Nursing level evaluation system based on artificial intelligence
Through the nursing level assessment system based on artificial intelligence, the areas of comprehensive weighted scores, patient demand index and resource allocation need to be optimized are solved, and the problem of lack of unified evaluation standards in the existing technology has been solved, and the improvement of nursing quality and patient satisfaction has been achieved.
Patent Information
- Application Number
- CN202411475431.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-22
- Publication Date
- 2025-03-07
AI Technical Summary
The lack of unified nursing level assessment standards and inconsistent application of evaluation standards in the prior art, which makes it difficult to guarantee nursing quality and patient satisfaction.
Adopt an artificial intelligence-based nursing level assessment system, which includes a nursing data acquisition module, a nursing data analysis module, a nursing data sorting module and a nursing level classification module. By calculating comprehensive weighted scores, patient demand index and resource allocation needs optimization areas, it provides unified evaluation standards and personalized nursing plans.
A unified nursing level assessment criteria and application consistency of assessment criteria is achieved, the quality of care and patient satisfaction is improved, resource allocation is optimized, and matching care is ensured that each patient receives.
Smart Images
Figure CN119581045A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of health care technology, and in particular to a nursing level assessment system based on artificial intelligence. Background Art
[0002] Nursing classification refers to the nursing level determined by medical staff based on the patient's condition and / or self-care ability during hospitalization. In order to ensure the quality and safety of nursing, responsible nurses with corresponding abilities are reasonably arranged according to the different nursing levels of patients to implement basic nursing and specialist nursing for patients. Ensure the safety of patients, improve the quality of nursing, and improve patient satisfaction. At present, the Barthel index rating scale is often used in clinical practice to assess daily living activities, and the management ability level is determined based on the total score of the Bathel index rating scale. For special populations (children, patients with mental illness, etc.), it is necessary to refer to the specialist quantity length for determination. When evaluating this quantity length, it is mostly based on the personal understanding of experienced nurses, but the understanding between people is not consistent, resulting in some discrepancies in the evaluation between departments and hospitals. Summary of the invention
[0003] 1. Technical issues to be resolved
[0004] In view of the shortcomings of the prior art, the present invention provides an artificial intelligence-based nursing level assessment system, which has the advantages of unified assessment standards and consistent application of assessment standards, and solves the problems of the prior art lack of unified assessment standards and inconsistent application of assessment standards.
[0005] (II) Technical solution
[0006] To achieve the above-mentioned object, the present invention provides the following technical solutions: a nursing level assessment system based on artificial intelligence, comprising a nursing data acquisition module, a nursing data analysis module, a nursing data arrangement module and a nursing level classification module;
[0007] The nursing data acquisition module includes a patient admission self-care data unit, a patient hospitalization condition degree data unit and a patient in-hospital demand data unit. The patient admission self-care data unit acquires the patient admission self-care data through the admission intelligent instrument and natural language processing technology. The patient hospitalization condition degree data unit acquires the patient hospitalization condition degree data through online monitoring equipment, electronic medical records and nursing records. The patient in-hospital demand data unit acquires the patient in-hospital demand data through online monitoring equipment and patient self-reports. The patient admission self-care data unit, the patient hospitalization condition degree data unit and the patient in-hospital demand data unit are connected to the nursing data analysis module through a network;
[0008] The nursing data analysis module includes a weighted scoring unit, a nursing level determination unit and a resource allocation optimization unit. The weighted scoring unit calculates a comprehensive weighted score Qz based on the patient's admission self-care data, the patient's hospital condition severity data and the patient's in-hospital demand data. The nursing level determination unit calculates the patient demand index Pz based on the patient's in-hospital demand data. The resource allocation optimization unit calculates the resource allocation optimization area Xz based on the patient's admission self-care data, the patient's hospital condition severity data and the patient's in-hospital demand data. The weighted scoring unit, the nursing level determination unit and the resource allocation optimization unit are connected to the nursing data sorting module via a network.
[0009] Preferably, the patient admission self-care data unit numbers the patient's daily living activity data according to the patient admission self-care data characteristics, and the patient's daily living activity data number is S 1 , S 2 , S 3 ,…S n .
[0010] Preferably, the patient hospitalization condition degree data unit numbers the patient's medical condition data according to the patient hospitalization condition degree data characteristics, and the patient's medical condition data number is G 1 , G 2 , G 3 ,…G n .
[0011] Preferably, the patient in-hospital demand data unit numbers the special demand data of the patient during hospital treatment according to the characteristics of the patient in-hospital demand data, and the special demand data of the patient during hospital treatment is numbered K 1 , K 2 , K 3 ,…K n .
[0012] Preferably, the weighted scoring unit calculates the comprehensive weighted score Qz based on the patient's admission self-care data, the patient's hospitalization condition severity data, and the patient's in-hospital demand data, and the calculation formula is:
[0013]
[0014] In the formula, Qz represents the comprehensive weighted score, S 1 , S 2 , S 3 ,…S n represents the patient's daily living activities data, S i Represents a certain activity data of the patient's daily life, a i Indicates the proportion of a patient's activity data in their daily data, G1 , G 2 , G 3 ,…G n Represents the patient's medical condition data, G i Indicates a data item of the patient's medical condition, b i Indicates the proportion of a certain data item in medical conditions to all medical conditions, K 1 , K 2 , K 3 ,…K n represents the special needs data of patients during hospital treatment, K i Indicates a special demand data of the patient during hospital treatment, c i It indicates the proportion of a special demand data in the total data during hospital treatment. They respectively represent the weighting coefficients of the patient's self-care data upon admission, the patient's hospital condition severity data and the patient's in-hospital demand data in the comprehensive weighted score.
[0015] Preferably, the nursing level determination unit calculates the patient demand index Pz according to the patient's in-hospital demand data, and the calculation formula is:
[0016]
[0017] In the formula, Pz represents the patient demand index, K 1 , K 2 , K 3 ,…K n represents the special needs data of patients during hospital treatment, K i Indicates a special demand data of the patient during hospital treatment, c i It indicates the proportion of a special demand data to the total data during hospital treatment. 1 , U 2 , U 3 ,…U m represents the data of the patient's satisfied needs during hospital treatment, U i Indicates the data of a certain demand of the patient being met during the hospital treatment, c i It indicates the proportion of a certain satisfied demand data to the total satisfied demand data during hospital treatment.
[0018] Preferably, the resource allocation optimization unit calculates the resource allocation optimization area Xz according to the patient's self-care data, the patient's hospitalization condition data and the patient's hospitalization demand data.
[0019] The formula is:
[0020] XZ
[0021] =(S1 , S 2 , S 3 ,...S n ∩I 1 ,I 2 ,I 3 ,...I m )∪(G 1 , G 2 , G 3 ,...G n ∩J 1 , J 2 , J 3 ,...J m )∪(K 1 , K 2 , K 3 ,...K n ∩U 1 , U 2 , U 3 ,...U m )
[0022] In the formula, Xz represents the area that needs to be optimized for resource allocation, S 1 , S 2 , S 3 ,…S n represents the patient's daily living activities data, I 1 ,I 2 ,I 3 ,...I m Represents the patient's daily self-care activity data, (S 1 , S 2 , S 3 ,...S n ∩I 1 ,I 2 ,I 3 ,...I m ) indicates the part of the data on the patients’ daily activities that they cannot take care of themselves, G 1 , G 2 , G 3 ,…G n represents the patient's medical condition data, J 1 , J 2 , J 3 ,...J m Indicates the patient's monitored medical condition data, (G 1 , G 2 , G 3 ,...G n ∩J 1 , J 2 , J 3 ,...J m) represents the part of the patient’s medical condition data that is not monitored, K 1 , K 2 , K 3 ,…K n Indicates the special needs data of patients during hospital treatment, U 1 , U 2 , U 3 ,…U m represents the data of the patient's satisfied needs during hospital treatment, (K 1 , K 2 , K 3 ,...K n ∩U 1 , U 2 , U 3 ,...U m ) represents the portion of unmet needs data of patients during their hospital treatment.
[0023] Preferably, the nursing data sorting module increases the number of nursing visits, provides additional rehabilitation treatment or arranges special medical monitoring for the patient's hospitalization self-care data unit, the patient's hospitalization condition severity data unit and the patient's in-hospital demand data unit according to the numerical range of the comprehensive weighted score Qz, when the comprehensive score of the comprehensive weighted score Qz is higher than 60 points; and regularly evaluates the satisfaction of the patient's in-hospital demand data unit according to the numerical range of the patient's demand index Pz, when the patient's demand index Pz≤0.98.
[0024] Preferably, the nursing data sorting module optimizes area Xz according to resource allocation needs, increases the number of nurses in the area where patients cannot take care of themselves on a daily basis in the patient's self-care data unit when they are admitted to the hospital, increases the monitoring equipment in the area where patients' medical conditions are not monitored in the patient's hospitalized condition severity data unit, and adjusts the patient's demand plan during hospital treatment in the patient's in-hospital demand data unit.
[0025] Preferably, the nursing level classification module customizes the nursing level according to the comprehensive weighted score Qz, the patient demand index Pz and the resource allocation optimization area Xz.
[0026] Compared with the prior art, the present invention provides a nursing level assessment system based on artificial intelligence, which has the following beneficial effects:
[0027] 1. The present invention calculates a comprehensive weighted score Qz, each of which is based on the patient's self-care data upon admission, the patient's condition severity data upon hospitalization, and the patient's in-hospital demand data. The value obtained based on the evaluation of the weighted coefficient is that when the patient's self-care ability is very poor (the patient's self-care data upon admission, the patient's hospital condition severity data, and the patient's in-hospital demand data have high scores), the condition is severe (the patient's hospital condition severity data has a high score), and there is a high demand for care (the patient's in-hospital demand data has a high score), the comprehensive weighted score Qz will be relatively high, indicating that the patient needs more nursing resources and close monitoring (adding pathology monitoring equipment). Through the above weighted scoring mechanism, medical staff can judge the patient's specific nursing needs, thereby providing personalized care plans, optimizing resource allocation, and improving the quality of care.
[0028] 2. The present invention evaluates the specific needs of patients by calculating the patient demand index Pz. When the nursing service can meet the specific needs of patients, the patient satisfaction is improved. The system records and analyzes the needs and satisfaction of patients in real time, which helps to improve the transparency of the nursing process and enables patients and their families to better understand the nursing plan. The data collected by the nursing data acquisition module helps to optimize nursing decisions and provide a data-supported decision-making basis for nursing management. Through the above calculation method, the nursing level determination unit can evaluate the needs of patients and adjust the nursing plan according to the nursing demand data that the patients have not met, so as to ensure that the patients' unmet needs are met, thereby improving patient satisfaction and treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 It is a schematic diagram of the structure of the present invention; DETAILED DESCRIPTION
[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0031] See also Figure 1 , the artificial intelligence-based nursing level assessment system includes a nursing data acquisition module, a nursing data analysis module, a nursing data collation module and a nursing level classification module;
[0032] The nursing data acquisition module includes a patient admission self-care data unit, a patient hospitalization condition degree data unit and a patient in-hospital demand data unit. The patient admission self-care data unit acquires the patient admission self-care data through the admission intelligent instrument and natural language processing technology. The patient hospitalization condition degree data unit acquires the patient hospitalization condition degree data through online monitoring equipment, electronic medical records and nursing records. The patient in-hospital demand data unit acquires the patient in-hospital demand data through online monitoring equipment and patient self-reports. The patient admission self-care data unit, the patient hospitalization condition degree data unit and the patient in-hospital demand data unit are connected to the nursing data analysis module through the network;
[0033] The nursing data analysis module includes a weighted scoring unit, a nursing level determination unit and a resource allocation optimization unit. The weighted scoring unit calculates a comprehensive weighted score Qz based on the patient's admission self-care data, the patient's hospital condition severity data and the patient's in-hospital demand data. The nursing level determination unit calculates the patient demand index Pz based on the patient's in-hospital demand data. The resource allocation optimization unit calculates the resource allocation optimization area Xz based on the patient's admission self-care data, the patient's hospital condition severity data and the patient's in-hospital demand data. The weighted scoring unit, the nursing level determination unit and the resource allocation optimization unit are connected to the nursing data sorting module through a network.
[0034] The patient's self-care data unit numbers the patient's daily living activity data (eating, dressing and personal hygiene habits) according to the patient's self-care data characteristics. The patient's daily living activity data is numbered S 1 , S 2 , S 3 ,…S n .
[0035] The patient's hospitalized condition data unit numbers the patient's medical condition data (symptom severity and vital sign stability) according to the patient's hospitalized condition data characteristics. The patient's medical condition data number is G 1 , G 2 , G 3 ,…G n .
[0036] The patient demand data unit in hospital numbers the patient's special demand data (nursing demand, monitoring demand and special treatment demand) during hospital treatment according to the characteristics of the patient's demand data in hospital. The special demand data of the patient during hospital treatment is numbered as K. 1 , K 2 , K 3 ,…K n .
[0037] The weighted scoring unit calculates the comprehensive weighted score Qz based on the patient's self-care data upon admission, the patient's hospitalization condition data, and the patient's in-hospital demand data. The calculation formula is:
[0038]
[0039] In the formula, Qz represents the comprehensive weighted score, S 1 , S 2 , S 3 ,…S n represents the patient's daily living activities data, S i Represents a certain activity data of the patient's daily life, a i Indicates the proportion of a patient's activity data in their daily data, G 1 , G 2 , G 3 ,…G n Represents the patient's medical condition data, G i Indicates a data item of the patient's medical condition, b i Indicates the proportion of a certain data item in medical conditions to all medical conditions, K 1 , K 2 , K 3 ,…K n represents the special needs data of patients during hospital treatment, K i Indicates a special demand data of the patient during hospital treatment, c i It indicates the proportion of a special demand data in the total data during hospital treatment. They respectively represent the weighting coefficients of the patient's self-care data upon admission, the patient's hospital condition severity data and the patient's in-hospital demand data in the comprehensive weighted score.
[0040] The advantages are: by calculating the comprehensive weighted score Qz, each weighted score is based on the patient's admission self-care data, the patient's hospitalization condition data and the patient's in-hospital demand data. The value obtained based on the evaluation of the weighted coefficient is that when the patient's self-care ability is very poor (the patient's self-care data upon admission, the patient's hospital condition severity data, and the patient's in-hospital demand data have high scores), the condition is severe (the patient's hospital condition severity data has a high score), and there is a high demand for care (the patient's in-hospital demand data has a high score), the comprehensive weighted score Qz will be relatively high, indicating that the patient needs more nursing resources and close monitoring (adding pathology monitoring equipment). Through the above weighted scoring mechanism, medical staff can judge the patient's specific nursing needs, thereby providing personalized care plans, optimizing resource allocation, and improving the quality of care.
[0041] The nursing level determination unit calculates the patient demand index Pz based on the patient's in-hospital demand data, and the calculation formula is:
[0042]
[0043] In the formula, Pz represents the patient demand index, K 1 , K 2 , K 3 ,…K n represents the special needs data of patients during hospital treatment, K i Indicates a special demand data of the patient during hospital treatment, c i It indicates the proportion of a special demand data to the total data during hospital treatment. 1 , U 2 , U 3 ,…U m represents the data of the patient's satisfied needs during hospital treatment, U i Indicates the data of a certain demand of the patient being met during the hospital treatment, c i It indicates the proportion of a certain satisfied demand data to the total satisfied demand data during hospital treatment.
[0044] The advantages are: by calculating the patient demand index Pz, the specific needs of the patient are evaluated. When the nursing service can meet the patient's specific needs, the patient satisfaction is improved. The system records and analyzes the patient's needs and satisfaction in real time, which helps to improve the transparency of the nursing process and enables patients and their families to better understand the nursing plan. The data collected by the nursing data acquisition module helps to optimize nursing decisions and provide a data-supported decision-making basis for nursing management. Through the above calculation method, the nursing level determination unit can evaluate the patient's needs and adjust the nursing plan according to the patient's unmet nursing needs data to ensure that the patient's unmet needs are met, thereby improving patient satisfaction and treatment effects.
[0045] The resource allocation optimization unit calculates the resource allocation optimization area Xz based on the patient's self-care data, the patient's hospitalization condition data, and the patient's hospital demand data. The calculation formula is:
[0046] XZ
[0047] =(S 1 , S 2 , S 3 ,..S n ∩I 1 ,I 2 ,I 3 ,...I m )∪(G 1 , G 2 , G 3 ,...G n ∩J 1 , J2 , J 3 ,...J m )∪(K 1 , K 2 , K 3 ,...K n ∩U 1 , U 2 , U 3 ,...U m )
[0048] In the formula, Xz represents the area that needs to be optimized for resource allocation, S 1 , S 2 , S 3 ,…S n represents the patient's daily living activities data, I 1 ,I 2 ,I 3 ,...I m Represents the patient's daily self-care activity data, (S 1 , S 2 , S 3 ,...S n ∩I 1 ,I 2 ,I 3 ,...I m ) indicates the part of the data on the patients’ daily activities that they cannot take care of themselves, G 1 , G 2 , G 3 ,…G n represents the patient's medical condition data, J 1 , J 2 , J 3 ,...J m Indicates the patient's monitored medical condition data, (G 1 , G 2 , G 3 ,...G n ∩J 1 , J 2 , J 3 ,...J m ) represents the part of the patient’s medical condition data that is not monitored, K 1 , K 2 , K 3 ,…K n Indicates the special needs data of patients during hospital treatment, U 1 , U 2 , U 3 ,…U m represents the data of the patient's satisfied needs during hospital treatment, (K 1 , K 2 , K3 ,...K n ∩U 1 , U 2 , U 3 ,...U m ) represents the portion of unmet needs data of patients during their hospital treatment.
[0049] The advantages are: by calculating the area Xz that needs to be optimized for resource allocation, it is helpful to divide the area where patients cannot take care of themselves in daily activities, the area where patients' medical conditions are not monitored, and the area where patients' unmet needs are during hospital treatment, and then redivide resources to improve the above parts, so that the resource allocation optimization unit can evaluate the gap between the actual needs of patients and existing resources, and adjust resource allocation accordingly to ensure that each patient receives matching care.
[0050] The nursing data collation module increases the number of nursing visits, provides additional rehabilitation treatment, or arranges special medical monitoring for the patient's hospitalization self-care data unit, the patient's hospitalization condition severity data unit, and the patient's in-hospital demand data unit based on the numerical range of the comprehensive weighted score Qz. When the comprehensive score of the comprehensive weighted score Qz is higher than 60 points, the nursing data collation module also regularly evaluates the satisfaction of the patient's in-hospital demand data unit based on the numerical range of the patient's demand index Pz. When the patient's demand index Pz≤0.98, the patient's in-hospital demand data unit is adjusted based on the patient's feedback and treatment progress. This helps ensure that nursing measures always meet the patient's changing needs.
[0051] The nursing data sorting module optimizes area Xz according to resource allocation needs, increases the number of nurses in the area where patients cannot take care of themselves in the daily self-care data unit, increases the monitoring equipment in the area where patients' medical conditions are not monitored in the patient's hospital condition data unit, and adjusts the patient's demand plan during hospital treatment in the patient's in-hospital demand data unit.
[0052] The nursing level classification module customizes the nursing level according to the comprehensive weighted score Qz, the patient demand index Pz and the resource allocation optimization area Xz. The customization process is as follows:
[0053] Comprehensive weighted score Qz:
[0054] Level 1 care: When the comprehensive weighted score Qz is greater than 70 points, it means that the patient's needs are very high and require close medical monitoring and high-intensity nursing services;
[0055] Secondary care: When the comprehensive weighted score Qz is between 50 and 70 points, it means that the patient needs more intensive nursing services, but does not require continuous high-intensity monitoring;
[0056] Level 3 care: When the comprehensive weighted score Qz is less than 50 points, it means that the patient needs basic nursing services and can undergo regular checkups, but does not require intensive care.
[0057] Patient demand index Pz:
[0058] Level 1 care: When the patient needs index Pz>1.2, the patient needs professional medical intervention and continuous nursing support;
[0059] Secondary care: When the patient need index Pz is between 0.98-1.2, the patient needs regular care and monitoring;
[0060] Level 3 care: When the patient needs index Pz≤0.98, the patient requires routine care and monitoring.
[0061] Resource allocation requires optimization of region Xz:
[0062] Level 1 care: When the indicator number of resource allocation optimization area Xz is high, it means that a large amount of nursing resources and urgent intervention are required;
[0063] Secondary care: When the indicator of resource allocation optimization area Xz is in the medium range, it means that resource allocation needs to be optimized, but it is not an emergency;
[0064] Level 3 care: When the indicator number of the resource allocation optimization area Xz is low, it means that the resource allocation is relatively reasonable and only daily maintenance and minor adjustments are needed.
[0065] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. Nursing level assessment system based on artificial intelligence, characterized by: It includes nursing data acquisition module, nursing data analysis module, nursing data sorting module and nursing level classification module; The nursing data acquisition module includes a patient admission self-care data unit, a patient hospitalization condition degree data unit and a patient in-hospital demand data unit. The patient admission self-care data unit acquires the patient admission self-care data through the admission intelligent instrument and natural language processing technology. The patient hospitalization condition degree data unit acquires the patient hospitalization condition degree data through online monitoring equipment, electronic medical records and nursing records. The patient in-hospital demand data unit acquires the patient in-hospital demand data through online monitoring equipment and patient self-reports. The patient admission self-care data unit, the patient hospitalization condition degree data unit and the patient in-hospital demand data unit are connected to the nursing data analysis module through a network; The nursing data analysis module includes a weighted scoring unit, a nursing level determination unit and a resource allocation optimization unit. The weighted scoring unit calculates a comprehensive weighted score Qz based on the patient's admission self-care data, the patient's hospital condition severity data and the patient's in-hospital demand data. The nursing level determination unit calculates the patient demand index Pz based on the patient's in-hospital demand data. The resource allocation optimization unit calculates the resource allocation optimization area Xz based on the patient's admission self-care data, the patient's hospital condition severity data and the patient's in-hospital demand data. The weighted scoring unit, the nursing level determination unit and the resource allocation optimization unit are connected to the nursing data sorting module via a network.
2. The artificial intelligence-based nursing level assessment system according to claim 1, characterized in that: The patient admission self-care data unit numbers the patient's daily living activity data according to the patient admission self-care data characteristics, and the patient's daily living activity data are numbered S1, S2, S3, ... S n .
3. The artificial intelligence-based nursing level assessment system according to claim 1, characterized in that: The patient's inpatient condition data unit numbers the patient's medical condition data according to the patient's inpatient condition data characteristics, and the patient's medical condition data are numbered G1, G2, G3, ... G n .
4. The artificial intelligence-based nursing level assessment system according to claim 1, characterized in that: The patient's in-hospital demand data unit numbers the patient's special demand data during hospital treatment according to the patient's in-hospital demand data characteristics. The patient's special demand data during hospital treatment are numbered as K1, K2, K3, ..., K n .
5. The artificial intelligence-based nursing level assessment system according to claim 4, characterized in that: The weighted scoring unit calculates the comprehensive weighted score Qz according to the patient's admission self-care data, the patient's hospitalization condition data and the patient's in-hospital demand data, and the calculation formula is: In the formula, Qz represents the comprehensive weighted score, S1, S2, S3, ...S n represents the patient's daily living activities data, S i Represents a certain activity data of the patient's daily life, a i Indicates the proportion of a patient's activity data in their daily data, G1, G2, G3, ...G n Represents the patient's medical condition data, G i represents a certain data of the patient's medical condition, bi represents the proportion of a certain data of the medical condition to all medical conditions, K1, K2, K3, ...K n represents the special needs data of patients during hospital treatment, K i Indicates a special demand data of the patient during hospital treatment, c i It indicates the proportion of a special demand data in the total data during hospital treatment. They respectively represent the weighting coefficients of the patient's self-care data upon admission, the patient's hospital condition severity data and the patient's in-hospital demand data in the comprehensive weighted score.
6. The artificial intelligence-based nursing level assessment system according to claim 3, characterized in that: The nursing level determination unit calculates the patient demand index Pz according to the patient's in-hospital demand data, and the calculation formula is: In the formula, Pz represents the patient demand index, K1, K2, K3, ...K n represents the special needs data of patients during hospital treatment, K i Indicates a special demand data of the patient during hospital treatment, c i Indicates the proportion of a special demand data to the total data during hospital treatment, U1, U2, U3, ...U m represents the data of the patient's satisfied needs during hospital treatment, U i Indicates the data of a certain demand of the patient being met during the hospital treatment, c i It indicates the proportion of a certain satisfied demand data to the total satisfied demand data during hospital treatment.
7. The artificial intelligence-based nursing level assessment system according to claim 4, characterized in that: The resource allocation optimization unit calculates the resource allocation optimization area Xz according to the patient's self-care data, the patient's hospitalization condition data and the patient's hospitalization demand data, and the calculation formula is: Xz=(S1、S2、S3、...S n ∩I1、I2、I3、...I m )∪(G1、G2、G3、...G n ∩J1、J2、J3、...J m )∪(K1、K2、K3、...K n ∩U1、U2、U3、...U m ) In the formula, Xz represents the area that needs to be optimized for resource allocation, S1, S2, S3, ...S n Represents the patient's daily living activities data, I1, I2, I3, ...I m Represents the patient's daily self-care activity data, (S1, S2, S3, ...S n ∩I1, I2, I3, ...I m ) indicates the data of the patient's daily activities that cannot be taken care of by himself, G1, G2, G3, ...G n Represents the patient's medical condition data, J1, J2, J3, ...J m Indicates the patient's monitored medical condition data, (G1, G2, G3, ...G n ∩J1, J2, J3, ...J m ) represents the part of the patient's medical condition data that is not monitored, K1, K2, K3, ... K n Represents the special needs data of patients during hospital treatment, U1, U2, U3, ...U m Represents the data of the patient's satisfied needs during hospital treatment, (K1, K2, K3, ...K n ∩U1, U2, U3, ...U m ) represents the portion of unmet needs data of patients during their hospital treatment.
8. The artificial intelligence-based nursing level assessment system according to claim 7, characterized in that: The nursing data sorting module increases the number of nursing visits, provides additional rehabilitation treatment or arranges special medical monitoring for the patient's hospitalization self-care data unit, the patient's hospitalization condition severity data unit and the patient's in-hospital demand data unit according to the numerical range of the comprehensive weighted score Qz, when the comprehensive score of the comprehensive weighted score Qz is higher than 60 points; and regularly evaluates the satisfaction of the patient's in-hospital demand data unit according to the numerical range of the patient's demand index Pz, when the patient's demand index Pz≤0.
98.
9. The artificial intelligence-based nursing level assessment system according to claim 7, characterized in that: The nursing data sorting module optimizes area Xz according to resource allocation needs, increases the number of nurses in the area where patients cannot take care of themselves daily in the patient's self-care data unit after admission, increases the monitoring equipment in the area where patients' medical conditions are not monitored in the patient's hospital condition data unit, and adjusts the patient's demand plan during hospital treatment in the patient's hospital demand data unit.
10. The artificial intelligence-based nursing level assessment system according to claim 9, characterized in that: The nursing level classification module customizes the nursing level according to the comprehensive weighted score Qz, the patient demand index Pz and the resource allocation optimization area Xz.