CN115204413A - Intelligent learning data processing method based on artificial intelligence - Google Patents
Intelligent learning data processing method based on artificial intelligence Download PDFInfo
- Publication number
- CN115204413A CN115204413A CN202210848161.0A CN202210848161A CN115204413A CN 115204413 A CN115204413 A CN 115204413A CN 202210848161 A CN202210848161 A CN 202210848161A CN 115204413 A CN115204413 A CN 115204413A
- Authority
- CN
- China
- Prior art keywords
- data
- classification
- intelligent learning
- template
- repeated
- 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
Images
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
- G06F16/20—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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Bioethics (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent learning data processing method based on artificial intelligence, which relates to the technical field of AI intelligent data processing and solves the technical problem that algorithm data is not encrypted; the data cleaning unit is used for reprocessing the classified template data, replacing repeated data by adopting repeated marks, reducing the overall capacity of the whole template data, eliminating the corresponding repeated data and cleaning the template data so as to improve the cleaning effect of the whole template data; the encryption unit encrypts the algorithm data, divides the algorithm data into nine groups of data streams, carries out subscript identification processing on digital marks in the nine groups of data streams, and is convenient for integrating the nine groups of data streams in the later period.
Description
Technical Field
The invention belongs to the technical field of AI intelligent data processing, and particularly relates to an intelligent learning data processing method based on artificial intelligence.
Background
Artificial intelligence, abbreviated in english as AI, is a new technical science of studying and developing theories, methods, techniques and application systems for simulating, extending and expanding human intelligence.
When data processing is carried out based on artificial intelligence data, artificial intelligence needs a large amount of learning data to train, corresponding intelligent data generally needs to be stored in corresponding equipment terminals, and when the artificial intelligence equipment needs to carry out data updating and data retrieving, corresponding data can be directly extracted from the corresponding storage equipment terminals, so that the data updating or retrieving work of the artificial intelligence equipment is completed;
however, during the storage process of the artificial intelligence learning data, the following disadvantages still exist and need to be improved:
1. a large amount of private algorithm data are arranged in the artificial intelligence learning data, the algorithm data and the corresponding AI data are bound and stored in the corresponding storage terminal, and because the algorithm data are not encrypted, part of illegal persons can easily steal the corresponding algorithm data by invading the corresponding storage terminal;
2. the capacity of the artificial intelligent learning data is large, the internal repeated data is also large, and the capacity of the intelligent learning data which is stored is not reduced, so that the corresponding storage equipment wastes a large amount of storage space to store the repeated data.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art; therefore, the invention provides an intelligent learning data processing method based on artificial intelligence, which is used for solving the technical problem that algorithm data is not encrypted.
To achieve the above object, an embodiment according to a first aspect of the present invention provides an artificial intelligence based intelligent learning data processing method, including the following steps:
firstly, collecting intelligent learning data of artificial intelligence, generating an intelligent learning data packet from the collected data, and transmitting the intelligent learning data packet to a processing center;
step two, a data classification unit is arranged in the processing center, the data classification unit classifies the intelligent learning data packet, and classifies the intelligent learning data in the intelligent learning data packet into AI data and algorithm data, wherein the algorithm data is positioned in the AI data, and the classified data is transmitted to a classification storage unit for storage, so that the AI data is used as template data, the algorithm data is used as classification data, and corresponding classification marks are arranged at classification nodes;
thirdly, carrying out capacity reduction processing on the template data, extracting repeated data in the template data, and replacing the repeated data by adopting corresponding repeated marks;
and step four, encrypting the classified data to divide the classified data into nine groups of data streams, marking the nine groups of data streams by adopting corresponding digital marks, carrying out subscript identification processing on the digital marks, and memorizing the division nodes of the nine groups of data streams.
Preferably, the intelligent learning data processing method is executed by an intelligent data processing system, and the intelligent data processing system comprises a data acquisition terminal, a processing center and a merging and extracting terminal;
the processing center comprises a data cleaning unit, a data classification unit, a classification storage unit and an encryption unit;
the data acquisition terminal is used for acquiring intelligent learning data of artificial intelligence, the data classification unit is used for classifying the acquired intelligent learning data, the data cleaning unit is used for reducing the capacity of the template data, the encryption unit is used for encrypting the classified data, the classification storage unit is used for respectively storing and processing the template data and the classified data, and the merging and extracting terminal is used for merging the original intelligent learning data.
Preferably, in the second step, the step of classifying the intelligent learning data packet by the data classification unit is as follows:
AI data in the intelligent learning data is taken as template data, algorithm data is taken as classification data, and the classification data adopts a mark FL i Labeling, wherein i represents different algorithm data;
extracting corresponding classification data from the template data and adopting a classification mark FL i Make a substitution and mark the class FL i And binding the classification data with the corresponding classification data, generating a classification data matching table, and transmitting the classification data and the classification data matching table to a classification storage unit for storage.
Preferably, in the third step, the step of performing capacity reduction processing on the template data includes:
extracting multiple groups of intelligent learning data from the cloud of the big data, analyzing the multiple groups of intelligent learning data to obtain a large amount of repeated data, and transmitting the repeated data to a repeated data template library for storage;
using repetition mark CF k Tagging different duplicate data, wherein k represents different duplicate data and k =1, 2, … …, n, and tagging the duplicates CF k Binding the duplicate data to generate a duplicate data matching table, and storing the duplicate data matching table;
identifying the same kind of data in the template data through the repeated data included in the repeated data matching table, and marking CF through repeated k Substitution of homogeneous data by repeatedly marking CF k The whole capacity of the whole template data is reduced by replacing the same kind of data;
and replacing the same type data in the template data by adopting the repeated marks, so that the whole capacity in the template data is reduced.
Preferably, in the fourth step, the step of encrypting the classified data includes:
each group of classified data is algorithm data, and each group of stored algorithm data is bound into a corresponding storage terminal, wherein each group of algorithm data corresponds to each storage terminal;
randomly dividing the algorithm data stored in the storage terminal, randomly dividing the algorithm data into nine groups of data streams, sequentially marking the nine groups of data streams by adopting corresponding numerical labels H, wherein H =1, 2, … … and 9, when H is 1, the data stream with the numerical label H being 1 is represented as a first group of data stream, when H is 2, the data stream with the numerical label H being 2 is represented as a second group of data stream, … …, and when H is 9, the data stream with the numerical label H being 9 is represented as a last group of data stream;
carrying out subscript processing on the numerical labels H carried by the nine data streams in sequence, wherein the numerical labels H of the original data streams arranged in sequence are as follows: 1. 2, … …, 9, subscript processed number H is expressed as: 1 2 、 1 2 3 、 2 3 3 、 3 4 5 、……、 8 For example, with the numerical designation H of 4, the expression that H is 4 after subscript labeling is: 3 4 5 the front subscript mark 3 represents that the data stream at the front end of the data stream with the digital mark 4 is provided with the digital mark 3, and the rear subscript mark 5 represents that the data stream at the rear end of the data stream with the digital mark 4 is provided with the digital mark 5;
data streams with different labels H are arranged in a disorganized mode to form three groups of sequencing data streams, the data streams with labels 2, 7 and 6 are used as a first group of data streams, the data streams with labels 9, 5 and 1 are used as a second group of data streams, the data streams with labels 4, 3 and 8 are used as a third group of data streams, and the data streams are stored in corresponding storage terminals according to the disorganized mode.
Preferably, the merging extraction terminal merges the classified intelligent learning data according to the digital label, the repetitive label and the classification label, wherein the specific merging step is as follows:
extracting corresponding template data according to actual requirements, and after the template data is extracted, according to the repeated mark CF k And the repeated data matching table is used for completing the same type of data in the template data, and the corresponding repeated data is used for covering the corresponding repeated mark CF k ；
According to the subscript mark of the digital mark H, data streams with different subscript marks are sequentially arranged, so that the corresponding data streams are integrated into complete algorithm data, and the algorithm data is classified data;
then according to the corresponding classification mark FL i And a classification data matching table for sequentially extracting corresponding classification data and marking by classification i The corresponding classification data are sequentially filled into the template data to obtain corresponding intelligent learning data.
Compared with the prior art, the invention has the beneficial effects that: the method comprises the steps that artificial intelligent learning data are collected, an intelligent learning data packet is transmitted into a processing center, a data classification unit in the processing center classifies the corresponding intelligent learning data into AI data and algorithm data, corresponding node marks are arranged at corresponding classification nodes, a data cleaning unit processes the classified template data again, repeated marks are adopted to replace the repeated data, the whole capacity of the whole template data is reduced, the corresponding repeated data are removed, and the template data are cleaned, so that the cleaning effect of the whole template data is improved;
the encryption unit encrypts the algorithm data, divides the algorithm data into nine groups of data streams, carries out subscript identification processing on digital marks in the nine groups of data streams, and is convenient for integrating the nine groups of data streams in the later period.
Drawings
FIG. 1 is a schematic flow chart of a method according to the principles of the present invention;
fig. 2 is a schematic diagram of the principle of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood 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 and fig. 2, the present application provides an intelligent learning data processing method based on artificial intelligence, which includes the following steps:
firstly, collecting intelligent learning data of artificial intelligence, generating an intelligent learning data packet from the collected data, and transmitting the intelligent learning data packet to a processing center;
step two, a data classification unit is arranged in the processing center, the data classification unit classifies the intelligent learning data packet, and classifies the intelligent learning data in the intelligent learning data packet into AI data and algorithm data, wherein the algorithm data is positioned in the AI data, and the classified data is transmitted to a classification storage unit for storage, so that the AI data is used as template data, the algorithm data is used as classification data, and corresponding classification marks are arranged at classification nodes;
thirdly, carrying out capacity reduction processing on the template data, extracting repeated data in the template data, and replacing the repeated data by adopting corresponding repeated marks;
and step four, encrypting the classified data to divide the classified data into nine groups of data streams, marking the nine groups of data streams by adopting corresponding digital marks, carrying out subscript identification processing on the digital marks, and memorizing the division nodes of the nine groups of data streams.
The intelligent learning data processing method is executed by a data processing system, and the data processing system comprises a data acquisition terminal, a processing center and a merging and extracting terminal;
the output end of the data acquisition terminal is electrically connected with the input end of the processing center, and the output end of the processing center is electrically connected with the input end of the merging extraction terminal;
the processing center comprises a data cleaning unit, a data classification unit, a classification storage unit and an encryption unit;
the data cleaning unit is connected with the classified storage unit in a bidirectional mode, the data classification unit is connected with the classified storage unit in a bidirectional mode, and the encryption unit is connected with the classified storage unit in a bidirectional mode;
the data acquisition terminal is used for acquiring intelligent learning data of artificial intelligence, generating an intelligent learning data packet from the acquired data and transmitting the intelligent learning data packet to the processing center;
the data classification unit inside the processing center classifies the corresponding intelligent learning data packet into AI data and algorithm data, wherein the algorithm data are located in the AI data, and transmits the classified data to the classification storage unit for storage, and corresponding classification marks are set at classification nodes, and the specific classification processing steps are as follows:
taking AI data inside the intelligent learning data as template data, taking algorithm data as classification data, and adopting a mark FL for the classification data i Marking, wherein i represents different algorithm data;
extracting corresponding classification data from the template data and adopting a classification mark FL i Make a substitution and mark the classification FL i Binding with corresponding classification data, generating a classification data matching table, and transmitting the classification data and the classification data matching table to a classification storage unit for storage (specifically, assuming that a set of template data is {1, 2, 3, 4, 5, 6, 7, 8, 4, 9}, where 3, 5, and 7 are algorithm data, the classification data is classified data, and a label FL is used 1 Replacing classification data 3 with classification labels FL 2 Replacing classification data 5 with classification labels FL 3 Replacing the classification data 7, wherein the classification data 3, 5 and 7 may be a large string of algorithm data, the whole template data after extracting the corresponding classification data from the template data is expressed in {1, 2, FL } 1 、4、FL 2 、6、FL 3 8, 4, 9, template data {1, 2, FL } 1 、4、FL 2 、6、FL 3 8, 4, 9}, the classification data and the classification data matching table are respectively stored in the classification storage unit);
the data cleaning unit is used for reprocessing the divided template data, reducing the whole capacity of the whole template data, eliminating the corresponding repeated data and cleaning the template data, so that the cleaning effect of the whole template data is improved, wherein the reprocessing step is as follows:
extracting multiple groups of intelligent learning data from the cloud of the big data, analyzing the multiple groups of intelligent learning data to obtain a large amount of repeated data, and transmitting the repeated data to a repeated data template library for storage;
using repetition mark CF k Tagging different duplicates, where k represents different duplicates and k =1, 2, … …, n, and tagging the duplicates with CF k Binding the duplicate data to generate a duplicate data matching table, and storing the duplicate data matching table;
identifying the same kind of data in the template data through the repeated data included in the repeated data matching table, and marking CF through repeated k Substitution of homogeneous data by repeatedly marking CF k The whole capacity of the whole template data is reduced by replacing the homogeneous data, so that the storage space in the classification storage unit is reasonably utilized (specifically, the classified mark FL is used i The processed template data is taken as an example, and the initial expression form is {1, 2, FL 1 、4、FL 2 、6、FL 3 8, 4, 9, assume 4 is homogeneous data, assume repetition marker CF 1 Match 4, marked by repetition CF k The expression form of the template data after replacement is {1, 2, FL 1 、CF 1 、FL 2 、6、FL 3 、8、CF 1 9, transmitting the processed template data to a classification storage unit for storage);
and the same type of data in the template data is replaced by adopting the repeated marks, so that the whole capacity in the template data is fully reduced.
The encryption unit encrypts algorithm data, wherein the algorithm data is classified data, and the specific encryption processing steps are as follows:
binding each set of stored algorithm data into a corresponding storage terminal, wherein each set of algorithm data corresponds to each storage terminal;
randomly dividing the algorithm data stored in the storage terminal, randomly dividing the algorithm data into nine groups of data streams, sequentially marking the nine groups of data streams by adopting corresponding numerical labels H, wherein H =1, 2, … … and 9, when H is 1, the data stream with the numerical label H being 1 is represented as a first group of data stream, when H is 2, the data stream with the numerical label H being 2 is represented as a second group of data stream, … …, and when H is 9, the data stream with the numerical label H being 9 is represented as a last group of data stream;
carrying out subscript processing on the numerical labels H carried by the nine data streams in sequence, wherein the numerical labels H of the original data streams arranged in sequence are as follows: 1. 2, … …, 9, the numerical designation H after subscript processing is expressed as: 1 2 、 1 2 3 、 2 3 3 、 3 4 5 、……、 8 9, taking the numerical designation H as 4 for example, the expression that H is 4 after subscript labeling is: 3 4 5 the front subscript mark 3 represents that the data stream at the front end of the data stream with the digital mark 4 is provided with the digital mark 3, and the rear subscript mark 5 represents that the data stream at the rear end of the data stream with the digital mark 4 is provided with the digital mark 5;
data streams with different labels H are arranged in a disorganized mode to form three groups of sequencing data streams, the data streams with labels 2, 7 and 6 are used as a first group of data streams, the data streams with labels 9, 5 and 1 are used as a second group of data streams, the data streams with labels 4, 3 and 8 are used as a third group of data streams, and the data streams are stored in corresponding storage terminals according to the disorganized mode.
The merging extraction terminal merges the classified intelligent learning data according to the digital marks, the repeated marks and the classification marks and outputs the integrated intelligent learning data after merging, wherein the concrete merging step is as follows:
extracting corresponding template data according to actual requirements, and after the template data is extracted, according to the repeated mark CF k And duplicate data matchingThe table is used for completing homogeneous data in the template data, and corresponding repeated data is used for covering corresponding repeated marks CF k ；
According to the subscript mark of the digital mark H, data streams with different subscript marks are sequentially arranged, so that the corresponding data streams are integrated into complete algorithm data, and the algorithm data is classified data;
then according to the corresponding classification mark FL i And a classification data matching table for sequentially extracting corresponding classification data via classification label FL i The corresponding classification data are sequentially filled into the template data to obtain corresponding intelligent learning data.
Part of data in the formula is obtained by removing dimension and taking the value to calculate, and the formula is obtained by simulating a large amount of collected data through software and is closest to a real situation; the preset parameters and the preset threshold values in the formula are set by those skilled in the art according to actual conditions or obtained through simulation of a large amount of data.
The working principle of the invention is as follows: the data acquisition terminal is used for acquiring artificial intelligent learning data and transmitting an intelligent learning data packet into the processing center, the data classification unit in the processing center classifies the corresponding intelligent learning data into AI data and algorithm data, corresponding node marks are arranged at corresponding classification nodes, and the data cleaning unit is used for reprocessing the classified template data, reducing the whole capacity of the whole template data, eliminating corresponding repeated data and cleaning the template data so as to improve the cleaning effect of the whole template data;
the encryption unit encrypts the algorithm data, divides the algorithm data into nine groups of data streams, carries out subscript identification processing on digital marks in the nine groups of data streams, and is convenient for integrating the nine groups of data streams in the later period.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (6)
1. The intelligent learning data processing method based on artificial intelligence is characterized by comprising the following steps:
firstly, collecting intelligent learning data of artificial intelligence, generating an intelligent learning data packet from the collected data, and transmitting the intelligent learning data packet to a processing center;
step two, a data classification unit is arranged in the processing center, classifies the intelligent learning data packet, classifies the intelligent learning data in the intelligent learning data packet into AI data and algorithm data, wherein the algorithm data is positioned in the AI data, and transmits the classified data to a classification storage unit for storage, so that the AI data is used as template data, the algorithm data is used as classification data, and corresponding classification marks are arranged at classification nodes;
thirdly, carrying out capacity reduction processing on the template data, extracting repeated data in the template data, and replacing the repeated data by adopting corresponding repeated marks;
and step four, encrypting the classified data to divide the classified data into nine groups of data streams, marking the nine groups of data streams by adopting corresponding digital marks, carrying out subscript identification processing on the digital marks, and memorizing the division nodes of the nine groups of data streams.
2. An intelligent learning data processing method based on artificial intelligence as claimed in claim 1, wherein the intelligent learning data processing method is executed by an intelligent data processing system, and the intelligent data processing system comprises a data acquisition terminal, a processing center and a merging extraction terminal;
the processing center comprises a data cleaning unit, a data classification unit, a classification storage unit and an encryption unit;
the data acquisition terminal is used for acquiring intelligent learning data of artificial intelligence, the data classification unit is used for classifying the acquired intelligent learning data, the data cleaning unit is used for reducing the capacity of the template data, the encryption unit is used for encrypting the classified data, the classification storage unit is used for respectively storing and processing the template data and the classified data, and the merging and extracting terminal is used for merging the original intelligent learning data.
3. The intelligent learning data processing method based on artificial intelligence of claim 2, wherein in the second step, the step of classifying the intelligent learning data packet by the data classification unit comprises:
AI data in the intelligent learning data is taken as template data, algorithm data is taken as classification data, and the classification data adopts a mark FL i Marking, wherein i represents different algorithm data;
extracting corresponding classification data from the template data and adopting a classification label FL i Make a substitution and mark the classification FL i And binding the classification data with the corresponding classification data, generating a classification data matching table, and transmitting the classification data and the classification data matching table to a classification storage unit for storage.
4. An artificial intelligence based intelligent learning data processing method according to claim 3, wherein in the third step, the step of performing capacity reduction processing on the template data is:
extracting multiple groups of intelligent learning data from the cloud of the big data, analyzing the multiple groups of intelligent learning data to obtain a large amount of repeated data, and transmitting the repeated data to a repeated data template library for storage;
using repetition mark CF k Tagging different duplicate data, wherein k represents different duplicate data and k =1, 2, … …, n, and tagging the duplicates CF k Binding the duplicate data to generate a duplicate data matching table, and storing the duplicate data matching tableStoring;
identifying the same kind of data in the template data through the repeated data included in the repeated data matching table, and marking CF through repeated k Substitution of homogeneous data by repeatedly marking CF k The whole capacity of the whole template data is reduced by replacing the same kind of data;
and replacing the same type data in the template data by adopting the repeated marks, so that the whole capacity in the template data is reduced.
5. The artificial intelligence based intelligent learning data processing method of claim 4, wherein in the fourth step, the step of encrypting the classified data comprises:
each group of classified data is algorithm data, and each group of stored algorithm data is bound into a corresponding storage terminal, wherein each group of algorithm data corresponds to each storage terminal;
randomly dividing the algorithm data stored in the storage terminal, randomly dividing the algorithm data into nine groups of data streams, sequentially marking the nine groups of data streams by adopting corresponding numerical labels H, wherein H =1, 2, … … and 9, when H is 1, the data stream with the numerical label H being 1 is represented as a first group of data stream, when H is 2, the data stream with the numerical label H being 2 is represented as a second group of data stream, … …, and when H is 9, the data stream with the numerical label H being 9 is represented as a last group of data stream;
carrying out subscript processing on the numerical labels H carried by the nine data streams in sequence, wherein the numerical labels H of the original data streams arranged in sequence are as follows: 1. 2, … …, 9, subscript processed number H is expressed as: 1 2 、 1 2 3 、 2 3 3 、 3 4 5 、……、 8 9, taking the numerical designation H as 4 for example, the expression that H is 4 after subscript labeling is: 3 4 5 the front subscript mark 3 represents the data stream with the number label 3 at the front end of the data stream with the number label 4, and the back subscript mark 5 represents the data stream with the number label 4 at the back end of the data streamThe stream carries a numerical label 5;
data streams with different labels H are arranged in a disorganized mode to form three groups of sequencing data streams, the data streams with labels 2, 7 and 6 are used as a first group of data streams, the data streams with labels 9, 5 and 1 are used as a second group of data streams, the data streams with labels 4, 3 and 8 are used as a third group of data streams, and the data streams are stored in corresponding storage terminals according to the disorganized mode.
6. An artificial intelligence based intelligent learning data processing method according to claim 5, wherein the merging extraction terminal merges the classified intelligent learning data according to the digital label, the repetitive label and the classification label, wherein the specific merging step is:
extracting corresponding template data according to actual requirements, and after the template data is extracted, according to the repeated mark CF k And the repeated data matching table is used for completing the same type of data in the template data, and the corresponding repeated data is used for covering the corresponding repeated mark CF k ；
According to the subscript mark of the digital mark H, data streams with different subscript marks are sequentially arranged, so that the corresponding data streams are integrated into complete algorithm data, and the algorithm data is classified data;
then according to the corresponding classification mark FL i And a classification data matching table for sequentially extracting corresponding classification data via classification label FL i The corresponding classification data are sequentially filled into the template data to obtain corresponding intelligent learning data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210848161.0A CN115204413A (en) | 2022-07-19 | 2022-07-19 | Intelligent learning data processing method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210848161.0A CN115204413A (en) | 2022-07-19 | 2022-07-19 | Intelligent learning data processing method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115204413A true CN115204413A (en) | 2022-10-18 |
Family
ID=83581968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210848161.0A Pending CN115204413A (en) | 2022-07-19 | 2022-07-19 | Intelligent learning data processing method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115204413A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116127483A (en) * | 2022-12-15 | 2023-05-16 | 中山市大成动漫科技有限公司 | Image material self-storage system for cartoon making |
| CN116527382A (en) * | 2023-05-26 | 2023-08-01 | 广西华利康科技有限公司 | Cloud computing-based data security transmission system |
| CN117176331A (en) * | 2023-11-03 | 2023-12-05 | 江苏高昕建筑系统有限公司 | Electric digital data processing device and processing method thereof |
-
2022
- 2022-07-19 CN CN202210848161.0A patent/CN115204413A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116127483A (en) * | 2022-12-15 | 2023-05-16 | 中山市大成动漫科技有限公司 | Image material self-storage system for cartoon making |
| CN116127483B (en) * | 2022-12-15 | 2024-02-27 | 中山市大成互娱游乐有限公司 | Image material self-storage system for cartoon making |
| CN116527382A (en) * | 2023-05-26 | 2023-08-01 | 广西华利康科技有限公司 | Cloud computing-based data security transmission system |
| CN116527382B (en) * | 2023-05-26 | 2024-02-20 | 安徽科大国创慧联运科技有限公司 | Cloud computing-based data security transmission system |
| CN117176331A (en) * | 2023-11-03 | 2023-12-05 | 江苏高昕建筑系统有限公司 | Electric digital data processing device and processing method thereof |
| CN117176331B (en) * | 2023-11-03 | 2024-02-02 | 江苏高昕建筑系统有限公司 | Electric digital data processing device and processing method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115204413A (en) | Intelligent learning data processing method based on artificial intelligence | |
| US9197244B2 (en) | Multi-layer system for symbol-space based compression of patterns | |
| CN109218223B (en) | Robust network traffic classification method and system based on active learning | |
| CN103390165B (en) | A kind of method and device of picture cluster | |
| CN106228398A (en) | Specific user's digging system based on C4.5 decision Tree algorithms and method thereof | |
| CN111144470A (en) | Unknown network flow identification method and system based on deep self-encoder | |
| CN105574544A (en) | Data processing method and device | |
| CN115174255B (en) | Industrial Internet platform data transmission safety protection system | |
| CN113890821B (en) | Log association method and device and electronic equipment | |
| CN114943089B (en) | Information security protection system for enterprise operation online data sharing | |
| CN107003992A (en) | Perception associative memory for neural language performance identifying system | |
| CN106055452A (en) | Method and apparatus for creating switch log template | |
| Wang et al. | Large-scale multimedia data mining using MapReduce framework | |
| CN107241305A (en) | A kind of network protocol analysis system and its analysis method based on polycaryon processor | |
| CN105117740A (en) | Font identification method and device | |
| CN103942274B (en) | A kind of labeling system and method for the biologic medical image based on LDA | |
| CN107330009A (en) | Descriptor disaggregated model creation method, creating device and storage medium | |
| CN106777336A (en) | A kind of exabyte composition extraction system and method based on deep learning | |
| CN107977592A (en) | A kind of image text detection method and system, user terminal and server | |
| CN107992528A (en) | Utilize more relation question answering systems of interpretable inference network | |
| CN106844412A (en) | A kind of human face data collection method and device | |
| CN109635089B (en) | Literature work novelty evaluation system and method based on semantic network | |
| CN113312924A (en) | Risk rule classification method and device based on NLP high-precision analysis label | |
| CN110209656B (en) | Data processing method and device | |
| CN111221967A (en) | Language data classification storage system based on block chain architecture |
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 |