Respiration control positioning method and system for radiation intervention

By generating the attribute set of respiratory positioning requirements and using the ability attribute data of radiointervention respiratory positioning sources for training and optimization, the problems of large size and low penetration of respiratory positioning machines are solved, and efficient matching and resource allocation of respiratory positioning requirements are achieved, improving the efficiency of respiratory positioning requirements. The patient's life and quality of life are achieved.

CN118903620AInactive Publication Date: 2024-11-08CHENGDU SEVENTH PEOPLES HOSPITAL
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410946853.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing respiratory positioning machine is large in size and is not portable, which makes it difficult for patients to inhale oxygen in time when going out, and the popularity rate in remote areas is low, affecting the quality of life and quality of life of patients. How to better and reasonably allocate and match respiratory positioning needs Resources are an urgent problem.

Method used

By generating the attribute set of respiratory positioning requirements objects, using the ability attribute data of multiple radioactive intervention respiratory positioning sources for training, receiving and optimizing model indicators and weights in real time, transmitting control permissions through encrypted communication lines, achieving maximum respiratory positioning requirements and resources Excellent match.

Benefits of technology

It improves the resource allocation efficiency and matching effect of respiratory positioning requirements, ensures that patients can obtain the necessary oxygen supply in time in any scenario, and improves the quality of life and survival.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118903620A_ABST
    Figure CN118903620A_ABST
Patent Text Reader

Abstract

The invention relates to the field of intelligent data control, and requests to protect a breathing control positioning method and system for radiation intervention, and the method comprises the steps: generating a breathing positioning demand object attribute set; ability attribute data of a plurality of existing radiation intervention respiration positioning sources are adopted as a training data set, and respiration positioning attribute indexes of the historical object attribute set are applied to the attribute set of the object to be subjected to respiration positioning after the historical object attribute set is trained; in the waiting process, the capability attribute data, received in real time, of the multiple radiation intervention respiration positioning sources are input into the trained attribute set of the object to be subjected to respiration positioning; transmitting the selected radiation intervention respiratory positioning source control authority to a respiratory positioning demand object; optimizing a model index and a weight of a respiration positioning demand object attribute set of a respiration positioning demand object receiving a radiation intervention respiration positioning source; according to the method, the breathing positioning demand resources can be reasonably allocated, and the breathing positioning demand and the breathing positioning provider can be optimally matched.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent data control, and in particular to a breathing control positioning method and system for radiological intervention. Background Art

[0002] As people's living standards improve and their awareness of health needs continues to grow, oxygen inhalation will gradually become a fashion for family health care. According to the working principle, home respiratory positioning machines are mainly classified into electronic respiratory positioning machines, molecular sieve respiratory positioning machines, chemical respiratory positioning machines, and oxygen-enriched membrane respiratory positioning machines. Molecular sieve respiratory positioning machines are currently the only mature respiratory positioning machines with international and national standards.

[0003] In daily care, patients can effectively relieve hypoxemia and improve their quality of life through oxygen therapy with a respiratory positioning machine. When patients go out for a walk or exercise, they are prone to hypoxia. However, since the respiratory positioning machine is large and inconvenient to carry, it is difficult to breathe oxygen in time when they encounter hypoxia when they are out, which affects the patient's range of activities and reduces the patient's quality of life. In addition, due to the shortage of radiological interventional resources, the penetration rate of respiratory positioning machines in remote areas is very low, which seriously affects the quality of life of local patients.

[0004] In particular, since the levels and capabilities of respiratory positioning are different in different regions, the urgency of different respiratory positioning needs is also different. How to better allocate resources and optimally match respiratory positioning needs is an urgent problem to be solved. Summary of the invention

[0005] According to a first aspect of the present invention, the present invention claims a breathing control positioning method for radiological intervention, characterized in that it comprises:

[0006] Generate a respiratory positioning requirement object attribute set, wherein the respiratory positioning requirement object attribute set includes a historical object attribute set and a to-be-respired positioning object attribute set;

[0007] Taking the capability attribute data of multiple existing radiological interventional respiratory positioning sources as a training data set, training the historical object attribute set, and applying the respiratory positioning attribute index of the historical object attribute set to the attribute set of the object to be respiratory positioned after the training is completed;

[0008] During the waiting process of the breathing positioning object, the capability attribute data of multiple radiological intervention breathing positioning sources received in real time are input into the attribute set of the training-completed breathing positioning object, and the output result is the query result of the radiological intervention breathing positioning source;

[0009] The control authority of the selected radiological intervention respiratory positioning source is transmitted to the subject requiring respiratory positioning through an encrypted communication line;

[0010] The model index and weight of the breathing positioning requirement object attribute set of the breathing positioning requirement object receiving the radiation intervention breathing positioning source are optimized.

[0011] Furthermore, the historical object attribute set and the to-be-breathed positioning object attribute set of the breathing positioning demand object attribute set adopt DOMP neural breathing positioning attributes; wherein the step of training the historical object attribute set comprises:

[0012] Collecting the radiation intervention respiratory positioning source and extracting the capability attribute data through the collector of the historical object attribute set, dividing the training sample set and the test sample set as the training data of the historical object attribute set;

[0013] Generate the historical object attribute set; the historical object attribute set includes two breathing positioning path samples OMP, and the two breathing positioning path samples OMP are synchronously trained;

[0014] Input the training sample set into two breathing positioning path samples OMP for training, optimize the index of the first breathing positioning path sample OMP, find the action with the maximum Q value in the first breathing positioning path sample OMP, and use the second breathing positioning path sample OMP to calculate the Q value that meets the requirements;

[0015] A residual function of the historical object attribute set is generated to represent the difference between the Q value of the current respiratory positioning requirement and the target Q value. When the residual function is minimized, it is determined that the training of the historical object attribute set is completed, and the test sample set is input into the trained historical object attribute set to calibrate the accuracy of the training.

[0016] Furthermore, after the training of the historical object attribute set is completed, the breathing positioning attribute index of the historical object attribute set is applied to the attribute set of the object to be breath-positioned; after the attribute set of the object to be breath-positioned performs a query on the radiation intervention breathing positioning source, the experience information is generated and sent to the historical object attribute set for the training iteration of the historical object attribute set.

[0017] Furthermore, the step of receiving capability attribute data of multiple radiation intervention respiratory positioning sources in real time includes:

[0018] The breathing positioning requirement object sends a detection interest packet to find potential radiation intervention breathing positioning sources and capability attribute data;

[0019] After receiving the radiological intervention breathing localization source, it is filtered through abnormal denoising to obtain a radiological intervention breathing localization source set as the input of the attribute set of the object to be breath localized.

[0020] Furthermore, a balanced optimization method is adopted to optimize the weight of the second respiratory positioning path sample OMP;

[0021] Before performing the radiological intervention breathing positioning source query, the step of triggering the radiological intervention breathing positioning source query is included; the reason for triggering the radiological intervention breathing positioning source query is determined to include at least: the breathing positioning demand object queries the radiological intervention breathing positioning source for the breathing positioning demand object when initializing; or the connected breathing positioning transmission channel deteriorates in quality or is disconnected and queries a new radiological intervention breathing positioning source for the breathing positioning demand object;

[0022] When deciding whether the quality of the connected respiratory positioning transmission channel deteriorates or the connection is interrupted, the interruption probability of the current respiratory positioning demand object connecting to the radiological intervention respiratory positioning source is calculated, and the current respiratory positioning demand priority is used as the random seed, and the hit replacement probability is calculated using a random function.

[0023] Generate a random number below 200 using the rand() function. It means that the probability of hitting the replacement of the radiological intervention respiratory positioning source is high;

[0024] That is, when the probability of interruption of the respiratory positioning transmission channel is greater than the maximum interruption probability, the probability calculation method will no longer be used for replacement identification, and the radiological intervention respiratory positioning source will be directly replaced.

[0025] According to a second aspect of the present invention, the present invention claims a breathing control positioning system for radiological intervention, characterized in that it comprises:

[0026] A breathing positioning attribute generation module: used to generate a breathing positioning requirement object attribute set, wherein the breathing positioning requirement object attribute set includes a historical object attribute set and a to-be-breathed positioning object attribute set;

[0027] A breathing positioning attribute training module is used to take the capability attribute data of multiple existing radiological intervention breathing positioning sources as a training data set to train the historical object attribute set, and after the training is completed, the breathing positioning attribute index of the historical object attribute set is applied to the attribute set of the object to be breath-positioned;

[0028] The radiological intervention breathing positioning source query module is used to input the capability attribute data of multiple radiological intervention breathing positioning sources received in real time into the attribute set of the trained object to be breath-positioned during the waiting process of the object requiring breathing positioning, and the output result is the query result of the radiological intervention breathing positioning source;

[0029] A transmission module, used for transmitting the selected radiological intervention respiratory positioning source control authority to the respiratory positioning demand object through an encrypted communication line;

[0030] The optimization module is used to optimize the model index and weight of the breathing positioning requirement object attribute set of the breathing positioning requirement object receiving the radiation intervention breathing positioning source.

[0031] Furthermore, the historical object attribute set and the to-be-breathed positioning object attribute set of the breathing positioning demand object attribute set adopt DOMP neural breathing positioning attributes; wherein the step of training the historical object attribute set comprises:

[0032] Collecting the radiation intervention respiratory positioning source and extracting the capability attribute data through the collector of the historical object attribute set, dividing the training sample set and the test sample set as the training data of the historical object attribute set;

[0033] Generate the historical object attribute set; the historical object attribute set includes two breathing positioning path samples OMP, and the two breathing positioning path samples OMP are synchronously trained;

[0034] Input the training sample set into two breathing positioning path samples OMP for training, optimize the index of the first breathing positioning path sample OMP, find the action with the maximum Q value in the first breathing positioning path sample OMP, and use the second breathing positioning path sample OMP to calculate the Q value that meets the requirements;

[0035] A residual function of the historical object attribute set is generated to represent the difference between the Q value of the current respiratory positioning requirement and the target Q value. When the residual function is minimized, it is determined that the training of the historical object attribute set is completed, and the test sample set is input into the trained historical object attribute set to calibrate the accuracy of the training.

[0036] Furthermore, after the training of the historical object attribute set is completed, the breathing positioning attribute index of the historical object attribute set is applied to the attribute set of the object to be breath-positioned; after the attribute set of the object to be breath-positioned performs a query on the radiation intervention breathing positioning source, the experience information is generated and sent to the historical object attribute set for the training iteration of the historical object attribute set.

[0037] Furthermore, the step of receiving capability attribute data of multiple radiation intervention respiratory positioning sources in real time includes:

[0038] The breathing positioning requirement object sends a detection interest packet to find potential radiation intervention breathing positioning sources and capability attribute data;

[0039] After receiving the radiological intervention breathing localization source, it is filtered through abnormal denoising to obtain a radiological intervention breathing localization source set as the input of the attribute set of the object to be breath localized.

[0040] A balanced optimization method is adopted to optimize the weight of the second respiratory positioning path sample OMP;

[0041] Before performing the radiological intervention breathing positioning source query, the step of triggering the radiological intervention breathing positioning source query is included; the reason for triggering the radiological intervention breathing positioning source query is determined to include at least: the breathing positioning demand object queries the radiological intervention breathing positioning source for the breathing positioning demand object when initializing; or the connected breathing positioning transmission channel deteriorates in quality or is disconnected and queries a new radiological intervention breathing positioning source for the breathing positioning demand object;

[0042] When deciding whether the quality of the connected respiratory positioning transmission channel has deteriorated or the connection is interrupted, the interruption probability of the current respiratory positioning demand object connecting to the radiological intervention respiratory positioning source is calculated, and the current respiratory positioning demand priority is used as the random seed. The hit replacement probability is calculated using a random function. That is, when the interruption probability of the respiratory positioning transmission channel is greater than the maximum interruption probability, the probability calculation method is no longer used for replacement identification, and the radiological intervention respiratory positioning source is directly replaced.

[0043] The invention relates to the field of intelligent data control, and claims protection for a breathing control positioning method and system for radiological intervention, which generate a breathing positioning demand object attribute set; take the capability attribute data of multiple existing radiological intervention breathing positioning sources as a training data set, train the historical object attribute set, and then apply the breathing positioning attribute index of the historical object attribute set to the attribute set of the object to be breathed; during the waiting process, input the capability attribute data of multiple radiological intervention breathing positioning sources received in real time into the attribute set of the object to be breathed after training, and the output result is the query result of the radiological intervention breathing positioning source; transmit the control authority of the selected radiological intervention breathing positioning source to the breathing positioning demand object; optimize the model index and weight of the breathing positioning demand object attribute set of the breathing positioning demand object receiving the radiological intervention breathing positioning source; the invention can better reasonably allocate breathing positioning demand resources and optimally match breathing positioning demand and breathing positioning provider. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flowchart of a breathing control positioning method for radiological intervention involved in the present invention;

[0045] Figure 2 A second working flow chart of a breathing control positioning method for radiological intervention involved in the present invention;

[0046] Figure 3 This is a structural module diagram of a breathing control positioning system for radiological intervention involved in the present invention. DETAILED DESCRIPTION

[0047] According to the first embodiment of the present invention, referring to Figure 1The present invention claims a breathing control positioning method for radiological intervention, characterized in that it includes:

[0048] Generate a respiratory positioning requirement object attribute set, wherein the respiratory positioning requirement object attribute set includes a historical object attribute set and a to-be-respired positioning object attribute set;

[0049] Taking the capability attribute data of multiple existing radiological interventional respiratory positioning sources as a training data set, training the historical object attribute set, and applying the respiratory positioning attribute index of the historical object attribute set to the attribute set of the object to be respiratory positioned after the training is completed;

[0050] During the waiting process of the breathing positioning object, the capability attribute data of multiple radiological intervention breathing positioning sources received in real time are input into the attribute set of the training-completed breathing positioning object, and the output result is the query result of the radiological intervention breathing positioning source;

[0051] The control authority of the selected radiological intervention respiratory positioning source is transmitted to the subject requiring respiratory positioning through an encrypted communication line;

[0052] The model index and weight of the breathing positioning requirement object attribute set of the breathing positioning requirement object receiving the radiation intervention breathing positioning source are optimized.

[0053] Further, see Figure 2 The historical object attribute set of the respiratory positioning demand object attribute set and the to-be-respired positioning object attribute set adopt DOMP neural respiratory positioning attributes; wherein the step of training the historical object attribute set comprises:

[0054] Collecting the radiation intervention respiratory positioning source and extracting the capability attribute data through the collector of the historical object attribute set, dividing the training sample set and the test sample set as the training data of the historical object attribute set;

[0055] Generate the historical object attribute set; the historical object attribute set includes two breathing positioning path samples OMP, and the two breathing positioning path samples OMP are synchronously trained;

[0056] Input the training sample set into two breathing positioning path samples OMP for training, optimize the index of the first breathing positioning path sample OMP, find the action with the maximum Q value in the first breathing positioning path sample OMP, and use the second breathing positioning path sample OMP to calculate the Q value that meets the requirements;

[0057] A residual function of the historical object attribute set is generated to represent the difference between the Q value of the current respiratory positioning requirement and the target Q value. When the residual function is minimized, it is determined that the training of the historical object attribute set is completed, and the test sample set is input into the trained historical object attribute set to calibrate the accuracy of the training.

[0058] Furthermore, after the training of the historical object attribute set is completed, the breathing positioning attribute index of the historical object attribute set is applied to the attribute set of the object to be breath-positioned; after the attribute set of the object to be breath-positioned performs a query on the radiation intervention breathing positioning source, the experience information is generated and sent to the historical object attribute set for the training iteration of the historical object attribute set.

[0059] Furthermore, the step of receiving capability attribute data of multiple radiation intervention respiratory positioning sources in real time includes:

[0060] The breathing positioning requirement object sends a detection interest packet to find potential radiation intervention breathing positioning sources and capability attribute data;

[0061] After receiving the radiological intervention breathing localization source, it is filtered through abnormal denoising to obtain a radiological intervention breathing localization source set as the input of the attribute set of the object to be breath localized.

[0062] Furthermore, the action formula for finding the maximum Q value of the first breathing positioning path sample OMP is expressed as:

[0063] a max (s′,ω)=argmax a′ Q(s′,a,ω) (1)

[0064] Among them, s represents the state, a represents the action, and ω is the weight index;

[0065] Use action a max (s′,ω) is calculated in the second respiratory positioning path sample OMP to obtain the target Q value, which is expressed as:

[0066] y=r+γQ′ (s′,argmax a′ Q(s′,a,ω),ω - ) (2)

[0067] Among them, γ represents the fault tolerance factor, and r represents the rich breathing positioning value.

[0068] Furthermore, the residual function formula of the historical object attribute set is expressed as:

[0069]

[0070] Among them, m represents the number of training times;

[0071] The balanced optimization method is adopted to optimize the weight of the second respiratory positioning path sample OMP, and the smooth optimization calculation is shown in formula (4):

[0072] ω - ←l*ω+(1-l)ω - (4)

[0073] Where l represents the optimization rate, l<<1, ω - is the weight index of the second breathing positioning path sample OMP;

[0074] Before performing the radiological intervention breathing positioning source query, the step of triggering the radiological intervention breathing positioning source query is included; the reason for triggering the radiological intervention breathing positioning source query is determined to include at least: the breathing positioning demand object queries the radiological intervention breathing positioning source for the breathing positioning demand object when initializing; or the connected breathing positioning transmission channel deteriorates in quality or is disconnected and queries a new radiological intervention breathing positioning source for the breathing positioning demand object;

[0075] When deciding whether the quality of the connected respiratory positioning transmission channel deteriorates or the connection is interrupted, the interruption probability of the current respiratory positioning demand object connecting to the radiological intervention respiratory positioning source is calculated, and the current respiratory positioning demand priority is used as the random seed, and the hit replacement probability is calculated using a random function, which is expressed as:

[0076]

[0077] Generate a random number below 200 using the rand() function. It means that the probability of executing the replacement of the radiological intervention respiratory positioning source is high; the formula is expressed as:

[0078]

[0079] Among them, H represents the replacement identification mark of the radiological intervention respiratory positioning source, P max It indicates the maximum interruption probability, that is, when the interruption probability of the respiratory positioning transmission channel is greater than the maximum interruption probability, the probability calculation method will no longer be used for replacement identification, and the radiological intervention respiratory positioning source will be directly replaced.

[0080] Further, after receiving the radiological intervention respiratory positioning source, the step of filtering by abnormal denoising includes:

[0081] The acquisition module receives the capability attribute data s of the i-th radiological intervention respiratory positioning source at time t t,i =(N t,i ,M t,i ,V t,i ,D t,i ), where N t,iM represents the round-trip time molecular sieve life between the i-th radiation intervention breathing positioning source and the breathing positioning demand object at time t; t,i represents the time offset of the i-th radiation intervention respiratory positioning source sending the data packet; V t,i represents the waiting speed of the i-th data at time t; D t,i represents the distance between the i-th radiological intervention breathing positioning source and the object that sends the breathing positioning request at time t;

[0082] N t,i Represents the molecular sieve life value. The smaller the molecular sieve life, the smaller the round-trip delay of the radiological intervention breathing positioning source, and the better the performance of the breathing positioning attribute. When the molecular sieve life value from the same radiological intervention breathing positioning source is obtained multiple times, it is more reliable to smooth the molecular sieve life. The smoothing method can be used. The calculation formula is as follows:

[0083] N t,i =u*N t-1,i +e*(R t,i -N t-1,i ) (7)

[0084] Among them, R t,i Indicates the currently observed instantaneous molecular sieve life value, u = 1, e = 0.125;

[0085] M t,i Indicates the smoothing offset time. Under the same cumulative running time, the larger the offset, the more idle the radiological intervention respiratory positioning source is, and the larger the remaining available cumulative running time is. On the contrary, the smaller the offset, the smaller the remaining available cumulative running time of the radiological intervention respiratory positioning source is. The calculation formula is:

[0086] M t,i =(1-σ)*M t-1,i +σ*(Data t,i -Data t-1,i ) (8)

[0087] Where, σ=0.5, Data t,i Indicates the current capability attribute data sending time, Data t-1,i Indicates the time when the last capability attribute data was sent. The difference between the two is the time offset.

[0088] V t,i Indicates the waiting speed of the breathing positioning object, V t,i >0 means the corresponding radiological intervention breathing positioning source and the object requesting breathing positioning are waiting in the same direction, V t,i <0 means that the corresponding radiological intervention breathing positioning source and the object requesting breathing positioning are waiting towards each other; the lower the speed, the more stable the radiological intervention breathing positioning source;

[0089] D t,i represents the distance between the i-th radiological intervention breathing positioning source and the breathing positioning requirement object sending the request at time t, D t,i >0 means that the corresponding radiological intervention respiratory positioning source is in front of the subject requiring respiratory positioning, D t,i <0 means that the corresponding radiological intervention breathing positioning source is behind the subject requiring breathing positioning; the closer the distance, the higher the stability of the radiological intervention breathing positioning source;

[0090] The multiple capability attribute data are used as the basis for sorting in turn to filter the radiological interventional breathing positioning sources with states; 4 states can respectively select one radiological interventional breathing positioning source, and the 4 radiological interventional breathing positioning sources contain 4 groups of 16 capability attribute data in total, which are input as the attribute set of the object to be breath positioned.

[0091] Furthermore, in the step of sequentially using the plurality of capability attribute data as a basis for sorting and filtering the radiological interventional respiratory positioning sources with status, the following steps are included:

[0092] Calculate the optimal value of each state, that is

[0093]

[0094] Calculate the execution time of action a t Query the score of the radiological interventional respiratory localization source:

[0095]

[0096] Among them, Max{G t,i} means in s t Execute a in the state t The highest score of the radiological interventional respiratory positioning source i queried during action;

[0097] The state index is normalized by adjusting the respiratory positioning attribute index of the attribute set of the object to be respiratory positioning, adjusting the value range of the action index, generating a mapping relationship between the radiological intervention respiratory positioning source and the state index value, and determining the radiological intervention respiratory positioning source with the highest score as the final query result;

[0098] The step of setting a rich breathing positioning value corresponding to the radiation intervention breathing positioning source is also included; the rich breathing positioning value function is expressed as:

[0099]

[0100] in, represents the throughput of the respiratory positioning transmission channel, Indicates the duration of the breathing positioning transmission channel, Indicates the molecular sieve life value of the currently connected radiation intervention respiratory positioning source, through N t,i Calculate the molecular sieve life; the range of other index coefficients is 1<<ρ≤2, 0<<φ≤0.5.

[0101] Furthermore, in the step of optimizing the model index and weight of the attribute set of the breathing positioning requirement object of the breathing positioning requirement object receiving the radiation intervention breathing positioning source, the steps include:

[0102] The respiratory positioning requirement object attribute set of the respiratory positioning requirement object learns the environment samples and optimizes the respiratory positioning attribute model and model weights by interacting with the real environment;

[0103] Optimize the attribute set model of the respiratory positioning requirement object;

[0104] In the steps of interacting with the real environment, learning environmental samples and optimizing the breathing localization attribute model and model weights,

[0105] Optimize the respiratory positioning attribute model and model weights, use local data and environmental status to train the respiratory positioning requirement object attribute set model, and transmit the weight results to an oxygen storage end after multiple iterations. The oxygen storage end calculates the gradient average value of the weight results of all the respiratory positioning requirement objects collected. The calculation formula is expressed as:

[0106]

[0107] Among them, n k Represents the number of times the breathing positioning demand object k is optimized locally, and n represents the total number of times the oxygen storage terminal aggregated weight is optimized; for each breathing positioning demand object, the oxygen storage terminal will optimize the weight once a day, especially when the breathing positioning demand object is first associated with the oxygen storage terminal or when it is associated with a new oxygen storage terminal.

[0108] According to the second embodiment of the present invention, referring to Figure 3 The present invention claims a breathing control positioning system for radiological intervention, characterized in that it comprises:

[0109] A breathing positioning attribute generation module: used to generate a breathing positioning requirement object attribute set, wherein the breathing positioning requirement object attribute set includes a historical object attribute set and a to-be-breathed positioning object attribute set;

[0110] A breathing positioning attribute training module is used to take the capability attribute data of multiple existing radiological intervention breathing positioning sources as a training data set to train the historical object attribute set, and after the training is completed, the breathing positioning attribute index of the historical object attribute set is applied to the attribute set of the object to be breath-positioned;

[0111] The radiological intervention breathing positioning source query module is used to input the capability attribute data of multiple radiological intervention breathing positioning sources received in real time into the attribute set of the trained object to be breath-positioned during the waiting process of the object requiring breathing positioning, and the output result is the query result of the radiological intervention breathing positioning source;

[0112] A transmission module, used for transmitting the selected radiological intervention respiratory positioning source control authority to the respiratory positioning demand object through an encrypted communication line;

[0113] The optimization module is used to optimize the model index and weight of the breathing positioning requirement object attribute set of the breathing positioning requirement object receiving the radiation intervention breathing positioning source.

[0114] Furthermore, the historical object attribute set and the to-be-breathed positioning object attribute set of the breathing positioning demand object attribute set adopt DOMP neural breathing positioning attributes; wherein the step of training the historical object attribute set comprises:

[0115] Collecting the radiation intervention respiratory positioning source and extracting the capability attribute data through the collector of the historical object attribute set, dividing the training sample set and the test sample set as the training data of the historical object attribute set;

[0116] Generate the historical object attribute set; the historical object attribute set includes two breathing positioning path samples OMP, and the two breathing positioning path samples OMP are synchronously trained;

[0117] Input the training sample set into two breathing positioning path samples OMP for training, optimize the index of the first breathing positioning path sample OMP, find the action with the maximum Q value in the first breathing positioning path sample OMP, and use the second breathing positioning path sample OMP to calculate the Q value that meets the requirements;

[0118] A residual function of the historical object attribute set is generated to represent the difference between the Q value of the current respiratory positioning requirement and the target Q value. When the residual function is minimized, it is determined that the training of the historical object attribute set is completed, and the test sample set is input into the trained historical object attribute set to calibrate the accuracy of the training.

[0119] Furthermore, after the training of the historical object attribute set is completed, the breathing positioning attribute index of the historical object attribute set is applied to the attribute set of the object to be breath-positioned; after the attribute set of the object to be breath-positioned performs a query on the radiation intervention breathing positioning source, the experience information is generated and sent to the historical object attribute set for the training iteration of the historical object attribute set.

[0120] Furthermore, the step of receiving capability attribute data of multiple radiation intervention respiratory positioning sources in real time includes:

[0121] The breathing positioning requirement object sends a detection interest packet to find potential radiation intervention breathing positioning sources and capability attribute data;

[0122] After receiving the radiological intervention breathing localization source, it is filtered through abnormal denoising to obtain a radiological intervention breathing localization source set as the input of the attribute set of the object to be breath localized.

[0123] Furthermore, the residual function formula of the historical object attribute set is expressed as:

[0124]

[0125] Among them, m represents the number of training times;

[0126] The balanced optimization method is adopted to optimize the weight of the second respiratory positioning path sample OMP, and the smooth optimization calculation is shown in formula (4):

[0127] ω - ←l*ω+(1-l)ω - (4)

[0128] Where l represents the optimization rate, l<<1, ω - is the weight index of the second breathing positioning path sample OMP;

[0129] Before performing the radiological intervention breathing positioning source query, the step of triggering the radiological intervention breathing positioning source query is included; the reason for triggering the radiological intervention breathing positioning source query is determined to include at least: the breathing positioning demand object queries the radiological intervention breathing positioning source for the breathing positioning demand object when initializing; or the connected breathing positioning transmission channel deteriorates in quality or is disconnected and queries a new radiological intervention breathing positioning source for the breathing positioning demand object;

[0130] When deciding whether the quality of the connected respiratory positioning transmission channel deteriorates or the connection is interrupted, the interruption probability of the current respiratory positioning demand object connecting to the radiological intervention respiratory positioning source is calculated, and the current respiratory positioning demand priority is used as the random seed, and the hit replacement probability is calculated using a random function, which is expressed as:

[0131]

[0132] Generate a random number below 200 using the rand() function. It means that the probability of executing the replacement of the radiological intervention respiratory positioning source is high; the formula is expressed as:

[0133]

[0134] Among them, H represents the replacement identification mark of the radiological intervention respiratory positioning source, P maxIt indicates the maximum interruption probability, that is, when the interruption probability of the respiratory positioning transmission channel is greater than the maximum interruption probability, the probability calculation method will no longer be used for replacement identification, and the radiological intervention respiratory positioning source will be directly replaced.

[0135] Those skilled in the art will appreciate that the contents disclosed in this disclosure may be subject to various variations and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0136] Flowcharts are used in this disclosure to illustrate the steps of the method according to the embodiments of the present disclosure. It should be understood that the preceding or following steps are not necessarily performed precisely in order. On the contrary, various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes.

[0137] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of a software functional module. The present disclosure is not limited to any particular form of combination of hardware and software.

[0138] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

[0139] The above is an explanation of the present disclosure and should not be considered as a limitation thereof. Although several exemplary embodiments of the present disclosure are described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present disclosure. Therefore, all such modifications are intended to be included within the scope of the present disclosure as defined in the claims. It should be understood that the above is an explanation of the present disclosure and should not be considered to be limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present disclosure is defined by the claims and their equivalents.

[0140] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0141] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A breathing control positioning method for radiological intervention, characterized in that: include: Generate a respiratory positioning requirement object attribute set, wherein the respiratory positioning requirement object attribute set includes a historical object attribute set and a to-be-respired positioning object attribute set; Taking the capability attribute data of multiple existing radiological interventional respiratory positioning sources as a training data set, training the historical object attribute set, and applying the respiratory positioning attribute index of the historical object attribute set to the attribute set of the object to be respiratory positioned after the training is completed; During the waiting process of the breathing positioning object, the capability attribute data of multiple radiological intervention breathing positioning sources received in real time are input into the attribute set of the training-completed breathing positioning object, and the output result is the query result of the radiological intervention breathing positioning source; The control authority of the selected radiological intervention respiratory positioning source is transmitted to the subject requiring respiratory positioning through an encrypted communication line; The model index and weight of the breathing positioning requirement object attribute set of the breathing positioning requirement object receiving the radiation intervention breathing positioning source are optimized.

2. The breathing control positioning method for radiological intervention according to claim 1, characterized in that: The historical object attribute set and the to-be-respired object attribute set of the respiratory positioning demand object attribute set adopt DOMP neural respiratory positioning attributes; wherein the step of training the historical object attribute set comprises: collecting radiological interventional respiratory positioning sources and extracting capability attribute data through a collector of the historical object attribute set, dividing the sets into training sample sets and testing sample sets as training data of the historical object attribute set; Generate the historical object attribute set; the historical object attribute set includes two breathing positioning path samples OMP, and the two breathing positioning path samples OMP are synchronously trained; Input the training sample set into two breathing positioning path samples OMP for training, optimize the index of the first breathing positioning path sample OMP, find the action with the maximum Q value in the first breathing positioning path sample OMP, and use the second breathing positioning path sample OMP to calculate the Q value that meets the requirements; A residual function of the historical object attribute set is generated to represent the difference between the Q value of the current respiratory positioning requirement and the target Q value. When the residual function is minimized, it is determined that the training of the historical object attribute set is completed, and the test sample set is input into the trained historical object attribute set to calibrate the accuracy of the training.

3. The breathing control positioning method for radiological intervention according to claim 2, characterized in that: After the training of the historical object attribute set is completed, the breathing positioning attribute index of the historical object attribute set is applied to the attribute set of the object to be breath-positioned; after the attribute set of the object to be breath-positioned performs a query on the radiological intervention breathing positioning source, the experience information is generated and sent to the historical object attribute set for the training iteration of the historical object attribute set.

4. The breathing control positioning method for radiological intervention according to claim 1, characterized in that: The steps of receiving capability attribute data of multiple radiological interventional respiratory positioning sources in real time include: The breathing positioning requirement object sends a detection interest packet to find potential radiation intervention breathing positioning sources and capability attribute data; After receiving the radiological intervention breathing localization source, it is filtered through abnormal denoising to obtain a radiological intervention breathing localization source set as the input of the attribute set of the object to be breath localized.

5. The breathing control positioning method for radiological intervention according to claim 2, characterized in that: Before performing the radiological intervention breathing positioning source query, the step of triggering the radiological intervention breathing positioning source query is included; The reasons for triggering the query of the radiological intervention breathing positioning source include at least: the breathing positioning requirement object queries the radiological intervention breathing positioning source for the breathing positioning requirement object when initializing; or the connected breathing positioning transmission channel deteriorates in quality or is disconnected, and a new radiological intervention breathing positioning source is queried for the breathing positioning requirement object; When deciding whether the quality of the connected respiratory positioning transmission channel deteriorates or the connection is interrupted, the interruption probability of the current respiratory positioning demand object connecting to the radiological intervention respiratory positioning source is calculated, and the current respiratory positioning demand priority is used as the random seed, and the hit replacement probability is calculated using a random function. Generate a random number below 200 using the rand() function. It means that the probability of hitting the replacement of the radiological intervention respiratory positioning source is high; That is, when the probability of interruption of the respiratory positioning transmission channel is greater than the maximum interruption probability, the probability calculation method will no longer be used for replacement identification, and the radiological intervention respiratory positioning source will be directly replaced.

6. A breathing control positioning system for radiological intervention, characterized in that: include: A breathing positioning attribute generation module: used to generate a breathing positioning requirement object attribute set, wherein the breathing positioning requirement object attribute set includes a historical object attribute set and a to-be-breathed positioning object attribute set; A breathing positioning attribute training module is used to take the capability attribute data of multiple existing radiological intervention breathing positioning sources as a training data set to train the historical object attribute set, and after the training is completed, the breathing positioning attribute index of the historical object attribute set is applied to the attribute set of the object to be breath-positioned; a radiological intervention breathing positioning source query module is used to input the capability attribute data of multiple radiological intervention breathing positioning sources received in real time into the attribute set of the object to be breath-positioned after the training is completed during the waiting process of the object requiring breathing positioning, and the output result is the query result of the radiological intervention breathing positioning source; A transmission module, used for transmitting the selected radiological intervention respiratory positioning source control authority to the respiratory positioning demand object through an encrypted communication line; The optimization module is used to optimize the model index and weight of the breathing positioning requirement object attribute set of the breathing positioning requirement object receiving the radiation intervention breathing positioning source.

7. The breathing control positioning system for radiological intervention according to claim 6, characterized in that: The historical object attribute set and the to-be-respired object attribute set of the respiratory positioning demand object attribute set adopt DOMP neural respiratory positioning attributes; wherein the step of training the historical object attribute set comprises: collecting radiological interventional respiratory positioning sources and extracting capability attribute data through a collector of the historical object attribute set, dividing the sets into training sample sets and testing sample sets as training data of the historical object attribute set; Generate the historical object attribute set; the historical object attribute set includes two breathing positioning path samples OMP, and the two breathing positioning path samples OMP are synchronously trained; Input the training sample set into two breathing positioning path samples OMP for training, optimize the index of the first breathing positioning path sample OMP, find the action with the maximum Q value in the first breathing positioning path sample OMP, and use the second breathing positioning path sample OMP to calculate the Q value that meets the requirements; A residual function of the historical object attribute set is generated to represent the difference between the Q value of the current respiratory positioning requirement and the target Q value. When the residual function is minimized, it is determined that the training of the historical object attribute set is completed, and the test sample set is input into the trained historical object attribute set to calibrate the accuracy of the training.

8. The breathing control positioning system for radiological intervention according to claim 7, characterized in that: After the training of the historical object attribute set is completed, the breathing positioning attribute index of the historical object attribute set is applied to the attribute set of the object to be breath-positioned; after the attribute set of the object to be breath-positioned performs a query on the radiological intervention breathing positioning source, the experience information is generated and sent to the historical object attribute set for the training iteration of the historical object attribute set.

9. The breathing control positioning system for radiological intervention according to claim 8, characterized in that: The steps of receiving capability attribute data of multiple radiological interventional respiratory positioning sources in real time include: The breathing positioning requirement object sends a detection interest packet to find potential radiation intervention breathing positioning sources and capability attribute data; After receiving the radiological intervention breathing localization source, it is filtered through abnormal denoising to obtain a radiological intervention breathing localization source set as the input of the attribute set of the object to be breath localized.

10. The breathing control positioning system for radiological intervention according to claim 9, characterized in that: A balanced optimization method is adopted to optimize the weight of the second respiratory positioning path sample OMP; Before performing the radiological intervention breathing positioning source query, the step of triggering the radiological intervention breathing positioning source query is included; The reasons for triggering the query of the radiological intervention breathing positioning source include at least: the breathing positioning requirement object queries the radiological intervention breathing positioning source for the breathing positioning requirement object when initializing; or the connected breathing positioning transmission channel deteriorates in quality or is disconnected, and a new radiological intervention breathing positioning source is queried for the breathing positioning requirement object; When deciding whether the quality of the connected respiratory positioning transmission channel deteriorates or the connection is interrupted, the interruption probability of the current respiratory positioning demand object connecting to the radiological intervention respiratory positioning source is calculated, and the current respiratory positioning demand priority is used as the random seed, and the hit replacement probability is calculated using a random function. Generate a random number below 200 using the rand() function. It means that the probability of hitting the replacement of the radiological intervention respiratory positioning source is high; That is, when the probability of interruption of the respiratory positioning transmission channel is greater than the maximum interruption probability, the probability calculation method will no longer be used for replacement identification, and the radiological intervention respiratory positioning source will be directly replaced.