A rule mining method and system for electrolyte abnormal timing trajectory

Abstract

The application discloses a rule mining method and system for electrolyte abnormal time sequence track. The rule mining method for electrolyte abnormal time sequence track comprises the following steps: inputting second electrolyte data into an initial electrolyte prediction model to obtain electrolyte prediction values and prediction time intervals; calculating a loss value based on electrolyte true values, electrolyte true time intervals, electrolyte prediction values and prediction time intervals; updating the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model, and performing clustering based on the second electrolyte data to obtain a total clustering result; performing association rule mining based on the total clustering result and a preset threshold to obtain screened rules; and performing rule mining on first electrolyte data based on the trained electrolyte prediction model and the screened rules to obtain prediction prognosis results of users to be mined, thereby improving the accuracy of prediction.

Description

Technical Field

[0001] The present application relates to the technical field related to rule mining of electrolyte abnormality time series trajectory, and in particular to a rule mining method and system for electrolyte abnormality time series trajectory. Background Art

[0002] Electrolyte imbalance refers to abnormal changes in the concentration of electrolytes (such as sodium, potassium, calcium, magnesium, and chloride), typically excessively high or low, in the body. These electrolytes play an important role in maintaining cellular function, acid-base balance, nerve conduction, and muscle contraction. When electrolyte concentrations become unbalanced, they can have serious effects on various body systems. The causes, severity, treatment, and outcomes of these disorders can vary significantly depending on the electrolytes involved. Association rule mining is a data mining technique used to discover relationships between different items in a dataset and is particularly suitable for analyzing large amounts of transactional data. The core goal of association rule mining is to discover sets of items that frequently appear together in the data and to establish rules based on these sets to predict other, unobserved relationships in the data.

[0003] Most existing survival time prediction methods require that critically ill patients undergo multiple examinations before predictions can be made based on the examination indicators in these examinations. Multiple examinations take a long time, which affects prediction efficiency. Summary of the Invention

[0004] This application aims to at least solve the technical problems existing in the prior art. To this end, this application proposes a rule mining method and system for electrolyte abnormality time series trajectory, which can mine the rules of electrolyte disorder and survival time, thereby improving the efficiency and accuracy of prediction.

[0005] In a first aspect of the present application, a method for mining rules of electrolyte abnormality time series trajectory is provided, comprising the following steps:

[0006] Acquire first electrolyte data of the user to be mined and second electrolyte data of historical users, wherein the second electrolyte data includes a real electrolyte value and a real electrolyte time interval of each historical user;

[0007] Constructing an initial electrolyte prediction model; and inputting the second electrolyte data into the initial electrolyte prediction model to obtain an electrolyte prediction value and a prediction time interval;

[0008] calculating a loss value based on the electrolyte actual value, the electrolyte actual time interval, the electrolyte predicted value, and the predicted time interval;

[0009] updating the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model;

[0010] performing clustering based on the second electrolyte data to obtain an overall clustering result;

[0011] Performing association rule mining based on the total clustering results and a preset threshold to obtain filtered rules;

[0012] Based on the trained electrolyte prediction model and the screened rules, rule mining is performed on the first electrolyte data to obtain a predicted prognosis result of the user to be mined.

[0013] The control method according to the embodiment of the present application has at least the following beneficial effects:

[0014] This method obtains the first electrolyte data of the user to be mined and the second electrolyte data of the historical users, wherein the second electrolyte data includes the electrolyte real value and the electrolyte real time interval of each historical user; constructs an initial electrolyte prediction model; and inputs the second electrolyte data into the initial electrolyte prediction model to obtain the electrolyte prediction value and the prediction time interval; calculates the loss value based on the electrolyte real value, the electrolyte real time interval, the electrolyte prediction value and the prediction time interval; updates the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model. This application improves the prediction accuracy by combining the electrolyte value and the electrolyte time interval for prediction; at the same time, clustering is performed based on the second electrolyte data to obtain the total clustering result; association rule mining is performed based on the total clustering result and a preset threshold to obtain a filtered rule; based on the trained electrolyte prediction model and the filtered rule, rule mining is performed on the first electrolyte data to obtain the predicted prognosis result of the user to be mined, thereby improving the accuracy of the prediction.

[0015] According to some embodiments of the present application, obtaining the second electrolyte data of a historical user includes:

[0016] Obtaining a corresponding identifier, an electrolyte test timestamp, and an electrolyte test type for each user in the historical users, wherein the electrolyte test type includes at least one of sodium ion, potassium ion, calcium ion, magnesium ion, chloride ion, phosphate, bicarbonate, and pH value that measures the acidity and alkalinity of blood;

[0017] A historical time series set is constructed based on the corresponding identifier, electrolyte examination timestamp, and electrolyte examination type using the following formula:

[0018] ;

[0019] in, is a set of historical time series, For the The historical time series of the examination records of each electrolyte examination type, For the The total number of electrolyte test types, For the Type of electrolyte test The second inspection and The actual time interval between electrolyte checks, For the Type of electrolyte test The actual value of electrolytes in the second examination;

[0020] The historical time series set is used as the second electrolyte data.

[0021] According to some embodiments of the present application, the loss value is calculated by the following formula:

[0022] ;

[0023] in, is the loss value, is the total length of the historical time series, is the first time interval in the electrolyte time intervals, is the first time intervals, The true value of the electrolyte Check the value, The predicted value of electrolyte A check value.

[0024] According to some embodiments of the present application, clustering based on the second electrolyte data to obtain an overall clustering result includes:

[0025] Clustering the second electrolyte data using the KMeans clustering method to obtain corresponding clustering results for each electrolyte inspection type;

[0026] The corresponding clustering results of all electrolyte examination categories are taken as the overall clustering result.

[0027] According to some embodiments of the present application, performing association rule mining based on the total clustering result and a preset threshold to obtain filtered rules includes:

[0028] Obtaining a true prognosis result for each of the historical users;

[0029] Performing association rule mining on each of the historical users based on the total clustering result and the true prognosis result to obtain a mined rule and its corresponding confidence value;

[0030] The mined rules whose corresponding confidence values ​​are greater than the preset threshold are filtered to obtain the filtered rules.

[0031] According to some embodiments of the present application, the method of performing rule mining on the first electrolyte data based on the trained electrolyte prediction model and the post-screening rules to obtain the predicted prognosis result of the user to be mined includes:

[0032] Inputting the first electrolyte data into the trained electrolyte prediction model to obtain a first electrolyte prediction value and a first prediction time interval;

[0033] Performing clustering based on the first electrolyte prediction value and the first prediction time interval to obtain a first clustering result;

[0034] Rule mining is performed based on the first clustering result and the filtered rules to obtain the predicted prognosis result.

[0035] According to some embodiments of the present application, updating the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model includes:

[0036] When the loss value is less than or equal to a preset loss value, the initial electrolyte prediction model is used as the trained electrolyte prediction model;

[0037] When the loss value is greater than a preset loss value, the parameters of the initial electrolyte prediction model are updated according to the loss value until the loss value is less than or equal to the preset loss value, thereby obtaining the trained electrolyte prediction model.

[0038] In a second aspect of the present application, a rule mining system for electrolyte abnormality time series trajectory is provided. The rule mining system for electrolyte abnormality time series trajectory includes:

[0039] A data acquisition module is used to acquire first electrolyte data of the user to be mined and second electrolyte data of historical users, wherein the second electrolyte data includes the electrolyte real value and electrolyte real time interval of each historical user;

[0040] A prediction module is used to construct an initial electrolyte prediction model; and input the second electrolyte data into the initial electrolyte prediction model to obtain an electrolyte prediction value and a prediction time interval;

[0041] a loss value calculation module, configured to calculate a loss value based on the electrolyte real value, the electrolyte real time interval, the electrolyte predicted value, and the predicted time interval;

[0042] An updating module, configured to update the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model;

[0043] A clustering module, configured to perform clustering based on the second electrolyte data to obtain an overall clustering result;

[0044] A rule screening module is used to mine association rules based on the total clustering results and a preset threshold to obtain filtered rules;

[0045] A rule mining module is used to perform rule mining on the first electrolyte data based on the trained electrolyte prediction model and the screened rules to obtain the predicted prognosis results of the user to be mined.

[0046] The system obtains the first electrolyte data of the user to be mined and the second electrolyte data of the historical users, wherein the second electrolyte data includes the electrolyte real value and the electrolyte real time interval of each historical user; constructs an initial electrolyte prediction model; and inputs the second electrolyte data into the initial electrolyte prediction model to obtain the electrolyte prediction value and the prediction time interval; calculates the loss value based on the electrolyte real value, the electrolyte real time interval, the electrolyte prediction value and the prediction time interval; updates the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model. The application improves the prediction accuracy by combining the electrolyte value and the electrolyte time interval for prediction; at the same time, clustering is performed based on the second electrolyte data to obtain the total clustering result; association rule mining is performed based on the total clustering result and the preset threshold to obtain the filtered rule; based on the trained electrolyte prediction model and the filtered rule, rule mining is performed on the first electrolyte data to obtain the predicted prognosis result of the user to be mined, thereby improving the accuracy of the prediction.

[0047] The third aspect of the present application provides an electronic device for rule mining of electrolyte abnormality timing trajectories, comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute the above-mentioned rule mining method for electrolyte abnormality timing trajectories.

[0048] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned rule mining method for electrolyte abnormality time series trajectory.

[0049] It should be noted that the beneficial effects between the second to fourth aspects of the present application and the prior art are the same as the beneficial effects between the above-mentioned rule mining system for electrolyte abnormality time series trajectory and the prior art, and will not be described in detail here.

[0050] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0052] Figure 1 This is a flow chart of a method for mining rules of electrolyte abnormality time series trajectory according to one embodiment of the present application;

[0053] Figure 2 1 is a schematic structural diagram of an embodiment of a rule mining system for electrolyte abnormality time series trajectory provided by the present application;

[0054] Figure 3 It is a structural diagram of an embodiment of the electronic device provided by this application. DETAILED DESCRIPTION

[0055] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.

[0056] In the description of this application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0057] In the description of this application, it should be understood that descriptions involving orientation, such as the orientation or positional relationship indicated by up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0058] In the description of this application, it should be noted that, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technical personnel in the relevant technical field can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution.

[0059] Electrolyte imbalance refers to abnormal changes in the concentration of electrolytes (such as sodium, potassium, calcium, magnesium, and chloride), typically excessively high or low, in the body. These electrolytes play an important role in maintaining cellular function, acid-base balance, nerve conduction, and muscle contraction. When electrolyte concentrations become unbalanced, they can have serious effects on various body systems. The causes, severity, treatment, and outcomes of these disorders can vary significantly depending on the electrolytes involved. Association rule mining is a data mining technique used to discover relationships between different items in a dataset and is particularly suitable for analyzing large amounts of transactional data. The core goal of association rule mining is to discover sets of items that frequently appear together in the data and to establish rules based on these sets to predict other, unobserved relationships in the data.

[0060] Most existing survival time prediction methods require that critically ill patients undergo multiple examinations before predictions can be made based on the examination indicators in these examinations. Multiple examinations take a long time, which affects prediction efficiency.

[0061] In order to solve the above technical defects, the embodiments of the present application provide a rule mining method and system for electrolyte abnormality time series trajectory.

[0062] See Figure 1 , is a flow chart of a method for mining rules of electrolyte abnormality time series trajectory provided by an embodiment of the present application, the method is applied to electronic equipment, which may be a server, etc. Figure 1 As shown in Figure 2, the rule mining method for the electrolyte abnormal time series trajectory includes:

[0063] Step S101: Acquire first electrolyte data of the user to be mined and second electrolyte data of historical users, wherein the second electrolyte data includes the electrolyte real value and electrolyte real time interval of each historical user;

[0064] Step S102: constructing an initial electrolyte prediction model; inputting the second electrolyte data into the initial electrolyte prediction model to obtain an electrolyte prediction value and a prediction time interval;

[0065] Step S103, calculating the loss value based on the actual electrolyte value, the actual electrolyte time interval, the predicted electrolyte value and the predicted time interval;

[0066] Step S104: updating the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model;

[0067] Step S105: performing clustering based on the second electrolyte data to obtain an overall clustering result;

[0068] Step S106: performing association rule mining based on the total clustering results and a preset threshold to obtain filtered rules;

[0069] Step S107: Based on the trained electrolyte prediction model and the filtered rules, rule mining is performed on the first electrolyte data to obtain a predicted prognosis result of the user to be mined.

[0070] This method obtains the first electrolyte data of the user to be mined and the second electrolyte data of the historical users, wherein the second electrolyte data includes the electrolyte real value and the electrolyte real time interval of each historical user; constructs an initial electrolyte prediction model; and inputs the second electrolyte data into the initial electrolyte prediction model to obtain the electrolyte prediction value and the prediction time interval; calculates the loss value based on the electrolyte real value, the electrolyte real time interval, the electrolyte prediction value and the prediction time interval, and updates the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model. This application improves the prediction accuracy by combining the electrolyte value and the electrolyte time interval for prediction; at the same time, clustering is performed based on the second electrolyte data to obtain the total clustering result; association rule mining is performed based on the total clustering result and a preset threshold to obtain a filtered rule; based on the trained electrolyte prediction model and the filtered rule, rule mining is performed on the first electrolyte data to obtain the predicted prognosis result of the user to be mined, thereby improving the accuracy of the prediction.

[0071] In some embodiments, obtaining the second electrolyte data of the historical user in step S101 includes:

[0072] Step S201: Obtain the corresponding identifier, electrolyte test timestamp, and electrolyte test type of each user in the historical user list, wherein the electrolyte test type includes at least one of sodium ion, potassium ion, calcium ion, magnesium ion, chloride ion, phosphate, bicarbonate, and pH value, which measures the acidity and alkalinity of the blood;

[0073] Step S202: Construct a historical time series set based on the corresponding identifier, electrolyte examination timestamp, and electrolyte examination type using the following formula:

[0074] ;

[0075] in, is a set of historical time series, For the The historical time series of the examination records of each electrolyte examination type, For the The total number of electrolyte test types, For the Type of electrolyte test The second inspection and The actual time interval between electrolyte checks, For the Type of electrolyte test The actual value of electrolytes in the second examination;

[0076] Step S203: Use the historical time series set as the second electrolyte data.

[0077] This application improves the accuracy of prediction by constructing time series with different time intervals as the data basis for subsequent prediction data.

[0078] In some embodiments, the loss value is calculated in step S103 using the following formula:

[0079] ;

[0080] in, is the loss value, is the total length of the historical time series, is the first time interval in the electrolyte time intervals, is the first time intervals, The true value of the electrolyte Check the value, The predicted value of electrolyte A check value.

[0081] This application calculates the loss value through the electrolyte real value, electrolyte real time interval, electrolyte predicted value and predicted time interval, and updates the model according to the loss value, thereby improving the accuracy of the model prediction and thus improving the accuracy of the prediction.

[0082] In some embodiments, clustering is performed based on the second electrolyte data in step S105 to obtain an overall clustering result, including:

[0083] Step S301: cluster the second electrolyte data using the KMeans clustering method to obtain corresponding clustering results for each electrolyte inspection type;

[0084] Step S302: taking the corresponding clustering results of all electrolyte inspection types as the total clustering result.

[0085] Specifically, the same electrolyte sequences of different users are clustered, and the clustering method uses the KMeans algorithm.

[0086] Specifically, when calculating the distance between different samples, an improved LSTM (Long Short-Term Memory Model) autoencoder is used for calculation, and the number of clusters is pre-set. The specific calculation formula is as follows:

[0087] ;

[0088] in, is the total memory transferred from the previous unit, For short-term memory, is the decayed short-term memory, For long-term memory, is the memory of the previous unit after adjustment, Candidate memory. is the input of the current unit, is the hidden state of the previous unit, is the hidden state of the current cell, and They are the memory of the previous unit and the memory of the current unit, is the neural network parameter matrix of the forget gate, is the neural network parameter matrix of the input gate, is the neural network parameter matrix of the output gate and candidate memory, These are sub-matrices decomposed from the neural network parameter matrix. The dimensions of these matrices depend on the dimensions of the input, output, and preset hidden parameters. and The time that has passed between is a time decay function, so that its input The bigger, The smaller the output.

[0089] Specifically, in some embodiments, the expression of the time decay function is:

[0090] .

[0091] In some embodiments, in step S106, association rule mining is performed based on the total clustering results and a preset threshold to obtain filtered rules, including:

[0092] Step S401: Obtain the real prognosis result of each historical user;

[0093] Step S402: performing association rule mining on each historical user based on the total clustering results and the actual prognosis results to obtain the mined rules and their corresponding confidence values;

[0094] Step S403: Filter the mined rules whose corresponding confidence values ​​are greater than a preset threshold to obtain filtered rules.

[0095] Specifically, the clustering results are treated as labels, a confidence threshold is specified, and association rule mining is performed on the labels. After clustering is completed, each cluster result is treated as a label, and the number of labels is determined by the predetermined number of clusters. In some embodiments, the number of clusters is 3. Each electrolyte is named into three categories: low, medium, and high based on the data distribution of the clustering results. The naming rule is the electrolyte name followed by low, medium, or high.

[0096] Specifically, a rule can include a left rule, which contains the mined labels and has a variable length. A rule can also include a right rule, which only includes the item "death" in this application. A rule can also include support, a confidence value, and a lift.

[0097] In some embodiments, the rules mined include:

[0098] {Low bicarbonate, low chloride, low pH} => {bad} (conf: 0.938, sup: 0.017, lift: 4.591);

[0099] {Low bicarbonate, low chloride, low pH, medium sodium} => {bad} (conf: 0.925, sup: 0.013, lift: 4.526);

[0100] {Low chloride, low pH, high potassium} => {bad} (conf: 0.886, supp: 0.010, lift:4.333).

[0101] Among them, conf is the confidence value, supp is the support value, and lift is the lift value.

[0102] In some embodiments, in step S107, rule mining is performed on the first electrolyte data based on the trained electrolyte prediction model and the filtered rules to obtain the predicted prognosis results of the user to be mined, including:

[0103] Step S501: inputting the first electrolyte data into the trained electrolyte prediction model to obtain a first electrolyte prediction value and a first prediction time interval;

[0104] Step S502: performing clustering based on the first electrolyte prediction value and the first prediction time interval to obtain a first clustering result;

[0105] Step S503: performing rule mining based on the first clustering result and the filtered rules to obtain a prediction and prognosis result.

[0106] This application helps medical staff better perceive the human body's condition and assists them in making decisions by mining the time series patterns corresponding to human bodies with poor prognosis.

[0107] In some embodiments, in step S104, the initial electrolyte prediction model is updated based on the loss value to obtain a trained electrolyte prediction model, including:

[0108] Step S601: When the loss value is less than or equal to the preset loss value, the initial electrolyte prediction model is used as the trained electrolyte prediction model;

[0109] Step S602: When the loss value is greater than the preset loss value, the parameters of the initial electrolyte prediction model are updated according to the loss value until the loss value is less than or equal to the preset loss value, thereby obtaining a trained electrolyte prediction model.

[0110] Specifically, to facilitate understanding by those skilled in the art, a set of best embodiments are provided below:

[0111] 1. Data Acquisition

[0112] Obtain the first electrolyte data of the user to be mined and the second electrolyte data of the historical users, wherein the second electrolyte data includes the electrolyte real value and electrolyte real time interval of each historical user, specifically:

[0113] Obtaining a corresponding identifier, an electrolyte test timestamp, and an electrolyte test type for each user in the historical users, wherein the electrolyte test type includes at least one of sodium ion, potassium ion, calcium ion, magnesium ion, chloride ion, phosphate, bicarbonate, and pH value that measures the acidity and alkalinity of blood;

[0114] The historical time series set is constructed based on the corresponding identifier, electrolyte examination timestamp, and electrolyte examination type using the following formula:

[0115] ;

[0116] in, is a set of historical time series, For the The historical time series of the examination records of each electrolyte examination type, For the The total number of electrolyte test types, For the Type of electrolyte test The second inspection and The actual time interval between electrolyte checks, For the Type of electrolyte test The actual value of electrolytes in the second examination;

[0117] The historical time series set is used as the second electrolyte data.

[0118] 2. Model prediction:

[0119] Constructing an initial electrolyte prediction model; and inputting the second electrolyte data into the initial electrolyte prediction model to obtain an electrolyte prediction value and a prediction time interval;

[0120] 3. Calculation of loss value:

[0121] The loss value is calculated based on the electrolyte actual value, electrolyte actual time interval, electrolyte predicted value and predicted time interval using the following formula:

[0122] ;

[0123] in, is the loss value, is the total length of the historical time series, is the first time interval in the electrolyte time intervals, is the first time intervals, The true value of the electrolyte Check the value, The predicted value of electrolyte A check value.

[0124] 4. Model training:

[0125] The initial electrolyte prediction model is updated based on the loss value to obtain a trained electrolyte prediction model, specifically:

[0126] When the loss value is less than or equal to the preset loss value, the initial electrolyte prediction model is used as the trained electrolyte prediction model;

[0127] When the loss value is greater than the preset loss value, the parameters of the initial electrolyte prediction model are updated according to the loss value until the loss value is less than or equal to the preset loss value, thereby obtaining a trained electrolyte prediction model.

[0128] 5. Second electrolyte data clustering:

[0129] Clustering is performed based on the second electrolyte data to obtain the overall clustering results, specifically:

[0130] The second electrolyte data is clustered using the KMeans clustering method to obtain the corresponding clustering results for each electrolyte inspection type;

[0131] The corresponding clustering results of all electrolyte examination types were taken as the overall clustering results.

[0132] 6. Association rule screening:

[0133] Based on the total clustering results and the preset threshold, association rules are mined to obtain the filtered rules, which are as follows:

[0134] Obtain the true prognosis results for each historical user;

[0135] Based on the total clustering results and the actual prognosis results, association rules are mined for each historical user to obtain the mined rules and their corresponding confidence values;

[0136] The mined rules whose corresponding confidence values ​​are greater than a preset threshold are filtered to obtain the filtered rules.

[0137] 7. Prognosis prediction:

[0138] Based on the trained electrolyte prediction model and the filtered rules, rule mining is performed on the first electrolyte data to obtain the predicted prognosis results of the user to be mined, specifically:

[0139] Inputting the first electrolyte data into the trained electrolyte prediction model to obtain a first electrolyte prediction value and a first prediction time interval;

[0140] Perform clustering based on the first electrolyte prediction value and the first prediction time interval to obtain a first clustering result;

[0141] Rule mining is performed based on the first clustering results and the filtered rules to obtain the predicted prognosis results.

[0142] In addition, refer to Figure 2 One embodiment of the present application provides a rule mining system for electrolyte abnormality time series trajectory, including a data acquisition module 1100, a prediction module 1200, a loss value calculation module 1300, an update module 1400, a clustering module 1500, a rule screening module 1600, and a rule mining module 1700, wherein:

[0143] The data acquisition module 1100 is used to acquire the first electrolyte data of the user to be mined and the second electrolyte data of the historical users, wherein the second electrolyte data includes the electrolyte real value and electrolyte real time interval of each historical user;

[0144] The prediction module 1200 is used to construct an initial electrolyte prediction model; and input the second electrolyte data into the initial electrolyte prediction model to obtain an electrolyte prediction value and a prediction time interval;

[0145] The loss value calculation module 1300 is used to calculate the loss value based on the actual electrolyte value, the actual electrolyte time interval, the predicted electrolyte value and the predicted time interval;

[0146] The updating module 1400 is used to update the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model;

[0147] The clustering module 1500 is used to perform clustering based on the second electrolyte data to obtain an overall clustering result;

[0148] The rule screening module 1600 is used to mine association rules based on the total clustering results and a preset threshold to obtain filtered rules;

[0149] The rule mining module 1700 is used to perform rule mining on the first electrolyte data based on the trained electrolyte prediction model and the filtered rules to obtain the predicted prognosis results of the user to be mined.

[0150] The system obtains the first electrolyte data of the user to be mined and the second electrolyte data of the historical users, wherein the second electrolyte data includes the electrolyte real value and the electrolyte real time interval of each historical user; constructs an initial electrolyte prediction model; and inputs the second electrolyte data into the initial electrolyte prediction model to obtain the electrolyte prediction value and the prediction time interval; calculates the loss value based on the electrolyte real value, the electrolyte real time interval, the electrolyte prediction value and the prediction time interval; updates the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model. The application improves the prediction accuracy by combining the electrolyte value and the electrolyte time interval for prediction; at the same time, clustering is performed based on the second electrolyte data to obtain the total clustering result; association rule mining is performed based on the total clustering result and the preset threshold to obtain the filtered rule; based on the trained electrolyte prediction model and the filtered rule, rule mining is performed on the first electrolyte data to obtain the predicted prognosis result of the user to be mined, thereby improving the accuracy of the prediction.

[0151] It should be noted that this system embodiment and the above-mentioned method embodiment are based on the same inventive concept, so the relevant content of the above-mentioned method embodiment is also applicable to this system embodiment and will not be repeated here.

[0152] Figure 3 A schematic diagram of the rule mining hardware structure provided by an embodiment of the present application is shown.

[0153] The device for mining rules in electrolyte abnormality time series trajectory may include a processor 301 and a memory 302 storing computer program instructions.

[0154] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0155] Memory 302 may include a large-capacity memory for data or instructions. By way of example and not limitation, memory 302 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a specific embodiment, memory 302 is a non-volatile solid-state memory.

[0156] In some embodiments, the memory 302 may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0157] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any one of the rule mining methods for electrolyte abnormality time series trajectories in the above embodiments.

[0158] In one example, the rule mining device for electrolyte abnormality time series trajectory may further include a communication interface 303 and a bus 310. Figure 3 As shown, the processor 301 , the memory 302 , and the communication interface 303 are connected via a bus 310 and communicate with each other.

[0159] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0160] Bus 310 includes hardware, software, or both, coupling components of the device for mining the rules of electrolyte anomaly timing traces to one another. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industrial Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 310 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0161] The rule mining device for electrolyte abnormal time series trajectory can execute the rule mining method for electrolyte abnormal time series trajectory in the embodiment of the present application based on the three-dimensional design model, thereby realizing the combination of Figure 1 and Figure 2 The present invention describes a rule mining method and system for electrolyte anomaly time series trajectory.

[0162] In addition, in conjunction with the rule mining method for electrolyte abnormality time series trajectory in the above embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the rule mining methods for electrolyte abnormality time series trajectory in the above embodiments is implemented.

[0163] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0164] The functional blocks shown in the above block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, and the like. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memory, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. Code segments can be downloaded via a computer network such as the Internet or an intranet.

[0165] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0166] Aspects of the present disclosure have been described above with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block in the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine such that execution of these instructions by the processor of the computer or other programmable data processing device enables the implementation of the functions / actions specified in one or more blocks in the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It should also be understood that each block in the block diagrams and / or flowcharts, as well as combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0167] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A rule mining method for electrolyte abnormality time series trajectory, characterized by: The rule mining method for electrolyte abnormality time series trajectory includes: Acquire first electrolyte data of the user to be mined and second electrolyte data of historical users, wherein the second electrolyte data includes a real electrolyte value and a real electrolyte time interval of each historical user; Constructing an initial electrolyte prediction model; and inputting the second electrolyte data into the initial electrolyte prediction model to obtain an electrolyte prediction value and a prediction time interval; calculating a loss value based on the electrolyte actual value, the electrolyte actual time interval, the electrolyte predicted value, and the predicted time interval; Updating the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model; performing clustering based on the second electrolyte data to obtain an overall clustering result; Performing association rule mining based on the total clustering results and a preset threshold to obtain filtered rules; Based on the trained electrolyte prediction model and the screened rules, rule mining is performed on the first electrolyte data to obtain a predicted prognosis result of the user to be mined.

2. The rule mining method for electrolyte abnormality time series trajectory according to claim 1 is characterized in that: Get historical user's second electrolyte data, including: Obtaining a corresponding identifier, an electrolyte test timestamp, and an electrolyte test type for each user in the historical users, wherein the electrolyte test type includes at least one of sodium ion, potassium ion, calcium ion, magnesium ion, chloride ion, phosphate, bicarbonate, and pH value that measures the acidity and alkalinity of blood; A historical time series set is constructed based on the corresponding identifier, electrolyte examination timestamp, and electrolyte examination type using the following formula: ； in, is a set of historical time series, For the The historical time series of the examination records of each electrolyte examination type, For the The total number of electrolyte test types, For the Type of electrolyte test The second inspection and The actual time interval between electrolyte checks, For the Type of electrolyte test The actual value of electrolytes in the second examination; The historical time series set is used as the second electrolyte data.

3. The rule mining method for electrolyte abnormality time series trajectory according to claim 2 is characterized in that: The loss value is calculated by the following formula: ； in, is the loss value, is the total length of the historical time series, is the first time interval in the electrolyte time intervals, is the first time intervals, The true value of the electrolyte Check the value, The predicted value of electrolyte A check value.

4. The rule mining method for electrolyte abnormality time series trajectory according to claim 2 is characterized in that: The clustering is performed based on the second electrolyte data to obtain an overall clustering result, including: Clustering the second electrolyte data using the KMeans clustering method to obtain corresponding clustering results for each electrolyte inspection type; The corresponding clustering results of all electrolyte examination categories are taken as the overall clustering result.

5. The rule mining method for electrolyte abnormality time series trajectory according to claim 1 is characterized in that: The association rule mining based on the total clustering result and the preset threshold is performed to obtain the filtered rules, including: Obtaining a true prognosis result for each of the historical users; Performing association rule mining on each of the historical users based on the total clustering result and the true prognosis result to obtain a mined rule and its corresponding confidence value; The mined rules whose corresponding confidence values ​​are greater than the preset threshold are filtered to obtain the filtered rules.

6. The rule mining method for electrolyte abnormality time series trajectory according to claim 1 is characterized in that: The method of performing rule mining on the first electrolyte data based on the trained electrolyte prediction model and the filtered rules to obtain a predicted prognosis result of the user to be mined includes: Inputting the first electrolyte data into the trained electrolyte prediction model to obtain a first electrolyte prediction value and a first prediction time interval; Performing clustering based on the first electrolyte prediction value and the first prediction time interval to obtain a first clustering result; Rule mining is performed based on the first clustering result and the filtered rules to obtain the predicted prognosis result.

7. The rule mining method for electrolyte abnormality time series trajectory according to claim 1 is characterized in that: The updating of the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model includes: When the loss value is less than or equal to a preset loss value, the initial electrolyte prediction model is used as the trained electrolyte prediction model; When the loss value is greater than a preset loss value, the parameters of the initial electrolyte prediction model are updated according to the loss value until the loss value is less than or equal to the preset loss value, thereby obtaining the trained electrolyte prediction model.

8. A rule mining system for electrolyte abnormality time series trajectory, characterized by: The rule mining system for electrolyte abnormality time series trajectory includes: A data acquisition module is used to acquire first electrolyte data of the user to be mined and second electrolyte data of historical users, wherein the second electrolyte data includes the electrolyte real value and electrolyte real time interval of each historical user; A prediction module is used to construct an initial electrolyte prediction model; and input the second electrolyte data into the initial electrolyte prediction model to obtain an electrolyte prediction value and a prediction time interval; a loss value calculation module, configured to calculate a loss value based on the electrolyte real value, the electrolyte real time interval, the electrolyte predicted value, and the predicted time interval; An updating module, configured to update the initial electrolyte prediction model based on the loss value to obtain a trained electrolyte prediction model; A clustering module, configured to perform clustering based on the second electrolyte data to obtain an overall clustering result; A rule screening module is used to mine association rules based on the total clustering results and a preset threshold to obtain filtered rules; A rule mining module is used to perform rule mining on the first electrolyte data based on the trained electrolyte prediction model and the screened rules to obtain the predicted prognosis results of the user to be mined.

9. A rule mining device for electrolyte abnormality time series trajectory, characterized by: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute a rule mining method for an electrolyte abnormality time series trajectory as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the rule mining method for electrolyte abnormality time series trajectory according to any one of claims 1 to 7.

Images