An emergency call method, system and device for user abnormal state
By comprehensively analyzing the patient's physical condition, behavioral abnormalities, and location anomalies, an emergency call for help is generated, solving the problem that elderly people or children cannot contact medical staff in a timely manner when alone in a hospital ward, thus achieving efficient emergency calls for help and accurate judgment of abnormal conditions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TONGJI HOSPITAL ATTACHED TO TONGJI MEDICAL COLLEGE HUAZHONG SCI TECH
- Filing Date
- 2024-11-20
- Publication Date
- 2026-05-15
AI Technical Summary
When elderly people or children are alone in a hospital ward, they may not be able to contact medical staff in time if they suddenly experience an abnormal condition, resulting in delayed treatment. Existing emergency call methods are inefficient.
By acquiring patients' physical detection information, behavioral detection information, and location change information, and using morphological recognition networks and abnormal state analysis networks, abnormal states of patients are identified, and abnormal distress calls are generated and sent to the medical staff's client.
It improves the accuracy and comprehensiveness of analyzing patients' abnormal conditions, enables timely calls for help from medical staff, and enhances the efficiency and accuracy of emergency calls.
Smart Images
Figure CN119625922B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the fields of abnormal state analysis and emergency rescue technology, and in particular to an emergency call method, system and device for users in abnormal states. Background Technology
[0002] Elderly patients or children often experience significant inconvenience in normal activities when alone in hospital wards due to their illnesses, especially when using the toilet, walking, squatting, or experiencing emotional distress. This can lead to sudden emergencies requiring immediate medical attention. However, because patients are alone in wards, they may be unable to contact or assist in contacting medical staff in a timely manner, resulting in delayed treatment and potentially causing death or worsening of their condition. Therefore, improving patient emergency communication methods or assisting patients in contacting medical staff during emergencies is a key focus of current healthcare research.
[0003] Traditional methods to assist patients in contacting medical staff in emergencies involve setting up emergency call buttons on the patient's clothing or portable wristbands to ensure that the patient can contact medical staff in case of an emergency. However, patients may not have time or may lose consciousness in the event of an emergency, making it impossible for them to contact medical staff in case of an emergency, resulting in low efficiency in contacting medical staff when patients experience sudden abnormalities. Summary of the Invention
[0004] The main objective of this invention is to provide an emergency call method, system, and device for users in abnormal states, aiming to solve the problem in the prior art where patients often do not have time or lose consciousness when they suddenly become abnormal, making it impossible for them to contact medical personnel in an emergency, resulting in low efficiency in contacting medical personnel when patients suddenly become abnormal.
[0005] To achieve the above objectives, the present invention provides an emergency distress call method for users in abnormal states, the method comprising:
[0006] The system acquires the patient's physical detection information, the patient's behavioral detection information, and the patient's location change information, and identifies the patient's current physical state based on the patient's physical detection information.
[0007] Based on the patient's behavior detection information, the patient's current behavior information is identified, and based on the patient's current behavior information, the patient's critical behavior information is analyzed through a morphological recognition network;
[0008] Based on the patient's location change information, the patient's location abnormal information is analyzed, and based on the patient's current physical state, the patient's critical behavior information, and the patient's location abnormal information, the patient's current abnormal state is identified through an abnormal state analysis network.
[0009] Based on the patient's current abnormal state, an abnormal distress call is generated and sent to the medical staff's client.
[0010] Optionally, identifying the patient's current physical state based on the patient's physical examination information includes:
[0011] The body detection information is broken down into detection data for each body detection type, and for each detection data, the detection data is processed by data distribution to obtain detection data distribution information;
[0012] Based on the detection data distribution information, the data distribution range and data distribution trend of the detection type are identified, and based on the data distribution range and data distribution trend of the detection type, the sub-body state corresponding to the detection type is identified through the state identification strategy of the detection type.
[0013] The sub-body states corresponding to all detection types are taken as the patient's current body state.
[0014] Optionally, identifying the patient's current behavioral information based on the patient's behavioral detection information includes:
[0015] Based on the patient's behavior monitoring information, the patient's body vibration monitoring information and the patient's behavior continuity information are identified, and based on the patient's body vibration monitoring information, the patient's body vibration amplitude and the intensity of body vibration experienced by the patient are identified;
[0016] Based on the patient's behavior duration information, the duration of the patient's behavior and the content of the patient's current behavior are identified. Based on the amplitude of the patient's body vibration and the intensity of the body vibration experienced by the patient, abnormal body vibration information of the patient is identified through vibration analysis strategy.
[0017] Based on the duration of the patient's behavior and the content of the patient's current behavior, an abnormal behavior analysis strategy is used to identify abnormal behavior information of the patient, and the abnormal vibration information of the patient's body and the abnormal behavior information of the patient are used as the patient's current behavior information.
[0018] Optionally, the morphological recognition network includes a vibration analysis network and a behavior analysis network. The step of analyzing the patient's critical behavior information through the morphological recognition network based on the patient's current behavioral information includes:
[0019] Based on the patient's abnormal body vibration information, the vibration analysis network is used to analyze the cause of the patient's body vibration, and based on the patient's abnormal behavior information, the behavior analysis network is used to identify the type of abnormal behavior of the patient.
[0020] In the abnormal behavior database, query each initial critical behavior information containing the cause of the body tremor and the type of abnormal behavior, and based on the duration of the patient's behavior and the amplitude of the patient's body tremor, filter the critical behavior information corresponding to the patient from each initial critical behavior information.
[0021] Optionally, analyzing the patient's location anomaly information based on the patient's location change information includes:
[0022] The patient's location change information is arranged in chronological order to generate the patient's movement trajectory and the patient's movement area. Based on the patient's movement area, the patient's historical movement database is used to query the patient's various movement types in the movement area.
[0023] Based on the patient's movement trajectory and the patient's historical movement trajectory for each movement type, the movement trajectory that the patient is suited to is identified, and when there is no movement trajectory that the patient is suited to, the patient's location change information is determined to be location abnormal information.
[0024] Optionally, the step of identifying the patient's current abnormal state through an abnormal state analysis network based on the patient's current physical state, the patient's critical behavior information, and the patient's location anomaly information includes:
[0025] Based on the patient's current physical state, the abnormal information of the patient's physical state is analyzed through a state analysis network. Based on the patient's critical behavior information and the abnormal information of the patient's physical state, the abnormal state identification network identifies each initial abnormal state corresponding to the patient and extracts the action trajectory features of each initial abnormal state and the patient trajectory features of the patient's action trajectory.
[0026] Calculate the patient's trajectory features and the similarity between them and each movement trajectory feature, and select the initial abnormal state corresponding to the maximum similarity as the patient's current abnormal state.
[0027] Furthermore, to achieve the above objectives, the present invention also provides an emergency call system for users in abnormal states, the emergency call system for users in abnormal states comprising:
[0028] The acquisition module is used to acquire the patient's physical detection information, the patient's behavior detection information, and the patient's location change information, and to identify the patient's current physical state based on the patient's physical detection information;
[0029] The analysis module is used to identify the patient's current behavior information based on the patient's behavior detection information, and to analyze the patient's critical behavior information through a morphological recognition network based on the patient's current behavior information.
[0030] The identification module is used to analyze the patient's location abnormality information based on the patient's location change information, and to identify the patient's current abnormal state based on the patient's current physical state, the patient's critical behavior information, and the patient's location abnormality information through an abnormal state analysis network.
[0031] The distress call module is used to generate abnormal distress call information for the patient based on the patient's current abnormal state, and send the abnormal distress call information to the medical staff's client.
[0032] Optionally, the acquisition module is specifically used for:
[0033] The body detection information is broken down into detection data for each body detection type, and for each detection data, the detection data is processed by data distribution to obtain detection data distribution information;
[0034] Based on the detection data distribution information, the data distribution range and data distribution trend of the detection type are identified, and based on the data distribution range and data distribution trend of the detection type, the sub-body state corresponding to the detection type is identified through the state identification strategy of the detection type.
[0035] The sub-body states corresponding to all detection types are taken as the patient's current body state.
[0036] Optionally, the analysis module is specifically used for:
[0037] Based on the patient's behavior monitoring information, the patient's body vibration monitoring information and the patient's behavior continuity information are identified, and based on the patient's body vibration monitoring information, the patient's body vibration amplitude and the intensity of body vibration experienced by the patient are identified;
[0038] Based on the patient's behavior duration information, the duration of the patient's behavior and the content of the patient's current behavior are identified. Based on the amplitude of the patient's body vibration and the intensity of the body vibration experienced by the patient, abnormal body vibration information of the patient is identified through vibration analysis strategy.
[0039] Based on the duration of the patient's behavior and the content of the patient's current behavior, an abnormal behavior analysis strategy is used to identify abnormal behavior information of the patient, and the abnormal vibration information of the patient's body and the abnormal behavior information of the patient are used as the patient's current behavior information.
[0040] Optionally, the analysis module is specifically used for:
[0041] Based on the patient's abnormal body vibration information, the vibration analysis network is used to analyze the cause of the patient's body vibration, and based on the patient's abnormal behavior information, the behavior analysis network is used to identify the type of abnormal behavior of the patient.
[0042] In the abnormal behavior database, query each initial critical behavior information containing the cause of the body tremor and the type of abnormal behavior, and based on the duration of the patient's behavior and the amplitude of the patient's body tremor, filter the critical behavior information corresponding to the patient from each initial critical behavior information.
[0043] Optionally, the identification module is specifically used for:
[0044] The patient's location change information is arranged in chronological order to generate the patient's movement trajectory and the patient's movement area. Based on the patient's movement area, the patient's historical movement database is used to query the patient's various movement types in the movement area.
[0045] Based on the patient's movement trajectory and the patient's historical movement trajectory for each movement type, the movement trajectory that the patient is suited to is identified, and when there is no movement trajectory that the patient is suited to, the patient's location change information is determined to be location abnormal information.
[0046] Optionally, the identification module is specifically used for:
[0047] Based on the patient's current physical state, the abnormal information of the patient's physical state is analyzed through a state analysis network. Based on the patient's critical behavior information and the abnormal information of the patient's physical state, the abnormal state identification network identifies each initial abnormal state corresponding to the patient and extracts the action trajectory features of each initial abnormal state and the patient trajectory features of the patient's action trajectory.
[0048] Calculate the patient's trajectory features and the similarity between them and each movement trajectory feature, and select the initial abnormal state corresponding to the maximum similarity as the patient's current abnormal state.
[0049] Thirdly, this application provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method described in any one of the first aspects.
[0050] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first aspects.
[0051] Fifthly, this application provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.
[0052] This invention provides an emergency call method, system, and device for users in abnormal states. The method includes: acquiring a patient's physical detection information, the patient's behavioral detection information, and the patient's location change information; identifying the patient's current physical state based on the physical detection information; identifying the patient's current behavioral information based on the behavioral detection information; analyzing the patient's critical behavioral information based on the current behavioral information using a morphological recognition network; analyzing the patient's location anomaly information based on the location change information; identifying the patient's current abnormal state based on the critical behavioral information and the patient's location anomaly information using an abnormal state analysis network; generating an abnormal call for help based on the patient's current abnormal state; and sending the abnormal call for help to a medical staff client. This solution utilizes sensor devices installed on the patient to collect real-time information on the patient's physical condition, behavior, and location changes. This allows for a comprehensive analysis of the patient's current abnormal state from three perspectives: physical condition, behavioral abnormalities, and location anomalies. Physical condition indicates whether there are abnormalities in the patient's physiological state; behavioral abnormalities indicate whether there are abnormalities in the patient's actions; and location anomalies provide evidence of special circumstances such as fainting, collapse, or falls. This solution then comprehensively analyzes and determines the patient's current abnormal state from these three perspectives, improving the accuracy and comprehensiveness of the analysis. It significantly reduces the risk of misjudgments, missed judgments, and analytical errors caused by incorrect assessments. Therefore, when a patient is unaccompanied, acting alone, and in an abnormal state, the solution can accurately determine the patient's condition and promptly call for help from medical personnel, improving the efficiency and accuracy of emergency calls and comprehensively enhancing the efficiency of communication between medical personnel and patients in the event of a sudden abnormal state. Attached Figure Description
[0053] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0054] Figure 1 This is a flowchart of an emergency distress call method for users in abnormal states provided in an embodiment of the present invention;
[0055] Figure 2 This is a schematic diagram of the structure of the emergency call system for abnormal user states provided in an embodiment of the present invention;
[0056] Figure 3An internal structural diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation
[0057] The emergency call method for user abnormal states provided in this invention is applied to emergency call systems for user abnormal states. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing specific embodiments only and is not intended to limit this application. The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or accompanying drawings of this application are used to distinguish different objects, not to describe a specific order.
[0058] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0059] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
[0060] The emergency call method for abnormal user states provided in this application embodiment can be applied to the application environment of dialysis replacement fluid preparation guidance. This method can be applied to a terminal, a server, or a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, etc. The terminal, through sensor devices installed on the patient, collects the patient's physical detection information, behavioral monitoring information, and location change information in real time. This allows for a comprehensive analysis of the patient's current abnormal state from three perspectives: physical state, behavioral abnormalities, and location abnormalities. Physical state indicates whether there are abnormalities in the patient's physiological state; behavioral abnormalities indicate whether there are abnormalities in the patient's actions; and location abnormalities provide evidence of special circumstances such as fainting, collapse, or falls. This solution then comprehensively analyzes and judges the patient's current abnormal state from these three perspectives, improving the accuracy and comprehensiveness of the analysis of the patient's abnormal physical state. It greatly avoids misjudgments, missed judgments, and analysis abnormalities caused by judgment abnormalities. This allows for accurate assessment of a patient's condition when they are unaccompanied, acting alone, and in an abnormal state, enabling them to promptly call for help from medical staff. This improves the efficiency and accuracy of emergency calls, and comprehensively enhances the efficiency of communication between medical staff and patients in the event of a sudden abnormal condition.
[0061] In one embodiment, such as Figure 1 As shown, an emergency call method for users in abnormal states is provided. Taking the application of this method to a terminal as an example, it includes the following steps:
[0062] Step S101: Obtain the patient's physical detection information, the patient's behavioral detection information, and the patient's location change information, and identify the patient's current physical state based on the patient's physical detection information.
[0063] In this embodiment, the terminal receives sensor data transmitted in real time from detection sensors installed on the patient's body surface to obtain the patient's physical detection information. This physical detection information includes, but is not limited to, detection data from various body detection types, including pulse detection, respiration detection, and blood pressure monitoring. The sensors for each body detection type are portable sensors, such as smart bracelets, capable of simultaneously detecting pulse and blood pressure. The sensor corresponding to the respiration detection type is an airflow sensor installed at the user's mouth. Then, the terminal collects the patient's behavioral monitoring information using devices such as vibration sensors and displacement sensors. The vibration sensors and joint displacement sensors are installed on the patient's limbs, head, and chest / abdomen. Finally, the terminal collects the patient's location information in real time using a locator installed on the patient's body surface to obtain the patient's location change information. Then, based on the patient's physical detection information, the terminal identifies the patient's current physical state, which is the patient's physiological state, used to characterize the patient's physiological characteristics, thereby determining whether the patient has any urgent physiological abnormalities. The specific identification process will be explained in detail later.
[0064] Step S102: Based on the patient's behavior detection information, identify the patient's current behavior information, and based on the patient's current behavior information, analyze the patient's critical behavior information through a morphological recognition network.
[0065] In this embodiment, the terminal identifies the patient's current behavior based on the patient's behavior detection information, and then analyzes the patient's critical behavior information through a morphological recognition network. This morphological recognition network includes a vibration analysis network and a behavior analysis network. The vibration analysis network analyzes the intensity of the vibration experienced by the patient's body and the cause of the vibration corresponding to the amplitude, while the behavior analysis network analyzes the duration of the patient's behavior and the type of behavioral abnormality corresponding to the content of the behavior. The specific identification process will be described in detail later. The aforementioned networks are neural networks based on reinforcement learning.
[0066] Step S103: Based on the patient's location change information, analyze the patient's location abnormality information, and based on the patient's current physical state, the patient's critical behavior information, and the patient's location abnormality information, identify the patient's current abnormal state through an abnormal state analysis network.
[0067] In this embodiment, the terminal analyzes the patient's location anomaly information based on the patient's location change information, and identifies the patient's current abnormal state through an abnormal state analysis network based on the patient's critical behavior information and the abnormal location information. The abnormal state analysis network is an artificial neural network. The specific analysis process will be described in detail later. Examples of abnormal location information include maintaining a fixed posture for a long time, changing a long distance over a short time, changing a short distance over a long time, or maintaining an abnormal posture for a long time.
[0068] Step S104: Based on the patient's current abnormal state, generate the patient's abnormal distress call information and send the abnormal distress call information to the medical staff's client.
[0069] In this embodiment, the terminal fills the patient's current abnormal state into the patient's abnormal distress call template to obtain the patient's abnormal distress call information. The abnormal distress call template includes, but is not limited to, abnormal state information, patient location information, duration of the abnormal state, and the urgency level corresponding to the abnormal state. Finally, the terminal sends the patient's abnormal distress call information to the medical staff's client.
[0070] Based on the above scheme, by installing sensor devices on the patient, real-time data on the patient's physical condition, behavior, and location changes is collected. This allows for a comprehensive analysis of the patient's current abnormal state from three perspectives: physical condition, behavioral abnormalities, and location anomalies. Physical condition indicates whether there are abnormalities in the patient's physiological state; behavioral abnormalities indicate whether there are abnormalities in the patient's actions; and location anomalies provide evidence of special circumstances such as fainting, collapse, or falls. This scheme then comprehensively analyzes and judges the patient's current abnormal state from these three perspectives, improving the accuracy and comprehensiveness of the analysis. It greatly avoids misjudgments, missed judgments, and analytical errors caused by misjudgments. Therefore, when a patient is unaccompanied, acting alone, and in an abnormal state, the scheme can accurately determine the patient's abnormal state and promptly call for help from medical personnel, improving the efficiency and accuracy of emergency calls and comprehensively enhancing the efficiency of communication between medical personnel and patients in the event of a sudden abnormal state.
[0071] Optionally, based on the patient's physical examination information, the current physical state of the patient is identified, including: breaking down the physical examination information into test data of various physical examination types, and performing data distribution processing on the test data for each test data to obtain test data distribution information; based on the test data distribution information, identifying the data distribution range and data distribution trend of each test type, and based on the data distribution range and data distribution trend of each test type, identifying the sub-physical states corresponding to each test type through a state identification strategy; and taking all sub-physical states corresponding to each test type as the patient's current physical state.
[0072] In this embodiment, the terminal breaks down the body detection information into detection data for each body detection type, and performs data distribution processing on each detection data to obtain detection data distribution information. This detection data distribution information is obtained by distributing and sorting the real-time collected detection data according to time sequence.
[0073] Then, based on the detection data distribution information, the terminal identifies the data distribution range and the data distribution trend of the detection type. The identification of the data distribution trend is achieved by using a curve fitting algorithm to fit the data distribution curve corresponding to the detection data distribution information.
[0074] Next, based on the data distribution range and trend of each detection type, the terminal identifies the corresponding sub-body state using a state recognition strategy for each detection type. Each detection type corresponds to a state recognition strategy, and each state recognition strategy includes the detection data range corresponding to each body state. Then, the terminal identifies the patient's corresponding body state based on the detection data range to which the patient's detection data belongs.
[0075] Finally, the terminal uses the sub-body states corresponding to all detection types as the patient's current body state.
[0076] Based on the above scheme, by splitting the test data of each test type to identify each sub-body state, the comprehensiveness and accuracy of identifying the patient's current body state are improved.
[0077] Optionally, based on the patient's behavior detection information, identify the patient's current behavior information, including: based on the patient's behavior monitoring information, identify the patient's body vibration monitoring information and the patient's behavior duration information; based on the patient's body vibration monitoring information, identify the patient's body vibration amplitude and the intensity of body vibration experienced by the patient; based on the patient's behavior duration information, identify the patient's behavior duration and the patient's current behavior content; based on the patient's body vibration amplitude and the intensity of body vibration experienced by the patient, identify the patient's abnormal body vibration information through a vibration analysis strategy; based on the patient's behavior duration and the patient's current behavior content, identify the patient's abnormal behavior information through a behavior anomaly analysis strategy, and use the patient's abnormal body vibration information and the patient's abnormal behavior information as the patient's current behavior information.
[0078] In this embodiment, the terminal identifies the patient's body vibration monitoring information and the patient's continuous behavior information based on the patient's behavior monitoring information. Based on the patient's body vibration monitoring information, it identifies the amplitude of the patient's body vibration and the intensity of the body vibration experienced by the patient. The body vibration monitoring information includes vibration monitoring information for various body locations, including but not limited to the head, hands, legs, and chest / abdomen. The intensity of body vibration in different locations differs from the actual vibration intensity experienced by that location. For example, a 10kg impact to the head corresponds to a vibration intensity level 3, while a 10kg impact to the legs corresponds to a vibration intensity level 1. Body vibration intensity can be divided into ten levels, with higher levels indicating higher vibration intensity. The more critical the body location, the easier it is to reach a higher vibration intensity level; conversely, the less critical the body location, the less likely it is to reach a high vibration intensity level. Key body locations include the head and chest / abdomen, while non-key body locations include the hands and legs. The head location is considered more critical than the chest / abdomen.
[0079] Then, based on the patient's continuous behavior information, the terminal identifies the duration of the patient's behavior and the content of the patient's current behavior. The device for collecting the patient's continuous behavior information can be motion capture sensors set at various joints of the patient. Based on these motion capture sensors, the patient's movements can be collected in real time. These movements include, but are not limited to, simple actions such as walking, squatting, moving, jumping, and climbing. The movements can also be the patient's current posture, such as lying down, sitting, prone, semi-reclining, or irregular postures.
[0080] Next, based on the patient's body vibration amplitude and intensity, the terminal identifies abnormal vibration information through a vibration analysis strategy. This strategy identifies vibration information corresponding to different body vibration amplitude and intensity ranges across different body areas. This vibration information includes both normal and abnormal vibration information. Specifically, the body vibration amplitude range for each body area includes both normal and abnormal vibration amplitude ranges; similarly, the body vibration intensity range for each body area includes both normal and abnormal vibration intensity ranges. Since the normal and abnormal vibration information differs across different body areas, the terminal aggregates all vibration information into the body area experiencing abnormal vibration, along with the corresponding vibration intensity or amplitude for that body area, as the patient's abnormal vibration information.
[0081] Finally, based on the duration of the patient's behavior and the content of the patient's current behavior, the terminal identifies abnormal behavior information through a behavior anomaly analysis strategy, and uses the patient's abnormal body vibration information and the abnormal behavior information as the patient's current behavior information. Each current behavior content corresponds to different behavior information within different behavior duration ranges. This behavior information includes normal behavior information and abnormal behavior information. When the terminal determines that the behavior information corresponding to the duration of the patient's current behavior content is abnormal, it uses both the patient's current behavior content and its corresponding duration as the patient's abnormal behavior information.
[0082] Based on the above scheme, by identifying different behavioral information corresponding to different durations of patient behavior, as well as the intensity or amplitude of body vibration corresponding to different body parts, abnormal body vibration information and abnormal behavior information of patients can be determined, thereby improving the accuracy and comprehensiveness of identification.
[0083] Optionally, the morphological recognition network includes a vibration analysis network and a behavior analysis network. Based on the patient's current behavioral information, the morphological recognition network analyzes the patient's critical behavior information, including: based on the patient's abnormal body vibration information, the vibration analysis network analyzes the cause of the patient's body vibration; based on the patient's abnormal behavior information, the behavior analysis network identifies the type of abnormal behavior; in the behavior abnormality database, it queries each initial critical behavior information containing the cause of body vibration and the type of abnormal behavior, and based on the duration of the patient's behavior and the amplitude of the patient's body vibration, it filters the corresponding critical behavior information from each initial critical behavior information.
[0084] In this embodiment, the terminal analyzes the cause of the patient's abnormal body vibration information through a vibration analysis network, and identifies the type of abnormal behavior based on the patient's abnormal behavior information through a behavior analysis network.
[0085] Then, the terminal queries the behavioral anomaly database for initial critical behavior information, including the cause of body vibration and the type of behavioral anomaly. Based on the duration of the patient's behavior and the amplitude of the patient's body vibration, the terminal filters the corresponding critical behavior information from each initial critical behavior information. Each initial critical behavior information corresponds to a range of body vibration amplitude for a specific body area and a range of behavior duration. The terminal then determines the corresponding initial critical behavior information for the patient based on the duration of the patient's behavior and the range of body vibration amplitude for each body area.
[0086] Based on the above scheme, by identifying the cause of the patient's abnormal vibration and the type of abnormal behavior, the patient's critical behavior information was screened, thereby improving the accuracy of the identification of critical behavior information.
[0087] Optionally, based on the patient's location change information, analyze the patient's location anomaly information, including: arranging the patient's location change information in chronological order to generate the patient's movement trajectory and the patient's movement area; querying the patient's historical movement database for each movement type in the movement area based on the patient's movement area; identifying the patient's appropriate movement trajectory based on the patient's movement trajectory and the patient's historical movement trajectory for each movement type; and determining the patient's location change information as location anomaly information when no appropriate movement trajectory exists.
[0088] In this embodiment, the terminal arranges the patient's location change information in chronological order to generate the patient's movement trajectory and the patient's current movement area. Based on the patient's current movement area, the terminal queries the patient's historical movement database for various movement types within that area. The patient's current movement area is one of several movement areas preset by medical staff, such as rest areas, restroom areas, corridor areas, garden areas, office areas, consultation desk areas, treatment areas, and testing areas.
[0089] Finally, based on the patient's movement trajectory and their historical movement trajectories for each movement type, the terminal identifies the patient's appropriate movement trajectory. If no suitable movement trajectory exists, the terminal classifies the patient's location change information as location anomaly information. Specifically, medical staff collect each patient's movement trajectory for different movement types and store it in a database. Due to the regularity of patient behavior, by matching the overlap between different movement trajectories and historical movement trajectories, it can be determined whether the patient's actions are within normal areas. When the patient's actions do not fall within normal areas, the terminal classifies the patient's location change information as location anomaly information.
[0090] Based on the above scheme, by adapting the patient's movement trajectory to the movement area, and then identifying the overlap based on the patient's historical movement trajectory, it is possible to determine whether the patient is in a location abnormality, thereby improving the efficiency and accuracy of identifying the patient's location abnormality information.
[0091] Optionally, based on the patient's current physical state, the patient's critical behavior information, and the patient's location anomaly information, an abnormal state analysis network is used to identify the patient's current abnormal state. This includes: based on the patient's current physical state, analyzing the patient's abnormal physical state information through the state analysis network; and based on the patient's critical behavior information and the patient's abnormal physical state information, identifying each initial abnormal state corresponding to the patient through an abnormal state identification network, and extracting the movement trajectory features of each initial abnormal state and the patient's movement trajectory features; calculating the similarity between the patient's trajectory features and each movement trajectory feature, and selecting the initial abnormal state corresponding to the highest similarity as the patient's current abnormal state.
[0092] In this embodiment, the terminal analyzes the patient's abnormal physical state information through a state analysis network based on the patient's current physical state. Based on the patient's critical behavior information and abnormal physical state information, an abnormal state recognition network identifies the patient's corresponding initial abnormal states and extracts the movement trajectory features for each initial abnormal state, as well as the patient's movement trajectory features. The state analysis network and the abnormal state recognition network are reinforcement learning-based neural networks. The movement trajectory feature extraction method involves extracting image features from the trajectory image corresponding to the patient's movement trajectory using an image feature extraction network. The image feature extraction network is a convolutional neural network based on a self-attention mechanism.
[0093] Then, the terminal uses a cosine similarity algorithm to calculate the patient's trajectory features and the similarity between them and each movement trajectory feature, and selects the initial abnormal state corresponding to the maximum similarity as the patient's current abnormal state.
[0094] Based on the above scheme, the accuracy and comprehensiveness of identifying the patient's current abnormal state are improved by identifying the patient's current abnormal state from three perspectives: physical condition, critical behavior information, and movement trajectory.
[0095] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0096] Based on the same inventive concept, this application also provides an emergency call system for user abnormal states to implement the emergency call method for user abnormal states described above. The solution provided by this system is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more embodiments of the emergency call system for user abnormal states provided below can be found in the limitations of the emergency call method for user abnormal states described above, and will not be repeated here.
[0097] Further reference Figure 2 As a response to the above Figure 1 The present application provides an embodiment of an emergency call system 200 for users in abnormal states, which includes an acquisition module 210, an analysis module 220, an identification module 230, and a call module 240, wherein:
[0098] The acquisition module 210 is used to acquire the patient's physical detection information, the patient's behavior detection information, and the patient's location change information, and to identify the patient's current physical state based on the patient's physical detection information;
[0099] The analysis module 220 is used to identify the patient's current behavior information based on the patient's behavior detection information, and to analyze the patient's critical behavior information through a morphological recognition network based on the patient's current behavior information.
[0100] The identification module 230 is used to analyze the patient's location abnormality information based on the patient's location change information, and to identify the patient's current abnormal state through an abnormal state analysis network based on the patient's current physical state, the patient's critical behavior information, and the patient's location abnormality information.
[0101] The emergency call module 240 is used to generate abnormal emergency call information for the patient based on the patient's current abnormal state, and send the abnormal emergency call information to the medical staff's client.
[0102] Optionally, the acquisition module 210 is specifically used for:
[0103] The body detection information is broken down into detection data for each body detection type, and for each detection data, the detection data is processed by data distribution to obtain detection data distribution information;
[0104] Based on the detection data distribution information, the data distribution range and data distribution trend of the detection type are identified, and based on the data distribution range and data distribution trend of the detection type, the sub-body state corresponding to the detection type is identified through the state identification strategy of the detection type.
[0105] The sub-body states corresponding to all detection types are taken as the patient's current body state.
[0106] Optionally, the analysis module 220 is specifically used for:
[0107] Based on the patient's behavior monitoring information, the patient's body vibration monitoring information and the patient's behavior continuity information are identified, and based on the patient's body vibration monitoring information, the patient's body vibration amplitude and the intensity of body vibration experienced by the patient are identified;
[0108] Based on the patient's behavior duration information, the duration of the patient's behavior and the content of the patient's current behavior are identified. Based on the amplitude of the patient's body vibration and the intensity of the body vibration experienced by the patient, abnormal body vibration information of the patient is identified through vibration analysis strategy.
[0109] Based on the duration of the patient's behavior and the content of the patient's current behavior, an abnormal behavior analysis strategy is used to identify abnormal behavior information of the patient, and the abnormal vibration information of the patient's body and the abnormal behavior information of the patient are used as the patient's current behavior information.
[0110] Optionally, the analysis module 220 is specifically used for:
[0111] Based on the patient's abnormal body vibration information, the vibration analysis network is used to analyze the cause of the patient's body vibration, and based on the patient's abnormal behavior information, the behavior analysis network is used to identify the type of abnormal behavior of the patient.
[0112] In the abnormal behavior database, query each initial critical behavior information containing the cause of the body tremor and the type of abnormal behavior, and based on the duration of the patient's behavior and the amplitude of the patient's body tremor, filter the critical behavior information corresponding to the patient from each initial critical behavior information.
[0113] Optionally, the identification module 230 is specifically used for:
[0114] The patient's location change information is arranged in chronological order to generate the patient's movement trajectory and the patient's movement area. Based on the patient's movement area, the patient's historical movement database is used to query the patient's various movement types in the movement area.
[0115] Based on the patient's movement trajectory and the patient's historical movement trajectory for each movement type, the movement trajectory that the patient is suited to is identified, and when there is no movement trajectory that the patient is suited to, the patient's location change information is determined to be location abnormal information.
[0116] Optionally, the identification module 230 is specifically used for:
[0117] Based on the patient's current physical state, the abnormal information of the patient's physical state is analyzed through a state analysis network. Based on the patient's critical behavior information and the abnormal information of the patient's physical state, the abnormal state identification network identifies each initial abnormal state corresponding to the patient and extracts the action trajectory features of each initial abnormal state and the patient trajectory features of the patient's action trajectory.
[0118] Calculate the patient's trajectory features and the similarity between them and each movement trajectory feature, and select the initial abnormal state corresponding to the maximum similarity as the patient's current abnormal state.
[0119] The modules in the aforementioned emergency call system for abnormal user states can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.
[0120] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown, the computer device includes a processor, memory, communication interface, display screen, and input system connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements an emergency call method for users in abnormal situations. The display screen can be an LCD screen or an e-ink screen. The input system can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.
[0121] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0122] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any one of the first aspects.
[0123] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.
[0124] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects.
[0125] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0126] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0127] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0128] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. An emergency distress call method for a user in an abnormal state, characterized in that, The method includes: The system acquires the patient's physical detection information, the patient's behavioral detection information, and the patient's location change information, and identifies the patient's current physical state based on the patient's physical detection information. Based on the patient's behavior detection information, the patient's current behavior information is identified, and based on the patient's current behavior information, the patient's critical behavior information is analyzed through a morphological recognition network; Based on the patient's location change information, the patient's location abnormal information is analyzed, and based on the patient's current physical state, the patient's critical behavior information, and the patient's location abnormal information, the patient's current abnormal state is identified through an abnormal state analysis network. Based on the patient's current abnormal state, generate the patient's abnormal distress call information and send the abnormal distress call information to the medical staff's client; The step of identifying the patient's current behavioral information based on the patient's behavioral detection information includes: Based on the patient's behavior detection information, the patient's body vibration monitoring information and the patient's behavior continuity information are identified, and based on the patient's body vibration monitoring information, the patient's body vibration amplitude and the intensity of body vibration experienced by the patient are identified; Based on the patient's continuous behavior information, the duration of the patient's behavior and the content of the patient's current behavior are identified. Based on the patient's body vibration amplitude and the intensity of the body vibration experienced by the patient, a vibration analysis strategy is used to identify abnormal body vibration information. The vibration analysis strategy comprises vibration information corresponding to different body vibration amplitude ranges and different body vibration intensity ranges. This vibration information includes normal vibration information and abnormal vibration information. Specifically, each body vibration amplitude range includes both normal and abnormal vibration amplitude ranges; each body vibration intensity range includes both normal and abnormal vibration intensity ranges. The terminal aggregates all vibration information into the body range of abnormal vibration information and the corresponding body vibration intensity or amplitude for that body range, which is then used as the patient's abnormal body vibration information. Based on the duration of the patient's behavior and the content of the patient's current behavior, an abnormal behavior analysis strategy is used to identify abnormal behavior information of the patient, and the abnormal vibration information of the patient's body and the abnormal behavior information of the patient are used as the patient's current behavior information. Based on the patient's current physical state, the patient's critical behavior information, and the patient's location anomaly information, the abnormal state analysis network identifies the patient's current abnormal state, including: Based on the patient's current physical state, the abnormal information of the patient's physical state is analyzed through a state analysis network. Based on the patient's critical behavior information and the abnormal information of the patient's physical state, the abnormal state identification network identifies each initial abnormal state corresponding to the patient and extracts the action trajectory features of each initial abnormal state and the patient trajectory features of the patient's action trajectory. Calculate the patient's trajectory features and the similarity between them and each movement trajectory feature, and select the initial abnormal state corresponding to the maximum similarity as the patient's current abnormal state.
2. The method according to claim 1, characterized in that, The step of identifying the patient's current physical state based on the patient's physical examination information includes: The body detection information is broken down into detection data for each body detection type, and for each detection data, the detection data is processed by data distribution to obtain detection data distribution information; Based on the detection data distribution information, the data distribution range and data distribution trend of the detection type are identified, and based on the data distribution range and data distribution trend of the detection type, the sub-body state corresponding to the detection type is identified through the state identification strategy of the detection type. The sub-body states corresponding to all detection types are taken as the patient's current body state.
3. The method according to claim 1, characterized in that, The morphological recognition network includes a vibration analysis network and a behavior analysis network. The analysis of the patient's critical behavior information based on the patient's current behavioral information via the morphological recognition network includes: Based on the patient's abnormal body vibration information, the vibration analysis network is used to analyze the cause of the patient's body vibration, and based on the patient's abnormal behavior information, the behavior analysis network is used to identify the type of abnormal behavior of the patient. In the abnormal behavior database, query each initial critical behavior information containing the cause of the body tremor and the type of abnormal behavior, and based on the duration of the patient's behavior and the amplitude of the patient's body tremor, filter the critical behavior information corresponding to the patient from each initial critical behavior information.
4. The method according to claim 1, characterized in that, The step of analyzing the patient's location anomaly information based on the patient's location change information includes: The patient's location change information is arranged in chronological order to generate the patient's movement trajectory and the patient's movement area. Based on the patient's movement area, the patient's historical movement database is used to query the patient's various movement types in the movement area. Based on the patient's movement trajectory and the patient's historical movement trajectory for each movement type, the movement trajectory that the patient is suited to is identified, and when there is no movement trajectory that the patient is suited to, the patient's location change information is determined to be location abnormal information.
5. An emergency call device for users in abnormal states, characterized in that, The device includes: The acquisition module is used to acquire the patient's physical detection information, the patient's behavior detection information, and the patient's location change information, and to identify the patient's current physical state based on the patient's physical detection information; The analysis module is used to identify the patient's current behavior information based on the patient's behavior detection information, and to analyze the patient's critical behavior information through a morphological recognition network based on the patient's current behavior information. The identification module is used to analyze the patient's location abnormality information based on the patient's location change information, and to identify the patient's current abnormal state based on the patient's current physical state, the patient's critical behavior information, and the patient's location abnormality information through an abnormal state analysis network. The distress call module is used to generate abnormal distress call information for the patient based on the patient's current abnormal state, and send the abnormal distress call information to the medical staff's client. The analysis module identifies the patient's current behavioral information based on the patient's behavioral detection information, including: Based on the patient's behavior monitoring information, the patient's body vibration monitoring information and the patient's behavior continuity information are identified, and based on the patient's body vibration monitoring information, the patient's body vibration amplitude and the intensity of body vibration experienced by the patient are identified; Based on the patient's behavior duration information, the duration of the patient's behavior and the content of the patient's current behavior are identified. Based on the amplitude of the patient's body vibration and the intensity of the body vibration experienced by the patient, abnormal body vibration information of the patient is identified through vibration analysis strategy. Based on the duration of the patient's behavior and the content of the patient's current behavior, an abnormal behavior analysis strategy is used to identify abnormal behavior information of the patient, and the abnormal vibration information of the patient's body and the abnormal behavior information of the patient are used as the patient's current behavior information. The identification module, based on the patient's current physical state, the patient's critical behavior information, and the patient's location anomaly information, identifies the patient's current abnormal state through an abnormal state analysis network, including: Based on the patient's current physical state, the abnormal information of the patient's physical state is analyzed through a state analysis network. Based on the patient's critical behavior information and the abnormal information of the patient's physical state, the abnormal state identification network identifies each initial abnormal state corresponding to the patient. The image feature extraction network extracts image features from the trajectory image corresponding to the movement trajectory, extracting the movement trajectory features of each initial abnormal state and the patient trajectory features of the patient's movement trajectory. Calculate the patient's trajectory features and the similarity between them and each movement trajectory feature, and select the initial abnormal state corresponding to the maximum similarity as the patient's current abnormal state.
6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.
8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.