limitation here.

[0052] Optionally, the reference object in the reference object distance estimation algorithm is a calibration object preset in the working area of the cryoprobe. The calibration object can be an object with a certain length and can be used to effectively identify the distance in the algorithm.

[0053] Optionally, the specific recognition target can be a part or all of the images of the calibration object in the real-time image data.

[0054] Optionally, according to the moving distance and the acquisition time period corresponding to multiple real-time image data, calculating the average speed corresponding to multiple real-time image data may include:

[0055] Determine the acquisition time period corresponding to the multiple real-time image data participating in the calculation of the moving distance;

[0056] Calculate the ratio between the moving distance and the acquisition time period to obtain the average speed corresponding to multiple real-time image data.

[0057] Specifically, the multiple real-time image data participating in the calculation of the moving distance are not necessarily equivalent to all real-time image data, because some real-time image data cannot be used for calculating the moving distance due to the lack of feature points.

[0058] Through the above embodiments, the predicted instantaneous speed and the average speed can be calculated respectively through the neural network model and the image analysis algorithm, and then the moving speed data corresponding to the cryoprobe can be obtained by calculating the weighted sum average value, so that accurate moving speed data can be calculated, and more intelligent and efficient control of the cryoprobe can be achieved in the follow-up, enabling the cryoprobe to quickly respond to the operator's actions and improving the operator's surgical efficiency and accuracy.

[0059] In an alternative embodiment, in the above steps, based on the multiple real-time image data and the calibration object preset in the working area of the cryoprobe, and based on the neural network algorithm and the image coordinate calibration algorithm, determining the moving direction data corresponding to the cryoprobe includes:

[0060] Input the multiple real-time image data into the trained direction recognition neural network model to obtain the predicted directions corresponding to the multiple real-time image data; the direction recognition neural network model is trained through a training data set including multiple training image sets and corresponding moving direction annotations;

[0061] According to the feature recognition algorithm corresponding to the calibration object preset in the working area of the cryoprobe, identify the calibration coordinates corresponding to the calibration object in each real-time image data;

[0062] Generate a trajectory for the multiple calibration coordinates corresponding to the multiple real-time image data in the continuous order of image acquisition time to obtain the coordinate moving direction of the multiple calibration coordinates;

[0063] Calculate the weighted sum average value of the predicted direction and the coordinate moving direction to obtain the moving direction data corresponding to the cryoprobe.

[0064] Through the above embodiments, the predicted direction and the coordinate moving direction can be calculated respectively through the neural network model and the feature recognition calibration algorithm, and then the moving direction data corresponding to the cryoprobe can be obtained by calculating the weighted sum average value, so that accurate moving direction data can be calculated, and more intelligent and efficient control of the cryoprobe can be achieved in the follow-up, enabling the cryoprobe to quickly respond to the operator's actions and improving the operator's surgical efficiency and accuracy.

[0065] In an alternative embodiment, in the above steps, determining the gas outlet probability corresponding to the cryoprobe according to the real-time pressing data, moving speed data, and moving direction data includes:

[0066] Input the real-time pressing data into the trained first gas outlet prediction neural network model to obtain the first gas outlet probability corresponding to the cryoprobe; the first gas outlet prediction neural network model is trained through a training data set including multiple training pressing data and corresponding cryoprobe gas outlet annotations;

[0067] Input the moving speed data and moving direction data into the trained second gas outlet prediction neural network model to obtain the second gas outlet probability corresponding to the cryoprobe; the second gas outlet prediction neural network model is trained through a training data set including multiple training moving speed data, training moving direction data, and corresponding cryoprobe gas outlet annotations;

[0068] Calculate the weighted sum average of the first gas outlet probability and the second gas outlet probability to obtain the gas outlet probability corresponding to the cryoprobe; wherein, the weight of the first gas outlet probability is proportional to the prediction accuracy rate of the first gas outlet prediction neural network model in the verification stage; the weight of the second gas outlet probability is proportional to the prediction accuracy rate of the second gas outlet prediction neural network model in the verification stage.

[0069] Through the above embodiment, the gas outlet probability can be predicted respectively through the first gas outlet prediction neural network model and the second gas outlet prediction neural network model, and then the gas outlet probability corresponding to the cryoprobe can be obtained by calculating the weighted sum average, so that the gas outlet probability of the cryoprobe can be predicted more accurately and reasonably, so as to realize more intelligent and efficient control of the cryoprobe in the subsequent process, enable the cryoprobe to quickly respond to the operator's actions, and improve the operator's surgical efficiency and accuracy.

[0070] In an alternative embodiment, in the above steps, determining the component working strategy corresponding to the gas outlet control component of the cryoprobe according to the gas outlet probability and a preset probability threshold includes:

[0071] Judge whether the gas outlet probability is greater than the preset probability threshold. If so, determine that the component working strategy corresponding to the gas outlet control component of the cryoprobe is to enter the open preparation state in advance; otherwise, determine that the component working strategy corresponding to the gas outlet control component of the cryoprobe is to remain closed.

[0072] Through the above embodiment, when it is judged whether the gas outlet probability is greater than the preset probability threshold, it can be determined that the component working strategy corresponding to the gas outlet control component of the cryoprobe is to enter the open preparation state in advance, so as to realize more intelligent and efficient control of the cryoprobe, enable the cryoprobe to quickly respond to the operator's actions, and improve the operator's surgical efficiency and accuracy.

[0073] In an alternative embodiment, the method further includes:

[0074] When the gas outlet control component of the cryoprobe enters the open preparation state, before recognizing the gas outlet control instruction triggered by the gas outlet control button, continuously calculate multiple gas outlet probabilities;

[0075] Determine whether the multiple gas outlet probabilities conform to a preset increasing trend to obtain a first determination result;

[0076] If the first determination result is yes, keep the gas outlet control component of the cryoprobe in the open preparation state;

[0077] If the first determination result is no, determine whether the probability difference between the most recently calculated gas outlet probability and the previously calculated gas outlet probability is greater than a preset probability difference threshold to obtain a second determination result;

[0078] If the second determination result is no, keep the gas outlet control component of the cryoprobe in the open preparation state;

[0079] If the second determination result is yes, control the gas outlet control component of the cryoprobe to enter the closed state.

[0080] Optionally, the preset increasing trend is used to define the continuous growth numerical relationship of multiple gas outlet probabilities and the magnitude threshold of the data change rate. It can be defined by the operator according to experience or experimental results and adjusted according to the implementation results. The present invention does not limit its specific rules.

[0081] The purpose of setting the above determination rules is to be able to maintain real-time monitoring of the gas outlet probability before the operator actually presses the start button, and to maintain a preparatory state in advance when the gas outlet probability remains or increases. However, when the growth probability drops rapidly, that is, when the operator may abandon gas outlet or suspend the operation, stop this preparatory state to prevent the cryogenic gas from warming up in the channel or other accidents.

[0082] Through the above embodiments, it is possible to maintain real-time monitoring of the gas outlet probability before the operator actually presses the start button, thereby enabling more intelligent and efficient control of the cryoprobe, and improving the operation efficiency and accuracy of the operator.

[0083] Embodiment Two

[0084] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a cryoprobe control device based on sensing feedback disclosed in an embodiment of the present invention. Among them, Figure 2 The described cryoprobe control device based on sensing feedback is applied to the data processing chip, processing terminal or processing server of the intelligent cryoprobe (wherein, the processing server can be a local server or a cloud server). AsFigure 2 As shown, the freezing pen control device based on sensor feedback may include:

[0085] The acquisition module 201 is used to acquire real-time image data acquired by the image sensing component and real-time pressing data acquired by the pressing sensing component in real time during the use of the freezing pen.

[0086] The determination module 202 is used to determine the moving speed data and moving direction data corresponding to the freezing pen according to the real-time image data and based on a preset image analysis algorithm.

[0087] The prediction module 203 is used to determine the gas emission probability corresponding to the freezing pen according to the real-time pressing data, the moving speed data and the moving direction data.

[0088] The control module 204 is used to determine the component working strategy corresponding to the gas outlet control component of the freezing pen according to the gas outlet probability and a preset probability threshold.

[0089] Specifically, the component working strategy is used to control the air outlet control component to enter the open ready state in advance to respond to the air outlet control instruction triggered by the air outlet control button.

[0090] Optionally, the gas outlet control component includes an intermediate valve component disposed on the gas outlet passage connecting the nitrogen storage component and the gas outlet of the freezing pen, and a gas outlet control valve disposed at the gas outlet of the freezing pen body, and the intermediate valve component and the gas outlet control valve are both connected to the gas outlet control button and are controlled by the gas outlet control button to open or close. Generally, when the control logic of the opening preparation state is not entered in advance, the operator needs to press the gas outlet control button to continuously open the intermediate valve component and the gas outlet control valve to achieve gas outlet.

[0091] Specifically, when the gas outlet control component receives the relevant command for instructing to enter the opening preparation state in advance, it opens the middle valve component to allow the refrigerated nitrogen to enter the gas outlet channel first. At this time, the gas outlet control valve waits for the control of the gas outlet control button. Once the control is received, it can be opened immediately for quick response.

[0092] Another advantage of the control technology of the present invention is that if the operator finds that there is no quick response when turning on the cryo-pen, he or she can immediately know that there is a problem with the timing of gas release, and can use this to check whether there is a problem during the operation to reduce surgical errors.

[0093] It can be seen that the above-described embodiments of the invention can comprehensively predict the gas outlet probability of the cryoprobe by means of the image data and the pressing sensing data during the use of the cryoprobe, so as to make the cryoprobe enter the open preparation state in advance, thereby enabling more intelligent and efficient control of the cryoprobe, enabling the cryoprobe to quickly respond to the operator's actions, and improving the surgical efficiency and accuracy of the operator.

[0094] In an alternative embodiment, the real-time image data includes a plurality of real-time image data continuously acquired by the image sensing component. Correspondingly, the specific manner in which the determination module 202 determines the moving speed data and the moving direction data corresponding to the cryoprobe based on the real-time image data and a preset image analysis algorithm includes:

[0095] Based on the neural network algorithm and the image speed recognition algorithm, determine the moving speed data corresponding to the cryoprobe according to the plurality of real-time image data;

[0096] Based on the neural network algorithm and the image coordinate calibration algorithm, determine the moving direction data corresponding to the cryoprobe according to the plurality of real-time image data and the calibration object preset in the working area of the cryoprobe.

[0097] Through the above embodiments, it is possible to implement determining the moving speed data and the moving direction data corresponding to the cryoprobe according to a plurality of real-time image data based on the neural network algorithm and the image recognition algorithm, so as to be able to analyze accurate moving speed data and moving direction data, in order to achieve more intelligent and efficient control of the cryoprobe in the subsequent process, enabling the cryoprobe to quickly respond to the operator's actions, and improving the surgical efficiency and accuracy of the operator.

[0098] In an alternative embodiment, the specific manner in which the determination module 202 determines the moving speed data corresponding to the cryoprobe based on the neural network algorithm and the image speed recognition algorithm according to the plurality of real-time image data includes:

[0099] Input the real-time image data with the acquisition time closest to the current time point into the trained speed recognition neural network model to obtain the predicted instantaneous speed corresponding to the real-time image data; the speed recognition neural network model is trained by a training data set including a plurality of training images and corresponding instantaneous speed annotations;

[0100] Based on the target recognition algorithm and the reference object distance estimation algorithm, calculate the moving distance of a specific recognition target in the plurality of real-time image data;

[0101] According to the moving distance and the acquisition time period corresponding to the plurality of real-time image data, calculate the average speed corresponding to the plurality of real-time image data;

[0102] Calculate the weighted sum average of the predicted instantaneous speed and the average speed to obtain the moving speed data corresponding to the cryoprobe.

[0103] Optionally, the neural network models in the present invention can all be neural network algorithm models with a CNN structure, an RNN structure or an LTSM structure, or a random forest algorithm model that integrates multiple classifiers. The operator can select according to the specific implementation scenario and data characteristics, and the present invention does not make any limitations here.

[0104] Optionally, the reference object in the reference object distance estimation algorithm is a calibration object preset in the working area of the cryoprobe. The calibration object can be an object with a certain length and can be used to effectively identify the distance in the algorithm.

[0105] Optionally, the specific recognition target can be part or all of the images of the calibration object in the real-time image data.

[0106] Optionally, the determining module 202 calculates the average speed corresponding to multiple real-time image data according to the moving distance and the acquisition time period corresponding to multiple real-time image data, which may include:

[0107] Determine the acquisition time period corresponding to the multiple real-time image data involved in calculating the moving distance;

[0108] Calculate the ratio between the moving distance and the acquisition time period to obtain the average speed corresponding to multiple real-time image data.

[0109] Specifically, the multiple real-time image data involved in calculating the moving distance are not necessarily the same as all real-time image data, because some real-time image data cannot be used to calculate the moving distance due to the lack of feature points.

[0110] Through the above embodiments, the instantaneous speed and the average speed can be calculated and predicted respectively through the neural network model and the image analysis algorithm, and then the moving speed data corresponding to the cryoprobe can be obtained by calculating the weighted sum average value, so as to accurately calculate the moving speed data, and then more intelligent and efficient control of the cryoprobe can be realized in the follow-up, so that the cryoprobe can quickly respond to the operator's actions and improve the operator's surgical efficiency and accuracy.

[0111] In an optional embodiment, the specific manner in which the determining module 202 determines the moving direction data corresponding to the cryoprobe based on the multiple real-time image data and the calibration object preset in the working area of the cryoprobe, based on the neural network algorithm and the image coordinate calibration algorithm, includes:

[0112] Input the multiple real-time image data into the trained direction recognition neural network model to obtain the predicted directions corresponding to the multiple real-time image data; the direction recognition neural network model is trained through a training data set including multiple training image sets and corresponding moving direction annotations;

[0113] According to the feature recognition algorithm corresponding to the calibration object preset in the working area of the cryoprobe, identify the calibration coordinates corresponding to the calibration object in each real-time image data;

[0114] Generate a trajectory for multiple calibration coordinates corresponding to multiple real-time image data in the continuous order of image acquisition time to obtain the coordinate movement direction of the multiple calibration coordinates;

[0115] Calculate the weighted summation average of the predicted direction and the coordinate movement direction to obtain the movement direction data corresponding to the cryoprobe.

[0116] Through the above embodiments, the predicted direction and the coordinate movement direction can be calculated respectively through the neural network model and the feature recognition calibration algorithm, and then the movement direction data corresponding to the cryoprobe can be obtained by calculating the weighted summation average, so that accurate movement direction data can be calculated, and more intelligent and efficient control of the cryoprobe can be realized in the follow-up, enabling the cryoprobe to quickly respond to the operator's actions and improving the operator's surgical efficiency and accuracy.

[0117] In an alternative embodiment, the specific manner in which the prediction module 203 determines the air outlet probability corresponding to the cryoprobe according to the real-time pressing data, the movement speed data, and the movement direction data includes:

[0118] Input the real-time pressing data into the trained first air outlet prediction neural network model to obtain the first air outlet probability corresponding to the cryoprobe; the first air outlet prediction neural network model is trained through a training data set including multiple training pressing data and corresponding cryoprobe air outlet annotations;

[0119] Input the movement speed data and the movement direction data into the trained second air outlet prediction neural network model to obtain the second air outlet probability corresponding to the cryoprobe; the second air outlet prediction neural network model is trained through a training data set including multiple training movement speed data, training movement direction data, and corresponding cryoprobe air outlet annotations;

[0120] Calculate the weighted summation average of the first air outlet probability and the second air outlet probability to obtain the air outlet probability corresponding to the cryoprobe; wherein, the weight of the first air outlet probability is proportional to the prediction accuracy rate of the first air outlet prediction neural network model in the verification stage; the weight of the second air outlet probability is proportional to the prediction accuracy rate of the second air outlet prediction neural network model in the verification stage.

[0121] Through the above embodiments, the outgassing probability can be predicted respectively by the first outgassing prediction neural network model and the second outgassing prediction neural network model, and then the outgassing probability corresponding to the cryoprobe can be obtained by calculating the weighted sum average value, so that the outgassing probability of the cryoprobe can be predicted more accurately and reasonably, so as to realize more intelligent and efficient control of the cryoprobe in the subsequent process, enabling the cryoprobe to quickly respond to the operator's actions and improving the surgical efficiency and accuracy of the operator.

[0122] In an alternative embodiment, the control module 204 determines the specific manner of the component working strategy corresponding to the outgassing control component of the cryoprobe according to the outgassing probability and a preset probability threshold, including:

[0123] Judge whether the outgassing probability is greater than the preset probability threshold. If so, determine that the component working strategy corresponding to the outgassing control component of the cryoprobe is to enter the open preparation state in advance; otherwise, determine that the component working strategy corresponding to the outgassing control component of the cryoprobe is to remain closed.

[0124] Through the above embodiments, when it is judged whether the outgassing probability is greater than the preset probability threshold, it can be determined that the component working strategy corresponding to the outgassing control component of the cryoprobe is to enter the open preparation state in advance, so as to realize more intelligent and efficient control of the cryoprobe, enabling the cryoprobe to quickly respond to the operator's actions and improving the surgical efficiency and accuracy of the operator.

[0125] In an alternative embodiment, the control module 204 is further configured to perform the following steps:

[0126] When the outgassing control component of the cryoprobe enters the open preparation state, before the outgassing control instruction triggered by the outgassing control button is recognized, continuously calculate multiple outgassing probabilities;

[0127] Judge whether the multiple outgassing probabilities conform to a preset increasing trend to obtain a first judgment result;

[0128] If the first judgment result is yes, keep the outgassing control component of the cryoprobe in the open preparation state;

[0129] If the first judgment result is no, judge whether the probability difference between the most recently calculated outgassing probability and the previously calculated outgassing probability is greater than a preset probability difference threshold to obtain a second judgment result;

[0130] If the second judgment result is no, keep the outgassing control component of the cryoprobe in the open preparation state;

[0131] If the second judgment result is yes, control the outgassing control component of the cryoprobe to enter the closed state.

[0132] Optionally, the preset growth trend is used to define the continuous growth numerical relationship of multiple gas outlet probabilities and the magnitude threshold of the data change rate, which can be defined by the operator according to experience or experimental results and adjusted according to the implementation results after implementation. The present invention does not limit its specific rules.

[0133] The purpose of setting the above judgment rule is to be able to maintain real-time monitoring of the gas outlet probability before the operator actually presses the start button, and to maintain a ready state in advance when the gas outlet probability remains or increases. And when the growth probability drops rapidly, that is, when the operator may abandon the gas outlet or pause the operation, stop this ready state to prevent the cryogenic gas from warming up in the channel or other accidents.

[0134] Through the above embodiments, it is possible to maintain real-time monitoring of the gas outlet probability before the operator actually presses the start button, so as to realize more intelligent and efficient control of the cryoprobe, and improve the operation efficiency and accuracy of the operator.

[0135] Embodiment III

[0136] Please refer to Figure 3 , Figure 3 which is another cryoprobe control device based on sensing feedback disclosed in the embodiments of the present invention. Figure 3 The described cryoprobe control device based on sensing feedback is applied to the data processing chip, processing terminal or processing server of the intelligent cryoprobe (wherein, the processing server can be a local server or a cloud server). As Figure 3 shown, the cryoprobe control device based on sensing feedback may include:

[0137] A memory 301 storing executable program code;

[0138] A processor 302 coupled to the memory 301;

[0139] Wherein, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the cryoprobe control method described in Embodiment I.

[0140] Embodiment IV

[0141] An embodiment of the present invention discloses an intelligent freezing pen, which includes a controller, a freezing pen body, an image sensing component, and a pressing sensing component. Among them, the orientation of the image sensing component is the same as that of the air outlet of the freezing pen body, the pressing sensing component is arranged at a position adjacent to the air outlet control button of the freezing pen body, and the controller executes some or all of the steps of the freezing pen control method based on sensing feedback described in Embodiment 1. For more technical details of the intelligent freezing pen in this embodiment, reference can be made to the description in Embodiment 1. For the structural details of the freezing pen body, reference can be made to the structural design disclosed by the applicant in the utility model patent with the patent application number 202122734813.1. It should be noted that the solution in this embodiment is a further improvement on the patent solution and does not completely copy the design of the patent solution. The corresponding improvements, such as the design details of the image sensing component and the pressing sensing component, can be applied by those skilled in the art according to the actual situation.

[0142] Embodiment 5

[0143] An embodiment of the present invention discloses a computer-readable storage medium, which stores a computer program for electronic data exchange. Among them, the computer program enables a computer to execute the steps of the freezing pen control method based on sensing feedback described in Embodiment 1.

[0144] Embodiment 6

[0145] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the freezing pen control method based on sensing feedback described in Embodiment 1.

[0146] The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily have to be performed in the particular order or continuous order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0147] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, equipment, and non-volatile computer-readable storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0148] The device, equipment, non-volatile computer-readable storage medium, and method provided by the embodiments of this specification are corresponding. Therefore, the device, equipment, and non-volatile computer storage medium also have beneficial technical effects similar to those of the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding device, equipment, and non-volatile computer storage medium will not be elaborated here.

[0149] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logical function is determined by the user programming the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL), and there is not just one type of HDL, but many types, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0150] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to make the controller implement the same function in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0151] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0152] For the convenience of description, the above devices are described by dividing them into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0153] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0154] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0155] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0157] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0158] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0159] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0160] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0161] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0162] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0163] Finally, it should be noted that the control device for a cryoprobe based on sensing feedback and the intelligent cryoprobe disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention. They are only used to illustrate the technical solutions of the present invention, rather than limiting it. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A freezing pen control device based on sensor feedback, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute a freezing pen control method based on sensor feedback, wherein the freezing pen includes a freezing pen body, an image sensor component and a pressure sensor component; the orientation of the image sensor component is the same as the orientation of the air outlet of the freezing pen body; the pressure sensor component is arranged near the air outlet control button of the freezing pen body; the method includes: When the freezing pen is in use, real-time image data acquired by the image sensing component and real-time pressing data acquired by the pressing sensing component are acquired in real time; According to the real-time image data, based on a preset image analysis algorithm, determining the moving speed data and moving direction data corresponding to the freezing pen; Determine the gas emission probability corresponding to the freezing pen according to the real-time pressing data, the moving speed data and the moving direction data; According to the gas outlet probability and a preset probability threshold, a component working strategy corresponding to the gas outlet control component of the freezing pen is determined; the component working strategy is used to control the gas outlet control component to enter an open ready state in advance to respond to the gas outlet control instruction triggered by the gas outlet control button.

2. The freezing pen control device based on sensor feedback according to claim 1, characterized in that: The real-time image data includes a plurality of real-time image data continuously acquired by the image sensing component; the moving speed data and moving direction data corresponding to the freezing pen are determined based on the real-time image data and a preset image analysis algorithm, including: According to the plurality of real-time image data, based on a neural network algorithm and an image speed recognition algorithm, determining the movement speed data corresponding to the freezing pen; According to the multiple real-time image data and the calibration object pre-set in the working area of ​​the freezing pen, based on the neural network algorithm and the image coordinate calibration algorithm, the moving direction data corresponding to the freezing pen is determined.

3. The freezing pen control device based on sensor feedback according to claim 2, characterized in that: The step of determining the movement speed data corresponding to the freezing pen based on the plurality of real-time image data and a neural network algorithm and an image speed recognition algorithm comprises: The real-time image data acquired at a time closest to the current time point is input into a trained speed recognition neural network model to obtain a predicted instantaneous speed corresponding to the real-time image data; the speed recognition neural network model is trained by a training data set including a plurality of training images and corresponding instantaneous speed annotations; Calculating the moving distance of a specific identified target in the plurality of real-time image data based on a target recognition algorithm and a reference object distance estimation algorithm; Calculate the average speed corresponding to the plurality of real-time image data according to the moving distance and the acquisition time period corresponding to the plurality of real-time image data; The weighted average value of the predicted instantaneous speed and the average speed is calculated to obtain the moving speed data corresponding to the freezing pen.

4. The freezing pen control device based on sensor feedback according to claim 2, characterized in that: The method of determining the moving direction data corresponding to the freezing pen based on the plurality of real-time image data and a calibration object pre-set in the working area of ​​the freezing pen based on a neural network algorithm and an image coordinate calibration algorithm comprises: Inputting the plurality of real-time image data into a trained direction recognition neural network model to obtain predicted directions corresponding to the plurality of real-time image data; the direction recognition neural network model is trained by a training data set including a plurality of training image sets and corresponding movement direction annotations; According to a feature recognition algorithm corresponding to the calibration object pre-set in the working area of ​​the freezing pen, the calibration coordinates corresponding to the calibration object in each of the real-time image data are identified; Generating trajectories for the plurality of calibration coordinates corresponding to the plurality of real-time image data in a continuous order of image acquisition time to obtain coordinate movement directions of the plurality of calibration coordinates; The weighted average value of the predicted direction and the coordinate moving direction is calculated to obtain the moving direction data corresponding to the freezing pen.

5. The freezing pen control device based on sensor feedback according to claim 1, characterized in that: Determining the gas emission probability corresponding to the freezing pen according to the real-time pressing data, the moving speed data and the moving direction data includes: Inputting the real-time pressing data into a trained first gas release prediction neural network model to obtain a first gas release probability corresponding to the freezing pen; the first gas release prediction neural network model is trained by a training data set including a plurality of training pressing data and corresponding freezing pen gas release annotations; Inputting the moving speed data and the moving direction data into a trained second gas outflow prediction neural network model to obtain a second gas outflow probability corresponding to the freezing pen; the second gas outflow prediction neural network model is trained by a training data set including a plurality of training moving speed data, training moving direction data and corresponding freezing pen gas outflow annotations; The weighted average of the first gas outflow probability and the second gas outflow probability is calculated to obtain the gas outflow probability corresponding to the freezing pen; wherein the weight of the first gas outflow probability is proportional to the prediction accuracy of the first gas outflow prediction neural network model in the verification stage; the weight of the second gas outflow probability is proportional to the prediction accuracy of the second gas outflow prediction neural network model in the verification stage.

6. The freezing pen control device based on sensor feedback according to claim 5, characterized in that: Determining a component working strategy corresponding to the gas outlet control component of the freezing pen according to the gas outlet probability and a preset probability threshold includes: It is determined whether the gas outlet probability is greater than a preset probability threshold. If so, the component working strategy corresponding to the gas outlet control component of the freezing pen is determined to enter the open preparation state in advance; otherwise, the component working strategy corresponding to the gas outlet control component of the freezing pen is determined to remain in the closed state.

7. The freezing pen control device based on sensor feedback according to claim 1, characterized in that: The method further comprises: When the air outlet control component of the freezing pen enters the opening preparation state, before the air outlet control instruction triggered by the air outlet control button is recognized, a plurality of the air outlet probabilities are continuously calculated; Determine whether the plurality of gas-exhaling probabilities conform to a preset growth trend, and obtain a first determination result; If the first judgment result is yes, keeping the air outlet control component of the freezing pen in an open ready state; If the first judgment result is no, determine whether the probability difference between the most recently calculated probability of exhalation and the probability of exhalation calculated last time is greater than a preset probability difference threshold, and obtain a second judgment result; If the second judgment result is no, keeping the air outlet control component of the freezing pen in an open ready state; If the second judgment result is yes, the air outlet control component of the freezing pen is controlled to enter a closed state.

8. A freezing pen control device based on sensor feedback, characterized in that: The freezing pen comprises a freezing pen body, an image sensing component and a pressure sensing component; the orientation of the image sensing component is the same as the orientation of the air outlet of the freezing pen body; The pressure sensor component is arranged near the air outlet control button of the freezing pen body; The device comprises: An acquisition module, used for acquiring real-time image data acquired by the image sensing component and real-time pressing data acquired by the pressing sensing component in real time during the use of the freezing pen; A determination module, used to determine the moving speed data and moving direction data corresponding to the freezing pen according to the real-time image data and based on a preset image analysis algorithm; A prediction module, used to determine the gas emission probability corresponding to the freezing pen according to the real-time pressing data, the moving speed data and the moving direction data; A control module is used to determine a component working strategy corresponding to the gas outlet control component of the freezing pen according to the gas outlet probability and a preset probability threshold; the component working strategy is used to control the gas outlet control component to enter an open ready state in advance to respond to the gas outlet control instruction triggered by the gas outlet control button.

Images