CN111507010A - AI artificial intelligence detects data model of halitosis - Google Patents
AI artificial intelligence detects data model of halitosis Download PDFInfo
- Publication number
- CN111507010A CN111507010A CN202010328720.6A CN202010328720A CN111507010A CN 111507010 A CN111507010 A CN 111507010A CN 202010328720 A CN202010328720 A CN 202010328720A CN 111507010 A CN111507010 A CN 111507010A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- training
- output end
- model
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 16
- 238000013499 data model Methods 0.000 title claims abstract description 13
- 206010006326 Breath odour Diseases 0.000 title description 2
- 208000032139 Halitosis Diseases 0.000 title description 2
- 238000012549 training Methods 0.000 claims abstract description 53
- 238000012360 testing method Methods 0.000 claims abstract description 47
- 238000002360 preparation method Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 239000000284 extract Substances 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 9
- 230000008569 process Effects 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000012217 deletion Methods 0.000 abstract description 2
- 230000037430 deletion Effects 0.000 abstract description 2
- 230000009471 action Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 210000000214 mouth Anatomy 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Abstract
The invention discloses a data model for AI artificial intelligence detection of breath, which comprises a historical database, wherein the output end of the historical database is connected with a data preparation module, the output end of the data preparation module is connected with a data preprocessing module, the output end of the data preprocessing module is connected with a configuration model, the output end of the configuration model is connected with a training module, and the output end of the training module is connected with an evaluation optimization module. The AI artificial intelligence detection breath data model processes and analyzes data extracted from the data preparation module, and comprises deletion of error data, interpolation processing of missing data, coding of interpolation processing data and other related data calculation; the training module evaluates the difference between the training output and the test output according to two key indexes of the training result and the training speed, compares the difference values generated by the training output and the test output, outputs a comparison value, reduces errors through one-time iteration and comparison after the evaluation optimization module finishes training, and improves the accuracy of the model.
Description
Technical Field
The invention relates to the technical field of breath detection, in particular to a data model for AI artificial intelligence breath detection.
Background
In the prior art, the current smart phone and the smart wearable device become the necessary tools for people to communicate, entertain and detect by various sensors, thereby greatly facilitating our lives and extending our body functions. The current MEMS sensor gradually gets up along with wearing equipment, can make preceding analog circuit or the device of function singleness possess more functions. Especially, the microphone is integrated with a digital low-power-consumption awakening mechanism at present, can be started all weather, performs voiceprint recognition and detects specific sentences all the time, performs related instructions, and greatly improves the intelligence and application scenes of the equipment. However, people often use a microphone to make a call, which is a common voice input inlet and is the most time period for contacting with the breath of the human body. However, the current devices for detecting human breath are stand-alone devices, and thus, a general user does not separately purchase such devices.
Disclosure of Invention
The invention aims to provide a data model for AI artificial intelligence detection of breath, which has the advantages of reducing errors and improving the accuracy of the model by one-time iteration and comparison in the modes of a data preparation module, a data preprocessing module, a configuration model, a training module and an evaluation optimization module, and solves the problems in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme: a data model for AI artificial intelligence detection of breath comprises a historical database, wherein the output end of the historical database is connected with a data preparation module, the output end of the data preparation module is connected with a data preprocessing module, the output end of the data preprocessing module is connected with a configuration model, the output end of the configuration model is connected with a training module, and the output end of the training module is connected with an evaluation optimization module;
the historical database is established under the experience summarized by the past data by training an AI artificial intelligence by using a machine learning algorithm under a large amount of historical data, and all the past data are stored and recorded in the database;
the data preparation module finds a certain rule from the historical database, predicts the future and extracts features from the historical database;
the data preprocessing module predicts the characteristics of breath, extracts the characteristics from the breath data, searches corresponding weights, calculates a probability according to the weights of the characteristics, collects data samples, makes labels, and performs data equalization and binarization processing;
the configuration model is used for processing breath data and determining to use a network model and a structure for training;
the training module evaluates the difference between the training output and the test output according to two key indexes of the training result and the training speed, compares the difference values generated by the training output and the test output, and outputs a comparison value;
after the training of the evaluation optimization module is finished, the test set in the breath data division is used, the error is reduced through one-time iteration and comparison, and the accuracy of the model is improved.
Preferably, the training module comprises a data testing module, a layered testing module and a testing comparison module, and the output end of the layered testing module of the data testing module is connected with the testing comparison module.
Preferably, the hierarchical testing module introduces the historical database into the system, cleans and splits the data, and places the extracted samples into different established models for testing.
Compared with the prior art, the invention has the following beneficial effects:
according to the data model for AI artificial intelligence detection of the breath, the characteristics extracted from a historical database and relevant statistical analysis are performed, a method for respectively predicting indexes of the affected breath indexes is determined according to the analysis result, and then the indexes are calculated according to the relevant theory and the data indexes of various breath obtained through prediction; processing and analyzing the data extracted from the data preparation module, including deleting error data, interpolating missing data, encoding interpolated data and other related data calculation; the training module evaluates the difference between the training output and the test output according to two key indexes of the training result and the training speed, compares the difference values generated by the training output and the test output, outputs a comparison value, divides a test set by using breath data after the training of the evaluation optimization module is finished, reduces errors through one-time iteration and comparison, and improves the accuracy of the model.
Drawings
FIG. 1 is an overall block diagram of the present invention.
In the figure: 1. a history database; 2. a data preparation module; 3. a data preprocessing module; 4. configuring a model; 5. a training module; 51. a data testing module; 52. a layered test module; 53. a test comparison module; 6. and evaluating an optimization module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a data model for AI artificial intelligence detection of breath includes a historical database 1, an output end of the historical database 1 is connected to a data preparation module 2, an output end of the data preparation module 2 is connected to a data preprocessing module 3, an output end of the data preprocessing module 3 is connected to a configuration model 4, an output end of the configuration model 4 is connected to a training module 5, and an output end of the training module 5 is connected to an evaluation optimization module 6.
The historical database 1 is built under the experience summarized by the past data by training AI artificial intelligence by using a machine learning algorithm under a large amount of historical data, and all the past data are stored and recorded in the database.
The data preparation module 2 finds a certain rule from the historical database 1 and predicts future, extracts features from the historical database 1, performs related statistical analysis, determines a method for respectively predicting indexes of the influence breath index according to an analysis result, and then calculates indexes according to various predicted breath data indexes according to a related theory.
The data preprocessing module 3 predicts the characteristics of a breath, extracts the characteristics from the breath data, searches corresponding weights, calculates a probability according to the weights of the characteristics, collects data samples, prepares labels, performs data equalization and binarization processing, processes and analyzes the data extracted in the data preparation module 2, and calculates related data including deletion of error data, interpolation processing of missing data, encoding of interpolation processing data and the like.
The use and processing of breath data by the configuration model 4 determines the use of network models and structures for training.
The training module 5 evaluates the difference between training output and test output, compares the difference values generated by the training output and the test output, and outputs a comparison value, the training module 5 comprises a data testing module 51, a layering testing module 52 and a test comparison module 53, the output end of the layering testing module 52 of the data testing module 51 is connected with the test comparison module 53, the layering testing module 52 introduces the historical database 1 into the system, cleans and splits the data, and places the extracted samples into different established models for testing.
After the training of the evaluation optimization module 6 is finished, the test set in the breath data division is used, the error is reduced through one-time iteration and comparison, and the accuracy of the model is improved.
The oral odor data of 400 patients are selected as input, the 400 data are randomly typed by taking 20 × 20 as data segments, and then the ratio of the number of the data to the number of the data segments is calculated according to the following steps of 3: and 7, dividing training data and test data according to the proportion, inputting the disordered breath data into the model, and continuously debugging the model data to complete model establishment after the model result is completed.
In summary, the following steps: according to the data model for AI artificial intelligence detection of the oral cavity, characteristics extracted from a historical database 1 and relevant statistical analysis are performed, a method for respectively predicting indexes of the affected oral cavity indexes is determined according to an analysis result, and then the indexes are calculated according to the data indexes of various oral cavity gases obtained by prediction according to a relevant theory; processing and analyzing the data extracted from the data preparation module 2, including deleting error data, interpolating missing data, encoding interpolated data and other related data calculation; the training module 5 evaluates the difference between the training output and the test output according to two key indexes of the training result and the training speed, compares the difference values generated by the training output and the test output, outputs a comparison value, and reduces errors by using a test set in the breath data division through one-time iteration and comparison after the training of the evaluation optimization module 6 is finished, thereby improving the accuracy of the model.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (3)
1. A data model for AI artificial intelligence detection of breath, comprising a history database (1), characterized in that: the output end of the historical database (1) is connected with the data preparation module (2), the output end of the data preparation module (2) is connected with the data preprocessing module (3), the output end of the data preprocessing module (3) is connected with the configuration model (4), the output end of the configuration model (4) is connected with the training module (5), and the output end of the training module (5) is connected with the evaluation optimization module (6);
the history database (1) is trained under the condition that AI artificial intelligence uses a machine learning algorithm to train under a large amount of history data, is established under the experience summarized by the past data, and stores and records all the past data in the database;
the data preparation module (2) finds a certain rule from the historical database (1), predicts a future prediction line and extracts features from the historical database (1);
the data preprocessing module (3) predicts the characteristics of breath, extracts the characteristics from the breath data, searches corresponding weights, calculates a probability according to the weights of the characteristics, collects data samples, makes labels, and performs data equalization and binarization processing;
the configuration model (4) is used for processing breath data and deciding to use a network model and a structure for training;
the training module (5) evaluates the difference between the training output and the test output according to two key indexes of the training result and the training speed, compares the difference values generated by the training output and the test output, and outputs a comparison value;
after the training of the evaluation optimization module (6) is finished, the test set in the breath data division is used, the error is reduced through one-time iteration and comparison, and the accuracy of the model is improved.
2. The AI artificial intelligence test breath data model according to claim 1, wherein the training module (5) comprises a data testing module (51), a layered testing module (52) and a test comparison module (53), and the output end of the layered testing module (52) of the data testing module (51) is connected with the test comparison module (53).
3. The AI artificial intelligence test breath data model according to claim 1, wherein the layered test module (52) introduces the historical database (1) into the system, cleans and splits the data, and places the extracted samples into different established models for testing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010328720.6A CN111507010A (en) | 2020-04-23 | 2020-04-23 | AI artificial intelligence detects data model of halitosis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010328720.6A CN111507010A (en) | 2020-04-23 | 2020-04-23 | AI artificial intelligence detects data model of halitosis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111507010A true CN111507010A (en) | 2020-08-07 |
Family
ID=71869709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010328720.6A Pending CN111507010A (en) | 2020-04-23 | 2020-04-23 | AI artificial intelligence detects data model of halitosis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507010A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105125215A (en) * | 2015-10-08 | 2015-12-09 | 湖南明康中锦医疗科技发展有限公司 | Neural network based breathing machine state analytic method and device |
| CN107463766A (en) * | 2017-06-23 | 2017-12-12 | 深圳市中识创新科技有限公司 | Generation method, device and the computer-readable recording medium of blood glucose prediction model |
| CN108474841A (en) * | 2015-04-20 | 2018-08-31 | 瑞思迈传感器技术有限公司 | Detection and identification by characteristic signal to the mankind |
| CN110301890A (en) * | 2019-05-31 | 2019-10-08 | 华为技术有限公司 | The method and device of apnea monitoring |
-
2020
- 2020-04-23 CN CN202010328720.6A patent/CN111507010A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108474841A (en) * | 2015-04-20 | 2018-08-31 | 瑞思迈传感器技术有限公司 | Detection and identification by characteristic signal to the mankind |
| CN105125215A (en) * | 2015-10-08 | 2015-12-09 | 湖南明康中锦医疗科技发展有限公司 | Neural network based breathing machine state analytic method and device |
| CN107463766A (en) * | 2017-06-23 | 2017-12-12 | 深圳市中识创新科技有限公司 | Generation method, device and the computer-readable recording medium of blood glucose prediction model |
| CN110301890A (en) * | 2019-05-31 | 2019-10-08 | 华为技术有限公司 | The method and device of apnea monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111951824A (en) | Detection method for distinguishing depression based on sound | |
| CN112043252B (en) | Emotion recognition system and method based on respiratory component in pulse signal | |
| KR20110013390A (en) | Signal judgment method, signal judgment apparatus, program, and signal judgment system | |
| CN112820279B (en) | Parkinson detection model construction method based on voice context dynamic characteristics | |
| CN109767836A (en) | A kind of medical diagnosis artificial intelligence system, device and its self-teaching method | |
| CN110659677A (en) | Human body falling detection method based on movable sensor combination equipment | |
| CN116821809B (en) | Vital sign data acquisition system based on artificial intelligence | |
| CN111899759A (en) | Method, device, equipment and medium for pre-training and model training of audio data | |
| CN112836105B (en) | Large-scale student aerobic capacity clustering method based on movement physiological characterization fusion | |
| CN115827888A (en) | Fault prediction method for complex equipment | |
| CN113674767A (en) | Depression state identification method based on multi-modal fusion | |
| CN116415723A (en) | Wind speed prediction method and device for railway disaster prevention system | |
| CN109271889B (en) | Action recognition method based on double-layer LSTM neural network | |
| KR102205806B1 (en) | Method for generation of respiratory state classifier and for respiratory state decision using generated respiratory state classifier | |
| CN116580706B (en) | Speech recognition method based on artificial intelligence | |
| CN111507010A (en) | AI artificial intelligence detects data model of halitosis | |
| CN115376638A (en) | Physiological characteristic data analysis method based on multi-source health perception data fusion | |
| CN114038562A (en) | Psychological development assessment method, device and system and electronic equipment | |
| CN113780356A (en) | Water quality prediction method and system based on ensemble learning model | |
| CN113571050A (en) | Voice depression state identification method based on Attention and Bi-LSTM | |
| CN112712855A (en) | Joint training-based clustering method for gene microarray containing deletion value | |
| Poh et al. | Anomaly detection for home activity based on sequence pattern | |
| Aluru et al. | Parkinson’s Disease Detection Using Machine Learning Techniques | |
| CN114420300B (en) | Chinese senile cognitive impairment prediction model | |
| CN115496113B (en) | Emotional behavior analysis method based on intelligent algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200807 |