Patient state information supervision method and related equipment

Abstract

The invention discloses a patient state information supervision method and related equipment. The method comprises the following steps: acquiring a voice record input request of a patient to which the equipment belongs through wearable intelligent terminal equipment; collecting effective voice information of the patient based on the voice record input request, wherein the effective voice information comprises diet types and diet amounts; querying the water content associated with the diet type, and evaluating the water intake of the patient based on the water content and the food intake. The problems that at present, a clinical nurse manually records the liquid inlet and outlet amount of a patient at a fixed time point, the consumed labor time is long, the water content of food is inaccurately estimated, when the condition of the patient changes, a physician cannot obtain completely accurate inlet and outlet amount data at the first time, the condition judgment time is delayed, and the accuracy is high can be solved. And even inappropriate medical advices can be given.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of smart medical care, and more specifically, the present invention relates to a patient status information monitoring method and related equipment. Background Art

[0002] At present, the method for clinical nurses to collect patients' fluid intake and output is fixed time points (6-9-15-20). Nurses go to the bedside to register and record and estimate the patients' oral fluid intake and urine and feces. Clinicians adjust the diagnosis and treatment plan and the dosage of diuretics for patients based on the patient intake and output data provided by nurses. The implementation of this clinical work cannot fully guarantee the accuracy and timeliness of patients' intake and output data. When patients report on their food intake, they partially rely on recall. Patients with better compliance with medical behavior use paper and pen to record. However, no matter which reporting method is used, there is an inaccurate estimate of the water content of food, and there may be omissions. The urine volume is measured with a measuring cup, which is relatively accurate, but there is still a possibility of forgetting. It takes an average of 2 minutes for each patient to record the patient's intake and output. Assuming that there are 60 patients in the ward, more than half of them need to record the intake and output. Therefore, it takes more than 1 hour for nurses to record the intake and output of patients in the ward every day. When a patient's condition changes, such as coughing up watery sputum or even pink foamy sputum due to intake and output problems, the doctor cannot immediately obtain completely accurate intake and output data, resulting in delays in the diagnosis of the condition and even issuing inappropriate medical advice (diuretics, etc.). Summary of the invention

[0003] A series of simplified concepts are introduced in the Summary of the Invention, which will be further described in detail in the Detailed Description of the Invention. The Summary of the Invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0004] In order to solve the problem that the current method for clinical nurses to collect patients' fluid intake and output is to manually record at fixed time points, which consumes a long time of manual labor, the water content of food is estimated inaccurately, and when the patient's condition changes, the doctor cannot get a completely accurate intake and output data in the first time, resulting in delays in the time of condition judgment and even the issuance of inappropriate medical advice, in the first aspect, the present invention proposes a patient status information supervision method, the above method includes:

[0005] Obtaining, through a wearable intelligent terminal device, a voice recording input request from a patient to whom the device belongs;

[0006] Collecting valid voice information of the patient based on the voice record input request, wherein the valid voice information includes the type and amount of food consumed;

[0007] The water content associated with the food type is queried to evaluate the patient's water intake based on the water content and the food amount.

[0008] Optionally, the wearable smart terminal device is a wristband-type smart terminal device, and obtaining a voice recording input request of a patient to which the wearable smart terminal device belongs through the wearable smart terminal device includes:

[0009] Acquiring arm posture information of a patient belonging to the wearable intelligent terminal device through the wearable intelligent terminal device;

[0010] In a case where it is determined based on the arm posture information that the patient performs an arm-raising action, recording a holding time of the arm-raising action;

[0011] When the holding time is greater than a preset time, the arm raising action is identified as a voice recording input request to simultaneously collect voice information.

[0012] Optionally, the wearable smart terminal device is a wristband-type smart terminal device, and the wristband-type smart terminal device is used to be worn on the dominant limb side of the patient, and the method further includes:

[0013] Acquiring arm posture information of a patient belonging to the wearable intelligent terminal device through the wearable intelligent terminal device;

[0014] When it is predicted that the patient is in an eating posture based on the arm posture information, a water intake reminder message is generated to prompt the patient to record the eating behavior.

[0015] Optionally, also include:

[0016] Monitoring the positional relationship between the wearable intelligent terminal device and the ward toilet;

[0017] Determine the current distance between the two based on the positional relationship, and if the current distance is less than the budgeted distance, collect flushing control information of the toilet;

[0018] When a flushing control instruction of the toilet is acquired, a current water seal height of the toilet is acquired to determine the excretion volume of the patient based on the current water seal height and a basic water seal height of the toilet;

[0019] The flushing control instruction is executed after the current water seal height of the toilet is acquired.

[0020] Optionally, also include:

[0021] Determine the current distance between the two based on the positional relationship, and if the current distance is less than the estimated distance, collect audio information in the toilet;

[0022] determining the type of the patient's excrement based on the audio information;

[0023] determining a water content of the feces based on the type of the feces;

[0024] The water excretion is calculated based on the water content of the excrement and the excretion amount.

[0025] Optionally, also include:

[0026] The water intake or water output is sent to a hospital diagnosis and treatment system or a medical care terminal associated with the patient.

[0027] Optionally, also include:

[0028] The patient's fluid intake and output data within 24 hours are analyzed, and an alarm message is generated when the fluid intake and output data exceeds a normal range.

[0029] In a second aspect, the present invention further provides a patient status information monitoring device, comprising:

[0030] An acquisition unit, used for acquiring a voice recording input request of a patient belonging to the wearable intelligent terminal device through the wearable intelligent terminal device;

[0031] An analyzing unit, configured to collect valid voice information of the patient based on the voice recording input request, wherein the valid voice information includes a type of diet and a diet amount;

[0032] The evaluation unit is used to query the water content associated with the food type to evaluate the patient's water intake based on the water content and the food amount.

[0033] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the patient status information monitoring method as described in any one of the above-mentioned first aspects when executing the computer program stored in the memory.

[0034] In a fourth aspect, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the patient status information monitoring method of any one of the above items in the first aspect is implemented.

[0035] In summary, the patient status information supervision method proposed in this application obtains the voice recording input request of the patient to which the device belongs through a wearable intelligent terminal device; based on the voice recording input request, the patient's valid voice information is collected, and the valid voice information includes the type of diet and the amount of diet; the water content associated with the type of diet is queried to evaluate the patient's water intake based on the water content and the amount of diet. As a result, the patient does not need to input manually, which reduces the burden of recording and improves convenience and compliance. Using the voice wake-up function, patients can record dietary information at any time to avoid forgetting. Automatically identify dietary information, process fuzzy descriptions, and ensure data accuracy. Context understanding capabilities avoid repeated input and improve user experience. Through a standardized food database, errors caused by subjective estimates of patients are avoided. Automatically calculate water intake, and the results are accurate and reliable. Real-time recording ensures the timeliness of data and provides a reliable basis for medical staff. The abnormal reminder function reduces the risks caused by insufficient or excessive fluid intake.

[0036] The patient status information supervision method of the present invention, and other advantages, objectives and features of the present invention will be reflected in part through the following description, and in part will also be understood by technicians in this field through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0038] Figure 1 A schematic diagram of a patient status information monitoring method provided in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of the structure of a patient status information monitoring device provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of the structure of an electronic device for monitoring patient status information provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present 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 described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0042] In order to solve the problem that the current method for clinical nurses to collect patients' fluid intake and output is to record them manually at fixed time points, which consumes a long time, the water content of food is not accurately estimated, and when the patient's condition changes, the doctor cannot get a completely accurate intake and output data in the first time, resulting in delays in the diagnosis of the condition and even the issuance of inappropriate medical advice, please refer to Figure 1 , is a flow chart of a patient status information supervision method provided in an embodiment of the present application, which may specifically include: steps S110 to S130.

[0043] S110, obtaining, through a wearable intelligent terminal device, a voice recording input request of a patient to which the device belongs.

[0044] S120: Collecting effective voice information of the patient based on the voice recording input request, wherein the effective voice information includes food types and food amounts.

[0045] S130, querying the water content associated with the food type to evaluate the patient's water intake based on the water content and food intake.

[0046] It is understandable that the patient wears a smart terminal device (such as a smart bracelet, a voice assistant device, etc.). The device is awakened by voice, for example: the patient says "I want to record my diet". The device activates the voice recording function. The device records the dietary information described by the patient, such as: "I ate a bowl of rice porridge and drank a glass of milk this morning."; "I ate half a watermelon at noon." The system uses speech recognition technology (such as a deep learning model) to convert speech into text, for example, the speech-to-text result: "I ate a bowl of rice porridge and drank a glass of milk this morning."; "I ate half a watermelon at noon." The voice-transcribed text is input into the NLP module for semantic analysis: extract keywords: dietary types: rice porridge, milk, watermelon. Dietary amount: one bowl, one cup, half. Fuzzy quantification: The system converts "half" into a weight unit through context and database (such as the standard size of watermelon is 4kg, half a = 2000 grams). "One bowl" is recognized as 200 ml through a preset template. Query the water content database, for example, the system maps the food type to the standard water content in the database: rice porridge: water content 90%. Milk: 87% water content. Watermelon: 92% water content. Water intake calculation formula: Water intake = diet × water content ratio, rice porridge: 200 ml × 90% = 180 ml. Milk: 250 ml × 87% = 217.5 ml. Watermelon: 2000 g × 92% = 1840 ml. The calculation results are synchronized to the patient's fluid management system. The system automatically accumulates the total daily water intake. When the total water intake is insufficient (<2000 ml), the system issues a reminder: "Today's water intake is insufficient, please increase water intake appropriately." When the intake is too much (>3000 ml), it reminds you to reduce water intake to prevent fluid retention.

[0047] In summary, the patient status information supervision method provided in the embodiment of the present application obtains a voice recording input request of the patient to which the device belongs through a wearable intelligent terminal device; based on the voice recording input request, the patient's valid voice information is collected, and the valid voice information includes the type of diet and the amount of diet; the water content associated with the type of diet is queried to evaluate the patient's water intake based on the water content and the amount of diet. Thus, the dietary information is automatically recorded to reduce the error of the patient's reliance on recollection. Based on database calculation, the inaccuracy of subjective estimation is avoided. Wearable devices support real-time collection and rapid data updates. Avoid the lag of fixed time recording. Voice input is natural and smooth, without manual recording. Reduce the workload of nurses and patients and improve compliance. The database can be continuously expanded to support more types of food. The system can be combined with other data (such as urine volume, body weight) for comprehensive analysis. It reduces the burden on patients and medical staff and provides a more scientific and efficient solution for the management of fluid intake and output balance.

[0048] According to some embodiments, the wearable smart terminal device is a wristband-type smart terminal device, and obtaining a voice recording input request of a patient to which the wearable smart terminal device belongs through the wearable smart terminal device includes:

[0049] Acquiring arm posture information of a patient belonging to the wearable intelligent terminal device through the wearable intelligent terminal device;

[0050] In a case where it is determined based on the arm posture information that the patient performs an arm-raising action, recording a holding time of the arm-raising action;

[0051] When the holding time is greater than a preset time, the arm raising action is identified as a voice recording input request to simultaneously collect voice information.

[0052] It is understandable that wristband-type smart terminal devices usually have built-in inertial measurement units (IMUs), including accelerometers, gyroscopes, and magnetometers, for detecting arm movements and posture changes. By analyzing the movement trajectory of the patient's arm, the device can determine whether there is an arm-raising action. After the system detects the arm-raising action, it uses a timer to monitor whether the action lasts for more than the set time threshold (for example, 2 seconds). Short arm-raising actions (such as unintentional hand raising or rapid adjustments) will not trigger a voice recording request to avoid false triggering. When a continuous arm-raising action is detected that exceeds the set time, the system automatically enters the voice collection mode without the patient's additional manual operation. This interactive method is convenient and intuitive, and is suitable for daily use by patients.

[0053] Exemplarily, the IMU in the wristband terminal device collects the acceleration, angular velocity and direction data of the arm. The data is input into the action recognition algorithm (such as a machine learning model or a rule algorithm) to determine whether it is an arm-raising action. The arm-raising action is usually manifested as the arm moving from a vertical (close to the body) position to a horizontal (shoulder-level) or higher position. The system can set a threshold for posture change, for example: the angle between the arm and the body is >45°. The vertical acceleration component (Z axis) of the wrist presents a continuous positive value. The patient raises his arm from one side of the body to the chest. The acceleration changes from static to gradually increasing. The angular velocity changes, and the angle of rotation along the shoulder joint reaches the target threshold. After detecting the arm-raising action, the system starts a timer to record the duration of the action. If the arm remains in the raised position for more than a preset time (such as 2 seconds), the voice input mode is triggered. Timing can distinguish between short arm raising (such as scratching, adjusting clothing) and intentional long arm raising. The duration threshold can be adjusted according to the actual usage scenario: shorter than 1 second: may be triggered by mistake. Longer than 5 seconds: the user may feel tired or inconvenient. The patient raises his wrist and keeps it near his mouth for 3 seconds. The system records the start time of arm raising and confirms the triggering of voice mode after 3 seconds. After the arm raising action and holding time meet the conditions, the wristband terminal device activates the built-in microphone. At the same time, the patient is notified through voice prompts or vibration feedback that voice input can be started. The system captures the patient's voice input (such as diet records, medication status). The voice content is converted into text through voice recognition, and effective information is extracted. Therefore, the arm raising action is a natural action for the patient, without the need for additional learning or reliance on complex instructions. Holding time judgment effectively distinguishes intentional operation from unintentional hand raising. Arm raising triggers voice collection, reduces waiting time, and improves data entry efficiency. It does not rely on the patient's language ability or cultural background and is suitable for a wide range of people.

[0054] In some examples, the wearable smart terminal device is a wristband-type smart terminal device, and the wristband-type smart terminal device is used to be worn on the dominant limb side of the patient, and the method further includes:

[0055] Acquiring arm posture information of a patient belonging to the wearable intelligent terminal device through the wearable intelligent terminal device;

[0056] When it is predicted that the patient is in an eating posture based on the arm posture information, a water intake reminder message is generated to prompt the patient to record the eating behavior.

[0057] It is understandable that the wristband-type smart terminal device is not only used to monitor the patient's arm posture, but also automatically determines whether the patient is in a state of eating through posture recognition and behavior prediction technology, and generates a water intake reminder message when necessary. Arm posture data is collected by wearing a smart wristband on the dominant limb (such as the right wristband). Posture information is usually provided in real time by the built-in inertial measurement unit (IMU), including: Accelerometer: detects the movement acceleration of the arm. Gyroscope: captures the angular velocity and posture changes of the arm. Magnetometer: provides spatial direction data of the arm. These data combinations can reflect the position and movement characteristics of the patient's arm. Eating behavior is usually accompanied by a series of specific actions, such as: moving the hand from the dining table to the mouth. Staying briefly near the mouth (such as eating or drinking water). Repeating the above actions for many times. By analyzing the changing trajectory of the arm posture, the smart wristband can predict whether the patient is in a state of eating. When the system determines that the patient is in a state of eating, it automatically generates a reminder message to prompt the patient to record dietary information, especially liquid intake. Through this function, the omission of dietary data caused by forgetfulness or neglect of patients can be effectively reduced.

[0058] Exemplarily, a wristband smart device is worn on the patient's dominant limb (such as the right hand). The built-in IMU collects acceleration, angular velocity and direction data in real time. For example, acceleration values ​​(X, Y, Z axis). Angular velocity values ​​(rotation around X, Y, Z axis). Spatial direction values ​​(calculated by a magnetometer). The system samples the patient's arm posture data in real time, and the frequency is usually between 50Hz and 100Hz. Eating posture recognition, arm lifting: moving from a lower position (such as a dining table or both sides of the body) to near the mouth. Dwelling time: The arm remains near the mouth for 2 to 5 seconds. Repeated action: There are multiple similar eating or drinking actions within a period of time. Machine learning-based classifiers (such as decision trees, support vector machines, neural networks): Input: multi-dimensional posture data collected by IMU. Output: Is it an eating posture? Feature extraction: curve features of acceleration and angular velocity changes. The spatial position of the starting point (dining table) and end point (mouth) of the action. Example data processing: The patient moves his hand from the dining table to his mouth. The IMU data may be as follows: Acceleration change: gradually increases to a peak value (such as +2m / s 2), and then slowly decreases. Angular velocity change: Reaching the peak value of rotation in a short time (such as 30° / s). Short stay: The hand is kept near the mouth for about 3 seconds. Result judgment: Based on the above data, the classification model outputs the judgment "eating posture". The eating posture recognition result is "true". The action occurs at a long time interval (such as not recording drinking or eating for several minutes). Prompt the patient to record the amount of liquid intake: "It is detected that you are drinking or eating, please record your intake." Provide voice or vibration prompts to guide the patient to start voice input. The prompt method may include: vibration feedback: the wristband vibrates to attract attention; voice prompt: the smart wristband issues an audio reminder. Therefore, the patient's eating status can be effectively judged through arm posture and behavior prediction. Action recognition based on machine learning models can adapt to the behavior patterns of different patients. Prompt patients to record their liquid intake to reduce the problem of incomplete data caused by forgetting. There is no need for patients to take the initiative to operate, and the system automatically generates prompts to reduce additional burden. Instant prompts for drinking behavior, without waiting for manual recording at a fixed time point.

[0059] In some examples, this also includes:

[0060] Monitoring the positional relationship between the wearable intelligent terminal device and the ward toilet;

[0061] Determine the current distance between the two based on the positional relationship, and if the current distance is less than the budgeted distance, collect flushing control information of the toilet;

[0062] When a flushing control instruction of the toilet is acquired, a current water seal height of the toilet is acquired to determine the excretion volume of the patient based on the current water seal height and a basic water seal height of the toilet;

[0063] The flushing control instruction is executed after the current water seal height of the toilet is acquired.

[0064] It is understandable that the smart wristband terminal automatically monitors the patient's excretion behavior and estimates the amount of excretion by combining positioning technology with the intelligent control system of the ward toilet. This method avoids the shortcomings of traditional manual recording and improves the accuracy and timeliness of data.

[0065] For example, the distance between the wearable device and the toilet can be used to determine whether the patient is using the toilet. Common positioning technologies include: Bluetooth beacon: The toilet has a built-in Bluetooth transmitter, and the wristband device receives the signal strength (RSSI) to determine the distance. Ultra-wideband (UWB): High-precision positioning technology that can achieve centimeter-level distance measurement. Wi-Fi or other signals: If the toilet and the wristband are both connected to the Internet, the position relationship can be detected based on wireless signals.

[0066] For example, the smart toilet has a built-in flushing control system that can collect flushing behavior and record relevant data through sensors: Flush instruction: determine whether the flushing behavior has been executed. Water seal height monitoring: monitor the change of the water seal height in the toilet in real time through the water level sensor.

[0067] For example, by comparing the difference in water seal height before and after flushing, the patient's excretion volume can be estimated: basic water seal height: the standard water seal height when the toilet is in a static state; current water seal height: the water seal height after excretion is completed and before flushing; perform excretion volume calculation.

[0068] Exemplarily, a Bluetooth Beacon, UWB module or water seal height sensor is installed on the toilet in the ward. The wristband device is bound to the toilet and records the signal characteristics of the toilet. The wristband device receives the positioning signal of the toilet and calculates the distance in real time. If the distance is less than the set threshold (such as 1 meter), the system determines that the patient is close to or using the toilet. For example, the wristband receives the Bluetooth signal of the toilet, and the RSSI value is -50dBm (corresponding to a distance of 0.8 meters), and it is determined that the patient has entered the toilet use area. After the patient uses the toilet, the flushing system will generate a control signal (such as through a physical button, foot pedal or automatic sensing). The wristband device monitors the flushing signal emitted by the toilet in real time to confirm the flushing behavior. When the flushing signal is not detected, the excretion calculation is not performed. If the flushing signal is collected, the water seal height data continues to be obtained. The water seal height is obtained and the excretion is calculated. For example, the toilet has a built-in water level sensor to record the current water seal height before flushing. The basic water seal height is obtained through initial calibration as a reference value. The system calls the discharge volume calculation model to convert the change in water seal height into a volume estimate. Discharge volume = k × (current water seal height - basic water seal height), k is the conversion coefficient, which is determined according to the specific structure of the toilet and the calibration results. For example, the basic water seal height is 10 cm, the current water seal height is 15 cm, k = 0.8 (the fitting coefficient of the toilet discharge volume and the water seal height difference), discharge volume: 0.8 × (15-10) = 4. After calculating the discharge volume, the toilet flushing instruction is automatically triggered, and the flushing behavior ensures hygiene. At the same time, the data of the water seal sensor is cleared to prepare for the next use. As a result, from distance monitoring to flushing control, there is no need for manual recording by patients or intervention by medical staff. The discharge volume data is automatically uploaded to the liquid input and output management system. The change in water seal height directly reflects the discharge volume, reducing subjective estimation errors. The water level sensor and calibration model further improve the calculation accuracy. Real-time monitoring of position and behavior ensures timely update of data. No need to rely on manual records by nurses.

[0069] In some examples, this also includes:

[0070] Determine the current distance between the two based on the positional relationship, and if the current distance is less than the estimated distance, collect audio information in the toilet;

[0071] determining the type of the patient's excrement based on the audio information;

[0072] determining a water content of the feces based on the type of the feces;

[0073] The water excretion is calculated based on the water content of the excrement and the excretion amount.

[0074] It is understandable that by collecting audio information from the smart toilet, the type of patient's excrement (such as urine or feces) can be further determined, and combined with the water content information of the excrement, the patient's water discharge can be accurately calculated. The built-in microphone in the toilet collects audio information, and the type of excrement is determined by analyzing the characteristics of the audio signal. For example, the audio characteristics of urine excretion are: strong persistence, stable audio frequency, and low amplitude. The sound has a "fluidity" characteristic, and usually collides with the water surface to form a sound similar to dripping or flowing water. Audio characteristics of fecal excretion: short and irregular, large amplitude changes, and a wide frequency range. The sound has a "block impact" characteristic, which may be accompanied by bubble sounds or water surface impact sounds. Through audio spectrum analysis (such as Fourier transform or wavelet transform), these features can be extracted and input into the machine learning model for classification. The water content of different types of excrement is significantly different, and human medical data can be referred to: Urine: The water content is as high as 98% to 99%. Feces: The water content is usually 60% to 80%, and the water content can be as high as 90% or more during diarrhea. Combining the audio analysis results with the water content range corresponding to the type, the water content of the excrement is further calculated. The water discharge is calculated by combining the excretion volume (calculated by the water seal height) and the water content of the excrement: water discharge = excretion volume × water content of excrement. This calculation result can more accurately reflect the patient's fluid loss and help medical staff assess the patient's water balance.

[0075] Exemplarily, the distance between the wearable smart terminal device and the toilet is less than the budgeted distance (such as 1 meter), and it is determined that the patient is using the toilet. Activate the built-in microphone of the toilet and start collecting audio. Divide the continuous audio into several time periods (such as 1 second) for real-time analysis. Determine the type of excrement based on the audio, and analyze the frequency distribution of the audio through Fourier transform. Urine audio: the frequency is concentrated in a narrow range (such as 100-500Hz) and the amplitude is relatively stable. Feces audio: the frequency distribution is wider (such as 50-2000Hz) and the amplitude varies greatly. Extract time features: urine is usually continuous audio. Feces may be short and irregular audio. Use support vector machine (SVM), random forest or deep learning model (such as convolutional neural network CNN) to train the classification model. Input: audio feature data (frequency, amplitude, duration, etc.). Output: excrement type (urine or feces). Map the water content range and determine the water content of the excrement based on the classification results: urine: the water content is set to 98% to 99%. Feces: The water content is set to 60% to 80%, and the specific value can be adjusted according to the patient's condition. For special cases such as diarrhea, the water content can be adjusted in combination with the doctor's settings or further analysis. Excretion volume is calculated by the height of the toilet water seal (such as 4 units of volume). Water content: determined according to the type of excrement (such as urine 99%). Calculation formula: Water discharge = excretion volume × water content, assuming excretion volume: 4 units of volume. Excrement type: urine (99% water content). Then the water discharge: 4×99%=3.96 units of water. Therefore, it is more scientific to accurately classify the type of excrement through audio analysis than to rely on the patient's subjective description. The combination of excretion volume and water content provides more accurate water discharge data. Automatically complete excrement detection and analysis without the intervention of patients or medical staff. Real-time calculation and recording to improve the timeliness of data. Excretion type and water discharge are updated in real time to support dynamic fluid balance assessment.

[0076] In some examples, this also includes:

[0077] The water intake or water output is sent to a hospital diagnosis and treatment system or a medical care terminal associated with the patient.

[0078] In some examples, this also includes:

[0079] The patient's fluid intake and output data within 24 hours are analyzed, and an alarm message is generated when the fluid intake and output data exceeds a normal range.

[0080] See also Figure 2 , an embodiment of the patient status information monitoring device in the embodiment of the present application may include:

[0081] An acquisition unit 21 is used to acquire a voice recording input request of a patient belonging to the wearable intelligent terminal device through the wearable intelligent terminal device;

[0082] An analyzing unit 22, configured to collect valid voice information of the patient based on the voice recording input request, wherein the valid voice information includes a type of diet and a diet amount;

[0083] The evaluation unit 23 is used to query the water content associated with the food type to evaluate the patient's water intake based on the water content and the food amount.

[0084] In summary, the patient status information monitoring device provided in the embodiment of the present application obtains a voice recording input request of the patient to which the device belongs through a wearable intelligent terminal device; based on the voice recording input request, the patient's valid voice information is collected, and the valid voice information includes the type of diet and the amount of diet; the water content associated with the type of diet is queried to evaluate the patient's water intake based on the water content and the amount of diet. Thus, the dietary information is automatically recorded to reduce the error of the patient's reliance on recollection. Based on database calculation, the inaccuracy of subjective estimation is avoided. Wearable devices support real-time collection and data updates quickly. Avoid the lag of fixed time recording. Voice input is natural and smooth, without manual recording. Reduce the workload of nurses and patients and improve compliance. The database can be continuously expanded to support more types of food. The system can be combined with other data (such as urine volume, weight) for comprehensive analysis. It reduces the burden on patients and medical staff and provides a more scientific and efficient solution for the management of fluid intake and output balance.

[0085] like Figure 3 As shown, the embodiment of the present application further provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 320 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any of the above-mentioned methods for supervising patient status information are implemented:

[0086] Obtaining, through a wearable intelligent terminal device, a voice recording input request from a patient to whom the device belongs;

[0087] Collecting valid voice information of the patient based on the voice record input request, wherein the valid voice information includes the type and amount of food consumed;

[0088] The water content associated with the food type is queried to evaluate the patient's water intake based on the water content and the food amount.

[0089] Since the electronic device introduced in this embodiment is a device used to implement a patient status information monitoring device in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation method of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0090] In the specific implementation process, when the computer program 311 is executed by the processor, it can achieve Figure 1 Any implementation method in the corresponding embodiment:

[0091] Obtaining, through a wearable intelligent terminal device, a voice recording input request from a patient to whom the device belongs;

[0092] Collecting valid voice information of the patient based on the voice record input request, wherein the valid voice information includes the type and amount of food consumed;

[0093] The water content associated with the food type is queried to evaluate the patient's water intake based on the water content and the food amount.

[0094] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0095] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0096] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0099] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device is caused to execute the following Figure 1 The process of patient status information supervision in the corresponding embodiment.

[0100] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0101] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0102] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0105] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0106] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A patient status information supervision method, characterized in that: include: Obtaining, through a wearable intelligent terminal device, a voice recording input request from a patient to whom the device belongs; Collecting valid voice information of the patient based on the voice record input request, wherein the valid voice information includes the type and amount of food consumed; The water content associated with the food type is queried to evaluate the patient's water intake based on the water content and the food amount.

2. The method according to claim 1, characterized in that The wearable intelligent terminal device is a wristband-type intelligent terminal device, and obtaining a voice recording input request of a patient to which the wearable intelligent terminal device belongs through the wearable intelligent terminal device includes: Acquiring arm posture information of a patient belonging to the wearable intelligent terminal device through the wearable intelligent terminal device; In a case where it is determined based on the arm posture information that the patient performs an arm-raising action, recording a holding time of the arm-raising action; When the holding time is greater than a preset time, the arm raising action is identified as a voice recording input request to simultaneously collect voice information.

3. The method according to claim 1, characterized in that The wearable smart terminal device is a wristband-type smart terminal device, and the wristband-type smart terminal device is used to be worn on the dominant limb side of the patient. The method further includes: Acquiring arm posture information of a patient belonging to the wearable intelligent terminal device through the wearable intelligent terminal device; When it is predicted that the patient is in an eating posture based on the arm posture information, a water intake reminder message is generated to prompt the patient to record the eating behavior.

4. The method according to claim 1, characterized in that Also includes: Monitoring the positional relationship between the wearable intelligent terminal device and the ward toilet; Determine the current distance between the two based on the positional relationship, and if the current distance is less than the budgeted distance, collect flushing control information of the toilet; When a flushing control instruction of the toilet is acquired, a current water seal height of the toilet is acquired to determine the excretion volume of the patient based on the current water seal height and a basic water seal height of the toilet; The flushing control instruction is executed after the current water seal height of the toilet is acquired.

5. The method according to claim 4, characterized in that Also includes: Determine the current distance between the two based on the positional relationship, and if the current distance is less than the estimated distance, collect audio information in the toilet; determining the type of the patient's excrement based on the audio information; determining a water content of the feces based on the type of the feces; The water excretion is calculated based on the water content of the excrement and the excretion amount.

6. The method according to any one of claims 1 to 5, characterized in that Also includes: The water intake or water output is sent to a hospital diagnosis and treatment system or a medical care terminal associated with the patient.

7. The method according to any one of claims 1 to 5, characterized in that Also includes: The patient's fluid intake and output data within 24 hours are analyzed, and an alarm message is generated when the fluid intake and output data exceeds a normal range.

8. A patient status information monitoring device, characterized in that: include: An acquisition unit, used for acquiring a voice recording input request of a patient belonging to the wearable intelligent terminal device through the wearable intelligent terminal device; An analyzing unit, configured to collect valid voice information of the patient based on the voice recording input request, wherein the valid voice information includes a type of diet and a diet amount; The evaluation unit is used to query the water content associated with the food type to evaluate the patient's water intake based on the water content and the food amount.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the patient status information monitoring method as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the patient status information supervision method according to any one of claims 1 to 7 is implemented.

Images