Hospital equipment informatization monitoring system

Abstract

The invention relates to the technical field of medical informatization, and discloses a hospital equipment informatization monitoring system, and the system comprises a data processing module which is used for collecting historical data of hospital equipment, carrying out the time sequence analysis of the historical data, obtaining the data at the next moment, and carrying out the anomaly detection of the data at the next moment, and obtaining the abnormal data; the data fusion module is used for collecting parameter data of the hospital equipment and carrying out data association on the historical data and the parameter data to obtain associated data; the cooperative control module is used for constructing a multivariable cooperative control equation according to the associated data and the abnormal data, and performing resource optimization on the multivariable cooperative control equation to obtain control adjustment parameters; and the report generation module is used for generating a hospital equipment monitoring informatization report according to the abnormal data and the control adjustment parameters. The hospital equipment informatization monitoring system can solve the problem that an existing hospital equipment informatization monitoring system is still low in reliability.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to an information monitoring system for hospital equipment. Background Art

[0002] In the modern medical environment, the normal operation of hospital equipment is crucial for the diagnosis, treatment and rehabilitation of patients. With the advancement of medical technology, more and more medical devices are introduced into daily diagnosis and treatment, which can collect a large amount of patient physiological parameters and equipment operation data in real time.

[0003] However, under the traditional hospital equipment management model, the data generated by hospital equipment is usually scattered in different systems, lacking unified management and integration. This leads to the phenomenon of "data islands", making it difficult to fully grasp the status of the equipment, affecting the accuracy and timeliness of decision-making. At the same time, the operating data of the equipment and the clinical data of the patient are often separated, and effective correlation analysis cannot be formed, which limits the comprehensive evaluation of equipment performance and patient health status. It may lead to insufficient emergency response in emergencies. In summary, the existing hospital equipment information monitoring system still has the problem of low reliability of the monitoring system. Summary of the invention

[0004] The present invention provides a hospital equipment information monitoring system, the main purpose of which is to solve the problem of low reliability of the monitoring system in the existing hospital equipment information monitoring system.

[0005] To achieve the above-mentioned purpose, the present invention provides a hospital equipment information monitoring system, including: a data processing module, a data fusion module, a collaborative control module, and a report generation module, specifically: A data processing module, used for collecting historical data of hospital equipment, performing time series analysis on the historical data to obtain data at the next moment, and performing anomaly detection on the data at the next moment to obtain abnormal data; A data fusion module, used for collecting parameter data of hospital equipment, and performing data association between the historical data and the parameter data to obtain associated data; A collaborative control module, used for constructing a multivariable collaborative control equation according to the associated data and the abnormal data, performing resource optimization on the multivariable collaborative control equation, and obtaining control adjustment parameters; A report generation module is used to generate a hospital equipment monitoring information report based on the abnormal data and the control adjustment parameters.

[0006] Optionally, when the data processing module performs the function of performing time series analysis on the historical data to obtain data at the next moment, it is specifically used to: Normalizing the historical data to obtain normalized data; Performing data stabilization on the normalized data to obtain a stabilization result; Performing partial correlation analysis on the stabilization results to obtain the lag order; Using the lag order and the stabilization result to fit the regression equation, to obtain a regression model; The regression model is used to perform data calculation on the stabilization result to obtain data at the next moment.

[0007] Optionally, when the data processing module performs the function of performing partial correlation analysis on the stabilization result to obtain the lag order, it is specifically used to: Performing autocorrelation calculation on the stabilization result to obtain an autocorrelation value; Using the autocorrelation value to perform partial correlation function calculation on the stabilization result to obtain a partial correlation function value; Constructing a partial correlation function graph according to the partial correlation function value; Performing confidence screening in the partial correlation function graph to obtain a confidence result; The lag order is screened out from the partial correlation function graph according to the confidence result.

[0008] Optionally, when the data processing module performs the function of performing anomaly detection on the next moment data to obtain abnormal data, it is specifically used to: Performing threshold detection on the next moment data using a preset fixed threshold to obtain a threshold result; Calculate the difference between the next moment data and the historical data; Using a preset difference threshold to perform mutation screening on the difference value to obtain a mutation result; Generate warning information according to the mutation result and the threshold result; The warning information and the next moment data are integrated to obtain abnormal data.

[0009] Optionally, when the data fusion module performs the function of associating the historical data and the parameter data to obtain associated data, it is specifically used to: Aligning the parameter data with the historical data to obtain aligned data; Performing feature extraction on the alignment data to obtain associated features; A cross-correlation analysis is performed on the correlation features to obtain correlation data.

[0010] Optionally, when the data fusion module performs the function of performing cross-correlation analysis on the associated features to obtain associated data, it is specifically used to: Performing frequency domain conversion on the correlation features to obtain frequency domain features; Performing convolution calculation on the frequency domain feature to obtain a convolution result; Performing inverse fast Fourier calculation on the convolution result to obtain a cross-correlation function; Performing a lagged sequence analysis based on the cross-correlation data to obtain a lagged time series; The lagged time series is screened for significance to obtain correlation data.

[0011] Optionally, when executing the function of constructing a multivariable collaborative control equation according to the associated data and the abnormal data, the collaborative control module is specifically used to: Constructing a state parameter vector according to the abnormal data; Constructing an objective function according to the associated data, the state parameter vector and the abnormal data; The preset control equation is fitted according to the objective function to obtain a multivariable collaborative control equation.

[0012] Optionally, when the collaborative control module performs the function of optimizing resources on the multivariable collaborative control equation to obtain control adjustment parameters, it is specifically used to: Performing state analysis according to the associated data and the abnormal data to generate a recursive stage; Constructing a state transfer function according to the associated data; Based on the recursive stage, the state transfer function is recursively calculated using the multivariable cooperative control equation to obtain a cooperative relationship; An optimal path tracking is performed on the cooperative relationship to obtain control adjustment parameters.

[0013] Optionally, when the collaborative control module performs the function of recursively calculating the state transfer function based on the recursive stage by using the multivariable collaborative control equation to obtain the collaborative relationship, it is specifically used to: Taking the state parameter vector as an initial vector; Recursively calculating the initial vector using the state transfer function to obtain a predicted state; The initial vector is subjected to a synergistic relationship calculation with the predicted state, the multivariable synergistic control equation, and the state transfer function to obtain a synergistic relationship, and the synergistic relationship calculation is performed using the following formula: in, Represents the initial vector and predicted status exist The collaborative relationship at the moment, is the multivariable cooperative control equation, is the state transfer function, The multivariable cooperative control equation For the initial vector The partial derivative of is the state transition function For the prediction vector The partial derivative of is the symbol for differentiation; The predicted state is used as the initial vector in the next recursive stage, and the process returns to the step of "recursively calculating the initial vector using the state transfer function to obtain the predicted state" until the recursive stage is completed.

[0014] Optionally, when the report generation module performs the function of generating a hospital equipment monitoring information report according to the abnormal data and the control adjustment parameters, it is specifically used to: Performing data sorting according to the abnormal data and the control and regulation parameters to generate a time series data structure; A text description is automatically generated according to the time series data structure to obtain a hospital equipment monitoring informationization report.

[0015] The data fusion of the present invention is not limited to simple data superposition, but can also combine multi-dimensional data such as equipment usage scenarios and patient information to provide richer contextual information. For example, combined with the patient's medical record data, the cause of equipment abnormality can be better understood, so as to formulate a more targeted maintenance strategy; the operation of hospital equipment often involves multiple variables (such as temperature, pressure, flow, etc.), and the adjustment of a single variable may affect the stability of other variables. By constructing a multivariable collaborative control equation, collaborative optimization can be achieved between multiple variables to ensure that the equipment operates in the optimal state, improve the operating efficiency of the equipment, and extend the service life of the equipment. Therefore, the hospital equipment information monitoring system proposed by the present invention can solve the problem of low reliability of the monitoring system in the existing hospital equipment information monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A functional module diagram of a hospital equipment information monitoring system provided by an embodiment of the present invention; Figure 2 A schematic diagram of a timing analysis process according to an embodiment of the present invention; Figure 3 A schematic diagram of a cross-correlation analysis process according to an embodiment of the present invention; Figure 4 A flowchart of a hospital equipment information monitoring method provided by an embodiment of the present invention.

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0019] Reference Figure 1 As shown, it is a functional module diagram of a hospital equipment information monitoring system provided by one embodiment of the present invention. In this embodiment, the hospital equipment information monitoring system 100 can be installed in an electronic device. According to the functions implemented, the hospital equipment information monitoring system 100 may include a data processing module 101, a data fusion module 102, a collaborative control module 103, and a report generation module 104. The module described in the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0020] In the embodiment of the present invention, the data processing module 101 includes collecting historical data of hospital equipment, performing time series analysis on the historical data to obtain data at the next moment, and performing anomaly detection on the data at the next moment to obtain abnormal data; In the embodiment of the present invention, the data fusion module 102 includes collecting parameter data of hospital equipment, and performing data association between the historical data and the parameter data to obtain associated data; In the embodiment of the present invention, the collaborative control module 103 includes constructing a multivariable collaborative control equation according to the associated data and the abnormal data, performing resource optimization on the multivariable collaborative control equation, and obtaining control adjustment parameters; In the embodiment of the present invention, the report generation module 104 generates a hospital equipment monitoring information report according to the abnormal data and the control adjustment parameters.

[0021] In detail, the modules described in the hospital equipment information monitoring system 100 described in the embodiment of the present invention adopt the same technical means as the hospital equipment information monitoring system described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0022] The following is a description of each component and specific workflow of the hospital equipment information monitoring system in conjunction with a specific embodiment: The data processing module 101 is used to collect historical data of hospital equipment, perform time series analysis on the historical data to obtain data at the next moment, and perform anomaly detection on the data at the next moment to obtain abnormal data.

[0023] In the embodiment of the present invention, the historical data of the hospital equipment refers to the historical data of the patient collected by the hospital equipment, including heart rate, blood pressure, blood oxygen and other data.

[0024] Ginseng Figure 2 As shown, when the data processing module performs the function of performing time series analysis on the historical data to obtain the data at the next moment, it is specifically used to: S21, normalizing the historical data to obtain normalized data; S22, performing data stabilization on the normalized data to obtain a stabilization result; S23, performing partial correlation analysis on the stabilization result to obtain a lag order; S24, fitting a regression equation using the lag order and the stabilization result to obtain a regression model; S25. Utilize the regression model to perform data calculation on the stabilization result to obtain data at the next moment.

[0025] In the embodiment of the present invention, the normalization processing refers to scaling the historical data to a fixed interval by subtracting the mean from the historical data and then dividing it by the standard deviation to obtain normalized data.

[0026] In an embodiment of the present invention, the data stabilization refers to selecting a data from the normalized data, using the data as the center value of the sliding window, calculating the average value within a window of a preset size, replacing the data with the average value, and obtaining a stabilization result.

[0027] In the embodiment of the present invention, when the data processing module performs the function of performing partial correlation analysis on the stabilization result to obtain the lag order, it is specifically used to: Performing autocorrelation calculation on the stabilization result to obtain an autocorrelation value; Using the autocorrelation value to perform partial correlation function calculation on the stabilization result to obtain a partial correlation function value; Constructing a partial correlation function graph according to the partial correlation function value; Performing confidence screening in the partial correlation function graph to obtain a confidence result; The lag order is screened out from the partial correlation function graph according to the confidence result.

[0028] In detail, the autocorrelation calculation is performed by calculating the mean of the stabilization result and the covariance of the time series, calculating the variance of the time series according to the mean, and calculating the quotient of the variance and the covariance to obtain the autocorrelation value.

[0029] In detail, the partial correlation function value can be calculated using the following function: in, The first The partial correlation function value of the data, For the preset The data autocorrelation value, For the The partial correlation coefficient of the data indicates that The lag order is The partial correlation of the data, is the normalization factor used to ensure the stability of the partial correlation function value, Lag The autocorrelation value after , indicating the first Data and The relevance of the data, is the index of the lag order, from 1 to All lags.

[0030] In detail, the partial correlation function graph is obtained by taking the partial correlation function value as the ordinate and the number of data corresponding to the partial correlation function value as the abscissa.

[0031] In detail, the confidence interval is calculated by the data size of the smoothed result, and the confidence interval is marked in the partial correlation function diagram, that is, the upper and lower limits of the confidence interval are added to the partial correlation function diagram, and the data corresponding to the last partial correlation coefficient that exceeds the confidence interval is used as the lag order.

[0032] In the embodiment of the present invention, the parameters of the preset regression equation are estimated according to the determined lag order and the data in the stabilization result to obtain a regression model, wherein the regression equation is: in, For the stabilization result The data at the moment, is a constant value, is the lag order, is the calculated error term, , , are the parameters of the equation, To stabilize the results The data at the moment, To stabilize the results The data at the moment, To stabilize the results Data at the moment.

[0033] In the embodiment of the present invention, the data in the stabilization result is substituted into the regression model to obtain the data at the next moment.

[0034] In the embodiment of the present invention, when the data processing module performs the function of performing anomaly detection on the next moment data to obtain abnormal data, it is specifically used to: Performing threshold detection on the next moment data using a preset fixed threshold to obtain a threshold result; Calculate the difference between the next moment data and the historical data; Using a preset difference threshold to perform mutation screening on the difference value to obtain a mutation result; Generate warning information according to the mutation result and the threshold result; The warning information and the next moment data are integrated to obtain abnormal data.

[0035] In the embodiment of the present invention, the fixed threshold refers to the normal range of the historical data. For example, the heart rate of a normal adult is usually between 60 and 100 beats per minute, and the fixed threshold may be lower than 60 or higher than 100.

[0036] In the embodiment of the present invention, the differential value refers to a first-order differential value calculated between the next moment data and the historical data, and the differential threshold is obtained by subtracting the next moment data from the historical data.

[0037] In the embodiment of the present invention, the differential threshold is set according to the standard deviation of historical data or other statistics. For example, if the patient's heart rate differential value exceeds 20 beats / minute, it indicates that there is a problem with the heart rate.

[0038] In the embodiment of the present invention, the results of threshold detection and mutation detection are comprehensively analyzed. If a data point satisfies the conditions of both threshold detection and mutation detection, it is considered that the data point is abnormal. Different priorities are assigned to different abnormalities according to the severity of the abnormality (such as the degree of exceeding the threshold, the magnitude of the mutation, etc.), and finally the abnormal data points and their severity are integrated into early warning information.

[0039] In the embodiment of the present invention, the next moment data is a prediction result obtained after time series analysis based on historical data.

[0040] In the embodiment of the present invention, the warning information is integrated with the data point at the next moment to form a complete abnormal data record, which includes information such as the timestamp of the next moment, the abnormal value, the reference value, the differential value, etc.

[0041] In the embodiment of the present invention, by predicting the data at the next moment and integrating threshold detection and mutation detection into a comprehensive anomaly detection framework, the accuracy of abnormal data recognition can be maintained while improving the efficiency of abnormal data recognition.

[0042] The data fusion module 102 is used to collect parameter data of hospital equipment, and associate the historical data with the parameter data to obtain associated data.

[0043] In an embodiment of the present invention, the parameter data refers to parameter data related to hospital equipment, such as the airflow rate, pressure value (inspiratory pressure, expiratory pressure), oxygen concentration, respiratory rate of a ventilator or the flow rate and infusion time of a drug infusion pump.

[0044] In an embodiment of the present invention, the patient's historical data is combined with the device parameters to provide a more comprehensive understanding of the patient's overall condition.

[0045] In the embodiment of the present invention, when the data fusion module performs the function of associating the historical data and the parameter data to obtain the associated data, it is specifically used to: Aligning the parameter data with the historical data to obtain aligned data; Performing feature extraction on the alignment data to obtain associated features; A cross-correlation analysis is performed on the correlation features to obtain correlation data.

[0046] In the embodiment of the present invention, by extracting the timestamps of the historical data and the parameter data, the timestamps are time-aligned, and a common time resolution is screened out, and the historical data and the parameter data are aggregated to the time resolution according to the time resolution, such as a group of temperature data (historical data) recorded every hour, and another group of humidity data (parameter data) recorded every 15 minutes. In order to align the two groups of data, a common time resolution (such as every 15 minutes) can be selected, and a data set is generated every fifteen groups, which includes temperature data and humidity data.

[0047] In the embodiment of the present invention, the feature extraction refers to extracting useful features from the aligned data for subsequent analysis. The associated features are obtained by calculating the basic statistics of each variable, such as mean, variance, maximum value, minimum value, median, etc., as well as the periodic dependence of the data.

[0048] Ginseng Figure 3 As shown, the cross-correlation analysis of the associated features to obtain the function of associated data is specifically used for: S31, performing frequency domain conversion on the correlation features to obtain frequency domain features; S32, performing convolution calculation on the frequency domain feature to obtain a convolution result; S33, performing inverse fast Fourier calculation on the convolution result to obtain a cross-correlation function; S34, performing a lagged sequence analysis according to the cross-correlation data to obtain a lagged time series; S35, performing significance screening on the lagged time series to obtain correlation data.

[0049] In the embodiment of the present invention, the frequency domain conversion can be performed using the following formula: in, is the frequency domain feature The value of a point, is the total number of associated features, For the associated feature The value of a point, A fixed base function is preset to represent a sine wave or cosine wave of a specific frequency. Take the value of the preset pi, is an imaginary unit, The value of the preset natural logarithm.

[0050] In the embodiment of the present invention, the associated features are multiplied point by point to obtain a convolution result.

[0051] In the embodiment of the present invention, the peak position is found in the cross-correlation function, the optimal lag time between each feature is determined, and a lag time series is constructed based on the found peak position; the peak position represents the most likely time delay between two features.

[0052] In an embodiment of the present invention, a statistical test is performed on the lagged time series to calculate the p-value, and based on a pre-set significance level, feature combinations with p-values ​​less than the significance level are screened out, and these feature combinations with significant correlations are retained, and the screened feature combinations and their corresponding lagged time series are integrated into associated data.

[0053] In the embodiments of the present invention, by correlating data from different sources, hidden correlations can be revealed, and the impact of device operation on the patient's condition can be understood, which can help formulate more effective treatment strategies and ensure that the device settings are most conducive to the patient's recovery.

[0054] The collaborative control module 103 is used to construct a multivariable collaborative control equation according to the associated data and the abnormal data, perform resource optimization on the multivariable collaborative control equation, and obtain control adjustment parameters.

[0055] In the embodiment of the present invention, the control equation is continuously updated according to the real-time data, so that the system can adapt to the changing situation, and the control parameters can be adjusted accurately to maintain or restore the patient's stable state.

[0056] In the embodiment of the present invention, when the collaborative control module executes the function of constructing a multivariable collaborative control equation according to the associated data and the abnormal data, it is specifically used to: Constructing a state parameter vector according to the abnormal data; Constructing an objective function according to the associated data, the state parameter vector and the abnormal data; The preset control equation is fitted according to the objective function to obtain a multivariable collaborative control equation.

[0057] In an embodiment of the present invention, the state parameter vector is obtained by obtaining all data points marked as abnormal and related information from the anomaly detection module, selecting key features related to the anomaly (such as heart rate, blood pressure, blood oxygen saturation, etc.) according to the type and severity of the abnormal data, that is, parameters that change significantly under abnormal conditions, and combining the selected key features and their corresponding lagged time series into a state parameter vector.

[0058] In the embodiment of the present invention, the objective function refers to an optimization target for describing the relationship between device parameters and patient status. By utilizing the lagged time series in the associated data and adjusting the weight matrix in the preset function, a comprehensive objective function is constructed, which measures the performance deviation of the system at different time points.

[0059] In detail, the preset function refers to: in, Linked Data and the state parameter vector The function representation of the relationship between For the The weight of the key features, For the The deviation function of the key feature is used to measure the Key Features With state parameter vector The difference between To find the minimum symbol, it means to find a set of state parameter vectors , so that the function Minimum.

[0060] In an embodiment of the present invention, the optimization problem is solved by an iterative method (such as gradient descent, L-BFGS) to minimize the objective function and obtain the final control equation parameters, that is, the multivariable collaborative control equation. The multivariable collaborative control equation is an equation of the form A(a)=KB(a), wherein K is the controller gain matrix, which is determined by minimizing the objective function and describes the relationship between the control input and the state parameters.

[0061] In the embodiment of the present invention, when the collaborative control module performs the function of optimizing resources on the multivariable collaborative control equation to obtain the control adjustment parameter, it is specifically used to: Performing state analysis according to the associated data and the abnormal data to generate a recursive stage; Constructing a state transfer function according to the associated data; Based on the recursive stage, the state transfer function is recursively calculated using the multivariable cooperative control equation to obtain a cooperative relationship; An optimal path tracking is performed on the cooperative relationship to obtain control adjustment parameters.

[0062] In an embodiment of the present invention, after obtaining the multivariable cooperative control equation, the dynamic behavior of the system is further analyzed to generate a recursive stage, and the initial state and the target state in each time step are generated by dividing the time step of the recursive stage.

[0063] In the embodiment of the present invention, a hysteresis relationship model is modeled according to the associated data to obtain a hysteresis relationship model, and a hysteresis time series in the associated data is used as an input of the hysteresis relationship model to obtain a state transfer function, wherein the hysteresis relationship model is in the form of: ,in, For the The associated data at the moment, , are two different lag times in the lagged time series, are model parameters, For the The associated data at the moment, Indicates at time Next, delayed The associated data of time units, At the moment Next, delayed The associated data of time units, is the symbol for nonlinear mapping.

[0064] In the embodiment of the present invention, based on the recursive stage, the state transfer function is recursively calculated using a multivariable collaborative control equation, and the collaborative relationship between the variables is discovered through iterative calculation, that is, how adjusting one variable will affect other variables.

[0065] In the embodiment of the present invention, when the collaborative control module performs the function of recursively calculating the state transfer function based on the recursive stage using the multivariable collaborative control equation to obtain the collaborative relationship, it is specifically used to: Taking the state parameter vector as an initial vector; Recursively calculating the initial vector using the state transfer function to obtain a predicted state; Calculate the synergistic relationship between the initial vector, the predicted state, the multivariable synergistic control equation and the state transfer function to obtain a synergistic relationship; The predicted state is used as the initial vector in the next recursive stage, and the process returns to the step of "recursively calculating the initial vector using the state transfer function to obtain the predicted state" until the recursive stage is completed.

[0066] In detail, the synergy relationship is calculated by the following formula: in, Represents the initial vector and predicted status exist The collaborative relationship at the moment, is the multivariable cooperative control equation, is the state transfer function, The multivariable cooperative control equation For the initial vector The partial derivative of is the state transition function For the prediction vector The partial derivative of is the derivative symbol.

[0067] In the embodiment of the present invention, the collaborative relationship obtained by recursive calculation is optimized to find the optimal path from the initial state to the target state in the system, and the control adjustment parameters finally obtained are used to guide specific operations to ensure that the system runs in the optimal manner.

[0068] In the embodiment of the present invention, the control equations are continuously updated according to real-time data, so that the system can quickly adapt to changing conditions, maintain optimal performance, and respond to the needs of patients in a timely manner.

[0069] The report generating module 104 is used to generate a hospital equipment monitoring information report according to the abnormal data and the control adjustment parameters.

[0070] In the embodiment of the present invention, the report generation module records all key events in detail, provides clear and structured information and suggestions, and ultimately improves the quality of medical services.

[0071] In the embodiment of the present invention, when the report generation module performs the function of generating a hospital equipment monitoring information report according to the abnormal data and the control adjustment parameters, it is specifically used to: Performing data sorting according to the abnormal data and the control and regulation parameters to generate a time series data structure; A text description is automatically generated according to the time series data structure to obtain a hospital equipment monitoring informationization report.

[0072] In the embodiment of the present invention, abnormal data and control parameters of the equipment are sorted according to time sequence and formatted uniformly to obtain a time series data structure, which is an ordered data set arranged in time sequence and represents the change of equipment status over time.

[0073] In an embodiment of the present invention, the sorted time series data is analyzed, key content is extracted, descriptive text is generated, and an algorithm (such as a rule engine or a natural language generation model) is used to automatically process the time series data, and a report is generated by extracting key events and generating summary text.

[0074] In the embodiment of the present invention, by integrating abnormal data and control parameters, generating time series data and performing textual description, not only the automated processing of monitoring information is achieved, but also intelligent tools are provided for equipment management and maintenance, thereby improving the efficiency and accuracy of monitoring and reducing the workload of manual data analysis.

[0075] like Figure 4 FIG. 1 is a flow chart of a hospital equipment information monitoring method provided by an embodiment of the present invention. In an embodiment of the present invention, the hospital equipment information monitoring method includes: S401, collecting historical data of hospital equipment, performing time series analysis on the historical data to obtain data at the next moment, performing anomaly detection on the data at the next moment to obtain abnormal data; S402, collecting parameter data of hospital equipment, and performing data association between the historical data and the parameter data to obtain associated data; S403, constructing a multivariable coordinated control equation according to the associated data and the abnormal data, performing resource optimization on the multivariable coordinated control equation, and obtaining control adjustment parameters; S404: Generate a hospital equipment monitoring information report based on the abnormal data and the control adjustment parameters.

[0076] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology.

[0077] Among them, Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0078] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in the system can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A hospital equipment information monitoring system, characterized in that: The system includes: a data processing module, a data fusion module, a collaborative control module, and a report generation module. Specifically: A data processing module, used for collecting historical data of hospital equipment, performing time series analysis on the historical data to obtain data at the next moment, and performing anomaly detection on the data at the next moment to obtain abnormal data; A data fusion module, used for collecting parameter data of hospital equipment, and performing data association between the historical data and the parameter data to obtain associated data; A collaborative control module, used for constructing a multivariable collaborative control equation according to the associated data and the abnormal data, performing resource optimization on the multivariable collaborative control equation, and obtaining control adjustment parameters; A report generation module is used to generate a hospital equipment monitoring information report based on the abnormal data and the control adjustment parameters.

2. A hospital equipment information monitoring system as claimed in claim 1, characterized in that: When the data processing module performs the function of performing time series analysis on the historical data to obtain the data at the next moment, it is specifically used to: Normalizing the historical data to obtain normalized data; Performing data stabilization on the normalized data to obtain a stabilization result; Performing partial correlation analysis on the stabilization results to obtain the lag order; Using the lag order and the stabilization result to fit the regression equation, to obtain a regression model; The regression model is used to perform data calculation on the stabilization result to obtain data at the next moment.

3. A hospital equipment information monitoring system as claimed in claim 2, characterized in that: When the data processing module performs the function of performing partial correlation analysis on the stabilization result to obtain the lag order, it is specifically used to: Performing autocorrelation calculation on the stabilization result to obtain an autocorrelation value; Using the autocorrelation value to perform partial correlation function calculation on the stabilization result to obtain a partial correlation function value; Constructing a partial correlation function graph according to the partial correlation function value; Performing confidence screening in the partial correlation function graph to obtain a confidence result; The lag order is screened out from the partial correlation function graph according to the confidence result.

4. A hospital equipment information monitoring system as claimed in claim 1, characterized in that: When the data processing module performs the function of performing anomaly detection on the next moment data to obtain abnormal data, it is specifically used to: Performing threshold detection on the next moment data using a preset fixed threshold to obtain a threshold result; Calculate the difference between the next moment data and the historical data; Using a preset difference threshold to perform mutation screening on the difference value to obtain a mutation result; Generate warning information according to the mutation result and the threshold result; The warning information and the next moment data are integrated to obtain abnormal data.

5. A hospital equipment information monitoring system as claimed in claim 1, characterized in that: When the data fusion module performs the function of associating the historical data and the parameter data to obtain the associated data, it is specifically used to: Aligning the parameter data with the historical data to obtain aligned data; Performing feature extraction on the alignment data to obtain associated features; A cross-correlation analysis is performed on the correlation features to obtain correlation data.

6. A hospital equipment information monitoring system as claimed in claim 5, characterized in that: When the data fusion module performs the function of performing cross-correlation analysis on the associated features to obtain associated data, it is specifically used to: Performing frequency domain conversion on the correlation features to obtain frequency domain features; Performing convolution calculation on the frequency domain feature to obtain a convolution result; Performing inverse fast Fourier calculation on the convolution result to obtain a cross-correlation function; Performing a lagged sequence analysis based on the cross-correlation data to obtain a lagged time series; The lagged time series is screened for significance to obtain correlation data.

7. A hospital equipment information monitoring system as claimed in claim 1, characterized in that: When the collaborative control module executes the function of constructing a multivariable collaborative control equation according to the associated data and the abnormal data, it is specifically used to: Constructing a state parameter vector according to the abnormal data; Constructing an objective function according to the associated data, the state parameter vector and the abnormal data; The preset control equation is fitted according to the objective function to obtain a multivariable collaborative control equation.

8. A hospital equipment information monitoring system as claimed in claim 7, characterized in that: When the collaborative control module performs the function of optimizing resources on the multivariable collaborative control equation to obtain control adjustment parameters, it is specifically used to: Performing state analysis according to the associated data and the abnormal data to generate a recursive stage; Constructing a state transfer function according to the associated data; Based on the recursive stage, the state transfer function is recursively calculated using the multivariable cooperative control equation to obtain a cooperative relationship; An optimal path tracking is performed on the cooperative relationship to obtain control adjustment parameters.

9. A hospital equipment information monitoring system as claimed in claim 8, characterized in that: When the collaborative control module performs the function of recursively calculating the state transfer function based on the recursive stage by using the multivariable collaborative control equation to obtain the collaborative relationship, it is specifically used to: Taking the state parameter vector as an initial vector; Recursively calculating the initial vector using the state transfer function to obtain a predicted state; The initial vector is subjected to a synergistic relationship calculation with the predicted state, the multivariable synergistic control equation, and the state transfer function to obtain a synergistic relationship, and the synergistic relationship calculation is performed using the following formula: ； in, Represents the initial vector and predicted status exist The collaborative relationship at the moment, is the multivariable cooperative control equation, is the state transfer function, The multivariable cooperative control equation For the initial vector The partial derivative of is the state transition function For the prediction vector The partial derivative of is the symbol for differentiation; The predicted state is used as the initial vector in the next recursive stage, and the process returns to the step of "recursively calculating the initial vector using the state transfer function to obtain the predicted state" until the recursive stage is completed.

10. A hospital equipment information monitoring system as claimed in claim 1, characterized in that: When the report generation module performs the function of generating a hospital equipment monitoring information report according to the abnormal data and the control adjustment parameters, it is specifically used to: Perform data sorting according to the abnormal data and the control and regulation parameters to generate a time series data structure; A text description is automatically generated according to the time series data structure to obtain a hospital equipment monitoring informationization report.

Images