User health monitoring device and method for hospital bed

Abstract

The present invention discloses a user health monitoring device and method for a hospital bed, the device comprising: an information acquisition module, a weight measurement module, a body fat measurement module, a human body composition measurement and analysis module, a data acquisition module, and a data evaluation module; the information acquisition module is used to acquire basic information of the user; the basic information includes age, gender, disease information, and surgical information; the weight measurement module is used to measure the user's weight information; the body fat measurement module is used to measure the user's body fat percentage; the human body composition measurement and analysis module is used to measure the user's human body composition analysis information set; the data evaluation module is connected to the information acquisition module and the data acquisition module, and is used to perform health monitoring and evaluation processing on the basic information, weight information, body fat percentage, and human body composition analysis information set to obtain health monitoring result information.

Description

Technical Field

[0001] The present invention relates to the medical field and the health monitoring field, and in particular to a user health monitoring device and method for a hospital bed. Background Art

[0002] During hospital treatment, critically ill patients or people with mobility difficulties need to be moved to the side of health monitoring equipment for physical health examinations due to their limited mobility. This process is time-consuming and labor-intensive and causes a lot of inconvenience to users.

[0003] Currently, beds for critically ill patients or those with limited mobility are typically equipped with a fixed, standard pager terminal or smart pager terminal at the bedside. This makes it difficult to fully monitor the user's health status within the existing bed environment. For critically ill patients, continuous health monitoring using a bed platform is crucial for their treatment and recovery. Summary of the Invention

[0004] The present invention mainly solves the problem of how to comprehensively monitor the health status of a user based on the existing hospital bed environment. The present invention discloses a user health monitoring device and method for a hospital bed.

[0005] In a first aspect of an embodiment of the present application, a user health monitoring device for a hospital bed is disclosed, comprising:

[0006] Information acquisition module, weight measurement module, body fat measurement module, body composition measurement and analysis module, data acquisition module, data evaluation module;

[0007] The information collection module is used to collect basic information of the user, including age, gender, disease information, and surgery information;

[0008] The weight measurement module is used to measure and obtain the user's weight information;

[0009] The body fat measurement module is used to measure the user's body fat percentage;

[0010] The body composition measurement and analysis module is used to measure and obtain a body composition analysis information set of the user; the body composition analysis information set includes a total body water value, a total protein value, a total inorganic salt value, a right upper muscle weight, a left upper muscle weight, a right lower muscle weight, a left lower muscle weight, and an extracellular water ratio value;

[0011] The data acquisition module is connected to the information acquisition module, weight measurement module, body fat measurement module, and human body composition measurement and analysis module respectively, and is used to collect basic information, weight information, body fat percentage value, and human body composition analysis information set, and send the collected basic information, weight information, body fat percentage value, and human body composition analysis information set to the data evaluation module;

[0012] The data evaluation module is connected to the information acquisition module and the data acquisition module, and is used to perform health monitoring evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information.

[0013] The weight measurement module is arranged on the upper surface of the bed board of the hospital bed;

[0014] The body fat measurement module includes a measuring electrode and a data processing submodule; the measuring electrode is connected to the data processing submodule and is used to collect the user's skin electrical signals; the data processing submodule is used to measure and process the collected skin electrical signals of the user to obtain the user's body fat percentage value; the measuring electrode includes an electrode body and a mounting bracket, the electrode body is installed on the mounting bracket; the mounting bracket is installed in the middle position of both sides of the upper surface of the bed board of the bed.

[0015] The body composition measurement and analysis module includes measurement electrodes, a mounting bracket, and a data analysis submodule;

[0016] The measuring electrode is mounted on the mounting bracket;

[0017] The mounting bracket is installed in the middle position of both sides of the upper surface of the bed board and in the middle position of the bottom of the upper surface of the bed board; the measuring electrode is connected to the data analysis submodule to collect the user's skin electrical signals; the data analysis submodule is used to perform human body composition analysis on the collected user's skin electrical signals to obtain a human body composition analysis information set.

[0018] The data evaluation module is used to perform health monitoring evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information, including:

[0019] The data evaluation module constructs a health monitoring time series information set using the weight information, body fat percentage value, and human body composition analysis information set collected at several moments; the health monitoring time series information set includes a weight sequence, a body fat percentage sequence, a total body water value sequence, a total protein value sequence, a total inorganic salt value sequence, a right upper muscle weight sequence, a left upper muscle weight sequence, a right lower muscle weight sequence, a left lower muscle weight sequence, and an extracellular water ratio value sequence;

[0020] Performing data preprocessing on the health monitoring time series information set to obtain a preprocessed sequence set;

[0021] Determine a corresponding standard sequence set based on the basic information; the standard sequence set includes a weight standard sequence, a body fat percentage standard sequence, a total body water value standard sequence, a total protein value standard sequence, a total inorganic salt value standard sequence, a right upper muscle weight standard sequence, a left upper muscle weight standard sequence, a right lower muscle weight standard sequence, a left lower muscle weight standard sequence, and an extracellular water ratio value standard sequence; the standard sequence set corresponding to each type of basic information is stored in the data evaluation module;

[0022] Perform health assessment processing on the pre-processing sequence set and the standard sequence set to obtain health monitoring result information.

[0023] The performing data preprocessing on the health monitoring time series information set to obtain a preprocessed sequence set includes:

[0024] Performing data cleaning on the health monitoring time series information set to obtain a first sequence set;

[0025] Data category detection processing is performed on the first sequence set to obtain a preprocessed sequence set.

[0026] A second aspect of an embodiment of the present invention discloses a user health monitoring method for a hospital bed, which is implemented using the user health monitoring device for a hospital bed, comprising:

[0027] S1, using the information collection module to collect basic information of the user; using the weight measurement module to measure the weight information of the user; using the body fat measurement module to measure the body fat percentage of the user;

[0028] S2, using the body composition measurement and analysis module to measure and obtain a body composition analysis information set of the user;

[0029] S3, using the data acquisition module to respectively acquire basic information, weight information, body fat percentage value, and body composition analysis information set from the information acquisition module, weight measurement module, body fat measurement module, and body composition measurement and analysis module, and sending the acquired basic information, weight information, body fat percentage value, and body composition analysis information set to the data evaluation module;

[0030] S4, using the data evaluation module, performing health monitoring evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information.

[0031] The data evaluation module performs health monitoring evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information, including:

[0032] S41, constructing a health monitoring time series information set using the weight information, body fat percentage, and body composition analysis information set collected at multiple moments; the health monitoring time series information set includes a weight sequence, a body fat percentage sequence, a total body water value sequence, a total protein value sequence, a total inorganic salt value sequence, a right upper muscle weight sequence, a left upper muscle weight sequence, a right lower muscle weight sequence, a left lower muscle weight sequence, and an extracellular water ratio value sequence;

[0033] S42, performing data preprocessing on the health monitoring time series information set to obtain a preprocessed sequence set;

[0034] S43, determining a corresponding standard sequence set based on the basic information; the standard sequence set includes a weight standard sequence, a body fat percentage standard sequence, a total body water value standard sequence, a total protein value standard sequence, a total inorganic salt value standard sequence, a right upper muscle weight standard sequence, a left upper muscle weight standard sequence, a right lower muscle weight standard sequence, a left lower muscle weight standard sequence, and an extracellular water ratio value standard sequence;

[0035] S44: Perform health assessment processing on the pre-processing sequence set and the standard sequence set to obtain health monitoring result information.

[0036] The data preprocessing of the health monitoring time series information set to obtain a preprocessed sequence set includes:

[0037] Performing data cleaning on the health monitoring time series information set to obtain a first sequence set;

[0038] Data category detection processing is performed on the first sequence set to obtain a preprocessed sequence set.

[0039] The health assessment process is performed on the pre-processed sequence set and the standard sequence set to obtain health monitoring result information, including:

[0040] Performing a first evaluation process on the weight sequence and the body fat percentage sequence in the preprocessed sequence set to obtain a first evaluation result value;

[0041] performing a second evaluation process on the body total water value sequence, the total protein value sequence, the total inorganic salt value sequence, the right upper muscle weight sequence, the left upper muscle weight sequence, the right lower muscle weight sequence, the left lower muscle weight sequence, and the extracellular water ratio value sequence in the preprocessing sequence set to obtain a second evaluation result value;

[0042] Performing weight calculation processing on the preprocessing sequence set to obtain a first weight value and a second weight value;

[0043] The first evaluation result value and the second evaluation result value are weighted and summed using the first weight value and the second weight value to obtain health monitoring result information.

[0044] The expression of the first evaluation process is:

[0045]

[0046] a i =sin(|w 0i -w i | / |w 0i +w i |)+|exp(w i / w0)-t1| / |w i +w0|,

[0047]

[0048] Among them, q i is the i-th item of the weight sequence in the preprocessing sequence set, r i is the i-th item of the cross-correlation sequence between the weight sequence and the weight standard sequence in the pre-processing sequence set, q 0i is the i-th item of the weight standard sequence, ρ1 and ρ2 are the preset first constant factor and second constant factor respectively, v i is the i-th item in the weight evaluation sequence, w 0i is the i-th item in the standard sequence of body fat percentage, w i is the i-th item of the body fat percentage sequence in the preprocessing sequence set, w0 is the mean of all elements of the body fat percentage standard sequence, t1 is the preset third constant factor, a i is the i-th item in the body fat percentage evaluation sequence, and pj1 is the first evaluation result value.

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

[0050] Relying on the existing hospital bed environment, the present invention has developed a dedicated user health monitoring device and method to achieve comprehensive monitoring of the user's health status; especially for critically ill patients, the present invention uses the hospital bed platform to continuously monitor their health status, which is of great significance to their treatment and rehabilitation process.

[0051] The present invention realizes continuous monitoring of the user's multi-source health information by setting up an information collection module, a weight measurement module, a body fat measurement module, and a human body composition measurement and analysis module; the present invention divides the user's health monitoring information into two categories: weight information and composition information through a data evaluation module, and designs different evaluation models to monitor the two categories of information separately; after obtaining the monitoring results, the weight values ​​of the two categories of information are calculated separately to obtain different weight values, and the weight values ​​are used to achieve accurate fusion of the two categories of information, thereby achieving accurate evaluation of the user's health status. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a composition diagram of the device of the present invention;

[0053] Figure 2 4 is an implementation flow chart of the method of the present invention. DETAILED DESCRIPTION

[0054] In order to better understand the content of the present invention, an embodiment is given here.

[0055] Figure 1 It is a composition diagram of the device of the present invention; Figure 2 4 is an implementation flow chart of the method of the present invention.

[0056] In a first aspect of an embodiment of the present application, a user health monitoring device for a hospital bed is disclosed, comprising: an information acquisition module, a weight measurement module, a body fat measurement module, a body composition measurement and analysis module, a data acquisition module, and a data evaluation module;

[0057] The information collection module is used to collect basic information of the user; the basic information includes age, gender, medical information, surgical information, etc.; the medical information includes information about the disease, and the surgical information includes whether surgery is required and the type of surgery;

[0058] The weight measurement module is used to measure and obtain the user's weight information;

[0059] The body fat measurement module is used to measure the user's body fat percentage;

[0060] The body composition measurement and analysis module is used to measure and obtain a body composition analysis information set of the user; the body composition analysis information set includes a total body water value, a total protein value, a total inorganic salt value, a right upper muscle weight, a left upper muscle weight, a right lower muscle weight, a left lower muscle weight, and an extracellular water ratio value;

[0061] The data acquisition module is connected to the weight measurement module, the body fat measurement module, and the body composition measurement and analysis module respectively, and is used to collect weight information, body fat percentage value, and body composition analysis information set, and send the collected weight information, body fat percentage value, and body composition analysis information set to the data evaluation module;

[0062] The data evaluation module is connected to the information acquisition module and the data acquisition module, and is used to perform health monitoring and evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information;

[0063] The data acquisition module collects corresponding information from the information acquisition module, weight measurement module, body fat measurement module, and body composition measurement and analysis module;

[0064] The weight measurement module is arranged on the upper surface of the bed board of the hospital bed;

[0065] The weight measurement module needs to be calibrated before use to record the weight of the bedding on the bed board of the hospital bed and subtract the weight in subsequent measurements.

[0066] The weight measurement module can be implemented using a weight measurement sensor;

[0067] The body fat measurement module can be implemented using a body fat measurement device;

[0068] The human body composition measurement and analysis module can be implemented using a human body composition analyzer.

[0069] The body fat measurement module includes a measuring electrode and a data processing submodule; the measuring electrode is connected to the data processing submodule and is used to collect the user's skin electrical signals; the data processing submodule is used to process the collected user's skin electrical signals to obtain the user's body fat percentage value; the measuring electrode includes an electrode body and a mounting bracket, and the electrode body is installed on the mounting bracket; the mounting bracket is installed in the middle position of both sides of the upper surface of the bed board of the hospital bed, specifically, it can be the position corresponding to the user's hands when the user lies flat on the bed board.

[0070] The body composition measurement and analysis module includes measurement electrodes, a mounting bracket, and a data analysis submodule;

[0071] The measuring electrode is mounted on the mounting bracket;

[0072] The mounting brackets are mounted on the middle positions of both sides of the upper surface of the bed board and the middle position of the bottom of the upper surface of the bed board; the measuring electrodes are connected to the data analysis submodule to collect the user's skin electrical signals; the data analysis submodule is used to process the collected user's skin electrical signals to obtain a body composition analysis information set;

[0073] The data evaluation module is used to perform health monitoring evaluation processing on the weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information, including:

[0074] The data evaluation module constructs a health monitoring time series information set using the weight information, body fat percentage value, and human body composition analysis information set collected at several moments; the health monitoring time series information set includes a weight sequence, a body fat percentage sequence, a total body water value sequence, a total protein value sequence, a total inorganic salt value sequence, a right upper muscle weight sequence, a left upper muscle weight sequence, a right lower muscle weight sequence, a left lower muscle weight sequence, and an extracellular water ratio value sequence;

[0075] Performing data preprocessing on the health monitoring time series information set to obtain a preprocessed sequence set;

[0076] Determine a corresponding standard sequence set based on the basic information; the standard sequence set includes a weight standard sequence, a body fat percentage standard sequence, a total body water value standard sequence, a total protein value standard sequence, a total inorganic salt value standard sequence, a right upper muscle weight standard sequence, a left upper muscle weight standard sequence, a right lower muscle weight standard sequence, a left lower muscle weight standard sequence, and an extracellular water ratio value standard sequence; the standard sequence set corresponding to each type of basic information is stored in the data evaluation module;

[0077] Performing health assessment processing on the pre-processing sequence set and the standard sequence set to obtain health monitoring result information;

[0078] The data preprocessing of the health monitoring time series information set to obtain a preprocessed sequence set includes:

[0079] Performing data cleaning on the health monitoring time series information set to obtain a first sequence set;

[0080] performing data category detection processing on the first sequence set to obtain a preprocessed sequence set;

[0081] The health assessment process is performed on the pre-processed sequence set and the standard sequence set to obtain health monitoring result information, including:

[0082] Performing a first evaluation process on the weight sequence and the body fat percentage sequence in the preprocessed sequence set to obtain a first evaluation result value;

[0083] performing a second evaluation process on the body total water value sequence, the total protein value sequence, the total inorganic salt value sequence, the right upper muscle weight sequence, the left upper muscle weight sequence, the right lower muscle weight sequence, the left lower muscle weight sequence, and the extracellular water ratio value sequence in the preprocessing sequence set to obtain a second evaluation result value;

[0084] Performing weight calculation processing on the preprocessing sequence set to obtain a first weight value and a second weight value;

[0085] Using the first weight value and the second weight value, performing weighted sum processing on the first evaluation result value and the second evaluation result value to obtain health monitoring result information;

[0086] The weighted summing process of the first evaluation result value and the second evaluation result value using the first weight value and the second weight value is to multiply the first evaluation result value by the first weight value, multiply the second evaluation result value by the second weight value, and add the two multiplied results to obtain the health monitoring result information;

[0087] The expression of the first evaluation process is:

[0088]

[0089] a i =sin(|w 0i -w i | / |w 0i +w i |)+|exp(w i / w0)-t1| / |w i +w0|,

[0090]

[0091] Among them, q i is the i-th item of the weight sequence in the preprocessing sequence set, r i is the i-th item of the cross-correlation sequence between the weight sequence and the weight standard sequence in the pre-processing sequence set, q 0i is the i-th item of the weight standard sequence, ρ1 and ρ2 are the preset first constant factor and second constant factor respectively, v i is the i-th item in the weight evaluation sequence, w 0i is the i-th item in the standard sequence of body fat percentage, w i is the i-th item of the body fat percentage sequence in the preprocessing sequence set, w0 is the mean of all elements of the body fat percentage standard sequence, t1 is the preset third constant factor, ai is the i-th item in the body fat percentage evaluation sequence, and pj1 is the first evaluation result value.

[0092] The expression of the second evaluation process is:

[0093] A body composition measurement matrix is ​​constructed using the body total water value sequence, total protein value sequence, total inorganic salt value sequence, right upper muscle weight sequence, left upper muscle weight sequence, right lower muscle weight sequence, left lower muscle weight sequence, and extracellular water ratio value sequence in the preprocessing sequence set as row vectors; the row vectors of the body composition measurement matrix are the body total water value sequence, total protein value sequence, total inorganic salt value sequence, right upper muscle weight sequence, left upper muscle weight sequence, right lower muscle weight sequence, left lower muscle weight sequence, and extracellular water ratio value sequence in the preprocessing sequence set;

[0094] A body composition standard matrix is ​​constructed using the body total water value standard sequence, total protein value standard sequence, total inorganic salt value standard sequence, right upper muscle weight standard sequence, left upper muscle weight standard sequence, right lower muscle weight standard sequence, left lower muscle weight standard sequence, and extracellular water ratio value standard sequence;

[0095] multiplying the transposed matrices of the body composition measurement matrix and the body composition standard matrix to obtain a correlation matrix;

[0096] Decomposing the correlation matrix to obtain an eigenvector matrix and an eigenvalue matrix;

[0097] Each eigenvalue is judged to determine whether the eigenvalue is greater than a preset eigenthreshhold value, and a judgment result value is obtained; the eigenvalue for which all judgment results are greater than a predetermined eigenvalue is determined as the first eigenvalue;

[0098] A first characteristic matrix is ​​constructed using the eigenvectors corresponding to all first eigenvalues; the row vectors of the first characteristic matrix are the eigenvectors corresponding to the first eigenvalues;

[0099] Using the mean of each row vector of the first characteristic matrix, and performing weighted summation with the first eigenvalue corresponding to the row vector, a second evaluation result value is obtained;

[0100] The weighted summation process of the second evaluation result value is:

[0101]

[0102] Among them, pj2 is the second evaluation result value, aa i is the first eigenvalue of the i-th element, bb i is the mean of the row vector corresponding to the i-th first eigenvalue, M1 is the number of first eigenvalues;

[0103] The performing weight calculation processing on the preprocessing sequence set to obtain a first weight value and a second weight value includes:

[0104] Perform statistical analysis on the weight sequence and body fat percentage sequence to obtain corresponding means and variances;

[0105] Perform weight calculation on the means and variances of the weight sequence and the body fat percentage sequence to obtain a corresponding first weight value z1;

[0106] The calculation expression of the first weight value is:

[0107] z1=tan|(μ1μ2) / (σ1σ2)|,

[0108] Among them, μ1 and μ2 are the means of the weight sequence and body fat percentage sequence, respectively, σ1 and σ2 are the variances of the weight sequence and body fat percentage sequence, respectively;

[0109] Using the body total water value sequence, total protein value sequence, total inorganic salt value sequence, right upper muscle weight sequence, left upper muscle weight sequence, right lower muscle weight sequence, left lower muscle weight sequence and extracellular water ratio value sequence in the preprocessing sequence set as row vectors, a body composition measurement matrix is ​​constructed;

[0110] performing a second weight value calculation process on the body composition measurement matrix to obtain a second weight value;

[0111] The expression for the second weight value calculation process is:

[0112]

[0113] Among them, A1 ij is the element in row i and column j of the body composition measurement matrix, A2 ij is the element in the i-th row and j-th column of the body composition standard matrix, N2 and M2 are the row dimension and column dimension of the body composition standard matrix respectively, and z2 is the second weight value;

[0114] The decomposition process may be an eigenvalue decomposition process;

[0115] The decomposition process of the correlation matrix to obtain an eigenvector matrix and an eigenvalue matrix includes:

[0116] K=UΛU T ,

[0117] Where K is the correlation matrix, U is the eigenvector matrix, and Λ is the eigenvalue matrix;

[0118] Specifically, the middle position of the bottom of the upper surface of the bed board corresponds to the position of the user's feet when the user lies flat on the bed board; the middle positions on both sides of the upper surface of the bed board correspond to the positions of the user's hands when the user lies flat on the bed board.

[0119] The standard sequence is constructed by randomly taking values ​​from the value interval of each type of measurement quantity.

[0120] The health monitoring result information is used to represent the user's health status. The smaller the value, the healthier the user.

[0121] The data cleaning process includes filling missing values, smoothing noise data, and smoothing or deleting outliers. Smoothing noise data involves first identifying noise data and then smoothing it based on the preceding and following data. Noise data is defined as values ​​that are less than the sensor's sensitivity or greater than the sensor's upper limit. Kalman filtering can be used to identify outliers. The filling value for missing values ​​can be determined by averaging the measured values ​​within a certain sampling interval before and after the missing value.

[0122] The performing data category detection processing on the first sequence set to obtain a preprocessed sequence set includes:

[0123] Determine whether the category of the data in each sequence in the first sequence set is consistent with the data type of the sequence, and delete inconsistent data from the sequence;

[0124] After completing the category judgment for all sequences, a set of preprocessed sequences is obtained.

[0125] In a second aspect of the embodiments of the present application, a method for monitoring user health of a hospital bed is disclosed, which is implemented using the user health monitoring device for a hospital bed, including:

[0126] S1, using the information collection module to collect basic information of the user; using the weight measurement module to measure the weight information of the user; using the body fat measurement module to measure the body fat percentage of the user;

[0127] S2, using the body composition measurement and analysis module to measure and obtain a body composition analysis information set of the user;

[0128] S3, using the data acquisition module to respectively acquire basic information, weight information, body fat percentage value, and body composition analysis information set from the information acquisition module, weight measurement module, body fat measurement module, and body composition measurement and analysis module, and sending the acquired basic information, weight information, body fat percentage value, and body composition analysis information set to the data evaluation module;

[0129] S4, using the data evaluation module, performing health monitoring evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information.

[0130] The data evaluation module performs health monitoring evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information, including:

[0131] S41, constructing a health monitoring time series information set using the weight information, body fat percentage, and body composition analysis information set collected at multiple moments; the health monitoring time series information set includes a weight sequence, a body fat percentage sequence, a total body water value sequence, a total protein value sequence, a total inorganic salt value sequence, a right upper muscle weight sequence, a left upper muscle weight sequence, a right lower muscle weight sequence, a left lower muscle weight sequence, and an extracellular water ratio value sequence;

[0132] S42, performing data preprocessing on the health monitoring time series information set to obtain a preprocessed sequence set;

[0133] S43, determining a corresponding standard sequence set based on the basic information; the standard sequence set includes a weight standard sequence, a body fat percentage standard sequence, a total body water value standard sequence, a total protein value standard sequence, a total inorganic salt value standard sequence, a right upper muscle weight standard sequence, a left upper muscle weight standard sequence, a right lower muscle weight standard sequence, a left lower muscle weight standard sequence, and an extracellular water ratio value standard sequence;

[0134] S44: Perform health assessment processing on the pre-processing sequence set and the standard sequence set to obtain health monitoring result information.

[0135] The data preprocessing of the health monitoring time series information set to obtain a preprocessed sequence set includes:

[0136] Performing data cleaning on the health monitoring time series information set to obtain a first sequence set;

[0137] performing data category detection processing on the first sequence set to obtain a preprocessed sequence set;

[0138] The health assessment process is performed on the pre-processed sequence set and the standard sequence set to obtain health monitoring result information, including:

[0139] Performing a first evaluation process on the weight sequence and the body fat percentage sequence in the preprocessed sequence set to obtain a first evaluation result value;

[0140] performing a second evaluation process on the body total water value sequence, the total protein value sequence, the total inorganic salt value sequence, the right upper muscle weight sequence, the left upper muscle weight sequence, the right lower muscle weight sequence, the left lower muscle weight sequence, and the extracellular water ratio value sequence in the preprocessing sequence set to obtain a second evaluation result value;

[0141] Performing weight calculation processing on the preprocessing sequence set to obtain a first weight value and a second weight value;

[0142] Using the first weight value and the second weight value, performing weighted sum processing on the first evaluation result value and the second evaluation result value to obtain health monitoring result information;

[0143] The weighted summing process of the first evaluation result value and the second evaluation result value using the first weight value and the second weight value is to multiply the first evaluation result value by the first weight value, multiply the second evaluation result value by the second weight value, and add the two multiplied results to obtain the health monitoring result information;

[0144] The expression of the first evaluation process is:

[0145]

[0146] a i =sin(|w 0i -w i | / |w 0i +w i |)+|exp(w i / w0)-t1| / |w i +w0|,

[0147]

[0148] Among them, q i is the i-th item of the weight sequence in the preprocessing sequence set, r i is the i-th item of the cross-correlation sequence between the weight sequence and the weight standard sequence in the pre-processing sequence set, q 0i is the i-th item of the weight standard sequence, ρ1 and ρ2 are the preset first constant factor and second constant factor respectively, v i is the i-th item in the weight evaluation sequence, w 0i is the i-th item in the standard sequence of body fat percentage, w i is the i-th item of the body fat percentage sequence in the preprocessing sequence set, w0 is the mean of all elements of the body fat percentage standard sequence, t1 is the preset third constant factor, a i is the i-th item in the body fat percentage evaluation sequence, and pj1 is the first evaluation result value.

[0149] The expression of the second evaluation process is:

[0150] A body composition measurement matrix is ​​constructed using the body total water value sequence, total protein value sequence, total inorganic salt value sequence, right upper muscle weight sequence, left upper muscle weight sequence, right lower muscle weight sequence, left lower muscle weight sequence, and extracellular water ratio value sequence in the preprocessing sequence set as row vectors; the row vectors of the body composition measurement matrix are the body total water value sequence, total protein value sequence, total inorganic salt value sequence, right upper muscle weight sequence, left upper muscle weight sequence, right lower muscle weight sequence, left lower muscle weight sequence, and extracellular water ratio value sequence in the preprocessing sequence set;

[0151] A body composition standard matrix is ​​constructed using the body total water value standard sequence, total protein value standard sequence, total inorganic salt value standard sequence, right upper muscle weight standard sequence, left upper muscle weight standard sequence, right lower muscle weight standard sequence, left lower muscle weight standard sequence, and extracellular water ratio value standard sequence;

[0152] multiplying the transposed matrices of the body composition measurement matrix and the body composition standard matrix to obtain a correlation matrix;

[0153] Decomposing the correlation matrix to obtain an eigenvector matrix and an eigenvalue matrix;

[0154] Each eigenvalue is judged to determine whether the eigenvalue is greater than a preset eigenthreshhold value, and a judgment result value is obtained; the eigenvalue for which all judgment results are greater than a predetermined eigenvalue is determined as the first eigenvalue;

[0155] A first characteristic matrix is ​​constructed using the eigenvectors corresponding to all first eigenvalues; the row vectors of the first characteristic matrix are the eigenvectors corresponding to the first eigenvalues;

[0156] Using the mean of each row vector of the first characteristic matrix, and performing weighted summation with the first eigenvalue corresponding to the row vector, a second evaluation result value is obtained;

[0157] The weighted summation process of the second evaluation result value is:

[0158]

[0159] Among them, pj2 is the second evaluation result value, aa i is the first eigenvalue of the i-th element, bb i is the mean of the row vector corresponding to the i-th first eigenvalue, M1 is the number of first eigenvalues;

[0160] The performing weight calculation processing on the preprocessing sequence set to obtain a first weight value and a second weight value includes:

[0161] Perform statistical analysis on the weight sequence and body fat percentage sequence to obtain corresponding means and variances;

[0162] Perform weight calculation on the means and variances of the weight sequence and the body fat percentage sequence to obtain a corresponding first weight value z1;

[0163] The calculation expression of the first weight value is:

[0164] z1=tan|(μ1μ2) / (σ1σ2)|,

[0165] Among them, μ1 and μ2 are the means of the weight sequence and body fat percentage sequence, respectively, σ1 and σ2 are the variances of the weight sequence and body fat percentage sequence, respectively;

[0166] Using the body total water value sequence, total protein value sequence, total inorganic salt value sequence, right upper muscle weight sequence, left upper muscle weight sequence, right lower muscle weight sequence, left lower muscle weight sequence and extracellular water ratio value sequence in the preprocessing sequence set as row vectors, a body composition measurement matrix is ​​constructed;

[0167] performing a second weight value calculation process on the body composition measurement matrix to obtain a second weight value;

[0168] The expression for the second weight value calculation process is:

[0169]

[0170] Among them, A1 ij is the element in row i and column j of the body composition measurement matrix, A2 ij is the element in the i-th row and j-th column of the body composition standard matrix, N2 and M2 are the row dimension and column dimension of the body composition standard matrix respectively, and z2 is the second weight value;

[0171] The decomposition process may be an eigenvalue decomposition process;

[0172] The decomposition process of the correlation matrix to obtain an eigenvector matrix and an eigenvalue matrix includes:

[0173] K=UΛU T ,

[0174] Where K is the correlation matrix, U is the eigenvector matrix, and Λ is the eigenvalue matrix;

[0175] The foregoing is merely 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 modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A user health monitoring device for a hospital bed, characterized in that: include: Information acquisition module, weight measurement module, body fat measurement module, body composition measurement and analysis module, data acquisition module, data evaluation module; The information collection module is used to collect basic information of the user, including age, gender, disease information, and surgery information; The weight measurement module is used to measure and obtain the user's weight information; The body fat measurement module is used to measure the user's body fat percentage; The body composition measurement and analysis module is used to measure and obtain a body composition analysis information set of the user; the body composition analysis information set includes a total body water value, a total protein value, a total inorganic salt value, a right upper muscle weight, a left upper muscle weight, a right lower muscle weight, a left lower muscle weight, and an extracellular water ratio value; The data acquisition module is connected to the information acquisition module, weight measurement module, body fat measurement module, and human body composition measurement and analysis module respectively, and is used to collect basic information, weight information, body fat percentage value, and human body composition analysis information set, and send the collected basic information, weight information, body fat percentage value, and human body composition analysis information set to the data evaluation module; The data evaluation module is connected to the information acquisition module and the data acquisition module, and is used to perform health monitoring and evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information; The data evaluation module constructs a health monitoring time series information set using the weight information, body fat percentage value, and human body composition analysis information set collected at several moments; the health monitoring time series information set includes a weight sequence, a body fat percentage sequence, a total body water value sequence, a total protein value sequence, a total inorganic salt value sequence, a right upper muscle weight sequence, a left upper muscle weight sequence, a right lower muscle weight sequence, a left lower muscle weight sequence, and an extracellular water ratio value sequence; Performing data preprocessing on the health monitoring time series information set to obtain a preprocessed sequence set; Determine a corresponding standard sequence set based on the basic information; the standard sequence set includes a weight standard sequence, a body fat percentage standard sequence, a total body water value standard sequence, a total protein value standard sequence, a total inorganic salt value standard sequence, a right upper muscle weight standard sequence, a left upper muscle weight standard sequence, a right lower muscle weight standard sequence, a left lower muscle weight standard sequence, and an extracellular water ratio value standard sequence; the standard sequence set corresponding to each type of basic information is stored in the data evaluation module; Performing health assessment processing on the pre-processing sequence set and the standard sequence set to obtain health monitoring result information; The health assessment process is performed on the pre-processed sequence set and the standard sequence set to obtain health monitoring result information, including: Performing a first evaluation process on the weight sequence and the body fat percentage sequence in the preprocessed sequence set to obtain a first evaluation result value; performing a second evaluation process on the body total water value sequence, the total protein value sequence, the total inorganic salt value sequence, the right upper muscle weight sequence, the left upper muscle weight sequence, the right lower muscle weight sequence, the left lower muscle weight sequence, and the extracellular water ratio value sequence in the preprocessing sequence set to obtain a second evaluation result value; Performing weight calculation processing on the preprocessing sequence set to obtain a first weight value and a second weight value; Using the first weight value and the second weight value, performing weighted sum processing on the first evaluation result value and the second evaluation result value to obtain health monitoring result information; The expression of the first evaluation process is: and i =sin(|in 0i -In i | / |in 0i +in i |)+|exp(in i / w0)-t1| / |w i +w0|, Among them, q i is the i-th item of the weight sequence in the preprocessing sequence set, r i is the i-th item of the cross-correlation sequence between the weight sequence and the weight standard sequence in the pre-processing sequence set, q 0i is the i-th item of the weight standard sequence, ρ1 and ρ2 are the preset first constant factor and second constant factor respectively, v i is the i-th item in the weight evaluation sequence, w 0i is the i-th item in the standard sequence of body fat percentage, w i is the i-th item of the body fat percentage sequence in the preprocessing sequence set, w0 is the mean of all elements of the body fat percentage standard sequence, t1 is the preset third constant factor, a i is the i-th item in the body fat percentage evaluation sequence, and pj1 is the first evaluation result value.

2. The user health monitoring device for a hospital bed according to claim 1, characterized in that: The weight measurement module is arranged on the upper surface of the bed board of the hospital bed; The body fat measurement module includes a measuring electrode and a data processing submodule; the measuring electrode is connected to the data processing submodule and is used to collect the user's skin electrical signals; the data processing submodule is used to measure and process the collected skin electrical signals of the user to obtain the user's body fat percentage value; the measuring electrode includes an electrode body and a mounting bracket, the electrode body is installed on the mounting bracket; the mounting bracket is installed in the middle position of both sides of the upper surface of the bed board of the bed.

3. The user health monitoring device for a hospital bed according to claim 1, characterized in that: The body composition measurement and analysis module includes measurement electrodes, a mounting bracket, and a data analysis submodule; The measuring electrode is mounted on the mounting bracket; The mounting bracket is installed in the middle position of both sides of the upper surface of the bed board and in the middle position of the bottom of the upper surface of the bed board; the measuring electrode is connected to the data analysis submodule to collect the user's skin electrical signals; the data analysis submodule is used to perform human body composition analysis on the collected user's skin electrical signals to obtain a human body composition analysis information set.

4. The user health monitoring device for a hospital bed according to claim 3, characterized in that: The data preprocessing of the health monitoring time series information set to obtain a preprocessed sequence set includes: Performing data cleaning on the health monitoring time series information set to obtain a first sequence set; Data category detection processing is performed on the first sequence set to obtain a preprocessed sequence set.

5. A user health monitoring method for a hospital bed, characterized in that: The method is implemented by using the user health monitoring device for a hospital bed according to any one of claims 1 to 4, comprising: S1, using the information collection module to collect basic information of the user; using the weight measurement module to measure the weight information of the user; using the body fat measurement module to measure the body fat percentage of the user; S2, using the body composition measurement and analysis module to measure and obtain a body composition analysis information set of the user; S3, using the data acquisition module to respectively acquire basic information, weight information, body fat percentage value, and body composition analysis information set from the information acquisition module, weight measurement module, body fat measurement module, and body composition measurement and analysis module, and sending the acquired basic information, weight information, body fat percentage value, and body composition analysis information set to the data evaluation module; S4, using the data evaluation module, performing health monitoring evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information.

6. The user health monitoring method for a hospital bed according to claim 5, characterized in that: The data evaluation module performs health monitoring evaluation processing on the basic information, weight information, body fat percentage value, and human body composition analysis information set to obtain health monitoring result information, including: S41, constructing a health monitoring time series information set using the weight information, body fat percentage, and body composition analysis information set collected at multiple moments; the health monitoring time series information set includes a weight sequence, a body fat percentage sequence, a total body water value sequence, a total protein value sequence, a total inorganic salt value sequence, a right upper muscle weight sequence, a left upper muscle weight sequence, a right lower muscle weight sequence, a left lower muscle weight sequence, and an extracellular water ratio value sequence; S42, performing data preprocessing on the health monitoring time series information set to obtain a preprocessed sequence set; S43, determining a corresponding standard sequence set based on the basic information; the standard sequence set includes a weight standard sequence, a body fat percentage standard sequence, a total body water value standard sequence, a total protein value standard sequence, a total inorganic salt value standard sequence, a right upper muscle weight standard sequence, a left upper muscle weight standard sequence, a right lower muscle weight standard sequence, a left lower muscle weight standard sequence, and an extracellular water ratio value standard sequence; S44: Perform health assessment processing on the pre-processing sequence set and the standard sequence set to obtain health monitoring result information.

7. The user health monitoring method for a hospital bed according to claim 6, characterized in that: The data preprocessing of the health monitoring time series information set to obtain a preprocessed sequence set includes: Performing data cleaning on the health monitoring time series information set to obtain a first sequence set; Data category detection processing is performed on the first sequence set to obtain a preprocessed sequence set.

8. The user health monitoring method for a hospital bed according to claim 6, characterized in that: The health assessment process is performed on the pre-processed sequence set and the standard sequence set to obtain health monitoring result information, including: Performing a first evaluation process on the weight sequence and the body fat percentage sequence in the preprocessed sequence set to obtain a first evaluation result value; performing a second evaluation process on the body total water value sequence, the total protein value sequence, the total inorganic salt value sequence, the right upper muscle weight sequence, the left upper muscle weight sequence, the right lower muscle weight sequence, the left lower muscle weight sequence, and the extracellular water ratio value sequence in the preprocessing sequence set to obtain a second evaluation result value; Performing weight calculation processing on the preprocessing sequence set to obtain a first weight value and a second weight value; The first evaluation result value and the second evaluation result value are weighted and summed using the first weight value and the second weight value to obtain health monitoring result information.

9. The user health monitoring method for a hospital bed according to claim 8, characterized in that: The expression of the first evaluation process is: and i =sin(|in 0i -In i | / |in 0i +in i |)+|exp(in i / w0)-t1| / |w i +w0|, Among them, q i is the i-th item of the weight sequence in the preprocessing sequence set, r i is the i-th item of the cross-correlation sequence between the weight sequence and the weight standard sequence in the pre-processing sequence set, q 0i is the i-th item of the weight standard sequence, ρ1 and ρ2 are the preset first constant factor and second constant factor respectively, v i is the i-th item in the weight evaluation sequence, w 0i is the i-th item in the standard sequence of body fat percentage, w i is the i-th item of the body fat percentage sequence in the preprocessing sequence set, w0 is the mean of all elements of the body fat percentage standard sequence, t1 is the preset third constant factor, a i is the i-th item in the body fat percentage evaluation sequence, and pj1 is the first evaluation result value.

Images