CN116881554A - Medical prescription recommendation method and device, electronic equipment and readable storage medium - Google Patents
Medical prescription recommendation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN116881554A CN116881554A CN202310815764.5A CN202310815764A CN116881554A CN 116881554 A CN116881554 A CN 116881554A CN 202310815764 A CN202310815764 A CN 202310815764A CN 116881554 A CN116881554 A CN 116881554A
- Authority
- CN
- China
- Prior art keywords
- medical
- data
- user
- feature extraction
- historical
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000000605 extraction Methods 0.000 claims abstract description 99
- 239000013598 vector Substances 0.000 claims abstract description 68
- 238000012545 processing Methods 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims description 36
- 238000011156 evaluation Methods 0.000 claims description 23
- 230000007958 sleep Effects 0.000 claims description 5
- 239000003814 drug Substances 0.000 abstract description 10
- 238000006243 chemical reaction Methods 0.000 abstract description 8
- 230000014759 maintenance of location Effects 0.000 abstract description 6
- 230000036541 health Effects 0.000 description 18
- 230000006399 behavior Effects 0.000 description 12
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 5
- 238000013145 classification model Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003190 augmentative effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 230000005548 health behavior Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004617 sleep duration Effects 0.000 description 1
- 230000003860 sleep quality Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Medicinal Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a medical prescription recommendation method, a medical prescription recommendation device, electronic equipment and a readable storage medium, and relates to the technical field of data processing and digital medical treatment. The method comprises the following steps: acquiring real-time inquiry data of a user, and correspondingly searching historical medical data of the user according to user information of the user; if the historical medical data of the user is found, performing feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors; if the historical medical data of the user is not found, performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors; and inputting the medical characteristic vector into a prediction model to predict the medical prescription, so as to obtain a recommended medical prescription, wherein the recommended medical prescription comprises at least one medical commodity. The method ensures the accuracy of the predicted prescription, facilitates the purchase of the medicine by the user through the accurate recommendation of the medical prescription, and improves the retention and conversion rate of the user.
Description
Technical Field
The present application relates to the field of data processing and digital medical technology, and in particular, to a medical prescription recommendation method, apparatus, electronic device, and readable storage medium.
Background
Along with the increasing cost of internet traffic, enterprises gradually turn to refined operation from the traditional popularization mode, and more emphasis is placed on user retention and conversion rate. In the related art, the method for improving the conversion rate is divided into two types, namely, optimizing the product path, improving the user experience, monitoring the page conversion funnel condition and testing improvement; secondly, users research and user tracking, find potential demands of users, and guide the users to convert. The methods are all based on the existing autonomous behavior of the user for tracking and optimizing, and cannot be fully applied to the inquiry behavior or shopping behavior of the Internet medical platform.
In the medical scene, more accurate commodity recommendation is required to be performed on a user (namely a patient), so that the problems that the user cannot accurately describe the requirement or cannot find proper health care products, medicines and the like in the medical field due to lack of expertise are solved. While the traditional medical scenes often recommend correct or proper prescriptions through doctor inquiry modes, internet big data in the related technology are more used for recommending commodities to users based on historical autonomous behaviors such as user consumption habits and the like. However, in the medical scenario, there is often no history shopping scenario for the user, that is, there is a cold start problem, so that the manner of recommending using internet big data in the related art cannot be applied to the medical scenario.
Disclosure of Invention
In view of the above, the application provides a medical prescription recommending method, a medical prescription recommending device, an electronic device and a readable storage medium, which ensure the accuracy of recommending prescriptions and improve the retention and conversion rate of users.
In a first aspect, an embodiment of the present application provides a medical prescription recommendation method, including:
acquiring real-time inquiry data of a user, and correspondingly searching historical medical data of the user according to user information of the user;
if the historical medical data of the user is found, performing feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors; if the historical medical data of the user is not found, performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
and inputting the medical characteristic vector into a prediction model to predict the medical prescription, so as to obtain a recommended medical prescription, wherein the recommended medical prescription comprises at least one medical commodity.
The method according to the embodiment of the application can also have the following additional technical characteristics:
in the above technical solution, optionally, the method further includes:
acquiring evaluation feedback information of a doctor on the recommended medical prescription;
and if the evaluation feedback information is that the recommended medical prescription prediction is correct, displaying the recommended medical prescription.
In any of the foregoing solutions, optionally, the method further includes:
acquiring order feedback information of the recommended medical prescription by a user;
and updating the prediction model according to the order feedback information and the evaluation feedback information.
In any of the above technical solutions, optionally, performing feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models to obtain a medical feature vector, or performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain a medical feature vector, including:
respectively carrying out feature extraction processing on acquired data through a plurality of different feature extraction models to obtain a plurality of sub-feature vectors, wherein the acquired data comprises the historical medical data and the real-time inquiry data or the acquired data comprises the real-time inquiry data;
and merging the plurality of sub-feature vectors to generate the multi-dimensional medical feature vector.
In any of the foregoing solutions, optionally, the method further includes:
acquiring sample data, and respectively training a plurality of different feature extraction models according to the sample data;
and when the model is trained, training the current feature extraction model by using the sample data to obtain a training result, adjusting the weight of the sample data according to the training result, and then using the sample data to extract the model of the next feature.
In any of the foregoing solutions, optionally, training a plurality of different feature extraction models according to the sample data, includes:
splitting the sample data into a plurality of phrases, and respectively training a plurality of different feature extraction models according to the phrases.
In any of the foregoing solutions, optionally, the historical medical data includes at least one of: historical ordering data, historical consultation data, historical medical prescriptions, historical physical examination data, historical movement data, historical sleep data and historical psychological consultation data.
In a second aspect, an embodiment of the present application provides a medical prescription recommendation apparatus, including:
the acquisition module is used for acquiring real-time inquiry data of a user and correspondingly searching historical medical data of the user according to user information of the user;
the feature extraction module is used for carrying out feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models if the historical medical data of the user is found out, so as to obtain medical feature vectors; if the historical medical data of the user is not found, performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
the prediction module is used for inputting the medical characteristic vector into a prediction model to predict the medical prescription, and obtaining a recommended medical prescription, wherein the recommended medical prescription comprises at least one medical commodity.
In a third aspect, embodiments of the present application provide an electronic device comprising a processor and a memory storing a program or instructions executable on the processor, which when executed by the processor, implement the steps of the method as in the first aspect.
In a fourth aspect, embodiments of the present application provide a readable storage medium having stored thereon a program or instructions which when executed by a processor perform the steps of the method as in the first aspect.
In a fifth aspect, embodiments of the present application provide a chip comprising a processor and a communication interface, the communication interface being coupled to the processor, the processor being configured to execute programs or instructions to implement a method as in the first aspect.
In a sixth aspect, embodiments of the present application provide a computer program product stored in a storage medium, the program product being executable by at least one processor to implement a method as in the first aspect.
In the embodiment of the application, the real-time inquiry data of the user is obtained, and the historical medical data corresponding to the user information is searched in the medical health service cloud platform according to the user information of the user. When the historical medical data corresponding to the user information is found in the medical health service cloud platform, the fact that the user generates medical behaviors on the platform is indicated, the acquired historical medical data and real-time inquiry data are subjected to feature extraction processing through a plurality of feature extraction models, medical feature vectors are obtained, and medical prescription prediction is carried out according to the medical feature vectors through a prediction model, so that recommended medical prescriptions suitable for the user are obtained. When the historical medical data corresponding to the user information is not found in the medical health service cloud platform, the user is a new user of the platform, and medical behaviors are not generated on the platform, the real-time inquiry data are subjected to feature extraction processing through a plurality of feature extraction models to obtain medical feature vectors, and medical prescription prediction is carried out by a prediction model according to the medical feature vectors to obtain recommended medical prescriptions suitable for the user.
According to the embodiment of the application, on one hand, various historical medical data can be combined, the medical prescription recommended by the platform can be ensured to be in the prescription range prescribed by a historic doctor, the accuracy of the predicted prescription is ensured, the range of recommended commodities is narrowed by purchasing records of users with similar demands on the historic recommended commodities, and the accuracy is improved. On the other hand, for a new user of the platform, namely, a user without history medical data, the method and the device can give the recommendation result with higher corresponding accuracy based on the real-time inquiry data of the user, and ensure the accuracy of cold start. Through accurate medical prescription recommendation, the user can purchase medicine conveniently, and the retention and conversion rate of the user on the medical health service cloud platform are improved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 illustrates one of the flow diagrams of a medical prescription recommendation method according to an embodiment of the present application;
FIG. 2 is a second flow chart of a medical prescription recommendation method according to an embodiment of the application;
FIG. 3 is a third flow chart of a medical prescription recommendation method according to an embodiment of the application;
FIG. 4 shows a block diagram of a medical prescription recommendation apparatus according to an embodiment of the present application;
fig. 5 shows a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
The technical solutions of the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which are obtained by a person skilled in the art based on the embodiments of the present application, fall within the scope of protection of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
Medical cloud (Medical cloud) refers to the fact that a Medical health service cloud platform is created by combining Medical technology on the basis of new technologies such as cloud computing, mobile technology, multimedia, 4G communication, big data, internet of things and the like, and Medical resources are shared and Medical scope is enlarged. Because of the application and combination of the cloud computing technology, the efficiency of the medical institution is improved, and residents can seek medical advice conveniently. At present, appointment registration, intelligent diagnosis and diagnosis guiding, electronic medical records, medical insurance, online inquiry, medicine purchasing, generation and analysis of physical examination reports and the like of hospitals are products combined with the medical field, and the medical cloud also has the advantages of data safety, information sharing, dynamic expansion and overall layout.
The medical prescription recommending method, the medical prescription recommending device, the electronic equipment and the readable storage medium provided by the embodiment of the application are described in detail through specific embodiments and application scenes thereof with reference to the accompanying drawings.
The embodiment of the application provides a medical prescription recommendation method which is applied to a medical health service cloud platform. As shown in fig. 1, the method includes:
step 101, acquiring real-time inquiry data of a user, and correspondingly searching historical medical data of the user according to user information of the user;
step 102, judging whether the historical medical data of the user is found, if the historical medical data of the user is found, entering step 103, and if the historical medical data of the user is not found, entering step 104;
step 103, performing feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
104, performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
and 105, inputting the medical characteristic vector into a prediction model to predict the medical prescription, and obtaining a recommended medical prescription, wherein the recommended medical prescription comprises at least one medical commodity.
In this embodiment, real-time inquiry data of the user is acquired, the inquiry data including a description of a disorder, search information of a medicine or a health product, and the like. And searching historical medical data corresponding to the user information in the medical health service cloud platform according to the user information (such as user ID, user mobile phone number and the like) of the user.
If the user has performed medical actions such as inquiry and medicine purchase on the medical health service cloud platform, the historical medical data of the user is stored under the condition of user authorization, and if the user is a new user of the platform, the historical medical data of the user is not stored in the platform.
When the historical medical data corresponding to the user information is found in the medical health service cloud platform, the fact that the user generates medical behaviors on the platform is indicated, the acquired historical medical data and real-time inquiry data are subjected to feature extraction processing through a plurality of feature extraction models, medical feature vectors are obtained, and medical prescription prediction is carried out according to the medical feature vectors through a prediction model, so that recommended medical prescriptions suitable for the user are obtained.
When the historical medical data corresponding to the user information is not found in the medical health service cloud platform, the user is a new user of the platform, and medical behaviors are not generated on the platform, the real-time inquiry data are subjected to feature extraction processing through a plurality of feature extraction models to obtain medical feature vectors, and medical prescription prediction is carried out by a prediction model according to the medical feature vectors to obtain recommended medical prescriptions suitable for the user.
Wherein, medical goods include medicines, health products, medical instruments, etc., and are not particularly limited herein.
The feature extraction model is a deep network model with feature extraction capability, and can extract medical features of historical medical data and/or real-time inquiry data.
In one embodiment, the plurality of feature extraction models include a Random Forest-based classification model, a DNN (Deep-Learning Neural Network, deep neural network) -based classification model and an RNN (Recurrent Neural Network ) -based classification model, wherein the Random Forest-based classification model is Random integration of decision trees, can improve the vulnerability of the decision trees to be attacked to a certain extent, is suitable for the situation that the data dimension is not high and higher accuracy is required to be achieved, does not need to adjust excessive parameters, and has better interpretation. And respectively extracting the characteristics of the text data set of the historical medical data and/or the real-time inquiry data through the three characteristic extraction models.
According to the embodiment of the application, on one hand, various historical medical data can be combined, the medical prescription recommended by the platform can be ensured to be in the prescription range prescribed by a historic doctor, the accuracy of the predicted prescription is ensured, the range of recommended commodities is narrowed by purchasing records of users with similar demands on the historic recommended commodities, and the accuracy is improved. On the other hand, for a new user of the platform, namely, a user without history medical data, the method and the device can give the recommendation result with higher corresponding accuracy based on the real-time inquiry data of the user, and ensure the accuracy of cold start.
Through accurate medical prescription recommendation, the user can purchase medicine conveniently, and the retention and conversion rate of the user on the medical health service cloud platform are improved.
In one embodiment of the present application, the historical medical data includes historical medical behavior data including, but not limited to, historical order data, historical inquiry data, historical medical prescriptions, and the like, and historical health behavior data including, but not limited to, historical physical examination data, historical exercise data, historical sleep data, historical psychological consultation data, and the like.
The application can analyze the data, and based on the process and result of online inquiry, different prescriptions of different diseases by massive doctors and search keywords after users enter a platform, the application can recommend more proper medical prescriptions for users by combining the experience of prescriptions corresponding to doctor symptoms and the result selected by other users with similar medicine purchasing behaviors in history records.
As a refinement and extension to the above embodiment, another medical prescription recommendation method is provided in the embodiment of the present application, as shown in FIG. 2, the method includes:
step 201, acquiring real-time inquiry data of a user, and correspondingly searching historical medical data of the user according to user information of the user;
step 202, judging whether the historical medical data of the user is found, if the historical medical data of the user is found, entering step 203, and if the historical medical data of the user is not found, entering step 204;
step 203, performing feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
step 204, performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
step 205, inputting the medical feature vector into a prediction model to predict a medical prescription, and obtaining a recommended medical prescription, wherein the recommended medical prescription comprises at least one medical commodity;
step 206, obtaining the evaluation feedback information of the doctor on the recommended medical prescription, and if the evaluation feedback information is that the recommended medical prescription is correctly predicted, displaying the recommended medical prescription.
Steps 201 to 205 are the same as or similar to steps 101 to 105 in the above embodiments, and are not repeated here.
In this embodiment, after the recommended medical prescription is generated, the recommended medical prescription is sent to the doctor terminal for the doctor to evaluate. If the recommended medical prescription is correct, feeding back evaluation feedback information of the correct recommended medical prescription; if the recommended medical prescription is incorrect, the feedback includes evaluation feedback information that the recommended medical prescription is incorrect and that an adjustment is made to the recommended medical prescription.
After the evaluation feedback information fed back by the doctor is obtained, if the evaluation feedback information is that the recommended medical prescription prediction is correct, displaying the evaluation feedback information to the user; if the evaluation feedback information is that the recommended medical prescription prediction is incorrect, the recommended medical prescription is updated by combining with the adjustment of the doctor on the recommended medical prescription, and the updated recommended medical prescription is displayed to the user.
According to the embodiment of the application, the medical prescription recommended to the user is further ensured to be accurate by combining with the evaluation feedback of the doctor and recommending to the user.
As a refinement and extension to the above embodiment, an embodiment of the present application provides still another medical prescription recommendation method, as shown in FIG. 3, including:
step 301, acquiring real-time inquiry data of a user, and correspondingly searching historical medical data of the user according to user information of the user;
step 302, judging whether the historical medical data of the user is found, if the historical medical data of the user is found, entering step 303, and if the historical medical data of the user is not found, entering step 304;
step 303, performing feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
step 304, performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
step 305, inputting the medical feature vector into a prediction model to predict a medical prescription, and obtaining a recommended medical prescription, wherein the recommended medical prescription comprises at least one medical commodity;
step 306, acquiring evaluation feedback information of the doctor on the recommended medical prescription, and if the evaluation feedback information is that the recommended medical prescription is correctly predicted, displaying the recommended medical prescription;
step 307, obtaining the order feedback information of the user on the recommended medical prescription, and updating the prediction model according to the order feedback information and the evaluation feedback information.
The steps 301 to 206 are the same as or similar to the steps 201 to 206 in the above embodiments, and are not repeated here.
In this embodiment, after a medical prescription is recommended to a user, order feed-back information of the user for the medical prescription is acquired, where the order feed-back information includes user order information including medical goods, purchase times, prescription evaluations, and the like that are ordered by the user when the recommended medical prescription is a plurality of, and user non-order information including non-order reasons and the like. And the feedback information of the order of the medical prescription by the user and the feedback information of the evaluation of the medical prescription by the doctor are used as new medical feature vectors to participate in the training and optimization of the prediction model of the next time, so that the accuracy of the prediction model is improved, and the accuracy of the recommended result is further ensured.
In any of the foregoing embodiments, performing feature extraction processing on the historical medical data and the real-time query data through a plurality of feature extraction models to obtain a medical feature vector, or performing feature extraction processing on the real-time query data through a plurality of feature extraction models to obtain a medical feature vector, including:
respectively carrying out feature extraction processing on acquired data through a plurality of different feature extraction models to obtain a plurality of sub-feature vectors, wherein the acquired data comprises the historical medical data and the real-time inquiry data or the acquired data comprises the real-time inquiry data;
and merging the plurality of sub-feature vectors to generate the multi-dimensional medical feature vector.
In this embodiment, feature extraction processing is performed on the acquired data by a plurality of different feature extraction models, respectively, and brand names, purchase times, and the like are mainly extracted for next data, and diagnosis results, number of interviews, duration of interviews, number of conversations, length of each conversation, and the like of the interviews are mainly extracted for the interview data, and prescription contents, total prescription count, and the like are mainly extracted for medical prescriptions. Physical examination data mainly extracts physical examination times, unqualified data and the like, exercise data mainly extracts exercise times, exercise projects, duration of each exercise and the like, sleep data mainly extracts sleep duration, sleep quality and the like, consultation data mainly extracts consultation times, whether rights are used for deduction, consultation results, sex of a consultation doctor and the like, and the data is extracted as content which can be understood by a model through feature extraction.
The features extracted by each feature extraction model are concatenated, that is, each set of data (historical medical data and/or real-time interrogation data) is extracted as a multi-dimensional vector, and the vectors are put into a set by the concatenation. For example, if 3 two-dimensional vectors are extracted for a set of data at a time, then 9 two-dimensional vectors are obtained after concatenation of vectors corresponding to the 3 feature extraction models, and all 9 two-dimensional vectors are used to describe the set of data.
Further, the medical characteristic vector is input into a prediction model to realize medical prescription prediction. The prediction model may be an SVM (Support Vector Mac, also called a support vector machine) model, which is suitable for processing data classification in a high-dimensional sample space based on a kernel function, setting a threshold according to the probability of classification, and outputting a predicted prescription when the probability of the predicted prescription passes the significance test.
By the mode, the sub-feature vectors extracted by the feature extraction models are spliced into the multi-dimensional medical feature vector in a cascading manner, medical prescription prediction is realized through various features, and the accuracy of medical prescription prediction is improved.
In any of the above embodiments, the method further comprises:
acquiring sample data, and respectively training a plurality of different feature extraction models according to the sample data;
and when the model is trained, training the current feature extraction model by using the sample data to obtain a training result, adjusting the weight of the sample data according to the training result, and then using the sample data to extract the model of the next feature.
In this embodiment, when model training is performed for a plurality of different feature extraction models, integrated training is performed, the weights of the samples are updated with the performance of the previous model, and the latter model is trained. For example, a weak learner 1 is first trained from a training set having initial weights, and then the weights of the samples are updated according to the performance of the weak learner 1. Then, the weak learner 2 is trained on the training set with the new weight, and the weights of the samples are updated according to the performances of the weak learner 2, thereby repeating the above steps a plurality of times to obtain m learners.
By the method, the defects inherent to a single model or a model with a certain group of parameters are overcome, so that more models are integrated, the advantages and disadvantages are overcome, and the limitation is avoided. In the integration, when each sample data with high error rate after the previous model training is put into the next model training, the weight (boosting) of each sample data is increased, and the sample data is more emphasized, so that the model training effect is improved.
In any of the foregoing embodiments, training a plurality of different feature extraction models according to the sample data, respectively, specifically includes:
splitting the sample data into a plurality of phrases, and respectively training a plurality of different feature extraction models according to the phrases.
In this embodiment, because the inquiry link and the psychological consultation link have dialogue contents, aiming at the inquiry data and the psychological consultation data in the sample data, a word segmentation mode of a word group is introduced, and the word group (phrase) obtained by word segmentation is used as a parameter input model for training, compared with the classification training using a single word as a parameter, the accuracy can be improved.
As a specific implementation of the medical prescription recommendation method, the embodiment of the application provides a medical prescription recommendation device. As shown in fig. 4, the medical prescription recommendation apparatus 400 includes: an acquisition module 401, a feature extraction module 402 and a prediction module 403.
The acquiring module 401 is configured to acquire real-time inquiry data of a user, and correspondingly search historical medical data of the user according to user information of the user;
the feature extraction module 402 is configured to perform feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models if the historical medical data of the user is found, so as to obtain a medical feature vector; if the historical medical data of the user is not found, performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
the prediction module 403 is configured to input the medical feature vector to a prediction model to perform medical prescription prediction, so as to obtain a recommended medical prescription, where the recommended medical prescription includes at least one medical commodity.
In the embodiment, real-time inquiry data of a user is acquired, and historical medical data corresponding to the user information is searched in a medical health service cloud platform according to the user information of the user. When the historical medical data corresponding to the user information is found in the medical health service cloud platform, the fact that the user generates medical behaviors on the platform is indicated, the acquired historical medical data and real-time inquiry data are subjected to feature extraction processing through a plurality of feature extraction models, medical feature vectors are obtained, and medical prescription prediction is carried out according to the medical feature vectors through a prediction model, so that recommended medical prescriptions suitable for the user are obtained. When the historical medical data corresponding to the user information is not found in the medical health service cloud platform, the user is a new user of the platform, and medical behaviors are not generated on the platform, the real-time inquiry data are subjected to feature extraction processing through a plurality of feature extraction models to obtain medical feature vectors, and medical prescription prediction is carried out by a prediction model according to the medical feature vectors to obtain recommended medical prescriptions suitable for the user.
According to the embodiment of the application, on one hand, various historical medical data can be combined, the medical prescription recommended by the platform can be ensured to be in the prescription range prescribed by a historic doctor, the accuracy of the predicted prescription is ensured, the range of recommended commodities is narrowed by purchasing records of users with similar demands on the historic recommended commodities, and the accuracy is improved. On the other hand, for a new user of the platform, namely, a user without history medical data, the method and the device can give the recommendation result with higher corresponding accuracy based on the real-time inquiry data of the user, and ensure the accuracy of cold start.
Through accurate medical prescription recommendation, the user can purchase medicine conveniently, and the retention and conversion rate of the user on the medical health service cloud platform are improved.
Further, the obtaining module 401 is further configured to obtain evaluation feedback information of the doctor on the recommended medical prescription;
the apparatus further comprises:
and the display module is used for displaying the recommended medical prescription if the evaluation feedback information is that the recommended medical prescription is predicted correctly.
Further, the obtaining module 401 is further configured to obtain order feedback information of the user on the recommended medical prescription;
the apparatus further comprises:
and the model training module is used for updating the prediction model according to the ordering feedback information and the evaluation feedback information.
Further, the feature extraction module 402 is specifically configured to:
respectively carrying out feature extraction processing on acquired data through a plurality of different feature extraction models to obtain a plurality of sub-feature vectors, wherein the acquired data comprises the historical medical data and the real-time inquiry data or the acquired data comprises the real-time inquiry data;
and merging the plurality of sub-feature vectors to generate the multi-dimensional medical feature vector.
Further, the obtaining module 401 is further configured to obtain sample data;
the model training module is also used for respectively training a plurality of different feature extraction models according to the sample data;
and when the model is trained, training the current feature extraction model by using the sample data to obtain a training result, adjusting the weight of the sample data according to the training result, and then using the sample data to extract the model of the next feature.
Further, the model training module is specifically configured to:
splitting the sample data into a plurality of phrases, and respectively training a plurality of different feature extraction models according to the phrases.
Further, the historical medical data includes at least one of: historical ordering data, historical consultation data, historical medical prescriptions, historical physical examination data, historical movement data, historical sleep data and historical psychological consultation data.
The medical prescription recommendation apparatus 400 in the embodiment of the present application may be an electronic device, or may be a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices than a terminal. By way of example, the electronic device may be a mobile phone, tablet, notebook, palmtop, vehicle-mounted electronic device, mobile internet appliance (Mobile Internet Device, MID), augmented Reality (Augmented Reality, AR)/Virtual Reality (VR) device, robot, wearable device, ultra-Mobile Personal Computer, UMPC, netbook or personal digital assistant (Personal Digital Assistant, PDA), etc., but may also be a server, network attached storage (Network Attached Storage, NAS), personal computer (Personal Computer, PC), television (Television, TV), teller machine or self-service machine, etc., and the embodiments of the present application are not limited in particular.
The medical prescription recommendation apparatus 400 in the embodiment of the present application may be an apparatus having an operating system. The operating system may be an Android operating system, an ios operating system, or other possible operating systems, and the embodiment of the present application is not limited specifically.
The medical prescription recommendation apparatus 400 provided in the embodiment of the present application can implement each process implemented in the embodiments of the medical prescription recommendation methods of fig. 1 to 3, and in order to avoid repetition, a detailed description is omitted here.
The embodiment of the present application further provides an electronic device, as shown in fig. 5, where the electronic device 500 includes a processor 501 and a memory 502, and a program or an instruction that can be executed on the processor 501 is stored in the memory 502, and when the program or the instruction is executed by the processor 501, the steps of the embodiment of the medical prescription recommendation method are implemented, and the same technical effects can be achieved, so that repetition is avoided, and no further description is given here.
The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device.
Memory 502 may be used to store software programs as well as various data. The memory 502 may mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area may store an operating system, application programs or instructions (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like. Further, the memory 502 may include volatile memory or nonvolatile memory, or the memory 502 may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM), static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (ddr SDRAM), enhanced SDRAM (Enhanced SDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DRRAM). Memory 502 in embodiments of the application includes, but is not limited to, these and any other suitable types of memory.
The processor 501 may include one or more processing units; optionally, the processor 501 integrates an application processor that primarily processes operations involving an operating system, user interface, application programs, etc., and a modem processor that primarily processes wireless communication signals, such as a baseband processor. It will be appreciated that the modem processor described above may not be integrated into the processor 501.
The embodiment of the application also provides a readable storage medium, and the readable storage medium stores a program or an instruction, which when executed by a processor, implements each process of the medical prescription recommendation method embodiment, and can achieve the same technical effects, so that repetition is avoided, and no further description is provided here.
The embodiment of the application also provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running programs or instructions to realize the processes of the embodiment of the medical prescription recommendation method and achieve the same technical effects, and the repetition is avoided, so that the description is omitted.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
Embodiments of the present application also provide a computer program product stored in a storage medium, where the program product is executed by at least one processor to implement the respective processes of the medical prescription recommendation method embodiment described above, and achieve the same technical effects, and are not repeated herein.
It should be noted that, in this document, 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. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.
Claims (10)
1. A medical prescription recommendation method, comprising:
acquiring real-time inquiry data of a user, and correspondingly searching historical medical data of the user according to user information of the user;
if the historical medical data of the user is found, performing feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors; if the historical medical data of the user is not found, performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
and inputting the medical characteristic vector into a prediction model to predict the medical prescription, so as to obtain a recommended medical prescription, wherein the recommended medical prescription comprises at least one medical commodity.
2. The method according to claim 1, wherein the method further comprises:
acquiring evaluation feedback information of a doctor on the recommended medical prescription;
and if the evaluation feedback information is that the recommended medical prescription prediction is correct, displaying the recommended medical prescription.
3. The method according to claim 2, wherein the method further comprises:
acquiring order feedback information of the recommended medical prescription by a user;
and updating the prediction model according to the order feedback information and the evaluation feedback information.
4. The method according to claim 1, wherein the feature extraction processing is performed on the historical medical data and the real-time inquiry data through a plurality of feature extraction models to obtain a medical feature vector, or the feature extraction processing is performed on the real-time inquiry data through a plurality of feature extraction models to obtain a medical feature vector, specifically comprising:
respectively carrying out feature extraction processing on acquired data through a plurality of different feature extraction models to obtain a plurality of sub-feature vectors, wherein the acquired data comprises the historical medical data and the real-time inquiry data or the acquired data comprises the real-time inquiry data;
and merging the plurality of sub-feature vectors to generate the multi-dimensional medical feature vector.
5. The method according to claim 4, wherein the method further comprises:
acquiring sample data, and respectively training a plurality of different feature extraction models according to the sample data;
and when the model is trained, training the current feature extraction model by using the sample data to obtain a training result, adjusting the weight of the sample data according to the training result, and then using the sample data to extract the model of the next feature.
6. The method according to claim 5, wherein training a plurality of different feature extraction models based on the sample data, respectively, specifically comprises:
splitting the sample data into a plurality of phrases, and respectively training a plurality of different feature extraction models according to the phrases.
7. The method according to any one of claim 1 to 6, wherein,
the historical medical data includes at least one of: historical ordering data, historical consultation data, historical medical prescriptions, historical physical examination data, historical movement data, historical sleep data and historical psychological consultation data.
8. A medical prescription recommendation device, comprising:
the acquisition module is used for acquiring real-time inquiry data of a user and correspondingly searching historical medical data of the user according to user information of the user;
the feature extraction module is used for carrying out feature extraction processing on the historical medical data and the real-time inquiry data through a plurality of feature extraction models if the historical medical data of the user is found out, so as to obtain medical feature vectors; if the historical medical data of the user is not found, performing feature extraction processing on the real-time inquiry data through a plurality of feature extraction models to obtain medical feature vectors;
the prediction module is used for inputting the medical characteristic vector into a prediction model to predict the medical prescription, and obtaining a recommended medical prescription, wherein the recommended medical prescription comprises at least one medical commodity.
9. An electronic device comprising a processor and a memory storing a program or instructions that, when executed by the processor, implement the steps of the medical prescription recommendation method of any one of claims 1 to 7.
10. A readable storage medium having stored thereon a program or instructions which when executed by a processor, implement the steps of the medical prescription recommendation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310815764.5A CN116881554A (en) | 2023-07-04 | 2023-07-04 | Medical prescription recommendation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310815764.5A CN116881554A (en) | 2023-07-04 | 2023-07-04 | Medical prescription recommendation method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116881554A true CN116881554A (en) | 2023-10-13 |
Family
ID=88259614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310815764.5A Pending CN116881554A (en) | 2023-07-04 | 2023-07-04 | Medical prescription recommendation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116881554A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117854713A (en) * | 2024-03-06 | 2024-04-09 | 之江实验室 | Method for training traditional Chinese medicine syndrome waiting diagnosis model and method for recommending information |
-
2023
- 2023-07-04 CN CN202310815764.5A patent/CN116881554A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117854713A (en) * | 2024-03-06 | 2024-04-09 | 之江实验室 | Method for training traditional Chinese medicine syndrome waiting diagnosis model and method for recommending information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111784455B (en) | Article recommendation method and recommendation equipment | |
| US10497013B2 (en) | Purchasing behavior analysis apparatus and non-transitory computer readable medium | |
| Kauffman et al. | Combining machine-based and econometrics methods for policy analytics insights | |
| US10453099B2 (en) | Behavior prediction on social media using neural networks | |
| US11172040B2 (en) | Method and apparatus for pushing information | |
| US20180011977A1 (en) | Data analysis system, data analysis method, and data analysis program | |
| CN112035611B (en) | Target user recommendation method, device, computer equipment and storage medium | |
| Boeschoten et al. | A framework for privacy preserving digital trace data collection through data donation | |
| CN111400613A (en) | Article recommendation method, device, medium and computer equipment | |
| CN111967914A (en) | User portrait based recommendation method and device, computer equipment and storage medium | |
| CN116881554A (en) | Medical prescription recommendation method and device, electronic equipment and readable storage medium | |
| CN114399396A (en) | Insurance product recommendation method and device, computer equipment and storage medium | |
| CN108280081B (en) | Method and device for generating webpage | |
| US10950222B2 (en) | Multimodal video system for generating a personality assessment of a user | |
| US20140372207A1 (en) | Profit index value generation system and profit index value generation method | |
| WO2024067779A1 (en) | Data processing method and related apparatus | |
| CN117557331A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN117057855A (en) | Data processing method and related device | |
| Cheung et al. | Correlation-based meta-analytic structural equation modeling: Effects of parameter covariance on point and interval estimates | |
| Lee et al. | A Meta-Analysis of Social Ecological Correlates of Physical Activity Among Koreans | |
| CN115579153A (en) | Inquiry evaluation method, inquiry evaluation device, electronic device, and readable storage medium | |
| Durán-Vaca et al. | Sentiment analysis on twitter to measure the perception of taxation in Colombia | |
| Gogołek | Refining Big Data | |
| CN113919896A (en) | Recommendation method, terminal and storage medium | |
| JP7044821B2 (en) | Information processing system and information processing method |
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 |