Artificial intelligence nursing risk assessment robot, storage medium and computer equipment

Abstract

The invention provides an artificial intelligence nursing risk assessment robot, a storage medium and computer equipment, and relates to the technical field of nursing risk assessment, and the robot comprises a data collection module which is used for collecting multi-dimensional state data of a user; the knowledge base system is used for performing nursing risk assessment according to the medical records of the user to obtain nursing risk point knowledge; the intelligent analysis engine is used for traversing nursing risk point knowledge based on the multi-dimensional state data of the user to carry out risk level analysis to obtain a risk assessment level, and the risk assessment level has a risk point knowledge tag and an intervention scheme tag; and the interactive interface is used for uploading the risk assessment level, the risk point knowledge tag and the intervention scheme tag to medical staff. The technical problems that in the prior art, nursing risk assessment often depends on data information of a single source, so that the accuracy and timeliness of assessment are insufficient, a nursing scheme is often based on a universal template, the individual difference of each patient is difficult to meet, and the nursing effect is poor are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of nursing risk assessment, and particularly to an artificial intelligence nursing risk assessment robot, a storage medium and a computer device. Background Art

[0002] Patient care work in places such as hospitals, nursing homes, and home care needs to handle complex conditions and diverse nursing needs. A nursing risk assessment robot can help medical staff evaluate the nursing risks of patients under dynamic monitoring and propose timely intervention measures.

[0003] There are many limitations in the nursing risk assessment of the prior art. First, traditional nursing risk assessment often relies on data information from a single source and cannot comprehensively reflect the comprehensive health status of patients, which limits the accuracy of nursing risk assessment. Especially when facing complex conditions and multiple physiological data, potential nursing risks are easily overlooked. Second, traditional nursing plans are often based on general rules and templates and it is difficult to consider the individual differences of each patient, such as the specific disease, age, living habits, etc. of the patient, thus resulting in limitations in the nursing effect. Third, traditional nursing risk assessment often has delays. Especially during the monitoring process, if medical staff fail to detect and take measures in time when a patient is at risk, serious consequences may occur. Summary of the Invention

[0004] This application provides an artificial intelligence nursing risk assessment robot, a storage medium and a computer device, aiming to solve the technical problems that the nursing risk assessment of the prior art often relies on data information from a single source, resulting in insufficient accuracy and timeliness of the assessment, and the nursing plan is often based on general rules and templates, making it difficult to meet the individual differences of each patient and resulting in poor nursing effects.

[0005] In the first aspect disclosed by this application, an artificial intelligence nursing risk assessment robot is provided. The robot includes: a data acquisition module for collecting multi-dimensional state data of a user; a knowledge base system for performing a nursing risk assessment based on the user's medical record to obtain nursing risk point knowledge; an intelligent analysis engine for traversing the nursing risk point knowledge based on the multi-dimensional state data of the user to perform risk level analysis and obtain a risk assessment level, where the risk assessment level has a risk point knowledge label and an intervention plan label; and an interaction interface for uploading the risk assessment level, the risk point knowledge label and the intervention plan label to medical staff.

[0006] In the second aspect disclosed by this application, a storage medium is provided, which deploys the artificial intelligence nursing risk assessment robot in the first aspect disclosed by this application and is used to implement any one of the steps performed by the artificial intelligence nursing risk assessment robot.

[0007] In a third aspect disclosed in the present application, a computer device is provided, including a memory and a processor. The memory stores a computer program. The computer device deploys the artificial intelligence nursing risk assessment robot according to the first aspect disclosed in the present application, and is used to implement any one of the steps executed by the artificial intelligence nursing risk assessment robot.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages: The data acquisition module acquires multi-dimensional state data of the user, providing basic information for subsequent risk assessment. The automated acquisition method can reduce the error of manual input, ensure the real-time and accuracy of the data, and make the assessment process more efficient; the knowledge base system conducts a nursing risk assessment based on the user's medical record, obtains nursing risk point knowledge, and can generate personalized risk assessment results according to the specific situation of the user, improving the pertinence and scientificity of risk analysis and reducing the possibility of missing nursing risks; the intelligent analysis engine traverses the nursing risk point knowledge according to the multi-dimensional state data of the patient, conducts a multi-dimensional risk level analysis, generates the nursing risk assessment level of the patient, and attaches relevant risk point knowledge labels and intervention plan labels. These labels can help medical staff quickly understand the current nursing risks of the patient and the corresponding treatment measures; the interaction interface displays the risk assessment results and relevant labels to medical staff through an intuitive graphical interface, ensuring that medical staff can clearly obtain the risk status of the patient and helping medical staff make decisions quickly.

[0009] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are specifically given below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a schematic structural diagram of the artificial intelligence nursing risk assessment robot provided by the embodiment of the present application.

[0011] Figure 2 It is a schematic structural diagram of an exemplary computer device provided by the embodiment of the present application.

[0012] Description of the reference numerals: data acquisition module 10, knowledge base system 20, intelligent analysis engine 30, interaction interface 40, decision sending module 50, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] By providing an artificial intelligence nursing risk assessment robot in the embodiments of the present application, the technical problems in the prior art are solved, where the nursing risk assessment often relies on data information from a single source, resulting in insufficient accuracy and timeliness of the assessment, and the nursing plan is often based on general rules and templates, making it difficult to meet the individual differences of each patient and resulting in poor nursing effects.

[0014] After introducing the basic principle of the present application, the various non-limiting embodiments of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0015] Embodiment 1, as Figure 1 shown, the embodiments of the present application provide an artificial intelligence nursing risk assessment robot, and the robot includes: A data acquisition module 10 for acquiring multi-dimensional state data of a user.

[0016] Use various types of physical sign sensors, such as electrocardiogram (ECG) sensors, blood pressure monitors, thermometers, etc., to monitor the user's vital signs in real time and acquire the user's basic vital sign data, such as heart rate, blood pressure, body temperature, respiratory rate, etc.; install cameras, such as infrared cameras or ordinary video cameras, in the user's activity area to monitor their activities in real time, and combine computer vision technologies, such as human pose recognition, motion analysis, etc., to extract the user's activity data; use microphones or voice sensors to collect the user's voice data in real time and obtain language expression information to judge whether there are signs of language disorders or the need for help.

[0017] Integrate the user's vital sign information, behavioral activity information, and language expression information to form multi-dimensional state data of the user, where each dimension represents a state information of the patient, providing a basis for subsequent risk assessment and intervention plans.

[0018] A knowledge base system 20 for performing a nursing risk assessment based on the user's medical record and obtaining nursing risk point knowledge.

[0019] Extract key information from the user's medical record file, including the type of the patient's disease, the duration of illness, age, gender, etc. This information is usually stored in an electronic medical record system in a structured or semi-structured form, and generate user index tags based on the key information in the user's medical record, including user disease type index tags, user illness duration index tags, user age index tags, user gender index tags, for subsequent risk assessment.

[0020] The generated user index tags are input into the nursing risk assessment knowledge base for querying to match the nursing risk point knowledge that meets the conditions. The risk point knowledge in the knowledge base includes the risks related to specific diseases, as well as nursing risks such as age and gender. For example, the elderly population may face a high risk of falling, while diabetic patients may face the risk of foot ulcers. According to the matching results, the nursing risk point knowledge is obtained, which may include the nursing risks, risk factors, and related nursing suggestions and intervention measures corresponding to each disease.

[0021] The intelligent analysis engine 30 is used to traverse the nursing risk point knowledge based on the user's multi-dimensional state data for risk level analysis to obtain a risk assessment level. Among them, the risk assessment level has a risk point knowledge label and an intervention plan label.

[0022] According to the nursing risk point knowledge, an associated risk level analysis model is matched. The associated risk level analysis model consists of several associated risk level analysis base channels. Each channel is used to process one risk assessment dimension. The user's multi-dimensional state data, including vital signs, behavior information, and language expression, is organized in matrix form as the model input. Each analysis base channel processes the user's multi-dimensional state data according to different risk factors to generate corresponding risk levels. The mode analysis is performed on the risk levels of each risk assessment channel to find the most frequently occurring risk level as the final risk assessment level. This is because different analysis dimensions may give different risk assessment results, and the mode analysis can ensure the stability and consistency of the assessment.

[0023] Among them, the risk assessment level has a risk point knowledge label and an intervention plan label. The risk point knowledge label is the nursing risk point related to this risk level, such as diabetic complications, fall risk, etc.; the intervention plan label is the intervention plan matched according to the assessment results, such as diet control, drug adjustment, physical therapy, etc.

[0024] The interaction interface 40 is used to upload the risk assessment level, the risk point knowledge label, and the intervention plan label to the medical staff.

[0025] The interaction interface needs to present the complex assessment results in a clear and concise form. For example, the assessment level, risk point knowledge, and intervention plan are displayed in the form of labels, charts, or short text descriptions. Different information can be presented in layers according to importance and urgency. For example, the risk assessment level is displayed first, and then the relevant risk point knowledge label and intervention plan label are displayed.

[0026] Through this interactive interface, the generated risk assessment results and intervention plan labels are effectively transmitted to medical staff. Through a clear data upload and information display mechanism, the interactive interface not only improves the work efficiency of medical staff, but also enhances the real-time and effectiveness of risk assessment.

[0027] Furthermore, the data acquisition module includes: A vital sign acquisition unit for acquiring the patient's vital sign information through a sign sensor; a behavior activity acquisition unit for acquiring the patient's behavior activity information through a camera; a language expression acquisition unit for acquiring the patient's language expression information through a speech recognition device; and an information integration unit for adding the patient's vital sign information, the patient's behavior activity information, and the patient's language expression information into the user's multi-dimensional state data.

[0028] Select appropriate sign sensors according to the patient's needs. Common sensors include electrocardiogram (ECG) sensors, blood pressure monitors, thermometers, etc. Continuously and real-time monitor the patient's physiological parameters through the sensors to obtain the user's basic vital sign information, including heart rate, blood pressure, body temperature, respiratory rate, etc.

[0029] Install a camera or infrared camera in the user's activity area. To improve privacy, a low-resolution camera can be used or image processing technology can be used to detect movement. The camera captures the patient's activity data in real time, including actions such as walking, getting up and sitting down, lying down, etc. It can also analyze whether the patient is performing meaningful activities, such as walking or exercising, through action recognition technology. Adopt video analysis technology, such as action recognition, pose recognition, etc., to extract the patient's behavior activity characteristics and obtain behavior activity information.

[0030] Install a high-quality microphone array that can capture clear voice signals under different environmental conditions. When the patient expresses information through voice, the microphone captures the sound signal in real time. After the sound signal is denoised and enhanced through digital signal processing technology, automatic speech recognition technology is used to convert the speech into text and extract the keywords therein, such as the patient's requests, symptom descriptions, etc., to generate language expression information.

[0031] Unify the formatting and fusion of the data collected by each sensor to form multi-dimensional data. Each type of data has its time stamp and is associated with the same patient ID to form the patient's complete multi-dimensional state data, providing comprehensive basic data support for subsequent nursing risk assessment.

[0032] Furthermore, the knowledge base system includes: An index label extraction unit for extracting user index labels according to the user's medical record, where the user index labels include user disease type index labels, user disease duration index labels, user age index labels, and user gender index labels; a knowledge base index unit for inputting the user disease type index labels, the user disease duration index labels, the user age index labels, and the user gender index labels into a nursing risk assessment knowledge base for indexing to obtain the nursing risk point knowledge.

[0033] Extract the main disease types from the user's medical record, such as diabetes, hypertension, heart disease, etc. Exemplarily, use natural language processing technology to analyze the text content in the medical record, automatically identify and classify the patient's disease types, and convert the disease types into a standardized label format according to the diagnosis information to generate user disease type index labels; extract the disease duration of the patient. Specifically, according to the admission time, diagnosis time, and follow-up records in the patient's medical record, calculate the duration of the patient's illness. If the patient has multiple diseases, the duration of each disease can be recorded separately, or the duration of the main disease can be selected as the index label to generate the user disease duration index label; extract the age from the patient's basic information and group it according to age. Specifically, extract the patient's date of birth, calculate the current age from the patient's basic information record to generate the user age index label. According to the patient's age, further age segmentation can be carried out, such as children, youth, middle-aged, and elderly, in order to compare and analyze with the data in the nursing risk point knowledge base; extract the gender from the patient's basic information to generate the user gender index label. The gender information is used to further analyze the impact of the patient's physiological differences on the nursing risk.

[0034] Through the above method, key parameters such as disease type, disease duration, age, and gender are extracted from the patient's medical record to generate user index labels, and a unique index label set is generated for each patient.

[0035] The extracted index labels, including user disease type index labels, user disease duration index labels, user age index labels, and user gender index labels, are used as input parameters and passed into the nursing risk assessment knowledge base. In the nursing risk assessment knowledge base, relevant nursing risk point knowledge is searched according to the input index labels. For example, if the user's disease type is diabetes, the knowledge base will return nursing risk points related to diabetes, such as hypoglycemia risk, hyperglycemia monitoring, etc. Through the index labels, relevant nursing risk point knowledge is obtained from the knowledge base. These knowledge points include specific risks that the patient may face, such as complications, disease progression, etc., and corresponding nursing strategies, such as regular examinations, drug management, etc.

[0036] Furthermore, the knowledge base system further includes a knowledge base construction unit, and the knowledge base construction unit includes: A resource library construction channel is used to set a collection of nursing risk knowledge and construct a nursing risk knowledge index resource library; a record data collection channel is used to collect user disease type index label record data, user disease duration index label record data, user age index label record data, user gender index label record data, and nursing risk point knowledge identification data, wherein the nursing risk point knowledge identification data belongs to the nursing risk knowledge index resource library; an expert system configuration channel is used to, based on the nursing risk knowledge index resource library, retrieve the nursing risk point knowledge identification data as supervision data, retrieve the user disease type index label record data, the user disease duration index label record data, the user age index label record data, and the user gender index label record data as input data, configure the expert system, and generate the nursing risk assessment knowledge library.

[0037] Define and collect various risk knowledge related to patient care. These knowledge points include but are not limited to: disease-related risks, such as the hypoglycemia risk of diabetic patients and the complication risk of heart disease patients; physiological state-related risks, such as the nursing risks brought by physiological characteristics such as hypertension and overweight; nursing operation-related risks, for example, the pressure ulcer risk of bedridden patients and the complication risk of operations such as intravenous injection or intubation; environmental factor risks, such as the infection risk in the hospital environment and the mental health risk of inpatients.

[0038] To ensure the unity and operability of risk knowledge, all knowledge is standardized to ensure the standardized description of risk points. At the same time, different risk points can be classified according to different levels such as mild, moderate, and severe, providing a basis for subsequent risk assessment.

[0039] According to the set collection of nursing risk knowledge, create a database structure, and establish an index for each nursing risk point in the database structure, so that the corresponding risk point and related nursing measures can be quickly found through the user's basic information. According to the processing results, generate a nursing risk knowledge index resource library.

[0040] Extract the medical record records of a large number of users from the medical record system, and use the same method as constructing the index label mentioned above to extract patient index labels from the medical record records to form user disease type index label record data, user disease duration index label record data, user age index label record data, and user gender index label record data.

[0041] Collect knowledge identifiers of nursing risk points related to patient index tags. These identifiers are specific nursing risk point tags for different patient conditions. For example, if a patient has diabetes, the knowledge base will mark corresponding hypoglycemia risks or diabetic retinopathy, etc. as nursing risk point identifiers. These knowledge identifier data are associated with tags such as the patient's disease type, disease course, age, and gender to form a complete index record.

[0042] Retrieve the knowledge identifier data of nursing risk points from the nursing risk knowledge index repository as supervision data, and retrieve the user's disease type index tag record data, the user's disease duration index tag record data, the user's age index tag record data, and the user's gender index tag record data as input data to configure the expert system. Specifically, based on professional knowledge and experience in the medical field, the expert system can deduce the nursing risks corresponding to different input data. For example, for an older diabetic patient, the nursing risks may include hyperglycemia, heart problems, renal failure, etc. Through configured rules, the expert system can map the input data to relevant nursing risk points and generate a nursing risk assessment knowledge base for different patients. This knowledge base covers the nursing risk assessment criteria and intervention measures for different patient groups to help medical staff perform patient care and risk management more accurately and efficiently.

[0043] Furthermore, the intelligent analysis engine includes: An analysis model matching unit for matching an associated risk level analysis model according to the nursing risk point knowledge, where the associated risk level analysis model consists of several associated risk level analysis base channels; a state matrix construction unit for constructing a user multi-dimensional state matrix according to the user multi-dimensional state data; a risk level acquisition unit for inputting the user multi-dimensional state matrix into the several associated risk level analysis base channels to obtain several risk levels; a mode analysis unit for performing mode analysis on the several risk levels to obtain the risk assessment level; an intervention plan matching unit for matching an intervention plan according to the nursing risk point knowledge and the risk assessment level to obtain the intervention plan tag; a knowledge tag acquisition unit for setting the nursing risk point knowledge as the risk point knowledge tag.

[0044] According to the nursing risk point knowledge, match the associated risk level analysis model. Each nursing risk point corresponds to a specific analysis model, and the model can evaluate the risk level according to different risk categories. The associated risk level analysis model can be constructed based on statistics and machine learning for quantitative risk assessment. The model consists of several sub-models, namely associated risk level analysis base channels, and each channel analyzes a specific risk dimension.

[0045] Convert the user's multi-dimensional status data into a matrix structure, where each column represents a different data dimension and each row represents specific status data. The constructed user multi-dimensional status matrix provides a standardized and structured data format for the input of the subsequent risk assessment model. The health status of the patient is detailedly represented in this matrix, enabling subsequent analysis to make comprehensive judgments based on these multi-dimensional data.

[0046] Input the user multi-dimensional status matrix into several associated risk level analysis base channels for analysis. Each analysis base channel focuses on certain specific dimensions in the multi-dimensional data matrix. For example, one channel mainly analyzes vital sign data, and another channel analyzes behavioral status data. Each risk level analysis base channel calculates the risk level based on the input user multi-dimensional status matrix. According to the design of the model, the channel processes the data through preset rules or machine learning algorithms and outputs the corresponding risk levels, such as low risk, medium risk, high risk, etc., which can respectively reflect the health risks of the patient in different dimensions.

[0047] The mode refers to the value that appears most frequently in the dataset. By performing mode analysis on the risk levels output by all analysis base channels, obtain the most frequently occurring risk level. This level can reflect the overall health risk level of the patient, and use this mode value as the final risk assessment level for the overall assessment of the patient's nursing risk.

[0048] According to the obtained risk assessment level, combine the nursing risk point knowledge to match the intervention plan. The obtained intervention plan label refers to the nursing measures or treatment methods recommended for the patient's current risk level and nursing needs. The specific intervention plan matching process will be detailedly elaborated in the subsequent steps and will not be elaborated here.

[0049] Set the matched nursing risk point knowledge as the risk point knowledge label. This label is a comprehensive description of the patient's health risk and nursing needs, providing detailed risk assessment background for medical staff to help them understand the specific nursing problems faced by the patient.

[0050] Furthermore, the intervention plan matching unit includes: An intervention plan configuration channel for configuring the intervention plan through medical staff based on the preset nursing risk point knowledge and the preset risk assessment level to obtain the preset intervention plan; a matching database construction channel for constructing an intervention plan matching database with the preset nursing risk point knowledge and the preset risk assessment level as the index identifiers and the preset intervention plan as the output data; an intervention plan matching channel for inputting the nursing risk point knowledge and the risk assessment level into the intervention plan matching database for intervention plan matching to obtain the intervention plan label.

[0051] The preset nursing risk point knowledge includes a set of established nursing risk points, and each risk point corresponds to different nursing problems that patients may face, such as disease type, symptoms, abnormal vital signs, etc. The preset risk assessment level characterizes the health risk level of patients, such as low, medium, and high risks. Medical staff manually or automatically configure appropriate intervention plans according to the preset nursing risk point knowledge and the preset risk assessment level to generate preset intervention plans. For example, for high-risk patients, the intervention plan includes first aid measures and emergency interventions; while the intervention plan for low-risk patients focuses on routine care and monitoring.

[0052] Using the preset nursing risk point knowledge and the preset risk assessment level as the index of the database can help quickly query and match the corresponding intervention plans. For each combination of nursing risk points and risk assessment levels, a preset intervention plan is set as the output data. These data are stored in the intervention plan matching database. The function of this database is to quickly match a suitable intervention plan when the patient's risk points and assessment levels are determined, realizing the automated and personalized management of the intervention plan.

[0053] Input the patient's nursing risk point knowledge and risk assessment level into the already constructed intervention plan matching database. The database returns the corresponding intervention plan according to the input risk points and risk assessment levels, and marks the returned intervention plan as an intervention plan label. This label contains corresponding nursing measures, treatment suggestions, etc. The intervention plan label provides accurate guidance for medical staff to help them formulate personalized nursing measures for patients and improve the nursing efficiency and effect.

[0054] Furthermore, it also includes: An intelligent warning module, which is used to generate a user status warning signal and send it to medical staff when the risk assessment level is greater than the risk assessment level threshold of the risk point knowledge label.

[0055] Obtain the risk assessment level threshold of the risk point knowledge label. The risk assessment level threshold is set according to the actual situation and specific requirements. For example, it is set by clinical experience, disease severity, historical data, or an expert system, indicating that above this threshold, the patient's health risk is too high and intervention measures need to be taken.

[0056] Compare the patient's current risk assessment level with the corresponding risk assessment level threshold. If the risk assessment level is greater than the threshold, it means that the patient's health condition has exceeded the safe range and intervention measures need to be taken. In this case, generate a user status warning signal and send it to medical staff. Medical staff can receive the warning in real time through mobile devices, computers, or other terminals and take corresponding countermeasures, thus realizing timely intervention and improving the nursing quality.

[0057] Furthermore, it further includes: An intelligent operation and maintenance module, which is used to monitor whether the patient terminal sends real-time time information to medical staff in real time. If the patient terminal does not send real-time time information to medical staff after a preset duration, a robot operation and maintenance signal is generated and sent to the robot operation and maintenance personnel.

[0058] The patient terminal refers to the device connecting the patient and the monitoring system, which can be a wearable device, an intelligent health monitoring device, or an integrated medical system, etc. It monitors in real time whether the patient terminal sends real-time time information to medical staff on time. This can be achieved by regularly checking the real-time data update from the patient terminal. A preset duration is set as the communication cycle between the patient terminal and medical staff, such as every 10 minutes, every 30 minutes, etc. This duration depends on the specific application scenario and the patient's health condition. Continuously calculate the time difference since the last time the patient terminal information was received. When this time difference exceeds the set preset duration, it is identified as a communication anomaly. In this case, a robot operation and maintenance signal is automatically generated, including anomaly type, anomaly duration, location, and device information, etc., and sent to the robot operation and maintenance personnel. These personnel are responsible for maintaining the normal operation of the robot and performing emergency handling according to the operation and maintenance signal. After receiving the signal, the operation and maintenance personnel immediately conduct remote inspections or dispatch personnel to handle it on-site to ensure that the robot can resume normal work and ensure that the real-time communication between the patient terminal and medical staff is not interrupted.

[0059] In summary, the artificial intelligence nursing risk assessment robot provided by the embodiments of the present application has the following technical effects: The data acquisition module collects the multi-dimensional state data of the user, providing basic information for subsequent risk assessment. The automated acquisition method can reduce the error of manual input, ensure the real-time and accuracy of the data, and make the assessment process more efficient; the knowledge base system conducts nursing risk assessment based on the user's medical record, obtains nursing risk point knowledge, and can generate personalized risk assessment results according to the specific situation of the user, improving the pertinence and scientificity of risk analysis and reducing the possibility of missing nursing risks; the intelligent analysis engine traverses the nursing risk point knowledge according to the multi-dimensional state data of the patient, conducts multi-dimensional risk level analysis, generates the nursing risk assessment level of the patient, and attaches relevant risk point knowledge labels and intervention plan labels. These labels can help medical staff quickly understand the current nursing risks of the patient and the corresponding treatment measures; the interaction interface displays the risk assessment results and relevant labels to medical staff through an intuitive graphical interface, ensuring that medical staff can clearly obtain the risk status of the patient and helping medical staff make decisions quickly.

[0060] Embodiment 2 provides a storage medium deployed with the artificial intelligence nursing risk assessment robot in the foregoing Embodiment 1, and is used to implement any one of the steps executed by the artificial intelligence nursing risk assessment robot.

[0061] Embodiment 3, as shown in Figure 2 FIG. 140 is a schematic structural diagram of an exemplary computer device of the present application. The computer device is deployed with the artificial intelligence nursing risk assessment robot in the foregoing Embodiment 1, and is used to implement any one of the steps executed by the artificial intelligence nursing risk assessment robot. In Figure 2 , the bus architecture is represented by bus 300. Bus 300 may include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and a memory represented by memory 304 together. Bus 300 may also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and thus will not be further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when executing operations.

[0062] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0063] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An artificial intelligence nursing risk assessment robot, characterized in that, The robot includes: A data acquisition module for acquiring multi-dimensional user status data; A knowledge base system for performing a nursing risk assessment based on the user's medical record to obtain nursing risk point knowledge; An intelligent analysis engine for performing risk level analysis by traversing the nursing risk point knowledge based on the multi-dimensional user status data to obtain a risk assessment level, wherein the risk assessment level has a risk point knowledge label and an intervention plan label; An interaction interface for uploading the risk assessment level, the risk point knowledge label, and the intervention plan label to medical staff.

2. The artificial intelligence nursing risk assessment robot according to claim 1, wherein The data acquisition module includes: A vital sign acquisition unit for acquiring patient vital sign information through a sign sensor; A behavior activity acquisition unit for acquiring patient behavior activity information through a camera; A language expression acquisition unit for acquiring patient language expression information through a voice recognition device; An information integration unit for adding the patient vital sign information, the patient behavior activity information, and the patient language expression information into the multi-dimensional user status data.

3. The artificial intelligence nursing risk assessment robot according to claim 1, wherein, The knowledge base system includes: An index label extraction unit for extracting user index labels according to the user's medical record, wherein the user index labels include a user disease type index label, a user disease duration index label, a user age index label, and a user gender index label; A knowledge base index unit for indexing the user disease type index label, the user disease duration index label, the user age index label, and the user gender index label into a nursing risk assessment knowledge base to obtain the nursing risk point knowledge.

4. The artificial intelligence nursing risk assessment robot according to claim 3, characterized in that, The knowledge base system further includes a knowledge base construction unit, and the knowledge base construction unit includes: A resource library construction channel for setting a nursing risk knowledge set and constructing a nursing risk knowledge index resource library; A record data acquisition channel for acquiring user disease type index label record data, user disease duration index label record data, user age index label record data, user gender index label record data, and nursing risk point knowledge identification data, wherein the nursing risk point knowledge identification data belongs to the nursing risk knowledge index resource library; An expert system configuration channel for, based on the nursing risk knowledge index resource library, retrieving the nursing risk point knowledge identification data as supervision data, retrieving the user disease type index label record data, the user disease duration index label record data, the user age index label record data, and the user gender index label record data as input data, and performing the configuration of an expert system to generate the nursing risk assessment knowledge base.

5. The artificial intelligence nursing risk assessment robot according to claim 1, wherein The intelligent analysis engine includes: An analysis model matching unit for matching an associated risk level analysis model according to the nursing risk point knowledge, wherein the associated risk level analysis model is composed of a number of associated risk level analysis base channels; A status matrix construction unit for constructing a multi-dimensional user status matrix according to the multi-dimensional user status data; A risk level acquisition unit, configured to input the user multi-dimensional state matrix into the several associated risk level analysis base channels to obtain several risk levels; A mode analysis unit, configured to perform mode analysis on the several risk levels to obtain the risk assessment level; An intervention plan matching unit, configured to match an intervention plan according to the nursing risk point knowledge and the risk assessment level to obtain the intervention plan label; A knowledge label acquisition unit, configured to set the nursing risk point knowledge as the risk point knowledge label.

6. The artificial intelligence nursing risk assessment robot according to claim 5, characterized in that, The intervention plan matching unit includes: An intervention plan configuration channel, configured to, through medical staff, configure an intervention plan based on preset nursing risk point knowledge and a preset risk assessment level to obtain a preset intervention plan; A matching database construction channel, configured to construct an intervention plan matching database with the preset nursing risk point knowledge and the preset risk assessment level as index identifiers and the preset intervention plan as output data; An intervention plan matching channel, configured to input the nursing risk point knowledge and the risk assessment level into the intervention plan matching database for intervention plan matching to obtain the intervention plan label.

7. The artificial intelligence nursing risk assessment robot according to claim 1, characterized in that, It further includes: An intelligent warning module, configured to generate a user status warning signal and send it to medical staff when the risk assessment level is greater than the risk assessment level threshold of the risk point knowledge label.

8. The robot according to claim 1, wherein It further includes: An intelligent operation and maintenance module, configured to monitor whether the patient terminal sends real-time time information to medical staff in real time. If the patient terminal does not send real-time time information to medical staff beyond a preset duration, generate a robot operation and maintenance signal and send it to robot operation and maintenance personnel.

9. A storage medium, characterized in that, Deploying the artificial intelligence nursing risk assessment robot according to any one of claims 1 to 8, for implementing any one of the steps performed by the artificial intelligence nursing risk assessment robot.

10. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, The computer device deploys the artificial intelligence nursing risk assessment robot according to any one of claims 1 to 8, for implementing any one of the steps performed by the artificial intelligence nursing risk assessment robot.

Images