WO2019085464A1 - Procédé et dispositif de notation de document d'infraction, et support d'informations lisible par ordinateur - Google Patents

Procédé et dispositif de notation de document d'infraction, et support d'informations lisible par ordinateur Download PDF

Info

Publication number
WO2019085464A1
WO2019085464A1 PCT/CN2018/089430 CN2018089430W WO2019085464A1 WO 2019085464 A1 WO2019085464 A1 WO 2019085464A1 CN 2018089430 W CN2018089430 W CN 2018089430W WO 2019085464 A1 WO2019085464 A1 WO 2019085464A1
Authority
WO
WIPO (PCT)
Prior art keywords
parameter
weight
case data
model
drug
Prior art date
Application number
PCT/CN2018/089430
Other languages
English (en)
Chinese (zh)
Inventor
阮晓雯
周瑜
徐亮
肖京
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019085464A1 publication Critical patent/WO2019085464A1/fr

Links

Images

Classifications

    • 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
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
    • 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

Definitions

  • the present application relates to the field of data processing, and in particular, to a violation document scoring method, a violation document scoring device, and a computer readable storage medium.
  • the application provides a data processing method, a violation document scoring device and a computer readable storage medium for scoring and evaluating the degree of illegal use of the controlled drugs.
  • the first aspect of the present application provides a method for scoring a violation document, the method comprising the steps of:
  • the processed case data and the parameter weight, the model parameter center value, the model parameter threshold, and the key parameter are input into the evaluation model, and the evaluation model analyzes the data to obtain an evaluation score.
  • a second aspect of the present application provides a violation document scoring apparatus, the violation document scoring apparatus comprising a memory and a processor, wherein the memory stores a violation document scoring program executable on the processor, and the violation document score
  • the program implements the following steps when executed by the processor:
  • the processed case data and the parameter weight, the model parameter center value, the model parameter threshold, and the key parameter are input into the evaluation model, and the evaluation model analyzes the data to obtain an evaluation score.
  • a third aspect of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a violation document scoring program, and when the violation document scoring program is executed by a processor, the following steps are implemented: receiving a database and various levels of medical treatment All case data of the institution;
  • the processed case data and the parameter weight, the model parameter center value, the model parameter threshold, and the key parameter are input into the evaluation model, and the evaluation model analyzes the data to obtain an evaluation score.
  • the method can be used to score the documents used by the controlled drugs, and it is more convenient to obtain the level of the controlled use of the controlled drugs.
  • the processed case data and the parameter weight, the model parameter center value, the model parameter threshold, and the key parameter are input into the evaluation model, and the evaluation model analyzes the data to obtain an evaluation score.
  • the machine learning-based algorithm not only quickly obtains the violation documents, but also evaluates the violation documents, reducing the cost and improving the efficiency.
  • FIG. 1 is a schematic diagram of an optional application environment of each embodiment of the present application.
  • FIG. 2 is a schematic diagram of an optional architecture of the violation document scoring apparatus of the present application.
  • FIG. 3 is a block diagram showing an embodiment of the violation document scoring system of FIG. 2;
  • FIG. 4 is a schematic diagram of an implementation process of a first embodiment of a method for scoring a violation document according to the present application
  • FIG. 5 is a schematic diagram of an implementation process of a second embodiment of a method for scoring a violation document according to the present application
  • FIG. 6 is a schematic diagram of an implementation process for determining parameter weights in a data directed transmission method of the present application
  • FIG. 7 is a schematic diagram of an implementation process of a third embodiment of a data directional transmission method according to the present application.
  • FIG. 8 is a schematic diagram of an implementation process of a fourth embodiment of a data directional transmission method according to the present application.
  • FIG. 1 it is a schematic diagram of an optional application environment of each embodiment of the present application.
  • the present application is applicable to the application environment 1 including, but not limited to, the insurance institution 10, the medical institution 11, the network 12, and the computing terminal 13.
  • the computing terminal 13 may be a mobile device, a smart phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (tablet computer), etc., and a desktop computer, such as a desktop computer.
  • the insurance mechanism 10 and the medical institution 11 may be a server or a database for storing data
  • the server may be a computing device such as a rack server, a blade server, a tower server or a rack server, and the server may be an independent server. It can also be a server cluster composed of multiple servers.
  • the database the implementation of different professional companies are different, the main database type is Oracle, there will also be various types of databases such as PostgreSQL, MySQL.
  • the network 12 may be an intranet, an Internet, a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, Wireless or wired networks such as 5G networks, Bluetooth, Wi-Fi, and call
  • the insurance mechanism 10 and the medical institution 11 are communicatively coupled to one or more of the computing terminals 13 (only one shown) through the network 12 to enable the computing terminal 13 to pass through the network 12. Data transmission and interaction with the insurance institution 10 and the medical institution 11.
  • FIG. 2 is a schematic diagram of an optional architecture of the violation document scoring apparatus of the present application.
  • the violation document scoring device 2 may correspond to an operation terminal 13, and the violation document scoring device 2 includes a violation document scoring system 3, a memory 21, and a processor 22.
  • the memory 21 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), random access Memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • the memory 21 may be an internal storage unit of the offending document scoring device 2, such as a hard disk or memory of the offending document scoring device 2.
  • the memory 21 may also be an external storage device of the offending document scoring device 2, such as a plug-in hard disk equipped on the offending document scoring device 2, a smart memory card (SMC), Secure Digital (SD) card, Flash Card, etc.
  • the memory 21 may also include both the internal storage unit of the offending document scoring device 2 and its external storage device.
  • the memory 21 is generally used to store an operating system installed in the violation document scoring device 2 and various types of application software, such as program codes of the violation document scoring system 3, and the like. Further, the memory 21 can also be used to temporarily store various types of data that have been output or are to be output.
  • the processor 22 may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments.
  • the processor 22 is typically used to control the overall operation of the offending document scoring device 2.
  • the processor 22 is configured to run program code or process data stored in the memory 21, such as running the violation document scoring system 3 and the like.
  • FIG. 3 is a schematic diagram of a module of the illegal document scoring system 3 of FIG.
  • the violation document scoring system 3 includes an acquisition module 31, a processing module 32, an establishment module 33, a parameter configuration module 34, an analysis module 35, a storage module 36, and an output module 37.
  • the obtaining module 31 is configured to receive all case data of the database and various medical institutions.
  • the database and all the case data of the medical institutions at all levels are received, and the database is a database of the insurance institution.
  • the case data in the insurance institution database mainly includes policies and receipts, and the medical institutions at all levels include provinces, cities, districts, and others. Regional hospitals, medical centers, etc.
  • the database the implementation of different professional companies are different, the main database type is Oracle, there will also be various types of databases such as PostgreSQL, MySQL.
  • the processing module 32 is configured to process the case data.
  • the processing method may include extracting case data of a specific single disease of one or more medical institutions from the case data, where the single disease is described as diabetes.
  • Diabetes is a group of metabolic diseases characterized by high blood sugar. Hyperglycemia is caused by defects in insulin secretion or its biological effects, or both. Diabetes is a long-standing hyperglycemia, leading to chronic damage and dysfunction of various tissues, especially the eyes, kidneys, heart, blood vessels, and nerves.
  • the treatment of diabetes often uses sulfonylureas, biguanide hypoglycemic agents, insulin sensitizers and various types of insulin. Most of these drugs are controlled drugs, which have strict requirements for their use. Extracting case data for these controlled drugs and analyzing these data can provide a lot of useful information.
  • the processing manner may further include testing and classifying the case data.
  • the case data when the case data is extracted from diabetes, the case data may include the following three categories:
  • the first category information on pre-existing parameters related to diabetes patients, including parameters such as the patient's allergy medication and sensitivity, the patient's current medication, age, weight, height, kidney or liver function;
  • the second category parameters related to the current state of the body of the diabetic patient (ie, patient condition parameters), such as blood pressure, heart rate, heart rate, temperature, blood oxygen concentration, respiratory rate or ventilation frequency;
  • the third category diabetes drug parameters, the use of controlled drugs, frequency of use, cost, time of drug use, current drug, drug class, drug allergy history and sensitivity.
  • the classification of the above case data is not intended to limit the present application, and the case data of diabetes is exemplified for better explanation, and those skilled in the art may apply the classification method to other diseases, and may also The classification is adjusted, for example, the classification level can be increased, more variables can be obtained, and the like.
  • the establishing module 33 is configured to establish an evaluation model.
  • the analysis of the above three types of data has a specific manner, and the models established according to different manners are also different.
  • a scoring evaluation model for the illegal use of the controlled drug can be established, and the above three types of data can be input into the model, and the illegal use score or grade of the controlled drug can be comprehensively obtained according to the multiple aspects and multiple features, and the patient can be subjected to the score and the grade according to the score and the grade.
  • a comprehensive analysis can also provide data on the use of controlled drugs to all parties.
  • the evaluation model is established based on the following formula:
  • ⁇ i 1/(Tmax(xi)-Tmin(Xi)) is the sensitivity index, Tmax, Tmin is the Xi threshold, Wi is the weight, and Zi is the evaluation index.
  • F(x) is the result of the scoring, the range is 0-100, Y is calculated by the input parameter Xi through the threshold range of the central value; Wi corresponds to the weight of the input parameter Xi; the Sgn() function is a Boolean function, and the output is 1 in the range, crossing the boundary Output 0; A is a vector of weights, which is easy to calculate in matrix form.
  • the parameter configuration module 34 is configured to determine parameter weights, model parameter center values, model parameter thresholds, and key parameters in the evaluation model.
  • the medical raw data includes various parameters, such as the foregoing classified three types of parameters (pre-stored parameters, patient condition parameters, drug parameters), the pre-stored parameters, patient condition parameters and drug parameters as first-level parameters, each of which includes A variety of second level parameters.
  • the first level parameter and the second level parameter have different effects on patient drug use and therefore have different weights.
  • the weight obtaining method of the various parameters will be described below.
  • the analytic hierarchy process and the entropy weight method are used to assign weights to each parameter.
  • the weight of the parameters in the model is crucial for the evaluation result, and the organization of the parameters is organized hierarchically according to the category, wherein the first level data is less, so the analytic hierarchy process ( ⁇ ) is used to determine Parameter weight. Since the parameters of the second layer are more than the parameter data, it is difficult to realize the weight operation using the analytic hierarchy process and it is easy to be confused. Therefore, the entropy weight method is used to determine the weight of each parameter. Both the analytic hierarchy process and the entropy weight method determine the weight of data in a certain level of a certain class, which is the weight division of each element in the layer to the corresponding upper-level element. Starting from the root node with a weight of 100% (all weights of all parameters), the analytic hierarchy process and the entropy weight method can be used to calculate the weight of each element corresponding to the whole.
  • Y ij (Xij-min(Xi)) / (max(Xi)-min(Xi)).
  • Step 2 Find the information entropy of each index:
  • the analysis module 35 is configured to input the data output by the processing module 32 and the parameter weights in the parameter configuration module 34, the model parameter center value, the model parameter threshold, and the key parameters into the scoring evaluation model, and use the scoring evaluation model.
  • the data was analyzed to give the score F(x) of the drug used in the disease.
  • the processing module 32 extracts case data of diabetes, for example, the case data includes pre-existing parameters (age, weight, height, etc.) of the diabetic patient, physical condition parameters (blood pressure, heart rate, temperature, blood oxygen concentration, etc.) of the diabetic patient, The drug use parameters (drug use, frequency of use, cost, etc.) of diabetic patients, the above case data is of great significance for the judgment of drug use of diabetic patients.
  • the above three types of case data have different effects on the violation document score, and therefore have different weights when the above data is input into the evaluation model to calculate the violation document score, and the parameter configuration module 34 is used to determine the parameter weights and the like in the evaluation model.
  • the pre-stored parameter, the patient condition parameter and the drug parameter are used as a first-level parameter, and the pre-stored parameter includes a plurality of second-level parameters such as age, body weight, and height, and the patient condition parameter includes blood pressure and heart rate.
  • a plurality of second-order parameters such as temperature
  • the drug parameters include a plurality of second-level parameters such as the amount of the drug used, the frequency of use, and the cost.
  • the parameter configuration module 34 determines the first level parameter by means of the analytic hierarchy process, and determines the second level parameter by signing up. The specific method has been described above and will not be described here. The technician presets different parameters according to experience.
  • the analysis module 35 inputs the data output by the processing module 32 and the above parameter input.
  • the violation document scoring model calculates the score of the violation document.
  • the storage module 36 is configured to store data output by the above module.
  • the storage module 36 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), Static Random Access Memory (SRAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • the output module 37 is configured to output the scores obtained by the analysis module 35, and may also be used to output data output by other modules.
  • the output destination may be the operation terminal 13 or may be The other terminal of the computing terminal 13 connected through the network.
  • the score is a score for a drug violation, for example, the higher the score, the greater the likelihood of violating the drug.
  • the analysis module 35 may further form an analysis report according to the score, and the analysis report may include sorting of different violation documents; and may classify different scores according to the segment; and may also include analysis of key parameters. The weighting factor of the parameter is adjusted according to the input and feedback result of the new data.
  • the score and the analysis report may also be output in different manners.
  • the analysis may be sent to the device on the network by email, or may be sent by using WiFi, Bluetooth, or the like.
  • the analysis report is sent to surrounding devices.
  • FIG. 4 is a schematic diagram of an implementation process of a first embodiment of a method for scoring a violation document according to the present application.
  • the execution order of the flow diagram shown in FIG. 4 may be changed according to different requirements, and some steps may be omitted as needed.
  • step S110 all the case data of the database and the medical institutions at all levels are received.
  • the database and all the case data of the medical institutions at all levels are received, and the database is a database of the insurance institution.
  • the case data in the insurance institution database mainly includes policies and receipts, and the medical institutions at all levels include provinces, cities, districts, and others. Regional hospitals, medical centers, etc.
  • the database the implementation of different professional companies is different, the main database type is Oracle, there are also various types of databases such as PostgreSQL, MySQL.
  • step S120 the case data is processed.
  • the processing of the case data includes extracting case data of a specific single disease of one or more medical institutions from the case data, and performing test and classification, for example, the case data may be divided into the following three.
  • Class patient pre-existing parameters, patient status parameters and drug parameters.
  • step S130 an evaluation model is established.
  • the analysis of the above three types of data has a specific manner, and the models established according to different manners are also different.
  • a scoring evaluation model for the illegal use of the controlled drug can be established, and the above three types of data can be input into the model, and the illegal use score or grade of the controlled drug can be comprehensively obtained according to the multiple aspects and multiple features, and the patient can be subjected to the score and the grade according to the score and the grade.
  • a comprehensive analysis can also provide data on the use of controlled drugs to all parties.
  • Step S140 determining parameter weights, model parameter center values, model parameter thresholds, and key parameters in the evaluation model.
  • the analytic hierarchy process and the entropy weight method are used to assign weights to each parameter.
  • the weight of the parameters in the model is crucial for the evaluation result, and the organization of the parameters is organized hierarchically according to the category, wherein the first layer and the second layer have less data, so the analytic hierarchy process is used ( ⁇ ) Determine the parameter weights. Since the parameters of the second layer are more than the parameter data, it is difficult to realize the weight operation using the analytic hierarchy process and it is easy to be confused. Therefore, the entropy weight method is used to determine the weight of each parameter. Both the analytic hierarchy process and the entropy weight method determine the weight of data in a certain level of a certain class, which is the weight division of each element in the layer to the corresponding upper-level element. Starting from the root node with a weight of 100% (all weights of all parameters), the analytic hierarchy process and the entropy weight method can be used to calculate the weight of each element corresponding to the whole.
  • determining the parameter weight by the entropy weight method comprises the steps of:
  • Step 1 standardize the data, and standardize the data of each indicator
  • Step 2 Find the information entropy of each indicator: According to the definition of information entropy in information theory, the information entropy of a set of data:
  • Step S150 the processed case data and the parameter weight, the model parameter center value, the model parameter threshold, and the key parameter are input into the evaluation model, and the evaluation model analyzes the data to obtain an evaluation score.
  • FIG. 5 is a schematic flowchart of an implementation process of a second embodiment of a method for scoring a violation document according to the present application.
  • the execution order of the flow diagram shown in FIG. 5 may be changed according to different requirements, and some steps may be omitted as needed.
  • step S210 all the case data of the database and the medical institutions at all levels are received.
  • Step S220 obtaining case data of a specific disease from the case data.
  • the processing method may include extracting case data of a specific single disease of one or more medical institutions from the case data, where the single disease is described as diabetes.
  • Diabetes is a group of metabolic diseases characterized by high blood sugar.
  • Hyperglycemia is caused by defects in insulin secretion or its biological effects, or both.
  • Hyperglycemia which persists in diabetes, causes chronic damage and dysfunction of various tissues, especially the eyes, kidneys, heart, blood vessels, and nerves.
  • the treatment of diabetes often uses sulfonylureas, biguanide hypoglycemic agents, insulin sensitizers and various types of insulin. Most of these drugs are controlled drugs, which have strict requirements for their use. Extracting case data for these controlled drugs and analyzing these data can provide a lot of useful information.
  • Step S230 classifying the case data of the specific disease.
  • a first category information about patient-related pre-existing parameters, including parameters of a patient's condition, such as a history of drug allergy or sensitivity, other current current use in the patient's tissue.
  • Drug age, weight, height, kidney or liver function
  • Category 2 parameters related to the current state of the patient's body (ie, patient condition parameters), such as blood pressure, heart rate, heart rate, temperature, blood oxygen, respiratory rate or ventilation
  • patient condition parameters such as blood pressure, heart rate, heart rate, temperature, blood oxygen, respiratory rate or ventilation
  • drug parameters the amount of drug use, frequency of use, cost, time of drug use, current drug, drug class, drug allergy history and sensitivity.
  • step S240 an evaluation model is established.
  • Step S250 determining parameter weights, model parameter center values, model parameter thresholds, and key parameters in the evaluation model.
  • Step S260 the processed case data and the parameter weight, the model parameter center value, the model parameter threshold, and the key parameter are input into the evaluation model, and the evaluation model analyzes the data to obtain an evaluation score.
  • the difference between the second embodiment of the violation document scoring method shown in FIG. 5 and the first embodiment of the violation document scoring method shown in FIG. 4 is that the step S210 described in FIG. 4 performs the case data in the second embodiment.
  • the treatment is divided into two steps of obtaining case data of a specific disease and classifying the case data of the specific disease.
  • FIG. 6 is a schematic flowchart of an implementation process for determining parameter weights in the data directional transmission method of the present application.
  • the execution order of the flow diagram shown in FIG. 6 may be changed according to different requirements, and some steps may be omitted as needed.
  • step S310 the data is standardized, and the data of each indicator is standardized.
  • step S320 the information entropy of each indicator is obtained.
  • the information entropy of a set of data is based on the definition of information entropy in information theory:
  • step S330 the weights of the indicators are determined.
  • FIG. 7 is a schematic flowchart of a third embodiment of a data directional transmission method according to the present application.
  • the execution order of the flow diagram shown in FIG. 7 may be changed according to different requirements, and some steps may be omitted as needed.
  • Step S410 receiving all case data of the database and various medical institutions
  • Step S420 processing the case data
  • Step S430 establishing an evaluation model
  • Step S440 determining parameter weights, model parameter center values, model parameter thresholds, and key parameters in the evaluation model
  • Step S450 the processed case data and the parameter weight, the model parameter center value, the model parameter threshold, and the key parameter are input into the evaluation model, and the evaluation model analyzes the data to obtain an evaluation score.
  • Step S460 sorting and classifying the scored documents according to preset logic.
  • sorting and classifying the scored documents helps to improve the efficiency of the illegal document extraction.
  • step S470 the sorted and classified documents are stored.
  • storing the sorted and classified documents for subsequent calling and viewing can improve work efficiency.
  • the document may be stored in a readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), a static random access memory. (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • Step S480 outputting a document that reaches a preset score.
  • the document may be outputted in different manners.
  • the document may be sent to a device on the network by means of a mail, or may be sent to a surrounding device by means of WiFi, Bluetooth, or the like. .
  • the third embodiment of the violation document scoring method shown in FIG. 7 is different from the first embodiment of the violation document scoring method shown in FIG. 4 in that the third embodiment adds the steps of sorting and classifying the scored documents, and storing the same. Steps and steps to output the documents.
  • FIG. 8 is a schematic flowchart of a fourth embodiment of a data directional transmission method according to the present application.
  • the execution order of the flow diagram shown in FIG. 8 may be changed according to different requirements, and some steps may be omitted as needed.
  • Step S510 receiving all the case data of the database and the medical institutions at all levels.
  • step S520 the case data is processed.
  • step S530 an evaluation model is established.
  • Step S540 determining a parameter weight, a model parameter center value, a model parameter threshold, and a key parameter in the evaluation model.
  • Step S550 the processed case data and the parameter weight, the model parameter center value, the model parameter threshold, and the key parameter are input into the evaluation model, and the evaluation model analyzes the data to obtain an evaluation score.
  • Step S560 comparing and analyzing the parameter weights, and adjusting the key parameters according to the size of the parameter weights.
  • the parameter weights are analyzed to obtain key parameters for the use of the controlled drug, and the dynamic adjustment of the key parameters can be closer to the true result.
  • Step S570 storing the adjusted key parameters.
  • the key parameters may be stored in a readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • a readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • Step S580 outputting the adjusted key parameters.
  • the document may also be outputted in different manners.
  • the key parameters may be tabulated, and the key parameter table may be sent to a device on the network by email, or may be through WiFi.
  • the key parameter table is sent to the surrounding devices by means of Bluetooth or the like.
  • the difference between the violation document scoring method shown in FIG. 8 and the first embodiment violation document scoring method shown in FIG. 4 is that the fourth embodiment has three steps of steps S560, S570, and S580.
  • the method can be used to score the documents used by the controlled drugs, and it is more convenient to obtain the level of the controlled use of the controlled drugs.
  • the processed case data and the parameter weight, the model parameter center value, the model parameter threshold, and the key parameter are input into the evaluation model, and the evaluation model analyzes the data to obtain an evaluation score.
  • the machine learning-based algorithm not only quickly obtains the violation documents, but also evaluates the violation documents, reducing the cost and improving the efficiency.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and can also be implemented by hardware, but in many cases, the former is A better implementation.
  • the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Biomedical Technology (AREA)
  • Chemical & Material Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medicinal Chemistry (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

La présente invention concerne un procédé de notation de document d'infraction. Le procédé comprend les étapes consistant : à recevoir toutes les données de dossier médical provenant d'une base de données et d'institutions médicales ; à traiter les données de dossier médical ; à établir un modèle d'évaluation ; à déterminer un poids de paramètre, une valeur centrale de paramètre de modèle, un seuil de paramètre de modèle et un paramètre clé dans le modèle d'évaluation ; et à entrer les données de dossier médical traitées, le poids de paramètre, la valeur centrale de paramètre de modèle, le seuil de paramètre de modèle et le paramètre clé dans le modèle d'évaluation, de telle sorte que le modèle d'évaluation analyse les données pour obtenir un score d'évaluation. La présente invention concerne également un dispositif de notation de document d'infraction et un support d'informations lisible par ordinateur. Selon la présente invention, des documents concernant des infractions lors de l'utilisation de médicaments réglementés peuvent être notés, et il est plus pratique d'obtenir les niveaux des infractions lors de l'utilisation des médicaments réglementés.
PCT/CN2018/089430 2017-11-01 2018-06-01 Procédé et dispositif de notation de document d'infraction, et support d'informations lisible par ordinateur WO2019085464A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711059323.8 2017-11-01
CN201711059323.8A CN108022635A (zh) 2017-11-01 2017-11-01 违规单据评分方法、违规单据评分装置及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019085464A1 true WO2019085464A1 (fr) 2019-05-09

Family

ID=62080417

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/089430 WO2019085464A1 (fr) 2017-11-01 2018-06-01 Procédé et dispositif de notation de document d'infraction, et support d'informations lisible par ordinateur

Country Status (2)

Country Link
CN (1) CN108022635A (fr)
WO (1) WO2019085464A1 (fr)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108022635A (zh) * 2017-11-01 2018-05-11 平安科技（深圳）有限公司 违规单据评分方法、违规单据评分装置及计算机可读存储介质
CN109212129A (zh) * 2018-06-30 2019-01-15 湖北海纳天鹰科技发展有限公司 一种规避空气中过敏原的目的地选择方法和装置
CN109616185A (zh) * 2018-12-13 2019-04-12 平安医疗健康管理股份有限公司 检测违规开具检查项目行为的方法及相关设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105389465A (zh) * 2015-10-29 2016-03-09 徐翼 病历数据处理方法、装置以及系统
US20170006010A1 (en) * 2013-08-23 2017-01-05 Morphotrust Usa, Llc System and Method for Identity Management
CN107256426A (zh) * 2017-06-19 2017-10-17 湖北省食品药品监督检验研究院 一种基于智能算法的药品安全信心指数系统及构建方法
CN108022635A (zh) * 2017-11-01 2018-05-11 平安科技（深圳）有限公司 违规单据评分方法、违规单据评分装置及计算机可读存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104766259A (zh) * 2015-03-31 2015-07-08 华据医疗评估信息技术（北京）有限公司 一种基于单病种模型的医疗临床质量监测与评价系统
CN105279382B (zh) * 2015-11-10 2017-12-22 成都数联易康科技有限公司 一种医疗保险异常数据在线智能检测方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170006010A1 (en) * 2013-08-23 2017-01-05 Morphotrust Usa, Llc System and Method for Identity Management
CN105389465A (zh) * 2015-10-29 2016-03-09 徐翼 病历数据处理方法、装置以及系统
CN107256426A (zh) * 2017-06-19 2017-10-17 湖北省食品药品监督检验研究院 一种基于智能算法的药品安全信心指数系统及构建方法
CN108022635A (zh) * 2017-11-01 2018-05-11 平安科技（深圳）有限公司 违规单据评分方法、违规单据评分装置及计算机可读存储介质

Also Published As

Publication number Publication date
CN108022635A (zh) 2018-05-11

Similar Documents

Publication Publication Date Title
US11475143B2 (en) Sensitive data classification
US20230142594A1 (en) Application of bayesian networks to patient screening and treatment
US20190311377A1 (en) Social security fraud behaviors identification method, device, apparatus and computer-readable storage medium
WO2021218336A1 (fr) Procédé et appareil de discrimination d'informations d'utilisateur et dispositif et support de stockage lisible par ordinateur
US20190171792A1 (en) Interaction network inference from vector representation of words
US20230099864A1 (en) User profiling based on transaction data associated with a user
US10992675B2 (en) Anomaly detection using tripoint arbitration
WO2019085464A1 (fr) Procédé et dispositif de notation de document d'infraction, et support d'informations lisible par ordinateur
US10430716B2 (en) Data driven featurization and modeling
WO2021135449A1 (fr) Procédé, appareil, dispositif et support de classification de données basés sur un apprentissage profond par renforcement
WO2022062449A1 (fr) Procédé et appareil de regroupement d'utilisateurs et dispositif électronique et support de stockage
US20180210925A1 (en) Reliability measurement in data analysis of altered data sets
WO2019080428A1 (fr) Procédé d'obtention de document cible et serveur d'application
CN112634017A (zh) 远程开卡激活方法、装置、电子设备及计算机存储介质
US11928683B2 (en) Feature encoding in online application origination (OAO) service for a fraud prevention system
US11335461B1 (en) Predicting glycogen storage diseases (Pompe disease) and decision support
WO2021208700A1 (fr) Procédé et appareil de sélection de données vocales, dispositif électronique et support d'enregistrement
CN108022653B (zh) 管控药物的特征获取方法、电子装置及计算机可读存储介质
CN112183113A (zh) 基于健康医疗大数据的保险客户名单筛选方法及装置
US20230068453A1 (en) Methods and systems for determining and displaying dynamic patient readmission risk and intervention recommendation
US20230214591A1 (en) Methods and devices for generating sensitive text detectors
US20210357702A1 (en) Systems and methods for state identification and classification of text data
US9892462B1 (en) Heuristic model for improving the underwriting process
CN114566280A (zh) 用户状态预测方法、装置、电子设备及存储介质
WO2021056740A1 (fr) Système et procédé de construction de modèle linguistique, dispositif informatique et support de stockage lisible

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18872103

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25/09/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18872103

Country of ref document: EP

Kind code of ref document: A1