CN117034202B - Big data-based medication prompt method, system, equipment and storage medium - Google Patents
Big data-based medication prompt method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN117034202B CN117034202B CN202311295326.7A CN202311295326A CN117034202B CN 117034202 B CN117034202 B CN 117034202B CN 202311295326 A CN202311295326 A CN 202311295326A CN 117034202 B CN117034202 B CN 117034202B
- Authority
- CN
- China
- Prior art keywords
- representing
- layer
- extraction layer
- output
- convolution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000003814 drug Substances 0.000 title claims abstract description 179
- 229940079593 drug Drugs 0.000 title claims abstract description 149
- 238000000034 method Methods 0.000 title claims abstract description 89
- 238000000605 extraction Methods 0.000 claims abstract description 162
- 230000004927 fusion Effects 0.000 claims abstract description 52
- 230000008569 process Effects 0.000 claims abstract description 32
- 230000015654 memory Effects 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 230000009471 action Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006866 deterioration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 235000012766 Cannabis sativa ssp. sativa var. sativa Nutrition 0.000 description 1
- 235000012765 Cannabis sativa ssp. sativa var. spontanea Nutrition 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 235000009120 camo Nutrition 0.000 description 1
- 235000005607 chanvre indien Nutrition 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 239000011487 hemp Substances 0.000 description 1
- 229940126701 oral medication Drugs 0.000 description 1
- 230000004793 poor memory Effects 0.000 description 1
- 201000010041 presbyopia Diseases 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses a big data-based medication prompt method, a system, equipment and a storage medium, which belong to the technical field of data processing, wherein the medication prompt method comprises the following steps: s1, acquiring an electronic medical record and historical medication information of a user; s2, inputting the electronic medical record of the user into an electronic medical record analysis model, and carrying out feature extraction, feature convolution and feature fusion to generate the latest medication information of the user; s3, determining the reminding frequency of the latest medication information according to the historical medication information, and sending the latest medication information of the user to the user terminal according to the reminding frequency of the latest medication information. According to the invention, the electronic medical record of the user is input into the constructed electronic medical record analysis model, so that the medication name, the medication quantity, the medication times and the medication contraindication information of the user are obtained through analysis, the situation that the medicine name has a rare word is fully considered in the analysis process, the medication name is subjected to secondary correction, and the medication generation information is accurate.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a medication prompt method, a system, equipment and a storage medium based on big data.
Background
With the development of society and the deterioration of environment, the aging of population is increasingly evident, and more old people suffer from various chronic diseases such as hypertension, diabetes and heart diseases, and various medicines are required to be taken for treating the diseases. However, due to the large number of medicines and poor memory of the old, some medicines are easy to leak or are repeatedly taken, so that the illness state is aggravated. Meanwhile, a large number of medicines have the problems of attention, how to take, the number of times of daily taking and the amount of each taking, which are all burdens on memory, and many old people have difficulty in seeing the characters of the mildly hemp printed on the medicines because of vision deterioration and presbyopia, so that a plurality of difficulties are caused. Most young chronic patients can continuously take medicines according to the doctor's advice, and the medicine taking compliance is good; only a small number of patients have untimely medication due to busy work or other factors, and the medication compliance is poor, so that the patients need to be reminded of medication.
The traditional patient medication behavior prompt is usually finished manually, and besides oral medication education of medical staff and the provision of the advertising information, a paper diary card records medication conditions and the like, but the popularization is limited due to the defects of inconvenient daily use, audience limitation, insufficient reinforcement education and the like. The prompting method of handwriting medication items through doctors or families is often not strict enough, and the historical medication conditions of patients are easily ignored, so that the patients cannot be reminded timely and repeatedly.
Disclosure of Invention
In order to solve the problems, the invention provides a medication prompt method, a system, equipment and a storage medium based on big data.
The technical scheme of the invention is as follows: the medicine prompt method based on big data comprises the following steps:
s1, acquiring an electronic medical record and historical medication information of a user;
s2, an electronic medical record analysis model is built, the electronic medical record of the user is input into the electronic medical record analysis model, feature extraction, feature convolution and feature fusion are carried out, and latest medication information of the user is generated;
s3, determining the reminding frequency of the latest medication information according to the historical medication information, and sending the latest medication information of the user to the user terminal according to the reminding frequency of the latest medication information.
Further, in S2, the electronic medical record analysis model includes a text extraction layer, a first feature extraction layer, a second feature extraction layer, a third feature extraction layer, a fourth feature extraction layer, a feature convolution layer, a feature fusion layer, and an information output layer;
the input end of the text extraction layer is used as the input end of the electronic medical record analysis model, the first output end of the text extraction layer is connected with the input end of the first characteristic extraction layer, the second output end of the text extraction layer is connected with the input end of the second characteristic extraction layer, the third output end of the text extraction layer is connected with the input end of the third characteristic extraction layer, and the fourth output end of the text extraction layer is connected with the input end of the fourth characteristic extraction layer;
the output end of the first characteristic extraction layer is connected with the input end of the characteristic convolution layer; the output end of the second characteristic extraction layer is connected with the first input end of the characteristic fusion layer; the output end of the third feature extraction layer is connected with the second input end of the feature fusion layer;
the output end of the characteristic convolution layer is connected with the first input end of the information output layer; the output end of the feature fusion layer is connected with the second input end of the information output layer; the output end of the fourth characteristic extraction layer is connected with the third input end of the information output layer;
the output end of the information output layer is used as the output end of the electronic medical record analysis model.
The beneficial effects of the above-mentioned further scheme are: in the invention, the text extraction layer is used as an input end of the electronic medical record analysis model and is used for extracting text information of the electronic medical record, so that the first feature extraction layer, the second feature extraction layer, the third feature extraction layer and the fourth feature extraction layer can conveniently extract features. The first feature extraction layer generates a medication name in the latest medication information by performing mathematical operation (such as exponential operation) on word vectors and word frequencies of keywords in the text information. The second feature extraction layer generates the medication quantity in the latest medication information by performing mathematical operation (such as exponential operation) on the frequency of occurrence of the numerical value in the text information. The third feature extraction layer generates the number of doses in the latest dose information by performing mathematical operation (such as logarithmic operation) on the frequency of occurrence of the numerical value in the text information. And the fourth feature extraction layer generates medication mode and medication tabu information in the latest medication information by carrying out mathematical operation (such as logarithmic operation) on word vectors and word frequencies of keywords in the text information. Since many medicine names are complex and often involve rarely used words, the feature convolution layer of the present invention corrects the medicine name generated by the first feature extraction layer through an activation operation. And the feature fusion layer integrates the medicine use quantity output by the second feature extraction layer and the medicine use times output by the third feature extraction layer. The information output layer is used for unifying the corrected medication names, medication quantity, medication times and medication tabu information as the output of the whole model.
Further, the expression of the first feature extraction layer is:
in the method, in the process of the invention,Xrepresenting the output of the first characteristic convolution layer,g m representing the first text information corresponding to the electronic medical recordmThe word vector of the individual keywords is used,d m representing the first text information corresponding to the electronic medical recordmThe word frequency of the individual keywords is determined,ηrepresenting the output of the text extraction layer,Mthe number of keywords corresponding to the text information of the electronic medical record is represented,erepresenting an index;
the expression of the second feature extraction layer is:
in the method, in the process of the invention,Yrepresenting the output of the second feature extraction layer,c n representing the first text information corresponding to the electronic medical recordnThe word frequency of the individual values is calculated,Nthe number of the numerical values of the text information corresponding to the electronic medical record is represented,erepresenting an index;
the expression of the third feature extraction layer is:
in the method, in the process of the invention,Zrepresenting the output of the third feature extraction layer,log(. Cndot.) represents a logarithmic function;
the expression of the fourth feature extraction layer is:
in the method, in the process of the invention,Wrepresenting the output of the fourth feature extraction layer.
Further, the expression of the characteristic convolution layer is:
in the method, in the process of the invention,Frepresenting the output of the characteristic convolution layer,sigmoid(. Cndot.) represents the activation function,Kthe number of convolution kernels representing the characteristic convolution layer,μ k representing the first of the characteristic convolution layerskThe offset of the individual convolution kernels is such that,a k representing the first of the characteristic convolution layerskThe height of the convolution kernel is such that,b k representing the first of the characteristic convolution layerskThe width of the individual convolution kernels is chosen,y k+2 representing the first of the characteristic convolution layerskThe output of the +2 convolution kernels,y k+1 representing the first of the characteristic convolution layerskThe output of the +1 convolution kernel,y k representing the first of the characteristic convolution layerskThe outputs of the individual convolution kernels are then,Xrepresenting the output of the first characteristic convolution layer.
Further, the expression of the feature fusion layer is:
in the method, in the process of the invention,Grepresenting the output of the feature fusion layer,representing the Hadamard product operation,Lthe number of convolution kernels representing the feature fusion layer,x l+2 representing the first of the feature fusion layerslThe output of the +2 convolution kernels,x l+1 representing the first of the feature fusion layerslThe output of the +1 convolution kernel,x l representing the first of the feature fusion layerslThe outputs of the individual convolution kernels are then,Yrepresenting the output of the second feature extraction layer,Zrepresenting the output of the third feature extraction layer,Arepresenting a matrix of all values in the second feature extraction layer,Brepresenting a matrix of all values in the third feature extraction layer.
Further, in S1, the historical medication information includes a historical timeout feedback number and a historical timeout feedback duration.
The beneficial effects of the above-mentioned further scheme are: in the invention, the user can feed back the medication result through the terminal after taking the medicine, such as taking the medicine on time, taking the medicine overtime, and the like. Therefore, whether the medication frequency of the reminding user is improved can be judged through the historical medication timeout times and timeout time of the user.
Further, in S3, the reminding frequency of the latest medication informationaThe calculation formula of (2) is as follows:
in the method, in the process of the invention,Jindicating the number of historical timeout feedback times,T j represent the firstjThe time-out feedback duration is a time,representing an upward rounding operation,εthe minimum value is represented by a value of,erepresenting an index.
Based on the method, the invention also provides a medication prompt system based on big data, which comprises a medication information acquisition unit, a medication information generation unit and a medication information prompt unit;
the medication information acquisition unit is used for acquiring the electronic medical record and the historical medication information of the user;
the medication information generating unit is used for constructing an electronic medical record analysis model, inputting the electronic medical record of the user into the electronic medical record analysis model, and carrying out feature extraction, feature convolution and feature fusion to generate the latest medication information of the user;
the medication information reminding unit determines the reminding frequency of the latest medication information according to the historical medication information, and sends the latest medication information of the user to the user terminal according to the reminding frequency of the latest medication information.
In order to achieve the above object, the present invention further provides a computer device, where the computer device includes a memory, a processor, and a medication prompt program stored in the memory and capable of running on the processor, and when the medication prompt program is executed by the processor, part or all of the steps of the medication prompt method are implemented.
To achieve the above object, the present invention further provides a computer readable storage medium storing a computer program, which when executed implements part or all of the steps of the medication prompt method described above.
The beneficial effects of the invention are as follows:
(1) The invention provides a medicine use prompting method, a system, equipment and a storage medium based on big data, which are characterized in that the medicine use name, medicine use quantity, medicine use times and medicine use tabu information of a user are obtained through analysis by inputting the electronic medical record of the user into a constructed electronic medical record analysis model, the analysis process fully considers the situation that the medicine name has a rare word, the medicine use name is subjected to secondary correction, and medicine use generation information is accurate;
(2) According to the electronic medical record analysis model, through construction of the text extraction layer, the first feature extraction layer, the second feature extraction layer, the third feature extraction layer, the fourth feature extraction layer, the feature convolution layer, the feature fusion layer and the information output layer, operations such as text information extraction, text feature extraction, numerical feature extraction, feature convolution and feature fusion can be completed on the electronic medical record, corrected medication names, medication numbers, medication times and medication tabu information are unified as output of the whole model, the constructed electronic medical record analysis model can simplify information extraction flow, and latest medication information can be generated according to extraction results of the electronic medical record in subsequent steps;
(3) According to the method, the historical overtime feedback times and the historical overtime feedback time length are extracted by combining the historical medication condition of the user, the targeted reminding frequency is generated for the user, and the situations of missed service, false service and the like of the user can be effectively prevented.
Drawings
FIG. 1 is a flow chart of a big data based medication prompt method;
FIG. 2 is a schematic diagram of a structure based on an electronic medical record analytical model;
FIG. 3 is a schematic diagram of a big data based medication hint system;
fig. 4 is a schematic structural diagram of a computer device.
Detailed Description
Embodiments of the present invention are further described below with reference to the accompanying drawings.
As shown in fig. 1, the invention provides a medication prompt method based on big data, which comprises the following steps:
s1, acquiring an electronic medical record and historical medication information of a user;
s2, an electronic medical record analysis model is built, the electronic medical record of the user is input into the electronic medical record analysis model, feature extraction, feature convolution and feature fusion are carried out, and latest medication information of the user is generated;
s3, determining the reminding frequency of the latest medication information according to the historical medication information, and sending the latest medication information of the user to the user terminal according to the reminding frequency of the latest medication information.
In the embodiment of the present invention, as shown in fig. 2, in S2, the electronic medical record analysis model includes a text extraction layer, a first feature extraction layer, a second feature extraction layer, a third feature extraction layer, a fourth feature extraction layer, a feature convolution layer, a feature fusion layer, and an information output layer;
the input end of the text extraction layer is used as the input end of the electronic medical record analysis model, the first output end of the text extraction layer is connected with the input end of the first characteristic extraction layer, the second output end of the text extraction layer is connected with the input end of the second characteristic extraction layer, the third output end of the text extraction layer is connected with the input end of the third characteristic extraction layer, and the fourth output end of the text extraction layer is connected with the input end of the fourth characteristic extraction layer;
the output end of the first characteristic extraction layer is connected with the input end of the characteristic convolution layer; the output end of the second characteristic extraction layer is connected with the first input end of the characteristic fusion layer; the output end of the third feature extraction layer is connected with the second input end of the feature fusion layer;
the output end of the characteristic convolution layer is connected with the first input end of the information output layer; the output end of the feature fusion layer is connected with the second input end of the information output layer; the output end of the fourth characteristic extraction layer is connected with the third input end of the information output layer;
the output end of the information output layer is used as the output end of the electronic medical record analysis model.
In the invention, the text extraction layer is used as an input end of the electronic medical record analysis model and is used for extracting text information of the electronic medical record, so that the first feature extraction layer, the second feature extraction layer, the third feature extraction layer and the fourth feature extraction layer can conveniently extract features. The first feature extraction layer generates a medication name in the latest medication information by performing mathematical operation (such as exponential operation) on word vectors and word frequencies of keywords in the text information. The second feature extraction layer generates the medication quantity in the latest medication information by performing mathematical operation (such as exponential operation) on the frequency of occurrence of the numerical value in the text information. The third feature extraction layer generates the number of doses in the latest dose information by performing mathematical operation (such as logarithmic operation) on the frequency of occurrence of the numerical value in the text information. And the fourth feature extraction layer generates medication mode and medication tabu information in the latest medication information by carrying out mathematical operation (such as logarithmic operation) on word vectors and word frequencies of keywords in the text information. Since many medicine names are complex and often involve rarely used words, the feature convolution layer of the present invention corrects the medicine name generated by the first feature extraction layer through an activation operation. And the feature fusion layer integrates the medicine use quantity output by the second feature extraction layer and the medicine use times output by the third feature extraction layer. The information output layer is used for unifying the corrected medication names, medication quantity, medication times and medication tabu information as the output of the whole model.
In the embodiment of the present invention, the expression of the first feature extraction layer is:
in the method, in the process of the invention,Xrepresenting the output of the first characteristic convolution layer,g m representing the first text information corresponding to the electronic medical recordmThe word vector of the individual keywords is used,d m representing the first text information corresponding to the electronic medical recordmThe word frequency of the individual keywords is determined,ηrepresenting the output of the text extraction layer,Mthe number of keywords corresponding to the text information of the electronic medical record is represented,erepresenting an index;
the expression of the second feature extraction layer is:
in the method, in the process of the invention,Yrepresenting the output of the second feature extraction layer,c n representing the first text information corresponding to the electronic medical recordnThe word frequency of the individual values is calculated,Nthe number of the numerical values of the text information corresponding to the electronic medical record is represented,erepresenting an index;
the expression of the third feature extraction layer is:
in the method, in the process of the invention,Zrepresenting the output of the third feature extraction layer,log(. Cndot.) represents a logarithmic function;
the expression of the fourth feature extraction layer is:
in the method, in the process of the invention,Wrepresenting the output of the fourth feature extraction layer.
In the embodiment of the invention, the expression of the characteristic convolution layer is as follows:
in the method, in the process of the invention,Frepresenting the output of the characteristic convolution layer,sigmoid(. Cndot.) represents the activation function,Kthe number of convolution kernels representing the characteristic convolution layer,μ k representing the first of the characteristic convolution layerskThe offset of the individual convolution kernels is such that,a k representing the first of the characteristic convolution layerskThe height of the convolution kernel is such that,b k representing the first of the characteristic convolution layerskThe width of the individual convolution kernels is chosen,y k+2 representing the first of the characteristic convolution layerskThe output of the +2 convolution kernels,y k+1 representing the first of the characteristic convolution layerskThe output of the +1 convolution kernel,y k representing the first of the characteristic convolution layerskThe outputs of the individual convolution kernels are then,Xrepresenting the output of the first characteristic convolution layer.
In the embodiment of the invention, the expression of the feature fusion layer is as follows:
in the method, in the process of the invention,Grepresenting the output of the feature fusion layer,representing the Hadamard product operation,Lthe number of convolution kernels representing the feature fusion layer,x l+2 representing the first of the feature fusion layerslThe output of the +2 convolution kernels,x l+1 representing the first of the feature fusion layerslThe output of the +1 convolution kernel,x l representing the first of the feature fusion layerslThe outputs of the individual convolution kernels are then,Yrepresenting the output of the second feature extraction layer,Zrepresenting the output of the third feature extraction layer,Arepresenting a matrix of all values in the second feature extraction layer,Brepresenting a matrix of all values in the third feature extraction layer.
In the embodiment of the present invention, in S1, the historical medication information includes a historical timeout feedback number and a historical timeout feedback duration.
In the invention, the user can feed back the medication result through the terminal after taking the medicine, such as taking the medicine on time, taking the medicine overtime, and the like. Therefore, whether the medication frequency of the reminding user is improved can be judged through the historical medication timeout times and timeout time of the user.
In the embodiment of the invention, in S3, the reminding frequency of the latest medication informationaThe calculation formula of (2) is as follows:
in the method, in the process of the invention,Jindicating the number of historical timeout feedback times,T j represent the firstjThe time-out feedback duration is a time,representing an upward rounding operation,εthe minimum value is represented by a value of,erepresenting an index.
The embodiment of the invention provides a big data-based medication prompt system, which is shown in figure 3 and comprises a medication information acquisition unit, a medication information generation unit and a medication information reminding unit;
the medication information acquisition unit is used for acquiring the electronic medical record and the historical medication information of the user;
the medication information generating unit is used for constructing an electronic medical record analysis model, inputting the electronic medical record of the user into the electronic medical record analysis model, and carrying out feature extraction, feature convolution and feature fusion to generate the latest medication information of the user;
the medication information reminding unit determines the reminding frequency of the latest medication information according to the historical medication information, and sends the latest medication information of the user to the user terminal according to the reminding frequency of the latest medication information.
The embodiment of the application also provides a computer device, which may be a server, and the internal structure of the computer device may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for medication prompt program. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by the processor, implements a medication prompt method based on big data. The system bus includes a data bus, an address bus, and a control bus. The internal memory may include volatile memory such as Random Access Memory (RAM) and/or cache memory, and may further include Read Only Memory (ROM).
It should be noted that while several modules/modules or sub-modules/modules of a computer device are mentioned in the detailed description above, such partitioning is merely exemplary and not mandatory. Indeed, according to embodiments of the invention, the features and functions of several or more of the modules/modules described above may be embodied in one module/module; conversely, the features and functions of one module/module described above may be further divided into a plurality of modules/modules to be embodied.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and when the computer program is executed, part or all of the steps of any one of the medicine use prompting methods in the method embodiment are realized.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program, which may be stored on a non-transitory computer readable storage medium, that when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that in the present invention, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (6)
1. The medicine use prompting method based on big data is characterized by comprising the following steps:
s1, acquiring an electronic medical record and historical medication information of a user;
s2, an electronic medical record analysis model is built, the electronic medical record of the user is input into the electronic medical record analysis model, feature extraction, feature convolution and feature fusion are carried out, and latest medication information of the user is generated;
s3, determining the reminding frequency of the latest medication information according to the historical medication information, and sending the latest medication information of the user to the user terminal according to the reminding frequency of the latest medication information;
in the step S2, the electronic medical record analysis model comprises a text extraction layer, a first feature extraction layer, a second feature extraction layer, a third feature extraction layer, a fourth feature extraction layer, a feature convolution layer, a feature fusion layer and an information output layer;
the input end of the text extraction layer is used as the input end of the electronic medical record analysis model, the first output end of the text extraction layer is connected with the input end of the first feature extraction layer, the second output end of the text extraction layer is connected with the input end of the second feature extraction layer, the third output end of the text extraction layer is connected with the input end of the third feature extraction layer, and the fourth output end of the text extraction layer is connected with the input end of the fourth feature extraction layer;
the output end of the first characteristic extraction layer is connected with the input end of the characteristic convolution layer; the output end of the second characteristic extraction layer is connected with the first input end of the characteristic fusion layer; the output end of the third feature extraction layer is connected with the second input end of the feature fusion layer;
the output end of the characteristic convolution layer is connected with the first input end of the information output layer; the output end of the characteristic fusion layer is connected with the second input end of the information output layer; the output end of the fourth characteristic extraction layer is connected with the third input end of the information output layer;
the output end of the information output layer is used as the output end of the electronic medical record analysis model;
the expression of the first feature extraction layer is as follows:
in the method, in the process of the invention,Xrepresenting the output of the first characteristic convolution layer,g m representing the first text information corresponding to the electronic medical recordmThe word vector of the individual keywords is used,d m representing the first text information corresponding to the electronic medical recordmThe word frequency of the individual keywords is determined,ηrepresenting the output of the text extraction layer,Mthe number of keywords corresponding to the text information of the electronic medical record is represented,erepresenting an index;
the expression of the second feature extraction layer is:
in the method, in the process of the invention,Yrepresenting the output of the second feature extraction layer,c n representing the first text information corresponding to the electronic medical recordnThe word frequency of the individual values is calculated,Nthe number of the numerical values of the text information corresponding to the electronic medical record is represented,erepresenting an index;
the expression of the third feature extraction layer is:
in the method, in the process of the invention,Zrepresenting the output of the third feature extraction layer,log(. Cndot.) represents a logarithmic function;
the expression of the fourth feature extraction layer is:
in the method, in the process of the invention,Wrepresenting an output of the fourth feature extraction layer;
the expression of the characteristic convolution layer is as follows:
in the method, in the process of the invention,Frepresenting the output of the characteristic convolution layer,sigmoid(. Cndot.) represents the activation function,Kthe number of convolution kernels representing the characteristic convolution layer,μ k representing the first of the characteristic convolution layerskThe offset of the individual convolution kernels is such that,a k representing the first of the characteristic convolution layerskThe height of the convolution kernel is such that,b k representing the first of the characteristic convolution layerskThe width of the individual convolution kernels is chosen,y k+2 representing the first of the characteristic convolution layerskThe output of the +2 convolution kernels,y k+1 representing the first of the characteristic convolution layerskThe output of the +1 convolution kernel,y k representing the first of the characteristic convolution layerskThe outputs of the individual convolution kernels are then,Xan output representing a first characteristic convolution layer;
the expression of the feature fusion layer is as follows:
in the method, in the process of the invention,Grepresenting the output of the feature fusion layer,representing the Hadamard product operation,Lthe number of convolution kernels representing the feature fusion layer,x l+2 representing the first of the feature fusion layerslThe output of the +2 convolution kernels,x l+1 representing the first of the feature fusion layerslThe output of the +1 convolution kernel,x l representing the first of the feature fusion layerslThe outputs of the individual convolution kernels are then,Yrepresenting the output of the second feature extraction layer,Zrepresenting the output of the third feature extraction layer,Arepresenting a matrix of all values in the second feature extraction layer,Brepresenting a matrix of all values in the third feature extraction layer.
2. The big data based medication hint method of claim 1, wherein in S1, the historical medication information includes a historical timeout feedback number and a historical timeout feedback duration.
3. The big data-based medication prompt method according to claim 1, wherein in S3, the latest medication information is reminded frequentlyaThe calculation formula of (2) is as follows:
in the method, in the process of the invention,Jindicating the number of historical timeout feedback times,T j represent the firstjThe time-out feedback duration is a time,representing an upward rounding operation,εthe minimum value is represented by a value of,erepresenting an index.
4. The medication prompt system based on big data is characterized by comprising a medication information acquisition unit, a medication information generation unit and a medication information prompt unit;
the medication information acquisition unit is used for acquiring the electronic medical record and the historical medication information of the user;
the medication information generating unit is used for constructing an electronic medical record analysis model, inputting the electronic medical record of the user into the electronic medical record analysis model, and carrying out feature extraction, feature convolution and feature fusion to generate the latest medication information of the user;
the medication information reminding unit determines the reminding frequency of the latest medication information according to the historical medication information, and sends the latest medication information of the user to the user terminal according to the reminding frequency of the latest medication information;
the medicine prompt system is realized based on a medicine prompt method, and the medicine prompt method comprises the following steps:
s1, acquiring an electronic medical record and historical medication information of a user;
s2, an electronic medical record analysis model is built, the electronic medical record of the user is input into the electronic medical record analysis model, feature extraction, feature convolution and feature fusion are carried out, and latest medication information of the user is generated;
s3, determining the reminding frequency of the latest medication information according to the historical medication information, and sending the latest medication information of the user to the user terminal according to the reminding frequency of the latest medication information;
in the step S2, the electronic medical record analysis model comprises a text extraction layer, a first feature extraction layer, a second feature extraction layer, a third feature extraction layer, a fourth feature extraction layer, a feature convolution layer, a feature fusion layer and an information output layer;
the input end of the text extraction layer is used as the input end of the electronic medical record analysis model, the first output end of the text extraction layer is connected with the input end of the first feature extraction layer, the second output end of the text extraction layer is connected with the input end of the second feature extraction layer, the third output end of the text extraction layer is connected with the input end of the third feature extraction layer, and the fourth output end of the text extraction layer is connected with the input end of the fourth feature extraction layer;
the output end of the first characteristic extraction layer is connected with the input end of the characteristic convolution layer; the output end of the second characteristic extraction layer is connected with the first input end of the characteristic fusion layer; the output end of the third feature extraction layer is connected with the second input end of the feature fusion layer;
the output end of the characteristic convolution layer is connected with the first input end of the information output layer; the output end of the characteristic fusion layer is connected with the second input end of the information output layer; the output end of the fourth characteristic extraction layer is connected with the third input end of the information output layer;
the output end of the information output layer is used as the output end of the electronic medical record analysis model;
the expression of the first feature extraction layer is as follows:
in the method, in the process of the invention,Xrepresenting the output of the first characteristic convolution layer,g m representing the first text information corresponding to the electronic medical recordmThe word vector of the individual keywords is used,d m representing the first text information corresponding to the electronic medical recordmThe word frequency of the individual keywords is determined,ηrepresenting the output of the text extraction layer,Mthe number of keywords corresponding to the text information of the electronic medical record is represented,erepresenting an index;
the expression of the second feature extraction layer is:
in the method, in the process of the invention,Yrepresenting the output of the second feature extraction layer,c n representing the first text information corresponding to the electronic medical recordnThe word frequency of the individual values is calculated,Nthe number of the numerical values of the text information corresponding to the electronic medical record is represented,erepresenting an index;
the expression of the third feature extraction layer is:
in the method, in the process of the invention,Zrepresenting the output of the third feature extraction layer,log(. Cndot.) represents a logarithmic function;
the expression of the fourth feature extraction layer is:
in the method, in the process of the invention,Wrepresenting an output of the fourth feature extraction layer;
the expression of the characteristic convolution layer is as follows:
in the method, in the process of the invention,Frepresenting the output of the characteristic convolution layer,sigmoid(. Cndot.) represents the activation function,Kthe number of convolution kernels representing the characteristic convolution layer,μ k representing the first of the characteristic convolution layerskThe offset of the individual convolution kernels is such that,a k representing the first of the characteristic convolution layerskThe height of the convolution kernel is such that,b k representing the first of the characteristic convolution layerskThe width of the individual convolution kernels is chosen,y k+2 representing the first of the characteristic convolution layerskThe output of the +2 convolution kernels,y k+1 representing the first of the characteristic convolution layerskThe output of the +1 convolution kernel,y k representing the first of the characteristic convolution layerskThe outputs of the individual convolution kernels are then,Xan output representing a first characteristic convolution layer;
the expression of the feature fusion layer is as follows:
in the method, in the process of the invention,Grepresenting the output of the feature fusion layer,representing the Hadamard product operation,Lrepresenting the number of convolution kernels of a feature fusion layer，x l+2 Representing the first of the feature fusion layerslThe output of the +2 convolution kernels,x l+1 representing the first of the feature fusion layerslThe output of the +1 convolution kernel,x l representing the first of the feature fusion layerslThe outputs of the individual convolution kernels are then,Yrepresenting the output of the second feature extraction layer,Zrepresenting the output of the third feature extraction layer,Arepresenting a matrix of all values in the second feature extraction layer,Brepresenting a matrix of all values in the third feature extraction layer.
5. A computer device comprising a memory, a processor and a medication hint program stored on the memory and executable on the processor, the medication hint program when executed by the processor implementing the steps of the medication hint method of any of claims 1 to 3.
6. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the steps of the medication intake prompting method according to any one of claims 1 to 3 are implemented when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311295326.7A CN117034202B (en) | 2023-10-09 | 2023-10-09 | Big data-based medication prompt method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311295326.7A CN117034202B (en) | 2023-10-09 | 2023-10-09 | Big data-based medication prompt method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117034202A CN117034202A (en) | 2023-11-10 |
| CN117034202B true CN117034202B (en) | 2024-01-05 |
Family
ID=88645307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311295326.7A Active CN117034202B (en) | 2023-10-09 | 2023-10-09 | Big data-based medication prompt method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117034202B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104137110A (en) * | 2013-01-17 | 2014-11-05 | 华为技术有限公司 | Medication reminder method, device and system |
| CN109637612A (en) * | 2018-10-31 | 2019-04-16 | 北京春雨天下软件有限公司 | A kind of medication taboo reminding method, server, terminal, equipment and readable medium |
| CN111191020A (en) * | 2019-12-27 | 2020-05-22 | 江苏省人民医院（南京医科大学第一附属医院） | Prescription recommendation method and system based on machine learning and knowledge graph |
| CN112116978A (en) * | 2020-09-17 | 2020-12-22 | 陕西师范大学 | Method, system and device for recommending rheumatism immunity medicine |
| CN113838573A (en) * | 2021-09-14 | 2021-12-24 | 北京百度网讯科技有限公司 | Clinical assistant decision-making diagnosis self-learning method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030086338A1 (en) * | 2001-11-08 | 2003-05-08 | Sastry Srikonda V. | Wireless web based drug compliance system |
-
2023
- 2023-10-09 CN CN202311295326.7A patent/CN117034202B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104137110A (en) * | 2013-01-17 | 2014-11-05 | 华为技术有限公司 | Medication reminder method, device and system |
| CN109637612A (en) * | 2018-10-31 | 2019-04-16 | 北京春雨天下软件有限公司 | A kind of medication taboo reminding method, server, terminal, equipment and readable medium |
| CN111191020A (en) * | 2019-12-27 | 2020-05-22 | 江苏省人民医院（南京医科大学第一附属医院） | Prescription recommendation method and system based on machine learning and knowledge graph |
| CN112116978A (en) * | 2020-09-17 | 2020-12-22 | 陕西师范大学 | Method, system and device for recommending rheumatism immunity medicine |
| CN113838573A (en) * | 2021-09-14 | 2021-12-24 | 北京百度网讯科技有限公司 | Clinical assistant decision-making diagnosis self-learning method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117034202A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11670415B2 (en) | Data driven analysis, modeling, and semi-supervised machine learning for qualitative and quantitative determinations | |
| US8612261B1 (en) | Automated learning for medical data processing system | |
| CN112631997B (en) | Data processing method, device, terminal and storage medium | |
| US20200257659A1 (en) | Method and apparatus for determing description information, electronic device and computer storage medium | |
| WO2020172446A1 (en) | Automated generation of structured patient data record | |
| US11270156B2 (en) | Machine learning for dynamically updating a user interface | |
| CN111210917A (en) | Medication guiding method and system based on offline code scanning | |
| CN109872822A (en) | Medical assist method, apparatus, equipment and medium | |
| CN112037875B (en) | Intelligent diagnosis and treatment data processing method, equipment, device and storage medium | |
| CN109871440B (en) | Intelligent prompting method, device and equipment based on semantic analysis | |
| CN112837772A (en) | Pre-inquiry case history generation method and device | |
| US11176471B1 (en) | Explainable machine learning models | |
| CN113409907A (en) | Intelligent pre-inquiry method and system based on Internet hospital | |
| CN111785383A (en) | Data processing method and related equipment | |
| CN112035619A (en) | Medical questionnaire screening method, device, equipment and medium based on artificial intelligence | |
| CN117034202B (en) | Big data-based medication prompt method, system, equipment and storage medium | |
| CN111078564B (en) | UI test case management method, device, computer equipment and computer readable storage medium | |
| CN111104481B (en) | Method, device and equipment for identifying matching field | |
| CN106502825A (en) | Data processing method and device | |
| CN115331046A (en) | Image classification method and device based on medical field, storage medium and equipment | |
| CA3165960A1 (en) | Extracting content from freeform text samples into custom fields in a software application | |
| CN114913956A (en) | Repeated medication reminding method and device based on knowledge graph and electronic equipment | |
| WO2021151329A1 (en) | Patient medication behavior intervention method and apparatus, and server and storage medium | |
| CN113870978A (en) | Artificial intelligence-based exercise recommendation method, device, server and medium | |
| CN113703898A (en) | Card type interaction method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |