Obstructive sleep apnea pathology information processing method, device, equipment and medium

Abstract

Embodiments of the present disclosure disclose a method, device, equipment and medium for processing information of obstructive sleep respiratory pathology. A specific embodiment of the method comprises: in response to determining that the first resource allocation information is used to perform resource adjustment, determining a first resource adjustment time period corresponding to the first resource allocation information; in response to the current time being within the first resource adjustment time period, performing resource adjustment on the sleep detector group according to the first resource allocation information, and controlling the sleep detector group to perform an obstructive sleep respiratory detection task; in response to detecting that the obstructive sleep respiratory detection task is completed, reading a sleep respiratory detection data group; diagnosing and detecting each sleep respiratory detection data in the sleep respiratory detection data group to generate a sleep respiratory diagnosis detection result; and sending the sleep respiratory diagnosis detection result group to a doctor terminal. The embodiment improves the diagnosis and detection efficiency of obstructive sleep apnea.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of obstructive sleep apnea information processing, and in particular, to an obstructive sleep apnea information processing method, device, equipment and medium. BACKGROUND

[0002] Obstructive sleep apnea (OSA) is a common disease with potential health risks. The main clinical manifestations of the disease are snoring during sleep, accompanied by apnea and shallow breathing, and repeated occurrence of hypoxemia, hypercapnia and sleep structure disorder at night. If it develops to a certain extent, it will often cause daytime sleepiness, cardiovascular complications and other multiple organ damage, seriously affecting the quality of life and life of patients. At present, for the diagnosis of obstructive sleep apnea, the commonly used way is that the patient regularly goes to the hospital for regular detection and diagnosis by the doctor. However, the above diagnosis method for obstructive sleep apnea usually has the following technical problems: regular diagnosis, low efficiency, and long time for diagnosis and detection, which is easy to waste the medical resources of the hospital.

[0003] The above information disclosed in this BACKGROUND section is only for enhancing the understanding of the background of the present inventive concepts, and therefore, it can include information that does not form the prior art known to those of ordinary skill in the art in the country to which this application pertains. SUMMARY

[0004] The summary of the present disclosure is used to introduce the concepts in a brief manner, which will be described in detail in the specific embodiments section. The summary of the present disclosure is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to be used to limit the scope of the claimed technical solutions.

[0005] Some embodiments of the present disclosure provide an obstructive sleep apnea information processing method, device, electronic equipment and computer readable medium to solve one or more of the technical problems mentioned in the background section.

[0006] In a first aspect, some embodiments of the present disclosure provide a method for processing information of obstructive sleep apnea, applied to an obstructive sleep apnea diagnosis all-in-one machine, the obstructive sleep apnea diagnosis all-in-one machine comprising a cluster of sleep detectors, an obstructive sleep apnea diagnosis system, and a doctor terminal. The method comprises: in response to receiving an obstructive sleep apnea detection task, obtaining execution resource allocation information corresponding to the obstructive sleep apnea detection task; determining a sleep detector group corresponding to the obstructive sleep apnea detection task, wherein the sleep detector group comprises sleep detectors in the cluster of sleep detectors that are indicated by the obstructive sleep apnea detection task to perform the task; in response to determining that the execution resource allocation information indicates that the execution resource is adjusted by first resource allocation information, determining a first resource adjustment time period corresponding to the first resource allocation information; in response to the current time being within the first resource adjustment time period, performing resource adjustment on the sleep detector group according to the first resource allocation information, and controlling the sleep detector group to perform the obstructive sleep apnea detection task; in response to detecting that the obstructive sleep apnea detection task is completed, reading sleep apnea detection data from the sleep detector group, wherein the sleep apnea detection data in the sleep apnea detection data group corresponds to the sleep detectors in the sleep detector group; performing diagnosis and detection on each sleep apnea detection data in the sleep apnea detection data group by using the obstructive sleep apnea diagnosis system to generate sleep apnea diagnosis detection results, thereby obtaining a sleep apnea diagnosis detection result group; and sending the sleep apnea diagnosis detection result group to the doctor terminal.

[0007] In a second aspect, some embodiments of the present disclosure provide a sleep apnea pathological information processing device, applied to a sleep apnea diagnosis all-in-one machine, the sleep apnea diagnosis all-in-one machine comprising a sleep detector cluster, a sleep apnea diagnosis system and a doctor terminal, the device comprising: an acquisition unit configured to acquire execution resource allocation information corresponding to a sleep apnea detection task in response to receiving the sleep apnea detection task; a first determination unit configured to determine a sleep detector group corresponding to the sleep apnea detection task, wherein the sleep detector group is each sleep detector in the sleep detector cluster that needs to execute the task indicated by the sleep apnea detection task; a second determination unit configured to determine a first resource adjustment time period corresponding to the first resource allocation information in response to determining that the execution resource allocation information represents execution resource adjustment through the first resource allocation information; an adjustment unit configured to perform resource adjustment on the sleep detector group according to the first resource allocation information and control the sleep detector group to execute the sleep apnea detection task in response to the current time being within the first resource adjustment time period; a reading unit configured to read a sleep apnea detection data group from the sleep detector group in response to detecting that the sleep apnea detection task is executed; a detection unit configured to perform diagnosis and detection on each sleep apnea detection data in the sleep apnea detection data group through the sleep apnea diagnosis system to generate sleep apnea diagnosis detection results, thereby obtaining a sleep apnea diagnosis detection result group; and a sending unit configured to send the sleep apnea diagnosis detection result group to the doctor terminal.

[0008] In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the first aspect.

[0009] In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method described in any implementation manner of the first aspect.

[0010] The above various embodiments of the present disclosure have the following beneficial effects: the sleep apnea diagnosis and detection efficiency is improved by the sleep apnea pathological information processing method of some embodiments of the present disclosure, so that patients can diagnose sleep apnea at home to avoid excessive occupation of hospital medical resources. Specifically, the reason why hospital medical resources are easily wasted is that periodic diagnosis is inefficient and takes a long time, which easily wastes hospital medical resources. Based on this, the sleep apnea pathological information processing method of some embodiments of the present disclosure first acquires execution resource allocation information corresponding to a sleep apnea detection task in response to receiving the sleep apnea detection task. Thus, each sleep detector that needs to execute the task can be allocated communication resources. Then, a sleep detector group corresponding to the sleep apnea detection task is determined, wherein the sleep detector group is each sleep detector in the sleep detector cluster indicated by the sleep apnea detection task that needs to execute the task. In response to determining that the execution resource allocation information represents execution resource adjustment through first resource allocation information, a first resource adjustment time period corresponding to the first resource allocation information is determined; in response to the current time being within the first resource adjustment time period, the sleep detector group is executed according to the first resource allocation information, and the sleep detector group is controlled to execute the sleep apnea detection task. Thus, the sleep detector can collect sleep detection data according to the execution time period recorded in the task. Then, in response to detecting that the sleep apnea detection task is executed, a sleep detection data group is read from the sleep detector group, wherein the sleep detection data in the sleep detection data group corresponds to the sleep detector in the sleep detector group. Each sleep detection data in the sleep detection data group is diagnosed and detected by the sleep apnea diagnosis system to generate a sleep diagnosis result, thereby obtaining a sleep diagnosis result group. Thus, the sleep detection data can be preliminarily diagnosed and analyzed to assist doctors in diagnosis. Finally, the sleep diagnosis result group is sent to the doctor terminal. Thus, the sleep apnea diagnosis and detection efficiency is improved, so that patients can diagnose sleep apnea at home to avoid excessive occupation of hospital medical resources. BRIEF DESCRIPTION OF DRAWINGS

[0011] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent upon consideration of the following detailed description, taken in conjunction with the accompanying drawings. Throughout the drawings, like or similar reference numerals designate identical or similar elements throughout the several views. It should be understood that the drawings are schematic and elements and features are not necessarily drawn to scale.

[0012] Figure 1is a flow chart of some embodiments of the method for processing information of obstructive sleep respiratory pathology according to the present disclosure;

[0013] Figure 2 is a structural schematic diagram of some embodiments of the device for processing information of obstructive sleep respiratory pathology according to the present disclosure.

[0014] Figure 3 is a structural schematic diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0015] Embodiments of the present disclosure will be described in more detail with reference to the drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly and completely understood. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes and are not intended to limit the scope of protection of the present disclosure.

[0016] It should also be noted that, for ease of description, only the parts related to the present application are shown in the drawings. The embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0017] It should be noted that the terms "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules or units.

[0018] It should be noted that the adjectives "one", "multiple" mentioned in the present disclosure are illustrative and not limiting, and those skilled in the art should understand that, unless otherwise explicitly stated in the context, it should be understood as "one or more".

[0019] The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are only for illustrative purposes and are not intended to limit the scope of the messages or information.

[0020] The present disclosure will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0021] Figure 1 is a flow chart of some embodiments of the method for processing information of obstructive sleep respiratory pathology according to the present disclosure. The flow 100 of some embodiments of the method for processing information of obstructive sleep respiratory pathology according to the present disclosure is shown. The method for processing information of obstructive sleep respiratory pathology is applied to an obstructive sleep respiratory diagnosis all-in-one machine, and the above-mentioned obstructive sleep respiratory diagnosis all-in-one machine comprises a sleep detector cluster, an obstructive sleep respiratory diagnosis system and a doctor terminal, and comprises the following steps:

[0022] In step 101, in response to receiving the obstructive sleep breathing detection task, the execution resource allocation information corresponding to the obstructive sleep breathing detection task is obtained.

[0023] In some embodiments, the execution subject (e.g., a computing device) of the obstructive sleep breathing pathology information processing method can obtain the execution resource allocation information corresponding to the obstructive sleep breathing detection task in response to receiving the obstructive sleep breathing detection task. The obstructive sleep breathing diagnosis all-in-one machine can refer to an OSA (Obstructive Sleep Apnea) all-in-one machine. The obstructive sleep breathing detection task can refer to a task of detecting the breathing of each patient user to be detected for obstructive sleep breathing. Among them, the sleep detector in the sleep detector cluster can be a detection instrument for detecting the patient user to be detected for obstructive sleep breathing. One sleep detector corresponds to one patient user. The execution resource allocation information can be information representing how the resources of the obstructive sleep breathing detection task are configured during execution. For example, the execution resource allocation information can be allocation information representing communication resources. Because a large number of sleep detectors are involved, it is necessary to reasonably allocate communication resources to ensure normal data collection. The obstructive sleep breathing detection task can also include the number of each sleep detector that needs to execute the task and the execution time period.

[0024] In step 102, the sleep detector group corresponding to the obstructive sleep breathing detection task is determined.

[0025] In some embodiments, the execution subject can determine the sleep detector group corresponding to the obstructive sleep breathing detection task. Among them, the sleep detector group is each sleep detector in the sleep detector cluster that needs to execute the task indicated by the obstructive sleep breathing detection task. That is, each sleep detector corresponding to the obstructive sleep breathing detection task can be determined through the number of each sleep detector included in the obstructive sleep breathing detection task.

[0026] In step 103, in response to determining that the execution resource allocation information represents that the first resource allocation information is used to execute resource adjustment, the first resource adjustment time period corresponding to the first resource allocation information is determined.

[0027] In some embodiments, the execution subject can determine a first resource adjustment time period corresponding to the first resource allocation information, in response to determining that the execution resource allocation information represents that the execution resource adjustment is performed by the first resource allocation information. The first resource allocation information can be information representing how to allocate resources for the obstructive sleep apnea detection task according to a preset time period. The first resource adjustment time period can be a time period in which the execution resource corresponding to the obstructive sleep apnea detection task is expanded or reduced. The first resource adjustment time period can be a time period preset in the first resource allocation information. For example, the first resource adjustment time period is an A time period. In the A time period, the communication resource corresponding to the obstructive sleep apnea detection task is increased by 1 / 3.

[0028] In step 104, in response to the current time being in the first resource adjustment time period, the execution resource of the sleep detector group is adjusted according to the first resource allocation information, and the sleep detector group is controlled to perform the obstructive sleep apnea detection task.

[0029] In some embodiments, the execution subject can adjust the execution resource of the sleep detector group according to the first resource allocation information, and control the sleep detector group to perform the obstructive sleep apnea detection task, in response to the current time being in the first resource adjustment time period. For example, the communication resource available to the sleep detector in the sleep detector group can be increased or decreased according to the first resource allocation information. Then, each sleep detector in the sleep detector group can be controlled to collect sleep respiration detection data of a patient user according to a preset execution time period. The sleep respiration detection data can include, but is not limited to, multiple physiological parameters such as heart rate, respiration, body movement, snoring, and multiple sleep parameters such as sleep duration, sleep distribution, sleep efficiency, dream, etc.

[0030] Optionally, in response to determining that the execution resource allocation information represents that the execution resource adjustment is performed by the second resource allocation information, the resource change information corresponding to the obstructive sleep apnea detection task is determined.

[0031] In some embodiments, the execution subject can determine resource change information corresponding to the obstructive sleep apnea detection task in response to determining that the execution resource allocation information indicates that the execution resource is adjusted by the second resource allocation information. The second resource allocation information is information based on which the resource is adjusted according to the resource change information. The resource change information can represent a change in the execution resource corresponding to the obstructive sleep apnea detection task. In practice, the resource change information can be a change in the GPU resource used by the obstructive sleep apnea detection task. The second resource allocation information can include a capacity reduction threshold and a capacity expansion threshold. The capacity reduction threshold is less than the capacity expansion threshold. The capacity reduction threshold can be a threshold for reducing the resource. The capacity expansion threshold can be a threshold for expanding the resource. For example, the resource change information corresponding to the obstructive sleep apnea detection task can be determined by resource statistics.

[0032] Optionally, the execution subject can perform resource adjustment on the sleep detector group according to the resource change information.

[0033] In some embodiments, the execution subject can perform resource adjustment on the sleep detector group according to the resource change information. For example, the communication resource of each sleep detector in the sleep detector group can be adjusted by a proportional change (change ratio) according to the change ratio represented by the resource change information.

[0034] Optionally, in response to determining that the execution resource allocation information indicates that the execution resource is adjusted according to the first resource allocation information and the second resource allocation information, the second resource adjustment time period corresponding to the first resource allocation information is determined.

[0035] In some embodiments, the execution subject can determine the second resource adjustment time period corresponding to the first resource allocation information in response to determining that the execution resource allocation information indicates that the execution resource is adjusted according to the first resource allocation information and the second resource allocation information. The first resource allocation information and the second resource allocation information can be executed simultaneously according to the execution resource allocation information. The second resource adjustment time period can refer to the first resource adjustment time period or a pre-set resource adjustment time period.

[0036] Optionally, in response to the current time being within the second resource adjustment time period, the current execution resource allocation information is determined.

[0037] In some embodiments, the execution subject can determine the current execution resource allocation information in response to the current time being within the second resource adjustment time period.

[0038] In practice, the execution subject can determine the current execution resource allocation information by the following steps:

[0039] In a first step, a communication resource change value corresponding to the obstructive sleep apnea detection task is determined. For example, first, the execution subject can determine the highest amount of communication resources used by the obstructive sleep apnea detection task as the maximum amount of communication resources. Then, the lowest amount of communication resources used by the obstructive sleep apnea detection task is determined as the minimum amount of communication resources. Finally, the ratio of the maximum amount of communication resources to the minimum amount of communication resources is determined as the communication resource change value.

[0040] In a second step, in response to determining that the communication resource change value is greater than a preset value, the second resource allocation information is determined as the current execution resource allocation information.

[0041] In a third step, in response to determining that the communication resource change value is less than or equal to the preset value, the first resource allocation information is determined as the current execution resource allocation information.

[0042] Optionally, the sleep detector group is adjusted according to the current execution resource allocation information.

[0043] In some embodiments, the execution subject can adjust the sleep detector group according to the current execution resource allocation information.

[0044] In step 105, in response to detecting that the obstructive sleep apnea detection task is completed, the sleep apnea detection data group is read from the sleep detector group.

[0045] In some embodiments, the execution subject can read the sleep apnea detection data group from the sleep detector group in response to detecting that the obstructive sleep apnea detection task is completed. The sleep apnea detection data in the sleep apnea detection data group corresponds to the sleep detector in the sleep detector group. That is, the sleep apnea detection data of the patient user collected from each sleep detector in the sleep detector group can be read through wired or wireless connection.

[0046] In step 106, each sleep apnea detection data in the sleep apnea detection data group is diagnosed by the obstructive sleep apnea diagnosis system to generate sleep apnea diagnosis detection results, thereby obtaining a sleep apnea diagnosis detection result group.

[0047] In some embodiments, the execution subject can diagnose and detect each sleep breathing detection data in the sleep breathing detection data set through the obstructive sleep breathing diagnosis system to generate sleep breathing diagnosis detection results, thereby obtaining a sleep breathing diagnosis detection result set. The obstructive sleep breathing diagnosis system can be a diagnosis system pre-constructed for intelligent diagnosis of sleep breathing detection data, and can include online expert diagnosis function and neural network model diagnosis function. The online expert diagnosis function can refer to the function of online doctors diagnosing and analyzing uploaded sleep breathing diagnosis detection results. The neural network model diagnosis function can refer to the function of diagnosing and analyzing sleep breathing detection data through a pre-trained sleep breathing detection data pathology recognition model. For example, the pre-trained sleep breathing detection data pathology recognition model can be a sleep apnea detection algorithm model based on CNN and LSTM, and can also be a sleep multi-modal representation learning model based on electroencephalogram, electrocardiogram and respiratory signal.

[0048] In practice, the execution subject can diagnose and detect each sleep breathing detection data in the sleep breathing detection data set through the following steps:

[0049] Firstly, the sleep breathing detection data is sent to the obstructive sleep breathing diagnosis system for parameter interval detection. For example, after receiving the sleep breathing detection data, the obstructive sleep breathing diagnosis system can determine whether each parameter data in the sleep breathing detection data is within the corresponding parameter interval.

[0050] Secondly, the sleep breathing detection data is diagnosed and detected through a pre-trained sleep breathing pathology recognition model to generate sleep breathing pathology recognition results. The sleep breathing pathology recognition model includes a sleep breathing pathology recognition network set. The sleep breathing pathology recognition model can be a pre-trained neural network model taking sleep breathing detection data as input and taking sleep breathing pathology recognition results as output. For example, the sleep breathing pathology recognition model can be a sleep apnea detection algorithm model based on CNN and LSTM, and can also be a sleep multi-modal representation learning model based on electroencephalogram, electrocardiogram and respiratory signal. One sleep breathing pathology recognition network corresponds to one sleep breathing detection type. The sleep breathing detection type can be divided by gender, age or decibel of snoring during sleep breathing. The sleep breathing pathology recognition network can refer to the sleep breathing pathology recognition model of a certain sleep breathing detection type.

[0051] The second step can include the following sub-steps:

[0052] In the first sub-step, the sleep respiration detection data is input into each sleep respiration pathology recognition network in the sleep respiration pathology recognition network set to generate a set of network output information corresponding to the sleep respiration detection data. Each network output information includes a set of network recognition results and a set of network prediction confidence levels. Each network recognition result in the set of network recognition results can be at least one. Each network prediction confidence level in the set of network prediction confidence levels can be at least one. The network recognition result can be the output of the sleep respiration pathology recognition network. For example, the network recognition result can be "the sleep respiration detection data indicates that user A has XX disease". One set of network recognition results corresponds to one sleep respiration pathology recognition network. One network recognition result corresponds to one network prediction confidence level. The network prediction confidence level can represent the accuracy of the network recognition result. The higher the network prediction confidence level, the more accurate the corresponding generated network recognition result. For example, the sleep respiration detection data can be directly input into each sleep respiration pathology recognition network in the sleep respiration pathology recognition network set to obtain the set of network output information.

[0053] In the second sub-step, according to the obtained set of network prediction confidence levels, the network recognition results in the set of network recognition results are fused to generate a set of fused recognition results and a corresponding set of fused network prediction confidence levels. One fused recognition result corresponds to one fused network prediction confidence level.

[0054] First, in response to determining that there is a result relationship between at least two network recognition results, at least one target network recognition result set is determined from the set of network recognition results. Each network recognition result in the target network recognition result set has a containing relationship. The containing relationship represents that the network recognition results have a range containing relationship between the result embodiment ranges. The result embodiment range can be the semantic coverage range that the recognition result can embody. For example, the A network recognition result is "the sleep respiration detection data indicates that user A has XX disease or YY disease"; the B network recognition result is "the sleep respiration detection data indicates that user A has XX disease"; then A and B have a containing relationship.

[0055] Secondly, for each target network recognition result set in the at least one target network recognition result set, the following processing steps are performed:

[0056] 1. The target network recognition results in the target network recognition result set are fused to obtain a fused recognition result. First, the execution subject can determine the recognition result semantics corresponding to each target network recognition result in the target network recognition result set to obtain a set of predicted result semantics. Then, the set of predicted result semantics is input into a text generation model to generate a fused recognition result. In practice, the text generation model can be a Transformer model.

[0057] 2. Confidence fusion is performed on each network prediction confidence in a target network prediction confidence group to generate an initial fusion network prediction confidence. The target network prediction confidence group corresponds to the target network identification result group. Each network prediction confidence can be weighted and summed to generate the initial fusion network prediction confidence.

[0058] Next, a fusion network prediction confidence set is generated according to the obtained at least one initial fusion network prediction confidence. The at least one initial fusion network prediction confidence can be determined as the fusion network prediction confidence set.

[0059] Then, the obtained at least one fusion identification result is determined as the fusion identification result set.

[0060] Finally, in a third sub-step, a sleep respiratory pathology identification result is generated according to the fusion network prediction confidence set. The sleep respiratory pathology identification result is the fusion identification result in the fusion identification result set. The fusion identification result corresponding to the fusion network prediction confidence in the front pre-set number can be selected from the fusion identification result set as the actual prediction result to obtain at least one fusion identification result. The at least one fusion identification result is combined as the sleep respiratory pathology identification result.

[0061] In a third step, in response to receiving the sleep respiratory data detection result sent by the obstructive sleep respiratory diagnosis system, the sleep respiratory data detection result and the sleep respiratory pathology identification result are combined as a sleep respiratory diagnosis detection result.

[0062] The sleep respiratory pathology identification model can be trained by the following steps:

[0063] In a first step, a set of sleep respiratory detection data sample groups is obtained. Each sleep respiratory detection data sample group corresponds to a sleep respiratory detection type.

[0064] In a second step, an initial sleep respiratory pathology identification model is determined. The initial sleep respiratory pathology identification model includes an initial sleep respiratory pathology identification network group, and each initial sleep respiratory pathology identification network corresponds to a sleep respiratory detection type.

[0065] In a third step, for each sleep respiratory detection data sample group in the set of sleep respiratory detection data sample groups, the following training steps are performed:

[0066] 1. Determine the initial sleep respiratory pathology identification network corresponding to the sleep respiratory detection data sample group.

[0067] 2. input at least one sleep respiration detection data sample in the sleep respiration detection data sample set into the initial sleep respiration pathology identification network to obtain an initial sleep respiration pathology identification result corresponding to the at least one sleep respiration detection data sample.

[0068] 3. determine whether the initial sleep respiration pathology identification network reaches a preset optimization target according to the initial sleep respiration pathology identification result corresponding to the at least one sample and the sample label corresponding to the at least one sleep respiration detection data sample.

[0069] 4. in response to determining that the initial sleep respiration pathology identification network reaches the preset optimization target, determine the initial sleep respiration pathology identification network as the trained sleep respiration pathology identification network.

[0070] 4. in response to determining that the initial sleep respiration pathology identification network reaches the preset optimization target, determine the initial sleep respiration pathology identification network as the trained sleep respiration pathology identification network.

[0071] Thus, through the sleep respiration pathology identification network set, the sleep respiration detection data can be analyzed from multiple angles. On this basis, by realizing the fusion of the identification result and the fusion of the prediction confidence, the output content can be unified to facilitate the subsequent accurate generation of the sleep respiration pathology identification result.

[0072] Step 107, send the sleep respiration diagnosis detection result set to the doctor terminal.

[0073] In some embodiments, the execution subject can send the sleep respiration diagnosis detection result set to the doctor terminal. For example, the sleep respiration diagnosis detection result set can be sent to the terminal of the doctor of sleep respiration diagnosis through wired connection or wireless connection.

[0074] Further reference Figure 2 , as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of obstructive sleep respiration pathology information processing devices, which correspond to the method embodiments shown in Figure 1 , the obstructive sleep respiration pathology information processing device can be applied to various electronic devices.

[0075] As Figure 2As shown, the obstructive sleep apnea pathological information processing apparatus 200 of some embodiments includes an acquisition unit 201, a first determination unit 202, a second determination unit 203, an adjustment unit 204, a reading unit 205, a detection unit 206, and a sending unit 207. The acquisition unit 201 is configured to, in response to receiving an obstructive sleep apnea detection task, acquire execution resource allocation information corresponding to the obstructive sleep apnea detection task. The first determination unit 202 is configured to determine a sleep detector group corresponding to the obstructive sleep apnea detection task, wherein the sleep detector group is each sleep detector in the sleep detector cluster indicated by the obstructive sleep apnea detection task that needs to perform the task. The second determination unit 203 is configured to, in response to determining that the execution resource allocation information represents execution resource adjustment through first resource allocation information, determine a first resource adjustment time period corresponding to the first resource allocation information. The adjustment unit 204 is configured to, in response to the current time being within the first resource adjustment time period, perform resource adjustment on the sleep detector group according to the first resource allocation information, and control the sleep detector group to perform the obstructive sleep apnea detection task. The reading unit 205 is configured to, in response to detecting that the obstructive sleep apnea detection task is completed, read a sleep respiration detection data group from the sleep detector group, wherein the sleep respiration detection data in the sleep respiration detection data group corresponds to the sleep detector in the sleep detector group. The detection unit 206 is configured to, through the obstructive sleep apnea diagnosis system, perform diagnosis detection on each sleep respiration detection data in the sleep respiration detection data group to generate sleep respiration diagnosis detection results, obtaining a sleep respiration diagnosis detection result group. The sending unit 207 is configured to send the sleep respiration diagnosis detection result group to the doctor terminal.

[0076] It can be understood that the units described in the obstructive sleep apnea pathological information processing apparatus 200 correspond to the respective steps in the method described above. Figure 1 The operations, features, and advantages described above for the method also apply to the obstructive sleep apnea pathological information processing apparatus 200 and the units contained therein, and are not repeated here.

[0077] Reference is made below to Figure 3 which shows a structural schematic diagram of an electronic device 300 (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. The electronic device in some embodiments of the present disclosure can include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet PC), a PMP (Portable Multimedia Player), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. Figure 3The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0078] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0079] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0080] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 309, or installed from a storage device 308, or installed from a ROM 302. When the computer program is executed by the processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0081] Note that the computer readable medium in some embodiments of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus or device. In some embodiments of the present disclosure, the computer readable signal medium can include a data signal propagated in baseband or propagated as a carrier wave in a propagated data signal, in which the computer readable program code is contained. Such propagated data signal can take a variety of forms, including but not limited to electro-magnetic, optical or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport program for use by or in connection with an instruction execution system, apparatus or device. Program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to wire, cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

[0082] In some embodiments, the client, server, or both can communicate using any current known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any current known or future developed networks.

[0083] The computer readable medium can be included in the electronic device, or can exist separately from the electronic device. The computer readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to receiving the obstructive sleep breathing detection task, acquire execution resource allocation information corresponding to the obstructive sleep breathing detection task; determine a sleep detector group corresponding to the obstructive sleep breathing detection task, wherein the sleep detector group is each sleep detector in the sleep detector cluster that needs to execute the task indicated by the obstructive sleep breathing detection task; in response to determining that the execution resource allocation information represents execution resource adjustment through first resource allocation information, determine a first resource adjustment time period corresponding to the first resource allocation information; in response to the current time being within the first resource adjustment time period, perform resource adjustment on the sleep detector group according to the first resource allocation information, and control the sleep detector group to execute the obstructive sleep breathing detection task; in response to detecting that the obstructive sleep breathing detection task is executed, read a sleep breathing detection data group from the sleep detector group, wherein the sleep breathing detection data in the sleep breathing detection data group corresponds to the sleep detector in the sleep detector group; perform diagnostic detection on each sleep breathing detection data in the sleep breathing detection data group through the obstructive sleep breathing diagnostic system to generate a sleep breathing diagnostic detection result, to obtain a sleep breathing diagnostic detection result group; and send the sleep breathing diagnostic detection result group to the doctor terminal.

[0084] Computer program code for carrying out operations of some embodiments of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0085] The flow and block diagrams in the drawings represent possible architectural, functional, and operational scenarios of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block can represent a module, a segment, or a portion of code that comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or combinations of hardware and software.

[0086] The units described in some embodiments of the present disclosure can be implemented by means of software, or can be implemented by hardware. The described units can also be arranged in a processor, for example, can be described as: a processor comprising an acquisition unit, a first determination unit, a second determination unit, an adjustment unit, a reading unit, a detection unit and a sending unit. Among them, the names of these units do not constitute a limitation to the units themselves in some cases, for example, the sending unit can also be described as "a unit for sending the sleep breathing diagnosis detection result set to the doctor terminal".

[0087] The functions described above in the specification can be performed at least in part by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), etc.

[0088] The above description is merely some of the preferred embodiments of the present disclosure and a description of the principles of the technology used. Those skilled in the art should understand that the scope of the application involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or equivalent features without departing from the above inventive concept. For example, the above features are replaced with the technical features disclosed in the embodiments of the present disclosure (but not limited to) having similar functions to form technical solutions.

Claims

1. A method for processing pathological information of obstructive sleep apnea, applied to an integrated obstructive sleep apnea diagnostic instrument, wherein the integrated obstructive sleep apnea diagnostic instrument comprises: A cluster of sleep monitoring devices, with one sleep monitoring device corresponding to one patient user, allowing patients to undergo obstructive sleep apnea diagnosis at home; the obstructive sleep apnea diagnostic system and the doctor's terminal, including: In response to receiving an obstructive sleep apnea detection task, obtain the execution resource allocation information corresponding to the obstructive sleep apnea detection task; Determine the sleep monitoring device group corresponding to the obstructive sleep apnea detection task, wherein the sleep monitoring device group is each sleep monitoring device in the sleep monitoring device cluster indicated by the obstructive sleep apnea detection task that needs to perform the task; In response to determining that the execution resource allocation information represents the execution resource adjustment through the first resource allocation information, a first resource adjustment time period corresponding to the first resource allocation information is determined; In response to the fact that the current time is within the first resource adjustment period, resource adjustment is performed on the sleep monitoring device group according to the first resource allocation information, and the sleep monitoring device group is controlled to perform the obstructive sleep apnea detection task; In response to the detection that the obstructive sleep apnea detection task has been completed, a sleep apnea detection data set is read from the sleep monitoring device set, wherein the sleep apnea detection data in the sleep apnea detection data set corresponds to the sleep monitoring device in the sleep monitoring device set; The obstructive sleep apnea diagnostic system is used to perform diagnostic tests on each sleep apnea test data in the sleep apnea test data set to generate sleep apnea diagnostic test results, thus obtaining a sleep apnea diagnostic test result set. The sleep breathing diagnostic test results are sent to the doctor's terminal. In response to determining that the execution resource allocation information represents the execution resource adjustment through the second resource allocation information, the resource change information corresponding to the obstructive sleep apnea detection task is determined; Based on the resource change information, resource adjustments are performed on the sleep monitoring device group; In response to determining that the execution resource allocation information represents the execution of resource adjustments based on the first resource allocation information and the second resource allocation information, a second resource adjustment time period corresponding to the first resource allocation information is determined, and the execution resource allocation information represents that the first resource allocation information and the second resource allocation information are executed simultaneously. In response to the fact that the current time falls within the second resource adjustment period, determine the current execution resource allocation information; Based on the current execution resource allocation information, the resources of the sleep monitoring device group are adjusted. The step of performing diagnostic tests on each sleep breathing test data in the sleep breathing test data set using the obstructive sleep breathing diagnostic system to generate sleep breathing diagnostic test results includes: The sleep breathing test data is sent to the obstructive sleep apnea diagnostic system for parameter range detection, wherein it is determined whether each parameter in the sleep breathing test data is within its corresponding parameter range. Obtain a set of sleep breathing test data samples, where one set of sleep breathing test data samples corresponds to one type of sleep breathing test; An initial sleep apnea pathology identification model is determined, wherein the initial sleep apnea pathology identification model includes an initial sleep apnea pathology identification network group, and one initial sleep apnea pathology identification network corresponds to one sleep apnea detection type; For each sleep apnea test data set in the sleep apnea test data set set, perform the following training steps: Determine the initial sleep apnea pathology identification network corresponding to the sleep apnea test data sample group; Input at least one sleep breathing test data sample from the sleep breathing test data sample group into the initial sleep breathing pathology identification network to obtain the initial sleep breathing pathology identification result corresponding to the at least one sleep breathing test data sample; Based on the initial sleep apnea pathology identification results corresponding to at least one sample and the sample labels corresponding to at least one sleep apnea detection data sample, determine whether the initial sleep apnea pathology identification network has achieved the preset optimization target. In response to the determination that the initial sleep apnea identification network has reached the preset optimization target, the initial sleep apnea identification network is determined as the trained sleep apnea identification network. The trained sleep apnea identification networks are merged into a sleep apnea identification model. The sleep breathing detection data is used to perform diagnostic detection through a pre-trained sleep breathing pathology recognition model to generate sleep breathing pathology recognition results. The sleep breathing pathology recognition model includes a sleep breathing pathology recognition network group. In response to receiving the sleep breathing data detection result sent by the obstructive sleep breathing diagnostic system, the sleep breathing data detection result and the sleep breathing pathology identification result are merged into a sleep breathing diagnostic detection result; The step of using a pre-trained sleep apnea pathology recognition model to diagnose and detect the sleep apnea test data to generate sleep apnea pathology recognition results includes: Using the aforementioned sleep apnea pathology identification network group, a set of identification network output information corresponding to the sleep apnea detection data is generated, wherein each identification network output information includes: a network identification result group and a network prediction confidence group; Based on the obtained set of network prediction confidence scores, the recognition results of each network in the set of network recognition results are fused to generate a fused recognition result set and a corresponding fused network prediction confidence score set. Based on the fusion network prediction confidence set, a sleep apnea pathology identification result is generated, wherein the sleep apnea pathology identification result is a fusion identification result in the fusion identification result set, including: selecting from the fusion identification result set the fusion network prediction confidence of the top preset number of fusion identification results as actual prediction results, obtaining at least one fusion identification result, and merging at least one fusion identification result into a sleep apnea pathology identification result; The step of determining the current execution resource allocation information includes: Determining the communication resource change value corresponding to the obstructive sleep apnea detection task includes: determining the maximum amount of communication resources used for the obstructive sleep apnea detection task as the maximum communication resource amount; determining the minimum amount of communication resources used for the obstructive sleep apnea detection task as the minimum communication resource amount; and determining the ratio of the maximum communication resource amount to the minimum communication resource amount as the communication resource change value. In response to determining that the change value of the communication resource is greater than a preset value, the second resource allocation information is determined as the currently executed resource allocation information; In response to determining that the change value of the communication resource is less than or equal to the preset value, the first resource allocation information is determined as the currently executed resource allocation information; The step of fusing the identification results of each network identification result in the network identification result set to generate a fused identification result set and a corresponding fused network prediction confidence set, based on the obtained network prediction confidence set, includes: In response to determining that there is an inclusion relationship between at least two network identification results, at least one target network identification result group is determined from the set of network identification result groups, wherein there is an inclusion relationship between the network identification results in the target network identification result group; For each target network identification result group in the at least one target network identification result group, the following processing steps are performed: The target network identification results in the target network identification result group are fused to obtain the fused identification result. The confidence scores of each network prediction in the target network prediction confidence score group are fused to generate an initial fused network prediction confidence score. The target network prediction confidence score group is a network prediction confidence score group corresponding to the target network identification result group. The confidence scores of each network prediction are weighted and summed to generate the initial fused network prediction confidence score. Generate a set of fusion network prediction confidence scores based on at least one initial fusion network prediction confidence score obtained; At least one of the obtained fusion recognition results is determined as the fusion recognition result set.

2. An obstructive sleep apnea pathology information processing device applied to the method of claim 1, applied to an obstructive sleep apnea diagnostic all-in-one machine, the obstructive sleep apnea diagnostic all-in-one machine comprising: A cluster of sleep monitoring devices, with one sleep monitoring device corresponding to one patient user, allowing patients to undergo obstructive sleep apnea diagnosis at home; the obstructive sleep apnea diagnostic system and the doctor's terminal, including: The acquisition unit is configured to acquire the execution resource allocation information corresponding to the obstructive sleep apnea detection task in response to receiving the obstructive sleep apnea detection task. The first determining unit is configured to determine the sleep monitoring device group corresponding to the obstructive sleep apnea detection task, wherein the sleep monitoring device group is each sleep monitoring device in the sleep monitoring device cluster indicated by the obstructive sleep apnea detection task that needs to perform the task. The second determining unit is configured to determine a first resource adjustment time period corresponding to the first resource allocation information in response to determining that the execution resource allocation information represents the execution resource adjustment through the first resource allocation information; The adjustment unit is configured to, in response to the current time being within the first resource adjustment period, perform resource adjustment on the sleep monitoring device group according to the first resource allocation information, and control the sleep monitoring device group to perform the obstructive sleep apnea detection task; The reading unit is configured to read a sleep breathing detection data set from the sleep monitoring device group in response to detecting that the obstructive sleep breathing detection task has been completed, wherein the sleep breathing detection data in the sleep breathing detection data set corresponds to the sleep monitoring device in the sleep monitoring device group; The detection unit is configured to perform diagnostic tests on each sleep breathing test data in the sleep breathing test data set through the obstructive sleep breathing diagnostic system to generate sleep breathing diagnostic test results and obtain a sleep breathing diagnostic test result set. The sending unit is configured to send the sleep breathing diagnostic test result set to the doctor's terminal; Specifically, in response to determining that the execution resource allocation information represents the execution resource adjustment through the second resource allocation information, the resource change information corresponding to the obstructive sleep apnea detection task is determined; Based on the resource change information, resource adjustments are performed on the sleep monitoring device group; In response to determining that the execution resource allocation information represents the execution of resource adjustments based on the first resource allocation information and the second resource allocation information, a second resource adjustment time period corresponding to the first resource allocation information is determined, and the execution resource allocation information represents that the first resource allocation information and the second resource allocation information are executed simultaneously. In response to the fact that the current time falls within the second resource adjustment period, determine the current execution resource allocation information; Based on the current execution resource allocation information, the resources of the sleep monitoring device group are adjusted. The step of performing diagnostic tests on each sleep breathing test data in the sleep breathing test data set using the obstructive sleep breathing diagnostic system to generate sleep breathing diagnostic test results includes: The sleep breathing test data is sent to the obstructive sleep apnea diagnostic system for parameter range detection, wherein it is determined whether each parameter in the sleep breathing test data is within its corresponding parameter range. Obtain a set of sleep breathing test data samples, where one set of sleep breathing test data samples corresponds to one type of sleep breathing test; An initial sleep apnea pathology identification model is determined, wherein the initial sleep apnea pathology identification model includes an initial sleep apnea pathology identification network group, and one initial sleep apnea pathology identification network corresponds to one sleep apnea detection type; For each sleep apnea test data set in the sleep apnea test data set set, perform the following training steps: Determine the initial sleep apnea pathology identification network corresponding to the sleep apnea test data sample group; Input at least one sleep breathing test data sample from the sleep breathing test data sample group into the initial sleep breathing pathology identification network to obtain the initial sleep breathing pathology identification result corresponding to the at least one sleep breathing test data sample; Based on the initial sleep apnea pathology identification results corresponding to at least one sample and the sample labels corresponding to at least one sleep apnea detection data sample, determine whether the initial sleep apnea pathology identification network has achieved the preset optimization target. In response to the determination that the initial sleep apnea identification network has reached the preset optimization target, the initial sleep apnea identification network is determined as the trained sleep apnea identification network. The trained sleep apnea identification networks are merged into a sleep apnea identification model. The sleep breathing detection data is used to perform diagnostic detection through a pre-trained sleep breathing pathology recognition model to generate sleep breathing pathology recognition results. The sleep breathing pathology recognition model includes a sleep breathing pathology recognition network group. In response to receiving the sleep breathing data detection result sent by the obstructive sleep breathing diagnostic system, the sleep breathing data detection result and the sleep breathing pathology identification result are merged into a sleep breathing diagnostic detection result; The step of using a pre-trained sleep apnea pathology recognition model to diagnose and detect the sleep apnea test data to generate sleep apnea pathology recognition results includes: Using the aforementioned sleep apnea pathology identification network group, a set of identification network output information corresponding to the sleep apnea detection data is generated, wherein each identification network output information includes: a network identification result group and a network prediction confidence group; Based on the obtained set of network prediction confidence scores, the recognition results of each network in the set of network recognition results are fused to generate a fused recognition result set and a corresponding fused network prediction confidence score set. Based on the fusion network prediction confidence set, a sleep apnea pathology identification result is generated, wherein the sleep apnea pathology identification result is a fusion identification result in the fusion identification result set, including: selecting from the fusion identification result set the fusion network prediction confidence of the top preset number of fusion identification results as actual prediction results, obtaining at least one fusion identification result, and merging at least one fusion identification result into a sleep apnea pathology identification result; The step of determining the current execution resource allocation information includes: Determining the communication resource change value corresponding to the obstructive sleep apnea detection task includes: determining the maximum amount of communication resources used for the obstructive sleep apnea detection task as the maximum communication resource amount; determining the minimum amount of communication resources used for the obstructive sleep apnea detection task as the minimum communication resource amount; and determining the ratio of the maximum communication resource amount to the minimum communication resource amount as the communication resource change value. In response to determining that the change value of the communication resource is greater than a preset value, the second resource allocation information is determined as the currently executed resource allocation information; In response to determining that the change value of the communication resource is less than or equal to the preset value, the first resource allocation information is determined as the currently executed resource allocation information; The step of fusing the identification results of each network identification result in the network identification result set to generate a fused identification result set and a corresponding fused network prediction confidence set, based on the obtained network prediction confidence set, includes: In response to determining that there is an inclusion relationship between at least two network identification results, at least one target network identification result group is determined from the set of network identification result groups, wherein there is an inclusion relationship between the network identification results in the target network identification result group; For each target network identification result group in the at least one target network identification result group, the following processing steps are performed: The target network identification results in the target network identification result group are fused to obtain the fused identification result. The confidence scores of each network prediction in the target network prediction confidence score group are fused to generate an initial fused network prediction confidence score. The target network prediction confidence score group is a network prediction confidence score group corresponding to the target network identification result group. The confidence scores of each network prediction are weighted and summed to generate the initial fused network prediction confidence score. Generate a set of fusion network prediction confidence scores based on at least one initial fusion network prediction confidence score obtained; At least one of the obtained fusion recognition results is determined as the fusion recognition result set.

3. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in claim 1.

4. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in claim 1.

Images