Sleeping position change reminder method, device, medium and electronic equipment

Abstract

The present application provides a method, device, medium and electronic device for reminding a change in lying position, which relates to the field of medical information processing, including: in response to detecting that a target to be reminded begins to execute a target item, obtaining a set of vital sign data lists ZS and a list of body state types ZT at intervals of a preset time length; obtaining a predicted body state type sequence within a target time window based on the set of vital sign data lists ZS, the list of body state types ZT and the HMM model; if the number of predicted body state types contained in Y that are target hidden state types is equal to or greater than a first preset number threshold, a lying position change reminder is issued at the current time. The present application improves the accuracy of lying position change reminders, and at the same time, when a certain physical indicator of the user suddenly increases and requires a lying position change, unnecessary damage to the user's body is caused because the user himself is not aware of it. And there is no need for manual timed reminders, which saves manpower.

Description

Technical Field

[0001] The present application relates to the field of medical information processing, and in particular to a method, device, medium and electronic device for reminding a lying position change. Background Art

[0002] In the medical field, prone oxygenation has been shown to be effective for some patients requiring oxygen. However, its practical application presents numerous challenges. Many patients experience physical discomfort after remaining in the prone position for a period of time, such as significant changes in vital signs, such as a rapid rise in blood pressure. This negatively impacts the patient's health and can exacerbate their risk of illness. Currently, turning patients every two hours is a common approach to alleviate the discomfort associated with prolonged prone positioning. However, this approach has significant drawbacks. It requires constant monitoring by medical staff during the turning process. Limited human resources and the complexity of practical care scenarios make it difficult to promptly detect and address patient distress. This not only increases the workload of medical staff but can also lead to greater health risks for patients if untimely intervention is not promptly addressed. Therefore, a technical solution that can effectively address these issues is urgently needed to improve the quality and safety of care for patients requiring prone oxygenation, reduce workload for medical staff, and mitigate risks for patients. Summary of the Invention

[0003] In response to the above technical problems, the present application provides a lying position change reminder method, device, medium and electronic equipment, which at least partially solve the problems existing in the prior art.

[0004] In a first aspect of the present application, a method for reminding a lying position change is provided, the method comprising:

[0005] S100, in response to detecting that the target to be reminded starts to perform the target event, every time a preset time length is passed, a physical sign data list set ZS and a physical condition type list ZT are obtained; wherein ZS=(ZS1, ZS2, ..., ZS i ,...,ZS n ); i = 1, 2, ..., n; n is the number of acquisition time points from the preset time length to the current time; the time interval between any two adjacent acquisition time points is the same; ZS i is a list of vital sign data of the target to be reminded collected from the preset time length to the i-th collection time point in the current time; ZS i =(ZS i，1 , ZS i，2 ,...,ZS i，j ,...,ZS i，m ); j = 1, 2, ..., m; m is the number of vital sign data corresponding to the target to be reminded; ZSi，j is the jth physical feature data of the target to be reminded collected at the i-th collection time point before the preset time length to the current time; ZT=(ZT1, ZT2, ..., ZT i ,...,ZT n );ZT i The physical state type corresponding to the i-th collection time point of the target to be reminded from the preset time length to the current time; the lying position corresponding to the target to be reminded when executing the target item is the target lying position;

[0006] S200, according to the physical sign data list set ZS, the physical state type list ZT and the HMM model, obtain the predicted physical state type sequence Y=(Y1, Y2, ..., Y x ,...,Y y ); x = 1, 2, ..., y; where y is the number of predicted body state types obtained within the target time window; Y x is the predicted physical state type of the target to be reminded corresponding to the xth target time point in the target time window; the time interval between any two adjacent target time points is the same; the start time of the target time window is the current time; where ZS is the observation sequence of the HMM model; ZT is the hidden sequence of the HMM model;

[0007] S300: If the number of predicted body state types included in Y that are target hidden state types is equal to or greater than a first preset number threshold, a lying position change reminder is issued at the current time.

[0008] In a second aspect of the present application, a lying position change reminder device is provided, the device comprising:

[0009] The list acquisition unit is configured to acquire a physical sign data list set ZS and a physical condition type list ZT once every preset time interval in response to detecting that the target to be reminded starts to execute the target item; wherein ZS=(ZS1, ZS2, ..., ZS i ,...,ZS n ); i = 1, 2, ..., n; n is the number of acquisition time points from the preset time length to the current time; the time interval between any two adjacent acquisition time points is the same; ZS i is a list of vital sign data of the target to be reminded collected from the preset time length to the i-th collection time point in the current time; ZS i =(ZS i，1 , ZS i，2 ,...,ZS i，j ,...,ZS i，m ); j = 1, 2, ..., m; m is the number of vital sign data corresponding to the target to be reminded; ZS i，jis the jth physical feature data of the target to be reminded collected at the i-th collection time point before the preset time length to the current time; ZT=(ZT1, ZT2, ..., ZT i ,...,ZT n );ZT i The physical state type corresponding to the i-th collection time point of the target to be reminded from the preset time length to the current time; the lying position corresponding to the target to be reminded when executing the target item is the target lying position;

[0010] The prediction unit is used to obtain the predicted body state type sequence Y=(Y1, Y2, ..., Y x ,...,Y y ); x = 1, 2, ..., y; where y is the number of predicted body state types obtained within the target time window; Y x is the predicted physical state type of the target to be reminded corresponding to the xth target time point in the target time window; the time interval between any two adjacent target time points is the same; the start time of the target time window is the current time; where ZS is the observation sequence of the HMM model; ZT is the hidden sequence of the HMM model;

[0011] The conversion unit is configured to issue a lying position conversion reminder at the current time if the number of predicted body state types included in Y that are target hidden state types is equal to or greater than a first preset number threshold.

[0012] In the third aspect of the present application, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the aforementioned lying position change reminder method.

[0013] In a fourth aspect of the present application, an electronic device is provided, comprising a processor and the above-mentioned non-transitory computer-readable storage medium.

[0014] This application has at least the following beneficial effects:

[0015] The present application provides a method for reminding patients of a change in supine position. When a patient receiving oxygen is in the prone position for an extended period, various physical signs may change significantly, leading to discomfort. To ensure timely reminders, the present application first acquires the patient's supine position-related physical signs at intervals of a preset length, starting with the patient receiving oxygen in the prone position. Based on the changes in these physical signs at different moments, the patient's physical condition is determined. The corresponding physical state type at each acquisition time point is also acquired. State types include stable and abnormal. Stable indicates that the patient receiving oxygen in the prone position is currently in good condition and does not need to be turned over; conversely, abnormal indicates that the patient receiving oxygen in the prone position is currently in poor condition and requires turning over. Furthermore, the physical sign data list ZS serves as the observed sequence of an HMM model, and the physical state type list ZT serves as the hidden sequence of the HMM model. Using the known physical sign data and the physical state types corresponding to the physical sign data collected at different times, the HMM model is used to perform backward predictions, predicting the hidden state sequence after the current time, i.e., the predicted physical state type sequence. However, since the training set used by the pre-trained HMM model in this embodiment is a set of several sets of vital sign data lists and body state type lists collected before the user inhaled oxygen, the training samples are relatively small, and the accuracy of the single predicted state obtained by the pre-trained HMM model may be low. Therefore, in this application, if the number of predicted body state types contained in Y that are target hidden state types is equal to or greater than the first preset number threshold, it means that the HMM model predicts that the body state type is abnormal a large number of times in the future. When it is equal to or greater than the first preset number threshold, then within the target time window, the patient is very likely to feel unwell, or the corresponding vital sign data indicates that the patient's condition is not good and needs to be turned over to relieve it. Therefore, a supine position change reminder is issued at the current time. This application improves the accuracy of supine position change reminders. At the same time, when a certain physical indicator of the user suddenly increases and requires supine position change, unnecessary damage to the user's body is caused because the user himself is not aware of it. And there is no need for manual timed reminders, saving manpower. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A flow chart of the lying position change reminder method provided in an embodiment of the present application;

[0018] Figure 2 This is a structural block diagram of the lying position change reminder device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0021] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this apparatus and / or practice this method.

[0022] Please refer to Figure 1 As shown, an embodiment of the present application provides a lying position change reminder method, the method comprising:

[0023] Step S100: In response to detecting that the target to be reminded starts to perform the target event, a physical sign data list set ZS and a physical condition type list ZT are obtained every preset time interval; wherein ZS=(ZS1, ZS2, ..., ZS i ,...,ZS n ); i = 1, 2, ..., n; n is the number of acquisition time points from the preset time length to the current time; the time interval between any two adjacent acquisition time points is the same; ZSi is a list of vital sign data of the target to be reminded collected from the preset time length to the i-th collection time point in the current time; ZS i =(ZS i，1 , ZS i，2 ,...,ZS i，j ,...,ZS i，m ); j = 1, 2, ..., m; m is the number of vital sign data corresponding to the target to be reminded; ZS i，j is the jth physical feature data of the target to be reminded collected at the i-th collection time point before the preset time length to the current time; ZT=(ZT1, ZT2, ..., ZT i ,...,ZT n );ZT i The physical state type corresponding to the i-th collection time point of the target to be reminded from the preset time length to the current time; the lying position corresponding to the target to be reminded when executing the target item is the target lying position.

[0024] Specifically, in this embodiment, the target to be reminded may be a patient requiring oxygen inhalation. The target to be reminded begins executing the target action, which means the patient requiring oxygen inhalation begins transitioning to the target supine position for oxygen inhalation. In this embodiment, the target supine position is the prone position. Non-target supine positions may include the supine position, the lateral position, etc. The preset time period may be 10 minutes. The interval between any two adjacent collection time points may be 1 minute. That is, in this embodiment, within ten minutes of the patient requiring oxygen inhalation starting in the prone position, vital sign data of the patient requiring oxygen is collected once every minute. This vital sign data can be collected using fixed medical devices, wearable medical devices, such as wristbands. Vital sign data includes blood pressure, heart rate, respiratory rate, etc. The physical condition type of the patient receiving oxygen in the prone position is also acquired once every minute. The acquisition method may include collecting information input by the patient receiving oxygen in the prone position; the input method may be voice input, etc. In this embodiment, the body state type includes stable and abnormal, wherein stable indicates that the patient who is receiving oxygen in the prone position is in good condition and does not need to turn over; conversely, abnormal indicates that the patient who is receiving oxygen in the prone position is in poor condition and needs to turn over.

[0025] It should be noted that when lying in the prone position for a long time, many aspects of the body's physical signs will change significantly and be uncomfortable. In terms of breathing, the restriction of chest movement leads to a decrease in tidal volume and a compensatory increase in respiratory rate, and the imbalance of pulmonary ventilation / blood flow ratio affects oxygenation; in circulation, venous return is blocked, resulting in abnormal blood pressure, and poor peripheral circulation causes limb swelling and numbness; in the nervous system, nerve compression causes radiating pain in the upper limbs, facial paresthesia, etc., and changes in brain blood supply lead to dizziness and headaches; the digestive system is affected, gastrointestinal motility is blocked, leading to abdominal distension and indigestion, and an increased risk of esophageal reflux; in terms of musculoskeletal system, muscle fatigue and pain, and changes in joint pressure accelerate wear, all of which indicate that lying in the prone position for a long time will bring many adverse effects to the body. Therefore, this application obtains physical signs related to the lying position, and then obtains the physical condition of the patient who is breathing oxygen in the prone position according to the changes in physical signs at different times.

[0026] Step S200: According to the physical sign data list set ZS, the physical state type list ZT and the HMM model, a predicted physical state type sequence Y=(Y1, Y2, ..., Y x ,...,Y y ); x = 1, 2, ..., y; where y is the number of predicted body state types obtained within the target time window; Y x is the predicted physical state type of the target to be reminded corresponding to the x-th target time point in the target time window; the time interval between any two adjacent target time points is the same; the start time of the target time window is the current time; among them, ZS is the observation sequence of the HMM model; ZT is the hidden sequence of the HMM model.

[0027] Specifically, in this embodiment, the vital sign data list set ZS is used as the observation sequence of the HMM model, and the body state type list ZT is used as the hidden sequence of the HMM model. Through the known vital sign data and the body state types corresponding to the vital sign data collected at different times, the HMM model is used to perform backward prediction to predict the hidden state sequence after the current time, that is, to predict the body state type sequence.

[0028] It should be noted that the HMM model in this application is a pre-trained HMM model, and the corresponding training set is a set of several groups of vital sign data lists and body state type lists collected before the user is reminded to inhale oxygen. As an example, one of the training sets is the historical vital sign data list and the corresponding historical body state type list corresponding to the first historical time window as the expected input in the training set; the historical body state type list corresponding to the second historical time window is the expected output in the training set; the time length of the first historical time window is equal to the preset time length; the time length of the second historical time window is equal to the length of the target time window. In this way, the state transition matrix, observation probability matrix and initial state probability vector corresponding to the HMM model are obtained. The end time of the first historical time window is the start time of the second historical time window, and the end time of the second historical time window is before the current oxygen inhalation.

[0029] As an example, the target time window may be 30 minutes, and the time interval between any two adjacent target time points may be 1 minute.

[0030] Step S300: If the number of predicted body state types included in Y that are target hidden state types is equal to or greater than a first preset number threshold, a lying position change reminder is issued at the current time.

[0031] Specifically, since the training set used by the pre-trained HMM model in this embodiment is a set of several groups of vital sign data lists and body state type lists collected before reminding the user to inhale oxygen, the training samples are relatively small, and the accuracy of a single predicted state obtained by the pre-trained HMM model may be relatively low. Therefore, in this embodiment, if the number of predicted body state types contained in Y that are target hidden state types is equal to or greater than the first preset number threshold, it means that in the future, the HMM model predicts that the body state type is abnormal a large number of times. When it is equal to or greater than the first preset number threshold, within the target time window, the patient is very likely to feel unwell, or the corresponding vital sign data indicates that the patient is in poor condition and needs to turn over to relieve it. Therefore, a supine position change reminder is issued at the current time.

[0032] It should be noted that the lying position change reminder can be used to remind patients as well as doctors.

[0033] In this embodiment, when a patient receiving oxygen remains in the prone position for an extended period, various physical signs may change significantly, leading to discomfort. To ensure timely notification, this embodiment first acquires the patient's physical signs related to their prone position at predetermined intervals, starting with the patient receiving oxygen in the prone position. Based on the changes in these physical signs at different moments in time, the patient's physical condition is determined. The corresponding physical state type at each acquisition time point is also acquired. Physical state types include stable and abnormal. Stable indicates that the patient receiving oxygen in the prone position is currently in good condition and does not need to be turned over; conversely, abnormal indicates that the patient receiving oxygen in the prone position is currently in poor condition and requires turning over. Furthermore, the physical sign data list ZS serves as the observed sequence of the HMM model, and the physical state type list ZT serves as the hidden sequence of the HMM model. Using the known physical sign data and the physical state types corresponding to the physical sign data acquired at different times, the HMM model is used to perform backward predictions, predicting the hidden state sequence after the current time point, i.e., the predicted physical state type sequence. However, since the training set used by the pre-trained HMM model in this embodiment is a set of several sets of vital sign data lists and body state type lists collected before the user inhaled oxygen, the training samples are relatively small, and the accuracy of the single predicted state obtained by the pre-trained HMM model may be low. Therefore, in this embodiment, if the number of predicted body state types contained in Y that are target hidden state types is equal to or greater than the first preset number threshold, it means that the HMM model predicts that the body state type is abnormal a large number of times in the future. When it is equal to or greater than the first preset number threshold, then within the target time window, the patient is very likely to feel unwell, or the corresponding vital sign data indicates that the patient's condition is not good and needs to be turned over to relieve it. Therefore, a supine position change reminder is issued at the current time. This embodiment improves the accuracy of supine position change reminders. At the same time, when a certain physical indicator of the user suddenly increases and requires supine position change, unnecessary damage to the user's body is caused because the user himself is not aware of it. And there is no need for manual timed reminders, saving manpower.

[0034] In an exemplary embodiment of the present application, after step S200, the method further includes:

[0035] S400, if the number of continuous predicted body state types contained in Y that are target hidden state types is equal to or greater than a second preset number threshold, then remind the target to be reminded to switch from the target lying position to the non-target lying position at the current time; wherein the second preset number threshold is less than the first preset number threshold.

[0036] In this embodiment, if the number of consecutive predicted body state types contained in Y that are target hidden state types is equal to or greater than the second preset number threshold, it means that the HMM model predicts that the body state type is continuously abnormal within a period of time in the future. In this case, the patient is very likely to feel unwell within the target time window, or the corresponding physical sign data indicates that the patient is in a bad state and needs to turn over to relieve the condition. Therefore, a supine position change reminder is issued at the current time. In this embodiment, the second preset number threshold is less than the first preset number threshold, that is, if the HMM model predicts that the body state type is abnormal for a continuous period of time, the probability of the patient feeling unwell is relatively high. This embodiment improves the accuracy of the supine position change reminder. At the same time, when a certain physical indicator of the user suddenly increases and requires supine position change, unnecessary damage is caused to the user's body because the user himself is not aware of it. And there is no need for manual timed reminders, which saves manpower.

[0037] In an exemplary embodiment of the present application, after step S300, the method further includes:

[0038] S500: If the target to be reminded has not changed its supine position, obtain a key vital sign data list set G = (G1, G2, ..., G i ,...,G n ); where G i is a list of vital sign data of the target to be reminded collected at the i-th collection time point within the key time window; G i =(G i，1 , G i，2 ,...,G i，j ,...,G i，m );G i，j is the jth individual feature data of the target to be reminded collected at the i-th collection time point within the key time window; the end time of the key time window is the time when the target to be reminded is detected to start executing the target item.

[0039] Specifically, if the target to be reminded has not switched to a supine position, that is, if a patient receiving oxygen in the prone position believes they are in good health and do not need to turn over after being reminded by medical staff, then a key vital sign data list set G is obtained. Specifically, the vital sign data of the patient before the target to be reminded began performing the target activity is obtained. The duration of the key time window is equal to the preset time duration.

[0040] S600, according to G and the first classification model, obtain a first predicted lying position conversion time range; the first predicted lying position conversion time range is one of several preset lying position conversion time ranges; each preset lying position conversion time range has a corresponding weight.

[0041] Specifically, based on the vital sign data of a patient who is currently receiving oxygen inhalation in the prone position before the patient begins receiving oxygen inhalation in the prone position and the first classification model, a first predicted lying position transition time range is obtained. Here, the first predicted lying position transition time range represents the predicted time range in which the user needs to transition from the target lying position to the non-target lying position. As an example, the first predicted lying position transition time range may be 0.5-1 hour. Several preset lying position transition time ranges may be 0.5-1 hour, 1-2 hours, 2-3 hours, and so on.

[0042] It should be noted that the specific model selection for the first classification model can be selected by those skilled in the art based on the purpose of the first classification model and is not specifically limited at this time. Furthermore, the first classification model is a pre-trained classification model, and the corresponding training set is a list of several patients requiring prone oxygen inhalation, including corresponding supine position transition times and vital sign data prior to the start of prone oxygen inhalation.

[0043] S700: Obtain a second predicted lying position conversion time range according to the ZS and the second classification model; wherein the longest time length of the second predicted lying position conversion time range is shorter than the shortest time length of the first predicted lying position conversion time range.

[0044] S800: Obtain a target predicted lying position transition time range H based on the weight corresponding to the first predicted lying position transition time range and the second predicted lying position transition time range, where H meets the following conditions:

[0045] H=[h min , h max ];

[0046] Among them, h min is the shortest time length corresponding to H; h max is the maximum time length corresponding to H; h min =e min ×α;h max =e max ×α;e min is the shortest time length corresponding to the second predicted lying position conversion time range E; max is the maximum time length corresponding to the second predicted lying position conversion time range E.

[0047] S900, based on H, issues a lying position change reminder.

[0048] Specifically, in this embodiment, first, based on the first predicted supine position conversion time range corresponding to the patient receiving oxygen inhalation in the prone position obtained by the first classification model, the second predicted supine position conversion time range is adjusted according to the weight corresponding to the first predicted supine position conversion time range to obtain the final target predicted supine position conversion time range H. The lower the upper and lower limits corresponding to the first predicted supine position conversion time range, the higher the corresponding weight. For example, if the first predicted supine position conversion time range can be 0.5-1, the corresponding weight is 1.3; if the first predicted supine position conversion time range can be 1-2, the corresponding weight is 1.1. Here, the first predicted lying position conversion time range is the lying position conversion time range predicted based on the patient's physical sign data when in a non-target lying position, that is, a non-prone position. The larger the corresponding upper and lower limits, that is, the longer the predicted time in the target lying position, then when the reminder is made, the patient's need to turn over when the reminder is made is greater than when the corresponding predicted target lying position time is shorter than when the preset lying position conversion time range is set. Therefore, the lower the upper and lower limits corresponding to the first predicted lying position conversion time range, the greater its impact on the subsequent time of continuing to inhale oxygen in the prone position, and therefore, the greater its corresponding weight. Then, the upper and lower limits of the second predicted lying position conversion time range are adjusted according to the weight, so that the obtained time of continuing to inhale oxygen in the prone position is more in line with the actual physical condition of the user's body.

[0049] In an exemplary embodiment of the present application, after step S500, the method further includes:

[0050] S900, obtain key target data list M=(M1, M2, ..., M g ,...,M h ); g = 1, 2, ..., h; where h is the number of key target data; M g is the g-th target data corresponding to the target to be reminded; the target data is used to describe the basic physiological information of the target to be reminded.

[0051] S1000, obtaining a first predicted lying position conversion time range based on G, M and the third classification model; and jumping to step S800.

[0052] Specifically, in this embodiment, the first predicted lying position conversion time range is obtained based on the key target data list M and the key vital signs data list set. The key target data in this embodiment may include the height, weight, gender, disease type, etc. of the target to be reminded. It is characteristic data that describes the basic physiological information of the reminder target. In this embodiment, a corresponding third classification model is set according to the patient's personalized information, and the key target data list M and the key vital signs data list set are used as input to obtain the first predicted lying position conversion time range. Compared with the previous embodiment, the obtained first predicted lying position conversion time range is more accurate and more targeted.

[0053] In an exemplary embodiment of the present application, after step S300, the method further includes:

[0054] S1100, if the number of predicted body state types included in Y that are target hidden state types is less than a preset number threshold, jump to "obtain a vital sign data list set ZS and a body state type list ZT once every preset time length."

[0055] Specifically, in this embodiment, if the number of predicted body state types in Y that are target hidden state types is less than a preset threshold, this indicates that the HMM model predicts that the body state types will mostly be stable over a period of time after the current time. Therefore, within the target time window, the patient is unlikely to experience discomfort or abnormal indicators, and turning over is not necessary for relief. Therefore, the "obtaining the vital sign data list set ZS and the body state type list ZT every preset time interval" procedure continues to be executed to continue monitoring the target for reminders.

[0056] Please refer to Figure 2 As shown, an embodiment of the present application provides a lying position change reminder device 100, which includes:

[0057] The list acquisition unit 110 is configured to acquire a physical sign data list set ZS and a physical condition type list ZT once every preset time interval in response to detecting that the target to be reminded starts to execute the target item; wherein ZS=(ZS1, ZS2, ..., ZS i ,...,ZS n ); i = 1, 2, ..., n; n is the number of acquisition time points from the preset time length to the current time; the time interval between any two adjacent acquisition time points is the same; ZS i is a list of vital sign data of the target to be reminded collected from the preset time length to the i-th collection time point in the current time; ZS i =(ZS i，1 , ZS i，2 ,...,ZS i，j,...,ZS i，m ); j = 1, 2, ..., m; m is the number of vital sign data corresponding to the target to be reminded; ZS i，j is the jth physical feature data of the target to be reminded collected at the i-th collection time point before the preset time length to the current time; ZT=(ZT1, ZT2, ..., ZT i ,...,ZT n );ZT i The physical state type corresponding to the i-th collection time point of the target to be reminded from the preset time length to the current time; the lying position corresponding to the target to be reminded when executing the target item is the target lying position.

[0058] The prediction unit 120 is used to obtain the predicted body state type sequence Y=(Y1, Y2, ..., Y x ,...,Y y ); x = 1, 2, ..., y; where y is the number of predicted body state types obtained within the target time window; Y x is the predicted physical state type of the target to be reminded corresponding to the x-th target time point in the target time window; the time interval between any two adjacent target time points is the same; the start time of the target time window is the current time; among them, ZS is the observation sequence of the HMM model; ZT is the hidden sequence of the HMM model.

[0059] The conversion unit 130 is configured to issue a lying position conversion reminder at the current time if the number of predicted body state types included in Y that are target hidden state types is equal to or greater than a first preset number threshold.

[0060] An embodiment of the present application further provides a computer program product, which includes program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present application described above in this specification.

[0061] Furthermore, although the steps of the method of the present application are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0062] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0063] In an exemplary embodiment of the present application, an electronic device capable of implementing the above method is also provided.

[0064] Those skilled in the art will appreciate that various aspects of the present application can be implemented as systems, methods, or program products. Therefore, various aspects of the present application can be specifically implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation that combines hardware and software aspects, which may be collectively referred to herein as a "circuit," "module," or "system."

[0065] The electronic device according to this embodiment of the present application is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0066] The electronic device is implemented as a general-purpose computing device. Components of the electronic device may include, but are not limited to, the aforementioned at least one processor, the aforementioned at least one storage, and a bus connecting different system components (including the storage and the processor).

[0067] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps described in the above “Exemplary Method” section of this specification according to various exemplary embodiments of the present application.

[0068] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0069] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0070] The bus may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0071] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may communicate with one or more devices that enable a user to interact with the electronic device, and / or may communicate with any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. As shown, the network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0072] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0073] In exemplary embodiments of the present application, a computer-readable storage medium is also provided, on which is stored a program product capable of implementing the aforementioned methods of this specification. In some possible implementations, various aspects of the present application may also be implemented in the form of a program product, which includes program code. When the program product is executed on a terminal device, the program code is used to cause the terminal device to execute the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present application.

[0074] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0075] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0076] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0077] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0078] Furthermore, the above-mentioned figures are merely illustrative of the processes included in the methods according to exemplary embodiments of the present application and are not intended to be limiting. It is readily understood that the processes illustrated in the above-mentioned figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0079] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0080] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for reminding a person of a change in lying position, characterized in that: The method comprises: S100, in response to detecting that the target to be reminded starts to perform the target item, every time a preset time length is passed, a physical sign data list set ZS and a physical condition type list ZT are obtained; wherein ZS=(ZS1, ZS2, ..., ZS i ,...,ZS n ); i = 1, 2, ..., n; n is the number of acquisition time points from the preset time length to the current time; the time interval between any two adjacent acquisition time points is the same; ZS i is a list of vital sign data of the target to be reminded collected from the preset time length to the i-th collection time point in the current time; ZS i =(ZS i，1 , ZS i，2 ,...,ZS i，j ,...,ZS i，m ); j = 1, 2, ..., m; m is the number of vital sign data corresponding to the target to be reminded; ZS i，j is the jth physical feature data of the target to be reminded collected at the i-th collection time point before the preset time length to the current time; ZT=(ZT1, ZT2, ..., ZT i ,...,ZT n );ZT i The physical state type corresponding to the i-th collection time point of the target to be reminded from the preset time length to the current time; the lying position corresponding to the target to be reminded when executing the target item is the target lying position; S200, according to the physical sign data list set ZS, the physical state type list ZT and the HMM model, obtain the predicted physical state type sequence Y=(Y1, Y2, ..., Y x ,...,Y y ); x = 1, 2, ..., y; where y is the number of predicted body state types obtained within the target time window; Y x is the predicted physical state type of the target to be reminded corresponding to the xth target time point in the target time window; the time interval between any two adjacent target time points is the same; the start time of the target time window is the current time; where ZS is the observation sequence of the HMM model; ZT is the hidden sequence of the HMM model; S300: If the number of predicted body state types included in Y that are target hidden state types is equal to or greater than a first preset number threshold, a lying position change reminder is issued at the current time.

2. The lying position change reminder method according to claim 1, characterized in that: After step S200, the method further includes: S400, if the number of continuous predicted body state types contained in Y that are target hidden state types is equal to or greater than a second preset number threshold, then remind the target to be reminded to switch from the target lying position to the non-target lying position at the current time; wherein the second preset number threshold is less than the first preset number threshold.

3. The lying position change reminder method according to claim 1, characterized in that: After step S300, the method further includes: S500: If the target to be reminded has not changed its supine position, obtain a key vital sign data list set G = (G1, G2, ..., G i ,...,G n ); where G i is a list of vital sign data of the target to be reminded collected at the i-th collection time point within the key time window; G i =(G i，1 , G i，2 ,...,G i，j ,...,G i，m );G i，j is the jth individual feature data of the target to be reminded collected at the i-th collection time point within the key time window; the end time of the key time window is the time when the target to be reminded is detected to start executing the target task; S600: Obtain a first predicted lying position transition time range based on G and the first classification model; the first predicted lying position transition time range is one of a plurality of preset lying position transition time ranges; each preset lying position transition time range has a corresponding weight; S700: Obtain a second predicted lying position transition time range based on the ZS and the second classification model; wherein a maximum time length of the second predicted lying position transition time range is less than a shortest time length of the first predicted lying position transition time range; S800: Obtain a target predicted lying position transition time range H based on the weight corresponding to the first predicted lying position transition time range and the second predicted lying position transition time range, where H meets the following conditions: H=[h min ,h max ]; Among them, h min is the shortest time length corresponding to H; h max is the maximum time length corresponding to H; h min =e min ×α;h max =e max ×α;e min is the shortest time length corresponding to the second predicted lying position conversion time range E; max is the maximum time length corresponding to the second predicted lying position conversion time range E; S900, based on H, issues a lying position change reminder.

4. The lying position change reminder method according to claim 3, characterized in that: After step S500, the method further includes: S900, obtain key target data list M=(M1, M2, ..., M g ,...,M h ); g = 1, 2, ..., h; where h is the number of key target data; M g The g-th target data corresponding to the target to be reminded; the target data is used to describe the basic physiological information of the target to be reminded; S1000, obtaining a first predicted lying position conversion time range based on G, M and the third classification model; and jumping to step S800.

5. The lying position change reminder method according to claim 1, characterized in that: After step S300, the method further includes: S1100: If the number of predicted body state types included in Y that are target hidden state types is less than a preset threshold, jump to "obtaining a vital sign data list set ZS and a body state type list ZT every preset time interval." 6. The lying position change reminder method according to claim 3, characterized in that: The time length of the critical time window is equal to the preset time length.

7. A lying position change reminder device, characterized in that: The device comprises: The list acquisition unit is configured to acquire a physical sign data list set ZS and a physical condition type list ZT once every preset time interval in response to detecting that the target to be reminded starts to execute the target item; wherein ZS=(ZS1, ZS2, ..., ZS i ,...,ZS n ); i = 1, 2, ..., n; n is the number of acquisition time points from the preset time length to the current time; the time interval between any two adjacent acquisition time points is the same; ZS i is a list of vital sign data of the target to be reminded collected from the preset time length to the i-th collection time point in the current time; ZS i =(ZS i，1 , ZS i，2 ,...,ZS i，j ,...,ZS i，m ); j = 1, 2, ..., m; m is the number of vital sign data corresponding to the target to be reminded; ZS i，j is the jth physical feature data of the target to be reminded collected at the i-th collection time point before the preset time length to the current time; ZT=(ZT1, ZT2, ..., ZT i ,...,ZT n );ZT i The physical state type corresponding to the i-th collection time point of the target to be reminded from the preset time length to the current time; the lying position corresponding to the target to be reminded when executing the target item is the target lying position; The prediction unit is used to obtain the predicted body state type sequence Y=(Y1, Y2, ..., Y x ,...,Y y ); x = 1, 2, ..., y; where y is the number of predicted body state types obtained within the target time window; Y x is the predicted physical state type of the target to be reminded corresponding to the xth target time point in the target time window; the time interval between any two adjacent target time points is the same; the start time of the target time window is the current time; where ZS is the observation sequence of the HMM model; ZT is the hidden sequence of the HMM model; The conversion unit is configured to issue a lying position conversion reminder at the current time if the number of predicted body state types included in Y that are target hidden state types is equal to or greater than a first preset number threshold.

8. A non-transitory computer-readable storage medium, characterized in that The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: The device comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 8.

Images