Control method and device of drug delivery device

Abstract

The invention discloses a control method and device of a drug delivery device, and the method comprises the steps: obtaining a current entity shot image, first electromyogram information, muscle sensor information, a target MRI tomography image and first electroencephalogram information of a target entity; determining a target anomaly category based on the current entity shot image, the first electromyogram information, the muscle sensor information, the target MRI tomography image and the first electroencephalogram information; determining a target drug administration category of the target entity based on the target abnormal category of the target entity; determining drug administration strategy information of the target entity based on the target drug administration category and the entity information of the target entity, wherein the drug administration strategy information comprises drug administration time and drug administration amount; and controlling the drug delivery device to output drugs of the target drug delivery category based on the drug delivery strategy information. According to the invention, the administration efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a control method and device for a drug delivery device. Background Art

[0002] In the prior art, when patients use medicines, it is necessary to adjust the medicines in a timely manner according to the patient's condition. However, currently, staff can only manually determine whether the medicine needs to be replaced, what medicine to replace, and obtain the medicine based on the patient's condition and examination report. This manual method leads to low drug administration efficiency. Summary of the invention

[0003] The embodiments of the present application provide a control method and device for a drug delivery device, which can improve drug delivery efficiency.

[0004] In a first aspect, the present application provides a control method for a drug delivery device, comprising:

[0005] Acquire a current entity shot image, first electromyography information, muscle sensor information, a target MRI tomography image, and first electroencephalography information of the target entity;

[0006] Determining a target abnormality category based on the current entity captured image, the first electromyography information, the muscle sensor information, the target MRI tomography image, and the first electroencephalography information;

[0007] determining a target medication category for the target entity based on the target anomaly category for the target entity;

[0008] Determine medication strategy information of the target entity based on the target medication category and entity information of the target entity, wherein the medication strategy information includes medication time and medication amount;

[0009] The drug administration device is controlled to output drugs of the target drug administration category based on the drug administration strategy information.

[0010] Optionally, the drug delivery device is disposed on a sleeve device, the sleeve device includes a plurality of sensors, the plurality of sensors are used to obtain the muscle sensor information, the drug delivery device includes a universal pipeline, a plurality of drug storage chambers, a plurality of power chambers and a needle-free injection head, the plurality of drug storage chambers and the plurality of power chambers correspond one to one, the plurality of drug storage chambers are used to store different types of drugs, and the drug delivery device is controlled to output the target drug delivery category of the drug based on the drug delivery strategy information, including:

[0011] Based on the target medication category of the target entity, the power output of the power chamber corresponding to the target medication category of the target entity is controlled to output the medicine in the corresponding medicine storage chamber through the needle-free injection head.

[0012] Optionally, determining the target abnormality category based on the current entity captured image, the first electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalography information includes:

[0013] Taking the shooting time of the image shot by the current entity as the current time;

[0014] When the acquisition end time of the first electromyogram information is earlier than the current time, and the time difference between the acquisition end time of the first electromyogram information and the current time is greater than a first preset duration, determining whether the number of channels in the first electromyogram information exceeds n;

[0015] If the number of channels in the first electromyogram information exceeds n, determining information of n preset channels in the first electromyogram information as second electromyogram information;

[0016] Inputting the muscle sensor information and the second electromyogram information into a target electromyogram generation model to obtain third electromyogram information;

[0017] The target abnormality category is determined based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalography information.

[0018] Optionally, determining the target abnormality category based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalogram information includes:

[0019] When the acquisition end time of the first electroencephalogram information is earlier than the current time, and the time difference between the acquisition end time of the first electroencephalogram information and the current time is greater than a second preset duration, obtaining a first classification model trained based on a first training set, wherein the first classification model includes a first feature extraction module, a second feature extraction module, and a first classification module, and the first training set includes multiple first samples and corresponding anomaly categories, wherein the first sample includes a physical captured image sample and a corresponding electroencephalogram sample;

[0020] Inputting the current entity captured image into a first feature extraction module of a first classification model to obtain a first extracted feature;

[0021] Inputting the first electroencephalogram information into a second feature extraction module of a first classification model to obtain a second extracted feature;

[0022] Inputting the first extracted feature and the second extracted feature into a target electroencephalogram generation model to obtain second electroencephalogram information;

[0023] The target abnormality category is determined based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the second electroencephalography information.

[0024] Optionally, determining the target abnormality category based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the second electroencephalogram information includes:

[0025] Acquire a second classification model trained based on a second training set, wherein the second classification model includes a third feature extraction module and a second classification module, and the second training set includes a plurality of MRI tomography image samples and corresponding annotated abnormality categories;

[0026] Inputting the target MRI tomographic image into the target lesion segmentation model to obtain a plurality of lesion segmentation regions on the target MRI tomographic image;

[0027] Inputting each lesion segmentation region into the third feature extraction module of the second classification model respectively to obtain a plurality of segmentation region features corresponding to the plurality of lesion segmentation regions;

[0028] Splicing features of multiple segmented regions to obtain feature information of the spliced ​​region;

[0029] The target abnormality category is determined based on the current entity captured image, the third electromyography information, the muscle sensor information, the stitching area feature information and the second electroencephalography information.

[0030] Optionally, the control method of the drug delivery device comprises:

[0031] Acquire multiple electromyogram information segments and corresponding category labels, wherein the electromyogram information segments include electromyogram information of N channels, where N is greater than n;

[0032] Cutting the electromyogram information fragment into a plurality of electromyogram information window segments based on a sliding window of a preset length, and obtaining a plurality of electromyogram information window segments and corresponding category labels;

[0033] Using the plurality of electromyogram information window segments and corresponding category labels of each channel as a third training set to train a third classification model, and determining a first prediction accuracy rate of the third classification model to obtain N first prediction accuracy rates of N channels;

[0034] The N1 channels corresponding to the first N1 first prediction accuracy rates ranked from large to small are determined as N1 candidate channels, where n <N1<N;

[0035] Select n channels from the N1 candidate channels as n preset channels.

[0036] Optionally, the selecting n channels from N1 candidate channels as n preset channels includes:

[0037] For each of the multiple different entities, combining the electromyogram information window segments of every n channels in the electromyogram information window segments of N1 candidate channels into one training sample, to obtain multiple different training samples to form a fourth training set;

[0038] Training a fourth classification model based on a fourth training set;

[0039] Acquire the electromyogram information window segments of each n channels of the electromyogram information window segments of N1 candidate channels of the target entity and combine them into a second sample to obtain a plurality of second samples and corresponding sample labels;

[0040] Taking every n channels as a channel combination, obtaining multiple n-channel combinations, and obtaining a sample set of each n-channel combination, each sample set including multiple second samples belonging to the same n-channel combination;

[0041] Predicting a sample set of each n-channel combination based on the fourth classification model to obtain a second prediction accuracy rate of each n-channel combination;

[0042] The n channels in the n-channel combination with the second highest prediction accuracy are determined as n preset channels.

[0043] In a second aspect, the control device of the drug delivery device provided by the present application comprises:

[0044] An acquisition module, used to acquire a current entity shot image, first electromyography information, muscle sensor information, a target MRI tomography image, and first electroencephalogram information of a target entity;

[0045] A first determination module, configured to determine a target abnormality category based on a current entity captured image, first electromyography information, muscle sensor information, a target MRI tomography image, and first electroencephalogram information;

[0046] a second determination module, configured to determine a target medication category for a target entity based on a target abnormality category for the target entity;

[0047] A third determination module is used to determine the medication strategy information of the target entity based on the target medication category and the entity information of the target entity, wherein the medication strategy information includes medication time and medication amount;

[0048] A control module is used to control the drug delivery device to output drugs of the target drug delivery category based on the drug delivery strategy information.

[0049] In a third aspect, the electronic device provided in the present application includes a memory and a processor, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the control method of the drug delivery device provided in the present application.

[0050] In a fourth aspect, the computer-readable storage medium provided in the present application stores a plurality of instructions, which are suitable for loading by a processor to implement the steps in the control method of the drug delivery device provided in the present application.

[0051] In a fifth aspect, the computer program product provided in the present application includes a computer program or instructions, which, when executed by a processor, implement the steps in the control method of the drug delivery device provided in the present application.

[0052] In the present application, compared with the related art, the current entity shot image, the first electromyogram information, the muscle sensor information, the target MRI tomography image and the first electroencephalogram information of the target entity are obtained; the target abnormality category is determined based on the current entity shot image, the first electromyogram information, the muscle sensor information, the target MRI tomography image and the first electroencephalogram information; the target medication category of the target entity is determined based on the target abnormality category of the target entity; the medication strategy information of the target entity is determined based on the target medication category and the entity information of the target entity, and the medication strategy information includes the medication time and the medication amount; the medication device is controlled to output the drugs of the target medication category based on the medication strategy information. The present application can improve the medication efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0054] Figure 1 is a schematic diagram of a control system of a drug delivery device provided in an embodiment of the present application;

[0055] Figure 2 It is a structural schematic diagram of a sleeve device in a control system of a drug delivery device provided in an embodiment of the present application;

[0056] Figure 3 is a schematic diagram of the structure of a drug delivery device in a control system of a drug delivery device provided in an embodiment of the present application;

[0057] Figure 4 It is a flow chart of an embodiment of a control method of a drug delivery device provided in an embodiment of the present application;

[0058] Figure 5is a structural schematic diagram of a first classification model in an embodiment of a control method for a drug delivery device provided in an embodiment of the present application;

[0059] Figure 6 is a flow chart of another embodiment of the control method of the drug delivery device provided in the embodiment of the present application;

[0060] Figure 7 is a schematic diagram of the structure of a control device of a drug delivery device provided in an embodiment of the present application;

[0061] Figure 8 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] It should be noted that the principles of the present application are illustrated by implementing them in an appropriate computing environment. The following description is based on the illustrated specific embodiments of the present application and should not be considered as limiting other specific embodiments of the present application that are not described in detail herein.

[0063] In the following description of the present application, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0064] In the following description of the present application, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0066] In order to improve the control effect of a drug delivery device, the embodiments of the present application provide a control method of a drug delivery device, a control device of a drug delivery device, an electronic device, a computer-readable storage medium, and a computer program product. The control method of a drug delivery device can be executed by the control device of the drug delivery device, or by an electronic device integrated with the control device of the drug delivery device.

[0067] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0068] Please refer to Figure 1 The present application also provides a control system for a drug delivery device, such as Figure 1 As shown, the control system electronic device 100 and the sleeve device of the medication device, the control device of the medication device provided by the present application is integrated in the electronic device 100. The electronic device 100 and the sleeve device communicate with each other to send and receive instructions.

[0069] like Figure 2 and Figure 3 As shown, in the embodiment of the present application, the drug delivery device is arranged on the sleeve device, the sleeve device includes multiple sensors, the multiple sensors are used to obtain muscle sensor information, the drug delivery device includes a universal pipeline, multiple drug storage chambers, multiple power chambers and a needle-free injection head, the multiple drug storage chambers correspond to the multiple power chambers one by one, and the multiple drug storage chambers are used to store different types of drugs. The needle-free injection head is also provided with an injection hole.

[0070] The sleeve device has an elastic expansion and contraction function and can be worn on the arms, legs, upper limbs and other parts of the body. This application takes the example of wearing the sleeve on the upper arm as an example. The sleeve device is in a grid-like shape, and there are multiple sensors on the grid. The multiple sensors can be pulse pressure sensors, body surface temperature sensors, muscle tension sensors, and force muscle position sensors. The multiple sensors obtain p lines of time series data. Here, these 5 lines of data are taken as an example. If the measured data type needs to be increased, the number of lines can be more than 5.

[0071] Figure 3 Taking three drug storage chambers as an example, the drug delivery device includes a power chamber, a drug storage chamber, a universal pipeline, a needle-free injection head, and an injection hole. The power chamber serves the purpose of driving, in which the power source relies on a compression spring or filling with high-pressure gas. The power device is a disposable consumable, and the compression spring or compressed gas needs to be refilled after use. The drug storage chamber must meet the needs of adults for more than 5 times the amount of this type of medicine. The medicine is a consumable. It needs to be filled up after use to prepare for the next use in advance. If the medicine has not been used for a long time, it is necessary to regularly remove the old medicine and fill it with new medicine. The universal pipeline is a disposable consumable and needs to be replaced with a new one after use. It is arranged in a horizontal vein in the cuff, connecting multiple drug delivery pipelines and needle-free injection needles. No matter which drug delivery pipeline is started, the medicine shares this universal pipeline. The needle-free injection head is a disposable consumable, which needs to be replaced with a new one after use. It is a longitudinal vein and close to the skin surface. The medicine is flushed out through the injection hole.

[0072] Among them, the electronic device 100 can be any device equipped with a processor and has processing capabilities, such as mobile electronic devices with processors such as smart phones, tablet computers, PDAs, laptops, smart speakers, or fixed electronic devices with processors such as desktop computers, televisions, servers, industrial equipment, etc.

[0073] In addition, if Figure 1 As shown, the control system of the drug delivery device may further include a memory for storing raw data, intermediate data, and result data.

[0074] In the embodiment of the present application, the memory may be a cloud memory. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of storage devices of various types (storage devices are also called storage nodes) in the network through application software or application interfaces to work together and provide external data storage and business access functions.

[0075] At present, the storage method of the storage system is: create a logical volume, and when creating a logical volume, allocate physical storage space for each logical volume. The physical storage space may be composed of disks of a storage device or several storage devices. The client stores data on a logical volume, that is, stores the data on the file system. The file system divides the data into many parts, each of which is an object. The object contains not only data but also additional information such as data identification (ID, ID entity). The file system writes each object into the physical storage space of the logical volume, and the file system records the storage location information of each object, so that when the client requests to access the data, the file system can allow the client to access the data according to the storage location information of each object.

[0076] The process of the storage system allocating physical storage space to a logical volume is as follows: based on the estimated capacity of the objects stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the grouping of independent redundant disk arrays (RAID, Redundant Array of Independent Disks), the physical storage space is pre-divided into stripes. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.

[0077] It should be noted that Figure 1The scenario diagram of the control system of the drug delivery device shown is merely an example. The control system and scenario of the drug delivery device described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the control system of the drug delivery device and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is equally applicable to similar technical problems.

[0078] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0079] Please refer to Figure 4 , Figure 4 FIG. 1 is a flow chart of an embodiment of a control method for a drug delivery device provided in an embodiment of the present application. Figure 4 As shown, the process of the control method of the drug delivery device provided by the present application is as follows:

[0080] 201. Obtain a current entity shot image, first electromyography information, muscle sensor information, a target MRI tomography image, and first electroencephalogram information of a target entity.

[0081] In an embodiment of the present application, an entity video captured by a camera is obtained, wherein the entity video contains the body movements of the target entity, and is captured by a visible light camera (r / g / b three channels) during the day and by an infrared camera (single channel) at night. The entity video is processed by frame division to obtain the current entity captured images of multiple target entities, and the current entity captured images obtained at the current time are obtained. The current time is the shooting time of the current entity captured image.

[0082] In the embodiment of the present application, the first electromyogram information may be an electromyogram signal currently collected by the target entity, and the first electromyogram information may be an electromyogram signal collected historically by the target entity.

[0083] In the embodiment of the present application, the first electroencephalogram information may be an electroencephalogram signal currently collected by the target entity, and the first electroencephalogram information may be an electroencephalogram signal collected historically by the target entity.

[0084] In an embodiment of the present application, the drug delivery device is arranged on the sleeve device, the sleeve device includes multiple sensors, the multiple sensors are used to obtain muscle sensor information, the drug delivery device includes a universal pipeline, multiple drug storage chambers, multiple power chambers and a needle-free injection head, the multiple drug storage chambers and the multiple power chambers correspond one to one, and the multiple drug storage chambers are used to store different types of medicines.

[0085] The sleeve device has an elastic expansion and contraction function and can be worn on the arms, legs, upper limbs and other parts of the body. This application takes the example of wearing the sleeve on the upper arm as an example. The sleeve device is in a grid-like shape, and there are multiple sensors on the grid. The multiple sensors can be pulse pressure sensors, body surface temperature sensors, muscle tension sensors, and force muscle position sensors. The multiple sensors obtain p lines of time series data. Here, these 5 lines of data are taken as an example. If the measured data type needs to be increased, the number of lines can be more than 5.

[0086] Specifically, pulse pressure data, body surface temperature data, muscle tension data, and force-generating muscle position data are obtained, and then constructed into pulse pressure, temperature, tension, x, y, 5-line timing signals as muscle sensor information.

[0087] In the embodiment of the present application, the target MRI tomography image is the target MRI tomography image obtained by the most recent MRI tomography of the target entity.

[0088] 202. Determine a target abnormality category based on the current entity captured image, the first electromyography information, the muscle sensor information, the target MRI tomography image, and the first electroencephalography information.

[0089] In an embodiment of the present application, the target abnormality category may be a primary myoclonus category, a subcortical non-segmental myoclonus category, a myoclonic dystonia category, a reticular reflex myoclonus category, and a spinal myoclonus category.

[0090] In a specific embodiment, an abnormality classification model is trained, and the current entity captured image, the first electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalogram information are input into the abnormality classification model to obtain the target abnormality category.

[0091] In another specific embodiment, determining the target abnormality category based on the current entity captured image, the first electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalography information includes:

[0092] (1) The shooting time of the image taken by the current entity is taken as the current time.

[0093] (2) When the acquisition end time of the first electromyogram information is earlier than the current time, and the time difference between the acquisition end time of the first electromyogram information and the current time is greater than a first preset time length, determine whether the number of channels in the first electromyogram information exceeds n.

[0094] The first preset duration may be 1 week, 2 weeks or other values.

[0095] When the collection end time of the first electromyogram information is earlier than the current time, and the time difference between the collection end time of the first electromyogram information and the current time is greater than the first preset duration, it indicates that the collection time of the first electromyogram information is too long and may not be accurate, and more accurate electromyogram information needs to be generated.

[0096] When the collection end time of the first electromyogram information is earlier than the current time and the time difference between the collection end time of the first electromyogram information and the current time is not greater than the first preset duration, it indicates that the collection time of the first electromyogram information is not long and can be used. Then, the current entity captured image, the first electromyogram information, the muscle sensor information, the target MRI tomography image and the first electroencephalogram information are input into the abnormal classification model to obtain the target abnormality category.

[0097] (3) If the number of channels in the first electromyographic information exceeds n, information of n preset channels in the first electromyographic information is determined as the second electromyographic information.

[0098] n preset channels can be preset.

[0099] In an embodiment of the present application, a control method of a drug delivery device includes:

[0100] Step 1-1: Acquire multiple electromyography information segments and corresponding category labels, where the electromyography information segments include electromyography information of N channels.

[0101] Specifically, the electromyogram signals of specific patients are tracked and collected. The electromyogram signals have a total of N channels, usually N ≥ 8. According to the patient's myoclonus / non-myoclonus, the collected electromyogram signals are cut into multiple large segments to obtain multiple electromyogram information segments. If the current segment appears during myoclonus, the category labels of the corresponding electromyogram information segments are all myoclonus; if the current segment appears during non-myoclonus, the category labels of the corresponding electromyogram information segments are all non-myoclonus.

[0102] Further, the category label may be a primary myoclonus category, a subcortical non-segmental myoclonus category, a myoclonic dystonia category, a reticular reflex myoclonus category, and a spinal myoclonus category.

[0103] Step 1-2: based on a sliding window of a preset length, the electromyogram information fragment is cut into multiple electromyogram information window segments to obtain multiple electromyogram information window segments and corresponding category labels.

[0104] The preset length of the sliding window may be 500 / 600 / 1000 points, etc., and this application does not impose any specific limitation. For example, each electromyogram information segment is split into 10 electromyogram information window segments, and 10 electromyogram information segments are split into 100 electromyogram information window segments.

[0105] Step 1-3: Use multiple EMG information window segments and corresponding category labels of each channel as the third training set to train the third classification model, and determine the first prediction accuracy of the third classification model to obtain N first prediction accuracy rates of N channels.

[0106] In an embodiment of the present application, multiple EMG information window segments and corresponding sample labels of each channel are used as a third training set to obtain N third training sets, and the third classification model is trained using the N third training sets to obtain the first prediction accuracy of the N third classification models, and the N first prediction accuracy of the N channels are obtained. The first prediction accuracy can be an accuracy index of the third classification model on the third training set. Accuracy is an index used to evaluate a classification model.

[0107] Step 1-4: Determine the N1 channels corresponding to the first N1 first prediction accuracy rates ranked from large to small as N1 candidate channels, where n <N1<N。

[0108] For example, N is 8, N1 is 7, and n is 5, which can be set according to the specific situation.

[0109] Step 1-5: Select n channels from the N1 candidate channels as n preset channels.

[0110] In a specific embodiment, n channels are randomly selected from N1 candidate channels as n preset channels.

[0111] In another specific embodiment, selecting n channels from N1 candidate channels as n preset channels includes:

[0112] Step 2-1: for each of the multiple different entities, combine the electromyogram information window segments of every n channels in the electromyogram information window segments of the N1 candidate channels into one training sample, and obtain multiple different training samples to form a fourth training set.

[0113] In the embodiment of the present application, for one of the multiple different entities, the electromyography information window segments of n channels are selected from the N1 candidate channels as a training sample, that is, training samples, and all randomly matched training samples form the fourth training set. For example, there are k entities and each channel has m window segments, then the fourth training set has training samples.

[0114] Step 2-2: Train a fourth classification model based on a fourth training set.

[0115] Step 2-3: Obtain the electromyogram information window segments of each n channels of the electromyogram information window segments of the N1 candidate channels of the target entity, combine them into a second sample, and obtain multiple second samples and corresponding sample labels.

[0116] For the target entity, select n channels of EMG information window segments from N1 candidate channels as a second sample, that is, For example, if each channel has m window segments, then A second sample.

[0117] Step 2-4: Taking every n channels as a channel combination to obtain multiple n-channel combinations, and obtaining a sample set for each n-channel combination, each sample set including multiple second samples belonging to the same n-channel combination.

[0118] Specifically, each sample set of n-channel combination includes m second samples.

[0119] Step 2-5: Predict the sample set of each n-channel combination based on the fourth classification model to obtain the second prediction accuracy of each n-channel combination.

[0120] Specifically, for a sample set of one n-channel combination, there are 10 second samples, of which 9 are correctly predicted by the fourth classification model, and the second prediction accuracy of the n-channel combination is 90%.

[0121] Step 2-6: Determine n channels in the n-channel combination with the second highest prediction accuracy as n preset channels.

[0122] (4) The muscle sensor information and the second electromyogram information are input into a target electromyogram generation model to obtain third electromyogram information.

[0123] Of course, in other embodiments, only the muscle sensor information may be input into the target electromyogram generation model to obtain the third electromyogram information.

[0124] In the embodiment of the present application, the target EMG generation model may be a trained generative adversarial network (CGAN).

[0125] Specifically, after the muscle sensor information is aligned with the second electromyogram information based on the timestamp, the information is input into the target electromyogram generation model to obtain the third electromyogram information of n channels.

[0126] (5) Determine the target abnormality category based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalography information.

[0127] In a specific embodiment, an abnormality classification model is trained, and the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalogram information are input into the abnormality classification model to obtain the target abnormality category.

[0128] In another specific embodiment, determining the target abnormality category based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image, and the first electroencephalography information includes:

[0129] Step 3-1: When the collection end time of the first EEG information is earlier than the current time, and the time difference between the collection end time of the first EEG information and the current time is greater than a second preset duration, obtain a first classification model trained based on the first training set, wherein the first classification model includes a first feature extraction module, a second feature extraction module and a first classification module, and the first training set includes multiple first samples and corresponding labeled abnormal categories, wherein the first sample includes a physical captured image sample and a corresponding EEG sample.

[0130] like Figure 5 As shown, the first classification model includes a first feature extraction module, a second feature extraction module and a first classification module. The first feature extraction module is used to receive the current entity captured image in the video frame format through entry 1, and output the first extracted feature, namely feature 1. The first feature extraction module includes multiple convolution layers and feature deformation layers, and the feature deformation layer is used to perform the reshape operation. The first entry parameter of entry 1 is input_shape = (W1, H1, D1), where W1 is the image width of the current entity captured image, H1 is the image height of the current entity captured image, and D1 is the image depth of the current entity captured image, where D1 = 3 under visible light and D1 = 1 for infrared images. The second feature extraction module is used to receive the first EEG information in the EEG (electroencephalogram) window fragment format through entry 2, and output the second extracted feature, namely feature 2. The second feature extraction module includes multiple convolutional layers and feature deformation layers. The feature deformation layer is used to perform the reshape operation. The second entry parameter of entry 2 is input_shape = (W2, H2, 1), where W2 is the number of points contained in the first EEG information and H2 is the number of rows of the first EEG information. The first classification module is used for feature splicing and classification

[0131] The second preset duration may be 1 week, 2 weeks or other values.

[0132] When the collection end time of the first EEG information is earlier than the current time, and the time difference between the collection end time of the first EEG information and the current time is greater than the second preset duration, it indicates that the collection time of the first EEG information is too long and may not be accurate, and more accurate EEG information needs to be generated.

[0133] When the collection end time of the first EEG information is earlier than the current time and the time difference between the collection end time of the first EEG information and the current time is not greater than the first preset duration, it indicates that the collection time of the first EEG information is not long and can be used. Then, the current entity captured image, the third electromyogram information, the muscle sensor information, the target MRI tomography image and the first EEG information are input into the abnormal classification model to obtain the target abnormality category.

[0134] The first training set includes a plurality of first samples and corresponding anomaly categories, wherein the first samples include entity-shot image samples and corresponding electroencephalogram samples. The first training set can be manually collected and annotated.

[0135] In an embodiment of the present application, the entity captured image samples in the first sample are input into the first feature extraction module of the first classification model, and the electroencephalogram samples in the first sample are input into the second feature extraction module of the first classification model to obtain the predicted abnormal category output by the first classification module of the first classification model; the loss value is calculated based on the predicted abnormal category of the first sample and the labeled abnormal category of the first sample; the first classification model is iteratively trained based on the loss value to obtain the first classification model trained based on the first training set.

[0136] Specifically, a loss value can be calculated based on the predicted abnormal category of the first sample and the labeled abnormal category of the first sample according to the cross entropy loss function, and the first classification model can be iteratively trained based on the loss value until the loss value is less than a preset loss value, thereby obtaining a first classification model trained based on the first training set.

[0137] Step 3-2: Input the current entity captured image into the first feature extraction module of the first classification model to obtain the first extracted feature.

[0138] Step 3-3: Input the first electroencephalogram information into the second feature extraction module of the first classification model to obtain a second extracted feature.

[0139] Step 3-4: Input the first extracted features and the second extracted features into the target EEG generation model to obtain second EEG information.

[0140] Step 3-5: Determine the target abnormality category based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the second electroencephalography information.

[0141] In a specific embodiment, an abnormality classification model is trained, and the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the second electroencephalogram information are input into the abnormality classification model to obtain the target abnormality category.

[0142] In another specific embodiment, determining the target abnormality category based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the second electroencephalography information includes:

[0143] Step 4-1: Obtain a second classification model trained based on a second training set, wherein the second classification model includes a third feature extraction module and a second classification module, and the second training set includes multiple MRI tomography image samples and corresponding annotated abnormality categories.

[0144] Among them, the second classification model can be Resnet50, vgg16.

[0145] Step 4-2: Input the target MRI tomography image into the target lesion segmentation model to obtain multiple lesion segmentation regions on the target MRI tomography image.

[0146] Among them, the target lesion segmentation model is a pre-trained model, such as Unet / Unet++.

[0147] Step 4-3: Input each lesion segmentation region into the third feature extraction module of the second classification model respectively to obtain multiple segmentation region features corresponding to the multiple lesion segmentation regions.

[0148] Step 4-4: Concatenate multiple segmented region features to obtain concatenated region feature information.

[0149] Step 4-5: Determine the target abnormality category based on the current entity captured image, the third electromyography information, the muscle sensor information, the stitching area feature information and the second electroencephalography information.

[0150] In the embodiment of the present application, the current entity shot image, the stitching area feature information and the second electroencephalogram information are reshaped() to generate a two-dimensional matrix deep3, the muscle sensor information deep1, the third electromyogram information deep2, and the two-dimensional matrix deep3 are synthesized into a three-channel image, and input into the convolutional neural network for classification to obtain the target abnormal category. The classification labels of the convolutional neural network are primary myoclonus category, subcortical non-segmental myoclonus category, myoclonic dystonia category, reticular reflex myoclonus category and spinal myoclonus category.

[0151] 203. Determine a target medication category for the target entity based on the target abnormality category of the target entity.

[0152] In the embodiments of the present application, the correspondence between the medication category and the target abnormality category is preset. Specifically, the medication category is clonazepam, and the target abnormality categories are: primary myoclonus, subcortical non-segmental myoclonus, myoclonic dystonia, reticular reflex myoclonus and spinal myoclonus, etc.; the medication category is immunoglobulin, and the target abnormality category is: myoclonus caused by immune inflammation-; the medication category is botulinum toxin, and the target abnormality category is palatal myoclonus and segmental myoclonus; the medication category is serotonin, and the target abnormality category is hypoxic myoclonus. The drugs required for specific types of myoclonus must meet clinical requirements.

[0153] 204. Determine medication strategy information of the target entity based on the target medication category and entity information of the target entity, where the medication strategy information includes medication time and medication amount.

[0154] In the embodiment of the present application, the dosage recommendation model is trained, and the entity information of the target entity and the target medication category are input into the dosage recommendation model to obtain the dosage and medication time. Specifically, the entity information of the target entity includes the patient's gender gen, age age, weight g, and medical history T. The entity information of multiple entities and the corresponding category labels score are obtained to form a training set, and the dosage recommendation model is trained. The dosage recommendation model can be a decision tree, a random forest, or a BP neural network, etc.

[0155] Load the dosage recommendation model, obtain the dosage l for each dose, and generate the dosage strategy information.

[0156] For example, the medication strategy information includes: if the patient's continuous myoclonus is less than 5 minutes, no medication will be given; if the patient's continuous myoclonus exceeds 5 minutes, medication will be started, with the total dosage of each dosage l, which will be slowly injected in about 30 seconds. After the first medication is completed, if the continuous state is still not controlled, if the dosage recommendation model outputs a confidence level ≤τ1, it indicates that the condition is within the controllable range, and the original dosage should be repeated once every 20 minutes; if the dosage recommendation model outputs a confidence level ∈(τ1,τ2], it indicates that the condition is relatively serious, and the original dosage should be repeated twice every 20 minutes; if the dosage recommendation model outputs a confidence level >τ2, a reminder is given to send the patient to the hospital immediately.

[0157] 205. Control the drug delivery device to output drugs of the target drug delivery category based on the drug delivery strategy information.

[0158] In the implementation of the present application, the power output of the power chamber corresponding to the target drug administration category of the target entity is controlled based on the target drug administration category of the target entity, and the medicine in the corresponding drug storage chamber is output through the needle-free injection head.

[0159] like Figure 6As shown, in an embodiment of the present application, a control method for a drug delivery device includes: obtaining an electromyogram, collecting muscle signals of an electromyography cuff, and establishing a feature map 1 between the electromyogram and the muscle signal, for example, feature map 1 is a target electromyogram generation model. Obtain an electroencephalogram (EEG), collect limb movement features obtained by video monitoring, and establish a feature map 2 between the electroencephalogram and limb movement features, for example, feature map 2 is a target electroencephalogram generation model.

[0160] During the use stage, the muscle signals of the EMG cuff are collected, a mapping muscle point map is generated through the target EMG generation model, the limb movement features obtained by video monitoring are collected, the mapping EEG features are generated through the target EEG generation model, the image features are collected from the head MRI, the mapping muscle point map, muscle signals, mapping EEG features and image features collected by the head MRI are input into the PC, the PC performs myoclonus type identification, issues instructions, and controls the drug delivery device on the EMG cuff to output drugs according to the drug type and drug injection strategy.

[0161] In order to facilitate better implementation of the control method of the drug delivery device provided in the embodiment of the present application, the embodiment of the present application also provides a control device of the drug delivery device based on the control method of the drug delivery device. The meanings of the terms are the same as those in the control method of the drug delivery device. For specific implementation details, please refer to the description in the above method embodiment.

[0162] Please refer to Figure 7 , Figure 7 This is a schematic diagram of the structure of a control device of a drug delivery device provided in an embodiment of the present application. The control device of the drug delivery device may include:

[0163] An acquisition module 701 is used to acquire a current entity shot image, first electromyography information, muscle sensor information, a target MRI tomography image and first electroencephalogram information of a target entity;

[0164] A first determination module 702, configured to determine a target abnormality category based on a current entity captured image, first electromyography information, muscle sensor information, a target MRI tomography image, and first electroencephalography information;

[0165] A second determination module 703 is used to determine a target medication category of a target entity based on a target abnormality category of the target entity;

[0166] A third determination module 704 is used to determine the medication strategy information of the target entity based on the target medication category and the entity information of the target entity, wherein the medication strategy information includes medication time and medication amount;

[0167] The control module 705 is used to control the drug delivery device to output the drugs of the target drug delivery category based on the drug delivery strategy information.

[0168] The specific implementation of each of the above modules can be found in the previous embodiments and will not be described in detail here.

[0169] An embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the processor is used to execute the steps in the control method of the drug delivery device provided in the present embodiment by calling a computer program stored in the memory.

[0170] Please refer to Figure 8 , Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0171] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0172] The processor 101 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 102, and calling data stored in the memory 102. Optionally, the processor 101 may include one or more processing cores; optionally, the processor 101 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 101.

[0173] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.

[0174] The electronic device also includes a power supply 103 for supplying power to each component. Optionally, the power supply 103 can be logically connected to the processor 101 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 103 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0175] The electronic device may further include an input unit 104, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0176] Although not shown, the electronic device may also include a display unit, an image acquisition component, etc., which will not be described in detail here. Specifically in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps in the control method of the drug delivery device provided in this application, such as:

[0177] Acquire a current entity captured image, first electromyogram information, muscle sensor information, target MRI tomography image and first electroencephalogram information of the target entity; determine a target abnormality category based on the current entity captured image, first electromyogram information, muscle sensor information, target MRI tomography image and first electroencephalogram information; determine a target medication category of the target entity based on the target abnormality category of the target entity; determine medication strategy information of the target entity based on the target medication category and entity information of the target entity, the medication strategy information including medication time and medication amount; and control a medication device to output drugs of the target medication category based on the medication strategy information.

[0178] It should be noted that the electronic device provided in the embodiment of the present application and the control method of the drug delivery device in the above embodiment belong to the same concept, and its specific implementation process is detailed in the above related embodiments and will not be repeated here.

[0179] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program stored therein is executed on a processor of an electronic device provided in an embodiment of the present application, the processor of the electronic device executes the steps in the control method of the drug delivery device provided in the present application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0180] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes various optional implementations of the control method of the drug delivery device.

[0181] The control method and device of a drug delivery device provided by the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0182] It should be noted that when the above embodiments of the present application are applied to specific products or technologies, the relevant data of the user is involved, and the user's permission or consent is required, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A control method for a drug delivery device, characterized in that: The control method of the drug delivery device comprises: Acquire a current entity shot image, first electromyography information, muscle sensor information, a target MRI tomography image, and first electroencephalography information of the target entity; Determining a target abnormality category based on the current entity captured image, the first electromyography information, the muscle sensor information, the target MRI tomography image, and the first electroencephalography information; determining a target medication category for the target entity based on the target anomaly category for the target entity; Determine medication strategy information of the target entity based on the target medication category and entity information of the target entity, wherein the medication strategy information includes medication time and medication amount; The drug administration device is controlled to output drugs of the target drug administration category based on the drug administration strategy information.

2. The control method of the drug delivery device according to claim 1, characterized in that: The drug delivery device is arranged on a sleeve device, the sleeve device includes a plurality of sensors, the plurality of sensors are used to obtain the muscle sensor information, the drug delivery device includes a universal pipeline, a plurality of drug storage chambers, a plurality of power chambers and a needle-free injection head, the plurality of drug storage chambers and the plurality of power chambers correspond one to one, the plurality of drug storage chambers are used to store different types of drugs, and the drug delivery device is controlled to output the target drug delivery category of drugs based on the drug delivery strategy information, including: Based on the target medication category of the target entity, the power output of the power chamber corresponding to the target medication category of the target entity is controlled to output the medicine in the corresponding medicine storage chamber through the needle-free injection head.

3. The control method of the drug delivery device according to claim 2, characterized in that: The determining of the target abnormality category based on the current entity captured image, the first electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalogram information includes: Taking the shooting time of the image shot by the current entity as the current time; When the acquisition end time of the first electromyogram information is earlier than the current time, and the time difference between the acquisition end time of the first electromyogram information and the current time is greater than a first preset duration, determining whether the number of channels in the first electromyogram information exceeds n; If the number of channels in the first electromyogram information exceeds n, determining information of n preset channels in the first electromyogram information as second electromyogram information; Inputting the muscle sensor information and the second electromyogram information into a target electromyogram generation model to obtain third electromyogram information; The target abnormality category is determined based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalography information.

4. The control method of the drug delivery device according to claim 3, characterized in that: The determining of the target abnormality category based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the first electroencephalogram information includes: When the acquisition end time of the first electroencephalogram information is earlier than the current time, and the time difference between the acquisition end time of the first electroencephalogram information and the current time is greater than a second preset duration, obtaining a first classification model trained based on a first training set, wherein the first classification model includes a first feature extraction module, a second feature extraction module, and a first classification module, and the first training set includes multiple first samples and corresponding anomaly categories, wherein the first sample includes a physical captured image sample and a corresponding electroencephalogram sample; Inputting the current entity captured image into a first feature extraction module of a first classification model to obtain a first extracted feature; Inputting the first electroencephalogram information into a second feature extraction module of a first classification model to obtain a second extracted feature; Inputting the first extracted feature and the second extracted feature into a target electroencephalogram generation model to obtain second electroencephalogram information; The target abnormality category is determined based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the second electroencephalography information.

5. The control method of the drug delivery device according to claim 4, characterized in that: The determining of the target abnormality category based on the current entity captured image, the third electromyography information, the muscle sensor information, the target MRI tomography image and the second electroencephalography information includes: Acquire a second classification model trained based on a second training set, wherein the second classification model includes a third feature extraction module and a second classification module, and the second training set includes a plurality of MRI tomography image samples and corresponding annotated abnormality categories; Inputting the target MRI tomographic image into the target lesion segmentation model to obtain a plurality of lesion segmentation regions on the target MRI tomographic image; Inputting each lesion segmentation region into the third feature extraction module of the second classification model respectively to obtain a plurality of segmentation region features corresponding to the plurality of lesion segmentation regions; Splicing features of multiple segmented regions to obtain feature information of the spliced ​​region; The target abnormality category is determined based on the current entity captured image, the third electromyography information, the muscle sensor information, the stitching area feature information and the second electroencephalography information.

6. The control method of the drug delivery device according to claim 5, characterized in that: The control method of the drug delivery device comprises: Acquire multiple electromyogram information segments and corresponding category labels, wherein the electromyogram information segments include electromyogram information of N channels, where N is greater than n; Cutting the electromyogram information fragment into a plurality of electromyogram information window segments based on a sliding window of a preset length, and obtaining a plurality of electromyogram information window segments and corresponding category labels; Using the plurality of electromyogram information window segments and corresponding category labels of each channel as a third training set to train a third classification model, and determining a first prediction accuracy rate of the third classification model to obtain N first prediction accuracy rates of N channels; The N1 channels corresponding to the first N1 first prediction accuracy rates ranked from large to small are determined as N1 candidate channels, where n <N1<N; Select n channels from the N1 candidate channels as n preset channels.

7. The control method of the drug delivery device according to claim 6, characterized in that: The step of selecting n channels from N1 candidate channels as n preset channels comprises: For each of the multiple different entities, combining the electromyogram information window segments of every n channels in the electromyogram information window segments of N1 candidate channels into one training sample, to obtain multiple different training samples to form a fourth training set; Training a fourth classification model based on a fourth training set; Acquire the electromyogram information window segments of each n channels of the electromyogram information window segments of N1 candidate channels of the target entity and combine them into a second sample to obtain a plurality of second samples and corresponding sample labels; Taking every n channels as a channel combination, obtaining multiple n-channel combinations, and obtaining a sample set of each n-channel combination, each sample set including multiple second samples belonging to the same n-channel combination; Predicting a sample set of each n-channel combination based on the fourth classification model to obtain a second prediction accuracy rate of each n-channel combination; The n channels in the n-channel combination with the second highest prediction accuracy are determined as n preset channels.

8. A control device for a drug delivery device, characterized in that: include: An acquisition module, used to acquire a current entity shot image, first electromyography information, muscle sensor information, a target MRI tomography image, and first electroencephalogram information of a target entity; A first determination module, configured to determine a target abnormality category based on a current entity captured image, first electromyography information, muscle sensor information, a target MRI tomography image, and first electroencephalogram information; a second determination module, configured to determine a target medication category for a target entity based on a target abnormality category for the target entity; A third determination module is used to determine the medication strategy information of the target entity based on the target medication category and the entity information of the target entity, wherein the medication strategy information includes medication time and medication amount; A control module is used to control the drug delivery device to output drugs of the target drug delivery category based on the drug delivery strategy information.

9. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the control method of the drug delivery device according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor to execute the steps in the control method of the drug delivery device according to any one of claims 1 to 7.

Images