CN116672069A

CN116672069A - Graphite film electromagnetic induction thermal ablation support and method thereof

Info

Publication number: CN116672069A
Application number: CN202310674253.6A
Authority: CN
Inventors: 朱彤; 李文宇; 左玉星
Original assignee: Hangzhou Tangji Medical Technology Co ltd
Current assignee: Hangzhou Tangji Medical Technology Co ltd
Priority date: 2023-06-08
Filing date: 2023-06-08
Publication date: 2023-09-01
Anticipated expiration: 2043-06-08
Also published as: CN116672069B

Abstract

The application discloses a graphite film electromagnetic induction thermal ablation support and a method thereof. The graphite film electromagnetic induction thermal ablation support includes: a gastric bypass stent body; a graphite layer coated on the outer surface of the gastric diversion stent main body; a plurality of temperature sensors disposed in a predetermined topological pattern on the graphite layer; and the processor is electrically connected with the plurality of temperature sensors, wherein the processor adopts an artificial intelligence control technology based on deep learning to regulate and control the electromagnetic waves through implicit characteristic distribution information of a waveform diagram of the electromagnetic waves and multiscale dynamic change characteristic information of the temperature in a time dimension, and in the process, spatial topological characteristics of the plurality of temperature sensors are introduced to strengthen expression of dynamic change characteristics of the temperature in time sequence, so that the accuracy of regulating and controlling the electromagnetic waves is improved.

Description

Graphite film electromagnetic induction thermal ablation support and method thereof

Technical Field

The application relates to the technical field of medical instruments, in particular to a graphite film electromagnetic induction thermal ablation support and a method thereof.

Background

The gastric diversion stent is a medical instrument for treating clinical obesity, and the principle is as follows: since most of the nutrition is absorbed by the intestinal tract, the gastric diversion stent is covered on a part of the intestinal tract by a film with good biocompatibility, so that the food is isolated from a part of the intestinal tract, and the absorption of the ingested food is reduced. The gastric bypass stent may thermally ablate the luminal wall, thereby allowing the luminal wall to create a new benign mucosa.

In thermal ablation by means of a gastric shunt stent, the temperature of the stent needs to be controlled, and since the gastric shunt stent is located in the lumen, it cannot be achieved by conventional heating means, such as electrical heating.

Accordingly, an optimized graphite film electromagnetic induction thermal ablation stent is desired.

Disclosure of Invention

The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a graphite film electromagnetic induction thermal ablation support and a method thereof. The graphite film electromagnetic induction thermal ablation support includes: a gastric bypass stent body; a graphite layer coated on the outer surface of the gastric diversion stent main body; a plurality of temperature sensors disposed in a predetermined topological pattern on the graphite layer; and the processor is electrically connected with the plurality of temperature sensors, wherein the processor adopts an artificial intelligence control technology based on deep learning to regulate and control the electromagnetic waves through implicit characteristic distribution information of a waveform diagram of the electromagnetic waves and multiscale dynamic change characteristic information of the temperature in a time dimension, and in the process, spatial topological characteristics of the plurality of temperature sensors are introduced to strengthen expression of dynamic change characteristics of the temperature in time sequence, so that the accuracy of regulating and controlling the electromagnetic waves is improved. By the mode, the heating and temperature control of the graphite film can be accurately realized.

According to one aspect of the present application, there is provided a graphite film electromagnetic induction thermal ablation stent comprising: a gastric bypass stent body; a graphite layer coated on the outer surface of the gastric diversion stent main body; a plurality of temperature sensors disposed in a predetermined topological pattern on the graphite layer; and a processor electrically connected to the plurality of temperature sensors.

In the graphite film electromagnetic induction thermal ablation support, the processor comprises: a data acquisition module for acquiring a waveform diagram of electromagnetic waves of a predetermined time period and temperature values of a plurality of predetermined time points within the predetermined time period acquired by the plurality of temperature sensors; the temperature characteristic extraction module is used for respectively arranging temperature values of a plurality of preset time points in the preset time period acquired by each temperature sensor into temperature input vectors according to a time dimension and then obtaining a plurality of temperature characteristic vectors through the multi-scale neighborhood characteristic extraction module; the global module is used for carrying out two-dimensional arrangement on the plurality of temperature characteristic vectors to obtain a temperature global characteristic matrix; the space topology feature extraction module is used for enabling the space topology matrixes of the plurality of temperature sensors to pass through a first convolution neural network model serving as a feature extractor to obtain a space topology feature matrix, wherein feature values of all positions on the non-diagonal positions of the space topology matrix are distances between the two corresponding temperature sensors; the map neural network module is used for enabling the space topological feature matrix and the temperature global feature matrix to pass through a map neural network model to obtain a topological temperature global feature matrix; the distribution evaluation optimization module is used for carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix so as to obtain an optimized topological temperature global feature matrix; an electromagnetic wave feature extraction module, configured to pass a waveform diagram of the electromagnetic wave in the predetermined period of time through a second convolutional neural network model serving as a filter to obtain an electromagnetic wave feature vector; the transfer module is used for calculating transfer vectors of the electromagnetic waveform feature vectors relative to the optimized topological temperature global feature matrix to serve as classification feature vectors; and a control result generation module for passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased.

In the above graphite film electromagnetic induction thermal ablation support, the temperature characteristic extraction module includes: a first scale temperature feature extraction unit, configured to perform one-dimensional convolutional encoding on the temperature input vector by using a first convolutional layer of the multi-scale neighborhood feature extraction module to obtain a first scale temperature feature vector, where the first convolutional layer has a first one-dimensional convolution kernel with a first length; a second scale temperature feature extraction unit, configured to perform one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale temperature feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and the multi-scale fusion unit is used for cascading the first-scale temperature characteristic vector and the second-scale temperature characteristic vector by using a cascading layer of the multi-scale neighborhood characteristic extraction module so as to obtain the plurality of temperature characteristic vectors.

In the above graphite film electromagnetic induction thermal ablation stent, the first scale temperature feature extraction unit is further configured to: performing one-dimensional convolution encoding on the temperature input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first-scale temperature feature vector; wherein, the formula is: Wherein->For the first one-dimensional convolution kernel>Width in the direction,For a first one-dimensional convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, < ->For the size of the first one-dimensional convolution kernel, +.>Representing the temperature input vector; the second scale temperature feature extraction unit is further configured to: performing one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale temperature feature vector; wherein, the formula is:wherein->For the second one-dimensional convolution kernel>Width in the direction,For a second one-dimensional convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, < ->For the size of the second one-dimensional convolution kernel, +.>Representing the temperature input vector.

In the above graphite film electromagnetic induction thermal ablation stent, the spatial topological feature extraction module is further configured to: performing two-dimensional convolution processing, feature matrix-based averaging pooling processing and nonlinear activation processing on input data in forward transfer of layers by using each layer of the first convolutional neural network model as a feature extractor to output the spatial topology feature matrix by the last layer of the first convolutional neural network model as a feature extractor, wherein the input of the first layer of the first convolutional neural network model as a feature extractor is the spatial topology matrix of the plurality of temperature sensors.

In the graphite film electromagnetic induction thermal ablation stent described above, the distribution evaluation optimization module is further configured to: carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix by the following formula to obtain an optimized topological temperature global feature vector; wherein, the formula is:wherein->Is the +.f. of the topology temperature global feature matrix>Global feature vector of topology temperature,>is the +.f. of the topology temperature global feature matrix>Global feature vector of topology temperature,>is the mean feature vector, ++>Setting up superparameters for a neighborhood->Represents a logarithmic function value based on 2, < +.>Indicating the pressed positionThe difference in terms of the subtraction,is the first +.>And the optimized topological temperature global feature vector.

In the graphite film electromagnetic induction thermal ablation stent described above, the electromagnetic wave feature extraction module is further configured to: and respectively performing two-dimensional convolution processing, mean pooling processing based on a feature matrix and nonlinear activation processing on input data in forward transfer of layers by using each layer of the second convolutional neural network model as a filter to output the electromagnetic waveform feature vector by the last layer of the second convolutional neural network model as the filter, wherein the input of the first layer of the second convolutional neural network model as the filter is a waveform diagram of electromagnetic waves in the preset time period.

In the graphite film electromagnetic induction thermal ablation support, the transfer module is further used for: calculating a transfer vector of the electromagnetic waveform feature vector relative to the optimized topological temperature global feature matrix by using the following formula as a classification feature vector; wherein, the formula is:wherein->Representing the optimized topology temperature global feature matrix, < >>Representing the electromagnetic waveform feature vector, +_>Representing the classification feature vector,/->Representing vector multiplication.

In the above graphite film electromagnetic induction thermal ablation stent, the control result generation module includes: the full-connection coding unit is used for carrying out full-connection coding on the classification characteristic vectors by using a full-connection layer of the classifier so as to obtain coded classification characteristic vectors; and the classification unit is used for inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

According to another aspect of the present application, there is provided a method of graphite film electromagnetic induction thermal ablation stent comprising: acquiring a waveform diagram of electromagnetic waves of a preset time period and temperature values of a plurality of preset time points in the preset time period acquired by the plurality of temperature sensors; the temperature values of a plurality of preset time points in the preset time period acquired by each temperature sensor are respectively arranged into temperature input vectors according to the time dimension, and then a plurality of temperature feature vectors are obtained through a multi-scale neighborhood feature extraction module; two-dimensionally arranging the plurality of temperature feature vectors to obtain a temperature global feature matrix; the space topology matrix of the plurality of temperature sensors is passed through a first convolution neural network model serving as a feature extractor to obtain a space topology feature matrix, wherein feature values of all positions on non-diagonal positions of the space topology matrix are distances between two corresponding temperature sensors; the space topology feature matrix and the temperature global feature matrix are subjected to a graph neural network model to obtain a topology temperature global feature matrix; carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix to obtain an optimized topological temperature global feature matrix; passing the waveform diagram of the electromagnetic wave in the preset time period through a second convolution neural network model serving as a filter to obtain an electromagnetic waveform characteristic vector; calculating a transfer vector of the electromagnetic waveform feature vector relative to the optimized topological temperature global feature matrix as a classification feature vector; and passing the classification feature vector through a classifier to obtain a classification result, the classification result being used to indicate that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased.

Compared with the prior art, the graphite film electromagnetic induction thermal ablation stent and the method thereof provided by the application comprise the following steps: a gastric bypass stent body; a graphite layer coated on the outer surface of the gastric diversion stent main body; a plurality of temperature sensors disposed in a predetermined topological pattern on the graphite layer; and the processor is electrically connected with the plurality of temperature sensors, wherein the processor adopts an artificial intelligence control technology based on deep learning to regulate and control the electromagnetic waves through implicit characteristic distribution information of a waveform diagram of the electromagnetic waves and multiscale dynamic change characteristic information of the temperature in a time dimension, and in the process, spatial topological characteristics of the plurality of temperature sensors are introduced to strengthen expression of dynamic change characteristics of the temperature in time sequence, so that the accuracy of regulating and controlling the electromagnetic waves is improved. By the mode, the heating and temperature control of the graphite film can be accurately realized.

Drawings

The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.

Fig. 1 is a schematic structural diagram of a graphite film electromagnetic induction thermal ablation stent according to an embodiment of the present application.

Fig. 2 is an application scenario diagram of a graphite film electromagnetic induction thermal ablation stent according to an embodiment of the present application.

FIG. 3 is a block diagram of a processor according to an embodiment of the application.

Fig. 4 is a block diagram of the temperature feature extraction module in the processor according to an embodiment of the application.

Fig. 5 is a block diagram of the control result generation module in the processor according to an embodiment of the present application.

Fig. 6 is a flow chart of a method of graphite film electromagnetic induction thermal ablation stent in accordance with an embodiment of the present application.

Fig. 7 is a schematic diagram of a system architecture of a method of graphite film electromagnetic induction thermal ablation stent in accordance with an embodiment of the present application.

Fig. 8 is a schematic perspective view of the overall structure of a graphite film electromagnetic induction thermal ablation support according to an embodiment of the application.

Fig. 9 is a schematic partial perspective view showing an internal structure of a sliding support rod position relationship of a graphite film electromagnetic induction thermal ablation support according to an embodiment of the application.

Fig. 10 is a schematic partial perspective view showing the internal structure of a movable cavity of a graphite film electromagnetic induction thermal ablation support according to an embodiment of the application.

Detailed Description

Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.

Scene overview: as described above, in thermal ablation by the gastric bypass stent, it is necessary to control the temperature of the stent, and since the gastric bypass stent is located in the lumen, it cannot be achieved by conventional heating means such as electric heating. Accordingly, an optimized graphite film electromagnetic induction thermal ablation stent is desired.

In order to solve the above problems, a layer of graphite film is coated outside the support, and temperature sensors are arranged at a plurality of positions of the graphite film for monitoring the heating temperature of the support. After the device is placed in a body, an alternating electromagnetic field is applied in the body by using an electromagnetic induction principle, the intensity of the electromagnetic field and a control waveform are controlled, and a graphite film is heated and temperature is controlled, so that the thermal ablation of the inner wall of a cavity is realized, and a new benign mucosa can be generated on the inner wall of the cavity.

Specifically, as shown in fig. 1, in the technical solution of the present application, a graphite film electromagnetic induction thermal ablation stent 10 is provided, which includes: a gastric bypass stent body 11; a graphite layer 12 coated on the outer surface of the gastric bypass stent body; a plurality of temperature sensors 13 arranged in a predetermined topological pattern on the graphite layer; and a processor 14 electrically connected to the plurality of temperature sensors.

Accordingly, considering that when the temperature of the gastric bypass stent is controlled to achieve thermal ablation, the change of the temperature value needs to be strictly controlled, it is found that when the temperature regulation is actually performed on the stent, since the relationship between the alternating electromagnetic field and the change of the temperature is difficult to determine, the determination can be roughly performed only through a large number of experiments, which not only wastes a large amount of time and effort, but also makes the determination result of the relationship not high in accuracy. Based on the above, in the technical scheme of the application, an artificial intelligence control technology based on deep learning is adopted to regulate and control the electromagnetic wave through implicit characteristic distribution information of a waveform diagram of the electromagnetic wave and multiscale dynamic change characteristic information of temperature in a time dimension, and in the process, spatial topological characteristics of a plurality of temperature sensors are also introduced to strengthen expression of dynamic change characteristics of temperature in time sequence, so that the accuracy of regulating and controlling the electromagnetic wave is improved. Therefore, electromagnetic waves can be accurately regulated and controlled according to actual conditions, and further heating and temperature control of the graphite film can be accurately realized, so that thermal ablation of the inner wall of the cavity is realized, and a new benign mucous membrane can be generated on the inner wall of the cavity.

Specifically, in the technical scheme of the application, firstly, a waveform diagram of electromagnetic waves in a preset time period is acquired, and temperature values of a plurality of preset time points in the preset time period are acquired through the plurality of temperature sensors. Then, considering that the temperature values acquired by the plurality of temperature sensors have different fluctuation characteristics under different time spans in the preset time period, in order to be able to sufficiently extract time sequence dynamic change characteristic distribution information of the temperature, the temperature values of a plurality of preset time points in the preset time period acquired by the temperature sensors are respectively arranged into temperature input vectors according to time dimensions, and then feature mining is performed in a multi-scale neighborhood feature extraction module, so as to extract multi-scale neighborhood associated features of the temperature values under different time spans, thereby obtaining a plurality of temperature feature vectors.

And then, the plurality of temperature characteristic vectors are arranged in two dimensions to integrate dynamic change characteristic distribution information of the temperature values acquired by the temperature sensors, so that a temperature global characteristic matrix is obtained. Furthermore, in consideration of the influence among the temperature sensors when the temperature sensors measure the temperature, the temperature change of the whole gastric bypass stent and the temperature value acquired by the temperature sensors are correlated, so that in the technical scheme of the application, the space topological feature among the temperature sensors is further introduced to optimize the dynamic change feature expression of the temperature. Specifically, the spatial topological matrixes of the plurality of temperature sensors are passed through a first convolution neural network model serving as a feature extractor to extract spatial topological features among the temperature sensors, so that a spatial topological feature matrix is obtained. In particular, here, the characteristic value of each position on the off-diagonal position of the spatial topology matrix is the distance between the respective two temperature sensors.

Further, the temperature characteristic vector of each temperature sensor is used as the characteristic representation of a node, the space topology characteristic matrix is used as the characteristic representation of an edge between the nodes, and the temperature global characteristic matrix and the space topology characteristic matrix which are obtained by two-dimensional arrangement of the temperature characteristic vectors pass through a graph neural network to obtain a topology temperature global characteristic matrix. Specifically, the graph neural network performs graph structure data coding on the spatial topological feature matrix and the temperature global feature matrix through a learnable neural network parameter to obtain the topological temperature global feature matrix containing irregular spatial topological features related to each temperature sensor and multi-scale dynamic change feature information of temperatures acquired by each temperature sensor in time sequence.

Then, for the signal characteristics of the electromagnetic wave, feature mining is carried out on the waveform diagram of the electromagnetic wave in the preset time period in a second convolution neural network model serving as a filter so as to extract local implicit feature distribution information of the waveform diagram of the electromagnetic wave, namely the implicit change feature of the electromagnetic wave in time sequence, so that an electromagnetic waveform feature vector is obtained.

And then, calculating a transfer vector of the electromagnetic waveform feature vector relative to the topological temperature global feature matrix to represent relevance feature distribution information between the overall multi-scale dynamic change feature of the temperature values acquired by each sensor on the bracket and the time sequence implicit change feature of the electromagnetic wave, namely the influence of the regulation change of the electromagnetic wave on the temperature of the gastric shunt bracket, and taking the influence as a classification feature vector to carry out classification processing in a classifier so as to obtain a classification result for representing that the frequency of the electromagnetic wave is increased or reduced and the amplitude of the electromagnetic wave is increased or reduced. Therefore, electromagnetic waves can be regulated and controlled according to actual conditions, and further heating and temperature control of the graphite film are realized, and the inner wall of the cavity is thermally ablated, so that a new benign mucosa can be generated on the inner wall of the cavity.

In particular, in the technical solution of the present application, for the topological temperature global feature matrix obtained by using the spatial topological feature matrix and the temperature global feature matrix through a graph neural network model, since each topological temperature global feature vector, for example, expresses spatial correlation feature expression of a multi-scale time sequence correlation feature of a single temperature sensor under the spatial topology of the temperature sensor for a row vector, the topological temperature global feature matrix may be regarded as an overall feature obtained by combining local feature sets relative to the plurality of topological temperature global feature vectors.

And, because each of the plurality of topological temperature global feature vectors represents a spatial correlation feature of a single sensor under a spatial topology, which has a data spatial topological correlation relationship, the plurality of topological temperature global feature vectors have a multi-source information correlation relationship in addition to a neighborhood distribution relationship correlated with each other.

Thus, in order to promote the effect of the associated distribution expression of the plurality of topological temperature global feature vectors as a whole, the applicant of the present application expresses the plurality of topological temperature global featuresEach of the topological temperature global feature vectors in the vector is, for example, noted asPerforming multisource information fusion pre-verification distribution evaluation optimization to obtain an optimized topological temperature global feature vector ++>The method is specifically expressed as follows: />Wherein->Setting up superparameters for the neighborhood and when +.>When the number of the global feature vectors of the topology temperature is smaller than or equal to zero or larger than the number of the global feature vectors of the topology temperature, the feature vector +.>May be an all zero vector or a unit vector.

Here, the optimization of the multisource information fusion pre-verification distribution evaluation can be used for realizing effective folding of the pre-verification information of each feature vector on the local synthesis distribution based on the quasi-maximum likelihood estimation of the feature distribution fusion robustness for the feature local collection formed by a plurality of mutually-associated neighborhood parts, and the optimization paradigm of standard expected fusion information which can be used for evaluating the internal association in the collection and the change relation between the collection is obtained through the pre-verification distribution construction under the multisource condition, so that the information expression effect of the feature vector fusion based on the multisource information association is improved. Therefore, the topological temperature global feature matrix obtained by combining the optimized topological temperature global feature vectors can have a better overall expression effect. Therefore, the electromagnetic wave can be accurately regulated and controlled according to actual conditions, and further the heating and temperature control of the graphite film are realized, and the inner wall of the cavity is thermally ablated, so that a new benign mucosa can be generated on the inner wall of the cavity.

Based on this, the application provides a processor of a graphite film electromagnetic induction thermal ablation support, comprising: a data acquisition module for acquiring a waveform diagram of electromagnetic waves of a predetermined time period and temperature values of a plurality of predetermined time points within the predetermined time period acquired by the plurality of temperature sensors; the temperature characteristic extraction module is used for respectively arranging temperature values of a plurality of preset time points in the preset time period acquired by each temperature sensor into temperature input vectors according to a time dimension and then obtaining a plurality of temperature characteristic vectors through the multi-scale neighborhood characteristic extraction module; the global module is used for carrying out two-dimensional arrangement on the plurality of temperature characteristic vectors to obtain a temperature global characteristic matrix; the space topology feature extraction module is used for enabling the space topology matrixes of the plurality of temperature sensors to pass through a first convolution neural network model serving as a feature extractor to obtain a space topology feature matrix, wherein feature values of all positions on the non-diagonal positions of the space topology matrix are distances between the two corresponding temperature sensors; the map neural network module is used for enabling the space topological feature matrix and the temperature global feature matrix to pass through a map neural network model to obtain a topological temperature global feature matrix; the distribution evaluation optimization module is used for carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix so as to obtain an optimized topological temperature global feature matrix; an electromagnetic wave feature extraction module, configured to pass a waveform diagram of the electromagnetic wave in the predetermined period of time through a second convolutional neural network model serving as a filter to obtain an electromagnetic wave feature vector; the transfer module is used for calculating transfer vectors of the electromagnetic waveform feature vectors relative to the optimized topological temperature global feature matrix to serve as classification feature vectors; and a control result generation module for passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased.

Fig. 2 is an application scenario diagram of a graphite film electromagnetic induction thermal ablation stent according to an embodiment of the present application. As shown in fig. 2, in this application scenario, a waveform of an electromagnetic wave for a predetermined period of time (e.g., D1 as illustrated in fig. 2) and temperature values for a plurality of predetermined time points within the predetermined period of time (e.g., S as illustrated in fig. 2) acquired by the plurality of temperature sensors are acquired, wherein the electromagnetic wave is generated by an electromagnetic wave generator (e.g., C as illustrated in fig. 2) that is adapted to generate an alternating electromagnetic field, the plurality of temperature sensors are located on the graphite film electromagnetic induction thermal ablation stent (e.g., F as illustrated in fig. 2), and then the waveform of the electromagnetic wave for the predetermined period of time and the temperature values for the plurality of predetermined time points within the predetermined period of time are input to a server (e.g., S as illustrated in fig. 2) that is equipped with a graphite film electromagnetic induction thermal ablation control algorithm, wherein the server is capable of using the graphite film electromagnetic induction thermal ablation control algorithm to apply the waveform of the electromagnetic wave for the predetermined period of time and the plurality of predetermined time points to the electromagnetic wave for increasing or decreasing frequency or decreasing the classification result of the electromagnetic wave.

Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.

An exemplary processor: FIG. 3 is a block diagram of a processor according to an embodiment of the application. As shown in fig. 3, a processor 100 according to an embodiment of the present application includes: a data acquisition module 110 for acquiring a waveform diagram of an electromagnetic wave of a predetermined period of time and temperature values of a plurality of predetermined time points within the predetermined period of time acquired by the plurality of temperature sensors; the temperature feature extraction module 120 is configured to arrange temperature values of a plurality of predetermined time points in the predetermined time period acquired by each temperature sensor into a temperature input vector according to a time dimension, and then obtain a plurality of temperature feature vectors through the multi-scale neighborhood feature extraction module; the globalization module 130 is configured to two-dimensionally arrange the plurality of temperature feature vectors to obtain a temperature global feature matrix; the spatial topology feature extraction module 140 is configured to pass the spatial topology matrices of the plurality of temperature sensors through a first convolutional neural network model serving as a feature extractor to obtain a spatial topology feature matrix, where feature values of positions on non-diagonal positions of the spatial topology matrix are distances between two corresponding temperature sensors; the graph neural network module 150 is configured to pass the spatial topology feature matrix and the temperature global feature matrix through a graph neural network model to obtain a topology temperature global feature matrix; the distribution evaluation optimization module 160 is configured to perform multisource information fusion pre-verification distribution evaluation optimization on each topology temperature global feature vector of the topology temperature global feature matrix to obtain an optimized topology temperature global feature matrix; an electromagnetic wave feature extraction module 170 for passing the waveform pattern of the electromagnetic wave of the predetermined period through a second convolutional neural network model as a filter to obtain an electromagnetic wave feature vector; a transfer module 180, configured to calculate a transfer vector of the electromagnetic waveform feature vector with respect to the optimized topological temperature global feature matrix as a classification feature vector; and a control result generation module 190 for passing the classification feature vector through a classifier to obtain a classification result indicating that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased.

More specifically, in the embodiment of the present application, the data acquisition module 110 is configured to acquire a waveform chart of an electromagnetic wave of a predetermined time period and temperature values of a plurality of predetermined time points within the predetermined time period acquired by the plurality of temperature sensors. Considering that when the temperature of the gastric bypass stent is controlled to realize thermal ablation, the change of the temperature value needs to be strictly controlled, but it is found that when the temperature regulation is actually performed on the stent, the association relationship between the change of the alternating electromagnetic field and the temperature is difficult to determine, and only a large amount of time and effort can be wasted, and the accuracy of the determination result of the association relationship is not high. Based on the above, in the technical scheme of the application, an artificial intelligence control technology based on deep learning is adopted to regulate and control the electromagnetic wave through implicit characteristic distribution information of a waveform diagram of the electromagnetic wave and multiscale dynamic change characteristic information of temperature in a time dimension, and in the process, spatial topological characteristics of a plurality of temperature sensors are also introduced to strengthen expression of dynamic change characteristics of temperature in time sequence, so that the accuracy of regulating and controlling the electromagnetic wave is improved.

More specifically, in the embodiment of the present application, the temperature feature extraction module 120 is configured to arrange the temperature values of a plurality of predetermined time points in the predetermined time period acquired by each temperature sensor into a temperature input vector according to a time dimension, and then obtain a plurality of temperature feature vectors through a multi-scale neighborhood feature extraction module. In order to fully extract time sequence dynamic change feature distribution information of temperature, the temperature values of a plurality of preset time points in the preset time period acquired by the temperature sensors are respectively arranged into temperature input vectors according to time dimensions and then feature mining is carried out in a multi-scale neighborhood feature extraction module, so that multi-scale neighborhood associated features of the temperature values in different time spans are extracted, and a plurality of temperature feature vectors are obtained.

Accordingly, in one specific example, as shown in fig. 4, the temperature feature extraction module 120 includes: a first scale temperature feature extraction unit 121, configured to perform one-dimensional convolutional encoding on the temperature input vector by using a first convolutional layer of the multi-scale neighborhood feature extraction module to obtain a first scale temperature feature vector, where the first convolutional layer has a first one-dimensional convolution kernel with a first length; a second scale temperature feature extraction unit 122, configured to perform one-dimensional convolution encoding on the temperature input vector using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale temperature feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and a multi-scale fusion unit 123, configured to use a cascade layer of the multi-scale neighborhood feature extraction module to cascade the first-scale temperature feature vector and the second-scale temperature feature vector to obtain the plurality of temperature feature vectors.

Accordingly, in a specific example, the first scale temperature feature extraction unit 121 is further configured to: performing one-dimensional convolution encoding on the temperature input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first-scale temperature feature vector; wherein, the formula is:wherein->For the first one-dimensional convolution kernel>Width in direction, ++>Is a first one-dimensional convolution kernel parameter vector,For a local vector matrix operating with a convolution kernel function, < ->For the size of the first one-dimensional convolution kernel, +.>Representing the temperature input vector.

Accordingly, in a specific example, the second scale temperature feature extraction unit 122 is further configured to: performing one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale temperature feature vector; wherein, the formula is:wherein->For the second one-dimensional convolution kernel>Width in direction, ++>Is a second one-dimensional convolution kernel parameter vector,For a local vector matrix operating with a convolution kernel function, < ->For the size of the second one-dimensional convolution kernel, +.>Representing the temperature input vector.

More specifically, in the embodiment of the present application, the global module 130 is configured to two-dimensionally arrange the plurality of temperature feature vectors to obtain a temperature global feature matrix. And two-dimensionally arranging the plurality of temperature characteristic vectors to integrate dynamic change characteristic distribution information of the temperature values acquired by the temperature sensors, thereby obtaining a temperature global characteristic matrix.

More specifically, in the embodiment of the present application, the spatial topology feature extraction module 140 is configured to pass the spatial topology matrices of the plurality of temperature sensors through a first convolutional neural network model serving as a feature extractor to obtain a spatial topology feature matrix, where feature values of each position on a non-diagonal position of the spatial topology matrix are distances between two corresponding temperature sensors. Considering that the temperature sensors can be influenced when the temperature sensors are used for measuring the temperature, and the temperature change of the whole gastric bypass stent is related to the temperature value acquired by the temperature sensors, the spatial topological feature among the temperature sensors is further introduced to optimize the dynamic change feature expression of the temperature.

Accordingly, in one specific example, the spatial topology feature extraction module 140 is further configured to: performing two-dimensional convolution processing, feature matrix-based averaging pooling processing and nonlinear activation processing on input data in forward transfer of layers by using each layer of the first convolutional neural network model as a feature extractor to output the spatial topology feature matrix by the last layer of the first convolutional neural network model as a feature extractor, wherein the input of the first layer of the first convolutional neural network model as a feature extractor is the spatial topology matrix of the plurality of temperature sensors.

More specifically, in the embodiment of the present application, the graph neural network module 150 is configured to pass the spatial topology feature matrix and the temperature global feature matrix through a graph neural network model to obtain a topology temperature global feature matrix. And taking the temperature characteristic vector of each temperature sensor as the characteristic representation of a node, taking the space topology characteristic matrix as the characteristic representation of an edge between the nodes, and passing the temperature global characteristic matrix and the space topology characteristic matrix which are obtained by two-dimensionally arranging the temperature characteristic vectors through a graph neural network to obtain a topology temperature global characteristic matrix. Specifically, the graph neural network performs graph structure data coding on the spatial topological feature matrix and the temperature global feature matrix through a learnable neural network parameter to obtain the topological temperature global feature matrix containing irregular spatial topological features related to each temperature sensor and multi-scale dynamic change feature information of temperatures acquired by each temperature sensor in time sequence.

More specifically, in the embodiment of the present application, the distribution evaluation optimization module 160 is configured to perform multisource information fusion pre-verification distribution evaluation optimization on each topology temperature global feature vector of the topology temperature global feature matrix to obtain an optimized topology temperature global feature matrix.

Thus, in order to promote the associative distribution expression effect of the plurality of topological temperature global feature vectors as a whole, the applicant of the present application, for each topological temperature global feature vector of the plurality of topological temperature global feature vectors, for example, marks asPerforming multisource information fusion pre-verification distribution evaluation optimization to obtain an optimized topological temperature global feature vector ++>。

Accordingly, in one specific example, the distribution evaluation optimization module 160 is further configured to: carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix by the following formula to obtain an optimized topological temperature global feature vector; wherein, the formula is:wherein->Is the +.f. of the topology temperature global feature matrix>Global feature of topology temperatureVector (S)>Is the +.f. of the topology temperature global feature matrix>Global feature vector of topology temperature,>is the mean feature vector, ++>Setting up superparameters for a neighborhood->Represents a logarithmic function value based on 2, < +.>Representing the subtraction by position,is the first +.>And the optimized topological temperature global feature vector.

Here, the optimization of the multisource information fusion pre-verification distribution evaluation can be used for realizing effective folding of the pre-verification information of each feature vector on the local synthesis distribution based on the quasi-maximum likelihood estimation of the feature distribution fusion robustness for the feature local collection formed by a plurality of mutually-associated neighborhood parts, and the optimization paradigm of standard expected fusion information which can be used for evaluating the internal association in the collection and the change relation between the collection is obtained through the pre-verification distribution construction under the multisource condition, so that the information expression effect of the feature vector fusion based on the multisource information association is improved. Therefore, the topological temperature global feature matrix obtained by combining the optimized topological temperature global feature vectors can have a better overall expression effect.

More specifically, in the embodiment of the present application, the electromagnetic wave feature extraction module 170 is configured to pass the waveform chart of the electromagnetic wave of the predetermined period of time through a second convolutional neural network model as a filter to obtain an electromagnetic wave feature vector. And for the signal characteristics of the electromagnetic wave, performing characteristic mining on the waveform diagram of the electromagnetic wave in the preset time period in a second convolution neural network model serving as a filter to extract local implicit characteristic distribution information of the waveform diagram of the electromagnetic wave, namely implicit variation characteristics of the electromagnetic wave in time sequence, so as to obtain electromagnetic waveform characteristic vectors.

Accordingly, in one specific example, the electromagnetic wave feature extraction module 170 is further configured to: and respectively performing two-dimensional convolution processing, mean pooling processing based on a feature matrix and nonlinear activation processing on input data in forward transfer of layers by using each layer of the second convolutional neural network model as a filter to output the electromagnetic waveform feature vector by the last layer of the second convolutional neural network model as the filter, wherein the input of the first layer of the second convolutional neural network model as the filter is a waveform diagram of electromagnetic waves in the preset time period.

More specifically, in the embodiment of the present application, the transfer module 180 is configured to calculate a transfer vector of the electromagnetic waveform feature vector with respect to the optimized topological temperature global feature matrix as a classification feature vector. Calculating the transfer vector of the electromagnetic waveform feature vector relative to the topological temperature global feature matrix to represent the relevance feature distribution information between the overall multi-scale dynamic change feature of the temperature values acquired by each sensor on the bracket and the time sequence implicit change feature of the electromagnetic wave, namely the influence of the regulation change of the electromagnetic wave on the temperature of the gastric shunt bracket, and taking the influence as a classification feature vector to carry out classification processing in a classifier so as to obtain a classification result for representing that the frequency of the electromagnetic wave is increased or reduced and the amplitude of the electromagnetic wave is increased or reduced.

Accordingly, in one specific example, the transfer module 180 is further configured to: the characteristic direction of the electromagnetic waveform is calculated according to the following formulaThe transfer vector of the quantity relative to the optimized topological temperature global feature matrix is used as a classification feature vector; wherein, the formula is:wherein->Representing the optimized topology temperature global feature matrix, < >>Representing the electromagnetic waveform feature vector, +_>Representing the classification feature vector,/->Representing vector multiplication.

More specifically, in the embodiment of the present application, the control result generating module 190 is configured to pass the classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased.

Accordingly, in one specific example, as shown in fig. 5, the control result generating module 190 includes: a full-connection encoding unit 191, configured to perform full-connection encoding on the classification feature vector by using a full-connection layer of the classifier to obtain an encoded classification feature vector; and a classification unit 192, configured to input the encoded classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

In summary, the processor 100 of the graphite film electromagnetic induction thermal ablation stent according to the embodiment of the application is illustrated, and adopts an artificial intelligence control technology based on deep learning to regulate and control electromagnetic waves through implicit characteristic distribution information of a waveform diagram of the electromagnetic waves and multi-scale dynamic change characteristic information of temperature in a time dimension, and in the process, spatial topological characteristics of a plurality of temperature sensors are introduced to strengthen expression of dynamic change characteristics of temperature in time sequence, so that the accuracy of regulating and controlling the electromagnetic waves is improved. By the mode, the heating and temperature control of the graphite film can be accurately realized.

As described above, the processor 100 of the graphite film electromagnetic induction thermal ablation stent according to the embodiment of the present application may be implemented in various terminal devices, for example, a server based on a graphite film electromagnetic induction thermal ablation control algorithm, etc. In one example, the processor 100 of the graphite film electromagnetic induction thermal ablation stent may be integrated into a terminal device as a software module and/or hardware module. For example, said processor 100 of the graphite film electromagnetic induction thermal ablation stent may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the processor 100 of the graphite film electromagnetic induction thermal ablation stent may also be one of the numerous hardware modules of the terminal device.

Alternatively, in another example, the processor 100 of the graphite film electromagnetic induction thermal ablation stent and the terminal device may be separate devices, and the processor 100 of the graphite film electromagnetic induction thermal ablation stent may be connected to the terminal device through a wired and/or wireless network and transmit interactive information in a agreed data format.

An exemplary method is: fig. 6 is a flow chart of a method of graphite film electromagnetic induction thermal ablation stent in accordance with an embodiment of the present application. As shown in fig. 6, a method for electromagnetic induction thermal ablation of a graphite film stent according to an embodiment of the present application includes: s110, acquiring a waveform diagram of electromagnetic waves in a preset time period and temperature values of a plurality of preset time points in the preset time period acquired by the plurality of temperature sensors; s120, arranging temperature values of a plurality of preset time points in the preset time period acquired by each temperature sensor into temperature input vectors according to time dimensions respectively, and then obtaining a plurality of temperature feature vectors through a multi-scale neighborhood feature extraction module; s130, two-dimensionally arranging the plurality of temperature feature vectors to obtain a temperature global feature matrix; s140, passing the space topology matrix of the plurality of temperature sensors through a first convolution neural network model serving as a feature extractor to obtain a space topology feature matrix, wherein feature values of all positions on the non-diagonal positions of the space topology matrix are distances between two corresponding temperature sensors; s150, passing the space topology feature matrix and the temperature global feature matrix through a graph neural network model to obtain a topology temperature global feature matrix; s160, carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix to obtain an optimized topological temperature global feature matrix; s170, passing the waveform diagram of the electromagnetic wave in the preset time period through a second convolution neural network model serving as a filter to obtain an electromagnetic waveform characteristic vector; s180, calculating a transfer vector of the electromagnetic waveform feature vector relative to the optimized topological temperature global feature matrix as a classification feature vector; and S190 passing the classification feature vector through a classifier to obtain a classification result, the classification result being used to indicate that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased.

Fig. 7 is a schematic diagram of a system architecture of a method of graphite film electromagnetic induction thermal ablation stent in accordance with an embodiment of the present application. As shown in fig. 7, in the system architecture of the method of the graphite film electromagnetic induction thermal ablation stent, firstly, a waveform diagram of electromagnetic waves of a predetermined period of time and temperature values of a plurality of predetermined time points within the predetermined period of time acquired by the plurality of temperature sensors are acquired; then, temperature values of a plurality of preset time points in the preset time period acquired by each temperature sensor are respectively arranged into temperature input vectors according to a time dimension, and then a plurality of temperature feature vectors are obtained through a multi-scale neighborhood feature extraction module; then, the temperature feature vectors are arranged in two dimensions to obtain a temperature global feature matrix; then, the space topology matrix of the plurality of temperature sensors is passed through a first convolution neural network model serving as a feature extractor to obtain a space topology feature matrix, wherein feature values of all positions on the off-diagonal positions of the space topology matrix are distances between the two corresponding temperature sensors; then, the space topology feature matrix and the temperature global feature matrix pass through a graph neural network model to obtain a topology temperature global feature matrix; then, carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix to obtain an optimized topological temperature global feature matrix; then, passing the waveform diagram of the electromagnetic wave in the preset time period through a second convolution neural network model serving as a filter to obtain an electromagnetic waveform characteristic vector; then, calculating a transfer vector of the electromagnetic waveform feature vector relative to the optimized topological temperature global feature matrix as a classification feature vector; finally, the classification feature vector is passed through a classifier to obtain a classification result, which is used to indicate that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased.

In a specific example, in the method for graphite film electromagnetic induction thermal ablation stent, the arranging the temperature values of a plurality of predetermined time points in the predetermined time period acquired by each temperature sensor into a temperature input vector according to a time dimension, and then obtaining a plurality of temperature feature vectors through a multi-scale neighborhood feature extraction module, includes: performing one-dimensional convolution encoding on the temperature input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first-scale temperature feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length; performing one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale temperature feature vector, wherein the second convolution layer is provided with a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and cascading the first-scale temperature feature vector and the second-scale temperature feature vector by using a cascading layer of the multi-scale neighborhood feature extraction module to obtain the plurality of temperature feature vectors.

In a specific example, in the method of graphite film electromagnetic induction thermal ablation of stents described above, the useThe first convolution layer of the multi-scale neighborhood feature extraction module performs one-dimensional convolution encoding on the temperature input vector to obtain a first-scale temperature feature vector, and the method further comprises the following steps: performing one-dimensional convolution encoding on the temperature input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first-scale temperature feature vector; wherein, the formula is:wherein->For the first one-dimensional convolution kernel>Width in the direction,For a first one-dimensional convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, < ->For the size of the first one-dimensional convolution kernel, +.>Representing the temperature input vector.

In a specific example, in the method for graphite film electromagnetic induction thermal ablation of a stent, the one-dimensional convolution encoding is performed on the temperature input vector by using the second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale temperature feature vector, and the method further includes: performing one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale temperature feature vector; wherein, the formula is: Wherein->For the second one-dimensional convolution kernel>Width in the direction,For a second one-dimensional convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, < ->For the size of the second one-dimensional convolution kernel, +.>Representing the temperature input vector.

In a specific example, in the method for graphite film electromagnetic induction thermal ablation stent, the step of passing the spatial topology matrix of the plurality of temperature sensors through a first convolutional neural network model as a feature extractor to obtain a spatial topology feature matrix further includes: performing two-dimensional convolution processing, feature matrix-based averaging pooling processing and nonlinear activation processing on input data in forward transfer of layers by using each layer of the first convolutional neural network model as a feature extractor to output the spatial topology feature matrix by the last layer of the first convolutional neural network model as a feature extractor, wherein the input of the first layer of the first convolutional neural network model as a feature extractor is the spatial topology matrix of the plurality of temperature sensors.

In a specific example, in the method for graphite film electromagnetic induction thermal ablation stent, performing multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix to obtain an optimized topological temperature global feature matrix, including: for each topology of the topology temperature global feature matrix, the following formula is adopted Carrying out multisource information fusion pre-verification distribution evaluation optimization on the temperature global feature vector to obtain an optimized topology temperature global feature vector; wherein, the formula is:wherein->Is the +.f. of the topology temperature global feature matrix>Global feature vector of topology temperature,>is the +.f. of the topology temperature global feature matrix>Global feature vector of topology temperature,>is the mean feature vector, ++>Setting up superparameters for a neighborhood->Represents a logarithmic function value based on 2, < +.>Representing subtraction by position +.>Is the first +.>And the optimized topological temperature global feature vector.

In a specific example, in the method for electromagnetic induction thermal ablation of a graphite film stent, the passing the waveform pattern of the electromagnetic wave for the predetermined period of time through a second convolutional neural network model as a filter to obtain an electromagnetic waveform feature vector further includes: and respectively performing two-dimensional convolution processing, mean pooling processing based on a feature matrix and nonlinear activation processing on input data in forward transfer of layers by using each layer of the second convolutional neural network model as a filter to output the electromagnetic waveform feature vector by the last layer of the second convolutional neural network model as the filter, wherein the input of the first layer of the second convolutional neural network model as the filter is a waveform diagram of electromagnetic waves in the preset time period.

In a specific example, in the method for graphite film electromagnetic induction thermal ablation stent, the calculating the transfer vector of the electromagnetic waveform feature vector with respect to the optimized topological temperature global feature matrix as a classification feature vector further includes: calculating a transfer vector of the electromagnetic waveform feature vector relative to the optimized topological temperature global feature matrix by using the following formula as a classification feature vector; wherein, the formula is:wherein->Representing the optimized topology temperature global feature matrix, < >>Representing the electromagnetic waveform feature vector, +_>Representing the classification feature vector,/->Representing vector multiplication.

In a specific example, in the method for graphite film electromagnetic induction thermal ablation stent, the step of passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased, includes: performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described method of the graphite film electromagnetic induction thermal ablation stent have been described in detail in the above description of the processor of the graphite film electromagnetic induction thermal ablation stent with reference to fig. 2 to 5, and thus, repetitive descriptions thereof will be omitted.

Structural example: this example relates to the following structure: graphite film F, fixed block F1, spacing groove F2, slip bracing piece F3, gag lever post F4, fixed column F5, shrink rope F6, activity chamber F7, spring F8, baffle F9 and opening F10, this example is solved and can appear the problem of landing when placing graphite film F.

Referring to fig. 8 to 10, there is shown: the specific working process is as follows: during operation, when placing graphite film F, initially drive graphite film F through external transport anchor clamps and move to the gastrointestinal tract in, when transport anchor clamps and graphite film F are released and are connected, transport anchor clamps are unable to stimulate baffle F9 this moment, baffle F9 moves to movable cavity F7's inside under spring F8's shrink pulling effect, opening F10 and gag lever post F4 coincide each other this moment, make sliding support pole F3 outside motion simultaneously under the pulling effect of shrink rope F6, sliding support pole F3 passes through gag lever post F4 and moves outside in limit groove F2's inside, when gag lever post F4 moves to the outside, make sliding support pole F3 outside slope through gag lever post F4 under the effect of limit groove F2 this moment, sliding support pole F3's outside end outside contacts and the butt with the inner wall of gastrointestinal tract, and then can prevent the circumstances that the landing appears when placing graphite film F, simultaneously also guaranteed graphite film F's stability when improving graphite film F's inside to support the validity to the gastrointestinal tract inner wall.

The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be considered as essential to the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.

The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.

It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.

The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims

1. A graphite film electromagnetic induction thermal ablation stent, comprising: a gastric bypass stent body; a graphite layer coated on the outer surface of the gastric diversion stent main body; a plurality of temperature sensors disposed in a predetermined topological pattern on the graphite layer; and a processor electrically connected to the plurality of temperature sensors.

2. The graphite film electromagnetic induction thermal ablation stent of claim 1, wherein the processor comprises: a data acquisition module for acquiring a waveform diagram of electromagnetic waves of a predetermined time period and temperature values of a plurality of predetermined time points within the predetermined time period acquired by the plurality of temperature sensors; the temperature characteristic extraction module is used for respectively arranging temperature values of a plurality of preset time points in the preset time period acquired by each temperature sensor into temperature input vectors according to a time dimension and then obtaining a plurality of temperature characteristic vectors through the multi-scale neighborhood characteristic extraction module; the global module is used for carrying out two-dimensional arrangement on the plurality of temperature characteristic vectors to obtain a temperature global characteristic matrix; the space topology feature extraction module is used for enabling the space topology matrixes of the plurality of temperature sensors to pass through a first convolution neural network model serving as a feature extractor to obtain a space topology feature matrix, wherein feature values of all positions on the non-diagonal positions of the space topology matrix are distances between the two corresponding temperature sensors; the map neural network module is used for enabling the space topological feature matrix and the temperature global feature matrix to pass through a map neural network model to obtain a topological temperature global feature matrix; the distribution evaluation optimization module is used for carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix so as to obtain an optimized topological temperature global feature matrix; an electromagnetic wave feature extraction module, configured to pass a waveform diagram of the electromagnetic wave in the predetermined period of time through a second convolutional neural network model serving as a filter to obtain an electromagnetic wave feature vector; the transfer module is used for calculating transfer vectors of the electromagnetic waveform feature vectors relative to the optimized topological temperature global feature matrix to serve as classification feature vectors; and a control result generation module for passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased.

3. The graphite film electromagnetic induction thermal ablation stent of claim 2, wherein the temperature signature extraction module comprises: a first scale temperature feature extraction unit, configured to perform one-dimensional convolutional encoding on the temperature input vector by using a first convolutional layer of the multi-scale neighborhood feature extraction module to obtain a first scale temperature feature vector, where the first convolutional layer has a first one-dimensional convolution kernel with a first length; a second scale temperature feature extraction unit, configured to perform one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale temperature feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and the multi-scale fusion unit is used for cascading the first-scale temperature characteristic vector and the second-scale temperature characteristic vector by using a cascading layer of the multi-scale neighborhood characteristic extraction module so as to obtain the plurality of temperature characteristic vectors.

4. The graphite film electromagnetic induction thermal ablation stent of claim 3, wherein the first scale temperature feature extraction unit is further configured to: performing one-dimensional convolution encoding on the temperature input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first-scale temperature feature vector; wherein, the formula is: Wherein->For the first one-dimensional convolution kernel>Width in the direction,For a first one-dimensional convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, < ->For the size of the first one-dimensional convolution kernel, +.>Representing the temperature input vector; the second scale temperature feature extraction unit is further configured to: performing one-dimensional convolution encoding on the temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale temperature feature vector; wherein, the formula is:wherein->For the second one-dimensional convolution kernel>Width in the direction,For a second one-dimensional convolution kernel parameter vector, +.>For a local vector matrix operating with a convolution kernel function, < ->For the size of the second one-dimensional convolution kernel, +.>Representing the temperature input vector.

5. The graphite film electromagnetic induction thermal ablation stent of claim 4, wherein the spatial topological feature extraction module is further configured to: performing two-dimensional convolution processing, feature matrix-based averaging pooling processing and nonlinear activation processing on input data in forward transfer of layers by using each layer of the first convolutional neural network model as a feature extractor to output the spatial topology feature matrix by the last layer of the first convolutional neural network model as a feature extractor, wherein the input of the first layer of the first convolutional neural network model as a feature extractor is the spatial topology matrix of the plurality of temperature sensors.

6. The graphite film electromagnetic induction thermal ablation stent of claim 5, wherein the distribution evaluation optimization module is further configured to: carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix by the following formula to obtain an optimized topological temperature global feature vector; wherein, the formula is:wherein->Is the +.f. of the topology temperature global feature matrix>Global feature vector of topology temperature,>is the global special of the topology temperatureFirst->The global feature vector of the topology temperature,is the mean feature vector, ++>Setting up superparameters for a neighborhood->Represents a logarithmic function value based on 2, < +.>Representing subtraction by position +.>Is the first +.>And the optimized topological temperature global feature vector.

7. The graphite film electromagnetic induction thermal ablation stent of claim 6, wherein the electromagnetic wave feature extraction module is further configured to: and respectively performing two-dimensional convolution processing, mean pooling processing based on a feature matrix and nonlinear activation processing on input data in forward transfer of layers by using each layer of the second convolutional neural network model as a filter to output the electromagnetic waveform feature vector by the last layer of the second convolutional neural network model as the filter, wherein the input of the first layer of the second convolutional neural network model as the filter is a waveform diagram of electromagnetic waves in the preset time period.

8. The graphite film electromagnetic induction thermal ablation stent of claim 7, whereinThe transfer module is further configured to: calculating a transfer vector of the electromagnetic waveform feature vector relative to the optimized topological temperature global feature matrix by using the following formula as a classification feature vector; wherein, the formula is:wherein->Representing the optimized topology temperature global feature matrix, < >>Representing the electromagnetic waveform feature vector, +_>The classification feature vector is represented as such,representing vector multiplication.

9. The graphite film electromagnetic induction thermal ablation stent of claim 8, wherein the control result generation module comprises: the full-connection coding unit is used for carrying out full-connection coding on the classification characteristic vectors by using a full-connection layer of the classifier so as to obtain coded classification characteristic vectors; and the classification unit is used for inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

10. A method of graphite film electromagnetic induction thermal ablation stent, comprising: acquiring a waveform diagram of electromagnetic waves of a preset time period and temperature values of a plurality of preset time points in the preset time period acquired by the plurality of temperature sensors; the temperature values of a plurality of preset time points in the preset time period acquired by each temperature sensor are respectively arranged into temperature input vectors according to the time dimension, and then a plurality of temperature feature vectors are obtained through a multi-scale neighborhood feature extraction module; two-dimensionally arranging the plurality of temperature feature vectors to obtain a temperature global feature matrix; the space topology matrix of the plurality of temperature sensors is passed through a first convolution neural network model serving as a feature extractor to obtain a space topology feature matrix, wherein feature values of all positions on non-diagonal positions of the space topology matrix are distances between two corresponding temperature sensors; the space topology feature matrix and the temperature global feature matrix are subjected to a graph neural network model to obtain a topology temperature global feature matrix; carrying out multisource information fusion pre-verification distribution evaluation optimization on each topological temperature global feature vector of the topological temperature global feature matrix to obtain an optimized topological temperature global feature matrix; passing the waveform diagram of the electromagnetic wave in the preset time period through a second convolution neural network model serving as a filter to obtain an electromagnetic waveform characteristic vector; calculating a transfer vector of the electromagnetic waveform feature vector relative to the optimized topological temperature global feature matrix as a classification feature vector; and passing the classification feature vector through a classifier to obtain a classification result, the classification result being used to indicate that the frequency of the electromagnetic wave should be increased or decreased and the amplitude of the electromagnetic wave should be increased or decreased.