CN116738064A - Method and system for recommending common medicines for specific diseases and symptoms based on big data - Google Patents
Method and system for recommending common medicines for specific diseases and symptoms based on big data Download PDFInfo
- Publication number
- CN116738064A CN116738064A CN202311019401.7A CN202311019401A CN116738064A CN 116738064 A CN116738064 A CN 116738064A CN 202311019401 A CN202311019401 A CN 202311019401A CN 116738064 A CN116738064 A CN 116738064A
- Authority
- CN
- China
- Prior art keywords
- medicine
- information
- diagnosis
- type
- symptoms
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 239000003814 drug Substances 0.000 title claims abstract description 302
- 201000010099 disease Diseases 0.000 title claims abstract description 125
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 125
- 229940079593 drug Drugs 0.000 title claims abstract description 96
- 208000024891 symptom Diseases 0.000 title claims abstract description 96
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003745 diagnosis Methods 0.000 claims abstract description 158
- 238000004364 calculation method Methods 0.000 claims abstract description 35
- 230000006399 behavior Effects 0.000 claims description 35
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 238000007599 discharging Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 239000000243 solution Substances 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 229940126532 prescription medicine Drugs 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000006186 oral dosage form Substances 0.000 description 2
- ZIXXRXGPBFMPFD-UHFFFAOYSA-N 1-chloro-4-[(4-chlorophenyl)disulfanyl]benzene Chemical compound C1=CC(Cl)=CC=C1SSC1=CC=C(Cl)C=C1 ZIXXRXGPBFMPFD-UHFFFAOYSA-N 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000002552 dosage form Substances 0.000 description 1
- 239000002547 new drug Substances 0.000 description 1
- 239000000820 nonprescription drug Substances 0.000 description 1
- 239000000955 prescription drug Substances 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Medicinal Chemistry (AREA)
- Pathology (AREA)
- Software Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application discloses a general medicine recommendation method and system for special diseases and symptoms based on big data, which belongs to the field of medicine recommendation, and the scheme comprises the following steps: the newly added treatment information of the hospital is obtained regularly and stored in a pre-constructed treatment information storage library; obtaining a disease diagnosis result of each piece of diagnosis information in the diagnosis information storage library, and classifying the diagnosis information with the same disease diagnosis result into the same type; acquiring a pre-constructed medicine association degree calculation model, analyzing the usage details of all medicines in the same type of treatment information through the medicine association degree calculation model, calculating the medicine association degrees of different medicines, and generating a medicine recommendation map; acquiring a user behavior log; and comparing the operation information of the user in the medicine purchasing process with disease diagnosis results and/or actual symptoms in the diagnosis information types, and based on the comparison result, matching the type of the closest diagnosis information and pushing a medicine recommendation map. The application has the effect of improving the medication accuracy.
Description
Technical Field
The application relates to the field of medicine recommendation, in particular to a method and a system for recommending common medicines for specific diseases and symptoms based on big data.
Background
In modern society, due to the convenience of the network, when people feel uncomfortable, people can choose to purchase medicines on a network platform according to symptoms and characteristics of some common medicines, such as medicine types, medicine adaptation symptoms and the like. However, the user purchases the medicine according to symptoms, so that the problem that the medicine is not corresponding to the actual symptoms often occurs, the medicine accuracy is low, and even the medicine risk exists.
Disclosure of Invention
In order to solve the problem that the user purchases medicines according to symptoms, the problem that medicines and actual symptoms are not corresponding often occurs, the medicine use accuracy is low, and even the problem that medicine use risks exist is solved.
In a first aspect, the application provides a general medicine recommendation method for special diseases and symptoms based on big data, which adopts the following technical scheme:
a general medicine recommending method based on big data for specific diseases and symptoms,
the method comprises the steps of periodically acquiring newly added treatment information of a hospital and storing the newly added treatment information into a pre-constructed treatment information storage library, wherein the treatment information comprises disease diagnosis results, actual symptoms and drug use details;
obtaining a disease diagnosis result of each piece of diagnosis information in the diagnosis information storage library, and classifying the diagnosis information with the same disease diagnosis result into the same type;
acquiring a pre-constructed medicine association degree calculation model, analyzing the usage details of all medicines in the same type of treatment information through the medicine association degree calculation model, calculating the medicine association degrees of different medicines, and generating a medicine recommendation map;
acquiring a user behavior log, wherein the user behavior log comprises operation information of a user in a medicine purchasing process;
comparing the operation information of the user in the medicine purchasing process with disease diagnosis results and/or actual symptoms in each diagnosis information type, and matching the type of the closest diagnosis information based on the comparison result;
and pushing the medicine recommendation map according to the type of the matched treatment information.
By adopting the technical scheme, newly added treatment information of a hospital is periodically acquired, after the treatment information is acquired, disease diagnosis results of the treatment information in the treatment information storage library are classified, medicine usage details of each type of disease diagnosis results are analyzed, medicine usage situations of the same type of disease diagnosis results are judged, medicine recommendation patterns are generated, when a user behavior log is acquired, the user behavior log is analyzed, so that the type of treatment information closest to the user behavior log is matched, and medicine recommendation patterns are carried out according to the type of treatment information for users to self-reference and select.
In a specific embodiment, before the step of storing in the pre-constructed visit information repository, the method specifically comprises the following steps:
acquiring a disease diagnosis result and actual symptoms of the newly-added diagnosis information;
judging whether the number of diseases corresponding to the disease diagnosis result is unique;
if the number of the diseases corresponding to the disease diagnosis result is not unique, the newly added diagnosis information is not stored in the diagnosis information storage library;
if the number of the diseases corresponding to the disease diagnosis result is unique, acquiring historical symptom information corresponding to the disease diagnosis result, and judging whether the actual symptoms in the newly added diagnosis information are contained in the historical symptom information;
if the actual symptoms in the newly added visit information are contained in the historical symptom information, the newly added visit information is stored in a visit information storage library;
if the actual symptoms in the newly added visit information are not included in the historical symptom information, the newly added visit information is not stored in the visit information storage library.
By adopting the technical scheme, the acquired newly-increased diagnosis information can possibly have the condition that the disease diagnosis results and the actual symptoms cannot be accurately corresponding, and when a plurality of disease diagnosis results exist in the diagnosis information, a plurality of actual symptoms can also exist at the same time, and the actual symptoms cannot be corresponding to the disease diagnosis results, so that the newly-increased diagnosis information stored in the diagnosis information storage library is more accurate by selectively screening the newly-increased diagnosis information.
In a specific embodiment, the method for calculating the medicine relevance of different medicines by analyzing the usage details of all medicines in the same type of treatment information through the medicine relevance calculation model specifically includes the following steps:
acquiring all the visit information in the same type and the medicine use details in each visit information;
listing all medicines used in the visit information according to the medicine use details in each visit information;
acquiring the occurrence times of each medicine name in all the doctor information, and calculating the use frequency of each medicine;
calculating the use intensity of each medicine according to the medicine use details in each visit information;
and acquiring a pre-constructed AI algorithm, and automatically calculating the association degree of each medicine by adopting the AI algorithm according to the use frequency and the use intensity of each medicine.
By adopting the technical scheme, the frequency and the intensity of use of each medicine are calculated mainly by acquiring all the doctor information in the same type and the medicine use details in each doctor information, and the relevance of each medicine is calculated through an AI algorithm, so that a user can conveniently select the medicine with the highest relevance as the purchased medicine by checking the relevance of the medicine, and the accuracy of medicine is improved.
In a specific embodiment of the present application,
the calculation formula of the frequency of use is as follows:
f=x/y, where F is the frequency of use of a certain drug, x is the number of occurrences of the certain drug in all of the doctor information of the same type, and y is the number of all of the doctor information of the same type;
the calculation formula of the use intensity is as follows:
intensity of use = total consumption of certain drugs) 100/days of concurrent patient recovery;
number of patient receiving in the same period = number of patient discharging in the same period.
In a specific embodiment, the method for automatically calculating the association degree of each drug by using the AI algorithm specifically comprises the following steps:
acquiring the use frequency and the use intensity of all medicines in the same type;
based on the frequency of use of all medicines in the same type, performing first association calculation on all medicines, wherein the calculation formula is as follows:
z=f×k, where Z is a degree of association and k is an association coefficient;
and acquiring the association degree of all the medicaments, and carrying out secondary association degree calculation on medicaments with the same association degree according to the use intensity of each medicament.
Through adopting above-mentioned technical scheme, according to the use frequency of medicine, can preliminary calculate the association degree of medicine and same type information of seeing a doctor, the higher the use frequency is, and the association degree is also higher, follow-up again according to the use intensity of medicine, carry out the priority division to the medicine that uses the frequency the same to improve the accuracy of association degree calculation.
In a specific embodiment, the method for automatically calculating the association degree of each drug by using the AI algorithm further comprises the following steps:
acquiring the historical use frequency of each medicament, and calculating to obtain the use frequency increase rate of the medicament;
judging whether the usage frequency increase rate of the medicine is larger than a preset first increase threshold value;
if the usage frequency increase rate of the medicine is larger than a preset first increase threshold value, marking the medicine as a special medicine;
if the usage frequency increase rate of the medicine is not greater than a preset first increase threshold value; the drug is not labeled with a particular drug.
By adopting the technical scheme, the special medicine marking can be carried out on the medicines with the usage frequency increasing rate reaching the standard by calculating the usage frequency increasing rate of each medicine, and the primary recommendation is carried out when the user purchases the medicines for some new medicines with better medicine effects or new discovered old medicines with better medicine effects.
In a specific embodiment, the comparing the operation information of the user in the process of purchasing medicine with the disease diagnosis result and/or the actual symptom in each type of the doctor information, and based on the comparison result, before matching the type of the closest doctor information, specifically including the following steps:
acquiring the number of historical visit information of each type, and calculating to obtain the disease growth rate of the type;
judging whether the disease growth rate of the type is larger than a preset second growth threshold value;
if the disease growth rate of the type is greater than a preset second growth threshold, marking the type of diagnosis information as epidemic disease;
if the disease growth rate of the type is not greater than the preset second growth threshold, marking the type of visit information.
By adopting the technical scheme, the recent growth condition of each disease can be analyzed to judge whether the disease is epidemic, and for epidemic, when the behavior log of a user is analyzed, when the symptom input by the user is nearly consistent with the symptom of the epidemic, the epidemic is directly matched with the behavior log, so that the matching efficiency and accuracy are improved.
In a second aspect, the application provides a general medicine recommendation system for severe cases and symptoms based on big data, which adopts the following technical scheme:
a general drug recommendation system for big data based on specific diseases and symptoms, comprising:
the diagnosis information acquisition module: the diagnosis information acquisition module is used for periodically acquiring newly added diagnosis information of a hospital;
the diagnosis information storage module: the diagnosis information storage module is used for storing the diagnosis information acquired regularly into a pre-constructed diagnosis information storage library;
the diagnosis information classification module: the diagnosis information classification module is used for classifying the diagnosis information with the same disease diagnosis result into the same type;
and the association degree analysis module is used for: the association degree analysis module is used for acquiring a pre-constructed medicine association degree calculation model, analyzing the usage details of all medicines in the same type of treatment information through the medicine association degree calculation model, and calculating the medicine association degrees of different medicines;
medicine recommendation module: the medicine recommendation module is used for generating a medicine recommendation map according to the medicine association degrees of different medicines;
the behavior log analysis module: the behavior log analysis module is used for acquiring a user behavior log, comparing the user behavior log with disease diagnosis results and/or actual symptoms in each diagnosis information type, and matching the type of the closest diagnosis information based on the comparison result;
medicine recommendation matching module: the medicine recommendation matching module is used for pushing a medicine recommendation map according to the type of the matched treatment information.
By adopting the technical scheme, newly added treatment information of a hospital is periodically acquired, after the treatment information is acquired, disease diagnosis results of the treatment information in the treatment information storage library are classified, medicine usage details of each type of disease diagnosis results are analyzed, medicine usage situations of the same type of disease diagnosis results are judged, medicine recommendation patterns are generated, when a user behavior log is acquired, the user behavior log is analyzed, so that the type of treatment information closest to the user behavior log is matched, and medicine recommendation patterns are carried out according to the type of treatment information for users to self-reference and select.
In a third aspect, the present application provides an intelligent terminal, which adopts the following technical scheme:
an intelligent terminal comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the computer program when executed by the processor implements a general medicine recommendation method based on big data of any one of the above-mentioned diseases and symptoms.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
a computer readable storage medium comprising a readable storage medium and a computer program stored for execution on the readable storage medium, the computer program loaded and executed by a processor to implement a general pharmaceutical recommendation method for big data based on specific diseases and symptoms as described in any of the above.
In summary, the present application includes at least one of the following beneficial technical effects:
the method comprises the steps of regularly acquiring newly added treatment information of a hospital, classifying disease diagnosis results of the treatment information in a treatment information storage library after the treatment information is acquired, analyzing medicine usage details of the disease diagnosis results of each type, judging medication conditions of the disease diagnosis results of the same type, generating a medicine recommendation map, analyzing a user behavior log when the user behavior log is acquired, so as to match the type of the treatment information closest to the user behavior log, and carrying out the medicine recommendation map according to the treatment information of the type for users to select by self reference.
By calculating the use frequency growth rate of each medicine, for some new medicines with better medicine effect or new discovered old medicines with better medicine effect, special medicine marking can be carried out on medicines with the use frequency growth rate reaching the standard, and primary recommendation is carried out when a user purchases the medicines.
Drawings
Fig. 1 is a schematic diagram of the overall structure of a general medicine recommendation system based on big data for specific diseases and symptoms according to an embodiment of the present application.
Fig. 2 is an overall flow chart of a general medicine recommendation method based on big data for specific diseases and symptoms in an embodiment of the application.
Fig. 3 is a schematic flow chart of preliminary screening of newly added doctor information in an embodiment of the application.
Fig. 4 is a schematic flow chart of calculating the drug association of different drugs in the embodiment of the application.
Reference numerals illustrate:
1. the diagnosis information acquisition module; 2. the information storage module of visiting a doctor; 3. a visit information classification module; 4. the association degree analysis module; 5. a medicine recommendation module; 6. a behavior log analysis module; 7. and a medicine recommendation matching module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, embodiments of the present application will be described in further detail with reference to the accompanying drawings.
An embodiment of the application discloses a general medicine recommendation system based on big data for specific diseases and symptoms, and referring to fig. 1, the system comprises a diagnosis information acquisition module 1, a diagnosis information storage module 2, a diagnosis information classification module 3, a relevance analysis module 4, a medicine recommendation module 5, a behavior log analysis module 6 and a medicine recommendation matching module 7. Specific:
the medical treatment information acquisition module 1 is used for periodically acquiring newly-increased medical treatment information of a hospital, wherein the newly-increased medical treatment information comprises disease diagnosis results, actual symptoms and medicine use details;
the visit information storage module 2 is used for storing the newly-added visit information acquired regularly into a pre-constructed visit information storage library;
the diagnosis information classification module 3 is used for acquiring the disease diagnosis result of each diagnosis information in the diagnosis information storage library and classifying the diagnosis information with the same disease diagnosis result into the same class;
the association degree analysis module 4 is used for acquiring a pre-constructed medicine association degree calculation model, analyzing the usage details of all medicines in the same type of treatment information through the medicine association degree calculation model, and calculating the medicine association degrees of different medicines;
the medicine recommendation module 5 is used for generating a medicine recommendation map aiming at a certain type of treatment information according to the medicine association degrees of different medicines;
the behavior log analysis module 6 is used for acquiring a user behavior log, comparing the user behavior log with disease diagnosis results and/or actual symptoms in each diagnosis information type, and matching the type of the closest diagnosis information based on the comparison result;
the medicine recommendation matching module 7 is used for pushing a medicine recommendation map according to the type of the matched treatment information.
In the implementation, newly added treatment information of a hospital is periodically acquired, after the treatment information is acquired, disease diagnosis results of the treatment information in a treatment information storage library are classified, medicine usage details of each type of disease diagnosis results are analyzed, medicine use conditions of the same type of disease diagnosis results are judged, medicine recommendation patterns are generated, when a user behavior log is acquired, the user behavior log is analyzed, so that the type of the treatment information closest to the user behavior log is matched, and the medicine recommendation patterns are carried out according to the type of the treatment information for users to refer to and select by themselves.
Referring to fig. 2, another embodiment of the present application provides a general medicine recommendation method for general diseases and symptoms based on big data, comprising the steps of:
s10, periodically acquiring newly added treatment information of a hospital and storing the newly added treatment information into a pre-constructed treatment information storage library;
it should be noted that, for the newly added diagnosis information obtained periodically, since there may be a case where one diagnosis information includes a plurality of disease diagnosis results, it is necessary to perform preliminary screening on the newly added diagnosis information, and referring to fig. 3, the specific steps are as follows:
a10, obtaining disease diagnosis results and actual symptoms of newly-added diagnosis information;
a20, judging whether the number of diseases corresponding to the disease diagnosis result is unique;
if the number of the diseases corresponding to the disease diagnosis result is not unique, the newly added diagnosis information is not stored in the diagnosis information storage library;
if the number of the diseases corresponding to the disease diagnosis result is unique, acquiring historical symptom information corresponding to the disease diagnosis result, and judging whether the actual symptoms in the newly added diagnosis information are contained in the historical symptom information;
if the actual symptoms in the newly added visit information are contained in the historical symptom information, the newly added visit information is stored in a visit information storage library;
if the actual symptoms in the newly added visit information are not included in the historical symptom information, the newly added visit information is not stored in the visit information storage library.
In the embodiment of the application, the newly added diagnosis information comprises a disease diagnosis result A, a disease diagnosis result B, an actual symptom a, an actual symptom B and an actual symptom c. Wherein the symptoms of the disease diagnosis result a include an actual symptom a and an actual symptom B, and the symptoms of the disease diagnosis result B include an actual symptom c. When the diagnosis information is acquired, since the diagnosis information includes a plurality of disease diagnosis results and a plurality of actual symptoms, if the diagnosis information is stored in the diagnosis information storage, it is not possible to determine what correspondence is between the disease diagnosis results and the actual symptoms in the follow-up, and therefore, it is not necessary to store the diagnosis information in the diagnosis information storage, thereby ensuring the accuracy of the diagnosis information in the diagnosis information storage.
S20, acquiring a disease diagnosis result of each piece of diagnosis information in the diagnosis information storage library, and classifying the diagnosis information with the same disease diagnosis result into the same type;
since the physique of each individual is different, the symptoms produced are different when different individuals get the same disease. Therefore, all the doctor information in the doctor information storage library needs to be classified, and after classification is completed, all the symptoms existing under the same disease diagnosis result can be obtained, so that the follow-up medicine recommendation is facilitated.
S30, acquiring a pre-constructed medicine association degree calculation model, analyzing the usage details of all medicines in the same type of treatment information through the medicine association degree calculation model, calculating the medicine association degrees of different medicines, and generating a medicine recommendation map;
in implementation, the drug association calculation model may calculate the drug association of different drugs by analyzing the usage details of all drugs in the same type of visit information, and referring to fig. 4, specifically includes the following steps:
b10, acquiring all the doctor information in the same type and the medicine use details in each doctor information;
b20, listing all medicines used in the doctor information according to the medicine use details in each doctor information;
b30, obtaining the occurrence times of each medicine name in all the doctor information, and calculating the use frequency of each medicine;
specifically, the calculation formula of the frequency of use is as follows:
f=x/y, where F is the frequency of use of a certain drug, x is the number of occurrences of a certain drug in all of the visit information under the same type, and y is the number of all of the visit information of the same type for that drug.
B40, calculating the use intensity of each medicine according to the medicine use details in each visit information;
specifically, the calculation formula of the use intensity is as follows:
intensity of use = total consumption of certain drugs) 100/days of concurrent patient recovery;
number of patient receiving in the same period = number of patient discharging in the same period.
Wherein, the consumption of a certain drug (DDDS) = (total amount of a certain drug oral dosage form/defined daily dose of a certain drug oral dosage form (DDD)) + (total amount of a certain drug injection dose/defined daily dose of a certain drug injection dosage form (DDD)).
And B50, acquiring a pre-constructed AI algorithm, and automatically calculating the association degree of each medicament by adopting the AI algorithm according to the use frequency and the use intensity of each medicament.
In the implementation, according to the use frequency and the use intensity of each medicine, the association degree of each medicine is automatically calculated by adopting an AI algorithm, and the method specifically comprises the following steps:
c10, obtaining the use frequency and the use intensity of all the medicaments in the same type;
c20, calculating the first association degree of each medicine one by one based on the use frequency of all medicines in the same type;
the formula of the first association degree calculation is as follows:
z=f×k, Z is a degree of association, and k is an association coefficient.
The value of K includes 1 and 0. When the medicine association degree is calculated for the first time, whether the medicine is a prescription medicine is judged, if the medicine is the prescription medicine, the association coefficient is 0 when the medicine is calculated for the first time, and if the medicine is not the prescription medicine, the association coefficient is 1 when the medicine is calculated for the first time.
In implementation, when a medicine recommendation map is generated, a secondary association degree calculation is performed on a medicine with an association degree of 0, and the calculation formula is as follows:
z=f×k, z is the degree of association, and K is 1.
For the drug, the calculated association z will be marked on the item of the drug recommendation map for the drug association, and the drug will be additionally marked as the prescription drug.
And C30, acquiring the calculated association degrees of all the medicaments, and carrying out secondary association degree calculation on medicaments with the same association degree according to the use intensity of each medicament.
In the correlation calculation, the higher the frequency of use of the non-prescription drug, the higher the correlation. For some medicines with the same association degree, secondary association degree calculation is performed according to the use intensity of the medicines. The higher priority of the medicines with the same association and higher use intensity is also higher.
In another embodiment of the present application, the association degree of each drug is automatically calculated by using an AI algorithm, and the method further includes the following steps:
d10, acquiring historical use frequency of each medicament, and calculating to obtain the use frequency increase rate of the medicament;
d20, judging whether the use frequency increase rate of the medicine is larger than a preset first increase threshold value;
if the usage frequency increase rate of the medicine is larger than a preset first increase threshold value, marking the medicine as a special medicine;
if the usage frequency increase rate of the medicine is not greater than a preset first increase threshold value; the drug is not labeled with a particular drug.
In practice, there are some new drugs with better efficacy, or new discovered old drugs with better efficacy, which are used for a smaller number of times in history, but the therapeutic effect on the disease diagnosis result may be better. Thus by analysing the historical data, drugs that have increased in magnitude over the last few uses are specifically marked. The effect of representing the medicine is good and the utilization rate is high when the increase range is large, so that the medicine is marked as a special medicine for users to select.
S40, obtaining a user behavior log;
the user behavior log comprises operation information of a user in the process of purchasing medicines. Specifically, the operation information includes the own symptoms input by the user, the disease determined by the user himself, and the like.
S50, comparing operation information of a user in the medicine purchasing process with disease diagnosis results and/or actual symptoms in each diagnosis information type, and matching the type of the closest diagnosis information based on the comparison result;
in one embodiment of the application, the operation information of the user in the medicine purchasing process is compared with the disease diagnosis results in each diagnosis information type, and the disease obtained by the user is primarily judged according to the operation information of the user in the medicine purchasing process, so that the type of the closest diagnosis information is matched according to the judged disease. The manner in which the user may initially determine the resulting condition includes, but is not limited to, determining based on symptoms entered by the user.
In another embodiment of the present application, the operation information of the user performed in the process of purchasing the medicine is compared with the actual symptoms in each of the doctor information types, the symptoms input by the user are obtained according to the operation information of the user performed in the process of purchasing the medicine, one doctor information type with the highest similarity between the actual symptoms in all doctor information types and the symptoms input by the user is matched, and the doctor information type is used as the closest doctor information type.
In still another embodiment of the present application, the operation information of the user performed during the medicine purchasing process is compared with the disease diagnosis result and the actual symptoms in each of the doctor information types, and if the disease obtained by the user can be judged according to the operation information of the user performed during the medicine purchasing process, the type of the closest doctor information is matched according to the judged disease; if the disease obtained by the user cannot be judged according to the operation information of the user in the medicine purchasing process, matching one of all the diagnosis information types with the highest similarity of the actual symptoms and the symptoms input by the user according to the symptoms input by the user, and taking the diagnosis information type as the type of the closest diagnosis information.
It should be noted that, in order to improve accuracy of disease judgment, before comparing operation information performed by a user in a medicine purchasing process with disease diagnosis results and/or actual symptoms in each diagnosis information type, and based on the comparison result, matching the type of the closest diagnosis information, the method further comprises the following steps:
acquiring the number of historical visit information of each type, and calculating to obtain the disease growth rate of the type;
judging whether the disease growth rate of the type is larger than a preset second growth threshold value;
if the disease growth rate of the type is greater than a preset second growth threshold, marking the type of diagnosis information as epidemic disease;
if the disease growth rate of the type is not greater than the preset second growth threshold, marking the type of visit information.
In implementation, the recent growth condition of each disease is analyzed to judge whether the disease is epidemic, and when the behavior log of a user is analyzed, when the symptom input by the user is nearly consistent with the symptom of the epidemic, the epidemic is directly matched with the behavior log, so that the matching efficiency and accuracy are improved.
S60, pushing the medicine recommendation map according to the type of the matched treatment information.
In the implementation, a user can select the most suitable medicine for purchase by observing the medicine recommendation map, so that the accuracy of medicine use is improved, and the medicine use risk is reduced.
Based on the same inventive concept, a further embodiment of the present application also discloses a computer readable storage medium, in which at least one instruction, at least one program, a code set or an instruction set is stored, the at least one instruction, the at least one program, the code set or the instruction set being loadable and executable by a processor to implement the steps of a general-purpose medicine recommendation method based on big data of the specific diseases and symptoms provided by the above method embodiment.
The computer-readable storage medium includes, for example: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above. The specific working processes of the above-described systems, devices and units may refer to the corresponding processes in the foregoing method embodiments, which are not described herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, apparatuses and methods may be implemented in other manners, for example, the apparatus embodiments described above are merely illustrative, for example, the modules or units are divided into only one kind of logic function, and there may be other manners of dividing actually being implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk.
The foregoing embodiments are only used to describe the technical solution of the present application in detail, but the descriptions of the foregoing embodiments are only used to help understand the method and the core idea of the present application, and should not be construed as limiting the present application. Variations or alternatives, which are easily conceivable by those skilled in the art, are included in the scope of the present application.
Claims (9)
1. A general medicine recommending method based on big data for special diseases and symptoms is characterized in that,
the method comprises the steps of periodically acquiring newly added treatment information of a hospital and storing the newly added treatment information into a pre-constructed treatment information storage library, wherein the treatment information comprises disease diagnosis results, actual symptoms and drug use details;
obtaining a disease diagnosis result of each piece of diagnosis information in the diagnosis information storage library, and classifying the diagnosis information with the same disease diagnosis result into the same type;
acquiring a pre-constructed medicine association degree calculation model, analyzing the usage details of all medicines in the same type of treatment information through the medicine association degree calculation model, calculating the medicine association degrees of different medicines, and generating a medicine recommendation map;
acquiring a user behavior log, wherein the user behavior log comprises operation information of a user in a medicine purchasing process;
comparing the operation information of the user in the medicine purchasing process with disease diagnosis results and/or actual symptoms in each diagnosis information type, and matching the type of the closest diagnosis information based on the comparison result;
pushing a medicine recommendation map according to the type of the matched treatment information;
the medicine relevance calculating model is used for analyzing the usage details of all medicines in the same type of treatment information and calculating the medicine relevance of different medicines, and specifically comprises the following steps:
acquiring all the visit information in the same type and the medicine use details in each visit information;
listing all medicines used in the visit information according to the medicine use details in each visit information;
acquiring the occurrence times of each medicine name in all the doctor information, and calculating the use frequency of each medicine;
calculating the use intensity of each medicine according to the medicine use details in each visit information;
and acquiring a pre-constructed AI algorithm, and automatically calculating the association degree of each medicine by adopting the AI algorithm according to the use frequency and the use intensity of each medicine.
2. The method for recommending common drugs for general diseases and symptoms based on big data according to claim 1, wherein the steps are specifically included before the steps are stored in a pre-constructed visit information repository:
acquiring a disease diagnosis result and actual symptoms of the newly-added diagnosis information;
judging whether the number of diseases corresponding to the disease diagnosis result is unique;
if the number of the diseases corresponding to the disease diagnosis result is not unique, the newly added diagnosis information is not stored in the diagnosis information storage library;
if the number of the diseases corresponding to the disease diagnosis result is unique, acquiring historical symptom information corresponding to the disease diagnosis result, and judging whether the actual symptoms in the newly added diagnosis information are contained in the historical symptom information;
if the actual symptoms in the newly added visit information are contained in the historical symptom information, the newly added visit information is stored in a visit information storage library;
if the actual symptoms in the newly added visit information are not included in the historical symptom information, the newly added visit information is not stored in the visit information storage library.
3. The method for recommending a commonly used medicine based on big data for treating diseases and symptoms according to claim 1, wherein,
the calculation formula of the frequency of use is as follows:
f=x/y, where F is the frequency of use of a certain drug, x is the number of occurrences of the certain drug in all of the doctor information of the same type, and y is the number of all of the doctor information of the same type;
the calculation formula of the use intensity is as follows:
intensity of use = total consumption of certain drugs) 100/days of concurrent patient recovery;
number of patient receiving in the same period = number of patient discharging in the same period.
4. The method for recommending common medicines for treating diseases and symptoms based on big data according to claim 3, wherein the association degree of each medicine is automatically calculated by adopting an AI algorithm, and the method specifically comprises the following steps:
acquiring the use frequency and the use intensity of all medicines in the same type;
based on the frequency of use of all medicines in the same type, performing first association calculation on all medicines, wherein the calculation formula is as follows:
z=f×k, where Z is a degree of association and k is an association coefficient;
and acquiring the association degree of all the medicaments, and carrying out secondary association degree calculation on medicaments with the same association degree according to the use intensity of each medicament.
5. The general medicine recommendation method based on big data for treating diseases and symptoms according to claim 4, wherein the association degree of each medicine is automatically calculated by adopting an AI algorithm, further comprising the following steps:
acquiring the historical use frequency of each medicament, and calculating to obtain the use frequency increase rate of the medicament;
judging whether the usage frequency increase rate of the medicine is larger than a preset first increase threshold value;
if the usage frequency increase rate of the medicine is larger than a preset first increase threshold value, marking the medicine as a special medicine;
if the usage frequency increase rate of the medicine is not greater than a preset first increase threshold value; the drug is not labeled with a particular drug.
6. The method for recommending common medicines for treating diseases and symptoms based on big data according to claim 1, wherein the comparing the operation information of the user in the process of purchasing medicines with the disease diagnosis results and/or actual symptoms in each diagnosis information type, and based on the comparison result, before matching the type of the closest diagnosis information, specifically comprising the following steps:
acquiring the number of historical visit information of each type, and calculating to obtain the disease growth rate of the type;
judging whether the disease growth rate of the type is larger than a preset second growth threshold value;
if the disease growth rate of the type is greater than a preset second growth threshold, marking the type of diagnosis information as epidemic disease;
if the disease growth rate of the type is not greater than the preset second growth threshold, marking the type of visit information.
7. A general medicine recommendation system for general diseases and symptoms based on big data, comprising:
visit information acquisition module (1): the diagnosis information acquisition module (1) is used for periodically acquiring newly added diagnosis information of a hospital;
visit information storage module (2): the diagnosis information storage module (2) is used for storing the diagnosis information acquired regularly into a pre-constructed diagnosis information storage library;
visit information classification module (3): the diagnosis information classification module (3) is used for classifying the diagnosis information with the same disease diagnosis result into the same type;
association degree analysis module (4): the association degree analysis module (4) is used for acquiring a pre-constructed medicine association degree calculation model, analyzing the usage details of all medicines in the same type of treatment information through the medicine association degree calculation model, and calculating the medicine association degrees of different medicines;
medicine recommendation module (5): the medicine recommending module (5) is used for generating a medicine recommending map according to the medicine association degrees of different medicines;
behavior log analysis module (6): the behavior log analysis module (6) is used for acquiring a user behavior log, comparing the user behavior log with disease diagnosis results and/or actual symptoms in each diagnosis information type, and matching the type of the closest diagnosis information based on the comparison result;
drug recommendation matching module (7): the medicine recommendation matching module (7) is used for pushing a medicine recommendation map according to the type of the matched treatment information.
8. An intelligent terminal, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program when executed by the processor implements a general medicine recommendation method based on big data for specific diseases and symptoms according to any one of claims 1 to 6.
9. A computer readable storage medium comprising a readable storage medium and a computer program stored for execution on said readable storage medium, said computer program being loaded and executed by a processor to implement a general pharmaceutical recommendation method for big data based on specific diseases and symptoms according to any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311019401.7A CN116738064A (en) | 2023-08-14 | 2023-08-14 | Method and system for recommending common medicines for specific diseases and symptoms based on big data |
| CN202311412990.5A CN117633340A (en) | 2023-08-14 | 2023-10-26 | Method and system for recommending common medicines for specific diseases and symptoms based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311019401.7A CN116738064A (en) | 2023-08-14 | 2023-08-14 | Method and system for recommending common medicines for specific diseases and symptoms based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116738064A true CN116738064A (en) | 2023-09-12 |
Family
ID=87910117
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311019401.7A Withdrawn CN116738064A (en) | 2023-08-14 | 2023-08-14 | Method and system for recommending common medicines for specific diseases and symptoms based on big data |
| CN202311412990.5A Pending CN117633340A (en) | 2023-08-14 | 2023-10-26 | Method and system for recommending common medicines for specific diseases and symptoms based on big data |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311412990.5A Pending CN117633340A (en) | 2023-08-14 | 2023-10-26 | Method and system for recommending common medicines for specific diseases and symptoms based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN116738064A (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109935290A (en) * | 2019-03-20 | 2019-06-25 | 杭州卓健信息科技有限公司 | A kind of drug matching system and its matching process based on big data analysis |
| CN111191020B (en) * | 2019-12-27 | 2023-09-22 | 江苏省人民医院（南京医科大学第一附属医院） | Prescription recommendation method and system based on machine learning and knowledge graph |
| CN113707261A (en) * | 2021-08-30 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Artificial intelligence-based medicine recommendation method and device and related equipment |
| JP7303517B1 (en) * | 2022-11-11 | 2023-07-05 | 株式会社Marketing Methodology&Innovation | Consultation recommendation system and consultation recommendation method |
-
2023
- 2023-08-14 CN CN202311019401.7A patent/CN116738064A/en not_active Withdrawn
- 2023-10-26 CN CN202311412990.5A patent/CN117633340A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN117633340A (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11158406B2 (en) | Automatic patient recruitment system | |
| KR102028667B1 (en) | A method, server and program for providing medical information | |
| Letterie et al. | Artificial intelligence in in vitro fertilization: a computer decision support system for day-to-day management of ovarian stimulation during in vitro fertilization | |
| CN109636623A (en) | Medical data method for detecting abnormality, device, equipment and storage medium | |
| US9378271B2 (en) | Database system for analysis of longitudinal data sets | |
| CN109637615B (en) | Method, device and equipment for judging abnormal medical prescription and readable storage medium | |
| CN109273098B (en) | Medicine curative effect prediction method and device based on intelligent decision | |
| US10242091B2 (en) | Method of knowledge extraction through data mining | |
| US20170199965A1 (en) | Medical system and method for predicting future outcomes of patient care | |
| CN109636652A (en) | Purchase monitoring method, monitoring service end and the storage medium of medicine abnormal behavior | |
| US20130275050A1 (en) | Methods and systems for integrated health systems | |
| WO2017017554A1 (en) | Reliability measurement in data analysis of altered data sets | |
| CN113643814A (en) | Health management scheme recommendation method, device, equipment and storage medium | |
| CN116246762B (en) | Prescription dose optimization method, device, equipment and medium based on artificial intelligence | |
| US20050283386A1 (en) | Method and system for marketing a treatment regimen | |
| CN116738064A (en) | Method and system for recommending common medicines for specific diseases and symptoms based on big data | |
| CN116580809A (en) | Medicine purchasing method, device and storage medium | |
| CN113066531B (en) | Risk prediction method, risk prediction device, computer equipment and storage medium | |
| Treadwell et al. | Consumer devices for patient-generated health data using blood pressure monitors for managing hypertension: systematic review | |
| CN114420257A (en) | Traditional Chinese medicine auxiliary diagnosis and treatment method, system, equipment and storage medium | |
| Heritage et al. | Integrating association rules mined from health-care data with ontological information for automated knowledge generation | |
| Baralis et al. | Personalized tag recommendation based on generalized rules | |
| CN111798948B (en) | Medical record information processing method, device, equipment and storage medium | |
| CN109559806B (en) | Abnormal hospitalization behavior judging method and related products | |
| Reps et al. | Identifying candidate risk factors for prescription drug side effects using causal contrast set mining |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230912 |