A medical monitoring method based on multimodal prompt interaction

Abstract

The present invention discloses a medical monitoring method based on multimodal prompt interaction, comprising: obtaining vital sign data of a patient, scoring and sorting the data according to patient information and vital sign data to obtain a patient monitoring score, and forming a patient monitoring sequence; obtaining business capability data, current workload, and location data of medical staff, sorting and scoring the data according to the business capability data, current workload, and location data of the medical staff to obtain a medical staff status score, and forming a medical staff allocation sequence; selecting the best medical staff in the medical staff allocation queue according to the priority order of the patients in the patient monitoring queue; generating a multimodal prompt strategy according to the patient monitoring score, and providing a multimodal prompt to the selected best medical staff according to the multimodal prompt strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of medical monitoring, and in particular to a medical monitoring method based on multimodal prompt interaction. Background Art

[0002] In the inpatient departments and intensive care units (ICUs) of modern hospitals, medical staff need to monitor the vital signs of multiple patients (such as heart rate, blood pressure, blood oxygen saturation, and respiratory rate) at the same time to ensure their safety.

[0003] However, with the popularization of medical equipment and the increase in the number of patients, the corresponding medical staff resources are obviously insufficient. Although existing technologies can remotely prompt and notify medical staff through centralized medical care systems, the current medical monitoring system mainly relies on central visual (such as monitor display) and auditory (such as alarm sound) prompts. This single prompt method can easily lead to information overload, especially when multiple patients issue alarms at the same time, the vision and hearing of medical staff are occupied. In particular, when medical staff are performing other tasks (such as emergency care, equipment operation), they may not notice the alarm information in time. Since the existing system mainly relies on vision and hearing, the cognitive load of medical staff will increase significantly, further reducing the response speed and accuracy to alarm information.

[0004] Furthermore, in multi-patient, multi-task scenarios, existing systems often fail to effectively prioritize alarms and lack a graded alert strategy tailored to the importance of different patients and the urgency of alarms. This can prevent medical staff from receiving critical alarm information in a timely manner. Furthermore, existing systems often employ simple first-come, first-served or fixed rules when processing alarms, failing to fully consider the priority of alarms and the importance of patients. This can lead to irrational resource allocation and delays in handling high-priority patients.

[0005] The purpose of this invention is to design a medical monitoring method based on multimodal prompt interaction in response to the above-mentioned problems in the prior art. Summary of the Invention

[0006] In view of this, the purpose of the present invention is to propose a medical monitoring method based on multimodal prompt interaction, which can solve the above problems.

[0007] The present invention provides a medical monitoring method based on multimodal prompt interaction, comprising:

[0008] Obtain the patient's vital signs data, score and sort them according to the patient information and vital signs data, obtain the patient monitoring score, and form a patient monitoring sequence;

[0009] Obtaining the medical staff's professional ability data, current workload, and location data, sorting and scoring them based on the medical staff's professional ability data, current workload, and location data to obtain the medical staff's status score and form a medical staff allocation sequence;

[0010] Select the best medical staff in the medical staff allocation queue based on the priority order of the patients in the patient monitoring queue;

[0011] A multimodal prompt strategy is generated according to the patient monitoring score, and multimodal prompts are provided to the selected optimal medical staff according to the multimodal prompt strategy.

[0012] Furthermore, the patient's vital signs data is obtained, and scoring and sorting are performed according to the patient information and the vital signs data to obtain a patient monitoring score, thereby forming a patient monitoring sequence. The steps include:

[0013] Obtain the patient's real-time heart rate data, blood pressure data, blood oxygen saturation data, respiratory rate data, and body temperature;

[0014] Through the patient's real-time heart rate data , blood pressure data , blood oxygen saturation data , respiratory rate data ,body temperature Calculate the patient's physical sign score for each indicator ;

[0015] Calculate the patient's monitoring score by the patient's physical sign score of each indicator , the specific calculation formula is as follows:

[0016] ,

[0017] in, is the weight of the corresponding indicator;

[0018] Obtain the patient's medical history data and use the patient's medical history data to mark the key monitoring vital signs data. The specific calculation formula is as follows:

[0019] ,

[0020] in, For medical history correction items, is the global weight coefficient of the impact of medical history.

[0021] Furthermore, the patient's real-time heart rate data , blood pressure data , blood oxygen saturation data , respiratory rate data ,body temperature Calculate the patient's physical sign score for each indicator include:

[0022] The sign scoring formula for heart rate data is: ;

[0023] The physical sign scoring formula for blood pressure data is: ;

[0024] The physical sign scoring formula for blood oxygen saturation data is: ;

[0025] The sign scoring formula for respiratory rate data is: ;

[0026] The physical sign scoring formula for body temperature data is: .

[0027] Furthermore, the patient's monitoring score is calculated by the patient's physical sign score of each indicator include:

[0028] If three consecutive indicator measurements satisfy |Δv / Δt|≥10%, where Δv is the change in the vital sign value and Δt is the time interval, the weight is adjusted using the weight adjustment formula, which is as follows:

[0029] ,

[0030] in, is the width of the normal range of each indicator.

[0031] Furthermore, the calculation formula of the medical history correction item is as follows:

[0032] ,

[0033] in, k is the medical history type and related signs The enhancement factor, is the sign score associated with medical history k, is the baseline risk addition for medical history k, and n is the total number of medical history types the patient has.

[0034] Furthermore, the obtaining of the medical personnel's professional capability data, current workload, and location data, sorting and scoring the medical personnel's professional capability data, current workload, and location data to obtain a medical personnel status score, and forming a medical personnel allocation sequence includes:

[0035] Calculate the compatibility A between medical staff’s professional capability data and patient medical record data through the semantic similarity model;

[0036] Calculate the current workload U of medical staff based on the current number of tasks and working hours of medical staff;

[0037] The medical staff's moving distance d and the required equipment preparation time Calculate the path cost C from the current location to the patient's location using the following formula:

[0038] ,

[0039] in, 、 are the moving distance d and the required equipment preparation time respectively The corresponding weight;

[0040] Calculate the medical staff status score based on data adaptability A, previous workload U, and path cost C , the calculation formula is as follows:

[0041] ;

[0042] S205 The medical staff status scores form a medical staff allocation sequence from high to low.

[0043] Furthermore, the calculation of the current workload U of the medical staff according to the current number of tasks and working hours of the medical staff includes:

[0044] Get the current task data volume of medical staff current_tasks and the maximum number of tasks they can carry max_capacity;

[0045] Get the continuous working time t, and calculate the current workload U based on the current task data volume current_tasks of the medical staff, the maximum number of tasks it can carry max_capacity, and the continuous working time t. The calculation formula is as follows:

[0046] .

[0047] Furthermore, selecting the best medical staff in the medical staff allocation queue according to the priority order of the patients in the patient monitoring queue includes:

[0048] Selecting several patients with the highest priority from the patient monitoring sequence to form a patient sequence to be assigned;

[0049] Treat each patient in the assigned patient sequence , traverse all medical staff in the medical staff allocation sequence , calculate the score of each patient-medical staff combination, and correct the score of each patient-medical staff combination by distance , the calculation formula is as follows:

[0050] ,

[0051] in, For patients The guardianship score, For medical staff Status score, For patients and medical care The physical distance between is the distance attenuation coefficient, is the distance correction factor;

[0052] The scores of each patient-medical staff combination are formed into a combination score matrix, and the patient-medical staff combination score that maximizes the global total score is selected to obtain an allocation table.

[0053] Furthermore, generating a multimodal prompting strategy based on the patient monitoring score and providing a multimodal prompting to the selected optimal medical staff according to the multimodal prompting strategy includes:

[0054] According to the allocation table, specific task prompts are generated for each medical staff member, and the task prompts include: basic information of the patient, abnormal physical signs, and urgency level;

[0055] Patient monitoring score Determine the prompt level and prompt the corresponding medical staff according to the prompt level.

[0056] Furthermore, the patient's monitoring score Determine the prompt level. The corresponding medical staff are prompted according to the prompt level, including:

[0057] like If the alert level is ≥4, it is extremely dangerous and a high-intensity vibration reminder will be issued through the wearable device. If the medical staff does not respond, a red light will flash quickly and a high-volume multi-frequency beep will be issued. The task prompt and monitoring confirmation will be displayed on the screen;

[0058] If 2.5≤ If the risk is less than 4, the alert level is high-risk and the wearable device will vibrate with medium intensity to remind you. If the medical staff does not respond, the device will flash an orange light and beep intermittently at a medium volume. The screen will also display task prompts and monitoring confirmation.

[0059] If 1.5≤ If the value is less than 2.5, the alert level is medium-risk, and the wearable device will vibrate briefly at a low frequency to remind you. If the medical staff does not respond, the device will flash a yellow light slowly and give a single low-volume reminder. The screen will also display task prompts and monitoring confirmation.

[0060] like 1.5 is a general alert level, with vibration reminders through wearable devices and task prompts and monitoring confirmations displayed on the screen.

[0061] Beneficial effects of the present invention:

[0062] First, by introducing a multi-parameter dynamic scoring formula for vital signs, combined with correction of past medical history and adaptive weighting mechanism, we solved the problems of difficulty in objectively grading patient risks, unresponsiveness to the trend of worsening condition, and easy omission of key patients. We achieved quantitative and refined risk management of the patient's criticality, greatly improved the efficiency of identifying high-risk patients, and enhanced the scientific and intelligent level of monitoring.

[0063] Secondly, the use of semantic adaptive deep models, multi-parameter load and real-time physical location information comprehensive scoring solves the problems of medical care allocation based only on professional expertise, ignoring load and fatigue, slow response, and unfair distribution. It achieves priority for the most suitable medical care, dynamic balance of resources, and priority for the fastest responding, least fatigued, and most professional personnel, thereby improving team work efficiency and safety.

[0064] Third, by establishing a multi-parameter linkage matching model of criticality × medical status × distance attenuation and introducing an optimization algorithm, we solved the problems of resource waste, allocation conflicts, and critically ill patients not being given priority treatment due to traditional single-factor allocation decisions, achieved global optimal medical resource scheduling, maximized rescue efficiency, ensured priority for key patients, and kept the entire process traceable.

[0065] Fourth, through multimodal graded warning (vibration, light, sound, screen), step-by-step upgrade and task confirmation mechanism, problems such as easily missed alarms, medical staff alarm fatigue, no closed-loop traceability of tasks, and low efficiency of warning transmission in special scenarios are solved. This reduces the probability of false alarms / missed alarms, ensures the closed loop of task handling, direct warning to medical staff, and facilitates operation, significantly improving patient safety and information traceability. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0067] Figure 1 It is a flow chart of the method of this embodiment. DETAILED DESCRIPTION

[0068] To facilitate understanding by those skilled in the art, the structure of the present invention will now be further described in detail with reference to the embodiments and accompanying drawings. It should be understood that the steps mentioned in this embodiment, unless otherwise specified, can be adjusted in sequence according to actual needs, and can even be executed simultaneously or partially simultaneously.

[0069] like Figure 1 As shown, an embodiment of the present invention provides a medical monitoring method based on multimodal prompt interaction, including:

[0070] S1 obtains the patient's vital signs data, scores and sorts them according to the patient information and vital signs data, obtains the patient monitoring score, and forms a patient monitoring sequence;

[0071] S101 obtains the patient's real-time heart rate data, blood pressure data, blood oxygen saturation data, respiratory rate data, and body temperature;

[0072] S102 uses the patient's real-time heart rate data , blood pressure data , blood oxygen saturation data , respiratory rate data ,body temperature Calculate the patient's physical sign score for each indicator ;

[0073] The physical sign scoring formula for S1021 heart rate data is: ;

[0074] The physical sign scoring formula for S1022 blood pressure data is: ;

[0075] The physical sign scoring formula for S1023 blood oxygen saturation data is: ;

[0076] The formula for the physical sign scoring of S1024 respiratory rate data is: ;

[0077] The physical sign scoring formula for S1025 body temperature data is: ;

[0078] In this step, a scoring function for each indicator is constructed using the normal range. The median of the normal heart rate range of 60-100 bpm, 80, is used as the reference point, with the numerator reflecting the actual deviation. The radius of the normal range (100-60 = 40, with a half-width of 20), indicates that every 20 bpm deviation from the median is worth 1 point. 90 mmHg is the threshold for hypotension (the shock risk threshold), while 50 covers the common pathological range (e.g., a hypertensive crisis ≥180 mmHg is worth 1.8 points). A blood oxygen saturation of ≤94% triggers a hypoxic alarm. The normal respiratory rate range is 12-20 breaths / minute, with the median of 16 used as the reference point. The standard human body temperature is 36-37.5°C; a value above 36.5°C indicates either excessive or excessive hypothermia.

[0079] S103 calculates the patient's monitoring score based on the patient's physical sign score for each indicator , the specific calculation formula is as follows:

[0080] ,

[0081] in, is the weight of the corresponding indicator.

[0082] Furthermore, if three consecutive indicator measurements satisfy |Δv / Δt|≥10%, where Δv is the change in the vital sign value and Δt is the time interval, the weight is adjusted using the weight adjustment formula, which is as follows:

[0083] ,

[0084] in, is the width of the normal range of each indicator.

[0085] In this step, if the heart rate changes from 80 to 100 (Δv=20Δv=20) within 5 minutes, the adjustment factor is 1+20 / 40=1.5, and the weight changes from 0.25 to 0.375. Three consecutive measurements can avoid occasional noise interference (such as false hypotension caused by probe displacement), and |Δv / Δt|≥10% ensures that only significant trend changes are responded to. In addition, the weight increase limit designed in this way (such as ≤0.5) to prevent a single indicator from monopolizing the score, and the weight attenuation lower limit (such as ≥0.05) to avoid indicator failure.

[0086] Blood oxygen is directly related to tissue oxygenation, and hypoxia of 5 minutes can cause irreversible damage, so it has the highest weight. Heart rate is the risk of cardiac arrest, and the golden rescue time is only 4-6 minutes, so it has a secondary weight. Respiratory rate drops earlier than blood oxygen, but is easily disturbed by subjective factors (such as pain). Body temperature changes slowly, mostly reflecting chronic pathological processes, lagging behind the core pathological process, and has the lowest weight. The weight corresponding to blood pressure can be dynamically adjusted. For example, if it drops by 20% within 10 minutes, the weight is increased to 0.30. As shown in Table 1, the basic weight corresponding to the score of each indicator can be designed as follows:

[0087] Table 1 Normal range and basic weight of each indicator

[0088]

[0089] S104 obtains the patient's medical history data and marks the key monitoring vital signs data with the patient's medical history data. The specific calculation formula is as follows:

[0090] ,

[0091] in, For medical history correction items, is the global weight coefficient of the impact of medical history.

[0092] In this step, It is a medical history correction item, which reflects the additional risk of monitoring needs caused by a specific medical history. It is the global weight coefficient of the impact of medical history, with a default value of 1.0, which increases to 1.5 when there is a medical history.

[0093] The calculation formula of the medical history correction item is as follows:

[0094] ,

[0095] in, k is the medical history type and related signs The enhancement factor, is the sign score associated with medical history k, is the baseline risk addition for medical history k, and n is the total number of medical history types the patient has.

[0096] In this step, the medical history type k is related to the physical signs The enhancement factor is based on clinical research evidence. Based on the corresponding physical sign scoring formula in the previous step, the baseline risk addition for medical history k can reflect the default risk of chronic diseases. The risk-weighted formula for medical history accurately reflects the risks of chronic underlying diseases and significant past medical history in the score.

[0097] S2 obtains the medical staff's professional ability data, current workload, and location data, sorts and scores them according to the medical staff's professional ability data, current workload, and location data, obtains the medical staff status score, and forms a medical staff allocation sequence;

[0098] S201 calculates the compatibility A between the medical staff's business capability data and the patient's medical record data through a semantic similarity model;

[0099] In this step, traditional methods rely on manual matching and rigid rules, which is both inefficient and difficult to reflect knowledge extension. It's impossible to determine the compatibility of different professional descriptions (such as "myocardial infarction" and "coronary syndrome") based solely on keywords. To retrieve professional competency data such as medical staff's professional experience and expertise, a pre-trained semantic similarity model, such as the BERT model, can be used to determine the compatibility A between the professional competency data and the patient's medical record data for each experience item. The value range is generally [0, 1]. BERT (Bidirectional Encoder Representations from Transformers) is a pre-trained deep language model based on the Transformer architecture. It can understand and represent complex semantic relationships in natural language and supports multi-granularity expressions such as "word, sentence, phrase, and document." Medical specialties are typically short text (such as "cardiovascular medicine," "emergency critical care," and "respiratory disease"). Case types are also short text (such as "myocardial infarction," "lung infection," and "arrhythmia"). BERT can understand synonyms, near-synonyms, technical terms, abbreviations, and the transition between long and short sentences. For example, "myocardial infarction" and "acute coronary syndrome" can be highly similar, even with different terms. This allows for automatic, dynamic, and accurate assessment of each healthcare professional's suitability for a specific case.

[0100] S202 calculates the current workload U of the medical staff based on the current number of tasks and working hours of the medical staff;

[0101] S2021 obtains the current task data volume current_tasks of the medical staff and the maximum number of tasks that can be carried max_capacity;

[0102] S2022 obtains the continuous working time t, and calculates the current workload U based on the current task data volume current_tasks of the medical staff, the maximum number of tasks that can be carried max_capacity, and the continuous working time t. The calculation formula is as follows:

[0103] ;

[0104] In this step, the traditional allocation mechanism only considers whether the order can be accepted, without considering the problem of accumulated fatigue of medical staff and the increased risk after continuous high-intensity work, which can easily lead to overwork and medical safety hazards. When U is closer to 1, it means the load is very heavy. Reflects the fatigue overflow caused by long working hours and objectively quantifies the current "busyness / fatigue level" of medical staff.

[0105] S203 is based on the medical staff's moving distance d and the required equipment preparation time Calculate the path cost C from the current location to the patient's location using the following formula:

[0106] ,

[0107] in, 、 are the moving distance d and the required equipment preparation time respectively The corresponding weight;

[0108] In this step, the physical arrival efficiency of different medical staff is not traditionally dynamically weighed, and the time required for equipment preparation before special operations is rarely considered. Therefore, "medical staff with high skills but the longest distance / preparation" may be assigned, resulting in response delays. The medical staff's travel distance d represents the distance between the medical staff's current location and the location of the patient to be assigned, usually in meters. The longer the distance, the slower the medical staff will reach the target patient, and the response time will deteriorate. Required equipment preparation time This value indicates the time required to prepare additional medical equipment (e.g., emergency vehicle, monitor, infusion pump, etc.) to complete the assigned task (e.g., first aid, specific intervention). If the patient is already fully equipped, this value can be zero. If equipment is required or configuration takes time, the value increases. A smaller C value indicates a faster response time and a greater likelihood of timely patient care. This improves first aid / rescue response efficiency and adapts to complex sites and clinical scenarios (e.g., large ICUs and pre-hospital emergency care).

[0109] S204 calculates the medical staff status score based on the data adaptability A, the previous workload U, and the path cost C , the calculation formula is as follows:

[0110] ;

[0111] S205 The medical staff status scores form a medical staff allocation sequence from high to low.

[0112] In this step, the larger A is, The larger the value, the more suitable the profession and the more capable the candidates are. The larger the value of U, the smaller the value of 1-U. A significant decrease indicates fatigue, overload, and a decrease in priority; the larger the C, The smaller the value, the higher the response cost and the lower the priority. The medical staff status score is evaluated by comprehensively considering the adaptability, load level, and fastest arrival time.

[0113] S3 selects the best medical staff in the medical staff allocation queue according to the priority order of the patients in the patient monitoring queue;

[0114] S301 selects several patients with the highest priority from the patient monitoring sequence to form a patient sequence to be assigned;

[0115] S302: Each patient in the patient sequence to be assigned , traverse all medical staff in the medical staff allocation sequence , calculate the score of each patient-medical staff combination, and correct the score of each patient-medical staff combination by distance , the calculation formula is as follows:

[0116] ,

[0117] in, For patients The guardianship score, For medical staff Status score, For patients and medical care The physical distance between is the distance attenuation coefficient, is the distance correction factor;

[0118] In this step, when resources are limited, how to dynamically narrow the dispatch scope that needs the most attention, avoid the interference of massive irrelevant data in the peak / emergency task allocation, and ensure the efficiency of batch dispatch and centralized allocation. Traditional medical care allocation generally only considers single factor allocation (such as pure criticality, pure distance, pure medical care status, etc.). Through steps S1 and S2, the patient can be calculated. Monitoring scores and medical staff Status scoring, quantified multiple parameters, and distance correction factors significantly shorten response time, ensuring rescue efficiency and patient safety.

[0119] S303 forms a combination score matrix with each patient-medical staff combination score, selects the patient-medical staff combination score that maximizes the global total score, and obtains an allocation table.

[0120] In this step, traditional medical care allocation only considers the maximum score or the nearest medical care, which can easily lead to conflicts or omissions of individual resources. The Hungarian optimization algorithm is used to support one-to-one optimal allocation, maximize the overall score, and achieve optimal nursing resource utilization at the team level.

[0121] S4 generates a multimodal prompt strategy based on the patient monitoring score, and provides multimodal prompts to the selected optimal medical staff according to the multimodal prompt strategy.

[0122] S401 generates a specific task prompt for each medical staff member according to the allocation table, wherein the task prompt includes: basic information of the patient, abnormal physical signs, and urgency;

[0123] S402 passes the patient's monitoring score Determine the prompt level and prompt the corresponding medical staff according to the prompt level;

[0124] S4021 If the alert level is ≥4, it is extremely dangerous and a high-intensity vibration reminder will be issued through the wearable device. If the medical staff does not respond, a red light will flash quickly and a high-volume multi-frequency beep will be issued. The task prompt and monitoring confirmation will be displayed on the screen;

[0125] S4022 if 2.5≤ If the risk is less than 4, the alert level is high-risk and the wearable device will vibrate with medium intensity to remind you. If the medical staff does not respond, the device will flash an orange light and beep intermittently at a medium volume. The screen will also display task prompts and monitoring confirmation.

[0126] S4023 if 1.5≤ If the value is less than 2.5, the alert level is medium-risk, and the wearable device will vibrate briefly at a low frequency to remind you. If the medical staff does not respond, the device will flash a yellow light slowly and give a single low-volume reminder. The screen will also display task prompts and monitoring confirmation.

[0127] S4024 1.5 is a general alert level, with vibration reminders through wearable devices and task prompts and monitoring confirmations displayed on the screen.

[0128] In this step, different patient risk stratifications (extreme, high, moderate, and general) correspond to different levels of alerts. This allows limited attention and resources to be focused on the people and issues most in need, avoiding the overwhelming distraction of all alerts and preventing the desensitization caused by "alarm fatigue." This ensures that truly critical situations are not overlooked. Requiring task prompts to be displayed on the screen and confirmed helps record operational traces, ensuring a closed-loop alarm system with documented evidence and improving medical safety and quality management.

[0129] Combining four alert methods—vibration, light, beep, and screen—maximizes the ability to mitigate environmental uncertainties (such as operating room noise, low lighting during night shifts, and inconspicuous screens). Through multi-sensory stimulation, medical staff are more likely to perceive alarms in complex scenarios and reduce missed alerts. A less impactful method (such as vibration) is initially employed, and only when medical staff fail to promptly acknowledge the situation is a more intense method escalated. This "soft first, strong later" strategy protects medical staff's focus (by preventing frequent, high-intensity interruptions) while ensuring critical situations are not missed.

[0130] Wearable devices can be worn on the wrists of medical staff. When medical staff are busy, walking, or operating, vibration and light signals can be sensed immediately. The skin on the wrist is sensitive, and vibration is highly sensitive and visible. Light prompts can be seen by lowering the head or raising the hand. Wearing it on the wrist can conveniently confirm tasks, browse messages, and operate buttons.

[0131] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 processor, or other programmable data processing device to produce 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 flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0135] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several distinct components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third etc. does not indicate any order. These words may be interpreted as names.

[0136] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0137] Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations fall within the scope of the claims and their equivalents, the present invention is intended to include such modifications and variations.

[0138] In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connect," "fixed," etc. should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0139] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms should not be understood as necessarily referring to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

Claims

1. A medical monitoring method based on multimodal prompt interaction, characterized in that: include: Obtain the patient's vital signs data, score and sort according to the patient information and vital signs data, obtain the patient monitoring score, and form the patient monitoring sequence. Specifically: Obtain the patient's real-time heart rate data, blood pressure data, blood oxygen saturation data, respiratory rate data, and body temperature; Through the patient's real-time heart rate data , blood pressure data , blood oxygen saturation data , respiratory rate data ,body temperature Calculate the patient's physical sign score for each indicator , specifically: The sign scoring formula for heart rate data is: ; The physical sign scoring formula for blood pressure data is: ; The physical sign scoring formula for blood oxygen saturation data is: ; The sign scoring formula for respiratory rate data is: ; The physical sign scoring formula for body temperature data is: ; Calculate the patient's monitoring score by the patient's physical sign score of each indicator , the specific calculation formula is as follows: ， in, is the weight of the corresponding indicator; Obtain the patient's medical history data and use the patient's medical history data to mark the key monitoring vital signs data. The specific calculation formula is as follows: ， in, For medical history correction items, is the global weight coefficient of the impact of medical history; Obtaining the medical staff's professional ability data, current workload, and location data, sorting and scoring them based on the medical staff's professional ability data, current workload, and location data to obtain the medical staff's status score and form a medical staff allocation sequence; Select the best medical staff in the medical staff allocation queue based on the priority order of the patients in the patient monitoring queue; A multimodal prompt strategy is generated according to the patient monitoring score, and multimodal prompts are provided to the selected optimal medical staff according to the multimodal prompt strategy.

2. A medical monitoring method based on multimodal prompt interaction according to claim 1, characterized in that: The patient's monitoring score is calculated by the patient's physical sign score of each indicator include: If three consecutive indicator measurements satisfy |Δv / Δt|≥10%, where Δv is the change in the vital sign value and Δt is the time interval, the weight is adjusted using the weight adjustment formula, which is as follows: ， in, is the width of the normal range of each indicator.

3. A medical monitoring method based on multimodal prompt interaction according to claim 1, characterized in that: The calculation formula of the medical history correction item is as follows: ， in, k is the medical history type and related signs The enhancement factor, is the sign score associated with medical history k, is the baseline risk addition for medical history k, and n is the total number of medical history types the patient has.

4. A medical monitoring method based on multimodal prompt interaction according to claim 1, characterized in that: The step of obtaining the medical staff's professional capability data, current workload, and location data, and sorting and scoring the medical staff's professional capability data, current workload, and location data to obtain a medical staff status score and form a medical staff allocation sequence includes: Calculate the compatibility A between medical staff’s professional capability data and patient medical record data through the semantic similarity model; Calculate the current workload U of medical staff based on the current number of tasks and working hours of medical staff; The medical staff's moving distance d and the required equipment preparation time Calculate the path cost C from the current location to the patient's location using the following formula: ， in, 、 are the moving distance d and the required equipment preparation time respectively The corresponding weight; Calculate the medical staff status score based on data adaptability A, previous workload U, and path cost C , the calculation formula is as follows: ； The medical staff status scores form a medical staff allocation sequence from high to low.

5. A medical monitoring method based on multimodal prompt interaction according to claim 4, characterized in that: The calculation of the current workload U of the medical staff according to the current number of tasks and working hours of the medical staff includes: Get the current task data volume of medical staff current_tasks and the maximum number of tasks they can carry max_capacity; Get the continuous working time t, and calculate the current workload U based on the current task data volume current_tasks of the medical staff, the maximum number of tasks it can carry max_capacity, and the continuous working time t. The calculation formula is as follows: 。 6. A medical monitoring method based on multimodal prompt interaction according to claim 1, characterized in that: The selecting of the best medical personnel in the medical personnel allocation queue according to the priority order of the patients in the patient monitoring queue includes: Selecting several patients with the highest priority from the patient monitoring sequence to form a patient sequence to be assigned; Treat each patient in the assigned patient sequence , traverse all medical staff in the medical staff allocation sequence , calculate the score of each patient-medical staff combination, and correct the score of each patient-medical staff combination by distance , the calculation formula is as follows: , in, For patients The guardianship score, For medical staff Status score, For patients and medical care The physical distance between is the distance attenuation coefficient, is the distance correction factor; The scores of each patient-medical staff combination are formed into a combination score matrix, and the patient-medical staff combination score that maximizes the global total score is selected to obtain an allocation table.

7. A medical monitoring method based on multimodal prompt interaction according to claim 6, characterized in that: Generating a multimodal prompt strategy based on the patient monitoring score and providing a multimodal prompt to the selected optimal medical staff according to the multimodal prompt strategy includes: According to the allocation table, specific task prompts are generated for each medical staff member, and the task prompts include: basic information of the patient, abnormal physical signs, and urgency level; Patient monitoring score Determine the prompt level and prompt the corresponding medical staff according to the prompt level.

8. A medical monitoring method based on multimodal prompt interaction according to claim 7, characterized in that: The patient's monitoring score Determine the prompt level. The corresponding medical staff include: like If the alert level is ≥4, it is extremely dangerous and a high-intensity vibration reminder will be issued through the wearable device. If the medical staff does not respond, a red light will flash quickly and a high-volume multi-frequency beep will be issued. The task prompt and monitoring confirmation will be displayed on the screen; If 2.5≤ If the risk is less than 4, the alert level is high-risk and the wearable device will vibrate with medium intensity to remind you. If the medical staff does not respond, the device will flash an orange light and beep intermittently at a medium volume. The screen will also display task prompts and monitoring confirmation. If 1.5≤ If the value is less than 2.5, the alert level is medium-risk, and the wearable device will vibrate briefly at a low frequency to remind you. If the medical staff does not respond, the device will flash a yellow light slowly and give a single low-volume reminder. The screen will also display task prompts and monitoring confirmation. like 1.5 is a general alert level, with vibration reminders through wearable devices and task prompts and monitoring confirmations displayed on the screen.

Images