Medication inspection method and device

Abstract

The invention discloses a medicine use inspection method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: acquiring historical medical information and current medical information of a user, counting medication information of the user, and generating a medicine sequence and a conflict medicine sequence; according to the safety coefficient of each drug in the drug sequence and the conflicting drug sequence, determining drug characteristics of each drug in the drug sequence and conflicting characteristics of each conflicting drug in the conflicting drug sequence; obtaining check drugs of a user, generating a check drug sequence, and determining check drug features of each check drug in the check drug sequence; and matching the checked drug features with the drug features and the conflict features, and finding out conflicting drugs of the checked drugs. According to the embodiment, personalized and accurate medication examination is realized, the accuracy of medication examination for the user can be effectively improved, healthy and valuable medication guidance is provided for the user, and the medication safety of the user is better guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for checking medication. Background Art

[0002] As people's health awareness increases, healthy medication is receiving more and more attention. Due to individual differences, a wide variety of drugs, and the professionalism of drug instructions, it is often difficult for users to accurately assess medication safety when taking medication on their own, which may lead to problems such as improper medication, drug interactions, and even life-threatening. Existing medication checks are usually based on a general drug knowledge base, which obtains conflicting drugs for current medications by searching for keywords.

[0003] In the process of implementing the present invention, the inventors found that the prior art has the following problems:

[0004] Existing medication inspection methods only provide general medication inspections, and the accuracy of medication inspections is also poor. They cannot provide users with healthy medication guidance and cannot ensure the safety of users' medications. Summary of the invention

[0005] In view of this, the embodiments of the present invention provide a method and device for medication inspection, which realizes personalized and accurate medication inspection. Based on the user's drug characteristics and conflicting characteristics of conflicting drugs extracted from the user's personal medical information, the conflicting drugs of the user's drugs are determined, which can effectively improve the accuracy of medication inspection for individual users, and then provide users with healthy and valuable medication guidance, and better ensure the safety of users' medication.

[0006] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for checking medication is provided, comprising:

[0007] Obtain the user's historical medical information and current medical information, count the user's medication information within a specified statistical period, and generate a drug sequence and a conflicting drug sequence; determine the drug characteristics of each drug in the drug sequence and the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence;

[0008] Obtain the user's checked drugs, generate a checked drug sequence, and determine the checked drug characteristics of each checked drug in the checked drug sequence according to the safety factor of each checked drug in the checked drug sequence;

[0009] The characteristics of the drug to be inspected are matched with the characteristics of the drug and the conflicting characteristics to find out the conflicting drugs of the drug to be inspected.

[0010] Optionally, after determining the drug characteristics of each drug in the drug sequence and the conflict characteristics of each conflicting drug in the conflicting drug sequence, the method further includes: converting each of the drug characteristics and each of the conflict characteristics into each drug characteristic spectrum diagram and each of the conflict characteristic spectrum diagrams, respectively; after determining the inspection drug characteristics of each inspection drug in the inspection drug sequence, the method further includes: converting the inspection drug characteristics into an inspection drug spectrum diagram; matching the inspection drug characteristics with the drug characteristics and the conflict characteristics to find out the conflicting drugs of the inspection drugs, includes: performing curve overlap matching on the inspection drug spectrum diagram with each of the drug characteristic spectrum diagrams and each of the conflict characteristic spectrum diagrams, and obtaining the conflicting drugs according to the matching results.

[0011] Optionally, the drug inspection spectrum graph is matched with each of the drug feature spectrum graphs and each of the conflict feature spectrum graphs, and the conflicting drug is obtained based on the matching result, including: determining the user's drug matching feature and the conflict matching feature associated with the drug matching feature based on each of the drug feature spectrum graphs and each of the conflict feature spectrum graphs; matching the drug inspection spectrum graph with the spectrum graph corresponding to the drug matching feature to obtain a target drug curve; searching for a target conflict curve associated with the target drug curve based on the conflict matching feature associated with the drug matching feature; and tracing the target conflict curve to obtain the conflicting drug of the drug inspection.

[0012] Optionally, the drug matching feature of the user and the conflict matching feature associated with the drug matching feature are determined based on each of the drug feature spectrum graphs and each of the conflict feature spectrum graphs, including: extracting key medication information including dosage and frequency from each of the drug feature spectrum graphs to generate a medication feature curve; extracting key conflict information including dosage and frequency from each of the conflict feature spectrum graphs to generate a conflict feature curve; using each of the drug features to perform segmented matching on the medication feature curve to obtain medication feature curve segments; using each of the conflict features to perform segmented matching on the conflict feature curve to obtain conflict feature curve segments; based on the relationship information between the medication feature curve segments, the conflict feature curve segments and the pre-acquired drugs, the drug matching feature and the conflict matching feature of the user are obtained, and an association relationship between the drug matching feature and the conflict matching feature is established.

[0013] Optionally, according to the safety factor of each drug in the drug sequence and the conflicting drug sequence, the drug characteristics of each drug in the drug sequence and the conflicting drug sequence are determined, including: calculating the number of drug grades corresponding to the drug sequence and the number of conflicting drug grades corresponding to the conflicting drug sequence according to the length of the drug sequence and the conflicting drug sequence; determining the drug grade coefficient of each drug in the drug sequence according to the number of drug grades and the safety factor of each drug in the drug sequence; determining the conflict grade coefficient of each conflicting drug in the conflicting drug sequence according to the number of conflicting drug grades and the safety factor of each conflicting drug in the conflicting drug sequence; calculating the convolution of the drug grade coefficient and the drug sequence to obtain the drug characteristics of each drug in the drug sequence; calculating the convolution of the conflict grade coefficient and the conflicting drug sequence to obtain the conflict characteristics of each conflicting drug in the conflicting drug sequence.

[0014] Optionally, the method also includes: forming a training sample set from the drug characteristics of each drug in the drug sequence and the conflict characteristics of each conflicting drug in the conflicting drug sequence, and using the training sample set to train and construct a medication inspection model; inputting the inspection drug characteristics into the medication inspection model, using the medication inspection model to find similar training samples that are similar to the inspection drug characteristics, and outputting the conflicting drugs of the inspection drug based on the similar training samples.

[0015] Optionally, statistics are collected on the medication information of the user within a specified statistical period to generate a drug sequence and a conflicting drug sequence, including: determining the drug set used by the user and the usage order of each drug in the drug set based on the medication information of the user within the specified statistical period; encoding each drug in the drug set and generating a drug sequence for the user within the statistical period according to the usage order; determining conflicting drugs for each drug in the drug set and determining an arrangement order of the conflicting drugs according to the usage order of each drug in the drug set; encoding each conflicting drug and generating a conflicting drug sequence for the user within the statistical period according to the arrangement order.

[0016] According to a second aspect of an embodiment of the present invention, there is provided a device for checking medication, comprising:

[0017] The drug feature determination module is used to obtain the user's historical medical information and current medical information, count the user's drug information within a specified statistical period, generate a drug sequence and a conflicting drug sequence; determine the drug features of each drug in the drug sequence and the conflicting features of each conflicting drug in the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence;

[0018] An inspection feature determination module, used to obtain the inspection drugs of the user, generate an inspection drug sequence, and determine the inspection drug feature of each inspection drug in the inspection drug sequence according to the safety factor of each inspection drug in the inspection drug sequence;

[0019] The conflicting drug checking module is used to match the characteristics of the checked drug with the characteristics of the drug and the conflicting characteristics to find out the conflicting drugs of the checked drug.

[0020] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for checking medication, including:

[0021] one or more processors;

[0022] a storage device for storing one or more programs,

[0023] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the embodiment of the present invention.

[0024] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0025] According to a fifth aspect of an embodiment of the present invention, there is provided a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method provided in the first aspect of the embodiment of the present invention is implemented.

[0026] One embodiment of the invention has the following advantages or beneficial effects: by obtaining the user's historical medical information and current medical information, counting the user's medication information within a specified statistical period, generating a drug sequence and a conflicting drug sequence; determining the drug characteristics of each drug in the drug sequence and the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence; obtaining the user's verified drugs, generating a verified drug sequence, and determining the verified drug characteristics of each verified drug in the verified drug sequence according to the safety factor of each verified drug in the verified drug sequence; matching the verified drug characteristics with the drug characteristics and the conflicting characteristics to find out the technical solution of the conflicting drugs of the verified drugs, realizing a personalized and accurate medication inspection, determining the conflicting drugs of the user's verified drugs based on the user's drug characteristics and the conflicting characteristics of the conflicting drugs extracted from the user's personal medical information, which can effectively improve the accuracy of the user's individual medication inspection, thereby providing the user with healthy and valuable medication guidance, and better ensuring the user's medication safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0028] Figure 1 is a schematic diagram of the main process of the method for checking medication according to an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of a process of a user logging into an account according to an embodiment of the present invention;

[0030] Figure 3 It is a schematic diagram of a method for determining drug characteristics and conflicting characteristics implemented by the present invention;

[0031] Figure 4 It is a schematic diagram of a method for constructing a drug sequence and a conflicting drug sequence according to an embodiment of the present invention;

[0032] Figure 5 is a schematic diagram of a method for determining drug features and conflicting features according to an embodiment of the present invention;

[0033] Figure 6 is a flow chart of a method for generating a medication check according to a reference embodiment of the present invention;

[0034] Figure 7 is a schematic diagram of drug characteristic spectra of three drugs according to an embodiment of the present invention;

[0035] Figure 8 is a schematic diagram of a method for determining drug matching features and conflicting matching features according to an embodiment of the present invention;

[0036] Fig. 9 It is a schematic diagram of a method for determining conflicting drugs for drug inspection according to an embodiment of the present invention;

[0037] Fig.10 is a flow chart of a method for checking medication according to another reference embodiment of the present invention;

[0038] Fig.11 Schematic diagram of the relationship between the overall functional units of the method for checking medication use according to an embodiment of the present invention;

[0039] Fig.12 is a schematic diagram of main modules of a device for checking medication according to an embodiment of the present invention;

[0040] Fig.13 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0041] Fig.14 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0042] It should be noted that in the technical solution of the present invention, the collection / collection, update, analysis, use, transmission, storage and other aspects of user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside of these legal uses, and are subject to supervision and management by national regulatory authorities. Necessary measures should be taken for user personal information to selectively block the use or access to personal information data to prevent illegal access to such personal information data, ensure that persons who have access to personal information data comply with the provisions of relevant laws and regulations, and ensure the security of user personal information. In addition, once these user personal information data are no longer needed, the risks should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0043] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0044] Existing medication inspection methods only provide general medication inspections, and the accuracy of medication inspections is also poor. They cannot provide users with healthy medication guidance and cannot ensure the safety of users' medications.

[0045] In order to solve the above-mentioned problems existing in the prior art, the present invention proposes a method for medication inspection, which takes the user as the dimension, based on the user's historical medical information and current medical information, by generating the user's drug sequence and conflicting drug sequence, obtaining the user's corresponding drug characteristics and the conflicting characteristics of the conflicting drugs, and then matching the inspection drug characteristics of the inspection drugs to be used by the user with the user's drug characteristics and conflicting characteristics to obtain the conflicting drugs of the inspection drugs, thereby realizing a personalized and accurate medication inspection. Based on the user's drug characteristics and conflicting drug characteristics extracted from the user's personal medical information, the conflicting drugs of the user's inspection drugs are determined, which can effectively improve the accuracy of medication inspection for individual users, thereby providing users with healthy and valuable medication guidance, and better ensuring the user's medication safety.

[0046] Figure 1 Schematic diagram of the main process of the method for checking medication according to an embodiment of the present invention. Figure 1 As shown, the method for checking medication use according to the embodiment of the present invention includes the following steps S101 to S103.

[0047] Step S101, obtaining the user's historical medical information and current medical information, counting the user's medication information within a specified statistical period, generating a drug sequence and a conflicting drug sequence; determining the drug characteristics of each drug in the drug sequence and the conflicting drug sequence based on the safety factor of each drug in the drug sequence and the conflicting drug sequence.

[0048] Specifically, when the data collection module of the medication inspection system receives a task to collect the user's medical information data, it obtains the user's historical medical information and the user's current medical information when the collection task is received from the data storage unit. The user of the embodiment of the present invention is the current online user of the platform. When the patient user logs in to the comprehensive medical platform, the control center of the platform first reviews the personal information and login password, and for the user who passes the review, generates a corresponding login account based on his or her personal information, uploads the login account and login password to the user login module for account login, and marks the user who has completed the account login as an online user. For the specific process, please refer to Figure 2 , Figure 2 Schematic diagram of the process of user account login in an embodiment of the present invention. The patient user first enters personal information and login password through the user login module, and the control center of the platform reviews the personal information and login password. If the review fails, the failure information is fed back to the user login module. If the review passes, the login account is generated, and the login account and login password are uploaded to the user login module for account login.

[0049] Further, according to the user's historical medical information and current medical information obtained, a statistical period is set for the user. For example, for the case of taking the same medicine three times a day each time, the statistical period is the time period of the first medication in each medical visit in the user's historical medical information, and the time period of the first medication in the medical visit time in the user's current medical information. Of course, it is also possible that the drug situation of the first three days in a medical visit information is different from the fourth day, so the statistical period should be divided into the time period of the first medication on the previous day and the time period of the first medication on the fourth day. The specific statistical period depends on the situation of the medical information, as long as a drug sequence or conflicting drug sequence represents the set of drugs taken by the user at one time. At the same time, identify the drugs that can be taken at the same time among all the drugs currently taken by the user and the conflicting drugs that conflict with these drugs and should not be taken at the same time; and the drugs that can be taken at the same time among the drugs taken by the user in history each time and the conflicting drugs that conflict with these drugs and should not be taken at the same time, and then generate a sequence of drugs that can be taken at the same time within the statistical period, and a sequence of conflicting drugs that cannot be taken at the same time or should not be taken at the same time.

[0050] Finally, based on the safety factor set by the drug description of each drug in the drug inspection system, the safety factor of each drug in the drug sequence and the safety factor of each conflicting drug in the conflicting drug sequence are obtained. Then the drug safety level of each drug in the drug sequence and the conflict level of each conflicting drug in the conflicting drug sequence are analyzed; the drug features of each drug in the drug sequence are extracted from each drug safety level and the drug sequence to which it belongs, and the conflict features of each conflicting drug in the conflicting drug sequence are extracted from each conflict level and the conflicting drug sequence to which it belongs.

[0051] The embodiment of the present invention is based on the user's historical medical information and current medical information, counts the drug sequence and conflicting drug sequence of each drug taken by the user, combines the safety factors of each drug, determines the drug characteristics of each drug in the drug sequence and the conflict characteristics of each conflicting drug in the conflicting drug sequence from the perspective of drug safety, and establishes a personalized and customized medication safety knowledge base for each user, providing necessary data support for the personalized and accurate medication inspection of this solution.

[0052] Step S102: Acquire the user's inspected drugs, generate an inspected drug sequence, and determine the inspected drug characteristics of each inspected drug in the inspected drug sequence according to the safety factor of each inspected drug in the inspected drug sequence.

[0053] Specifically, the medication check in the embodiment of the present invention is mainly used to issue medication guidance to users in advance, so the specific scenario is a medication plan that the user is preparing to take that is different from the current medication. For example, the user's treatment is divided into two stages, and it is currently the medication period of the first stage. Then before the start of the second stage, it is necessary to perform a medication check on the medication of the second stage, which aims to check the medication risks for the user in advance and provide an early warning of medication. Therefore, the checked drugs in the embodiment of the present invention are the drugs that the user is preparing to take that are different from the current drugs.

[0054] Furthermore, according to a method similar to the above, a sequence of drugs for preparation is generated, and the safety level of each drug is determined based on the safety factor of each drug in the sequence, and the characteristics of the drugs are extracted from each safety level and the sequence of drugs to which it belongs.

[0055] Step S103: Match the characteristics of the drug to be inspected with the characteristics of the drug and the conflicting characteristics to find out the conflicting drugs of the drug to be inspected.

[0056] Specifically, given that the user's drug characteristics and conflict characteristics are safety feature extractions of drugs that the user has taken, and that conflicting drugs are records of conflicting medications for each drug in the user's drug sequence, there is a corresponding association between drug characteristics and conflict characteristics. Based on this, the inspection drug characteristics are first matched with the drug characteristics to obtain the target characteristics, and then the target conflict characteristics corresponding to the target characteristics are queried from the conflict characteristics. Finally, the corresponding drug is determined through the target conflict characteristics, which is the conflicting drug of the inspection drug.

[0057] The embodiment of the present invention collects the user's historical medical information and current medical information in the user dimension, obtains the user's historical and current drug categories, constructs the user's drug sequence and conflict sequence, and mines the drug characteristics and conflict characteristics that characterize the individual user through the drug safety factor, and then determines the conflicting drugs for the checked drugs through the feature matching method, thereby providing users with personalized and accurate medication checks.

[0058] From the above analysis, it can be seen that the determination of the drug characteristics and conflict characteristics in the embodiment of the present invention is directly related to the effect of the medication inspection. Figure 3 Schematic diagram of a method for determining drug characteristics and conflicting characteristics implemented by the present invention. As another embodiment of the present invention, Figure 3 As shown, the determination method includes:

[0059] Step S301, obtaining the user's historical medical information and current medical information, and determining the drug set used by the user and the order of use of each drug in the drug set based on the user's medication information within a specified statistical period.

[0060] Specifically, the medical information of the embodiment of the present invention includes the name of the user's medication, dosage, drug effect, drug adjustment record, and the relationship between drugs (interaction relationship between drugs). The user's historical medical information also includes the user's allergy history, disease history and complications. It can be understood that the relationship between drugs mainly includes the known conflicts between drugs and other drugs or foods, that is, drugs that cannot be taken at the same time or should not be taken at the same time.

[0061] Furthermore, from these historical medical information and current medical information, the statistical period is determined, and the names, dosages, effects, and relationships between drugs of the user in the statistical period are obtained to form medication information. Then, based on the user's medication information, the drugs in the statistical period are grouped into a drug set, and the order of taking each drug in the drug set is determined, that is, the order of using each drug.

[0062] Step S302: encode each of the drugs in the drug set, and generate a drug sequence for the user in the statistical period according to the usage order.

[0063] Specifically, in order to facilitate subsequent feature mining, it is necessary to encode each drug in the drug set. Based on the predetermined coding rules for each drug, the drug code of each drug is obtained according to the coding rules. The drug code is used instead of the drug. According to the user's usage order, the drug sequence of the user within the statistical period is generated. The drug sequence represents the arrangement of various drugs used by the user at one time.

[0064] Step S303: determining the conflicting drugs of each drug in the drug set, and determining the arrangement order of the conflicting drugs according to the usage order of each drug in the drug set.

[0065] Specifically, based on the relationship between the drugs in the medical information, the conflicting drugs corresponding to each drug in the drug set are determined. The specific conflicting drugs can be one or more, or one drug with the greatest impact can be selected from multiple conflicting drugs according to the agreed screening rules. Then, the order of use of each drug in the drug set is used as the arrangement order of the corresponding conflicting drugs.

[0066] Step S304: encode each of the conflicting drugs, and generate a conflicting drug sequence for the user within the statistical period according to the arrangement order.

[0067] Specifically, similar to the above, the determined conflicting drugs are encoded according to the preset coding rules to obtain the drug codes of each conflicting drug, and the drug codes of the conflicting drugs are used to replace the corresponding conflicting drugs, and the drug codes of each conflicting drug are arranged according to the arrangement order of the above conflicting drugs to generate the conflicting drug sequence of the user within the statistical period. It can be understood that when the number of conflicting drugs corresponding to a drug is multiple, in order to facilitate the determination of the corresponding association between the conflicting drug and the drug, it is preferred to attach the identification of the corresponding associated drug to the drug code of each conflicting drug to determine the drug in the drug sequence to which each conflicting drug in the conflicting drug sequence corresponds.

[0068] Figure 4Schematic diagram of the construction method of the drug sequence and conflicting drug sequence of the embodiment of the present invention. The data collection end of the platform obtains the user's current medical information, including medical records, drug information prescribed by doctors, and instructions for use of drugs. And retrieve the user's historical medical information according to the current online user, including the user's medical history, medication record and the relationship between drugs (interaction relationship between drugs), etc. The data collection end can use the large language model LLM, and optimize the user's current medical information and historical medical information by using the summarization and induction capabilities of the LLM model, as well as the reference and comparison with other users' medical information. Then, according to the current collection time, set the corresponding statistical period, generate a drug sequence by sorting and coding each drug in the same statistical period according to the order of use, and at the same time determine the conflicting drugs corresponding to each drug, arrange and code them based on the order of use of each drug, and generate a conflicting drug sequence.

[0069] Step S305: Calculate the number of drug grades corresponding to the drug sequence and the number of conflicting drug grades corresponding to the conflicting drug sequence according to the lengths of the drug sequence and the conflicting drug sequence.

[0070] Specifically, the composition length of the drug sequence and the composition length of its conflicting drug sequence are counted. In addition, considering the differences in the dimensions of the effects of different drugs, for example, the main effect of drug A is in the time dimension, while the main effect of drug B is in the frequency dimension, then an adjustment base needs to be set so that the two drugs can be compared on the same scale. For example, we can multiply the time dimension signal of drug A by a smaller adjustment base to match the frequency dimension signal of drug B. In this way, we can more easily observe the interaction and potential conflict between the two drugs. And considering that the interaction between drugs will change over time, the adjustment time is set to capture this temporal change. Using these three parameters (sequence composition length, sequence adjustment base, sequence adjustment interval), the number of drug grades corresponding to the drug sequence and the number of conflicting drug grades corresponding to the conflicting drug sequence are calculated. The specific calculation formula is: , Among them, L is the length of the sequence, ∆T represents the adjustment interval, m is the number of adjustment bases, and J is the standardized base of each adjustment base. Based on this, the number of drug grades in the drug sequence and the number of conflicting drug grades in the conflicting drug sequence can be calculated.

[0071] Step S306: Determine the drug classification coefficient of each drug in the drug sequence according to the number of drug classifications and the safety factor of each drug in the drug sequence.

[0072] Specifically, according to the distribution of the specific values ​​of the safety factors of each drug in the drug sequence, combined with the number of drug grades calculated above, the drug classification rules of the drug sequence are determined, and according to the drug classification rules, the drug classification coefficients corresponding to each drug in the drug sequence, that is, the grades corresponding to each drug, are determined. For example, the most intuitive drug classification rule is to divide the largest safety factor in the drug sequence into segments according to the number of drug grades, obtain the safety factor corresponding to each segment, that is, each grade, and then determine the classification coefficient to which each drug belongs according to the safety factor of each drug. For example, if the largest safety factor is 13.5 and the number of drug grades is 3, then 4.5 obtained by 13.5 / 3 is the basis for each grade, that is, 0~4.5 is the first grade, indicating the safest drug grade, and the drug classification coefficient of drugs falling into this grade is 1; 4.5~9.0 is the second grade, indicating the second safest drug grade, and the drug classification coefficient of drugs falling into this grade is 2; 9.0~13.5 is the third grade, indicating the least safe drug grade, and the drug classification coefficient of drugs falling into this grade is 3.

[0073] Step S307: Determine the conflict grading coefficient of each conflicting drug in the conflicting drug sequence according to the number of conflicting drug grades and the safety factor of each conflicting drug in the conflicting drug sequence.

[0074] Similarly, similar to the above determination of the drug grading coefficient of each of the drugs in the drug sequence, the conflicting drug grading rules of the conflicting drug sequence are determined based on the distribution of specific values ​​of the safety factors of each conflicting drug in the conflicting drug sequence, combined with the above calculated number of conflicting drug grades, and according to the conflicting drug grading rules, the conflict grading coefficient corresponding to each conflicting drug in the conflicting drug sequence, that is, the grade corresponding to each conflicting drug, is determined.

[0075] Step S308: Calculate the convolution of the drug classification coefficient and the drug sequence to obtain drug characteristics of each drug in the drug sequence.

[0076] Specifically, the drug classification coefficient of each drug in the drug sequence is convolved with the drug sequence to extract the drug features of each drug taken by the user this time from the perspective of drug safety.

[0077] Step S309, calculating the convolution of the conflict grading coefficient and the conflicting drug sequence to obtain the conflict characteristics of each of the conflicting drugs in the conflicting drug sequence.

[0078] Specifically, the conflict classification coefficient of each conflicting drug in the conflicting drug sequence is convolved with the conflicting drug sequence to extract the conflict characteristics of each conflicting drug in the user's current medication from the perspective of medication safety.

[0079] Figure 5It is a schematic diagram of a method for determining drug characteristics and conflict characteristics of an embodiment of the present invention. Based on the generated drug sequence and conflicting drug sequence, the number of drug grades corresponding to the drug sequence and the number of conflicting drug grades corresponding to the conflicting drug sequence are calculated according to the length, adjustment base and adjustment interval of the drug sequence and the conflicting drug sequence. Then, based on the calculated number of grades and the safety factor of each drug in the drug sequence, as well as the number of conflicting drug grades and the safety factor of each conflicting drug in the conflicting drug sequence, the drug grade coefficient of each drug in the drug sequence and the conflicting drug grade coefficient of each conflicting drug in the conflicting drug sequence are determined. Finally, by calculating the convolution of the drug grade coefficient of each drug with the drug sequence, and the convolution of the conflicting drug grade coefficient of each conflicting drug with the conflicting drug sequence, the drug characteristics of each drug in the drug sequence and the conflicting characteristics of each conflicting drug in the conflicting sequence are obtained.

[0080] The embodiment of the present invention constructs a drug sequence and a conflicting drug sequence that characterize each time a user takes medicine through drug coding and sorting, and then classifies the drugs in the drug sequence and the conflicting drugs in the conflicting drug sequence according to the length of the sequence, as well as the adjustment cardinality and adjustment interval of the drugs, and then mines the drug features and conflicting features of each time the user takes medicine through convolution, thereby ensuring the efficiency and accuracy of determining the drug features and the conflicting features.

[0081] Figure 6 is a flow chart of a method for generating a medication check according to a reference embodiment of the present invention. As another embodiment of the present invention, Figure 6 As shown, the method for checking medication may include:

[0082] Step S601, obtain the user's historical medical information and current medical information, count the user's medication information within a specified statistical period, generate a drug sequence and a conflicting drug sequence; determine the drug characteristics of each drug in the drug sequence and the conflicting drug sequence based on the safety factor of each drug in the drug sequence and the conflicting drug sequence.

[0083] Step S602: convert each of the drug features and each of the conflict features into a drug feature spectrum graph and a conflict feature spectrum graph respectively.

[0084] Specifically, in order to improve the accuracy and efficiency of medication inspection, the embodiment of the present invention performs more fine-grained and dynamic mining of drug features and conflict features from the perspective of spectrum graphs, and uses spectrum graph generation tools to convert each of the above-obtained drug features into a corresponding drug feature spectrum graph, and convert each conflict feature into a corresponding conflict feature spectrum graph. Figure 71 is a schematic diagram of drug characteristic spectra of three drugs according to an embodiment of the present invention, which respectively show drug characteristic spectra of drug A, drug B and drug C.

[0085] Step S603: Acquire the user's inspected drugs, generate an inspected drug sequence, and determine the inspected drug characteristics of each inspected drug in the inspected drug sequence according to the safety factor of each inspected drug in the inspected drug sequence.

[0086] Step S604: convert the drug inspection feature into a drug inspection frequency spectrum.

[0087] Specifically, according to the above-mentioned method of generating a drug feature spectrum graph, the determined drug features of the drug to be inspected are also converted into a drug spectrum graph through a dedicated spectrum graph generation tool, and the digitized drug features to be inspected are converted into a finer-grained, higher-order drug spectrum graph.

[0088] Step S605: perform curve overlap matching on the drug inspection spectrum diagram, each of the drug characteristic spectrum diagrams and each of the conflict characteristic spectrum diagrams, and obtain the conflicting drug according to the matching result.

[0089] Specifically, based on the spectrum graphs obtained by various feature conversions, each spectrum graph of the drug to be inspected is first matched with each drug feature spectrum graph of the user to obtain the target drug feature spectrum graph with the curve overlapped and matched in each drug feature spectrum graph. Then, the target conflict feature spectrum graph corresponding to the target drug feature spectrum graph is searched from each conflict feature spectrum graph. Finally, the corresponding conflicting drug is retrieved from the target conflict feature spectrum graph, which is the conflicting drug of the inspected drug.

[0090] According to one embodiment of the present invention, the drug inspection spectrum graph is matched with each of the drug feature spectrum graphs and each of the conflict feature spectrum graphs, and the conflicting drug is obtained according to the matching result, including: determining the user's drug matching feature and the conflict matching feature associated with the drug matching feature according to each of the drug feature spectrum graphs and each of the conflict feature spectrum graphs; matching the drug inspection spectrum graph with the spectrum graph corresponding to the drug matching feature to obtain a target drug curve; searching for a target conflict curve associated with the target drug curve according to the conflict matching feature associated with the drug matching feature; and tracing the target conflict curve to obtain the conflicting drug of the drug inspection.

[0091] Specifically, when matching with each drug as the granularity, in order to further improve the accuracy, the total drug characteristics of each user taking the medicine cannot be ignored, such as the total dosage and the comprehensive efficacy of each drug after superposition. Therefore, the embodiment of the present invention fuses the characteristic spectrum graphs of each drug, first obtains the comprehensive characteristic spectrum graph of the drug, and then segments, matches and extracts features of the comprehensive characteristic spectrum graph according to the granularity of each drug to obtain a drug matching feature with comprehensive characteristics. For the conflicting features corresponding to the drug features, according to this method, the conflicting feature spectrum graphs are also fused, and then the fused spectrum graph is segmented and feature extracted according to the conflicting drugs to obtain a conflict matching feature with comprehensive conflicting features.

[0092] Furthermore, the spectrum of the drug to be inspected and the spectrum of the drug matching feature are matched by curve overlap, that is, the target drug curve that overlaps with the spectrum of the drug to be inspected is searched in the spectrum of the drug matching feature. Then, the target conflict curve corresponding to the target drug curve is searched from the conflict matching feature corresponding to the drug matching feature. Finally, the target conflict curve is traced to the source of the drug, the drug corresponding to the target conflict curve is searched, and the found drug is used as the conflict drug of the inspected drug.

[0093] According to another embodiment of the present invention, the drug matching feature of the user and the conflict matching feature associated with the drug matching feature are determined based on each of the drug feature spectrum graphs and each of the conflict feature spectrum graphs, including: extracting key medication information including dosage and frequency from each of the drug feature spectrum graphs to generate a medication feature curve; extracting key conflict information including dosage and frequency from each of the conflict feature spectrum graphs to generate a conflict feature curve; using each of the drug features to perform segmented matching on the medication feature curve to obtain medication feature curve segments; using each of the conflict features to perform segmented matching on the conflict feature curve to obtain conflict feature curve segments; according to the relationship information between the medication feature curve segments, the conflict feature curve segments and the pre-acquired drugs, the drug matching feature and the conflict matching feature of the user are obtained, and an association relationship between the drug matching feature and the conflict matching feature is established.

[0094] Specifically, for the determination of drug matching features and conflict matching features, an embodiment of the present invention provides a specific curve-based determination scheme. For medication inspection, the main focus is on the user's medication dosage and frequency. Therefore, in order to improve efficiency and accuracy, key medication information involving dosage and frequency is extracted from each drug feature spectrum diagram and marked. Based on these marked key medication information, a medication feature curve representing the user's medication this time is generated. Similarly, key conflict information involving dosage and frequency is extracted from each conflict feature spectrum diagram, marked, and a conflict feature curve is generated.

[0095] Then, the above-mentioned drug features are used to perform segmented matching of the drug usage characteristic curve at the drug granularity to obtain the drug usage characteristic curve segments corresponding to each drug in the drug sequence. Similarly, the conflicting features are used to perform segmented matching of the conflicting drug characteristic curve at the conflicting drug granularity to obtain the conflicting characteristic curve segments corresponding to each conflicting drug in the conflicting drug sequence.

[0096] Finally, the user's drug matching features are extracted from each of the user's medication feature curve segments, and the user's conflict matching features are extracted from each of the user's conflict feature curve segments. Then, the relationship information between the drugs acquired in advance is used to establish a corresponding association relationship between the drug matching features and the conflict matching features.

[0097] Figure 8 It is a schematic diagram of a method for determining drug matching features and conflict matching features according to an embodiment of the present invention. Based on the drug features of each drug obtained as described above, and the conflict features of the corresponding associated conflicting drugs, each drug feature and conflict feature is converted into a drug feature spectrum diagram and a conflict feature spectrum diagram, and key medication information is extracted from each drug spectrum diagram to generate a medication feature curve for the user's current medication; key conflict information is extracted from each conflict feature spectrum diagram to generate a conflict feature curve for the current medication. Each drug feature and conflict feature is then used to segmentally match the medication feature curve and the conflict feature curve, respectively, to obtain medication feature curve segments and conflict feature curve segments. Finally, based on the medication feature curve segments and the conflict feature curve segments, the user's drug matching features and conflict matching features are obtained, and then the association relationship between the drug matching features and the conflict matching features is established in combination with the relationship information between the drugs acquired in advance.

[0098] Fig. 9 It is a schematic diagram of a method for determining conflicting drugs for inspected drugs according to an embodiment of the present invention. According to a preset inspection node, log in to the inspection terminal, obtain the user's inspected drugs, and generate an inspected drug sequence. Then, according to the safety factor of each inspected drug in the inspected drug sequence, determine the inspected drug features of each inspected drug in the inspected drug sequence, and convert the inspected drug features into an inspected drug spectrum graph. Match the inspected drug spectrum graph with the spectrum graph corresponding to the above-mentioned drug matching feature to obtain a target drug curve; according to the conflict matching feature associated with the drug matching feature, find the target conflict curve associated with the target drug curve; perform drug traceability on the target conflict curve to obtain the conflicting drugs for the inspected drugs.

[0099] The embodiment of the present invention provides a method for checking drug usage, which converts drug features, conflict features and checked drug features into corresponding frequency spectrum graphs, and uses a curve matching method of the frequency spectrum graph to accurately perform curve overlap matching to obtain conflicting drugs for checked drugs, thereby further improving the accuracy of the inspection of checked drugs, thereby providing users with accurate, healthy and valuable medication guidance, and better ensuring the safety of users' medication.

[0100] Fig.10 : is a flow chart of a method for checking medication according to another reference embodiment of the present invention. As another embodiment of the present invention, Fig.10 As shown, the method for checking medication may include:

[0101] Step S1001, obtain the user's historical medical information and current medical information, count the user's medication information within a specified statistical period, generate a drug sequence and a conflicting drug sequence; determine the drug characteristics of each drug in the drug sequence and the conflicting drug sequence based on the safety factor of each drug in the drug sequence and the conflicting drug sequence.

[0102] Step S1002: Acquire the user's inspected drugs, generate an inspected drug sequence, and determine the inspected drug characteristics of each inspected drug in the inspected drug sequence according to the safety factor of each inspected drug in the inspected drug sequence.

[0103] Step S1003: The drug features of each drug in the drug sequence and the conflict features of each conflicting drug in the conflicting drug sequence are combined into a training sample set, and the training sample set is used to train and construct a medication inspection model.

[0104] Specifically, based on the drug features of each drug in the drug sequence of each medication of the user and the conflict features of each conflicting drug in the corresponding associated conflicting drug sequence, the comprehensive overall medication features of the user are reflected. In the embodiment of the present invention, the drug features of each drug in the drug sequence and the conflict features of each conflicting drug in the conflicting drug sequence can also form a training sample set, and use the training sample set to train a predefined medication inspection model. After the training converges, a trained medication inspection model with medication inspection capabilities is obtained.

[0105] Step S1004: input the characteristics of the drug to be inspected into the medication inspection model, use the medication inspection model to search for similar training samples that are similar to the characteristics of the drug to be inspected, and output conflicting drugs of the drug to be inspected based on the similar training samples.

[0106] Specifically, based on the above-trained medication inspection model, the characteristics of the inspected drugs are input into the medication inspection model. The medication inspection model learns the medication inspection capability based on the training sample set, searches for similar training samples with similar characteristics to the inspected drugs, and outputs the conflicting drugs corresponding to the inspected drugs based on the conflicting characteristics in the similar training samples.

[0107] The embodiment of the present invention adopts a machine learning model method to construct a medication inspection model, and the drug features of each drug in the drug sequence and the conflict features of each conflicting drug in the conflicting drug sequence are combined into a training sample set to train the medication inspection model, and then the medication inspection model is used to output the conflicting drugs for the inspection drugs, which can greatly improve the efficiency of medication inspection, and based on the iterative training capability of the medication inspection model, not only the scenario adaptability of the medication inspection method is improved, but also it is more conducive to promotion and application.

[0108] Fig.11 It is a schematic diagram of the relationship between the overall functional units of the method for medication inspection in an embodiment of the present invention. The data acquisition module is mainly responsible for obtaining the user's historical medical information and current medical information, counting the user's medication information within a specified statistical period, and generating a drug sequence and a conflicting drug sequence. The data processing module is mainly responsible for determining the drug characteristics of each drug in the drug sequence and the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence. The data analysis module is mainly responsible for converting each drug characteristic and each conflicting characteristic into each drug characteristic spectrum diagram and each conflicting characteristic spectrum diagram, and analyzing each spectrum diagram. The intelligent control module is mainly responsible for obtaining the user's inspection drugs, calling the drug sequence generation method of the data acquisition module, and generating an inspection drug sequence; calling the drug characteristic determination method of the data processing module, determining the inspection drug characteristics of each inspection drug in the inspection drug sequence; calling the characteristic spectrum diagram generation method of the data analysis module, generating an inspection drug spectrum diagram; finally, the inspection drug spectrum diagram is matched with each drug characteristic spectrum diagram and each conflicting characteristic spectrum diagram by curve overlap, and the conflicting drug is obtained according to the matching result. The control center is responsible for unified control of the execution steps of each module and the interactive communication between modules.

[0109] Fig.12 Schematic diagram of the main modules of the device for checking medication according to an embodiment of the present invention. Fig.12 As shown, the device 1200 for checking medication mainly includes a medication feature determination module 1201 , an inspection feature determination module 1202 and a conflicting medication check module 1203 .

[0110] The drug feature determination module 1201 is used to obtain the user's historical medical information and current medical information, count the user's drug information within a specified statistical period, generate a drug sequence and a conflicting drug sequence; determine the drug feature of each drug in the drug sequence and the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence, and the conflict feature of each conflicting drug in the conflicting drug sequence;

[0111] The inspection feature determination module 1202 is used to obtain the inspection drugs of the user, generate an inspection drug sequence, and determine the inspection drug feature of each inspection drug in the inspection drug sequence according to the safety factor of each inspection drug in the inspection drug sequence;

[0112] The conflicting drug checking module 1203 is used to match the characteristics of the checked drug with the characteristics of the drug and the conflicting characteristics, and find out the conflicting drugs of the checked drug.

[0113] According to one embodiment of the present invention, the device 1200 for checking medication further includes a first spectrum generating module (not shown in the figure), which is used for: after determining the drug characteristics of each drug in the drug sequence and the conflict characteristics of each conflicting drug in the conflicting drug sequence, converting each of the drug characteristics and each of the conflicting characteristics into each of the drug characteristic spectrum diagrams and each of the conflicting characteristic spectrum diagrams respectively; the device 1200 for checking medication further includes a second spectrum generating module (not shown in the figure), which is used for: after determining the inspection drug characteristics of each of the inspection drugs in the inspection drug sequence, converting the inspection drug characteristics into the inspection drug spectrum diagram; the conflicting drug checking module 1203 is further used for: performing curve overlap matching on the inspection drug spectrum diagram with each of the drug characteristic spectrum diagrams and each of the conflicting characteristic spectrum diagrams, and obtaining the conflicting drug according to the matching result.

[0114] According to another embodiment of the present invention, the conflicting drug inspection module 1203 is further used to: determine the user's drug matching features and the conflicting matching features associated with the drug matching features based on each of the drug feature spectrum graphs and each of the conflicting feature spectrum graphs; match the drug inspection spectrum graph with the spectrum graph corresponding to the drug matching features to obtain a target drug curve; search for a target conflict curve associated with the target drug curve based on the conflict matching features associated with the drug matching features; perform drug traceability on the target conflict curve to obtain conflicting drugs of the inspection drug.

[0115] According to another embodiment of the present invention, the conflicting drug checking module 1203 is further used to: extract key medication information including dosage and frequency from each of the drug characteristic spectrum graphs to generate a medication characteristic curve; extract key conflict information including dosage and frequency from each of the conflict characteristic spectrum graphs to generate a conflict characteristic curve; use each of the drug characteristics to segmentally match the medication characteristic curve to obtain medication characteristic curve segments; use each of the conflict characteristics to segmentally match the conflict characteristic curve to obtain conflict characteristic curve segments; obtain the user's drug matching characteristics and conflict matching characteristics based on the relationship information between the medication characteristic curve segments, the conflict characteristic curve segments and the pre-acquired drugs, and establish an association relationship between the drug matching characteristics and the conflict matching characteristics.

[0116] According to another embodiment of the present invention, the drug feature determination module 1201 is further used to: calculate the number of drug grades corresponding to the drug sequence and the number of conflicting drug grades corresponding to the conflicting drug sequence according to the lengths of the drug sequence and the conflicting drug sequence; determine the drug grade coefficient of each of the drugs in the drug sequence according to the number of drug grades and the safety factor of each of the drugs in the drug sequence; determine the conflict grade coefficient of each of the conflicting drugs in the conflicting drug sequence according to the number of conflicting drug grades and the safety factor of each of the conflicting drugs in the conflicting drug sequence; calculate the convolution of the drug grade coefficient and the drug sequence to obtain the drug feature of each of the drugs in the drug sequence; calculate the convolution of the conflict grade coefficient and the conflicting drug sequence to obtain the conflict feature of each of the conflicting drugs in the conflicting drug sequence.

[0117] According to another embodiment of the present invention, the device 1200 for checking medication further includes a model checking module (not shown in the figure), which is used to: form a training sample set with the drug characteristics of each drug in the drug sequence and the conflict characteristics of each conflicting drug in the conflicting drug sequence, and use the training sample set to train and construct a medication checking model; input the checked drug characteristics into the medication checking model, use the medication checking model to find similar training samples that are similar to the checked drug characteristics, and output the conflicting drugs of the checked drugs based on the similar training samples.

[0118] According to another embodiment of the present invention, the drug feature determination module 1201 is further used to: determine the drug set used by the user and the usage order of each drug in the drug set based on the user's medication information within a specified statistical period; encode each of the drugs in the drug set, and generate a drug sequence for the user within the statistical period according to the usage order; determine the conflicting drugs for each of the drugs in the drug set, and determine the arrangement order of the conflicting drugs according to the usage order of each drug in the drug set; encode each of the conflicting drugs, and generate a conflicting drug sequence for the user within the statistical period according to the arrangement order.

[0119] Fig.13 is an exemplary system architecture diagram to which embodiments of the present invention can be applied.

[0120] like Fig.13 As shown, system architecture 1300 may include terminal devices 1301, 1302, 1303, network 1304 and server 1305. Network 1304 is used to provide a medium for communication links between terminal devices 1301, 1302, 1303 and server 1305. Network 1304 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0121] Users can use terminal devices 1301, 1302, 1303 to interact with server 1305 through network 1304 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 1301, 1302, 1303, such as medication checking applications, etc. (only as an example).

[0122] The terminal devices 1301 , 1302 , and 1303 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0123] The server 1305 may be a server that provides various services, such as a background management server that provides support for medication checks performed by users using terminal devices 1301, 1302, and 1303 (for example only). The background management server may obtain the user's historical medical information and current medical information, count the user's medication information within a specified statistical period, generate a drug sequence and a conflicting drug sequence; determine the drug characteristics of each drug in the drug sequence and the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence and the conflicting drug sequence; obtain the user's inspection drugs, generate an inspection drug sequence, determine the inspection drug characteristics of each inspection drug in the inspection drug sequence according to the safety factor of each inspection drug in the inspection drug sequence; match the inspection drug characteristics with the drug characteristics and the conflicting characteristics, find out the conflicting drugs of the inspection drug, and process, and feed back the processing results (such as conflicting drugs, etc. - for example only) to the terminal device.

[0124] It should be noted that the medication checking method provided in the embodiment of the present invention is generally executed by the server 1305 , and accordingly, the medication checking device is generally disposed in the server 1305 .

[0125] It should be understood that Fig.13 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0126] Reference below Fig.14 , Fig.14 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. Fig.14 The terminal device or server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0127] like Fig.14 As shown, the computer system 1400 includes a central processing unit (CPU) 1401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1402 or a program loaded from a storage part 1408 into a random access memory (RAM) 1403. In the RAM 1403, various programs and data required for the operation of the system 1400 are also stored. The CPU 1401, the ROM 1402, and the RAM 1403 are connected to each other through a bus 1404. An input / output (I / O) interface 1405 is also connected to the bus 1404.

[0128] The following components are connected to the I / O interface 1405: an input section 1406 including a keyboard, a mouse, etc.; an output section 1407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1408 including a hard disk, etc.; and a communication section 1409 including a network interface card such as a LAN card, a modem, etc. The communication section 1409 performs communication processing via a network such as the Internet. A drive 1410 is also connected to the I / O interface 1405 as needed. A removable medium 1411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1410 as needed, so that a computer program read therefrom is installed into the storage section 1408 as needed.

[0129] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1409, and / or installed from the removable medium 1411. When the computer program is executed by the central processing unit (CPU) 1401, the above-mentioned functions defined in the system of the present invention are executed.

[0130] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0131] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0132] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor including: a drug feature determination module, a verification feature determination module and a conflict drug inspection module.

[0133] Among them, the names of these modules do not constitute a limitation of the modules themselves in certain cases. For example, the conflicting drug inspection module can also be described as "a module for matching the characteristics of the inspected drug with the characteristics of the drug and the conflicting characteristics, and finding out the conflicting drugs of the inspected drug."

[0134] On the other hand, the present invention also provides a computer-readable medium, which may be included in the device described in the embodiment; or it may exist independently and not be assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by a device, the device includes: obtaining the user's historical medical information and current medical information, counting the user's medication information within a specified statistical period, generating a drug sequence and a conflicting drug sequence; determining the drug characteristics of each drug in the drug sequence and the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence; obtaining the user's inspection drugs, generating an inspection drug sequence, and determining the inspection drug characteristics of each inspection drug in the inspection drug sequence according to the safety factor of each inspection drug in the inspection drug sequence; matching the inspection drug characteristics with the drug characteristics and the conflicting characteristics, and finding out the conflicting drugs of the inspection drugs.

[0135] The technical solution according to the embodiment of the present invention has the following advantages or beneficial effects: by obtaining the user's historical medical information and current medical information, counting the user's medication information within a specified statistical period, generating a drug sequence and a conflicting drug sequence; determining the drug characteristics of each drug in the drug sequence and the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence; obtaining the user's verified drugs, generating a verified drug sequence, and determining the verified drug characteristics of each verified drug in the verified drug sequence according to the safety factor of each verified drug in the verified drug sequence; matching the verified drug characteristics with the drug characteristics and the conflicting characteristics to find out the conflicting drugs of the verified drugs, a technical solution realizes a personalized and accurate medication inspection, and determines the conflicting drugs of the user's verified drugs based on the user's drug characteristics and the conflicting drugs extracted from the user's personal medical information, which can effectively improve the accuracy of medication inspection for individual users, thereby providing users with healthy and valuable medication guidance and better ensuring the safety of users' medication.

[0136] The specific implementation methods described herein do not constitute limitations on the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A method for checking medication, characterized in that: include: Obtain the user's historical medical information and current medical information, count the user's medication information within a specified statistical period, and generate a drug sequence and a conflicting drug sequence; determine the drug characteristics of each drug in the drug sequence and the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence; Obtain the user's checked drugs, generate a checked drug sequence, and determine the checked drug characteristics of each checked drug in the checked drug sequence according to the safety factor of each checked drug in the checked drug sequence; The characteristics of the drug to be inspected are matched with the characteristics of the drug and the conflicting characteristics to find out the conflicting drugs of the drug to be inspected.

2. The method according to claim 1, characterized in that After determining the drug characteristics of each drug in the drug sequence and the conflict characteristics of each conflicting drug in the conflicting drug sequence, the method further includes: Convert each of the drug features and each of the conflict features into a drug feature spectrum graph and a conflict feature spectrum graph respectively; After determining the drug characteristics of each drug in the drug sequence, the method further includes: Converting the drug inspection feature into a drug inspection frequency spectrum; The step of matching the drug feature to be inspected with the drug feature and the conflict feature to find out the conflicting drug of the drug to be inspected includes: The checked drug spectrum graph is matched with each of the drug characteristic spectrum graphs and each of the conflicting characteristic spectrum graphs by curve overlap, and the conflicting drug is obtained according to the matching result.

3. The method according to claim 2, characterized in that The drug inspection spectrum is matched with each of the drug characteristic spectrums and each of the conflict characteristic spectrums, and the conflicting drug is obtained according to the matching result, including: Determine the drug matching feature of the user and the conflict matching feature associated with the drug matching feature according to each of the drug feature spectrum graphs and each of the conflict feature spectrum graphs; Matching the drug inspection spectrum with the spectrum corresponding to the drug matching feature to obtain a target drug curve; searching, according to the conflict matching feature associated with the drug matching feature, for a target conflict curve associated with the target drug curve; The target conflict curve is subjected to drug traceability to obtain conflicting drugs of the inspected drugs.

4. The method according to claim 3, characterized in that Determining the drug matching feature of the user and the conflict matching feature associated with the drug matching feature according to each of the drug feature spectrum graphs and each of the conflict feature spectrum graphs includes: Extracting key medication information including dosage and frequency from each of the drug characteristic spectrum graphs to generate a medication characteristic curve; extracting key conflict information including dosage and frequency from each of the conflict characteristic spectrum graphs to generate a conflict characteristic curve; Using each of the drug features to perform segmented matching on the medication characteristic curve to obtain medication characteristic curve segments; using each of the conflict features to perform segmented matching on the conflict characteristic curve to obtain conflict characteristic curve segments; According to the relationship information between the medication characteristic curve segment, the conflict characteristic curve segment and the pre-acquired drugs, the drug matching feature and the conflict matching feature of the user are obtained, and an association relationship between the drug matching feature and the conflict matching feature is established.

5. The method according to claim 1, characterized in that: Determining drug characteristics of each drug in the drug sequence and conflict characteristics of each conflicting drug in the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence includes: According to the lengths of the drug sequence and the conflicting drug sequence, the number of drug grades corresponding to the drug sequence and the number of conflicting drug grades corresponding to the conflicting drug sequence are calculated; Determining a drug classification coefficient of each drug in the drug sequence according to the number of drug classifications and the safety factor of each drug in the drug sequence; Determining the conflict grading coefficient of each conflicting drug in the conflicting drug sequence according to the number of conflicting drug gradings and the safety factor of each conflicting drug in the conflicting drug sequence; Calculating the convolution of the drug classification coefficient and the drug sequence to obtain drug characteristics of each drug in the drug sequence; The convolution of the conflict grading coefficient and the conflicting drug sequence is calculated to obtain the conflict characteristics of each of the conflicting drugs in the conflicting drug sequence.

6. The method according to claim 1, characterized in that The method further comprises: The drug features of each drug in the drug sequence and the conflict features of each conflicting drug in the conflicting drug sequence form a training sample set, and the training sample set is used to train and construct a medication inspection model; The characteristics of the drug to be inspected are input into the medication inspection model, the medication inspection model is used to find similar training samples similar to the characteristics of the drug to be inspected, and conflicting drugs of the drug to be inspected are output based on the similar training samples.

7. The method according to claim 1, characterized in that Collecting statistics on the medication information of the user within a specified statistical period, generating a drug sequence and a conflicting drug sequence, including: Determine the drug set used by the user and the order of use of each drug in the drug set according to the drug use information of the user in a specified statistical period, Encoding each of the drugs in the drug set, and generating a drug sequence for the user in the statistical period according to the usage order; Determining conflicting drugs for each of the drugs in the drug set, and determining an arrangement order of the conflicting drugs according to a usage order of each of the drugs in the drug set; Each of the conflicting drugs is encoded, and a conflicting drug sequence for the user within the statistical period is generated according to the arrangement order.

8. A device for checking medication, characterized in that: include: The drug feature determination module is used to obtain the user's historical medical information and current medical information, count the user's drug information within a specified statistical period, generate a drug sequence and a conflicting drug sequence; determine the drug features of each drug in the drug sequence and the conflicting features of each conflicting drug in the conflicting drug sequence according to the safety factor of each drug in the drug sequence and the conflicting drug sequence; An inspection feature determination module, used to obtain the inspection drugs of the user, generate an inspection drug sequence, and determine the inspection drug feature of each inspection drug in the inspection drug sequence according to the safety factor of each inspection drug in the inspection drug sequence; The conflicting drug checking module is used to match the characteristics of the checked drug with the characteristics of the drug and the conflicting characteristics to find out the conflicting drugs of the checked drug.

9. A mobile electronic device terminal, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images