CN114595380B

CN114595380B - Medicine recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN114595380B
Application number: CN202210135011.5A
Authority: CN
Inventors: 姚良勇; 刘山山; 赵欣园; 石景龙; 李洪光
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2022-02-14
Filing date: 2022-02-14
Publication date: 2024-03-26
Anticipated expiration: 2042-02-14
Also published as: CN114595380A

Abstract

The embodiment of the disclosure provides a medicine recommendation method, a medicine recommendation device, electronic equipment and a storage medium. The medicine recommending method comprises the following steps: acquiring target information input by a user and associated with a target prescription drug; determining a target non-prescription drug capable of replacing the target prescription drug based on the target information; recommending the target over-the-counter drug. According to the method and the device for recommending the non-prescription drugs, the non-prescription drugs which can replace the prescription drugs can be automatically recommended based on the inquiry information of the drug users, the processing process is simpler and more convenient, and the user experience can be improved.

Description

Medicine recommendation method and device, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of internet, and in particular relates to a medicine recommending method, a medicine recommending device, electronic equipment and a storage medium.

Background

In order to meet the medicine purchasing demands of users, various online medicine purchasing software is generated, the users can purchase medicines through the online medicine purchasing software, and the online medicine purchasing software provides great convenience for the users.

When online purchasing software is used to purchase prescription drugs for users, there is a need to know non-prescription drugs that can replace the prescription drugs in some situations, so how to recommend non-prescription drugs to users is a technical problem that needs to be solved at present.

Disclosure of Invention

In view of the above, embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a storage medium for recommending a drug, which are capable of automatically recommending a target non-prescription drug that can replace the target prescription drug.

According to a first aspect of embodiments of the present disclosure, there is provided a medicine recommendation method, including:

acquiring target information input by a user and associated with a target prescription drug;

determining a target non-prescription drug capable of replacing the target prescription drug based on the target information;

recommending the target over-the-counter drug.

Optionally, the acquiring the target information associated with the target prescription drug input by the user includes: and in response to receiving the search request of the target prescription medicine, acquiring the identification of the target prescription medicine input by a user, and determining the identification of the target prescription medicine as the target information.

Optionally, the determining a target over-the-counter drug capable of replacing the target prescription drug based on the target information includes: acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises a prescription medicine identifier and an over-the-counter medicine identifier corresponding to the prescription medicine identifier; inquiring the non-prescription medicine identification corresponding to the identification of the target prescription medicine from the medicine knowledge base, and determining the non-prescription medicine corresponding to the inquired non-prescription medicine identification as the target non-prescription medicine.

Optionally, the acquiring the target information associated with the target prescription drug input by the user includes: and in response to determining that the target prescription medicine selected for the medicine administration user is interrupted to be purchased, acquiring inquiry information of the medicine administration user input by the user, and determining the inquiry information of the medicine administration user as the target information.

Optionally, the determining a target over-the-counter drug capable of replacing the target prescription drug based on the target information includes: acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises medicine efficacy and non-prescription medicine identifications corresponding to the medicine efficacy; extracting the disease information of the drug administration user from the inquiry information of the drug administration user, inquiring the first target drug efficacy matched with the disease information from the drug knowledge base, acquiring the non-prescription drug identification corresponding to the first target drug efficacy, and determining the non-prescription drug corresponding to the acquired non-prescription drug identification as the target non-prescription drug.

Optionally, the determining a target over-the-counter drug capable of replacing the target prescription drug based on the target information includes: acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises medicine efficacy, a prescription medicine identifier corresponding to the medicine efficacy and an over-the-counter medicine identifier corresponding to the medicine efficacy; extracting the disease information of the drug user and the identification of the target prescription drug from the inquiry information of the drug user, inquiring a second target drug efficacy which is matched with the disease information and contains the target prescription drug identification in the corresponding prescription drug from the drug knowledge base, acquiring an over-the-counter drug identification corresponding to the second target drug efficacy, and determining the over-the-counter drug corresponding to the acquired over-the-counter drug identification as the target over-the-counter drug.

Optionally, the determining a target over-the-counter drug capable of replacing the target prescription drug based on the target information includes: acquiring a pre-trained medicine recommendation model; the medicine recommendation model is obtained through training based on inquiry information of a sample medicine user and non-prescription medicines actually purchased by the sample medicine user; taking the inquiry information of the medicine administration user as the input of the medicine recommendation model to obtain a first output of the medicine recommendation model, wherein the first output is used for indicating non-prescription medicines corresponding to the inquiry information of the medicine administration user; and determining the non-prescription medicine corresponding to the inquiry information of the medicine user as the target non-prescription medicine.

Optionally, the drug recommendation model is trained by: taking the inquiry information of the sample drug administration user as input of a drug recommendation model to be trained, and obtaining second output of the drug recommendation model to be trained, wherein the second output is used for indicating non-prescription drugs corresponding to the inquiry information of the sample drug administration user; and after training is determined to be completed based on the second output of the medicine recommendation model to be trained and the non-prescription medicine actually purchased by the sample medication user, taking the trained model as the medicine recommendation model.

Optionally, before acquiring the inquiry information of the drug administration user input by the user in response to determining that the target prescription drug selected for the drug administration user is interrupted for purchase, the method further comprises: responding to the non-prescription information instruction triggered on the inquiry information filling page, and determining that the target prescription medicine selected by the user is interrupted to be purchased; or, in response to an exit page instruction triggered on the inquiry information filling page, determining that the target prescription drug selected for the administration user is interrupted for purchase.

According to a second aspect of embodiments of the present disclosure, there is provided a medicine recommendation apparatus including:

the acquisition module is used for acquiring target information which is input by a user and is associated with the target prescription medicine;

a first determination module for determining a target non-prescription drug capable of replacing the target prescription drug based on the target information;

and the recommending module is used for recommending the target non-prescription medicine.

Optionally, the acquiring module includes: an identification acquisition unit configured to acquire an identification of the target prescription drug input by a user in response to receiving a search request for the target prescription drug, and determine the identification of the target prescription drug as the target information.

Optionally, the first determining module includes: a fourth obtaining unit, configured to obtain a pre-constructed drug knowledge base, where the drug knowledge base includes a prescription drug identifier and an over-the-counter drug identifier corresponding to the prescription drug identifier; and the third query unit is used for querying the non-prescription drug identification corresponding to the identification of the target prescription drug from the drug knowledge base and determining the non-prescription drug corresponding to the queried non-prescription drug identification as the target non-prescription drug.

Optionally, the acquiring module includes: and the information acquisition unit is used for acquiring inquiry information of the drug administration user input by the user in response to determining that the target prescription drug selected for the drug administration user is interrupted to be purchased, and determining the inquiry information of the drug administration user as the target information.

Optionally, the first determining module includes: the first acquisition unit is used for acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises medicine efficacy and non-prescription medicine identifications corresponding to the medicine efficacy; the first query unit is used for extracting the disease information of the drug user from the inquiry information of the drug user, querying the first target drug efficacy matched with the disease information from the drug knowledge base, acquiring the non-prescription drug identification corresponding to the first target drug efficacy, and determining the non-prescription drug corresponding to the acquired non-prescription drug identification as the target non-prescription drug.

Optionally, the first determining module includes: the second acquisition unit is used for acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises medicine efficacy, a prescription medicine identifier corresponding to the medicine efficacy and a non-prescription medicine identifier corresponding to the medicine efficacy; and the second query unit is used for extracting the condition information of the drug user and the identification of the target prescription drug from the inquiry information of the drug user, querying a second target drug efficacy which is matched with the condition information and contains the target prescription drug identification from the drug knowledge base, acquiring a non-prescription drug identification corresponding to the second target drug efficacy, and determining the non-prescription drug corresponding to the acquired non-prescription drug identification as the target non-prescription drug.

Optionally, the first determining module includes: a third acquisition unit for acquiring a medicine recommendation model trained in advance; the medicine recommendation model is obtained through training based on inquiry information of a sample medicine user and non-prescription medicines actually purchased by the sample medicine user; the prediction unit is used for taking the inquiry information of the drug administration user as the input of the drug recommendation model to obtain a first output of the drug recommendation model, wherein the first output is used for indicating non-prescription drugs corresponding to the inquiry information of the drug administration user; and the determining unit is used for determining the non-prescription medicine corresponding to the inquiry information of the medicine administration user as the target non-prescription medicine.

Optionally, the medicine recommendation model is obtained through training of the following modules: the training module is used for taking the inquiry information of the sample drug administration user as the input of a drug recommendation model to be trained to obtain second output of the drug recommendation model to be trained, wherein the second output is used for indicating non-prescription drugs corresponding to the inquiry information of the sample drug administration user; and the second determining module is used for determining that the training is finished based on the second output of the medicine recommendation model to be trained and the non-prescription medicine actually purchased by the sample administration user, and taking the trained model as the medicine recommendation model.

Optionally, the apparatus further comprises: the third determining module is used for responding to the non-prescription information instruction triggered on the inquiry information filling page and determining that the target prescription medicine selected by the user for taking the medicine is interrupted to be purchased; or the fourth determining module is used for responding to the exit page instruction triggered on the inquiry information filling page and determining that the target prescription medicine selected by the user for taking the medicine is interrupted to be purchased.

According to a third aspect of embodiments of the present disclosure, there is provided an electronic device comprising: one or more processors; and one or more computer-readable storage media having instructions stored thereon; the instructions, when executed by the one or more processors, cause the processor to perform the drug recommendation method of any one of the above.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, causes the processor to perform the drug recommendation method as defined in any one of the above.

The embodiment of the disclosure provides a medicine recommendation method, a medicine recommendation device, electronic equipment and a storage medium. Target information input by a user and associated with a target prescription drug is acquired, a target non-prescription drug capable of replacing the target prescription drug is determined based on the target information, and the target non-prescription drug is recommended. Therefore, in the embodiment of the disclosure, the target non-prescription medicine capable of replacing the target prescription medicine can be automatically recommended based on the target information associated with the target prescription medicine, the processing process is simpler and more convenient, and the user experience can be improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required to be used in the description of the embodiments of the present disclosure will be briefly introduced below, and it is obvious that the drawings in the following description are only some drawings of the embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.

Fig. 1 is a flow chart of purchasing prescription drugs according to an embodiment of the present disclosure.

Fig. 2 is a flowchart of steps of a drug recommendation method according to an embodiment of the present disclosure.

FIG. 3 is a flow chart of steps of another drug recommendation method according to an embodiment of the present disclosure.

Fig. 4 is a flow chart of steps of yet another drug recommendation method in accordance with an embodiment of the present disclosure.

Fig. 5 is a schematic diagram of a query information filling page according to an embodiment of the present disclosure.

Fig. 6 is a flow chart of steps of yet another drug recommendation method in accordance with an embodiment of the present disclosure.

Fig. 7 is a schematic diagram of a medicine recommendation page according to an embodiment of the present disclosure.

Fig. 8 is a flow chart of steps of yet another drug recommendation method in accordance with an embodiment of the present disclosure.

Fig. 9 is a schematic diagram of a drug recommendation window according to an embodiment of the present disclosure.

Fig. 10 is a block diagram of a medicine recommendation apparatus according to an embodiment of the present disclosure.

Fig. 11 is a schematic structural view of an electronic device according to an embodiment of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, not all embodiments of the present disclosure. Based on the embodiments in this disclosure, all other embodiments that a person of ordinary skill in the art would obtain without making any inventive effort are within the scope of protection of this disclosure.

The medicine recommendation method disclosed by the embodiment of the disclosure can be applied to various clients supporting the online medicine purchasing function. The client may be an APP (application program) or the like that supports an online drug purchase function.

Referring to fig. 1, a flow chart of purchasing prescription drugs is shown in an embodiment of the present disclosure. As shown in fig. 1, when a user purchases a prescription drug using a client supporting an online purchase function, a process of purchasing the prescription drug may include the steps of: the method comprises the steps of purchasing prescription drugs on a drug purchasing page by a user, entering a consultation information filling page to fill out consultation information, submitting a medication application after filling out, checking the medication application by an online doctor, generating an electronic prescription after checking, checking the electronic prescription by a pharmacist, and checking the order flow (including goods allocation, goods delivery and the like) of a merchant after passing.

Referring to fig. 2, a flowchart of steps of a drug recommendation method according to an embodiment of the present disclosure is shown.

As shown in fig. 2, the medicine recommendation method may include the steps of:

step 201, obtaining target information associated with a target prescription drug entered by a user.

In an alternative embodiment, the client may acquire target information associated with the target prescription drug input by the user when the user searches for the target prescription drug, and make a recommendation of the target non-prescription drug based on the target information.

In another alternative embodiment, the client may acquire target information associated with the target prescription drug entered by the user when the target prescription drug selected for the administration user is discontinued from purchasing, and make a recommendation of the target non-prescription drug based on the target information.

Step 202, determining a target non-prescription drug capable of replacing the target prescription drug based on the target information.

The client analyzes based on the target information associated with the target prescription drug to determine a target non-prescription drug that can replace the target prescription drug. The specific process of determining the target non-prescription drug will be described in detail in the examples below.

Step 203 recommends the target over-the-counter drug.

After determining the target over-the-counter drug, the client can recommend the target over-the-counter drug so that the user can purchase the target over-the-counter drug.

It should be noted that, in the embodiments of the present application, the recommendation of the non-prescription drug information meets the requirements of legal regulations and meets the government guidelines.

According to the method and the device for recommending the non-prescription drugs, the target non-prescription drugs which can replace the target prescription drugs can be automatically recommended based on the target information related to the target prescription drugs, the processing process is simpler and more convenient, and the user experience can be improved.

Referring to fig. 3, a flowchart of steps of another drug recommendation method of an embodiment of the present disclosure is shown.

As shown in fig. 3, the medicine recommendation method may include the steps of:

step 301, in response to receiving a search request for the target prescription drug, acquiring an identification of the target prescription drug input by a user, and determining the identification of the target prescription drug as the target information.

When a user inputs an identifier of a target prescription drug in an input box on a drug purchase page of a client, and triggers a search request carrying the identifier of the target prescription drug, or when the user selects the target prescription drug on the drug purchase page of the client, and triggers a search request carrying the identifier of the target prescription drug, the client responds to receiving the search request for the target prescription drug, can analyze and acquire the identifier of the target prescription drug input by the user from the search request, and determines the identifier of the target prescription drug as the target information.

Illustratively, the identification may include, but is not limited to, a name, a number, and the like.

Step 302, determining a target non-prescription drug capable of replacing the target prescription drug based on the target information.

In an alternative embodiment, a drug knowledge base is pre-built, and the client queries a target over-the-counter drug capable of replacing the target prescription drug based on the drug knowledge base.

Optionally, based on the existing medicine database and the disease database, classifying medicines in the medicine database into prescription medicines and non-prescription medicines, analyzing the medicine efficacy of each prescription medicine and non-prescription medicine, grouping the prescription medicines and non-prescription medicines according to the medicine efficacy, dividing the prescription medicines and non-prescription medicines with the same medicine efficacy into the same group, dividing the group into two types of prescription medicines and non-prescription medicines, and then constructing a medicine knowledge base based on the prescription medicine identifications and the non-prescription medicine identifications corresponding to the prescription medicine identifications.

Illustratively, the prescription drug identifier and the non-prescription drug identifier corresponding to the prescription drug identifier may be stored in a drug knowledge base in a KV (Key-Value) data table or the like, where the prescription drug identifier may be stored as a Key, and the non-prescription drug identifier corresponding to the prescription drug identifier may be stored as a Value.

For such drug knowledge base, determining a target over-the-counter drug capable of replacing the target prescription drug based on the target information may include: acquiring a pre-constructed medicine knowledge base; inquiring the non-prescription medicine identification corresponding to the identification of the target prescription medicine from the medicine knowledge base, and determining the non-prescription medicine corresponding to the inquired non-prescription medicine identification as the target non-prescription medicine.

Step 303, recommending said target over-the-counter drug.

In an alternative embodiment, the client may generate and jump to a medicine recommendation page after determining the target non-prescription medicine that can replace the target prescription medicine, and display the target non-prescription medicine in the medicine recommendation page.

In another alternative embodiment, the client may, after determining a target non-prescription drug that can replace the target prescription drug, generate and pop up a drug recommendation window and display the target non-prescription drug in the drug recommendation window.

Referring to fig. 4, a flowchart of steps of yet another drug recommendation method of an embodiment of the present disclosure is shown.

As shown in fig. 4, the medicine recommendation method may include the steps of:

and step 401, in response to determining that the target prescription medicine selected for the medicine administration user is interrupted to be purchased, acquiring inquiry information of the medicine administration user input by the user, and determining the inquiry information of the medicine administration user as the target information.

As shown in fig. 1, after a user purchases a prescription drug in a drug purchase page, the user enters a consultation information filling page to fill in the consultation information of the drug user.

Referring to fig. 5, a schematic diagram of a query information filling page of an embodiment of the present disclosure is shown. As shown in fig. 5, in the inquiry information filling page, basic information of the administration user (the administration user refers to a user who uses a medicine) needs to be set, the actual diagnosis of the disease of the administration user at the present time is set, whether the administration user uses the medicine, whether related contraindications are not present, whether allergy history and adverse reactions are not present, prescription information of the administration user is supplemented, and the like.

However, if prescription information is not provided for the administering user (e.g., the administering user has not used the prescription drug, no prescription information exists, is not willing to provide prescription information, etc.), the prescription drug will be discontinued from purchase. And the client side responds to the fact that the target prescription medicine selected for the medicine user is interrupted to be purchased, acquires the inquiry information of the medicine user filled in the inquiry information filling page, and determines the inquiry information of the medicine user as the target information.

Step 402, determining a target non-prescription drug capable of replacing the target prescription drug based on the target information.

The client side analyzes the inquiry information of the drug user, so as to determine the target non-prescription drug capable of replacing the target prescription drug. The specific process of determining the target non-prescription drug will be described in detail in the examples below.

Step 403, recommending said target over-the-counter drug.

After determining the target non-prescription drug, the client may recommend the target non-prescription drug to purchase the target non-prescription drug for the administration user.

According to the method and the device for recommending the target non-prescription drugs, under the condition that the target prescription drugs selected for the drug users are broken and purchased, the target non-prescription drugs capable of replacing the target prescription drugs can be automatically recommended based on the inquiry information of the drug users, so that the operation of paying inquiry is not needed, the processing process is simpler and more convenient, and the user experience can be improved.

Referring to fig. 6, a flowchart of steps of yet another drug recommendation method of an embodiment of the present disclosure is shown.

As shown in fig. 6, the medicine recommendation method may include the steps of:

step 601, a user selects a target prescription drug for a medication user and submits a prescription drug purchase order.

The user refers to a user who purchases a medicine, and the medication user refers to a user who uses a medicine. In practical application, the user and the medication user may be the same user or different users, which is not limited in this embodiment.

And the user selects target prescription drugs for the drug users in a drug purchasing page of the client, and then submits a prescription drug purchasing order and pays.

Illustratively, the order information for the prescription drug purchase order may include, but is not limited to: identification (name, number, etc.) of the target prescription drug, price of the target prescription drug, type of the target prescription drug (type is prescription drug), purchase time of the target prescription drug, etc.

Step 602, the client receives the prescription drug purchase order and jumps to the inquiry information filling page.

After receiving the prescription drug purchase order, the client determines that the type of the target prescription drug in the order information is the prescription drug, and jumps to the inquiry information filling page.

Step 603, the user fills out the inquiry information of the drug administration user in the inquiry information filling page.

Illustratively, the inquiry information of the administering user may include, but is not limited to: basic information of a medicine administration user, the medicine administration user confirms the diagnosis of the disease of the medicine administration, whether the medicine administration user uses target prescription medicines, whether the medicine administration user has no related contraindications, whether the medicine administration user has no anaphylactic history and adverse reactions, the identification of the target prescription medicines, the prescription information of the target prescription medicines, and the like.

Step 604, whether the user has prescription information for the target prescription drug. If yes, go to step 605; if not, go to step 606.

Step 605, the user uploads prescription information for the target prescription drug. Step 611 is then performed.

If the user has prescription information of the target prescription drug, the prescription information of the target prescription drug needs to be uploaded in a consultation information filling page.

Illustratively, the manner in which prescription information is uploaded may include, but is not limited to: a picture of prescription information is selected from the existing pictures, a picture of prescription information is taken, and so on.

In step 606, the user clicks the "no prescription information" button on the inquiry information filling page, triggering the no prescription information instruction.

As shown in fig. 5, a "no prescription information" button that can be clicked by the user is provided in the inquiry information filling page. If the user does not have prescription information for the target prescription drug, the "no prescription information" button on the inquiry information fill page may be clicked, thereby triggering an no prescription information instruction, which may be received by the client.

In step 607, the client determines that the target prescription drug selected for the administration user is discontinued for purchase in response to the no-prescription information instruction triggered on the inquiry information fill page.

And the client responds to the non-prescription information instruction triggered by the user on the inquiry information filling page, so that the target prescription medicine selected by the user for the administration user can be determined to be interrupted for purchase.

In response to determining that the selected target prescription drug for the administration user is discontinued for purchase, the client determines a target over-the-counter drug capable of replacing the target prescription drug based on the inquiry information of the administration user, step 608.

The client acquires inquiry information of the drug administration user, and determines a target non-prescription drug capable of replacing the target prescription drug based on the inquiry information of the drug administration user.

Optionally, based on the existing medicine database and the disease database, classifying the medicines in the medicine database into prescription medicines and non-prescription medicines, analyzing the medicine efficacy of each non-prescription medicine, grouping the non-prescription medicines according to the medicine efficacy, classifying the non-prescription medicines with the same medicine efficacy into the same group, and then constructing a medicine knowledge base based on the medicine efficacy and the non-prescription medicine identifications corresponding to the medicine efficacy.

Illustratively, drug efficacy may include, but is not limited to: the disease to be treated, the age group to which it is applicable, etc. For example, the age group of the medication user may be set as follows: 0 (birth) -6 years old for infants, 7-12 years old for young children, 13-17 years old for teenagers, 18-45 years old for young, 46-69 years old for middle-aged, and more than 69 years old.

Illustratively, the medicine efficacy and the non-prescription medicine corresponding to the medicine efficacy can be stored in a medicine knowledge base in the form of a Key-Value (Key-Value) data table and the like, wherein the medicine efficacy can be stored as a Key, and the non-prescription medicine identifier corresponding to the medicine efficacy is stored as a Value.

For such a drug knowledge base, the process of determining a target over-the-counter drug capable of replacing the target prescription drug based on the inquiry information of the drug administration user may include: acquiring a pre-constructed medicine knowledge base comprising medicine efficacy and non-prescription medicine identifications corresponding to the medicine efficacy; extracting the disease information of the drug administration user from the inquiry information of the drug administration user, inquiring the first target drug efficacy matched with the disease information from the drug knowledge base, acquiring the non-prescription drug identification corresponding to the first target drug efficacy, and determining the non-prescription drug corresponding to the acquired non-prescription drug identification as the target non-prescription drug.

Illustratively, the medication user's condition information extracted from the medication user's inquiry information may include, but is not limited to: the user who is taking the medicine can do diagnosis of the disease, the age of the user who is taking the medicine, etc.

And in the process of inquiring the first target medicine efficacy, matching each medicine efficacy stored in a medicine knowledge base with the disease information of the medicine administration user, and if the disease treated in the medicine efficacy is the same as the confirmed disease of the medicine administration user, and the applicable age range in the medicine efficacy comprises the age of the medicine administration user, determining that the medicine efficacy is the first target medicine efficacy matched with the disease information of the medicine administration user.

Optionally, based on the existing medicine database and the disease database, classifying medicines in the medicine database into prescription medicines and non-prescription medicines, analyzing medicine efficacy of each prescription medicine and non-prescription medicine, grouping the prescription medicines and non-prescription medicines according to medicine efficacy, dividing the prescription medicines and non-prescription medicines with the same medicine efficacy into the same group, dividing the group into two types of prescription medicines and non-prescription medicines, and then constructing a medicine knowledge base based on medicine efficacy, prescription medicine identifications corresponding to the medicine efficacy and non-prescription medicine identifications corresponding to the medicine efficacy.

Illustratively, the medicine efficacy, the prescription medicine identifier corresponding to the medicine efficacy and the non-prescription medicine identifier corresponding to the medicine efficacy may be stored in a medicine knowledge base in the form of a KV (Key-Value) data table or the like, wherein the medicine efficacy may be stored as a Key, and the prescription medicine identifier corresponding to the medicine efficacy and the non-prescription medicine identifier corresponding to the medicine efficacy may be stored as a Value.

For such a drug knowledge base, the process of determining a target over-the-counter drug capable of replacing the target prescription drug based on the inquiry information of the drug administration user may include: acquiring a pre-constructed medicine knowledge base comprising medicine efficacy, a prescription medicine identifier corresponding to the medicine efficacy and a non-prescription medicine identifier corresponding to the medicine efficacy; extracting the disease information of the drug user and the identification of the target prescription drug from the inquiry information of the drug user, inquiring the second target drug efficacy which is matched with the disease information and contains the target prescription drug identification from the drug knowledge base, acquiring the non-prescription drug identification corresponding to the second target drug efficacy, and determining the non-prescription drug corresponding to the acquired non-prescription drug identification as the target non-prescription drug.

In the process of inquiring the second target medicine efficacy, firstly, matching each medicine efficacy stored in a medicine knowledge base with the disease information of the medicine administration user, and if the disease treated in the medicine efficacy is the same as the confirmed disease of the medicine administration user, and the applicable age range in the medicine efficacy comprises the age of the medicine administration user, determining that the medicine efficacy is the medicine efficacy matched with the disease information of the medicine administration user; then, judging whether the prescription medicine identification corresponding to the medicine efficacy contains the identification of the target prescription medicine or not according to the medicine efficacy matched with the symptom information of the medicine administration user; and finally, if the medicine is judged to be contained, determining the medicine efficacy matched with the disease information of the medicine administration user as the second target medicine efficacy matched with the disease information and containing the target prescription medicine identification in the corresponding prescription medicine identification.

In another alternative embodiment, a drug recommendation model is pre-trained, and the client determines a target over-the-counter drug that can replace the target prescription drug based on the drug recommendation model.

Optionally, the training process of the medicine recommendation model includes the following steps a1 to a5:

And a1, acquiring inquiry information of a sample administration user and the non-prescription drugs actually purchased by the sample administration user.

Sample data can be constructed based on massive historical inquiry information, historical drug purchase information and the like. Wherein the sample data includes inquiry information of a sample administration user and non-prescription drugs actually purchased by the sample administration user.

Illustratively, the over-the-counter drug actually purchased by the sample administration user may comprise one or more. The sample administration user's inquiry information may include, but is not limited to: basic information of a sample administration user, the fact that the sample administration user purchases non-prescription medicines, whether the sample administration user has no related contraindications, whether the sample administration user has no allergic history and adverse reactions, and the like.

And a2, taking inquiry information of the sample drug administration user as input of a drug recommendation model to be trained, and obtaining second output of the drug recommendation model to be trained.

In the implementation, the medicine recommendation model to be trained can be any applicable AI (Artificial Intelligence ) model, and has a multi-target classification function or a multi-target probability prediction function. Illustratively, the drug recommendation model to be trained may include, but is not limited to: RNN (Recurrent Neural Network ), SVM (Support Vector Machine, support vector machine), LSTM (Long Short-Term Memory) model, naive bayes model, logistic regression model, decision tree model, etc.

A second output is used to indicate an over-the-counter drug for which the sample administration user's inquiry information corresponds. Illustratively, the second output may include a predicted probability for each non-prescription drug, and when the predicted probability for a particular non-prescription drug exceeds a preset threshold, the non-prescription drug may be determined to be the non-prescription drug for which the interrogation information for the sample administration user corresponds.

And a step a3 of determining whether training is completed or not based on the second output of the medicine recommendation model to be trained and the non-prescription medicine actually purchased by the sample administration user. If yes, executing the step a4; if not, step a5 is performed.

And calculating a loss function of the medicine recommendation model to be trained according to the second output of the medicine recommendation model to be trained and the non-prescription medicine actually purchased by the sample medicine user.

In an implementation, the loss function of the drug recommendation model to be trained can be any applicable loss function. Illustratively, the loss function of the drug recommendation model to be trained may include, but is not limited to: cross entropy loss (CrossEntropy Loss), 0-1 loss (zero-one loss), log loss (Logistic loss), hinge loss (Hinge loss), exponential loss (exact loss), square loss (Squared loss), absolute loss (Absolute loss), huber loss (Huber loss), and the like.

And a step a4, in response to determining that the training is completed, taking the model after the training as the medicine recommendation model.

And a5, adjusting model parameters to continue training in response to determining that training is not completed.

The process of determining a target over-the-counter drug capable of replacing the target prescription drug based on the interview information of the drug user using the trained drug recommendation model may include: acquiring a pre-trained medicine recommendation model; taking the inquiry information of the medicine administration user as the input of the medicine recommendation model to obtain a first output of the medicine recommendation model, wherein the first output is used for indicating non-prescription medicines corresponding to the inquiry information of the medicine administration user; and determining the non-prescription medicine corresponding to the inquiry information of the medicine user as the target non-prescription medicine.

Illustratively, the first output may include a predicted probability for each non-prescription drug, and when the predicted probability for a particular non-prescription drug exceeds a preset threshold, the non-prescription drug may be determined to be the non-prescription drug for which the prescribing user's inquiry information corresponds.

Step 609, the client jumps to a medicine recommendation page, and displays the target non-prescription medicine in the medicine recommendation page.

Under the condition that a user clicks a 'no-prescription information' button on a query information filling page, the client determines that target prescription drugs selected for a user to be used are interrupted to be purchased, and after determining that target non-prescription drugs capable of replacing the target prescription drugs based on the query information of the user to be used, the client jumps to a drug recommendation page and displays the target non-prescription drugs in the drug recommendation page.

In an alternative embodiment, the client may also perform a sorting operation on the target non-prescription drugs after determining that the target non-prescription drugs can replace the target prescription drugs, and then select at least one of the target non-prescription drugs that is ranked first for display.

Any suitable ordering method may be selected for the particular process of the ordering operation. Illustratively, the ordering may include, but is not limited to: ranking using a recommended ranking model, ranking based on similarity of the target non-prescription drug to the target non-prescription drug, random ranking, and so forth. The similarity can be obtained by weighting parameters such as drug efficacy, drug ingredients, drug contraindications, adverse reactions, shops, manufacturers and the like.

Referring to fig. 7, a schematic diagram of a medicine recommendation page according to an embodiment of the present disclosure is shown. As shown in fig. 7, in the medicine recommendation page, target non-prescription medicines such as medicine 1, medicine 2, etc. may be displayed, and the on-sale store and price of the target non-prescription medicines, such as store 1 and price, store 2 and price, store 3 and price, etc. in fig. 7, may be displayed. It should be noted that the medicine recommendation page shown in fig. 7 is only an exemplary page, and other information may be included in the medicine recommendation page in practical applications, which is not limited in this embodiment.

At step 610, the user selects a target over-the-counter drug in the drug recommendation page and submits an over-the-counter drug purchase order.

The user may select a target non-prescription drug to be purchased on the drug recommendation page, and then submit a non-prescription drug purchase order and make a payment.

Illustratively, the order information for an over-the-counter drug order may include, but is not limited to: identification of the target non-prescription drug (name, number, etc.), price of the target non-prescription drug, type of the target non-prescription drug (type is non-prescription drug), time of purchase of the target non-prescription drug, etc.

In step 611, the client determines that the purchase is complete.

After the user uploads the prescription information of the target prescription drug in step 605, the client determines that the purchase of the drug is completed.

After the purchase user selects the target non-prescription drug in the drug recommendation page and submits the non-prescription drug purchase order in step 610, the client determines that the purchase is completed.

Referring to fig. 8, a flowchart of steps of yet another drug recommendation method of an embodiment of the present disclosure is shown.

As shown in fig. 8, the medicine recommendation method may include the steps of:

step 801, a user selects a target prescription drug for a medication user and submits a prescription drug purchase order.

Step 802, the client receives a prescription drug purchase order, and jumps to a consultation information filling page.

Step 803, the user fills out the inquiry information of the drug administration user in the inquiry information filling page.

Step 804, whether the user has prescription information of the target prescription drug. If yes, go to step 805; if not, go to step 806.

In step 805, the user uploads prescription information for the target prescription drug. Step 811 is then performed.

Step 806, the user exits the inquiry information to fill out the page, triggering an exit page instruction.

If the user does not provide prescription information for the target prescription drug, the inquiry information filling page may be exited, thereby triggering an exit page instruction that may be received by the client.

In step 807, the client determines that the target prescription drug selected for the administration user is discontinued for purchase in response to the exit page instruction triggered on the inquiry information fill page.

And the client responds to an exit page instruction triggered by the user on the inquiry information filling page, so that the target prescription medicine selected by the user for the administration user can be determined to be interrupted for purchase.

In response to determining that the selected target prescription drug for the administering user is discontinued for purchase, the client determines a target over-the-counter drug capable of replacing the target prescription drug based on the query information of the administering user, step 808.

Step 809, the client pops up a medicine recommendation popup, and displays the target non-prescription medicine in the medicine recommendation popup.

Under the condition that the user exits the inquiry information filling page, the client determines that the target prescription medicine selected for the user is interrupted to be purchased, and after determining that the target non-prescription medicine capable of replacing the target prescription medicine based on the inquiry information of the user, the client pops up a medicine recommendation popup and displays the target non-prescription medicine in the medicine recommendation popup.

Referring to fig. 9, a schematic diagram of a drug recommendation window is shown, according to an embodiment of the present disclosure. As shown in fig. 9, in the medicine recommendation window, a target non-prescription medicine such as medicine 1, medicine 2, and medicine 3 may be displayed, and a "buy to" button may be displayed. The user may select the target non-prescription drug to be purchased and click on the "buy" button to purchase the selected target non-prescription drug. It should be noted that the medicine recommendation popup shown in fig. 9 is only an exemplary popup, and other information may be further included in the medicine recommendation popup in practical applications, which is not limited in this embodiment.

At step 810, the user selects a target over-the-counter drug in the drug recommendation window and submits an over-the-counter drug purchase order.

The user may select a target over-the-counter drug to be purchased in the drug recommendation window, and then submit an over-the-counter drug purchase order and make a payment.

In step 811, the client determines that the purchase is complete.

After the user uploads the prescription information of the target prescription drug in step 805, the client determines that the purchase of the drug is completed.

After the user selects the target non-prescription drug in the drug recommendation window and submits the non-prescription drug purchase order in step 810, the client determines that the purchase is completed.

For portions of the embodiment shown in fig. 8 that are similar to the embodiment shown in fig. 6, specific reference is made to the description related to the embodiment shown in fig. 6, and this embodiment will not be discussed in detail here.

Referring to fig. 10, a block diagram of a medicine recommendation apparatus according to an embodiment of the present disclosure is shown.

As shown in fig. 10, the medicine recommendation apparatus may include the following modules:

an acquiring module 1001, configured to acquire and acquire a non-prescription drug identifier corresponding to the second target drug efficacy, where the acquired non-prescription drug identifier is acquired;

a first determining module 1002 for determining a target non-prescription drug capable of replacing the target prescription drug based on the target information;

A recommending module 1003, configured to recommend the target non-prescription drug.

Optionally, the obtaining module 1001 includes: an identification acquisition unit configured to acquire an identification of the target prescription drug input by a user in response to receiving a search request for the target prescription drug, and determine the identification of the target prescription drug as the target information.

Optionally, the first determining module 1002 includes: a fourth obtaining unit, configured to obtain a pre-constructed drug knowledge base, where the drug knowledge base includes a prescription drug identifier and an over-the-counter drug identifier corresponding to the prescription drug identifier; and the third query unit is used for querying the non-prescription drug identification corresponding to the identification of the target prescription drug from the drug knowledge base and determining the non-prescription drug corresponding to the queried non-prescription drug identification as the target non-prescription drug.

Optionally, the obtaining module 1001 includes: and the information acquisition unit is used for acquiring inquiry information of the drug administration user input by the user in response to determining that the target prescription drug selected for the drug administration user is interrupted to be purchased, and determining the inquiry information of the drug administration user as the target information.

Optionally, the first determining module 1002 includes: the first acquisition unit is used for acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises medicine efficacy and non-prescription medicine identifications corresponding to the medicine efficacy; the first query unit is used for extracting the disease information of the drug user from the inquiry information of the drug user, querying the first target drug efficacy matched with the disease information from the drug knowledge base, acquiring the non-prescription drug identification corresponding to the first target drug efficacy, and determining the non-prescription drug corresponding to the acquired non-prescription drug identification as the target non-prescription drug.

Optionally, the first determining module 1002 includes: the second acquisition unit is used for acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises medicine efficacy, a prescription medicine identifier corresponding to the medicine efficacy and a non-prescription medicine identifier corresponding to the medicine efficacy; and the second query unit is used for extracting the condition information of the drug user and the identification of the target prescription drug from the inquiry information of the drug user, querying a second target drug efficacy which is matched with the condition information and contains the target prescription drug identification from the drug knowledge base, acquiring a non-prescription drug identification corresponding to the second target drug efficacy, and determining the non-prescription drug corresponding to the acquired non-prescription drug identification as the target non-prescription drug.

Optionally, the first determining module 1002 includes: a third acquisition unit for acquiring a medicine recommendation model trained in advance; the medicine recommendation model is obtained through training based on inquiry information of a sample medicine user and non-prescription medicines actually purchased by the sample medicine user; the prediction unit is used for taking the inquiry information of the drug administration user as the input of the drug recommendation model to obtain a first output of the drug recommendation model, wherein the first output is used for indicating non-prescription drugs corresponding to the inquiry information of the drug administration user; and the determining unit is used for determining the non-prescription medicine corresponding to the inquiry information of the medicine administration user as the target non-prescription medicine.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

In an embodiment of the present disclosure, an electronic device is also provided. The electronic device may include one or more processors and one or more computer-readable storage media having instructions stored thereon, such as an application program. The instructions, when executed by the one or more processors, cause the processor to perform the drug recommendation method of any of the embodiments above.

Referring to fig. 11, a schematic diagram of an electronic device structure of an embodiment of the present disclosure is shown. As shown in fig. 11, the electronic device includes a processor 1101, a communication interface 1102, a memory 1103 and a communication bus 1104. The processor 1101, the communication interface 1102, and the memory 1103 communicate with each other via a communication bus 1104.

A memory 1103 for storing a computer program.

The processor 1101 is configured to implement the medicine recommendation method according to any of the above embodiments when executing the program stored in the memory 1103.

The communication interface 1102 is used for communication between the electronic device and other devices.

The communication bus 1104 mentioned above may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The processor 1101 mentioned above may include, but is not limited to: central processing units (Central Processing Unit, CPU), network processors (Network Processor, NP), digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like.

The memory 1103 mentioned above may include, but is not limited to: read Only Memory (ROM), random access Memory (Random Access Memory RAM), compact disk Read Only Memory (Compact Disc ReadOnly Memory CD-ROM), electrically erasable programmable Read Only Memory (Electronic Erasable Programmable ReadOnly Memory EEPROM), hard disk, floppy disk, flash Memory, and the like.

In an embodiment of the present disclosure, there is also provided a non-transitory computer-readable storage medium having stored thereon a computer program executable by a processor of an electronic device, which when executed by the processor causes the processor to perform the drug recommendation method as described in any of the embodiments above.

It should be noted that, all actions for acquiring signals, information or data in the present application are performed under the condition of conforming to the corresponding data protection rule policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present disclosure are not directed to any particular programming language. It will be appreciated that the contents of the embodiments of the present disclosure described herein may be implemented using various programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the embodiments of the present disclosure.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the disclosure may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the disclosure, various features of embodiments of the disclosure are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., an embodiment of the disclosure that claims require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this disclosure.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Various component embodiments of the present disclosure may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in a moving picture generating apparatus according to an embodiment of the present disclosure may be implemented in practice using a microprocessor or a Digital Signal Processor (DSP). Embodiments of the present disclosure may also be implemented as a device or apparatus program for performing part or all of the methods described herein. Such a program implementing embodiments of the present disclosure may be stored on a computer readable medium or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the embodiments of the disclosure, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the present disclosure may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

The foregoing is merely a specific implementation of the embodiments of the disclosure, but the protection scope of the embodiments of the disclosure is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the embodiments of the disclosure, and the changes or substitutions are intended to be covered by the protection scope of the embodiments of the disclosure.

Claims

1. A method of recommending a drug, comprising: acquiring target information input by a user and associated with a target prescription drug; determining a target non-prescription drug capable of replacing the target prescription drug based on the target information; recommending the target non-prescription drug so as to automatically recommend the target non-prescription drug that can replace the target prescription drug based on the user's inquiry information;

the obtaining the target information input by the user and associated with the target prescription drug comprises the following steps: in response to determining that a target prescription drug selected for a drug administration user is interrupted for purchase, acquiring inquiry information of the drug administration user input by a user, and determining the inquiry information of the drug administration user as the target information;

wherein the interrupted purchase comprises: the user does not use the target prescription medicine, does not have prescription information of the target prescription medicine, and is reluctant to provide the prescription information.

2. The method of claim 1, wherein the obtaining target information associated with the target prescribed drug entered by the user comprises: and in response to receiving the search request of the target prescription medicine, acquiring the identification of the target prescription medicine input by a user, and determining the identification of the target prescription medicine as the target information.

3. The method of claim 2, wherein the determining a target over-the-counter drug capable of replacing the target prescription drug based on the target information comprises: acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises a prescription medicine identifier and an over-the-counter medicine identifier corresponding to the prescription medicine identifier; inquiring the non-prescription medicine identification corresponding to the identification of the target prescription medicine from the medicine knowledge base, and determining the non-prescription medicine corresponding to the inquired non-prescription medicine identification as the target non-prescription medicine.

4. The method of claim 3, wherein the determining a target over-the-counter drug capable of replacing the target prescription drug based on the target information comprises: acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises medicine efficacy and non-prescription medicine identifications corresponding to the medicine efficacy; extracting the disease information of the drug administration user from the inquiry information of the drug administration user, inquiring the first target drug efficacy matched with the disease information from the drug knowledge base, acquiring the non-prescription drug identification corresponding to the first target drug efficacy, and determining the non-prescription drug corresponding to the acquired non-prescription drug identification as the target non-prescription drug.

5. The method of claim 3, wherein the determining a target over-the-counter drug capable of replacing the target prescription drug based on the target information comprises: acquiring a pre-constructed medicine knowledge base, wherein the medicine knowledge base comprises medicine efficacy, a prescription medicine identifier corresponding to the medicine efficacy and an over-the-counter medicine identifier corresponding to the medicine efficacy; extracting the disease information of the drug user and the identification of the target prescription drug from the inquiry information of the drug user, inquiring the second target drug efficacy which is matched with the disease information and contains the target prescription drug identification from the drug knowledge base, acquiring the non-prescription drug identification corresponding to the second target drug efficacy, and determining the non-prescription drug corresponding to the acquired non-prescription drug identification as the target non-prescription drug.

6. The method of claim 3, wherein the determining a target over-the-counter drug capable of replacing the target prescription drug based on the target information comprises: acquiring a pre-trained medicine recommendation model; the medicine recommendation model is obtained through training based on inquiry information of a sample medicine user and non-prescription medicines actually purchased by the sample medicine user; taking the inquiry information of the medicine administration user as the input of the medicine recommendation model to obtain a first output of the medicine recommendation model, wherein the first output is used for indicating non-prescription medicines corresponding to the inquiry information of the medicine administration user; and determining the non-prescription medicine corresponding to the inquiry information of the medicine user as the target non-prescription medicine.

7. The method of claim 6, wherein the drug recommendation model is trained by: taking the inquiry information of the sample drug administration user as input of a drug recommendation model to be trained, and obtaining second output of the drug recommendation model to be trained, wherein the second output is used for indicating non-prescription drugs corresponding to the inquiry information of the sample drug administration user; and after training is determined to be completed based on the second output of the medicine recommendation model to be trained and the non-prescription medicine actually purchased by the sample medication user, taking the trained model as the medicine recommendation model.

8. The method of claim 3, further comprising, prior to acquiring user entered inquiry information for a drug user in response to determining that a target prescription drug selected for the drug user is discontinued from purchasing: responding to the non-prescription information instruction triggered on the inquiry information filling page, and determining that the target prescription medicine selected by the user is interrupted to be purchased; or, in response to an exit page instruction triggered on the inquiry information filling page, determining that the target prescription drug selected for the administration user is interrupted for purchase.

9. An electronic device, comprising: one or more processors; and one or more computer-readable storage media having instructions stored thereon; the instructions, when executed by the one or more processors, cause the processor to perform the drug recommendation method of any one of claims 1 to 8.

10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, causes the processor to perform the drug recommendation method of any one of claims 1 to 8.