CN113704555B - Feature management method based on medical direction federal learning - Google Patents
Feature management method based on medical direction federal learning Download PDFInfo
- Publication number
- CN113704555B CN113704555B CN202110803319.8A CN202110803319A CN113704555B CN 113704555 B CN113704555 B CN 113704555B CN 202110803319 A CN202110803319 A CN 202110803319A CN 113704555 B CN113704555 B CN 113704555B
- Authority
- CN
- China
- Prior art keywords
- federal learning
- management method
- data
- feature management
- medical
- 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.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 42
- 238000013507 mapping Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000010801 machine learning Methods 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims abstract description 8
- 201000010099 disease Diseases 0.000 claims abstract description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 5
- 230000000977 initiatory effect Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/80—Information retrieval; Database structures therefor; File system structures therefor of semi-structured data, e.g. markup language structured data such as SGML, XML or HTML
- G06F16/81—Indexing, e.g. XML tags; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/80—Information retrieval; Database structures therefor; File system structures therefor of semi-structured data, e.g. markup language structured data such as SGML, XML or HTML
- G06F16/84—Mapping; Conversion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application discloses a feature management method based on medical direction federal learning, which comprises the following steps: mapping the international value range and the local value range to establish a conversion mapping relation; according to the conversion mapping relation, converting the medical data input according to the local value range into standardized data according to the international value range; setting a standard characteristic template according to the disease name aimed by the machine learning model, wherein the standard characteristic template comprises a plurality of retrieval items corresponding to international values of standardized data; retrieving and acquiring a required data index according to the retrieval items of the standard characteristic templates; and initiating a request for federal learning to train the machine learning model to other training nodes according to the selection operation of the data index. The application has the advantages of providing the characteristic management method based on medical direction federal learning, which can quickly search the characteristic data and can perform personalized setting.
Description
Technical Field
The application relates to the field of federal learning, in particular to a feature management method based on medical direction federal learning.
Background
In the near future, the medical industry will incorporate more high technologies such as artificial intelligence and sensing technology, so that the medical service is truly intelligentized, and the prosperous development of medical industry is promoted. In the great background of new medical improvement in China, intelligent medical treatment is going into the lives of ordinary people. There is a need for privacy protection of medical industry data, so when applying artificial intelligence to research, model training and data prediction in the medical field, multiple medical institutions are often required to perform in a networking and data collaboration manner.
When machine learning training is carried out on data of a medical system, feature selection is carried out on patient data in a database, the feature selection often affects training results, and the existing technical scheme cannot conveniently select and screen the features of the data, so that negative effects are brought to final model training results and federal learning results.
Disclosure of Invention
In order to solve the defects of the prior art, the application provides a feature management method based on medical direction federal learning, which comprises the following steps: a unified reference standard for data standardization is established, and is defined as an international value range; establishing a data standardized court reference standard, and defining the court reference standard as a local value range; mapping the international value range and the local value range to establish a conversion mapping relation; according to the conversion mapping relation, converting medical data input according to the local value range into standardized data according to the international value range; setting a standard characteristic template according to the disease name aimed by a machine learning model, wherein the standard characteristic template comprises a plurality of retrieval items corresponding to the international values of the standardized data; retrieving and acquiring a required data index according to the retrieval item of the standard characteristic template; and initiating a request for training a machine learning model by federal learning to other training nodes according to the selection operation of the data index.
Further, the feature management method based on medical direction federal learning further comprises the following steps: inquiring and matching the corresponding international value according to the text field input by the user; the international value and its corresponding standard field are added to the search entry of the standard feature template.
Further, the feature management method based on medical direction federal learning further comprises the following steps: setting logic relations of a plurality of search entries in the standard feature template; and generating a retrieval formula for retrieval according to the logical relation.
Further, the feature management method based on medical direction federal learning further comprises the following steps: and acquiring the data index at each federal learning node according to the international value corresponding to the search formula.
Further, the feature management method based on medical direction federal learning further comprises the following steps: modifying or adding the logic relation of a plurality of the retrieval entries in the standard characteristic template; and generating a retrieval formula for retrieval according to the logical relation.
Further, the feature management method based on medical direction federal learning further comprises the following steps: inquiring and matching the corresponding international value according to the text field input by the user; the international value and its corresponding standard field are added to a new feature template.
Further, the feature management method based on medical direction federal learning further comprises the following steps: and setting a comparison symbol for each retrieval item so as to determine the operation condition of the retrieved numerical relation.
Further, the feature management method based on medical direction federal learning further comprises the following steps: a preset threshold value is set for each retrieval entry to determine a threshold condition of the retrieved data relationship.
Further, the feature management method based on medical direction federal learning further comprises the following steps: a connection symbol is set for each of the search entries to determine a logical relationship between the search entries.
Further, the feature management method based on medical direction federal learning further comprises the following steps: generating a search formula and a search result aiming at the search formula according to all the search items; the search results include a data source, a data amount, and a data value.
The application has the advantages that: the feature management method based on medical direction federal learning can quickly search feature data and can perform personalized setting.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, are incorporated in and constitute a part of this specification. The drawings and their description are illustrative of the application and are not to be construed as unduly limiting the application. In the drawings:
FIG. 1 is a schematic diagram of the main steps of a feature management method based on medical direction federal learning according to one embodiment of the present application;
FIG. 2 is a schematic diagram of an interface for an operation of a feature management method based on medical direction federal learning in accordance with an embodiment of the present application;
FIG. 3 is a schematic diagram of a second operational interface of a feature management method based on medical direction federal learning, according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a third operational interface of a feature management method based on medical direction federal learning according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
Referring to fig. 1 to 4, the feature management method based on medical direction federal learning of the present application includes the steps of: a unified reference standard for data standardization is established, and is defined as an international value range; establishing a data standardized court reference standard, and defining the court reference standard as a local value range; mapping the international value range and the local value range to establish a conversion mapping relation; according to the conversion mapping relation, converting the medical data input according to the local value range into standardized data according to the international value range; setting a standard characteristic template according to the disease name aimed by the machine learning model, wherein the standard characteristic template comprises a plurality of retrieval items corresponding to international values of standardized data; retrieving and acquiring a required data index according to the retrieval items of the standard characteristic templates; and initiating a request for federal learning to train the machine learning model to other training nodes according to the selection operation of the data index.
As a more specific scheme, as shown in fig. 2 and 3, the international value range is formulated by setting a national standard value and a corresponding national standard value description. Specifically, the national standard value includes at least Arabic numerals and Chinese characters.
When the data is standardized, the national standard value or the corresponding national standard value description thereof can be edited or deleted, and a table file with the national standard value and the national standard value description can be imported.
More specifically, formulating the local value range includes setting a local value and a corresponding local value description. The place value includes at least an Arabic number, and the place value description includes at least a Chinese character.
As shown in fig. 2, the editing work of the international value range can be performed by an interface or an import method.
As shown in FIG. 3, the international and local value fields may be mapped by association of Chinese characters of the international and local value descriptions.
In order to facilitate the operation and inquiry of the user, the method of the application can inquire and match the corresponding international value according to the text field input by the user as shown in the interface of fig. 4; the international value and its corresponding standard field are added to the retrieved entry of the standard feature template.
To simplify the management effort, for general diseases and models, logical relationships of multiple search entries in a standard feature template may be set; a search formula for searching is generated according to the logical relation.
When data is acquired from each training node, acquiring a data index at each federal learning node according to the international value corresponding to the search formula. The data index referred to herein is data representing the location, length, and type of data, and not the data itself.
In order to realize the retrieval of the personalized feature data, the feature management method based on medical direction federal learning further comprises the following steps: modifying or adding the logic relation of a plurality of retrieval items in the standard characteristic template; a search formula for searching is generated according to the logical relation.
As an extended technical solution, in order to adapt to new model training requirements, the feature management method based on medical direction federal learning further includes the following steps: inquiring and matching the corresponding international value according to the text field input by the user; the international value and its corresponding standard field are added to a new feature template.
As a further alternative, as shown in fig. 4, a comparison symbol may be set for each search term to determine the operation condition of the numerical relationship of the search. In addition, a preset threshold may be set for each search entry to determine a threshold condition of the searched data relationship. A connection symbol is set for each search term to determine the logical relationship between the search terms. This allows more refined acquisition of the required feature data.
As a more specific aspect, the feature management method based on medical direction federal learning further includes the steps of: generating a search formula and a search result aiming at the search formula according to all the search items; the search results include a data source, a data amount, and a data value.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (7)
1. A feature management method based on medical direction federal learning is characterized by comprising the following steps:
the feature management method based on medical direction federal learning comprises the following steps:
a unified reference standard for data standardization is established, and is defined as an international value range;
establishing a data standardized court reference standard, and defining the court reference standard as a local value range;
mapping the international value range and the local value range to establish a conversion mapping relation;
according to the conversion mapping relation, converting medical data input according to the local value range into standardized data according to the international value range;
setting a standard characteristic template according to the disease name aimed by a machine learning model, wherein the standard characteristic template comprises a plurality of retrieval items corresponding to the international values of the standardized data;
retrieving and acquiring a required data index according to the retrieval item of the standard characteristic template;
initiating a request for federal learning training machine learning models to other training nodes according to the selection operation of the data index;
the feature management method based on medical direction federal learning further comprises the following steps:
inquiring and matching the corresponding international value according to the text field input by the user;
adding the international value and the corresponding standard field thereof to a retrieval entry of the standard feature template;
the feature management method based on medical direction federal learning further comprises the following steps:
setting logic relations of a plurality of search entries in the standard feature template;
generating a retrieval formula for retrieval according to the logic relation;
the feature management method based on medical direction federal learning further comprises the following steps:
and acquiring the data index at each federal learning node according to the international value corresponding to the search formula.
2. The medical direction federal learning-based feature management method according to claim 1, wherein:
the feature management method based on medical direction federal learning further comprises the following steps:
modifying or adding the logic relation of a plurality of the retrieval entries in the standard characteristic template;
and generating a retrieval formula for retrieval according to the logical relation.
3. The medical direction federal learning-based feature management method according to claim 2, wherein:
the feature management method based on medical direction federal learning further comprises the following steps:
inquiring and matching the corresponding international value according to the text field input by the user;
the international value and its corresponding standard field are added to a new feature template.
4. A method of feature management based on medical direction federal learning according to claim 3, wherein:
the feature management method based on medical direction federal learning further comprises the following steps:
and setting a comparison symbol for each retrieval item so as to determine the operation condition of the retrieved numerical relation.
5. The medical direction federal learning-based feature management method according to claim 4, wherein: the feature management method based on medical direction federal learning further comprises the following steps:
a preset threshold value is set for each retrieval entry to determine a threshold condition of the retrieved data relationship.
6. The medical direction federal learning-based feature management method according to claim 5, wherein: the feature management method based on medical direction federal learning further comprises the following steps:
a connection symbol is set for each of the search entries to determine a logical relationship between the search entries.
7. The medical direction federal learning-based feature management method according to claim 6, wherein: the feature management method based on medical direction federal learning further comprises the following steps:
generating a search formula and a search result aiming at the search formula according to all the search items;
the search results include a data source, a data amount, and a data value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110803319.8A CN113704555B (en) | 2021-07-16 | 2021-07-16 | Feature management method based on medical direction federal learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110803319.8A CN113704555B (en) | 2021-07-16 | 2021-07-16 | Feature management method based on medical direction federal learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113704555A CN113704555A (en) | 2021-11-26 |
| CN113704555B true CN113704555B (en) | 2023-11-07 |
Family
ID=78648739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110803319.8A Active CN113704555B (en) | 2021-07-16 | 2021-07-16 | Feature management method based on medical direction federal learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113704555B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108614885A (en) * | 2018-05-03 | 2018-10-02 | 杭州认识科技有限公司 | Knowledge mapping analysis method based on medical information and device |
| CN110797124A (en) * | 2019-10-30 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Model multi-terminal collaborative training method, medical risk prediction method and device |
| CN111079022A (en) * | 2019-12-20 | 2020-04-28 | 深圳前海微众银行股份有限公司 | Personalized recommendation method, device, equipment and medium based on federal learning |
| WO2020233256A1 (en) * | 2019-07-12 | 2020-11-26 | 之江实验室 | General medical termbase-based multi-center medical terminology standardization system |
| CN112233746A (en) * | 2020-11-05 | 2021-01-15 | 克拉玛依市中心医院 | Method for automatically standardizing medical data |
| CN112542223A (en) * | 2020-12-21 | 2021-03-23 | 西南科技大学 | Semi-supervised learning method for constructing medical knowledge graph from Chinese electronic medical record |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2020209737A1 (en) * | 2019-01-14 | 2021-07-29 | 5 Health Inc. | Methods and systems for managing medical information |
| US11514329B2 (en) * | 2019-03-27 | 2022-11-29 | General Electric Company | Data-driven deep learning model generalization analysis and improvement |
| US20210027889A1 (en) * | 2019-07-23 | 2021-01-28 | Hank.AI, Inc. | System and Methods for Predicting Identifiers Using Machine-Learned Techniques |
-
2021
- 2021-07-16 CN CN202110803319.8A patent/CN113704555B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108614885A (en) * | 2018-05-03 | 2018-10-02 | 杭州认识科技有限公司 | Knowledge mapping analysis method based on medical information and device |
| WO2020233256A1 (en) * | 2019-07-12 | 2020-11-26 | 之江实验室 | General medical termbase-based multi-center medical terminology standardization system |
| CN110797124A (en) * | 2019-10-30 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Model multi-terminal collaborative training method, medical risk prediction method and device |
| CN111079022A (en) * | 2019-12-20 | 2020-04-28 | 深圳前海微众银行股份有限公司 | Personalized recommendation method, device, equipment and medium based on federal learning |
| CN112233746A (en) * | 2020-11-05 | 2021-01-15 | 克拉玛依市中心医院 | Method for automatically standardizing medical data |
| CN112542223A (en) * | 2020-12-21 | 2021-03-23 | 西南科技大学 | Semi-supervised learning method for constructing medical knowledge graph from Chinese electronic medical record |
Non-Patent Citations (1)
| Title |
|---|
| 基于机器学习的北京市三甲医院疾病诊断名称规范化研究;李谊澄;侯锐志;邹宗毓;周子君;;医学与社会(08);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113704555A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111159330B (en) | Database query statement generation method and device | |
| CN103631596B (en) | Business object data typing and the configuration device and collocation method for updating rule | |
| CN109492077A (en) | The petrochemical field answering method and system of knowledge based map | |
| US20030217071A1 (en) | Data processing method and system, program for realizing the method, and computer readable storage medium storing the program | |
| CN105718585B (en) | Document and label word justice correlating method and its device | |
| CN107633060A (en) | A kind of information processing method and electronic equipment | |
| EP2131293A1 (en) | Method for mapping an X500 data model onto a relational database | |
| CN113190687A (en) | Knowledge graph determining method and device, computer equipment and storage medium | |
| CN112100402A (en) | Power grid knowledge graph construction method and device | |
| CN104346331A (en) | Retrieval method and system for XML database | |
| Afzal et al. | OWLMap: fully automatic mapping of ontology into relational database schema | |
| CN110956271B (en) | Multi-stage classification method and device for mass data | |
| CN113704555B (en) | Feature management method based on medical direction federal learning | |
| Pomp et al. | Eskape: Platform for enabling semantics in the continuously evolving internet of things | |
| CN112286916B (en) | Data processing method, device, equipment and storage medium | |
| CN105677745A (en) | General efficient self-service data search system and implementation method | |
| CN110716913B (en) | Mutual migration method of Kafka and Elasticissearch database data | |
| CN103810243A (en) | Innovative hotspot pre-warning recognition system and method | |
| CN115329753B (en) | Intelligent data analysis method and system based on natural language processing | |
| JPH10143539A (en) | Information retrieving method, its system, recording medium recording information resource dictionary data and recording medium recording information retrieving program | |
| CN109815297A (en) | A kind of tree access arithmetic system not depending on relational database | |
| CN109918436B (en) | Medical knowledge management and query system | |
| CN114612071A (en) | Data management method based on knowledge graph | |
| CN108073590A (en) | The management method and device of document database | |
| JP2002063165A (en) | Method and system and program for information retrieval, and recording medium having the same program recorded thereon |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |