Old people nursing method based on functional capability and nursing risk and related equipment

Abstract

The invention discloses a functional capability and nursing risk-based elderly care method and related equipment, and relates to the field of medical nursing, and the method comprises the steps: obtaining multi-dimensional functional capability information and nursing risk indexes of an elderly patient, carrying out the structural integration through a weighted scoring model, and generating a joint evaluation file; and outputting the function baseline value, the risk category and the comprehensive risk index. The system calls a nursing intervention rule base according to the file, and a personalized intervention list is automatically generated to serve as an execution baseline for trend monitoring. Continuously updating function and risk data in the nursing process, and generating a time sequence trend chart and a risk level change curve; when a drop in function or an increase in risk is detected, the system triggers reevaluation and automatically adjusts the intervention list. According to the method, fusion of function evaluation and risk identification and automatic generation and dynamic adjustment of intervention suggestions are realized, and the intelligent and individualized levels of elderly care are improved.

Description

TECHNICAL FIELD

[0001] The present specification relates to the field of medical care, and more particularly, an elderly care method based on functional capacity and nursing risk and related equipment. BACKGROUND

[0002] With the acceleration of global population aging, elderly patients face a variety of potential risks in the process of inpatient and post-discharge care, including falls, pressure ulcers, delirium, malnutrition, and inappropriate medication use. These nursing risks not only can directly lead to serious complications in patients, reduce the quality of life, but also significantly increase the consumption of medical resources and the burden of nursing staff.

[0003] Existing nursing information systems mostly rely on single risk event assessment tools, such as scoring fall risk through the Morse scale or identifying pressure ulcer risk through the Braden scale. Although such tools have been widely used in clinical practice, due to the independent assessment dimensions, lack of unified structured integration, they cannot fully reflect the overall state of elderly patients in cognitive, motor, nutritional, psychological, and sensory functions. At the same time, existing systems often only stop at the stage of risk identification and classification, lack of intelligent linkage with intervention measures, and nursing staff still need to rely on experience to consult paper guidelines or manually develop intervention plans. In addition, existing systems are mostly static assessments, lacking monitoring and path dynamic adjustment mechanisms for functional changes, and cannot adapt to the volatility of elderly patients' conditions and continuous care needs. More importantly, most of the system's interactive objects are only for nurses, lacking the participation of doctors, patients, and family members, making it difficult to form information sharing and risk consensus, resulting in fragmented care services and incomplete closed loop.

[0004] Therefore, it is necessary to provide an elderly care method based on functional capacity and nursing risk and related equipment to at least solve some of the above problems. SUMMARY

[0005] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the specific embodiments section. The summary section of the present application does not mean to attempt to limit the key features and necessary technical features of the claimed technical solutions, nor to attempt to determine the protection scope of the claimed technical solutions.

[0006] In a first aspect, the present application proposes an elderly care method based on functional capacity and nursing risk, comprising:

[0007] To obtain multidimensional functional ability information and nursing risk indicators of elderly patients to form basic input data, the multidimensional functional ability information includes cognition, motor function, nutrition, psychology and sensory function, and the nursing risk indicators include fall risk, pressure ulcer risk, delirium risk, malnutrition risk and medication use risk.

[0008] Based on the above basic input data, the above functional ability information and the above nursing risk indicators are structured and integrated, and a joint assessment file is generated through a weighted scoring model. The above file simultaneously outputs functional baseline values, risk categories and comprehensive risk index.

[0009] Based on the comprehensive risk index and risk category in the joint assessment file, the nursing intervention rule base is invoked to automatically generate a personalized nursing intervention suggestion list, which is used as the execution baseline for trend monitoring. The personalized nursing intervention list includes intervention measures, execution frequency, reassessment timing, and path escalation prompts.

[0010] During the implementation of intervention measures, the above-mentioned multidimensional functional ability information and nursing risk indicators are continuously collected and updated. The time series trend graph and risk level change curve are generated by comparing the above-mentioned implementation baseline. When the trend shows that the functional indicators are declining or the risk level is rising, the reassessment step is triggered, and the above-mentioned personalized nursing intervention list is automatically adjusted based on the reassessment results.

[0011] In one feasible implementation, the above-mentioned fusion assessment step employs a dual-axis mapping mechanism of function and risk;

[0012] The aforementioned dual-axis mapping mechanism between function and risk specifically includes:

[0013] Establish a causal association weight matrix between functional ability indicators and nursing risk factors;

[0014] When a certain functional dimension drops to a preset threshold, the weight of the corresponding risk category is automatically increased to recalculate the comprehensive risk index and further drive the linkage of the aforementioned personalized care intervention list and pathway.

[0015] In one feasible implementation, the update of the aforementioned causal correlation weight matrix employs a dynamic time series correction mechanism, specifically including:

[0016] A time series of changes in functional abilities was generated based on data from multiple patient assessments.

[0017] The rate of decline of the functional dimension was calculated using a sliding time window and then correlated with the incidence of risk factors.

[0018] When the rate of functional decline exceeds a threshold, a real-time update of the weight matrix is ​​triggered.

[0019] The updated weight matrix is ​​used to recalculate the comprehensive risk index, and this index is fed back into the intervention list generation step to dynamically optimize the frequency of interventions and the timing of path adjustments.

[0020] In one feasible implementation, the above-mentioned personalized nursing intervention suggestion list step is dynamically optimized by combining a knowledge rule base with a machine learning model;

[0021] The aforementioned knowledge rule base is used to match standard interventions from nursing guidelines based on risk categories and levels;

[0022] The aforementioned machine learning model uses trend monitoring and intervention execution effects as training samples to verify and correct the personalized nursing intervention suggestions generated by the aforementioned knowledge rule base, and feeds the optimized personalized nursing intervention suggestions back to the aforementioned trend monitoring step in order to continuously improve individual fit and execution compliance.

[0023] In one feasible implementation, the specific steps for constructing the aforementioned knowledge rule base include:

[0024] Collect multi-source nursing knowledge, including international and regional nursing guidelines, hospital-based nursing pathways, and expert experience rules;

[0025] The above nursing knowledge is structured to form a multi-level mapping table of risk category-level-intervention measures;

[0026] Set execution frequency, indications, and contraindications constraints for the intervention measures involved in the above multi-level mapping table;

[0027] By using a consistency verification method to perform conflict detection and fusion on the above multi-layer mapping tables, a standardized knowledge rule base that can be called by the system is formed.

[0028] In one feasible implementation, the specific structure of the above-mentioned machine learning model includes:

[0029] The input layer is used to receive the patient's historical functional ability sequence, risk level change trend, and intervention execution results;

[0030] The feature extraction layer, including a temporal convolutional network and an attention mechanism module, is used to extract features of functional capability change patterns and features sensitive to intervention effects.

[0031] The fusion layer is used to perform vector-level concatenation and weighted fusion of the above-mentioned functional capability change pattern features, the above-mentioned intervention effect sensitivity features, and the above-mentioned knowledge rule base recommendation results to form fused features;

[0032] The output layer is used to generate corrected personalized nursing intervention suggestions based on the above-mentioned fusion features.

[0033] In one feasible implementation, it further includes:

[0034] The aforementioned joint assessment files, the aforementioned list of intervention recommendations, and trend results will be displayed through a multi-role interactive interface, enabling nurses to implement and record interventions, physicians to assist in decision-making, and patients and their families to conduct self-assessments and provide feedback.

[0035] Secondly, this invention also proposes an elderly care system based on functional capabilities and care risks, comprising:

[0036] The acquisition unit is used to acquire multidimensional functional ability information and nursing risk indicators of elderly patients to form basic input data. The multidimensional functional ability information includes cognition, motor function, nutrition, psychology and sensory function. The nursing risk indicators include fall risk, pressure ulcer risk, delirium risk, malnutrition risk and medication use risk.

[0037] The first generation unit is used to structure and integrate the functional ability information and nursing risk indicators based on the above basic input data, and generate a joint assessment file through a weighted scoring model. The file outputs functional baseline values, risk categories and comprehensive risk index.

[0038] The second generation unit is used to automatically generate a personalized nursing intervention suggestion list by calling the nursing intervention rule base according to the comprehensive risk index and risk category in the joint assessment file, and to use the personalized nursing intervention list as the execution baseline for trend monitoring. The personalized nursing intervention list includes intervention measures, execution frequency, reassessment timing and path upgrade prompts.

[0039] The adjustment unit is used to continuously collect and update the above-mentioned multidimensional functional ability information and the above-mentioned nursing risk indicators during the implementation of intervention measures, compare the above-mentioned implementation baseline to generate a time series trend graph and risk level change curve, and trigger a reassessment step when the trend shows that the functional indicators are declining or the risk level is rising, and automatically adjust the above-mentioned personalized nursing intervention list based on the reassessment results.

[0040] Thirdly, the present invention also proposes an electronic device comprising: a memory and a processor, characterized in that the processor is used to execute a computer program stored in the memory to implement the steps of the elderly care method based on functional capacity and care risk as described in any of the first aspects.

[0041] Fourthly, the present invention also proposes a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the elderly care method based on functional capacity and care risk as described in any one of the first aspects.

[0042] In summary, this invention, through the design of a dual-axis assessment framework integrating functional capabilities and nursing risks, unifies cognitive, motor, nutritional, psychological, and sensory functional capabilities with nursing risk indicators such as falls, pressure ulcers, delirium, malnutrition, and medication use, forming a structured joint assessment file. This overcomes the problem of the separation between functional status and risk identification in traditional systems. Based on the results of this joint assessment, the system can automatically generate a personalized nursing intervention list, including not only intervention measures and execution frequency, but also setting the timing and path escalation prompts for reassessment, achieving an intelligent closed loop from risk identification to intervention execution, significantly reducing the workload of nursing staff. Simultaneously, this invention, through a trend monitoring mechanism, continuously tracks the time-series changes in function and risk. Once a decline in function or an increase in risk is detected, the system automatically triggers a reassessment and optimizes the intervention list, addressing the lack of dynamic adjustment in existing technologies. The system also introduces a multi-role interaction module, enabling nurses to execute and record interventions, doctors to obtain decision support, and patients and their families to self-assess and provide feedback, thereby establishing a collaborative care ecosystem of "patient-family-nurse-doctor," compensating for the problem of single interaction roles in existing technologies. In summary, this invention achieves significant improvements and optimizations compared to existing technologies in terms of sensitivity of early risk identification, individualization and timeliness of nursing intervention, dynamic continuity of care pathways, and extensiveness of service collaboration.

[0043] Other advantages, objectives and features of this application will be apparent in part from the description which follows, and in part from what those skilled in the art will understand through study and practice of this application. Attached Figure Description

[0044] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0045] Figure 1 A schematic diagram of a method for elderly care based on functional capabilities and nursing risks provided in this application embodiment;

[0046] Figure 2 A structural schematic diagram of an elderly care system based on functional capabilities and care risks is provided for an embodiment of this application;

[0047] Figure 3 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0048] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will now be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0049] Please see Figure 1 This is a flowchart illustrating an elderly care method based on functional ability and care risk, provided in an embodiment of this application. Specifically, it may include:

[0050] Firstly, this application proposes an elderly care approach based on functional capacity and care risk, including:

[0051] S110. Obtain multidimensional functional ability information and nursing risk indicators of elderly patients to form basic input data. The multidimensional functional ability information includes cognition, motor function, nutrition, psychology and sensory function. The nursing risk indicators include fall risk, pressure ulcer risk, delirium risk, malnutrition risk and medication use risk.

[0052] S120. Based on the above basic input data, the above functional ability information and the above nursing risk indicators are structured and integrated, and a joint assessment file is generated through a weighted scoring model. The above file simultaneously outputs functional baseline values, risk categories and comprehensive risk index.

[0053] S130. Based on the comprehensive risk index and risk category in the joint assessment file, call the nursing intervention rule base to automatically generate a personalized nursing intervention suggestion list, and use the personalized nursing intervention list as the execution baseline for trend monitoring. The personalized nursing intervention list includes intervention measures, execution frequency, reassessment timing, and path upgrade prompts.

[0054] S140. During the implementation of intervention measures, continuously collect and update the above-mentioned multidimensional functional ability information and the above-mentioned nursing risk indicators, compare the above-mentioned implementation baseline to generate a time series trend graph and risk level change curve, and when the trend shows that the functional indicators are declining or the risk level is rising, trigger the reassessment step, and automatically adjust the above-mentioned personalized nursing intervention list based on the reassessment results.

[0055] For example, firstly, multidimensional functional ability information and nursing risk indicators are obtained for elderly patients. The functional ability information includes five dimensions: cognition, motor function, nutrition, psychology, and sensory function. The nursing risk indicators include risk of falls, pressure ulcers, delirium, malnutrition, and medication use. By collecting the above multidimensional information, the patient's current physical condition and potential risks can be comprehensively reflected, providing basic data for subsequent comprehensive assessment.

[0056] Based on this, the collected functional ability information and nursing risk indicators are structurally integrated, and a weighted scoring model is introduced to generate a joint assessment profile. This profile not only outputs the patient's current functional baseline value, but also includes the identification results of risk categories and a comprehensively calculated risk index. Through this joint profile, nursing staff can obtain a holistic health profile of the patient across both functional and risk dimensions, rather than being limited to a single risk point.

[0057] Subsequently, based on the comprehensive risk index and risk category in the joint assessment file, the system calls upon a pre-set nursing intervention rule base to automatically generate a personalized nursing intervention suggestion list for the patient. This list is output in a structured manner, including specific intervention measures, frequency of implementation, timing of reassessment, and prompts for path escalation. Simultaneously, this intervention list also serves as the execution baseline for trend monitoring, ensuring that the effectiveness of subsequent interventions can be verified and adjusted through dynamic monitoring.

[0058] During the implementation of intervention measures, the system continuously collects and updates the patient's multidimensional functional ability information and nursing risk indicators, and compares them with baseline data to generate time series trend charts and risk level change curves. When monitoring results show that the patient's functional indicators are continuously declining or the risk level is trending upward, the system will automatically trigger a reassessment step, and adjust and optimize the original personalized nursing intervention list based on the reassessment results, thereby forming a continuous closed-loop care process.

[0059] In summary, this invention, through the design of a dual-axis assessment framework integrating functional capabilities and nursing risks, unifies cognitive, motor, nutritional, psychological, and sensory functional capabilities with nursing risk indicators such as falls, pressure ulcers, delirium, malnutrition, and medication use, forming a structured joint assessment file. This overcomes the problem of the separation between functional status and risk identification in traditional systems. Based on the results of this joint assessment, the system can automatically generate a personalized nursing intervention list, including not only intervention measures and execution frequency, but also setting the timing and path escalation prompts for reassessment, achieving an intelligent closed loop from risk identification to intervention execution, significantly reducing the workload of nursing staff. Simultaneously, this invention, through a trend monitoring mechanism, continuously tracks the time-series changes in function and risk. Once a decline in function or an increase in risk is detected, the system automatically triggers a reassessment and optimizes the intervention list, addressing the lack of dynamic adjustment in existing technologies. The system also introduces a multi-role interaction module, enabling nurses to execute and record interventions, doctors to obtain decision support, and patients and their families to self-assess and provide feedback, thereby establishing a collaborative care ecosystem of "patient-family-nurse-doctor," compensating for the problem of single interaction roles in existing technologies. In summary, this invention achieves significant improvements and optimizations compared to existing technologies in terms of sensitivity of early risk identification, individualization and timeliness of nursing intervention, dynamic continuity of care pathways, and extensiveness of service collaboration.

[0060] In one feasible implementation, the above-mentioned fusion assessment step employs a dual-axis mapping mechanism of function and risk;

[0061] The aforementioned dual-axis mapping mechanism between function and risk specifically includes:

[0062] Establish a causal association weight matrix between functional ability indicators and nursing risk factors;

[0063] When a certain functional dimension drops to a preset threshold, the weight of the corresponding risk category is automatically increased to recalculate the comprehensive risk index and further drive the linkage of the aforementioned personalized care intervention list and pathway.

[0064] For example, the integrated assessment step incorporates a dual-axis mapping mechanism of function and risk. This mechanism establishes a causal association weight matrix between multidimensional functional ability indicators and nursing risk factors in elderly patients. This allows the assessment to consider not only the independent level of each individual risk but also the synergistic effect of functional decline on risk changes. Specifically, the system first models the association between the patient's functional ability dimensions, such as cognitive ability, motor ability, nutritional status, psychological state, and sensory function, and their corresponding nursing risk categories. Through a comprehensive weighting of historical clinical data and expert experience, a causal weight matrix is ​​constructed to quantify the influence strength between different functional dimensions and various risk events.

[0065] When monitoring results show that a certain functional dimension has declined to a preset threshold, the system automatically increases the weight of the risk category associated with that function. For example, when a patient's mobility falls below the threshold, the weight of the fall risk will be dynamically increased. When nutritional function deteriorates, the weights of malnutrition risk and pressure ulcer risk will both increase. This dynamic adjustment allows the comprehensive risk index to more sensitively reflect changes in the patient's true condition, rather than simply being a static summation of scores.

[0066] The updated comprehensive risk index will directly drive the optimization and generation of subsequent personalized nursing intervention lists and serve as the input baseline for the trend monitoring module. When the risk index increases significantly due to weight adjustments, the system can proactively prompt nurses or doctors to strengthen intervention measures, such as increasing the frequency of rounds, adjusting dietary structure, or adding fall prevention aids. Simultaneously, it can trigger linked updates to care pathways, ensuring that the patient's care plan can be promptly revised in response to dynamic changes in function and risk. Through this mechanism, this embodiment achieves dynamic coupling between functional capabilities and nursing risks, making risk identification more proactive and sensitive, and promoting the transformation of nursing intervention from static management to intelligent, dynamic pathway adjustment.

[0067] In one feasible implementation, the update of the aforementioned causal correlation weight matrix employs a dynamic time series correction mechanism, specifically including:

[0068] A time series of changes in functional abilities was generated based on data from multiple patient assessments.

[0069] The rate of decline of the functional dimension was calculated using a sliding time window and then correlated with the incidence of risk factors.

[0070] When the rate of functional decline exceeds a threshold, a real-time update of the weight matrix is ​​triggered.

[0071] The updated weight matrix is ​​used to recalculate the comprehensive risk index, and this index is fed back into the intervention list generation step to dynamically optimize the frequency of interventions and the timing of path adjustments.

[0072] For example, the causal association weight matrix is ​​updated using a dynamic time-series correction mechanism to ensure that the association between functional capacity and nursing risk can be adjusted in real time as the patient's condition changes. Specifically, the system first generates time-series data on functional capacity based on multiple assessments of the patient at different times. This data reflects the dynamic trends of multidimensional functions such as cognition, motor function, nutrition, psychology, and sensory function. Based on this, the system performs local analysis of changes in each functional dimension using a sliding time window approach, calculates the rate of functional decline, and performs correlation fitting between this rate and the incidence of corresponding nursing risk factors. Through this fitting relationship, the potential coupling strength between functional change trends and risk events can be identified.

[0073] When the system detects that the rate of decline in a certain functional dimension exceeds a preset threshold, it automatically triggers a real-time update of the causal association weight matrix. This increases or adjusts the weight of the risk category corresponding to that functional dimension, thereby more accurately reflecting the impact of functional deterioration on risk levels. Subsequently, the updated weight matrix is ​​used to recalculate the comprehensive risk index, which not only includes static assessment information but also incorporates the dynamic factor of the rate of functional change. Finally, the new risk index is fed back into the personalized care intervention list generation step to dynamically optimize the frequency of intervention measures and the timing of care pathway adjustments. For example, when motor function declines rapidly in a short period of time, the system can automatically increase the weight of fall risk and accordingly increase the frequency of fall prevention measures in nursing recommendations or prompt caregivers to conduct reassessments in advance. Through the above-mentioned dynamic time series correction mechanism, this embodiment achieves a closed-loop adaptive update of risk assessment and intervention generation, enabling the system to respond more proactively and sensitively to the trend of patient functional deterioration.

[0074] In one feasible implementation, the above-mentioned personalized nursing intervention suggestion list step is dynamically optimized by combining a knowledge rule base with a machine learning model;

[0075] The aforementioned knowledge rule base is used to match standard interventions from nursing guidelines based on risk categories and levels;

[0076] The aforementioned machine learning model uses trend monitoring and intervention execution effects as training samples to verify and correct the personalized nursing intervention suggestions generated by the aforementioned knowledge rule base, and feeds the optimized personalized nursing intervention suggestions back to the aforementioned trend monitoring step in order to continuously improve individual fit and execution compliance.

[0077] For example, the generation of a personalized nursing intervention recommendation list does not rely on a single static rule, but rather achieves dynamic optimization through a combination of a knowledge rule base and a machine learning model. Specifically, the system first calls upon a pre-set knowledge rule base, which establishes a mapping relationship between risk categories, risk levels, and standard interventions based on nursing guidelines and clinical experience. For instance, when a patient is assessed as having a high risk of falls, the system automatically matches fall prevention measures recommended in the guidelines, such as increased rounds, the addition of assistive devices, or adjustments to the ward environment. The resulting intervention list ensures consistency and safety with clinical nursing standards.

[0078] However, to avoid the rigidity of static rules and the lack of adaptation due to individual differences, this embodiment further introduces a machine learning model. This model uses patient trend monitoring data and historical intervention performance as training samples to learn the implicit relationship between functional changes and intervention results. In this way, the model can validate the effectiveness of the initial intervention list generated by the knowledge rule base and make adjustments based on the actual feedback from individual patients. For example, when the system finds that a certain type of patient has limited recovery after receiving standard nutritional intervention, the model will optimize the intervention list for that type of patient, adding personalized dietary recommendations or combining other measures to improve the effectiveness of the intervention.

[0079] The optimized personalized nursing intervention recommendations not only retain the standardization of nursing guidelines but also possess the ability to dynamically adjust and adapt to individual needs. The system feeds back the revised intervention recommendations to the trend monitoring step, enabling subsequent functions and risk tracking to be iteratively optimized based on the latest intervention results. Through this rule-based and learning-driven mechanism, this embodiment achieves closed-loop optimization of nursing recommendations, continuously improving the suitability and adherence of personalized nursing interventions, thereby significantly enhancing care quality and efficiency while ensuring safety.

[0080] In one feasible implementation, the specific steps for constructing the aforementioned knowledge rule base include:

[0081] Collect multi-source nursing knowledge, including international and regional nursing guidelines, hospital-based nursing pathways, and expert experience rules;

[0082] The above nursing knowledge is structured to form a multi-level mapping table of risk category-level-intervention measures;

[0083] Set execution frequency, indications, and contraindications constraints for the intervention measures involved in the above multi-level mapping table;

[0084] By using a consistency verification method to perform conflict detection and fusion on the above multi-layer mapping tables, a standardized knowledge rule base that can be called by the system is formed.

[0085] For example, the construction of the knowledge rule base does not rely directly on a single source of nursing guidelines, but rather on the integration of multi-source nursing knowledge. Specifically, the system first collects multi-dimensional knowledge content, including international and regional nursing guidelines, nursing pathways developed within hospitals, and clinical expert experience rules. These knowledge sources cover the actual application situations at different levels, in different regions, and in different medical institutions, thereby ensuring the comprehensiveness and authority of the rule base.

[0086] Subsequently, the system performs structured processing on the aforementioned multi-source nursing knowledge, establishing a multi-layered mapping table according to risk category, risk level, and corresponding intervention measures. For example, for fall risk, the system establishes low-risk, medium-risk, and high-risk levels in the mapping table, with each level corresponding to a series of intervention measures, such as the frequency of daily rounds, environmental safety arrangements, or the use of assistive tools. Through this structured mapping, the originally scattered textual nursing experience can be transformed into a data structure that can be directly accessed by the computer.

[0087] During the mapping process, the system also sets corresponding execution frequency, indications, and contraindications for each intervention. For example, nutritional interventions will have their execution frequency set based on the patient's body mass index and metabolic status, while drug management measures need to consider past medical history and potential contraindications to ensure that the generated intervention recommendations meet individualized needs.

[0088] Finally, to address potential conflicts and discrepancies between different knowledge sources, the system introduces a consistency verification method to detect and fuse conflicts in the multi-layered mapping table. When inconsistencies are detected in the recommended measures for the same risk category across different guidelines, the system adjusts these measures through priority settings and expert consensus mechanisms to ensure that the final output is both scientifically sound and clinically feasible. After these processes, the resulting standardized knowledge rule base can be directly accessed by the system to support the generation of personalized nursing intervention recommendations.

[0089] Through this construction process, this embodiment not only realizes the digitization and structuring of nursing knowledge, but also ensures the standardization, adaptability and scalability of the rule base in terms of content, thereby providing a stable and reliable knowledge foundation for intelligent intervention suggestions.

[0090] In one feasible implementation, the specific structure of the above-mentioned machine learning model includes:

[0091] The input layer is used to receive the patient's historical functional ability sequence, risk level change trend, and intervention execution results;

[0092] The feature extraction layer, including a temporal convolutional network and an attention mechanism module, is used to extract features of functional capability change patterns and features sensitive to intervention effects.

[0093] The fusion layer is used to perform vector-level concatenation and weighted fusion of the above-mentioned functional capability change pattern features, the above-mentioned intervention effect sensitivity features, and the above-mentioned knowledge rule base recommendation results to form fused features;

[0094] The output layer is used to generate corrected personalized nursing intervention suggestions based on the above-mentioned fusion features.

[0095] For example, the specific structure of the machine learning model consists of an input layer, a feature extraction layer, a fusion layer, and an output layer, used to achieve intelligent correction and dynamic optimization of nursing intervention recommendations. Specifically, the input layer receives historical functional ability sequences formed from multiple patient assessments, trends in risk level changes, and the results of previous interventions. This input data comprehensively reflects the dynamic situation of the patient in terms of functional status, risk evolution, and intervention effects, providing a foundation for subsequent feature learning.

[0096] A feature extraction layer is placed after the input layer, containing a temporal convolutional network and an attention mechanism module. The temporal convolutional network can model the time series of functional changes, extracting the patterns of change in the patient's functional dimensions over different time periods, thereby identifying potential long-term decline trends or short-term abnormal fluctuations. Simultaneously, the attention mechanism module can assign differentiated weights to different time periods and risk factors, highlighting sensitive features highly correlated with intervention effects. For example, if the risk of falls continuously increases within a certain time window, the attention mechanism will increase the weight of features in that segment in the overall modeling.

[0097] After feature extraction, the model proceeds to the fusion layer. This layer not only performs vector-level concatenation of features showing functional change patterns and intervention-sensitive features, but also incorporates standardized intervention results recommended by the knowledge rule base as additional input. A weighted fusion method is used to integrate data-driven features with knowledge-driven results. In this way, the model maintains interpretability consistent with nursing guidelines while allowing for personalized adjustments based on actual patient data, avoiding insufficient adaptability caused by relying solely on empirical rules.

[0098] Finally, the output layer generates revised personalized nursing intervention suggestions based on the aforementioned fusion features. These suggestions not only include specific intervention measures but also allow for adjustments to the frequency of implementation and assessment timing to better align with the patient's functional status and risk trends. The generated intervention results are fed back to the trend monitoring module for subsequent iterative optimization. Through this structured design, this embodiment achieves a dual-driven approach of knowledge rules and machine learning, continuously improving the individual fit and adherence to nursing recommendations, thereby significantly enhancing the quality and safety of care for elderly patients.

[0099] In one feasible implementation, it further includes:

[0100] The aforementioned joint assessment files, the aforementioned list of intervention recommendations, and trend results will be displayed through a multi-role interactive interface, enabling nurses to implement and record interventions, physicians to assist in decision-making, and patients and their families to conduct self-assessments and provide feedback.

[0101] For example, the system also includes a multi-role interactive interface to visually display the joint assessment profile, personalized nursing intervention list, and trend monitoring results to different users. Through this interface, nurses can directly view the patient's functional status and risk level, obtain the nursing intervention list generated by the system, and immediately record the interventions after implementation. Doctors can quickly browse the core summary and trend curves of the joint assessment through the interface, thereby referencing nursing risk and functional change information in their diagnostic and treatment decisions to achieve medical-nursing collaboration. Patients and their families can also conduct self-assessments and provide feedback through the interface, such as inputting the patient's functional experience in daily life, their acceptance of interventions, or adverse reactions. This feedback data is collected by the system in real time and serves as supplementary input for subsequent assessments and intervention optimization.

[0102] Through the aforementioned multi-role interaction design, the system is no longer limited to use by a single caregiver, but rather constructs a multi-party participation model involving "nurses, doctors, patients, and family members." In this model, risk identification and intervention execution can reach a consensus, information transmission is more transparent, and the execution and adjustment of care pathways can obtain support from multiple parties. Therefore, this embodiment achieves information sharing, role collaboration, and continuity management in the care process, further improving the integrity and effectiveness of elderly care services.

[0103] Secondly, this invention also proposes an elderly care system based on functional capabilities and care risks, such as... Figure 2 As shown, it includes:

[0104] The acquisition unit 21 is used to acquire multidimensional functional ability information and nursing risk indicators of elderly patients to form basic input data. The multidimensional functional ability information includes cognition, motor function, nutrition, psychology and sensory function. The nursing risk indicators include fall risk, pressure ulcer risk, delirium risk, malnutrition risk and medication use risk.

[0105] The first generation unit 22 is used to structure and integrate the functional ability information and nursing risk indicators based on the above basic input data, and generate a joint assessment file through a weighted scoring model. The file outputs functional baseline values, risk categories and comprehensive risk index.

[0106] The second generation unit 23 is used to automatically generate a personalized nursing intervention suggestion list by calling the nursing intervention rule base according to the comprehensive risk index and risk category in the joint assessment file, and to use the personalized nursing intervention list as the execution baseline for trend monitoring. The personalized nursing intervention list includes intervention measures, execution frequency, reassessment timing and path upgrade prompts.

[0107] The adjustment unit 24 is used to continuously collect and update the above-mentioned multidimensional functional ability information and the above-mentioned nursing risk indicators during the implementation of intervention measures, compare the above-mentioned execution baseline to generate a time series trend graph and a risk level change curve, and trigger a reassessment step when the trend shows that the functional indicators are declining or the risk level is rising, and automatically adjust the above-mentioned personalized nursing intervention list based on the reassessment results.

[0108] In one feasible implementation, an elderly care system based on functional capacity and care risk can also perform any step of the method proposed in the first aspect.

[0109] Thirdly, the present invention also proposes an electronic device 300, such as... Figure 3 As shown, it includes a memory 310, a processor 320, and a computer program 311 stored on the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of the elderly care method based on functional capacity and care risk as described in any of the first aspects.

[0110] Fourthly, the present invention also proposes a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the elderly care method based on functional capacity and care risk as described in any one of the first aspects.

[0111] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0112] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0113] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0114] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0115] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0116] This 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 performs the voice-based identity recognition process in the corresponding embodiment.

[0117] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0118] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0121] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0122] If the integrated unit is implemented as 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 this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0123] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An elderly care method based on functional ability and care risk, characterized in that, Includes the following steps: To obtain multidimensional functional ability information and nursing risk indicators of elderly patients to form basic input data, wherein the multidimensional functional ability information includes cognition, motor function, nutrition, psychology and sensory function, and the nursing risk indicators include fall risk, pressure ulcer risk, delirium risk, malnutrition risk and medication use risk. Based on the aforementioned basic input data, the functional ability information and the nursing risk indicators are structurally integrated, and a joint assessment file is generated through a weighted scoring model. The file simultaneously outputs the functional baseline value, risk category, and comprehensive risk index. Based on the comprehensive risk index and risk category in the joint assessment file, the nursing intervention rule base is invoked to automatically generate a personalized nursing intervention suggestion list, and the personalized nursing intervention list is used as the execution baseline for trend monitoring. The personalized nursing intervention list includes intervention measures, execution frequency, reassessment timing, and path escalation prompts. During the implementation of intervention measures, the multidimensional functional ability information and the nursing risk indicators are continuously collected and updated. The time series trend graph and risk level change curve are generated by comparing the implementation baseline. When the trend shows that the functional indicators are declining or the risk level is rising, the reassessment step is triggered, and the personalized nursing intervention list is automatically adjusted based on the reassessment results.

2. The elderly care method based on functional ability and nursing risk according to claim 1, characterized in that, The fusion assessment step employs a dual-axis mapping mechanism of function and risk. The dual-axis mapping mechanism between function and risk specifically includes: Establish a causal association weight matrix between functional ability indicators and nursing risk factors; When a certain functional dimension drops to a preset threshold, the weight of the corresponding risk category is automatically increased to recalculate the comprehensive risk index and further drive the linkage of the subsequent personalized care intervention list and pathway.

3. The elderly care method based on functional ability and nursing risk according to claim 2, characterized in that, The update of the causal correlation weight matrix adopts a dynamic time series correction mechanism, specifically including: A time series of changes in functional abilities was generated based on data from multiple patient assessments. The rate of decline of the functional dimension was calculated using a sliding time window and then correlated with the incidence of risk factors. When the rate of functional decline exceeds a threshold, a real-time update of the weight matrix is ​​triggered. The updated weight matrix is ​​used to recalculate the comprehensive risk index, and this index is fed back into the intervention list generation step to dynamically optimize the frequency of interventions and the timing of path adjustments.

4. The elderly care method based on functional ability and nursing risk according to claim 1, characterized in that, The personalized nursing intervention suggestion list step is dynamically optimized by combining a knowledge rule base with a machine learning model; The knowledge rule base is used to match standard interventions from nursing guidelines based on risk categories and levels; The machine learning model uses trend monitoring and intervention execution effects as training samples to verify and correct the personalized nursing intervention suggestions generated by the knowledge rule base, and feeds the optimized personalized nursing intervention suggestions back to the trend monitoring step to continuously improve individual fit and execution compliance.

5. The elderly care method based on functional ability and nursing risk according to claim 4, characterized in that, The specific steps for constructing the knowledge rule base include: Collect multi-source nursing knowledge, including international and regional nursing guidelines, hospital-based nursing pathways, and expert experience rules; The nursing knowledge is structured to form a multi-level mapping table of risk category-level-intervention measures; Set execution frequency, indications, and contraindications constraints for the intervention measures involved in the multi-layer mapping table; The multi-layer mapping tables are conflict-detected and merged using a consistency verification method to form a standardized knowledge rule base that can be called by the system.

6. The elderly care method based on functional ability and nursing risk according to claim 4, characterized in that, The specific structure of the machine learning model includes: The input layer is used to receive the patient's historical functional ability sequence, risk level change trend, and intervention execution results; The feature extraction layer, including a temporal convolutional network and an attention mechanism module, is used to extract features of functional capability change patterns and features sensitive to intervention effects. The fusion layer is used to perform vector-level concatenation and weighted fusion of the functional capability change pattern features, the intervention effect sensitivity features, and the recommendation results of the knowledge rule base to form fused features; The output layer is used to generate revised personalized care intervention recommendations based on the fusion features.

7. The elderly care method based on functional ability and nursing risk according to claim 1, characterized in that, Also includes: The joint assessment file, the list of intervention recommendations, and trend results are displayed through a multi-role interactive interface, enabling nurses to implement and record interventions, doctors to assist in decision-making, and patients and their families to conduct self-assessments and provide feedback.

8. An elderly care system based on functional capabilities and care risks, characterized in that, include: The acquisition unit is used to acquire multidimensional functional ability information and nursing risk indicators of elderly patients to form basic input data. The multidimensional functional ability information includes cognition, motor function, nutrition, psychology and sensory function, and the nursing risk indicators include fall risk, pressure ulcer risk, delirium risk, malnutrition risk and medication use risk. The first generation unit is used to structure and integrate the functional ability information and the nursing risk indicators based on the basic input data, and generate a joint assessment file through a weighted scoring model. The file simultaneously outputs the functional baseline value, risk category and comprehensive risk index. The second generation unit is used to automatically generate a personalized nursing intervention suggestion list by calling the nursing intervention rule base according to the comprehensive risk index and risk category in the joint assessment file, and to use the personalized nursing intervention list as the execution baseline for trend monitoring. The personalized nursing intervention list includes intervention measures, execution frequency, reassessment timing and path upgrade prompts. The adjustment unit is used to continuously collect and update the multidimensional functional ability information and the nursing risk indicators during the implementation of intervention measures, compare the execution baseline to generate a time series trend graph and a risk level change curve, and trigger a reassessment step when the trend shows that the functional indicators are declining or the risk level is rising, and automatically adjust the personalized nursing intervention list based on the reassessment results.

9. An electronic device, comprising: The memory and processor are characterized in that the processor, when executing a computer program stored in the memory, implements the steps of the elderly care method based on functional capacity and care risk as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the elderly care method based on functional capacity and care risk as described in any one of claims 1-7.

Images