CN113903423A

CN113903423A - Medication scheme recommendation method, device, equipment and medium

Info

Publication number: CN113903423A
Application number: CN202111370753.8A
Authority: CN
Inventors: 刘保卫; 周英明
Original assignee: North Health Medical Big Data Technology Co ltd
Current assignee: North Health Medical Big Data Technology Co ltd
Priority date: 2021-11-18
Filing date: 2021-11-18
Publication date: 2022-01-07

Abstract

The embodiment of the invention discloses a medication scheme recommendation method, a medication scheme recommendation device, medication scheme recommendation equipment and a medication scheme recommendation medium. According to the method, the target class corresponding to the target user is determined in each medication user class obtained through pre-clustering according to the obtained user basic data, symptom description data and user inspection data of the target user, so that a medication scheme knowledge base corresponding to the target class is obtained, a medication scheme recommendation list corresponding to the target user is generated according to the medication scheme knowledge base, automatic generation of the medication scheme recommendation list of the user is achieved, the medication scheme of the user is obtained through the clustering analysis result of the existing data, and accuracy of medicine recommendation is improved.

Description

Medication scheme recommendation method, device, equipment and medium

Technical Field

The embodiment of the invention relates to the technical field of big data, in particular to a medication scheme recommendation method, a device, equipment and a medium.

Background

With the rapid accumulation of electronic record data of hospitals and the development of big data technology, a foundation is laid for the mining application of the electronic record data. Currently, most of the medication recommendation mainly uses the interaction records of the patient and the medicine, and the recommendation is based on the collaborative filtering technology, however, due to the particularity of the medicine recommendation, the medicine recommendation is not accurate only by the dictated symptoms of the patient and the evaluation of the medicine by the patient.

Disclosure of Invention

The embodiment of the invention provides a medication scheme recommendation method, a medication scheme recommendation device, medication scheme recommendation equipment and a medication scheme recommendation medium, so as to improve the accuracy of medicine recommendation.

In a first aspect, an embodiment of the present invention provides a medication scheme recommendation method, where the method includes:

acquiring user basic data, symptom description data and user check data of a target user;

determining a target class corresponding to the target user in each medication user class obtained by pre-clustering based on the user basic data, the symptom description data and the user check data;

and acquiring a medication scheme knowledge base corresponding to the target class, and generating a medication scheme recommendation list corresponding to the target user based on the medication scheme knowledge base.

Optionally, the method further includes:

acquiring historical basic data, historical symptom data, historical inspection data and historical medication scheme data of each historical user;

clustering each historical user based on the historical basic data, the historical symptom data and the historical inspection data to determine each medication user class;

and aiming at each medication user class, determining a medication scheme knowledge base corresponding to the medication user class based on historical medication scheme data of historical users contained in the medication user class.

Optionally, the determining a knowledge base of medication schemes corresponding to the medication user class based on the historical medication scheme data of the historical user included in the medication user class includes:

converging historical medication scheme data of historical users contained in the medication user class, and determining knowledge base standby data corresponding to the medication user class based on a convergence processing result;

and determining an invalid medication scheme which does not meet the requirement of preset medication rationality in the knowledge base standby data, and determining a medication scheme knowledge base corresponding to the medication user class based on the knowledge base standby data and the invalid medication scheme.

Optionally, the standby data of the knowledge base includes symptom descriptions, drug names, drug administration methods, unit prices of drugs, drug quantities, total price of the scheme, total treatment periods of the scheme, therapeutic index of the scheme, and ratios of the scheme corresponding to each historical administration scheme.

Optionally, the determining an invalid medication regimen in the knowledge base backup data that does not meet the preset medication rationality requirement includes at least one of:

determining the historical medication scheme with the total duration of the treatment course exceeding a set duration threshold in the knowledge base standby data as a non-effective medication scheme;

determining the historical medication scheme in the knowledge base standby data, wherein the medication method does not meet the requirements of the medicine use instruction, as a non-effective medication scheme;

determining the historical medication scheme of which the symptom description does not meet the requirement of the medicine use instruction in the standby data of the knowledge base as a non-effective medication scheme;

and determining the medicine name in the standby data of the knowledge base to be in accordance with the historical medication scheme of the preset invalid medicine name to be a non-effective medication scheme.

Optionally, the method further includes:

determining a regimen efficacy index for the historical regimen based on a total regimen price and a total regimen treatment course for the historical regimen;

and determining the solution ratio of the historical medication scheme based on the solution use number of the historical medication scheme and the total number of disease solutions corresponding to the historical medication scheme.

Optionally, the generating a medication scheme recommendation list corresponding to the target user based on the medication scheme knowledge base includes:

and generating a medication scheme recommendation list corresponding to the target user based on at least one of a scheme total price, a scheme total treatment period, a scheme curative effect index and a scheme proportion of each medication scheme to be recommended in the medication scheme knowledge base.

In a second aspect, an embodiment of the present invention further provides a medication scheme recommendation apparatus, where the apparatus includes:

the data acquisition module is used for acquiring user basic data, symptom description data and user check data of a target user;

the target class determining module is used for determining a target class corresponding to the target user in each medication user class obtained by pre-clustering based on the user basic data, the symptom description data and the user checking data;

and the list generation module is used for acquiring the medication scheme knowledge base corresponding to the target class and generating a medication scheme recommendation list corresponding to the target user based on the medication scheme knowledge base.

In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement a medication recommendation method as provided in any embodiment of the invention.

In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the medication recommendation method according to any embodiment of the present invention.

The embodiment of the invention has the following advantages or beneficial effects:

the method comprises the steps of determining a target class corresponding to a target user in each medication user class obtained through pre-clustering according to obtained user basic data, symptom description data and user inspection data of the target user, further obtaining a medication scheme knowledge base corresponding to the target class, and generating a medication scheme recommendation list corresponding to the target user according to the medication scheme knowledge base, so that automatic generation of the medication scheme recommendation list of the user is achieved.

Drawings

In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, a brief description is given below of the drawings used in describing the embodiments. It should be clear that the described figures are only views of some of the embodiments of the invention to be described, not all, and that for a person skilled in the art, other figures can be derived from these figures without inventive effort.

Fig. 1 is a schematic flow chart of a medication scheme recommendation method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of a medication scheme recommendation method according to a second embodiment of the present invention;

fig. 3 is a schematic flow chart of a medication scheme recommendation method according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of a medication scheme recommendation device according to a fourth embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a schematic flow chart of a medication scheme recommendation method according to an embodiment of the present invention, which is applicable to a case where a medication scheme recommendation list is automatically generated for a user according to user basic data, symptom description data, and user inspection data of the user, and is particularly applicable to a case where a category to which the user belongs is determined according to a clustering result of medical big data, and further a medication scheme recommendation list is determined according to a medication scheme knowledge base corresponding to the category to which the user belongs, where the method may be executed by a medication scheme recommendation apparatus, and the apparatus may be implemented by hardware and/or software, and the method specifically includes the following steps:

s110, acquiring user basic data, symptom description data and user check data of the target user.

The target user may be a user to whom a medication is to be recommended. The user basic data may be basic information previously entered by the user, such as name, sex, age, presence or absence of allergy history, whether it is a pregnant woman, and the like. The symptom description data can be related data describing symptoms of the user, and the symptom description data can comprise description information of the user on the symptoms and can also comprise diagnosis conclusions of the doctor on the symptoms. The user check data may be result information of the item check performed by the user.

Specifically, the user basic data, symptom description data and user examination data of the target user can be obtained from the medical institution diagnosis and treatment database. For example, when it is detected that a medical staff or a target user triggers generation of a medication scheme control on a terminal device, user basic data, symptom description data and user examination data of the target user can be obtained from a medical institution diagnosis and treatment database; the terminal device can be a mobile phone, a computer, a tablet or a hospital inquiry robot.

And S120, determining a target class corresponding to the target user in each medication user class obtained by pre-clustering based on the user basic data, the symptom description data and the user check data.

In this embodiment, a diagnosis and treatment database of a plurality of medical institutions may be obtained in advance, where the diagnosis and treatment database includes user basic data of each historical user, symptom description data of each historical user, user examination data of each historical user, and historical medication scheme data of each historical user; further, clustering processing is carried out on the user basic data of each historical user, the symptom description data of each historical user and the user check data of each historical user, so that all historical users in the diagnosis and treatment database are clustered, and each medication user class is obtained.

For example, historical users with similar symptom description data, similar ages in the same stage (e.g., 30-40 years), and similar user examination data may be classified in the same medication user class; or, the historical users with consistent symptom description data, the same characteristics (such as pregnant women) of the users and the consistent items of the user examination can be divided into the same medication user class; alternatively, the historical users whose symptom description data are consistent, whose users have the same allergy history, and whose user examination data are consistent may be classified into the same medication user class, and the like.

After the medication user classes are obtained through clustering, a medication scheme knowledge base corresponding to the medication user classes can be constructed based on historical medication scheme data of historical users contained in the medication user classes. Based on the mode, a medication scheme knowledge base corresponding to each medication user class can be constructed.

Specifically, in this embodiment, the target class corresponding to the target user can be determined in each medication user class obtained by pre-clustering according to the user basic data, symptom description data and user check data of the target user currently having the requirement of recommending the medication scheme. For example, a feature vector of the target user can be obtained according to user basic data, symptom description data and user check data of the target user, the distance between the feature vector and the clustering center of each medication user class is calculated, and the medication user class corresponding to the clustering center with the shortest distance is determined as the target class; or calculating the similarity between the feature vector and the clustering centers of the medication user classes, and determining the medication user class corresponding to the clustering center with the highest similarity as the target class.

S130, acquiring a medication scheme knowledge base corresponding to the target class, and generating a medication scheme recommendation list corresponding to the target user based on the medication scheme knowledge base.

Specifically, after the medication scheme knowledge base corresponding to the target class is obtained, a medication scheme recommendation list corresponding to the target user can be generated according to historical medication scheme data in the medication scheme knowledge base. Optionally, after the medication scheme recommendation list is generated, the medication scheme recommendation method may be displayed on a display interface of the terminal device.

Illustratively, all historical medication scheme data can be acquired from a medication scheme knowledge base, and all historical medication scheme data matched with the disease name are sorted according to the recommended priority and the disease name to generate a medication scheme recommendation list; or, all historical medication scheme data matched with the disease name can be sorted according to the recommendation priority, and the medication scheme recommendation list is generated by taking N historical medication scheme data which are ranked first. Wherein the recommended priority can be at least one of a total price of the plan, a total treatment period of the plan, a curative effect index of the plan and a proportion of the plan. The disease name corresponding to the target user can be automatically determined according to the symptom description data and/or the user examination data, and can be manually input by a doctor or a user.

For example, the generating of the medication recommendation list corresponding to the target user based on the medication knowledge base may be: and generating a medication scheme recommendation list corresponding to the target user based on at least one of a scheme total price, a scheme total treatment period, a scheme curative effect index and a scheme proportion of each medication scheme to be recommended in the medication scheme knowledge base.

The medication scheme to be recommended may be a medication scheme corresponding to the disease name of the target user in the medication scheme knowledge base. The total price of the scheme can be the price of all medicines contained in the medication scheme under the total treatment period; the total treatment effect index of the scheme can be the ratio of the total price of the scheme to the total treatment course of the scheme; the ratio of the medication may be a ratio of the number of the medication to be recommended to all the medications corresponding to the disease names of the medication to be recommended. Illustratively, if there are 300 patients in the medication regimen knowledge base for which there is historical medication regimen data for a regimen, then the number of a regimens is 300. Specifically, the total price of the medication schemes to be recommended, the total treatment period of the medication schemes, the curative effect index of the medication schemes, the proportion of the medication schemes, or any combination of the above indexes can be used as the recommendation priority, the medication schemes to be recommended are sorted, and the medication scheme recommendation list corresponding to the target user is obtained based on the sorting result. By the mode, the ordered medication scheme recommendation lists with different dimensions can be generated and provided for doctors or patients according to the attributes concerned by the doctors or patients, such as the total price of the scheme, the total treatment period of the scheme, the curative effect index of the scheme, the ratio of the scheme and the like, so that the doctors or patients can quickly determine the medication scheme meeting the actual requirement according to the medication scheme recommendation lists with different dimensions.

According to the technical scheme of the embodiment, the target class corresponding to the target user is determined in each medication user class obtained through pre-clustering according to the obtained user basic data, symptom description data and user inspection data of the target user, so that the medication scheme knowledge base corresponding to the target class is obtained, the medication scheme recommendation list corresponding to the target user is generated according to the medication scheme knowledge base, the medication scheme recommendation list of the user is automatically generated, the medication scheme of the user is obtained by the method through the clustering analysis result of the existing data, and the accuracy of medicine recommendation is improved.

Example two

Fig. 2 is a schematic flow chart of a medication scheme recommendation method provided in the second embodiment of the present invention, where on the basis of the foregoing embodiment, optionally, the method further includes: acquiring historical basic data, historical symptom data, historical inspection data and historical medication scheme data of each historical user; clustering each historical user based on the historical basic data, the historical symptom data and the historical inspection data to determine each medication user class; and aiming at each medication user class, determining a medication scheme knowledge base corresponding to the medication user class based on historical medication scheme data of historical users contained in the medication user class. Wherein explanations of the same or corresponding terms as those of the above embodiments are omitted. Referring to fig. 2, the medication recommendation method provided in this embodiment includes the following steps:

s210, acquiring historical basic data, historical symptom data, historical examination data and historical medication data of each historical user.

The historical basic data can be user basic data of a historical user, the historical symptom data can be symptom description data of the historical user, the historical check data can be user check data of the historical user, and the historical medication data can be actual medication information of the historical user. Specifically, complete diagnosis and treatment data of each historical user from admission to discharge can be acquired from a diagnosis and treatment database of a medical institution, and the complete diagnosis and treatment data comprises historical basic data, historical symptom data, historical examination data and historical medication scheme data.

Of course, in consideration of the fact that in an actual situation, the number of patients is large, and the same patient is diagnosed and treated in a plurality of medical institutions respectively, it is difficult to obtain a comprehensive and effective recommendation result based on data acquired by a single hospital or a single type of disease, and therefore, the present embodiment can extract historical basic data, historical symptom data, historical examination data, and historical medication plan data of all historical users from diagnosis and treatment databases of a plurality of medical institutions, so as to further improve the accuracy of the recommendation result.

S220, clustering is carried out on each historical user based on the historical basic data, the historical symptom data and the historical inspection data, and each medication user class is determined.

Specifically, the present embodiment may perform clustering processing on all historical basic data, historical symptom data, and historical inspection data to obtain clustering results of all historical users. The characteristic variables and the clustering category number required by clustering can be set according to actual requirements, if the clustering effect does not meet the requirements, the characteristic variables and the clustering category number can be adjusted, and clustering processing is carried out on historical basic data, historical symptom data and historical inspection data again.

In this embodiment, the purpose of performing cluster analysis using the history basic data, the history symptom data, and the history inspection data is to: the method can determine users with similar user characteristics, similar symptom descriptions and similar examination information as the same class, and can divide more detailed medication user classes under the background of large data with huge patient amount, so that the users can be accurately classified, and further, the accuracy of the recommendation result is improved by establishing a corresponding medication scheme knowledge base for each medication user class.

For example, historical users with similar historical symptom data, similar ages in the same stage (e.g., 0-3 years), and similar user check data can be classified into the same medication user class; or historical users with similar symptom description data, users with the same characteristics (such as pregnant women) and similar historical examination data are divided into the same medication user class; alternatively, historical users having similar historical symptom data, users having the same allergy history, and user examination data may be classified into the same medication user group.

Optionally, before performing clustering processing on each historical user based on the historical basic data, the historical symptom data, and the historical inspection data, the method may further include: performing data deduplication processing, data completion processing and data standardization processing on the historical basic data, the historical symptom data and the historical inspection data; the history basic data, the history symptom data, and the history examination data are updated based on each processing result.

The data deduplication may be that when at least two pieces of data of the historical user are acquired, if the two pieces of data are completely repeated, one piece of data is removed. The data complementing processing may be performed when at least two pieces of data of the historical user are acquired, and if the two pieces of data are not completely repeated and blank data exists in the two pieces of data, the other piece of data may be complemented based on one piece of data. For example, the a1 data is derived from a first medical institution diagnosis database, the a2 data is derived from a second medical institution diagnosis database, the identity card information is absent from the historical basic data of the a1 data, and the identity card information is included in the a2 data, so that the identity card information of the a1 data can be supplemented based on the identity card information in the a2 data.

The data normalization processing may be to convert the history basic data, the history symptom data, and the history examination data into the history basic data, the history symptom data, and the history examination data that meet the uniform description requirement before vectorizing the history basic data, the history symptom data, and the history examination data. Specifically, in consideration of the fact that the data sources of the historical users may be different, descriptors used by the medical institutions for symptoms and descriptors for examination items may be different, and thus, the data may be converted into unified descriptors. Specifically, the words to be detected in the historical basic data, the historical symptom data and the historical inspection data can be extracted, and if the words to be detected are the preset words to be converted, the preset standard words are adopted to replace the words to be detected.

And S230, aiming at each medication user class, determining a medication scheme knowledge base corresponding to the medication user class based on historical medication scheme data of historical users contained in the medication user class.

Specifically, for each medication user class, a medication scheme knowledge base corresponding to the medication user class can be formed according to the historical medication scheme data of the historical user included in the medication user class.

In an optional implementation manner, the determining, based on the historical medication data of the historical user included in the medication user class, a knowledge base of medication schemes corresponding to the medication user class includes: converging historical medication scheme data of historical users contained in the medication user class, and determining knowledge base standby data corresponding to the medication user class based on a convergence processing result; and determining an invalid medication scheme which does not meet the requirement of preset medication rationality in the knowledge base standby data, and determining a medication scheme knowledge base corresponding to the medication user class based on the knowledge base standby data and the invalid medication scheme.

The standby data of the knowledge base can comprise symptom descriptions (or disease names), medicine names, medicine administration methods, unit prices of medicines, medicine quantities, total price of the schemes, total treatment periods of the schemes, curative effect indexes of the schemes and proportion of the schemes corresponding to all historical medication schemes. The disease name is input into the standby data of the knowledge base, and a medication scheme list corresponding to the disease name can be formed. The method of administration may include the frequency of administration as well as the dosage amount administered. The therapeutic index of the scheme can refer to the evaluation index of the administration scheme, and can be set according to specific requirements, for example, the ratio of the total price of the scheme to the treatment course can be used as the therapeutic index. The term "regimen ratio" refers to the ratio of the number of regimens to the total number of regimens for the disease name.

Specifically, the therapeutic effect index of the regimen can be calculated according to the total price of the regimen and the total treatment course of the regimen, and the regimen proportion can be calculated according to the regimen usage number of the historical medication regimens and the usage number of all medication regimens contained in the diseases corresponding to the historical medication regimens. Namely, the method further comprises: determining a regimen efficacy index for the historical regimen based on a total regimen price and a total regimen treatment course for the historical regimen; and determining the solution ratio of the historical medication scheme based on the solution use number of the historical medication scheme and the total number of disease solutions corresponding to the historical medication scheme. For example, the number of used medication regimens for the historical medication regimen is 1000, the name of the disease corresponding to the historical medication regimen is fever, the total number of the disease regimens corresponding to the historical medication regimen, i.e., the total number of the medication regimens corresponding to the fever is 3000, and the regimen proportion of the historical medication regimen is 1/3.

In the optional implementation manner, historical medication scheme data of all historical users belonging to the medication user class can be aggregated to form knowledge base standby data corresponding to the medication user class; further, an invalid medication scheme which does not meet the requirement of the preset medication rationality is screened from the knowledge base standby data, the invalid medication scheme is removed from the knowledge base standby data to form a medication scheme knowledge base, or the medication scheme knowledge base is constructed according to other medication schemes except the invalid medication scheme in the knowledge base standby data. Of course, an unreasonable medication scheme library can be constructed according to each invalid medication scheme; and if the invalid medication scheme does not exist, directly forming a medication scheme knowledge base based on the standby data of the knowledge base.

Illustratively, the determining an invalid medication regimen in the knowledge base backup data that does not meet the preset medication rationality requirement includes at least one of: determining the historical medication scheme with the total duration of the treatment course exceeding a set duration threshold in the knowledge base standby data as a non-effective medication scheme; determining the historical medication scheme in the knowledge base standby data, wherein the medication method does not meet the requirements of the medicine use instruction, as a non-effective medication scheme; determining the historical medication scheme of which the symptom description does not meet the requirement of the medicine use instruction in the standby data of the knowledge base as a non-effective medication scheme; and determining the medicine name in the standby data of the knowledge base to be in accordance with the historical medication scheme of the preset invalid medicine name to be a non-effective medication scheme. The preset invalid drug name can be a drug name with improper combination or violating medication contraindication.

That is, a historical medication regimen for which the total duration of the treatment period is too long may be determined as an ineffective medication regimen, or a historical medication regimen for which the administration method does not meet the administration requirements specified in the specification may be determined as an ineffective medication regimen, or a historical medication regimen for which the symptom description (e.g., disease name) does not meet the indication requirements specified in the specification may be determined as an ineffective medication regimen, or a historical medication regimen for which the combination is inappropriate or violates medication contraindications may be determined as an ineffective medication regimen. Of course, a reasonable medication working group can be formed according to authoritative experts, and joint judgment can be performed on each historical medication scheme in the standby data of the knowledge base.

By the method, whether the unreasonable medication situation exists in the standby data of the knowledge base can be judged, if so, unreasonable historical medication schemes are screened out, and the medication scheme knowledge base is formed on the basis of the historical medication scheme data with reasonable medication, so that unreasonable scheme screening before the medication scheme is recommended for the user is realized, and the accuracy of the medication scheme recommended for the user is further improved.

S240, acquiring user basic data, symptom description data and user check data of a target user, and determining a target class corresponding to the target user in each medication user class based on the user basic data, the symptom description data and the user check data.

S250, acquiring a medication scheme knowledge base corresponding to the target class, and generating a medication scheme recommendation list corresponding to the target user based on the medication scheme knowledge base.

According to the technical scheme of the embodiment, the historical basic data, the historical symptom data, the historical inspection data and the historical medication scheme data of each historical user are obtained, the medication user classes are obtained through clustering according to the historical basic data, the historical symptom data and the historical inspection data, the medication scheme knowledge base corresponding to the medication user classes is established based on the historical medication scheme data of the historical users contained in the medication user classes, so that when the user basic data, the symptom description data and the user inspection data of the target user are obtained, the target class corresponding to the target user can be determined in each user medication class, the medication scheme recommendation list is formed according to the medication scheme knowledge base corresponding to the target class, the method achieves accurate determination of the medication user classes, and accuracy of user classification is improved under a big data scene, and further the accuracy of the recommendation result is improved.

EXAMPLE III

Fig. 3 is a schematic flow chart of a medication scheme recommendation method according to a third embodiment of the present invention, where this embodiment is applicable to a case where a medication scheme recommendation list is automatically generated for a user according to user basic data, symptom description data, and user inspection data of the user, and is particularly applicable to a case where a category to which the user belongs is determined according to a clustering result of medical big data, and further a medication scheme recommendation list is determined according to a medication scheme knowledge base corresponding to the category to which the user belongs, where the method may be executed by a medication scheme recommendation apparatus, and the apparatus may be implemented by hardware and/or software, and the method specifically includes the following steps:

and S301, carrying out data aggregation processing on the diagnosis and treatment databases of the medical institutions.

Specifically, the diagnosis and treatment database of each medical institution includes complete diagnosis and treatment data of patients from admission to discharge, including historical basic data, historical symptom data, historical examination data, historical medication data, and the like.

S302, data preprocessing is carried out on the gathered data.

The preprocessing comprises data de-duplication processing, data filling processing and data standardization processing.

And S303, performing cluster analysis on each historical user to obtain each medicine user class.

Specifically, the historical basic data, the historical symptom data and the historical inspection data of each historical user can be clustered to obtain a clustering result, namely, each medication user class.

S304, judging whether each medicine user class meets the clustering requirement, if so, executing S305, otherwise, adjusting the clustering characteristic variable and the class number and returning to execute S303.

The clustering requirement may be that the class interval between the medication user classes is greater than a preset first threshold, and/or the interval of the user data in each medication user class is less than a preset second threshold. That is, the clustering requirement may be that samples within a cluster are as close as possible to each other, and/or that samples between clusters are as far as possible.

S305, for each medication user class, obtaining knowledge base standby data corresponding to the medication user class according to historical medication scheme data of historical users contained in the medication user class.

Specifically, the historical medication scheme data of the historical users of each medication user class can be gathered and statistically analyzed to obtain the standby data of the knowledge base. In the standby data of the knowledge base, a medication scheme list can be obtained by inputting disease names, and each treatment scheme comprises data such as disease names, medicine dosages, medication frequency, unit prices and quantities of medicines, total scheme prices, treatment courses, curative effect indexes, scheme ratios and the like. The therapeutic index refers to the evaluation index of the therapeutic scheme, and can be set according to specific requirements, for example, the ratio of the total price of the scheme to the treatment course can be used as the therapeutic index. The proportion of the number of the schemes to the total number of the schemes in the disease is referred to as the scheme proportion.

S306, judging whether an invalid medication scheme exists in the standby data of the knowledge base, and if so, executing S307; if not, go to S308.

And S307, generating an unreasonable medication knowledge base based on the invalid medication scheme.

And S308, generating a medication scheme knowledge base corresponding to the medication user class.

Specifically, if the invalid medication scheme does not exist in the knowledge base standby data, the medication scheme knowledge base can be directly constructed according to the knowledge base standby data; and if the invalid medication scheme exists in the knowledge base standby data, constructing a medication scheme knowledge base according to other historical medication scheme data except the unreasonable medication knowledge base in the knowledge base standby data.

S309, judging whether a medicine scheme recommendation requirement exists, if so, executing S310, and if not, executing S312.

And S310, matching the target class corresponding to the target user.

Specifically, user basic data, symptom description data, and user check data of a target user may be obtained, and a target class corresponding to the target user is determined in each medication user class based on the user basic data, the symptom description data, and the user check data.

S311, generating a medication scheme recommendation list according to the medication scheme knowledge base corresponding to the target class, the disease name corresponding to the target user and the sequencing condition.

The disease name may be determined by the symptom description data and the user examination data, or may be manually entered or selected by a doctor or a user. The sorting condition can be the total price of the scheme, the total treatment period of the scheme, the curative effect index, the ratio of the scheme and the like.

And S312, ending.

The medication scheme recommendation method provided by the embodiment realizes automatic generation of the medication scheme recommendation list of the user, obtains the medication scheme of the user by using the clustering analysis result of the existing data, and improves the accuracy of medicine recommendation.

Example four

Fig. 4 is a schematic structural diagram of a medication scheme recommendation apparatus according to a fourth embodiment of the present invention, where this embodiment is applicable to a case where a medication scheme recommendation list is automatically generated for a user according to user basic data, symptom description data, and user inspection data of the user, and is particularly applicable to a case where a category to which the user belongs is determined according to a clustering result of medical big data, and further a medication scheme recommendation list is determined according to a medication scheme knowledge base corresponding to the category to which the user belongs, where the apparatus specifically includes: a data acquisition module 410, a target class determination module 420, and a list generation module 430.

A data obtaining module 410, configured to obtain user basic data, symptom description data, and user check data of a target user;

a target class determination module 420, configured to determine, based on the user basic data, the symptom description data, and the user check data, a target class corresponding to the target user among the medication user classes obtained through pre-clustering;

the list generating module 430 is configured to obtain a medication scheme knowledge base corresponding to the target class, and generate a medication scheme recommendation list corresponding to the target user based on the medication scheme knowledge base.

Optionally, the apparatus further includes a historical information reading module, a clustering module, and a knowledge base constructing module, wherein;

the historical information reading module is used for acquiring historical basic data, historical symptom data, historical inspection data and historical medication scheme data of each historical user;

the clustering module is used for clustering each historical user based on the historical basic data, the historical symptom data and the historical inspection data to determine each medication user class;

and the knowledge base construction module is used for determining a medication scheme knowledge base corresponding to the medication user class according to the medication user class and based on historical medication scheme data of historical users contained in the medication user class.

Optionally, the knowledge base constructing module is specifically configured to:

converging historical medication scheme data of historical users contained in the medication user class, and determining knowledge base standby data corresponding to the medication user class based on a convergence processing result; and determining an invalid medication scheme which does not meet the requirement of preset medication rationality in the knowledge base standby data, and determining a medication scheme knowledge base corresponding to the medication user class based on the knowledge base standby data and the invalid medication scheme.

Optionally, the knowledge base building module includes an invalid scheme determining unit, and the invalid scheme determining unit is configured to determine, in the knowledge base backup data, an invalid medication scheme that does not meet a preset medication rationality requirement based on at least one of the following methods:

Optionally, the knowledge base building module further includes a therapeutic effect ratio calculation unit, where the therapeutic effect ratio calculation unit is configured to determine a scheme therapeutic effect index of the historical medication scheme based on a total scheme price and a total scheme treatment period of the historical medication scheme; and determining the solution ratio of the historical medication scheme based on the solution use number of the historical medication scheme and the total number of disease solutions corresponding to the historical medication scheme.

Optionally, the list generating module 430 is specifically configured to:

In this embodiment, the data acquisition module is used to acquire user basic data, symptom description data and user check data of a target user, the target class determination module is used to determine a target class corresponding to the target user among various medication user classes obtained through pre-clustering, the list generation module is used to acquire a medication scheme knowledge base corresponding to the target class, and a medication scheme recommendation list corresponding to the target user is generated according to the medication scheme knowledge base, so that automatic generation of the medication scheme recommendation list of the user is realized.

The medication scheme recommending device provided by the embodiment of the invention can execute the medication scheme recommending method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.

It should be noted that, the units and modules included in the system are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the embodiment of the invention.

EXAMPLE five

Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 5 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention. The device 12 is typically an electronic device that undertakes medication recommendation list generation functionality.

As shown in FIG. 5, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a memory 28, and a bus 18 that couples the various components (including the memory 28 and the processing unit 16).

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

Electronic device 12 typically includes a variety of computer-readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer device readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer storage media. By way of example only, the storage device 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk-Read Only Memory (CD-ROM), a Digital Video disk (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product 40, with program product 40 having a set of program modules 42 configured to carry out the functions of embodiments of the invention. Program product 40 may be stored, for example, in memory 28, and such program modules 42 include, but are not limited to, one or more application programs, other program modules, and program data, each of which examples or some combination may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.

Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, mouse, camera, etc., and display), one or more devices that enable a user to interact with electronic device 12, and/or any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), Wide Area Network (WAN), and/or a public Network such as the internet) via the Network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, Redundant processing units, external disk drive Arrays, disk array (RAID) devices, tape drives, and data backup storage devices, to name a few.

The processor 16 executes various functional applications and data processing by executing programs stored in the memory 28, for example, to implement the medication scheme recommendation method provided by the above embodiment of the present invention, including:

Of course, those skilled in the art will appreciate that the processor may also implement the medication recommendation method provided in any of the embodiments of the present invention.

EXAMPLE six

A sixth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the medication recommendation method provided in any embodiment of the present invention, where the method includes:

Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A medication recommendation method, comprising:

2. The method of claim 1, further comprising:

3. The method of claim 2, wherein determining the knowledge base of medication intake schemes corresponding to the medication intake user class based on historical medication intake scheme data of historical users included in the medication intake user class comprises:

4. The method of claim 3, wherein the knowledge base backup data comprises a symptom description, a drug name, a drug administration method, a drug unit price, a drug quantity, a total plan price, a total plan treatment period, a plan efficacy index, and a plan proportion for each historical medication plan.

5. The method of claim 4, wherein determining in the knowledge-base backup data an invalid medication regimen that does not meet a preset medication rationality requirement comprises at least one of:

6. The method of claim 4, further comprising:

7. The method of claim 1, wherein the generating a medication recommendation list corresponding to the target user based on the medication knowledge base comprises:

8. A medication regime recommendation apparatus, the apparatus comprising:

9. An electronic device, characterized in that the electronic device comprises:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the medication recommendation method of any of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a medication recommendation method according to any one of claims 1-7.