CN116662489A - Intelligent form matching optimization method and system - Google Patents
Intelligent form matching optimization method and system Download PDFInfo
- Publication number
- CN116662489A CN116662489A CN202310927918.XA CN202310927918A CN116662489A CN 116662489 A CN116662489 A CN 116662489A CN 202310927918 A CN202310927918 A CN 202310927918A CN 116662489 A CN116662489 A CN 116662489A
- Authority
- CN
- China
- Prior art keywords
- matching
- optimization
- data
- similarity
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004458 analytical method Methods 0.000 claims abstract description 103
- 238000012544 monitoring process Methods 0.000 claims abstract description 48
- 238000013507 mapping Methods 0.000 claims abstract description 31
- 230000002159 abnormal effect Effects 0.000 claims description 42
- 230000003993 interaction Effects 0.000 claims description 27
- 230000000737 periodic effect Effects 0.000 claims description 18
- 230000004044 response Effects 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 13
- 238000011156 evaluation Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 230000006978 adaptation Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 8
- 230000001419 dependent effect Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 2
- 238000011282 treatment Methods 0.000 description 26
- 239000003814 drug Substances 0.000 description 10
- 229940079593 drug Drugs 0.000 description 9
- 239000000955 prescription drug Substances 0.000 description 5
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 229940126532 prescription medicine Drugs 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000000857 drug effect Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000011269 treatment regimen Methods 0.000 description 2
- 206010002199 Anaphylactic shock Diseases 0.000 description 1
- 208000019872 Drug Eruptions Diseases 0.000 description 1
- 208000031226 Hyperlipidaemia Diseases 0.000 description 1
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 208000026350 Inborn Genetic disease Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 208000026935 allergic disease Diseases 0.000 description 1
- 230000007815 allergy Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 208000016361 genetic disease Diseases 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013215 result calculation Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 230000008054 signal transmission 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application relates to the technical field of electric digital data processing, and provides an intelligent form matching optimization method and system, wherein the method comprises the following steps: dividing words of the user file based on TF-IDF inverse document word frequency, and constructing multidimensional similarity analysis characteristics; constructing a form matching model; inputting the multidimensional similarity analysis characteristics into a form matching model, and outputting a grading scheme set; selecting and identifying the scoring scheme set, establishing a mapping relation between a selected result and multidimensional similarity analysis characteristics, and selecting a reason identifier; and inputting the continuous monitoring data, the selected reason identifier and the mapping relation into an optimization matching unit, and performing model feedback optimization on the form matching model. The method and the device can solve the problem that the form matching is dependent on a fixed database when the form is matched in the prior art, so that the optimization of the matching process cannot be accurately performed, and the matching degree of a user and the form can be improved.
Description
Technical Field
The application relates to the technical field of electric digital data processing, in particular to an intelligent form matching optimization method and system.
Background
In an automatic form matching system, the form matching of a user is usually performed according to a constructed form database, so that the working efficiency can be improved, and the probability of abnormal form opening risks caused by experience problems can be reduced. However, since the form database constructed at present is fixed, the form database cannot be optimized and adjusted according to the user's own situation, and the form matched through the form database is easily not adapted to the user.
In summary, when form matching is performed in the prior art, there is a problem that form matching is performed depending on a fixed database, so that optimization of a matching process cannot be performed accurately.
Disclosure of Invention
Based on this, it is necessary to provide an intelligent form matching optimization method and system for solving the above technical problems.
An intelligent form matching optimization method, the method comprising: the method comprises the steps of connecting a data interaction unit, reading and constructing a user file based on user basic information, wherein the user file comprises a data characteristic identifier; dividing words of the user file based on TF-IDF inverse document word frequency, and constructing multidimensional similarity analysis characteristics according to word division results; acquiring past user interaction data, and carrying out data identification on the past user interaction data to construct a form matching model; inputting the multidimensional similarity analysis features into the form matching model, scoring cosine similarity through a similarity analysis unit of the form matching model, and outputting a scoring scheme set; selecting and identifying the scoring scheme set, establishing a mapping relation between a selected result and multidimensional similar analysis characteristics, and selecting a reason identifier; and continuously monitoring the user to obtain continuous monitoring data, inputting the continuous monitoring data, the selected reason identifier and the mapping relation into an optimization matching unit, and performing model feedback optimization on the form matching model, wherein the optimization matching unit is an optimization unit of the form matching model.
In one embodiment, further comprising: extracting user response data information from the continuous monitoring data; constructing user body basic characteristics through the user basic information; evaluating the fitness of the user through the response data information and the body basic characteristics; and generating stability feedback data through the adaptation degree evaluation result, inputting the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
In one embodiment, further comprising: obtaining a dosing feedback cycle node based on the selected result; constructing a test window through the administration feedback period node; acquiring user monitoring data in a detection window according to the continuous monitoring data, and generating periodic feedback data according to the user monitoring data; and inputting the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
In one embodiment, further comprising: counting the abnormal reaction frequency and the abnormal reaction degree of the user according to the continuous monitoring data to obtain an abnormal counting result; taking the abnormal statistical result as abnormal feedback data; and inputting the abnormal feedback data, the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
In one embodiment, the cosine similarity scoring by the similarity analysis unit of the form matching model, and outputting a scoring scheme set includes: performing similarity matching analysis through a cosine similarity algorithm to generate a first similarity matching analysis result; carrying out similarity analysis through a Jaccard similarity coefficient algorithm to generate a second similarity matching analysis result; and carrying out result merging and sorting on the first similar matching analysis result and the second similar matching analysis result, and outputting the scoring scheme set through the result merging and sorting.
In one embodiment, further comprising: setting a similarity constraint threshold; judging whether the highest similarity result in the result merging and sorting meets the similarity constraint threshold; when the similarity constraint threshold cannot be met, a null value is output.
In one embodiment, further comprising: the calculation formula of the first similarity matching analysis result is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein A represents one dimension characteristic in the multi-dimension similar analysis characteristic, B represents one dimension characteristic of a database in the form matching model, n represents the number of dimension characteristics, and i represents any one data of 1-n.
An intelligent form matching optimization system comprising:
the user file reading module is used for connecting the data interaction unit and reading and constructing a user file based on the user basic information, wherein the user file comprises a data characteristic identifier;
the multidimensional similarity analysis feature construction module is used for word segmentation of the user file based on TF-IDF inverse document word frequency and constructing multidimensional similarity analysis features according to word segmentation results;
the form matching model construction module is used for collecting past user interaction data, carrying out data identification on the past user interaction data and constructing a form matching model;
the cosine similarity scoring module is used for inputting the multidimensional similarity analysis features into the form matching model, scoring the cosine similarity through a similarity analysis unit of the form matching model and outputting a scoring scheme set;
the selected reason identification module is used for carrying out selected identification on the scoring scheme set, establishing a mapping relation between a selected result and the multidimensional similarity analysis characteristic and carrying out selected reason identification;
and the model feedback optimization module is used for continuously monitoring the user to obtain continuous monitoring data, inputting the continuous monitoring data, the selected reason identifier and the mapping relation into the optimization matching unit, and performing model feedback optimization on the form matching model, wherein the optimization matching unit is an optimization unit of the form matching model.
The intelligent form matching optimization method and system can solve the problem that the form matching is dependent on a fixed database when the form is matched in the prior art, so that the matching process cannot be optimized accurately. Firstly, word segmentation is carried out on a user file to obtain multidimensional similarity analysis characteristics; then, carrying out similarity scoring on a similarity analysis unit of a form matching model according to the multidimensional similarity analysis characteristics, and obtaining a scoring scheme set according to a similarity scoring result; selecting the scoring scheme set, selecting the reason identifier, establishing a mapping relation between a selected result and the multidimensional similarity analysis characteristic, and improving the adaptation degree of the form scheme and the user file by scheme selection; continuously monitoring the real-time condition of a user, and obtaining stability feedback data, periodic feedback data and abnormal feedback data according to a monitoring result; and finally, inputting the abnormal feedback data, the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into an optimization unit of the form matching model to perform feedback optimization on the model, so that the matching degree of a user and the form can be improved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic flow chart of an intelligent form matching optimization method;
FIG. 2 is a schematic flow chart of an output scoring schema set in an intelligent form matching optimization method;
FIG. 3 is a schematic flow chart of generating stability feedback data in an intelligent form matching optimization method;
FIG. 4 is a schematic diagram of an intelligent form matching optimization system.
Reference numerals illustrate: the system comprises a user file reading module 1, a multidimensional similarity analysis characteristic construction module 2, a form matching model construction module 3, a cosine similarity scoring module 4, a selected cause identification module 5 and a model feedback optimization module 6.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
As shown in fig. 1, the present application provides an intelligent form matching optimization method, which includes:
step S100: the method comprises the steps of connecting a data interaction unit, reading and constructing a user file based on user basic information, wherein the user file comprises a data characteristic identifier;
specifically, the method provided by the application is used for optimizing the form matching process, wherein the form matching refers to the construction of a form matching database based on the historical demand and the historical form data, and the similarity matching is carried out through the form matching database according to the existing demand, so that one or more forms with highest similarity are obtained. The application area of form matching is relatively wide, for example: the method can be applied to various aspects of factory material purchase forms, product manufacturing requirement analysis forms, company account reimbursement forms, hospital prescription forms and the like, wherein the hospital prescription forms have the highest use frequency. In the present application, the present embodiment is mainly described by specific application of a hospital prescription form for the convenience of understanding by those skilled in the art.
The specific implementation process of the intelligent form matching optimization method provided by the application is realized by an intelligent form matching optimization system. The data interaction unit is used for performing data interaction between the form matching database and the user, for example: the data interaction unit which is intelligently matched with the hospital prescription form is used for carrying out information interaction among the hospital prescription database, the main doctor and the patient, and the data interaction unit carries out data interaction with the intelligent form matching optimization system through the signal transmission module.
Firstly, the data interaction unit is connected through the intelligent form matching optimizing system, and the user refers to a user to be subjected to form matching, for example: patient patients to be subjected to rehabilitation prescription matching in hospitals and the like, and relevant data reading is performed according to basic information of users, so as to construct user files, wherein the user files refer to recorded data of relevant information of the users, such as: patient case, etc., wherein the user profile includes a data characteristic identification, which refers to information characteristics contained in the user profile, such as: in the case of a patient, it may refer to the identification of the patient's different disease types, including patient gender, age, complaints, current medical history, genetic history, past history, diagnosis, physical examination, common diseases, etc. By constructing the patient cases, the disease information of the patient can be clearly and accurately obtained, and the original data is provided for the next analysis of the patient cases.
Step S200: dividing words of the user file based on TF-IDF inverse document word frequency, and constructing multidimensional similarity analysis characteristics according to word division results;
specifically, the user file is segmented through TF-IDF inverse document word frequency, the word segmentation refers to counting and extracting words or phrases that occur frequently in the user file and occur rarely in other articles, and multi-dimensional similarity analysis features are constructed according to the word segmentation result, and the multi-dimensional similarity analysis features refer to a plurality of word segmentation features in the user file, such as: information such as hypertension and hyperlipidemia in the patient case. By word segmentation of the user file, the key information of the patient cases in the user file can be extracted, the data analysis efficiency can be improved, and support is provided for data retrieval of the next step of history similar forms.
Step S300: acquiring past user interaction data, and carrying out data identification on the past user interaction data to construct a form matching model;
specifically, the interactive data of the past user is collected, where the interactive data refers to the historical form data of the past user, for example: patient treatment data, wherein the treatment data includes past patient cases and past treatment regimens. And then carrying out data identification on the past user interaction data, and constructing a form matching model according to a data identification result. For example: the method comprises the steps of carrying out data type identification on previous cases and previous treatment schemes of previous patients, constructing a form matching model according to previous patient treatment data, wherein the form matching model is used for carrying out prescription matching on the patients, is a medical expert database combining artificial intelligence and a database, comprises a prescription matching unit, a similarity analysis unit and an optimization unit, stores a large number of previous patient cases and previous treatment schemes, can carry out judgment and decision through simulating thinking modes of experts in the human medical field, and can be updated through continuous learning.
By constructing the form matching model, the risk of form opening abnormality caused by experience problems of a form responsible person can be reduced, and the efficiency and accuracy of form matching are improved.
Step S400: inputting the multidimensional similarity analysis features into the form matching model, scoring cosine similarity through a similarity analysis unit of the form matching model, and outputting a scoring scheme set;
as shown in fig. 2, in one embodiment, the step S400 of the present application further includes:
step S410: performing similarity matching analysis through a cosine similarity algorithm to generate a first similarity matching analysis result;
in one embodiment, step S410 of the present application further includes:
step S411: the calculation formula of the first similarity matching analysis result is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein A represents one dimension characteristic in the multi-dimension similar analysis characteristic, B represents one dimension characteristic of a database in the form matching model, n represents the number of dimension characteristics, and i represents any one data of 1-n.
Specifically, the multidimensional similarity analysis feature is input into the form matching model, and cosine similarity scoring is performed by a similarity analysis unit of the form matching model, for example: in the form matching model, inputting the multi-dimensional similarity analysis characteristics into a prescription matching unit of the form matching model for prescription matching, wherein the prescription matching refers to case information and treatment schemes of a plurality of past similar patients meeting the conditions are searched out from the prescription matching unit according to the multi-dimensional similarity analysis characteristics. And scoring the similarity of the plurality of treatment schemes by a similarity analysis unit of the form matching model.
Firstly, carrying out similarity matching analysis on the treatment schemes through a cosine similarity algorithm to generate a first similarity matching analysis result, wherein the calculation formula of the first similarity matching analysis result is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein->And (3) representing a first similarity matching analysis result, wherein A represents one dimension characteristic in the multidimensional similarity analysis characteristics, B represents one dimension characteristic of a database in the form matching model, n represents the number of dimension characteristics, and i represents any one data of 1-n. For example, the dimensions given for each sample include gender, age, complaints, current medical history, past history, disease diagnosis, physical constitutionAnd (5) checking. Calculated by comparing two samplesThe value represents the similarity of two samples, and the calculated similarity value ranges from [ -1,1]The closer the value is to 1, the higher the representative similarity.
Step S420: carrying out similarity analysis through a Jaccard similarity coefficient algorithm to generate a second similarity matching analysis result;
specifically, similarity analysis is performed on the multiple treatment schemes through a Jaccard similarity coefficient algorithm, and a second similar matching analysis result is generated, wherein the calculation formula of the second similar matching analysis result is as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein->Representing a second similarity analysis result, wherein A represents one dimension characteristic in the multidimensional similarity analysis characteristic, B represents one dimension characteristic of a database in the form matching model, j represents any one characteristic data in the dimension characteristic, a jaccard value calculated by comparing two samples represents the similarity of the two samples, and the calculated value ranges from [0,1]The closer the value is to 1, the higher the representative similarity.
Step S430: and carrying out result merging and sorting on the first similar matching analysis result and the second similar matching analysis result, and outputting the scoring scheme set through the result merging and sorting.
In one embodiment, step S430 of the present application further includes:
step S431: setting a similarity constraint threshold;
step S432: judging whether the highest similarity result in the result merging and sorting meets the similarity constraint threshold;
step S433: when the similarity constraint threshold cannot be met, a null value is output.
Specifically, the first similar matching analysis result and the second similar matching analysis result are ranked according to the similarity value from large to small, and a matching analysis result sequence is obtained. A similarity constraint threshold is set, which can be custom set by those skilled in the art based on actual conditions, typically setting the similarity constraint threshold to 50%.
Judging the highest similarity result in the matching analysis result sequence according to the similarity constraint threshold, when the highest similarity result is smaller than the similarity constraint threshold, outputting a scoring scheme set as a null value, and when the highest similarity result is larger than or equal to the similarity constraint threshold, outputting the scoring scheme set according to the output quantity of preset scoring schemes, wherein the scoring scheme set comprises a plurality of scoring schemes and corresponding similarity results. The output number of the preset scoring schemes can be set by a person skilled in the art in a user-defined manner according to practical situations, for example: and when the output number of the preset scoring schemes is 3, outputting the scheme with the top 3 similarity ranks in the matching analysis result sequence to obtain the scoring scheme set. And carrying out similar matching analysis on the treatment schemes by a cosine similarity algorithm and a Jaccard similarity coefficient algorithm, carrying out result merging and sorting on similar matching analysis results, and outputting the scoring scheme set by the result merging and sorting, so that the accuracy of the scoring scheme set output can be improved.
Step S500: selecting and identifying the scoring scheme set, establishing a mapping relation between a selected result and multidimensional similar analysis characteristics, and selecting a reason identifier;
specifically, the scoring scheme set is sent to a form responsible person through the data interaction unit to perform scheme selection identification, for example: a prescription regimen selection identification is made by the attending physician, which refers to determining by the attending physician which regimen of the set of scoring regimens is the first treatment regimen and the selected reason needs to be noted.
And then establishing a mapping relation between the selected result and the multidimensional similarity analysis feature. For example: the scoring set is 3 treatment schemes, and the corresponding similarity results are respectively 0.93, 0.90 and 0.87. The treatment scheme with the similarity result of 0.93 is found to be too strong to be matched with the physique of a patient after the evaluation of the scheme by an attending physician, so that the treatment scheme with the similarity result of 0.90 is determined as a first treatment scheme, and the selected reason is marked as mild in medication and is more suitable for the physique of the patient. By selecting the identification, the adaptation degree of the form scheme and the user can be improved.
Step S600: and continuously monitoring the user to obtain continuous monitoring data, inputting the continuous monitoring data, the selected reason identifier and the mapping relation into an optimization matching unit, and performing model feedback optimization on the form matching model, wherein the optimization matching unit is an optimization unit of the form matching model.
As shown in fig. 3, in one embodiment, the step S600 of the present application further includes:
step S610: extracting user response data information from the continuous monitoring data;
step S620: constructing user body basic characteristics through the user basic information;
step S630: evaluating the fitness of the user through the response data information and the body basic characteristics;
step S640: and generating stability feedback data through the adaptation degree evaluation result, inputting the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
Specifically, the patient is treated according to the first treatment scheme, and the physical condition of the patient during treatment is continuously monitored, so as to obtain continuous monitoring data, wherein the continuous monitoring data comprises medication response information, abnormal response information, physical rehabilitation condition and the like. And extracting user response data information from the continuous monitoring data, wherein the user response data information refers to patient medication response information, and the patient medication response information refers to response of patients after taking prescription drugs, and comprises allergy, drug fever, drug rash, shock and the like.
And constructing user body basic characteristics through the user basic information, wherein the user body basic characteristics comprise characteristics of gender, age, physical examination, genetic diseases and the like. And carrying out the matching degree evaluation of the prescription drug and the patient according to the drug response information and the body basic characteristics, wherein the matching degree evaluation refers to the response of the prescription drug to the patient after taking the prescription drug, and the matching degree of the prescription drug to the patient is judged by combining the self information of the patient, and the stability feedback data is generated according to the matching degree evaluation result. For example: when the drug effect is strong, if the physical quality of the patient is good and the body can bear the side effect of the drug, the stability is good, and if the physical quality of the patient is poor and the side effect of the drug effect cannot be born, the stability is poor. By generating stability feedback data, the degree of patient compliance with the prescribed medication can be ascertained.
In one embodiment, step S600 of the present application further includes:
step S650: obtaining a dosing feedback cycle node based on the selected result;
step S660: constructing a test window through the administration feedback period node;
step S670: acquiring user monitoring data in a detection window according to the continuous monitoring data, and generating periodic feedback data according to the user monitoring data;
step S680: and inputting the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
Specifically, according to the first treatment scheme, a taking feedback period node is obtained, wherein the taking feedback period node refers to a feedback period node of taking medicine by a patient, and the taking feedback period node is generally a treatment course feedback and is not limited to the specific performance of a certain day. Constructing a test window according to the administration feedback period node, wherein the test window refers to specific test time, for example: in the process of taking prescription medicines by patients, one course of taking the prescription medicines is 7 days, the inspection window is the 7 th N day of taking the medicines, wherein N is an integer greater than or equal to 1. And extracting the continuous monitoring data according to the inspection window to obtain patient monitoring data in the inspection window, evaluating the effect of taking the prescription medicine by the patient at a treatment course node according to the patient monitoring data, and generating periodic feedback data. By generating the periodic feedback data, the physical condition of the patient at each course of treatment node during the administration of the prescribed medication can be intuitively represented.
In one embodiment, step S600 of the present application further includes:
step S690: counting the abnormal reaction frequency and the abnormal reaction degree of the user according to the continuous monitoring data to obtain an abnormal counting result;
step S6100: taking the abnormal statistical result as abnormal feedback data;
step S6110: and inputting the abnormal feedback data, the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
Specifically, according to the continuous monitoring data, the abnormal reaction frequency and the abnormal reaction degree of the patient are counted, and an abnormal statistical result is obtained, wherein the abnormal statistical result comprises the abnormal reaction frequency and the abnormal reaction degree. And using the abnormal statistical result as abnormal feedback data, and obtaining the abnormal feedback data to determine the abnormal condition of the patient during the taking of the prescription medicine. And finally, inputting the abnormal feedback data, the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into an optimization matching unit of the form matching model to perform model feedback optimization. The method solves the problem that the form matching is dependent on a fixed database when the form is matched in the prior art, so that the optimization of the matching process cannot be accurately performed, and the matching degree of a user and the form can be improved by constructing an optimization matching unit to optimize the form matching model.
In one embodiment, as shown in FIG. 4, an intelligent form matching optimization system is provided, comprising: a user file reading module 1, a multidimensional similarity analysis feature construction module 2, a form matching model construction module 3, a cosine similarity scoring module 4, a selected cause identification module 5 and a model feedback optimization module 6, wherein:
the user file reading module 1 is used for connecting a data interaction unit, reading and constructing a user file based on user basic information, wherein the user file comprises a data characteristic identifier;
the multidimensional similar analysis feature construction module 2 is used for dividing the user file based on the TF-IDF inverse document word frequency and constructing multidimensional similar analysis features according to the word division result;
the form matching model construction module 3 is used for collecting past user interaction data, carrying out data identification on the past user interaction data and constructing a form matching model;
the cosine similarity scoring module 4 is used for inputting the multidimensional similarity analysis features into the form matching model, scoring the cosine similarity through a similarity analysis unit of the form matching model and outputting a scoring scheme set;
the selected reason identification module 5 is used for carrying out selected identification on the scoring scheme set, establishing a mapping relation between a selected result and multidimensional similar analysis characteristics and carrying out selected reason identification;
the model feedback optimization module 6 is configured to perform continuous monitoring on the user, obtain continuous monitoring data, input the continuous monitoring data, the selected reason identifier, and the mapping relationship into an optimization matching unit, and perform model feedback optimization on the form matching model, where the optimization matching unit is an optimization unit of the form matching model.
In one embodiment, the system further comprises:
the user response data information extraction module is used for extracting user response data information from the continuous monitoring data;
the user body basic feature construction module is used for constructing user body basic features through the user basic information;
the fitness evaluation module is used for evaluating the fitness of the user through the response data information and the body basic characteristics;
and the stability feedback data generation module is used for generating stability feedback data through the adaptation degree evaluation result, inputting the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
In one embodiment, the system further comprises:
the taking feedback period node obtaining module is used for obtaining a taking feedback period node based on the selected result;
the test window construction module is used for constructing a test window through the administration feedback period node;
the periodic feedback data generation module is used for acquiring user monitoring data in the inspection window through the continuous monitoring data and generating periodic feedback data through the user monitoring data;
and the model optimization module is used for inputting the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit and executing model optimization.
In one embodiment, the system further comprises:
the abnormal statistical result obtaining module is used for carrying out abnormal reaction frequency and abnormal reaction degree statistics of the user through the continuous monitoring data to obtain an abnormal statistical result;
the abnormal feedback data acquisition module is used for taking the abnormal statistical result as abnormal feedback data;
the information input module is used for inputting the abnormal feedback data, the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
In one embodiment, the system further comprises:
the similarity matching analysis module is used for performing similarity matching analysis through a cosine similarity algorithm to generate a first similarity matching analysis result;
the similarity analysis module is used for carrying out similarity analysis through a Jaccard similarity coefficient algorithm to generate a second similarity matching analysis result;
and the scoring scheme set output module is used for carrying out result merging and sorting on the first similar matching analysis result and the second similar matching analysis result and outputting the scoring scheme set through the result merging and sorting.
In one embodiment, the system further comprises:
the similarity constraint threshold setting module is used for setting a similarity constraint threshold;
the highest similarity result judging module is used for judging whether the highest similarity result in the result merging and sorting meets the similarity constraint threshold or not;
and the control output module is used for outputting a null value when the similarity constraint threshold cannot be met.
In one embodiment, the system further comprises:
the first similarity matching analysis result calculation formula module refers to the calculation formula of the first similarity matching analysis result as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein A represents one dimension characteristic in the multi-dimension similar analysis characteristic, B represents one dimension characteristic of a database in the form matching model, n represents the number of dimension characteristics, and i represents any one data of 1-n.
In summary, the application provides an intelligent form matching optimization method and system, which have the following technical effects:
1. the method solves the problem that the form matching is dependent on a fixed database when the form is matched in the prior art, so that the optimization of the matching process cannot be accurately performed, and the matching degree of a user and the form can be improved by inputting abnormal feedback data, treatment course feedback data, stability feedback data, a selected reason identifier and a mapping relation into an optimization matching unit of the form matching model to perform model feedback optimization of the form matching model.
2. By constructing the form matching model, the risk of form opening abnormality caused by experience problems of a form responsible person can be reduced, and the efficiency and accuracy of form matching are improved.
3. And carrying out similarity matching analysis on the plurality of list schemes by a cosine similarity algorithm and a Jaccard similarity coefficient algorithm, carrying out result merging and sorting on similar matching analysis results, and outputting the scoring scheme set by the result merging and sorting, so that the accuracy of the scoring scheme set output can be improved.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (8)
1. An intelligent form matching optimization method, which is characterized by comprising the following steps:
the method comprises the steps of connecting a data interaction unit, reading and constructing a user file based on user basic information, wherein the user file comprises a data characteristic identifier;
dividing words of the user file based on TF-IDF inverse document word frequency, and constructing multidimensional similarity analysis characteristics according to word division results;
acquiring past user interaction data, and carrying out data identification on the past user interaction data to construct a form matching model;
inputting the multidimensional similarity analysis features into the form matching model, scoring cosine similarity through a similarity analysis unit of the form matching model, and outputting a scoring scheme set;
selecting and identifying the scoring scheme set, establishing a mapping relation between a selected result and multidimensional similar analysis characteristics, and selecting a reason identifier;
and continuously monitoring the user to obtain continuous monitoring data, inputting the continuous monitoring data, the selected reason identifier and the mapping relation into an optimization matching unit, and performing model feedback optimization on the form matching model, wherein the optimization matching unit is an optimization unit of the form matching model.
2. The intelligent form matching optimization method of claim 1, wherein the method comprises:
extracting user response data information from the continuous monitoring data;
constructing user body basic characteristics through the user basic information;
evaluating the fitness of the user through the response data information and the body basic characteristics;
and generating stability feedback data through the adaptation degree evaluation result, inputting the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
3. The intelligent form matching optimization method of claim 2, wherein the method comprises:
obtaining a dosing feedback cycle node based on the selected result;
constructing a test window through the administration feedback period node;
acquiring user monitoring data in a detection window according to the continuous monitoring data, and generating periodic feedback data according to the user monitoring data;
and inputting the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
4. The intelligent form matching optimization method of claim 3, wherein the method comprises:
counting the abnormal reaction frequency and the abnormal reaction degree of the user according to the continuous monitoring data to obtain an abnormal counting result;
taking the abnormal statistical result as abnormal feedback data;
and inputting the abnormal feedback data, the periodic feedback data, the stability feedback data, the selected reason identifier and the mapping relation into the optimization matching unit, and executing model optimization.
5. The intelligent form matching optimization method according to claim 1, wherein the cosine similarity scoring is performed by the similarity analysis unit of the form matching model, and a scoring scheme set is output, further comprising:
performing similarity matching analysis through a cosine similarity algorithm to generate a first similarity matching analysis result;
carrying out similarity analysis through a Jaccard similarity coefficient algorithm to generate a second similarity matching analysis result;
and carrying out result merging and sorting on the first similar matching analysis result and the second similar matching analysis result, and outputting the scoring scheme set through the result merging and sorting.
6. The intelligent form matching optimization method of claim 5, wherein the method comprises:
setting a similarity constraint threshold;
judging whether the highest similarity result in the result merging and sorting meets the similarity constraint threshold;
when the similarity constraint threshold cannot be met, a null value is output.
7. The intelligent form matching optimization method of claim 6, wherein the method comprises:
the calculation formula of the first similarity matching analysis result is as follows:
；
wherein A represents one dimension characteristic in the multi-dimension similar analysis characteristic, B represents one dimension characteristic of a database in the form matching model, n represents the number of dimension characteristics, and i represents any one data of 1-n.
8. An intelligent form matching optimization system, the system comprising:
the user file reading module is used for connecting the data interaction unit and reading and constructing a user file based on the user basic information, wherein the user file comprises a data characteristic identifier;
the multidimensional similarity analysis feature construction module is used for word segmentation of the user file based on TF-IDF inverse document word frequency and constructing multidimensional similarity analysis features according to word segmentation results;
the form matching model construction module is used for collecting past user interaction data, carrying out data identification on the past user interaction data and constructing a form matching model;
the cosine similarity scoring module is used for inputting the multidimensional similarity analysis features into the form matching model, scoring the cosine similarity through a similarity analysis unit of the form matching model and outputting a scoring scheme set;
the selected reason identification module is used for carrying out selected identification on the scoring scheme set, establishing a mapping relation between a selected result and the multidimensional similarity analysis characteristic and carrying out selected reason identification;
and the model feedback optimization module is used for continuously monitoring the user to obtain continuous monitoring data, inputting the continuous monitoring data, the selected reason identifier and the mapping relation into the optimization matching unit, and performing model feedback optimization on the form matching model, wherein the optimization matching unit is an optimization unit of the form matching model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310927918.XA CN116662489A (en) | 2023-07-27 | 2023-07-27 | Intelligent form matching optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310927918.XA CN116662489A (en) | 2023-07-27 | 2023-07-27 | Intelligent form matching optimization method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116662489A true CN116662489A (en) | 2023-08-29 |
Family
ID=87724455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310927918.XA Pending CN116662489A (en) | 2023-07-27 | 2023-07-27 | Intelligent form matching optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116662489A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105912881A (en) * | 2016-06-14 | 2016-08-31 | 华南师范大学 | Individual-based treatment scheme recommendation system based on big data knowledge base |
| CN113345587A (en) * | 2021-06-16 | 2021-09-03 | 北京邮电大学 | Man-machine collaborative health case matching method and system based on chronic disease big data |
| WO2021189983A1 (en) * | 2020-10-19 | 2021-09-30 | 平安科技（深圳）有限公司 | Medical case search method and apparatus based on interactive feedback, and readable storage medium |
| CN114997181A (en) * | 2022-05-30 | 2022-09-02 | 华北电力大学 | Intelligent question-answering method and system based on user feedback correction |
-
2023
- 2023-07-27 CN CN202310927918.XA patent/CN116662489A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105912881A (en) * | 2016-06-14 | 2016-08-31 | 华南师范大学 | Individual-based treatment scheme recommendation system based on big data knowledge base |
| WO2021189983A1 (en) * | 2020-10-19 | 2021-09-30 | 平安科技（深圳）有限公司 | Medical case search method and apparatus based on interactive feedback, and readable storage medium |
| CN113345587A (en) * | 2021-06-16 | 2021-09-03 | 北京邮电大学 | Man-machine collaborative health case matching method and system based on chronic disease big data |
| CN114997181A (en) * | 2022-05-30 | 2022-09-02 | 华北电力大学 | Intelligent question-answering method and system based on user feedback correction |
Non-Patent Citations (1)
| Title |
|---|
| 徐凌杰 译: "数据中心一体化最佳实践：设计仓储级计算机 原书第3版", 湖南科学技术出版社 , pages: 23 - 24 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111986770B (en) | Prescription medication auditing method, device, equipment and storage medium | |
| CN105260598A (en) | Oral diagnosis and treatment decision support system and decision method | |
| Fang et al. | Feature Selection Method Based on Class Discriminative Degree for Intelligent Medical Diagnosis. | |
| CN105868526B (en) | The community-acquired pneumonia in children data handling system and method kept based on robust tensor | |
| CA2465706A1 (en) | Patient data mining | |
| CN101911078A (en) | Based on disease probability vector retrieval of similar patient case | |
| CN114639479A (en) | Intelligent diagnosis auxiliary system based on medical knowledge map | |
| CN110739076A (en) | medical artificial intelligence public training platform | |
| US20200058408A1 (en) | Systems, methods, and apparatus for linking family electronic medical records and prediction of medical conditions and health management | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| CN116910172B (en) | Follow-up table generation method and system based on artificial intelligence | |
| KR20200022113A (en) | Oriental medicine prescription and health coordinator service system and method | |
| KR20200022106A (en) | Oriental medicine diagnostic prescription service system and method | |
| CN117497149A (en) | Hospital management method and system based on artificial intelligence | |
| CN117037999A (en) | Intelligent treatment prescription matching method and system for hospital rehabilitation department | |
| CN111627523A (en) | Clinical nutrition diagnosis and treatment simulation system and simulation method | |
| CN109192312B (en) | Intelligent management system and method for adverse events of heart failure patients | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| KR20200022110A (en) | Oriental medicine Clinical data collection and deep learning based data analysis system | |
| CN116884612A (en) | Intelligent analysis method, device, equipment and storage medium for disease risk level | |
| CN116662489A (en) | Intelligent form matching optimization method and system | |
| CN113642669B (en) | Feature analysis-based fraud prevention detection method, device, equipment and storage medium | |
| CN114724701A (en) | Noninvasive ventilation curative effect prediction system based on superposition integration algorithm and automatic encoder | |
| CN113517044A (en) | Clinical data processing method and system for evaluating citicoline based on pharmacokinetics | |
| CN114649071A (en) | Real world data-based peptic ulcer treatment scheme prediction system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |