Cerebral stroke user-oriented nursing scheme evaluation method and device

Abstract

The invention discloses a cerebral stroke user-oriented nursing scheme assessment method and device. The method comprises the steps of obtaining a physiological parameter information set of a to-be-assessed nursing scheme of a cerebral stroke user and a physiological parameter information set of a conventional nursing scheme; performing data preprocessing on each physiological parameter information set to obtain a preprocessed physiological parameter information set of the to-be-evaluated nursing scheme and a preprocessed physiological parameter information set of the conventional nursing scheme; and performing nursing effect quantitative evaluation processing on the preprocessed physiological parameter information set of the to-be-evaluated nursing scheme and the preprocessed physiological parameter information set of the conventional nursing scheme to obtain an evaluation effect value of the to-be-evaluated nursing scheme.

Description

Technical Field

[0001] The present invention relates to the field of medical data processing, and in particular to a nursing program evaluation method and device for stroke patients. Background Art

[0002] It is reported that stroke is one of the three most harmful diseases to humans in the world today. Domestic research shows that as one of the chronic diseases, stroke still has no radical treatment plan. Only drugs and health-related behavior patterns can prevent the occurrence and recurrence of stroke. Most stroke patients need to return to their families for rehabilitation treatment after treatment. Therefore, effective postoperative care for stroke is of great significance to the recovery of stroke users.

[0003] With the development of communication and microelectronics technology, Internet-assisted nursing models based on smart bracelets and Internet social software are being increasingly studied and applied. There is currently a lack of quantitative evaluation models for how to accurately and efficiently measure and evaluate the advantages of Internet nursing models over conventional nursing models for stroke patients. For postoperative nursing plans for stroke patients, how to quickly and accurately evaluate the effects of various nursing plans is an issue that needs to be addressed urgently. Summary of the invention

[0004] The present invention mainly solves the problem of how to quickly and accurately evaluate the effects of various nursing plans for postoperative nursing plans for cerebral stroke users. The present invention discloses a nursing plan evaluation method and device for stroke users.

[0005] In a first aspect of the embodiment of the present application, a nursing plan evaluation method for stroke users is disclosed, comprising:

[0006] S1, obtaining a set of physiological parameter information of a nursing program to be evaluated and a set of physiological parameter information of a conventional nursing program for a stroke user;

[0007] The physiological parameter information set includes a blood pressure measurement data sequence, a blood sugar measurement data sequence, a body temperature measurement data sequence, a pulse measurement data sequence, and a blood oxygen saturation measurement data sequence of the stroke user collected after the implementation of each type of nursing plan; each type of measurement data sequence is a data sequence of each type of physiological parameter collected according to the same discrete sampling time;

[0008] S2, performing data preprocessing on each physiological parameter information set to obtain a preprocessed physiological parameter information set of the nursing scheme to be evaluated and a physiological parameter information set of the conventional nursing scheme;

[0009] S3, performing a quantitative evaluation process on the pre-processed physiological parameter information set of the nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme to obtain an evaluation effect value of the nursing scheme to be evaluated;

[0010] The data preprocessing of each physiological parameter information set to obtain the preprocessed physiological parameter information set of the nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme includes:

[0011] S21, performing normalization processing on each measurement data sequence in each physiological parameter information set to obtain a corresponding normalized physiological parameter information set;

[0012] S22, performing category discrimination processing on each measurement data sequence in each normalized physiological parameter information set to obtain a corresponding physiological parameter information set with unified category;

[0013] S23, performing pattern discrimination processing on the unified physiological parameter information sets of each category to obtain corresponding pre-processed physiological parameter information sets;

[0014] The unified physiological parameter information sets of each category are subjected to pattern discrimination processing to obtain corresponding pre-processed physiological parameter information sets, including:

[0015] S231, for each data attribute of each measurement data sequence of each unified physiological parameter information set, using data acquisition information of the data as a known independent variable and data values ​​of the data as a known dependent variable, constructing a curve to be approximated using the known independent variable and the known dependent variable;

[0016] S232, using a function approximation method to perform curve fitting on the curve to be approximated to obtain a physiological characteristic polynomial of the class data attribute; using the physiological characteristic polynomial, calculating and processing the known independent variable to obtain an approximate dependent variable; judging whether the absolute value of the difference between the approximate dependent variable and the corresponding known dependent variable is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, deleting the data from the normalized physiological parameter information set; if it is less than or equal to the first regression discrimination threshold, not processing the data;

[0017] S233, performing fusion processing on all data after executing S231 to S232 of each measurement data sequence of the physiological parameter information set of the unified category to obtain a corresponding pre-processed physiological parameter information set.

[0018] The step of performing a quantitative evaluation process on the pre-processed physiological parameter information set of the nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme to obtain an evaluation effect value of the nursing scheme to be evaluated includes:

[0019] S31, the physiological parameter information set of the pre-processed nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme are respectively represented as a data matrix to be evaluated and a standard data matrix; the row vectors in the data matrix to be evaluated are the measurement data sequence of each category of the physiological parameter information set of the pre-processed nursing scheme to be evaluated; the row vectors in the standard data matrix are the measurement data sequence of each category of the physiological parameter information set of the pre-processed conventional nursing scheme;

[0020] S32, performing weight vector calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a weight vector;

[0021] S33, performing physiological index difference calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a difference vector;

[0022] S34, using the weight vector to perform weighted summation on the difference vector to obtain an evaluation effect value of the nursing plan to be evaluated.

[0023] The step of performing weight vector calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a weight vector comprises:

[0024] S321, performing correlation calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a correlation vector;

[0025] S322, using the correlation vector, performing perturbation extraction calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a perturbation matrix;

[0026] S323, decomposing the perturbation matrix to obtain a weight vector;

[0027] The related calculation process, its calculation expression is:

[0028]

[0029] Among them, V ij is the element in the i-th row and j-th column of the data matrix V to be evaluated, K ij is the element in the i-th row and j-th column of the standard data matrix K, l i is the i-th element of the correlation vector, and N is the column dimension of the data matrix V to be evaluated.

[0030] The calculation expression of the perturbation extraction calculation process is:

[0031]

[0032] Among them, y ij represents the element in the i-th row and j-th column of the perturbation matrix Y, M is the row dimension of the data matrix V to be evaluated, and ρ is the correlation calculation factor.

[0033] The decomposing the perturbation matrix to obtain a weight vector includes:

[0034] Decomposing the perturbation matrix to obtain a corresponding left decomposition matrix, a characteristic matrix and a right decomposition matrix;

[0035] The decomposition process is calculated as follows:

[0036] Y=UAV,

[0037] Among them, U is the left decomposition matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix;

[0038] Extracting the diagonal elements of the feature matrix to obtain a weight vector;

[0039] The step of calculating the difference value of physiological indicators between the data matrix to be evaluated and the standard data matrix to obtain a difference vector includes:

[0040] S331, subtracting the data matrix to be evaluated from the standard data matrix to obtain a difference matrix;

[0041] S332, performing difference extraction processing on the difference matrix to obtain a solution vector;

[0042] S333, performing geometric center extraction processing on the difference matrix to obtain a geometric center vector;

[0043] S334, subtract the solution vector from the geometric center vector and take the absolute value to obtain a difference vector.

[0044] In a second aspect of an embodiment of the present invention, a nursing plan evaluation device for stroke patients is disclosed, the device comprising:

[0045] A memory storing executable program code;

[0046] a processor coupled to the memory;

[0047] The processor calls the executable program code stored in the memory to execute the nursing plan evaluation method for stroke users.

[0048] According to a third aspect of an embodiment of the present invention, a computer storable medium is disclosed, wherein the computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the nursing plan evaluation method for stroke users.

[0049] The beneficial effects of the present invention are:

[0050] Aiming at the problem of accurate evaluation of nursing plans for stroke users, the present invention processes the collected physiological data sets of users under different nursing plans, establishes a quantitative evaluation model, and realizes accurate evaluation of nursing plans for stroke users, providing a theoretical basis for achieving scientific nursing for stroke users.

[0051] In the process of processing the physiological data of users of different evaluation schemes, the present invention adopts the method of parallel calculation of weights and difference quantities, which effectively reduces the coupling interference between the two types of quantities and improves the accuracy of the quantitative evaluation model. In the process of calculating the weight vector, by adopting the correlation calculation and perturbation extraction calculation processing, the weights of various physiological parameters are quickly extracted, and the correlation interference of the collected data of each physiological parameter is suppressed. In the process of calculating the difference vector, by establishing the difference extraction processing and geometric center extraction method, the amplification and compensation of the difference quantity are effectively realized, and the effective capture of the physiological parameter improvement brought by the nursing scheme to be evaluated is realized, and finally the accurate and efficient evaluation of the nursing scheme to be evaluated is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION

[0053] In order to better understand the content of the present invention, an embodiment is given here.

[0054] Figure 1 It is a flow chart for implementing the method of the present invention.

[0055] With regard to the postoperative nursing plans for stroke patients, how to quickly and accurately evaluate the effects of various nursing plans is a problem. The present invention discloses a nursing plan evaluation method and device for stroke patients.

[0056] In a first aspect of the embodiment of the present application, a nursing plan evaluation method for stroke users is disclosed, comprising:

[0057] S1, obtaining a set of physiological parameter information of a nursing program to be evaluated and a set of physiological parameter information of a conventional nursing program for a stroke user;

[0058] The physiological parameter information set includes a blood pressure measurement data sequence, a blood sugar measurement data sequence, a body temperature measurement data sequence, a pulse measurement data sequence, and a blood oxygen saturation measurement data sequence of the stroke user collected after the implementation of each type of nursing plan; each type of measurement data sequence is a data sequence of each type of physiological parameter collected according to the same discrete sampling time;

[0059] S2, performing data preprocessing on each physiological parameter information set to obtain a preprocessed physiological parameter information set of the nursing scheme to be evaluated and a physiological parameter information set of the conventional nursing scheme;

[0060] S3, performing a quantitative evaluation process on the pre-processed physiological parameter information set of the nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme to obtain an evaluation effect value of the nursing scheme to be evaluated;

[0061] The data preprocessing of each physiological parameter information set to obtain the preprocessed physiological parameter information set of the nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme includes:

[0062] S21, performing normalization processing on each measurement data sequence in each physiological parameter information set to obtain a corresponding normalized physiological parameter information set;

[0063] S22, performing category discrimination processing on each measurement data sequence in each normalized physiological parameter information set to obtain a corresponding physiological parameter information set with unified category;

[0064] S23, performing pattern discrimination processing on the unified physiological parameter information sets of each category to obtain corresponding pre-processed physiological parameter information sets;

[0065] The normalization process is performed on each measurement data sequence in each physiological parameter information set to obtain a corresponding normalized physiological parameter information set, including:

[0066] Each measurement data sequence in each physiological parameter information set is normalized respectively, and the corresponding normalized physiological parameter information set is constructed using all normalized measurement data sequences in each physiological parameter information set.

[0067] The step of performing category discrimination processing on each measurement data sequence in each normalized physiological parameter information set to obtain a corresponding category-unified physiological parameter information set includes:

[0068] Performing category discrimination processing on each measurement data sequence in each normalized physiological parameter information set to obtain a measurement data sequence after category discrimination processing; using all the measurement data sequences after category discrimination processing in each normalized physiological parameter information set to construct a corresponding physiological parameter information set with unified category;

[0069] The unified physiological parameter information sets of each category are subjected to pattern discrimination processing to obtain corresponding pre-processed physiological parameter information sets, including:

[0070] S231, for each data attribute of each measurement data sequence of the physiological parameter information set of the unified category, using the data acquisition information of the data as a known independent variable and the data value of the data as a known dependent variable, constructing a curve to be approximated by using the known independent variable and the known dependent variable;

[0071] S232, using a function approximation method to perform curve fitting on the curve to be approximated to obtain a physiological characteristic polynomial of the class data attribute; using the physiological characteristic polynomial, calculating and processing the known independent variable to obtain an approximate dependent variable; judging whether the absolute value of the difference between the approximate dependent variable and the corresponding known dependent variable is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, deleting the data from the normalized physiological parameter information set; if it is less than or equal to the first regression discrimination threshold, not processing the data;

[0072] S233, fusing all data after executing S231 to S232 of each measurement data sequence of the physiological parameter information set of the unified category to obtain a corresponding preprocessed physiological parameter information set;

[0073] The curve fitting of the curve to be approximated by the function approximation method may be performed by using the best consistent linear approximation method. The physiological characteristic polynomial f(Ix) is expressed as:

[0074] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α2(Ix) 2 +α1(Ix)+α0,

[0075] Wherein, P1 is the order of the physiological characteristic polynomial f(Ix), α0, α1, α2, …, α P1 are the coefficients of the physiological characteristic polynomial f(Ix);

[0076] The step of performing a quantitative evaluation process on the pre-processed physiological parameter information set of the nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme to obtain an evaluation effect value of the nursing scheme to be evaluated includes:

[0077] S31, the physiological parameter information set of the pre-processed nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme are respectively represented as a data matrix to be evaluated and a standard data matrix; the row vectors in the data matrix to be evaluated are the measurement data sequence of each category of the physiological parameter information set of the pre-processed nursing scheme to be evaluated; the row vectors in the standard data matrix are the measurement data sequence of each category of the physiological parameter information set of the pre-processed conventional nursing scheme;

[0078] S32, performing weight vector calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a weight vector;

[0079] S33, performing physiological index difference calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a difference vector;

[0080] S34, using the weight vector to perform weighted summation on the difference vector to obtain an evaluation effect value of the nursing plan to be evaluated.

[0081] The step of performing weight vector calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a weight vector comprises:

[0082] S321, performing correlation calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a correlation vector;

[0083] S322, using the correlation vector, performing perturbation extraction calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a perturbation matrix;

[0084] S323, decomposing the perturbation matrix to obtain a weight vector;

[0085] The related calculation process, its calculation expression is:

[0086]

[0087] Among them, V ij is the element in the i-th row and j-th column of the data matrix V to be evaluated, K ij is the element in the i-th row and j-th column of the standard data matrix K, l i is the i-th element of the correlation vector, and N is the column dimension of the data matrix V to be evaluated.

[0088] The calculation expression of the perturbation extraction calculation process is:

[0089]

[0090] Among them, y ij represents the element in the i-th row and j-th column of the perturbation matrix Y, M is the row dimension of the data matrix V to be evaluated, and ρ is the correlation calculation factor, which can be 0.5.

[0091] The decomposing the perturbation matrix to obtain a weight vector includes:

[0092] Decomposing the perturbation matrix to obtain a corresponding left decomposition matrix, a characteristic matrix and a right decomposition matrix;

[0093] The decomposition process is calculated as follows:

[0094] Y=UAV,

[0095] Among them, U is the left decomposition matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix;

[0096] Extracting the diagonal elements of the feature matrix to obtain a weight vector;

[0097] The decomposition process may adopt QR decomposition or the like.

[0098] The step of calculating the difference value of physiological indicators between the data matrix to be evaluated and the standard data matrix to obtain a difference vector includes:

[0099] S331, subtracting the data matrix to be evaluated from the standard data matrix to obtain a difference matrix;

[0100] S332, performing difference extraction processing on the difference matrix to obtain a solution vector;

[0101] S333, performing geometric center extraction processing on the difference matrix to obtain a geometric center vector;

[0102] S334, subtract the solution vector from the geometric center vector and take the absolute value to obtain a difference vector.

[0103] The difference extraction process is to take out the largest number in each row to form the solution vector z + ; The expression of the solution vector is:

[0104]

[0105] in, is the solution vector z + The i-th element of ijis the element in the i-th row and j-th column of the difference matrix, and m and n are the row and column dimensions of the difference matrix respectively;

[0106] The expression for the geometric center extraction process is:

[0107]

[0108] Among them, α i is the i-th element of the geometric center vector;

[0109] The category determination is to determine whether the attributes of the data in each measurement data sequence in the physiological parameter information set are consistent with the data attributes of the measurement data sequence, and to delete the inconsistent data from the measurement data sequence.

[0110] The normalization process comprises:

[0111]

[0112] Among them, x ij represents the jth data in the i-th measurement data sequence, m represents the number of measurement data sequences, n represents the number of data contained in the measurement data sequence, and x i ' j Represents the data in the normalized measurement data series.

[0113] The data collection information is a collection time value;

[0114] The nursing plan to be evaluated may be an Internet-assisted nursing plan for stroke users, which includes health education behavior, self-management behavior, and social support behavior;

[0115] The health education behavior is to provide patients with relevant knowledge, preventive measures, rehabilitation exercises and other information about cerebral stroke through WeChat public accounts, mini-programs and other platforms, so as to enhance patients' health literacy and behavioral intentions; self-management behavior is to guide patients to formulate and implement personalized self-management plans through WeChat group interactions, check-ins and other methods, including diet, exercise, medication, emotions and other aspects, to enhance patients' self-efficacy and behavioral control; social support behavior is to establish a communication and mutual assistance network between patients, family members, medical staff and volunteers through WeChat groups, video conferences and other methods, provide emotional, information and tool support, and enhance patients' social norms and behavioral cues.

[0116] The blood pressure measurement data sequence, blood sugar measurement data sequence, body temperature measurement data sequence, pulse measurement data sequence, and blood oxygen saturation measurement data sequence of the stroke user are collected by corresponding measurement sensors.

[0117] In a second aspect of an embodiment of the present invention, a nursing plan evaluation device for stroke patients is disclosed, the device comprising:

[0118] A memory storing executable program code;

[0119] a processor coupled to the memory;

[0120] The processor calls the executable program code stored in the memory to execute the nursing plan evaluation method for stroke users.

[0121] According to a third aspect of an embodiment of the present invention, a computer storable medium is disclosed, wherein the computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the nursing plan evaluation method for stroke users.

[0122] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A nursing program evaluation method for stroke patients, characterized in that: include: S1, obtaining a set of physiological parameter information of a nursing program to be evaluated and a set of physiological parameter information of a conventional nursing program for a stroke user; S2, performing data preprocessing on each physiological parameter information set to obtain a preprocessed physiological parameter information set of the nursing scheme to be evaluated and a physiological parameter information set of the conventional nursing scheme; S3, performing nursing effect quantitative evaluation processing on the pre-processed physiological parameter information set of the nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme to obtain an evaluation effect value of the nursing scheme to be evaluated.

2. The nursing program evaluation method for stroke patients according to claim 1, characterized in that: The data preprocessing of each physiological parameter information set to obtain the preprocessed physiological parameter information set of the nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme includes: S21, performing normalization processing on each measurement data sequence in each physiological parameter information set to obtain a corresponding normalized physiological parameter information set; S22, performing category discrimination processing on each measurement data sequence in each normalized physiological parameter information set to obtain a corresponding physiological parameter information set with unified category; S23, performing pattern discrimination processing on the unified physiological parameter information sets of each category to obtain corresponding pre-processed physiological parameter information sets.

3. The nursing program evaluation method for stroke patients as claimed in claim 2, characterized in that: The unified physiological parameter information sets of each category are subjected to pattern discrimination processing to obtain corresponding pre-processed physiological parameter information sets, including: S231, for each data attribute of each measurement data sequence of each unified physiological parameter information set, using data acquisition information of the data as a known independent variable and data values ​​of the data as a known dependent variable, constructing a curve to be approximated using the known independent variable and the known dependent variable; S232, using a function approximation method to perform curve fitting on the curve to be approximated to obtain a physiological characteristic polynomial of the class data attribute; using the physiological characteristic polynomial, calculating and processing the known independent variable to obtain an approximate dependent variable; judging whether the absolute value of the difference between the approximate dependent variable and the corresponding known dependent variable is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, deleting the data from the normalized physiological parameter information set; if it is less than or equal to the first regression discrimination threshold, not processing the data; S233, performing fusion processing on all data after executing S231 to S232 of each measurement data sequence of the physiological parameter information set of the unified category to obtain a corresponding pre-processed physiological parameter information set.

4. The nursing program evaluation method for stroke patients as claimed in claim 2, characterized in that: The step of performing a quantitative evaluation process on the pre-processed physiological parameter information set of the nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme to obtain an evaluation effect value of the nursing scheme to be evaluated includes: S31, the physiological parameter information set of the pre-processed nursing scheme to be evaluated and the physiological parameter information set of the conventional nursing scheme are respectively represented as a data matrix to be evaluated and a standard data matrix; the row vectors in the data matrix to be evaluated are the measurement data sequence of each category of the physiological parameter information set of the pre-processed nursing scheme to be evaluated; the row vectors in the standard data matrix are the measurement data sequence of each category of the physiological parameter information set of the pre-processed conventional nursing scheme; S32, performing weight vector calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a weight vector; S33, performing physiological index difference calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a difference vector; S34, using the weight vector to perform weighted summation on the difference vector to obtain an evaluation effect value of the nursing plan to be evaluated.

5. The nursing program evaluation method for stroke patients as claimed in claim 4, characterized in that: The step of performing weight vector calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a weight vector comprises: S321, performing correlation calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a correlation vector; S322, using the correlation vector, performing perturbation extraction calculation processing on the data matrix to be evaluated and the standard data matrix to obtain a perturbation matrix; S323, decomposing the perturbation matrix to obtain a weight vector.

6. The nursing program evaluation method for stroke patients as claimed in claim 5, characterized in that: The related calculation process, its calculation expression is: Among them, V ij is the element in the i-th row and j-th column of the data matrix V to be evaluated, K ij is the element in the i-th row and j-th column of the standard data matrix K, l i is the i-th element of the correlation vector, and N is the column dimension of the data matrix V to be evaluated; The calculation expression of the perturbation extraction calculation process is: Among them, y ij represents the element in the i-th row and j-th column of the perturbation matrix Y, M is the row dimension of the data matrix V to be evaluated, and ρ is the correlation calculation factor.

7. The nursing program evaluation method for stroke patients as claimed in claim 6, characterized in that: The decomposing the perturbation matrix to obtain a weight vector includes: Decomposing the perturbation matrix to obtain a corresponding left decomposition matrix, a characteristic matrix and a right decomposition matrix; The decomposition process is calculated as follows: Y=UAV, Among them, U is the left decomposition matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix; The diagonal elements of the feature matrix are extracted to obtain a weight vector.

8. The nursing program evaluation method for stroke patients as claimed in claim 4, characterized in that: The step of calculating the difference value of physiological indicators between the data matrix to be evaluated and the standard data matrix to obtain a difference vector includes: S331, subtracting the data matrix to be evaluated from the standard data matrix to obtain a difference matrix; S332, performing difference extraction processing on the difference matrix to obtain a solution vector; S333, performing geometric center extraction processing on the difference matrix to obtain a geometric center vector; S334, subtract the solution vector from the geometric center vector and take the absolute value to obtain a difference vector.

9. A nursing plan evaluation device for stroke patients, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the nursing plan evaluation method for stroke users as described in any one of claims 1 to 8.

10. A computer storable medium, characterized in that: The computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the nursing plan evaluation method for stroke users according to any one of claims 1 to 8.

Images